Diff of /Sprout/ERDB.pm

-revision 1.27, Tue Oct 18 06:52:35 2005 UTC
+revision 1.71, Sat Oct 14 18:08:12 2006 UTC
 Line 9
      use DBObject;
      use Stats;
      use Time::HiRes qw(gettimeofday);
+     use Digest::MD5 qw(md5_base64);
      use FIG;
  =head1 Entity-Relationship Database Package
-Line 90
+Line 91
 -bit signed integer
+ =item counter
+-bit unsigned integer
  =item date
 -bit unsigned integer, representing a PERL date/time value
-Line 109
+Line 114
  compatability with certain database packages), but the only values supported are
 and 1.
+ =item id-string
+ variable-length string, maximum 25 characters
  =item key-string
  variable-length string, maximum 40 characters
-Line 125
+Line 134
  variable-length string, maximum 255 characters
+ =item hash-string
+ variable-length string, maximum 22 characters
  =back
+ The hash-string data type has a special meaning. The actual key passed into the loader will
+ be a string, but it will be digested into a 22-character MD5 code to save space. Although the
+ MD5 algorithm is not perfect, it is extremely unlikely two strings will have the same
+ digest. Therefore, it is presumed the keys will be unique. When the database is actually
+ in use, the hashed keys will be presented rather than the original values. For this reason,
+ they should not be used for entities where the key is meaningful.
  =head3 Global Tags
  The entire database definition must be inside a B<Database> tag. The display name of
-Line 170
+Line 190
  Name of the field. The field name should contain only letters, digits, and hyphens (C<->),
  and the first character should be a letter. Most underlying databases are case-insensitive
- with the respect to field names, so a best practice is to use lower-case letters only.
+ with the respect to field names, so a best practice is to use lower-case letters only. Finally,
+ the name C<search-relevance> has special meaning for full-text searches and should not be
+ used as a field name.
  =item type
-Line 189
+Line 211
  entity, the fields without a relation attribute are said to belong to the
  I<primary relation>. This relation has the same name as the entity itself.
+ =item searchable
+ If specified, then the field is a candidate for full-text searching. A single full-text
+ index will be created for each relation with at least one searchable field in it.
+ For best results, this option should only be used for string or text fields.
  =back
  =head3 Indexes
-Line 302
+Line 330
  # "maxLen" is the maximum permissible length of the incoming string data used to populate a field
  # of the specified type. "dataGen" is PERL string that will be evaluated if no test data generation
  # string is specified in the field definition. "avgLen" is the average byte length for estimating
- # record sizes.
+ # record sizes. "sort" is the key modifier for the sort command.
- my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, dataGen => "StringGen('A')" },
+ my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",  dataGen => "StringGen('A')" },
-                   int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, dataGen => "IntGen(0, 99999999)" },
+                   int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n", dataGen => "IntGen(0, 99999999)" },
-                   string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, dataGen => "StringGen(IntGen(10,250))" },
+                   counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n", dataGen => "IntGen(0, 99999999)" },
-                   text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, dataGen => "StringGen(IntGen(80,1000))" },
+                   string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, sort => "",  dataGen => "StringGen(IntGen(10,250))" },
-                   date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, dataGen => "DateGen(-7, 7, IntGen(0,1400))" },
+                   text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, sort => "",  dataGen => "StringGen(IntGen(80,1000))" },
-                   float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, dataGen => "FloatGen(0.0, 100.0)" },
+                   date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, sort => "n", dataGen => "DateGen(-7, 7, IntGen(0,1400))" },
-                   boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   2, dataGen => "IntGen(0, 1)" },
+                   float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, sort => "g", dataGen => "FloatGen(0.0, 100.0)" },
+                   boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, sort => "n", dataGen => "IntGen(0, 1)" },
+                  'hash-string' =>
+                              { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, sort => "",  dataGen => "SringGen(22)" },
+                  'id-string' =>
+                              { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, sort => "",  dataGen => "SringGen(22)" },
                   'key-string' =>
-                              { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, dataGen => "StringGen(IntGen(10,40))" },
+                              { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, sort => "",  dataGen => "StringGen(IntGen(10,40))" },
                   'name-string' =>
-                              { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, dataGen => "StringGen(IntGen(10,80))" },
+                              { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, sort => "",  dataGen => "StringGen(IntGen(10,80))" },
                   'medium-string' =>
-                              { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, dataGen => "StringGen(IntGen(10,160))" },
+                              { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",  dataGen => "StringGen(IntGen(10,160))" },
                  );
  # Table translating arities into natural language.
-Line 402
+Line 435
      # Write the HTML heading stuff.
      print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";
      print HTMLOUT "</head>\n<body>\n";
+     # Write the documentation.
+     print HTMLOUT $self->DisplayMetaData();
+     # Close the document.
+     print HTMLOUT "</body>\n</html>\n";
+     # Close the file.
+     close HTMLOUT;
+ }
+ =head3 DisplayMetaData
+ C<< my $html = $erdb->DisplayMetaData(); >>
+ Return an HTML description of the database. This description can be used to help users create
+ the data to be loaded into the relations and form queries. The output is raw includable HTML
+ without any HEAD or BODY tags.
+ =over 4
+ =item filename
+ The name of the output file.
+ =back
+ =cut
+ sub DisplayMetaData {
+     # Get the parameters.
+     my ($self) = @_;
+     # Get the metadata and the title string.
+     my $metadata = $self->{_metaData};
+     # Get the title string.
+     my $title = $metadata->{Title};
+     # Get the entity and relationship lists.
+     my $entityList = $metadata->{Entities};
+     my $relationshipList = $metadata->{Relationships};
+     # Declare the return variable.
+     my $retVal = "";
+     # Open the output file.
+     Trace("Building MetaData table of contents.") if T(4);
      # Here we do the table of contents. It starts as an unordered list of section names. Each
      # section contains an ordered list of entity or relationship subsections.
-     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";
      # Loop through the Entities, displaying a list item for each.
      foreach my $key (sort keys %{$entityList}) {
          # Display this item.
-         print HTMLOUT "<li><a href=\"#$key\">$key</a></li>\n";
+         $retVal .= "<li><a href=\"#$key\">$key</a></li>\n";
      }
      # Close off the entity section and start the relationship section.
-     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";
      # Loop through the Relationships.
      foreach my $key (sort keys %{$relationshipList}) {
          # Display this item.
          my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});
-         print HTMLOUT "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";
+         $retVal .= "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";
      }
      # Close off the relationship section and list the join table section.
-     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";
      # Close off the table of contents itself.
-     print HTMLOUT "</ul>\n";
+     $retVal .=  "</ul>\n";
      # Now we start with the actual data. Denote we're starting the entity section.
-     print HTMLOUT "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";
+     $retVal .= "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";
      # Loop through the entities.
      for my $key (sort keys %{$entityList}) {
          Trace("Building MetaData entry for $key entity.") if T(4);
          # Create the entity header. It contains a bookmark and the entity name.
-         print HTMLOUT "<a name=\"$key\"></a><h3>$key</h3>\n";
+         $retVal .= "<a name=\"$key\"></a><h3>$key</h3>\n";
          # Get the entity data.
          my $entityData = $entityList->{$key};
          # If there's descriptive text, display it.
          if (my $notes = $entityData->{Notes}) {
-             print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";
+             $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";
          }
          # Now we want a list of the entity's relationships. First, we set up the relationship subsection.
-         print HTMLOUT "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
+         $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
          # Loop through the relationships.
          for my $relationship (sort keys %{$relationshipList}) {
              # Get the relationship data.
-Line 446
+Line 519
                  # Get the relationship sentence and append the arity.
                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);
                  # Display the relationship data.
-                 print HTMLOUT "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";
+                 $retVal .= "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";
              }
          }
          # Close off the relationship list.
-         print HTMLOUT "</ul>\n";
+         $retVal .= "</ul>\n";
          # Get the entity's relations.
          my $relationList = $entityData->{Relations};
          # Create a header for the relation subsection.
-         print HTMLOUT "<h4>Relations for <b>$key</b></h4>\n";
+         $retVal .= "<h4>Relations for <b>$key</b></h4>\n";
          # Loop through the relations, displaying them.
          for my $relation (sort keys %{$relationList}) {
              my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});
-             print HTMLOUT $htmlString;
+             $retVal .= $htmlString;
          }
      }
      # Denote we're starting the relationship section.
-     print HTMLOUT "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";
+     $retVal .= "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";
      # Loop through the relationships.
      for my $key (sort keys %{$relationshipList}) {
          Trace("Building MetaData entry for $key relationship.") if T(4);
-Line 470
+Line 543
          my $relationshipStructure = $relationshipList->{$key};
          # Create the relationship header.
          my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);
-         print HTMLOUT "<h3><a name=\"$key\"></a>$headerText</h3>\n";
+         $retVal .= "<h3><a name=\"$key\"></a>$headerText</h3>\n";
          # Get the entity names.
          my $fromEntity = $relationshipStructure->{from};
          my $toEntity = $relationshipStructure->{to};
-Line 480
+Line 553
          # since both sentences will say the same thing.
          my $arity = $relationshipStructure->{arity};
          if ($arity eq "11") {
-             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>$toEntity</b>.\n";
          } else {
-             print HTMLOUT "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";
+             $retVal .= "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";
              if ($arity eq "MM" && $fromEntity ne $toEntity) {
-                 print HTMLOUT "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";
+                 $retVal .= "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";
              }
          }
-         print HTMLOUT "</p>\n";
+         $retVal .= "</p>\n";
          # If there are notes on this relationship, display them.
          if (my $notes = $relationshipStructure->{Notes}) {
-             print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";
+             $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";
          }
          # Generate the relationship's relation table.
          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
-         print HTMLOUT $htmlString;
+         $retVal .= $htmlString;
      }
      Trace("Building MetaData join table.") if T(4);
      # Denote we're starting the join table.
-     print HTMLOUT "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";
+     $retVal .= "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";
      # Create a table header.
-     print HTMLOUT _OpenTable("Join Table", "Source", "Target", "Join Condition");
+     $retVal .= _OpenTable("Join Table", "Source", "Target", "Join Condition");
      # Loop through the joins.
      my $joinTable = $metadata->{Joins};
      my @joinKeys = keys %{$joinTable};
-Line 508
+Line 581
          # Separate out the source, the target, and the join clause.
          $joinKey =~ m!^([^/]+)/(.+)$!;
          my ($sourceRelation, $targetRelation) = ($1, $2);
-         Trace("Join with key $joinKey is from $sourceRelation to $targetRelation.") if T(4);
+         Trace("Join with key $joinKey is from $sourceRelation to $targetRelation.") if T(Joins => 4);
          my $source = $self->ComputeObjectSentence($sourceRelation);
          my $target = $self->ComputeObjectSentence($targetRelation);
          my $clause = $joinTable->{$joinKey};
          # Display them in a table row.
-         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";
      }
      # Close the table.
-     print HTMLOUT _CloseTable();
+     $retVal .= _CloseTable();
-     # Close the document.
+     Trace("Built MetaData HTML.") if T(3);
-     print HTMLOUT "</body>\n</html>\n";
+     # Return the HTML.
-     # Close the file.
+     return $retVal;
-     close HTMLOUT;
-     Trace("Built MetaData web page.") if T(3);
  }
  =head3 DumpMetaData
-Line 626
+Line 697
      Trace("Creating table $relationName: $fieldThing") if T(2);
      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);
      Trace("Relation $relationName created in database.") if T(2);
-     # If we want to build the indexes, we do it here.
+     # If we want to build the indexes, we do it here. Note that the full-text search
+     # index will not be built until the table has been loaded.
      if ($indexFlag) {
          $self->CreateIndex($relationName);
      }
  }
+ =head3 VerifyFields
+ C<< my $count = $erdb->VerifyFields($relName, \@fieldList); >>
+ Run through the list of proposed field values, insuring that all the character fields are
+ below the maximum length. If any fields are too long, they will be truncated in place.
+ =over 4
+ =item relName
+ Name of the relation for which the specified fields are destined.
+ =item fieldList
+ Reference to a list, in order, of the fields to be put into the relation.
+ =item RETURN
+ Returns the number of fields truncated.
+ =back
+ =cut
+ sub VerifyFields {
+     # Get the parameters.
+     my ($self, $relName, $fieldList) = @_;
+     # Initialize the return value.
+     my $retVal = 0;
+     # Get the relation definition.
+     my $relData = $self->_FindRelation($relName);
+     # Get the list of field descriptors.
+     my $fieldTypes = $relData->{Fields};
+     my $fieldCount = scalar @{$fieldTypes};
+     # Loop through the two lists.
+     for (my $i = 0; $i < $fieldCount; $i++) {
+         # Get the type of the current field.
+         my $fieldType = $fieldTypes->[$i]->{type};
+         # If it's a character field, verify the length.
+         if ($fieldType =~ /string/) {
+             my $maxLen = $TypeTable{$fieldType}->{maxLen};
+             my $oldString = $fieldList->[$i];
+             if (length($oldString) > $maxLen) {
+                 # Here it's too big, so we truncate it.
+                 Trace("Truncating field $i in relation $relName to $maxLen characters from \"$oldString\".") if T(1);
+                 $fieldList->[$i] = substr $oldString, 0, $maxLen;
+                 $retVal++;
+             }
+         }
+     }
+     # Return the truncation count.
+     return $retVal;
+ }
+ =head3 DigestFields
+ C<< $erdb->DigestFields($relName, $fieldList); >>
+ Digest the strings in the field list that correspond to data type C<hash-string> in the
+ specified relation.
+ =over 4
+ =item relName
+ Name of the relation to which the fields belong.
+ =item fieldList
+ List of field contents to be loaded into the relation.
+ =back
+ =cut
+ #: Return Type ;
+ sub DigestFields {
+     # Get the parameters.
+     my ($self, $relName, $fieldList) = @_;
+     # Get the relation definition.
+     my $relData = $self->_FindRelation($relName);
+     # Get the list of field descriptors.
+     my $fieldTypes = $relData->{Fields};
+     my $fieldCount = scalar @{$fieldTypes};
+     # Loop through the two lists.
+     for (my $i = 0; $i < $fieldCount; $i++) {
+         # Get the type of the current field.
+         my $fieldType = $fieldTypes->[$i]->{type};
+         # If it's a hash string, digest it in place.
+         if ($fieldType eq 'hash-string') {
+             $fieldList->[$i] = $self->DigestKey($fieldList->[$i]);
+         }
+     }
+ }
+ =head3 DigestKey
+ C<< my $digested = $erdb->DigestKey($keyValue); >>
+ Return the digested value of a symbolic key. The digested value can then be plugged into a
+ key-based search into a table with key-type hash-string.
+ Currently the digesting process is independent of the database structure, but that may not
+ always be the case, so this is an instance method instead of a static method.
+ =over 4
+ =item keyValue
+ Key value to digest.
+ =item RETURN
+ Digested value of the key.
+ =back
+ =cut
+ sub DigestKey {
+     # Get the parameters.
+     my ($self, $keyValue) = @_;
+     # Compute the digest.
+     my $retVal = md5_base64($keyValue);
+     # Return the result.
+     return $retVal;
+ }
  =head3 CreateIndex
  C<< $erdb->CreateIndex($relationName); >>
-Line 658
+Line 858
          my @fieldList = _FixNames(@{$indexData->{IndexFields}});
          my $flds = join(', ', @fieldList);
          # Get the index's uniqueness flag.
-         my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');
+         my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
          # Create the index.
          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
-                                     flds => $flds, unique => $unique);
+                                     flds => $flds, kind => $unique);
          if ($rv) {
              Trace("Index created: $indexName for $relationName ($flds)") if T(1);
          } else {
-Line 793
+Line 993
  =head3 Get
- C<< my $query = $erdb->Get(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>
+ C<< my $query = $erdb->Get(\@objectNames, $filterClause, \@params); >>
  This method returns a query object for entities of a specified type using a specified filter.
  The filter is a standard WHERE/ORDER BY clause with question marks as parameter markers and each
-Line 801
+Line 1001
  following call requests all B<Genome> objects for the genus specified in the variable
  $genus.
- C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", $genus); >>
+ C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", [$genus]); >>
  The WHERE clause contains a single question mark, so there is a single additional
  parameter representing the parameter value. It would also be possible to code
-Line 818
+Line 1018
  It is possible to specify multiple entity and relationship names in order to retrieve more than
  one object's data at the same time, which allows highly complex joined queries. For example,
- C<< $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", $genus); >>
+ C<< $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]); >>
  If multiple names are specified, then the query processor will automatically determine a
  join path between the entities and relationships. The algorithm used is very simplistic.
- 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
- 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
- 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
  coded as C<['People', 'IsParentOf']>, then the people returned will be parents. If, however,
  the join path is C<['IsParentOf', 'People']>, then the people returned will be children.
+ If an entity or relationship is mentioned twice, the name for the second occurrence will
+ be suffixed with C<2>, the third occurrence will be suffixed with C<3>, and so forth. So,
+ for example, if we have C<['Feature', 'HasContig', 'Contig', 'HasContig']>, then the
+ B<to-link> field of the first B<HasContig> is specified as C<HasContig(to-link)>, while
+ the B<to-link> field of the second B<HasContig> is specified as C<HasContig2(to-link)>.
  =over 4
  =item objectNames
-Line 851
+Line 1056
  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
+ Note that the case is important. Only an uppercase "ORDER BY" with a single space will
+ be processed. The idea is to make it less likely to find the verb by accident.
  The rules for field references in a sort order are the same as those for field references in the
  filter clause in general; however, odd things may happen if a sort field is from a secondary
  relation.
- =item param1, param2, ..., paramN
+ Finally, you can limit the number of rows returned by adding a LIMIT clause. The LIMIT must
+ be the last thing in the filter clause, and it contains only the word "LIMIT" followed by
+ a positive number. So, for example
+ C<< "Genome(genus) = ? ORDER BY Genome(species) LIMIT 10" >>
- Parameter values to be substituted into the filter clause.
+ will only return the first ten genomes for the specified genus. The ORDER BY clause is not
+ required. For example, to just get the first 10 genomes in the B<Genome> table, you could
+ use
+ C<< "LIMIT 10" >>
+ =item params
+ Reference to a list of parameter values to be substituted into the filter clause.
  =item RETURN
-Line 869
+Line 1089
  sub Get {
      # Get the parameters.
-     my ($self, $objectNames, $filterClause, @params) = @_;
+     my ($self, $objectNames, $filterClause, $params) = @_;
-     # Construct the SELECT statement. The general pattern is
+     # Process the SQL stuff.
-     #
+     my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
-     # SELECT name1.*, name2.*, ... nameN.* FROM name1, name2, ... nameN
+         $self->_SetupSQL($objectNames, $filterClause);
-     #
+     # Create the query.
-     my $dbh = $self->{_dbh};
+     my $command = "SELECT DISTINCT " . join(".*, ", @{$mappedNameListRef}) .
-     my $command = "SELECT DISTINCT " . join('.*, ', @{$objectNames}) . ".* FROM " .
+         ".* $suffix";
-                 join(', ', @{$objectNames});
+     my $sth = $self->_GetStatementHandle($command, $params);
-     # Check for a filter clause.
+     # Now we create the relation map, which enables DBQuery to determine the order, name
-     if ($filterClause) {
+     # and mapped name for each object in the query.
-         # Here we have one, so we convert its field names and add it to the query. First,
+     my @relationMap = ();
-         # We create a copy of the filter string we can work with.
+     for my $mappedName (@{$mappedNameListRef}) {
-         my $filterString = $filterClause;
+         push @relationMap, [$mappedName, $mappedNameHashRef->{$mappedName}];
-         # Next, we sort the object names by length. This helps protect us from finding
-         # object names inside other object names when we're doing our search and replace.
-         my @sortedNames = sort { length($b) - length($a) } @{$objectNames};
-         # We will also keep a list of conditions to add to the WHERE clause in order to link
-         # entities and relationships as well as primary relations to secondary ones.
-         my @joinWhere = ();
-         # The final preparatory step is to create a hash table of relation names. The
-         # table begins with the relation names already in the SELECT command.
-         my %fromNames = ();
-         for my $objectName (@sortedNames) {
-             $fromNames{$objectName} = 1;
-         }
-         # We are ready to begin. We loop through the object names, replacing each
-         # object name's field references by the corresponding SQL field reference.
-         # Along the way, if we find a secondary relation, we will need to add it
-         # to the FROM clause.
-         for my $objectName (@sortedNames) {
-             # Get the length of the object name plus 2. This is the value we add to the
-             # size of the field name to determine the size of the field reference as a
-             # whole.
-             my $nameLength = 2 + length $objectName;
-             # Get the object's field list.
-             my $fieldList = $self->_GetFieldTable($objectName);
-             # Find the field references for this object.
-             while ($filterString =~ m/$objectName\(([^)]*)\)/g) {
-                 # At this point, $1 contains the field name, and the current position
-                 # is set immediately after the final parenthesis. We pull out the name of
-                 # the field and the position and length of the field reference as a whole.
-                 my $fieldName = $1;
-                 my $len = $nameLength + length $fieldName;
-                 my $pos = pos($filterString) - $len;
-                 # Insure the field exists.
-                 if (!exists $fieldList->{$fieldName}) {
-                     Confess("Field $fieldName not found for object $objectName.");
-                 } else {
-                     # Get the field's relation.
-                     my $relationName = $fieldList->{$fieldName}->{relation};
-                     # Insure the relation is in the FROM clause.
-                     if (!exists $fromNames{$relationName}) {
-                         # Add the relation to the FROM clause.
-                         $command .= ", $relationName";
-                         # Create its join sub-clause.
-                         push @joinWhere, "$objectName.id = $relationName.id";
-                         # Denote we have it available for future fields.
-                         $fromNames{$relationName} = 1;
-                     }
-                     # Form an SQL field reference from the relation name and the field name.
-                     my $sqlReference = "$relationName." . _FixName($fieldName);
-                     # Put it into the filter string in place of the old value.
-                     substr($filterString, $pos, $len) = $sqlReference;
-                     # Reposition the search.
-                     pos $filterString = $pos + length $sqlReference;
-                 }
-             }
-         }
-         # The next step is to join the objects together. We only need to do this if there
-         # is more than one object in the object list. We start with the first object and
-         # run through the objects after it. Note also that we make a safety copy of the
-         # list before running through it.
-         my @objectList = @{$objectNames};
-         my $lastObject = shift @objectList;
-         # Get the join table.
-         my $joinTable = $self->{_metaData}->{Joins};
-         # Loop through the object list.
-         for my $thisObject (@objectList) {
-             # Look for a join.
-             my $joinKey = "$lastObject/$thisObject";
-             if (!exists $joinTable->{$joinKey}) {
-                 # Here there's no join, so we throw an error.
-                 Confess("No join exists to connect from $lastObject to $thisObject.");
-             } else {
-                 # Get the join clause and add it to the WHERE list.
-                 push @joinWhere, $joinTable->{$joinKey};
-                 # Save this object as the last object for the next iteration.
-                 $lastObject = $thisObject;
-             }
-         }
-         # Now we need to handle the whole ORDER BY thing. We'll put the order by clause
-         # in the following variable.
-         my $orderClause = "";
-         # Locate the ORDER BY verb (if any).
-         if ($filterString =~ m/^(.*)ORDER BY/g) {
-             # Here we have an ORDER BY verb. Split it off of the filter string.
-             my $pos = pos $filterString;
-             $orderClause = substr($filterString, $pos);
-             $filterString = $1;
-         }
-         # Add the filter and the join clauses (if any) to the SELECT command.
-         if ($filterString) {
-             push @joinWhere, "($filterString)";
-         }
-         if (@joinWhere) {
-             $command .= " WHERE " . join(' AND ', @joinWhere);
-         }
-         # Add the sort clause (if any) to the SELECT command.
-         if ($orderClause) {
-             $command .= " ORDER BY $orderClause";
-         }
      }
-     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());
      # Return the statement object.
-     my $retVal = DBQuery::_new($self, $sth, @{$objectNames});
+     my $retVal = DBQuery::_new($self, $sth, \@relationMap);
      return $retVal;
  }
- =head3 GetList
+ =head3 Search
- C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>
- Return a list of object descriptors for the specified objects as determined by the
+ C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>
- specified filter clause.
- This method is essentially the same as L</Get> except it returns a list of objects rather
+ Perform a full text search with filtering. The search will be against a specified object
- than a query object that can be used to get the results one record at a time.
+ in the object name list. That object will get an extra field containing the search
+ relevance. Note that except for the search expression, the parameters of this method are
+ the same as those for L</Get> and follow the same rules.
  =over 4
+ =item searchExpression
+ Boolean search expression for the text fields of the target object.
+ =item idx
+ Index in the I<$objectNames> list of the table to be searched in full-text mode.
  =item objectNames
  List containing the names of the entity and relationship objects to be retrieved.
-Line 1017
+Line 1141
  or secondary entity relations; however, all of the entities and relationships involved must
  be included in the list of object names.
- The filter clause can also specify a sort order. To do this, simply follow the filter string
+ =item params
- with an ORDER BY clause. For example, the following filter string gets all genomes for a
- particular genus and sorts them by species name.
- C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
- The rules for field references in a sort order are the same as those for field references in the
- filter clause in general; however, odd things may happen if a sort field is from a secondary
- relation.
- =item param1, param2, ..., paramN
- Parameter values to be substituted into the filter clause.
+ Reference to a list of parameter values to be substituted into the filter clause.
  =item RETURN
- Returns a list of B<DBObject>s that satisfy the query conditions.
+ Returns a query object for the specified search.
  =back
  =cut
- #: Return Type @%
- sub GetList {
+ sub Search {
      # Get the parameters.
-     my ($self, $objectNames, $filterClause, @params) = @_;
+     my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
      # Declare the return variable.
-     my @retVal = ();
+     my $retVal;
-     # Perform the query.
+     # Create a safety copy of the parameter list.
-     my $query = $self->Get($objectNames, $filterClause, @params);
+     my @myParams = @{$params};
-     # Loop through the results.
+     # Get the first object's structure so we have access to the searchable fields.
-     while (my $object = $query->Fetch) {
+     my $object1Name = $objectNames->[$idx];
-         push @retVal, $object;
+     my $object1Structure = $self->_GetStructure($object1Name);
+     # Get the field list.
+     if (! exists $object1Structure->{searchFields}) {
+         Confess("No searchable index for $object1Name.");
+     } else {
+         # Get the field list.
+         my @fields = @{$object1Structure->{searchFields}};
+         # Clean the search expression.
+         my $actualKeywords = $self->CleanKeywords($searchExpression);
+         # We need two match expressions, one for the filter clause and one in the
+         # query itself. Both will use a parameter mark, so we need to push the
+         # search expression onto the front of the parameter list twice.
+         unshift @myParams, $actualKeywords, $actualKeywords;
+         # Build the match expression.
+         my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
+         my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
+         # Process the SQL stuff.
+         my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
+             $self->_SetupSQL($objectNames, $filterClause, $matchClause);
+         # Create the query. Note that the match clause is inserted at the front of
+         # the select fields.
+         my $command = "SELECT DISTINCT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .
+             ".* $suffix";
+         my $sth = $self->_GetStatementHandle($command, \@myParams);
+         # Now we create the relation map, which enables DBQuery to determine the order, name
+         # and mapped name for each object in the query.
+         my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
+         # Return the statement object.
+         $retVal = DBQuery::_new($self, $sth, \@relationMap, $object1Name);
      }
-     # Return the result.
+     return $retVal;
-     return @retVal;
  }
- =head3 ComputeObjectSentence
+ =head3 GetFlat
- C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>
+ C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>
- Check an object name, and if it is a relationship convert it to a relationship sentence.
+ This is a variation of L</GetAll> that asks for only a single field per record and
+ returns a single flattened list.
  =over 4
- =item objectName
+ =item objectNames
- Name of the entity or relationship.
+ List containing the names of the entity and relationship objects to be retrieved.
+ =item filterClause
+ WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
+ be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
+ B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
+ parameter list as additional parameters. The fields in a filter clause can come from primary
+ entity relations, relationship relations, or secondary entity relations; however, all of the
+ entities and relationships involved must be included in the list of object names.
+ =item parameterList
+ List of the parameters to be substituted in for the parameters marks in the filter clause.
+ =item field
+ Name of the field to be used to get the elements of the list returned.
  =item RETURN
- Returns a string containing the entity name or a relationship sentence.
+ Returns a list of values.
  =back
  =cut
+ #: Return Type @;
- sub ComputeObjectSentence {
+ sub GetFlat {
      # Get the parameters.
-     my ($self, $objectName) = @_;
+     my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
-     # Set the default return value.
+     # Construct the query.
-     my $retVal = $objectName;
+     my $query = $self->Get($objectNames, $filterClause, $parameterList);
-     # Look for the object as a relationship.
+     # Create the result list.
-     my $relTable = $self->{_metaData}->{Relationships};
+     my @retVal = ();
-     if (exists $relTable->{$objectName}) {
+     # Loop through the records, adding the field values found to the result list.
-         # Get the relationship sentence.
+     while (my $row = $query->Fetch()) {
+         push @retVal, $row->Value($field);
+     }
+     # Return the list created.
+     return @retVal;
+ }
+ =head3 Delete
+ C<< my $stats = $erdb->Delete($entityName, $objectID); >>
+ Delete an entity instance from the database. The instance is deleted along with all entity and
+ relationship instances dependent on it. The idea of dependence here is recursive. An object is
+ always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many
+ relationship connected to a dependent entity or the "to" entity connected to a 1-to-many
+ dependent relationship.
+ =over 4
+ =item entityName
+ Name of the entity type for the instance being deleted.
+ =item objectID
+ ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),
+ then it is presumed to by a LIKE pattern.
+ =item testFlag
+ If TRUE, the delete statements will be traced without being executed.
+ =item RETURN
+ Returns a statistics object indicating how many records of each particular table were
+ deleted.
+ =back
+ =cut
+ #: Return Type $%;
+ sub Delete {
+     # Get the parameters.
+     my ($self, $entityName, $objectID, $testFlag) = @_;
+     # Declare the return variable.
+     my $retVal = Stats->new();
+     # Get the DBKernel object.
+     my $db = $self->{_dbh};
+     # We're going to generate all the paths branching out from the starting entity. One of
+     # the things we have to be careful about is preventing loops. We'll use a hash to
+     # determine if we've hit a loop.
+     my %alreadyFound = ();
+     # These next lists will serve as our result stack. We start by pushing object lists onto
+     # the stack, and then popping them off to do the deletes. This means the deletes will
+     # start with the longer paths before getting to the shorter ones. That, in turn, makes
+     # sure we don't delete records that might be needed to forge relationships back to the
+     # original item. We have two lists-- one for TO-relationships, and one for
+     # FROM-relationships and entities.
+     my @fromPathList = ();
+     my @toPathList = ();
+     # This final hash is used to remember what work still needs to be done. We push paths
+     # onto the list, then pop them off to extend the paths. We prime it with the starting
+     # point. Note that we will work hard to insure that the last item on a path in the
+     # TODO list is always an entity.
+     my @todoList = ([$entityName]);
+     while (@todoList) {
+         # Get the current path.
+         my $current = pop @todoList;
+         # Copy it into a list.
+         my @stackedPath = @{$current};
+         # Pull off the last item on the path. It will always be an entity.
+         my $entityName = pop @stackedPath;
+         # Add it to the alreadyFound list.
+         $alreadyFound{$entityName} = 1;
+         # Get the entity data.
+         my $entityData = $self->_GetStructure($entityName);
+         # The first task is to loop through the entity's relation. A DELETE command will
+         # be needed for each of them.
+         my $relations = $entityData->{Relations};
+         for my $relation (keys %{$relations}) {
+             my @augmentedList = (@stackedPath, $relation);
+             push @fromPathList, \@augmentedList;
+         }
+         # Now we need to look for relationships connected to this entity.
+         my $relationshipList = $self->{_metaData}->{Relationships};
+         for my $relationshipName (keys %{$relationshipList}) {
+             my $relationship = $relationshipList->{$relationshipName};
+             # Check the FROM field. We're only interested if it's us.
+             if ($relationship->{from} eq $entityName) {
+                 # Add the path to this relationship.
+                 my @augmentedList = (@stackedPath, $entityName, $relationshipName);
+                 push @fromPathList, \@augmentedList;
+                 # Check the arity. If it's MM we're done. If it's 1M
+                 # and the target hasn't been seen yet, we want to
+                 # stack the entity for future processing.
+                 if ($relationship->{arity} eq '1M') {
+                     my $toEntity = $relationship->{to};
+                     if (! exists $alreadyFound{$toEntity}) {
+                         # Here we have a new entity that's dependent on
+                         # the current entity, so we need to stack it.
+                         my @stackList = (@augmentedList, $toEntity);
+                         push @fromPathList, \@stackList;
+                     } else {
+                         Trace("$toEntity ignored because it occurred previously.") if T(4);
+                     }
+                 }
+             }
+             # Now check the TO field. In this case only the relationship needs
+             # deletion.
+             if ($relationship->{to} eq $entityName) {
+                 my @augmentedList = (@stackedPath, $entityName, $relationshipName);
+                 push @toPathList, \@augmentedList;
+             }
+         }
+     }
+     # Create the first qualifier for the WHERE clause. This selects the
+     # keys of the primary entity records to be deleted. When we're deleting
+     # from a dependent table, we construct a join page from the first qualifier
+     # to the table containing the dependent records to delete.
+     my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
+     # We need to make two passes. The first is through the to-list, and
+     # the second through the from-list. The from-list is second because
+     # the to-list may need to pass through some of the entities the
+     # from-list would delete.
+     my %stackList = ( from_link => \@fromPathList, to_link => \@toPathList );
+     # Now it's time to do the deletes. We do it in two passes.
+     for my $keyName ('to_link', 'from_link') {
+         # Get the list for this key.
+         my @pathList = @{$stackList{$keyName}};
+         Trace(scalar(@pathList) . " entries in path list for $keyName.") if T(3);
+         # Loop through this list.
+         while (my $path = pop @pathList) {
+             # Get the table whose rows are to be deleted.
+             my @pathTables = @{$path};
+             # Start the DELETE statement. We need to call DBKernel because the
+             # syntax of a DELETE-USING varies among DBMSs.
+             my $target = $pathTables[$#pathTables];
+             my $stmt = $db->SetUsing(@pathTables);
+             # Now start the WHERE. The first thing is the ID field from the starting table. That
+             # starting table will either be the entity relation or one of the entity's
+             # sub-relations.
+             $stmt .= " WHERE $pathTables[0].id $qualifier";
+             # Now we run through the remaining entities in the path, connecting them up.
+             for (my $i = 1; $i <= $#pathTables; $i += 2) {
+                 # Connect the current relationship to the preceding entity.
+                 my ($entity, $rel) = @pathTables[$i-1,$i];
+                 # The style of connection depends on the direction of the relationship.
+                 $stmt .= " AND $entity.id = $rel.$keyName";
+                 if ($i + 1 <= $#pathTables) {
+                     # Here there's a next entity, so connect that to the relationship's
+                     # to-link.
+                     my $entity2 = $pathTables[$i+1];
+                     $stmt .= " AND $rel.to_link = $entity2.id";
+                 }
+             }
+             # Now we have our desired DELETE statement.
+             if ($testFlag) {
+                 # Here the user wants to trace without executing.
+                 Trace($stmt) if T(0);
+             } else {
+                 # Here we can delete. Note that the SQL method dies with a confessing
+                 # if an error occurs, so we just go ahead and do it.
+                 Trace("Executing delete from $target using '$objectID'.") if T(3);
+                 my $rv = $db->SQL($stmt, 0, $objectID);
+                 # Accumulate the statistics for this delete. The only rows deleted
+                 # are from the target table, so we use its name to record the
+                 # statistic.
+                 $retVal->Add($target, $rv);
+             }
+         }
+     }
+     # Return the result.
+     return $retVal;
+ }
+ =head3 SortNeeded
+ C<< my $parms = $erdb->SortNeeded($relationName); >>
+ Return the pipe command for the sort that should be applied to the specified
+ relation when creating the load file.
+ For example, if the load file should be sorted ascending by the first
+ field, this method would return
+     sort -k1 -t"\t"
+ If the first field is numeric, the method would return
+     sort -k1n -t"\t"
+ Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate
+ keys using a sort.
+ =over 4
+ =item relationName
+ Name of the relation to be examined.
+ =item
+ Returns the sort command to use for sorting the relation, suitable for piping.
+ =back
+ =cut
+ #: Return Type $;
+ sub SortNeeded {
+     # Get the parameters.
+     my ($self, $relationName) = @_;
+     # Declare a descriptor to hold the names of the key fields.
+     my @keyNames = ();
+     # Get the relation structure.
+     my $relationData = $self->_FindRelation($relationName);
+     # Find out if the relation is a primary entity relation,
+     # a relationship relation, or a secondary entity relation.
+     my $entityTable = $self->{_metaData}->{Entities};
+     my $relationshipTable = $self->{_metaData}->{Relationships};
+     if (exists $entityTable->{$relationName}) {
+         # Here we have a primary entity relation.
+         push @keyNames, "id";
+     } elsif (exists $relationshipTable->{$relationName}) {
+         # Here we have a relationship. We sort using the FROM index.
+         my $relationshipData = $relationshipTable->{$relationName};
+         my $index = $relationData->{Indexes}->{"idx${relationName}From"};
+         push @keyNames, @{$index->{IndexFields}};
+     } else {
+         # Here we have a secondary entity relation, so we have a sort on the ID field.
+         push @keyNames, "id";
+     }
+     # Now we parse the key names into sort parameters. First, we prime the return
+     # string.
+     my $retVal = "sort -t\"\t\" ";
+     # Get the relation's field list.
+     my @fields = @{$relationData->{Fields}};
+     # Loop through the keys.
+     for my $keyData (@keyNames) {
+         # Get the key and the ordering.
+         my ($keyName, $ordering);
+         if ($keyData =~ /^([^ ]+) DESC/) {
+             ($keyName, $ordering) = ($1, "descending");
+         } else {
+             ($keyName, $ordering) = ($keyData, "ascending");
+         }
+         # Find the key's position and type.
+         my $fieldSpec;
+         for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {
+             my $thisField = $fields[$i];
+             if ($thisField->{name} eq $keyName) {
+                 # Get the sort modifier for this field type. The modifier
+                 # decides whether we're using a character, numeric, or
+                 # floating-point sort.
+                 my $modifier = $TypeTable{$thisField->{type}}->{sort};
+                 # If the index is descending for this field, denote we want
+                 # to reverse the sort order on this field.
+                 if ($ordering eq 'descending') {
+                     $modifier .= "r";
+                 }
+                 # Store the position and modifier into the field spec, which
+                 # will stop the inner loop. Note that the field number is
+                 # 1-based in the sort command, so we have to increment the
+                 # index.
+                 $fieldSpec = ($i + 1) . $modifier;
+             }
+         }
+         # Add this field to the sort command.
+         $retVal .= " -k$fieldSpec";
+     }
+     # Return the result.
+     return $retVal;
+ }
+ =head3 GetList
+ C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>
+ Return a list of object descriptors for the specified objects as determined by the
+ specified filter clause.
+ This method is essentially the same as L</Get> except it returns a list of objects rather
+ than a query object that can be used to get the results one record at a time.
+ =over 4
+ =item objectNames
+ List containing the names of the entity and relationship objects to be retrieved.
+ =item filterClause
+ WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
+ be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
+ specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
+ in the filter clause should be added to the parameter list as additional parameters. The
+ fields in a filter clause can come from primary entity relations, relationship relations,
+ or secondary entity relations; however, all of the entities and relationships involved must
+ be included in the list of object names.
+ The filter clause can also specify a sort order. To do this, simply follow the filter string
+ with an ORDER BY clause. For example, the following filter string gets all genomes for a
+ particular genus and sorts them by species name.
+ C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
+ The rules for field references in a sort order are the same as those for field references in the
+ filter clause in general; however, odd things may happen if a sort field is from a secondary
+ relation.
+ =item params
+ Reference to a list of parameter values to be substituted into the filter clause.
+ =item RETURN
+ Returns a list of B<DBObject>s that satisfy the query conditions.
+ =back
+ =cut
+ #: Return Type @%
+ sub GetList {
+     # Get the parameters.
+     my ($self, $objectNames, $filterClause, $params) = @_;
+     # Declare the return variable.
+     my @retVal = ();
+     # Perform the query.
+     my $query = $self->Get($objectNames, $filterClause, $params);
+     # Loop through the results.
+     while (my $object = $query->Fetch) {
+         push @retVal, $object;
+     }
+     # Return the result.
+     return @retVal;
+ }
+ =head3 GetCount
+ C<< my $count = $erdb->GetCount(\@objectNames, $filter, \@params); >>
+ Return the number of rows found by a specified query. This method would
+ normally be used to count the records in a single table. For example, in a
+ genetics database
+     my $count = $erdb->GetCount(['Genome'], 'Genome(genus-species) LIKE ?', ['homo %']);
+ would return the number of genomes for the genus I<homo>. It is conceivable, however,
+ to use it to return records based on a join. For example,
+     my $count = $erdb->GetCount(['HasFeature', 'Genome'], 'Genome(genus-species) LIKE ?',
+                                 ['homo %']);
+ would return the number of features for genomes in the genus I<homo>. Note that
+ only the rows from the first table are counted. If the above command were
+     my $count = $erdb->GetCount(['Genome', 'Feature'], 'Genome(genus-species) LIKE ?',
+                                 ['homo %']);
+ it would return the number of genomes, not the number of genome/feature pairs.
+ =over 4
+ =item objectNames
+ Reference to a list of the objects (entities and relationships) included in the
+ query.
+ =item filter
+ A filter clause for restricting the query. The rules are the same as for the L</Get>
+ method.
+ =item params
+ Reference to a list of the parameter values to be substituted for the parameter marks
+ in the filter.
+ =item RETURN
+ Returns a count of the number of records in the first table that would satisfy
+ the query.
+ =back
+ =cut
+ sub GetCount {
+     # Get the parameters.
+     my ($self, $objectNames, $filter, $params) = @_;
+     # Insure the params argument is an array reference if the caller left it off.
+     if (! defined($params)) {
+         $params = [];
+     }
+     # Declare the return variable.
+     my $retVal;
+     # Find out if we're counting an entity or a relationship.
+     my $countedField;
+     if ($self->IsEntity($objectNames->[0])) {
+         $countedField = "id";
+     } else {
+         # For a relationship we count the to-link because it's usually more
+         # numerous. Note we're automatically converting to the SQL form
+         # of the field name (to_link vs. to-link).
+         $countedField = "to_link";
+     }
+     # Create the SQL command suffix to get the desired records.
+     my ($suffix, $mappedNameListRef, $mappedNameHashRef) = $self->_SetupSQL($objectNames,
+                                                                             $filter);
+     # Prefix it with text telling it we want a record count.
+     my $firstObject = $mappedNameListRef->[0];
+     my $command = "SELECT COUNT($firstObject.$countedField) $suffix";
+     # Prepare and execute the command.
+     my $sth = $self->_GetStatementHandle($command, $params);
+     # Get the count value.
+     ($retVal) = $sth->fetchrow_array();
+     # Check for a problem.
+     if (! defined($retVal)) {
+         if ($sth->err) {
+             # Here we had an SQL error.
+             Confess("Error retrieving row count: " . $sth->errstr());
+         } else {
+             # Here we have no result.
+             Confess("No result attempting to retrieve row count.");
+         }
+     }
+     # Return the result.
+     return $retVal;
+ }
+ =head3 ComputeObjectSentence
+ C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>
+ Check an object name, and if it is a relationship convert it to a relationship sentence.
+ =over 4
+ =item objectName
+ Name of the entity or relationship.
+ =item RETURN
+ Returns a string containing the entity name or a relationship sentence.
+ =back
+ =cut
+ sub ComputeObjectSentence {
+     # Get the parameters.
+     my ($self, $objectName) = @_;
+     # Set the default return value.
+     my $retVal = $objectName;
+     # Look for the object as a relationship.
+     my $relTable = $self->{_metaData}->{Relationships};
+     if (exists $relTable->{$objectName}) {
+         # Get the relationship sentence.
          $retVal = _ComputeRelationshipSentence($objectName, $relTable->{$objectName});
      }
      # Return the result.
-Line 1131
+Line 1747
      }
  }
+ =head3 InsertValue
+ C<< $erdb->InsertValue($entityID, $fieldName, $value); >>
+ This method will insert a new value into the database. The value must be one
+ associated with a secondary relation, since primary values cannot be inserted:
+ they occur exactly once. Secondary values, on the other hand, can be missing
+ or multiply-occurring.
+ =over 4
+ =item entityID
+ ID of the object that is to receive the new value.
+ =item fieldName
+ Field name for the new value-- this includes the entity name, since
+ field names are of the format I<objectName>C<(>I<fieldName>C<)>.
+ =item value
+ New value to be put in the field.
+ =back
+ =cut
+ sub InsertValue {
+     # Get the parameters.
+     my ($self, $entityID, $fieldName, $value) = @_;
+     # Parse the entity name and the real field name.
+     if ($fieldName =~ /^([^(]+)\(([^)]+)\)/) {
+         my $entityName = $1;
+         my $fieldTitle = $2;
+         # Get its descriptor.
+         if (!$self->IsEntity($entityName)) {
+             Confess("$entityName is not a valid entity.");
+         } else {
+             my $entityData = $self->{_metaData}->{Entities}->{$entityName};
+             # Find the relation containing this field.
+             my $fieldHash = $entityData->{Fields};
+             if (! exists $fieldHash->{$fieldTitle}) {
+                 Confess("$fieldTitle not found in $entityName.");
+             } else {
+                 my $relation = $fieldHash->{$fieldTitle}->{relation};
+                 if ($relation eq $entityName) {
+                     Confess("Cannot do InsertValue on primary field $fieldTitle of $entityName.");
+                 } else {
+                     # Now we can create an INSERT statement.
+                     my $dbh = $self->{_dbh};
+                     my $fixedName = _FixName($fieldTitle);
+                     my $statement = "INSERT INTO $relation (id, $fixedName) VALUES(?, ?)";
+                     # Execute the command.
+                     $dbh->SQL($statement, 0, $entityID, $value);
+                 }
+             }
+         }
+     } else {
+         Confess("$fieldName is not a valid field name.");
+     }
+ }
  =head3 InsertObject
  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>
-Line 1147
+Line 1826
  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
- C<< $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>
+ C<< $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>
  =over 4
-Line 1293
+Line 1972
  =item RETURN
- Returns a statistical object containing the number of records read and a list of
+ Returns a statistical object containing a list of the error messages.
- the error messages.
  =back
-Line 1348
+Line 2026
          my $size = -s $fileName;
          Trace("$size bytes loaded into $relationName.") if T(2);
          # If we're rebuilding, we need to create the table indexes.
-         if ($truncateFlag && ! $dbh->{_preIndex}) {
+         if ($truncateFlag) {
+             # Indexes are created here for PostGres. For PostGres, indexes are
+             # best built at the end. For MySQL, the reverse is true.
+             if (! $dbh->{_preIndex}) {
              eval {
                  $self->CreateIndex($relationName);
              };
-Line 1356
+Line 2037
                  $retVal->AddMessage($@);
              }
          }
+             # The full-text index (if any) is always built last, even for MySQL.
+             # First we need to see if this table has a full-text index. Only
+             # primary relations are allowed that privilege.
+             if ($self->_IsPrimary($relationName)) {
+                 # Get the relation's entity/relationship structure.
+                 my $structure = $self->_GetStructure($relationName);
+                 # Check for a searchable fields list.
+                 if (exists $structure->{searchFields}) {
+                     # Here we know that we need to create a full-text search index.
+                     # Get an SQL-formatted field name list.
+                     my $fields = join(", ", $self->_FixNames(@{$structure->{searchFields}}));
+                     # Create the index.
+                     $dbh->create_index(tbl => $relationName, idx => "search_idx_$relationName",
+                                        flds => $fields, kind => 'fulltext');
+                 }
+             }
+         }
      }
      # Analyze the table to improve performance.
+     Trace("Analyzing and compacting $relationName.") if T(3);
      $dbh->vacuum_it($relationName);
+     Trace("$relationName load completed.") if T(3);
      # Return the statistics.
      return $retVal;
  }
-Line 1421
+Line 2121
      return $this;
  }
  =head3 GetEntity
+ C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>
+ Return an object describing the entity instance with a specified ID.
+ =over 4
+ =item entityType
+ Entity type name.
+ =item ID
+ ID of the desired entity.
+ =item RETURN
+ Returns a B<DBObject> representing the desired entity instance, or an undefined value if no
+ instance is found with the specified key.
+ =back
+ =cut
+ sub GetEntity {
+     # Get the parameters.
+     my ($self, $entityType, $ID) = @_;
+     # Create a query.
+     my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);
+     # Get the first (and only) object.
+     my $retVal = $query->Fetch();
+     # Return the result.
+     return $retVal;
+ }
+ =head3 GetChoices
+ C<< my @values = $erdb->GetChoices($entityName, $fieldName); >>
+ Return a list of all the values for the specified field that are represented in the
+ specified entity.
+ Note that if the field is not indexed, then this will be a very slow operation.
+ =over 4
+ =item entityName
+ Name of an entity in the database.
+ =item fieldName
+ Name of a field belonging to the entity. This is a raw field name without
+ the standard parenthesized notation used in most calls.
+ =item RETURN
+ Returns a list of the distinct values for the specified field in the database.
+ =back
+ =cut
+ sub GetChoices {
+     # Get the parameters.
+     my ($self, $entityName, $fieldName) = @_;
+     # Declare the return variable.
+     my @retVal;
+     # Get the entity data structure.
+     my $entityData = $self->_GetStructure($entityName);
+     # Get the field.
+     my $fieldHash = $entityData->{Fields};
+     if (! exists $fieldHash->{$fieldName}) {
+         Confess("$fieldName not found in $entityName.");
+     } else {
+         # Get the name of the relation containing the field.
+         my $relation = $fieldHash->{$fieldName}->{relation};
+         # Fix up the field name.
+         my $realName = _FixName($fieldName);
+         # Get the database handle.
+         my $dbh = $self->{_dbh};
+         # Query the database.
+         my $results = $dbh->SQL("SELECT DISTINCT $realName FROM $relation");
+         # Clean the results. They are stored as a list of lists, and we just want the one list.
+         @retVal = sort map { $_->[0] } @{$results};
+     }
+     # Return the result.
+     return @retVal;
+ }
+ =head3 GetEntityValues
+ C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>
+ Return a list of values from a specified entity instance. If the entity instance
+ does not exist, an empty list is returned.
+ =over 4
+ =item entityType
+ Entity type name.
+ =item ID
+ ID of the desired entity.
+ =item fields
+ List of field names, each of the form I<objectName>C<(>I<fieldName>C<)>.
+ =item RETURN
+ Returns a flattened list of the values of the specified fields for the specified entity.
+ =back
+ =cut
+ sub GetEntityValues {
+     # Get the parameters.
+     my ($self, $entityType, $ID, $fields) = @_;
+     # Get the specified entity.
+     my $entity = $self->GetEntity($entityType, $ID);
+     # Declare the return list.
+     my @retVal = ();
+     # If we found the entity, push the values into the return list.
+     if ($entity) {
+         push @retVal, $entity->Values($fields);
+     }
+     # Return the result.
+     return @retVal;
+ }
+ =head3 GetAll
+ C<< my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>
+ Return a list of values taken from the objects returned by a query. The first three
+ parameters correspond to the parameters of the L</Get> method. The final parameter is
+ a list of the fields desired from each record found by the query. The field name
+ syntax is the standard syntax used for fields in the B<ERDB> system--
+ B<I<objectName>(I<fieldName>)>-- where I<objectName> is the name of the relevant entity
+ or relationship and I<fieldName> is the name of the field.
+ The list returned will be a list of lists. Each element of the list will contain
+ the values returned for the fields specified in the fourth parameter. If one of the
+ fields specified returns multiple values, they are flattened in with the rest. For
+ example, the following call will return a list of the features in a particular
+ spreadsheet cell, and each feature will be represented by a list containing the
+ feature ID followed by all of its aliases.
+ C<< $query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>
+ =over 4
+ =item objectNames
+ List containing the names of the entity and relationship objects to be retrieved.
+ =item filterClause
+ WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
+ be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
+ B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
+ parameter list as additional parameters. The fields in a filter clause can come from primary
+ entity relations, relationship relations, or secondary entity relations; however, all of the
+ entities and relationships involved must be included in the list of object names.
+ =item parameterList
+ List of the parameters to be substituted in for the parameters marks in the filter clause.
+ =item fields
+ List of the fields to be returned in each element of the list returned.
+ =item count
+ Maximum number of records to return. If omitted or 0, all available records will be returned.
+ =item RETURN
+ Returns a list of list references. Each element of the return list contains the values for the
+ fields specified in the B<fields> parameter.
+ =back
+ =cut
+ #: Return Type @@;
+ sub GetAll {
+     # Get the parameters.
+     my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
+     # Translate the parameters from a list reference to a list. If the parameter
+     # list is a scalar we convert it into a singleton list.
+     my @parmList = ();
+     if (ref $parameterList eq "ARRAY") {
+         Trace("GetAll parm list is an array.") if T(4);
+         @parmList = @{$parameterList};
+     } else {
+         Trace("GetAll parm list is a scalar: $parameterList.") if T(4);
+         push @parmList, $parameterList;
+     }
+     # Insure the counter has a value.
+     if (!defined $count) {
+         $count = 0;
+     }
+     # Add the row limit to the filter clause.
+     if ($count > 0) {
+         $filterClause .= " LIMIT $count";
+     }
+     # Create the query.
+     my $query = $self->Get($objectNames, $filterClause, \@parmList);
+     # Set up a counter of the number of records read.
+     my $fetched = 0;
+     # Loop through the records returned, extracting the fields. Note that if the
+     # counter is non-zero, we stop when the number of records read hits the count.
+     my @retVal = ();
+     while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {
+         my @rowData = $row->Values($fields);
+         push @retVal, \@rowData;
+         $fetched++;
+     }
+     Trace("$fetched rows returned in GetAll.") if T(SQL => 4);
+     # Return the resulting list.
+     return @retVal;
+ }
+ =head3 Exists
+ C<< my $found = $sprout->Exists($entityName, $entityID); >>
+ Return TRUE if an entity exists, else FALSE.
+ =over 4
+ =item entityName
+ Name of the entity type (e.g. C<Feature>) relevant to the existence check.
+ =item entityID
+ ID of the entity instance whose existence is to be checked.
+ =item RETURN
+ Returns TRUE if the entity instance exists, else FALSE.
+ =back
+ =cut
+ #: Return Type $;
+ sub Exists {
+     # Get the parameters.
+     my ($self, $entityName, $entityID) = @_;
+     # Check for the entity instance.
+     Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
+     my $testInstance = $self->GetEntity($entityName, $entityID);
+     # Return an existence indicator.
+     my $retVal = ($testInstance ? 1 : 0);
+     return $retVal;
+ }
+ =head3 EstimateRowSize
+ C<< my $rowSize = $erdb->EstimateRowSize($relName); >>
+ Estimate the row size of the specified relation. The estimated row size is computed by adding
+ up the average length for each data type.
+ =over 4
+ =item relName
+ Name of the relation whose estimated row size is desired.
+ =item RETURN
+ Returns an estimate of the row size for the specified relation.
+ =back
+ =cut
+ #: Return Type $;
+ sub EstimateRowSize {
+     # Get the parameters.
+     my ($self, $relName) = @_;
+     # Declare the return variable.
+     my $retVal = 0;
+     # Find the relation descriptor.
+     my $relation = $self->_FindRelation($relName);
+     # Get the list of fields.
+     for my $fieldData (@{$relation->{Fields}}) {
+         # Get the field type and add its length.
+         my $fieldLen = $TypeTable{$fieldData->{type}}->{avgLen};
+         $retVal += $fieldLen;
+     }
+     # Return the result.
+     return $retVal;
+ }
+ =head3 GetFieldTable
+ C<< my $fieldHash = $self->GetFieldTable($objectnName); >>
+ Get the field structure for a specified entity or relationship.
+ =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};
+ }
+ =head2 Data Mining Methods
+ =head3 GetUsefulCrossValues
+ C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>
+ Return a list of the useful attributes that would be returned by a B<Cross> call
+ from an entity of the source entity type through the specified relationship. This
+ means it will return the fields of the target entity type and the intersection data
+ fields in the relationship. Only primary table fields are returned. In other words,
+ the field names returned will be for fields where there is always one and only one
+ value.
+ =over 4
+ =item sourceEntity
+ Name of the entity from which the relationship crossing will start.
+ =item relationship
+ Name of the relationship being crossed.
+ =item RETURN
+ Returns a list of field names in Sprout field format (I<objectName>C<(>I<fieldName>C<)>.
+ =back
+ =cut
+ #: Return Type @;
+ sub GetUsefulCrossValues {
+     # Get the parameters.
+     my ($self, $sourceEntity, $relationship) = @_;
+     # Declare the return variable.
+     my @retVal = ();
+     # Determine the target entity for the relationship. This is whichever entity is not
+     # the source entity. So, if the source entity is the FROM, we'll get the name of
+     # the TO, and vice versa.
+     my $relStructure = $self->_GetStructure($relationship);
+     my $targetEntityType = ($relStructure->{from} eq $sourceEntity ? "to" : "from");
+     my $targetEntity = $relStructure->{$targetEntityType};
+     # Get the field table for the entity.
+     my $entityFields = $self->GetFieldTable($targetEntity);
+     # The field table is a hash. The hash key is the field name. The hash value is a structure.
+     # For the entity fields, the key aspect of the target structure is that the {relation} value
+     # must match the entity name.
+     my @fieldList = map { "$targetEntity($_)" } grep { $entityFields->{$_}->{relation} eq $targetEntity }
+                         keys %{$entityFields};
+     # Push the fields found onto the return variable.
+     push @retVal, sort @fieldList;
+     # Get the field table for the relationship.
+     my $relationshipFields = $self->GetFieldTable($relationship);
+     # Here we have a different rule. We want all the fields other than "from-link" and "to-link".
+     # This may end up being an empty set.
+     my @fieldList2 = map { "$relationship($_)" } grep { $_ ne "from-link" && $_ ne "to-link" }
+                         keys %{$relationshipFields};
+     # Push these onto the return list.
+     push @retVal, sort @fieldList2;
+     # Return the result.
+     return @retVal;
+ }
+ =head3 FindColumn
+ C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>
+ Return the location a desired column in a data mining header line. The data
+ mining header line is a tab-separated list of column names. The column
+ identifier is either the numerical index of a column or the actual column
+ name.
+ =over 4
+ =item headerLine
+ The header line from a data mining command, which consists of a tab-separated
+ list of column names.
+ =item columnIdentifier
+ Either the ordinal number of the desired column (1-based), or the name of the
+ desired column.
+ =item RETURN
+ Returns the array index (0-based) of the desired column.
+ =back
+ =cut
+ sub FindColumn {
+     # Get the parameters.
+     my ($headerLine, $columnIdentifier) = @_;
+     # Declare the return variable.
+     my $retVal;
+     # Split the header line into column names.
+     my @headers = ParseColumns($headerLine);
+     # Determine whether we have a number or a name.
+     if ($columnIdentifier =~ /^\d+$/) {
+         # Here we have a number. Subtract 1 and validate the result.
+         $retVal = $columnIdentifier - 1;
+         if ($retVal < 0 || $retVal > $#headers) {
+             Confess("Invalid column identifer \"$columnIdentifier\": value out of range.");
+         }
+     } else {
+         # Here we have a name. We need to find it in the list.
+         for (my $i = 0; $i <= $#headers && ! defined($retVal); $i++) {
+             if ($headers[$i] eq $columnIdentifier) {
+                 $retVal = $i;
+             }
+         }
+         if (! defined($retVal)) {
+             Confess("Invalid column identifier \"$columnIdentifier\": value not found.");
+         }
+     }
+     # Return the result.
+     return $retVal;
+ }
+ =head3 ParseColumns
+ C<< my @columns = ERDB::ParseColumns($line); >>
+ Convert the specified data line to a list of columns.
+ =over 4
+ =item line
+ A data mining input, consisting of a tab-separated list of columns terminated by a
+ new-line.
- C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>
+ =item RETURN
- Return an object describing the entity instance with a specified ID.
+ Returns a list consisting of the column values.
- =over 4
+ =back
- =item entityType
+ =cut
- Entity type name.
+ sub ParseColumns {
+     # Get the parameters.
+     my ($line) = @_;
+     # Chop off the line-end.
+     chomp $line;
+     # Split it into a list.
+     my @retVal = split(/\t/, $line);
+     # Return the result.
+     return @retVal;
+ }
- =item ID
+ =head2 Virtual Methods
- ID of the desired entity.
+ =head3 CleanKeywords
+ C<< my $cleanedString = $erdb->CleanKeywords($searchExpression); >>
+ Clean up a search expression or keyword list. This is a virtual method that may
+ be overridden by the subclass. The base-class method removes extra spaces
+ and converts everything to lower case.
+ =over 4
+ =item searchExpression
+ Search expression or keyword list to clean. Note that a search expression may
+ contain boolean operators which need to be preserved. This includes leading
+ minus signs.
  =item RETURN
- Returns a B<DBObject> representing the desired entity instance, or an undefined value if no
+ Cleaned expression or keyword list.
- instance is found with the specified key.
  =back
  =cut
- sub GetEntity {
+ sub CleanKeywords {
      # Get the parameters.
-     my ($self, $entityType, $ID) = @_;
+     my ($self, $searchExpression) = @_;
-     # Create a query.
+     # Lower-case the expression and copy it into the return variable. Note that we insure we
-     my $query = $self->Get([$entityType], "$entityType(id) = ?", $ID);
+     # don't accidentally end up with an undefined value.
-     # Get the first (and only) object.
+     my $retVal = lc($searchExpression || "");
-     my $retVal = $query->Fetch();
+     # Remove extra spaces.
+     $retVal =~ s/\s+/ /g;
+     $retVal =~ s/(^\s+)|(\s+$)//g;
      # Return the result.
      return $retVal;
  }
- =head3 GetEntityValues
+ =head2 Internal Utility Methods
- C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>
- Return a list of values from a specified entity instance.
+ =head3 _RelationMap
- =over 4
+ C<< my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef); >>
- =item entityType
+ Create the relation map for an SQL query. The relation map is used by B<DBObject>
+ to determine how to interpret the results of the query.
- Entity type name.
+ =over 4
- =item ID
+ =item mappedNameHashRef
- ID of the desired entity.
+ Reference to a hash that maps modified object names to real object names.
- =item fields
+ =item mappedNameListRef
- List of field names, each of the form I<objectName>C<(>I<fieldName>C<)>.
+ Reference to a list of modified object names in the order they appear in the
+ SELECT list.
  =item RETURN
- Returns a flattened list of the values of the specified fields for the specified entity.
+ Returns a list of 2-tuples. Each tuple consists of an object name as used in the
+ query followed by the actual name of that object. This enables the B<DBObject> to
+ determine the order of the tables in the query and which object name belongs to each
+ mapped object name. Most of the time these two values are the same; however, if a
+ relation occurs twice in the query, the relation name in the field list and WHERE
+ clause will use a mapped name (generally the actual relation name with a numeric
+ suffix) that does not match the actual relation name.
  =back
  =cut
- sub GetEntityValues {
+ sub _RelationMap {
      # Get the parameters.
-     my ($self, $entityType, $ID, $fields) = @_;
+     my ($mappedNameHashRef, $mappedNameListRef) = @_;
-     # Get the specified entity.
+     # Declare the return variable.
-     my $entity = $self->GetEntity($entityType, $ID);
-     # Declare the return list.
      my @retVal = ();
-     # If we found the entity, push the values into the return list.
+     # Build the map.
-     if ($entity) {
+     for my $mappedName (@{$mappedNameListRef}) {
-         push @retVal, $entity->Values($fields);
+         push @retVal, [$mappedName, $mappedNameHashRef->{$mappedName}];
      }
-     # Return the result.
+     # Return it.
      return @retVal;
  }
- =head3 GetAll
- C<< my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>
- Return a list of values taken from the objects returned by a query. The first three
+ =head3 _SetupSQL
- parameters correspond to the parameters of the L</Get> method. The final parameter is
- a list of the fields desired from each record found by the query. The field name
- syntax is the standard syntax used for fields in the B<ERDB> system--
- B<I<objectName>(I<fieldName>)>-- where I<objectName> is the name of the relevant entity
- or relationship and I<fieldName> is the name of the field.
- The list returned will be a list of lists. Each element of the list will contain
+ Process a list of object names and a filter clause so that they can be used to
- the values returned for the fields specified in the fourth parameter. If one of the
+ build an SQL statement. This method takes in a reference to a list of object names
- fields specified returns multiple values, they are flattened in with the rest. For
+ and a filter clause. It will return a corrected filter clause, a list of mapped
- example, the following call will return a list of the features in a particular
+ names and the mapped name hash.
- spreadsheet cell, and each feature will be represented by a list containing the
- feature ID followed by all of its aliases.
- C<< $query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>
+ This is an instance method.
  =over 4
  =item objectNames
- List containing the names of the entity and relationship objects to be retrieved.
+ Reference to a list of the object names to be included in the query.
  =item filterClause
- WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
+ A string containing the WHERE clause for the query (without the C<WHERE>) and also
- be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
+ optionally the C<ORDER BY> and C<LIMIT> clauses.
- B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
- parameter list as additional parameters. The fields in a filter clause can come from primary
- entity relations, relationship relations, or secondary entity relations; however, all of the
- entities and relationships involved must be included in the list of object names.
- =item parameterList
- List of the parameters to be substituted in for the parameters marks in the filter clause.
- =item fields
- List of the fields to be returned in each element of the list returned.
- =item count
+ =item matchClause
- Maximum number of records to return. If omitted or 0, all available records will be returned.
+ An optional full-text search clause. If specified, it will be inserted at the
+ front of the WHERE clause. It should already be SQL-formatted; that is, the
+ field names should be in the form I<table>C<.>I<fieldName>.
  =item RETURN
- Returns a list of list references. Each element of the return list contains the values for the
+ Returns a three-element list. The first element is the SQL statement suffix, beginning
- fields specified in the B<fields> parameter.
+ with the FROM clause. The second element is a reference to a list of the names to be
+ used in retrieving the fields. The third element is a hash mapping the names to the
+ objects they represent.
  =back
  =cut
- #: Return Type @@;
- sub GetAll {
+ sub _SetupSQL {
-     # Get the parameters.
+     my ($self, $objectNames, $filterClause, $matchClause) = @_;
-     my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
+     # Adjust the list of object names to account for multiple occurrences of the
-     # Translate the parameters from a list reference to a list. If the parameter
+     # same object. We start with a hash table keyed on object name that will
-     # list is a scalar we convert it into a singleton list.
+     # return the object suffix. The first time an object is encountered it will
-     my @parmList = ();
+     # not be found in the hash. The next time the hash will map the object name
-     if (ref $parameterList eq "ARRAY") {
+     # to 2, then 3, and so forth.
-         @parmList = @{$parameterList};
+     my %objectHash = ();
+     # This list will contain the object names as they are to appear in the
+     # 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 {
-         push @parmList, $parameterList;
+             # 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;
      }
-     # Create the query.
-     my $query = $self->Get($objectNames, $filterClause, @parmList);
-     # Set up a counter of the number of records read.
-     my $fetched = 0;
-     # Insure the counter has a value.
-     if (!defined $count) {
-         $count = 0;
      }
-     # Loop through the records returned, extracting the fields. Note that if the
+     # Begin the SELECT suffix. It starts with
-     # counter is non-zero, we stop when the number of records read hits the count.
+     #
-     my @retVal = ();
+     # FROM name1, name2, ... nameN
-     while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {
+     #
-         my @rowData = $row->Values($fields);
+     my $suffix = "FROM " . join(', ', @fromList);
-         push @retVal, \@rowData;
+     # Now for the WHERE. First, we need a place for the filter string.
-         $fetched++;
+     my $filterString = "";
+     # We will also keep a list of conditions to add to the WHERE clause in order to link
+     # entities and relationships as well as primary relations to secondary ones.
+     my @joinWhere = ();
+     # Check for a filter clause.
+     if ($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.
+         $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;
+         # 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.
+                             $suffix .= ", $relationName";
+                             push @joinWhere, "$objectName.id = $relationName.id";
+                         } else {
+                             # Here we have a mapping situation.
+                             $suffix .= ", $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;
+                 }
      }
-     # Return the resulting list.
+         }
-     return @retVal;
+     }
+     # 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, because we shift off the first object before
+     # processing the rest.
+     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 $orderClause = "";
+     # This is only necessary if we have a filter string in which the ORDER BY
+     # and LIMIT clauses can live.
+     if ($filterString) {
+         # 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 = $1;
+         }
+     }
+     # All the things that are supposed to be in the WHERE clause of the
+     # SELECT command need to be put into @joinWhere so we can string them
+     # together. We begin with the match clause. This is important,
+     # because the match clause's parameter mark must precede any parameter
+     # marks in the filter string.
+     if ($matchClause) {
+         push @joinWhere, $matchClause;
+     }
+     # Add the filter string. We put it in parentheses to avoid operator
+     # precedence problems with the match clause or the joins.
+     if ($filterString) {
+         Trace("Filter string is \"$filterString\".") if T(4);
+         push @joinWhere, "($filterString)";
+     }
+     # String it all together into a big filter clause.
+     if (@joinWhere) {
+         $suffix .= " WHERE " . join(' AND ', @joinWhere);
+     }
+     # Add the sort or limit clause (if any).
+     if ($orderClause) {
+         $suffix .= " $orderClause";
+     }
+     # Return the suffix, the mapped name list, and the mapped name hash.
+     return ($suffix, \@mappedNameList, \%mappedNameHash);
  }
- =head3 EstimateRowSize
+ =head3 _GetStatementHandle
- C<< my $rowSize = $erdb->EstimateRowSize($relName); >>
+ This method will prepare and execute an SQL query, returning the statement handle.
+ The main reason for doing this here is so that everybody who does SQL queries gets
+ the benefit of tracing.
- Estimate the row size of the specified relation. The estimated row size is computed by adding
+ This is an instance method.
- up the average length for each data type.
  =over 4
- =item relName
+ =item command
- Name of the relation whose estimated row size is desired.
+ Command to prepare and execute.
+ =item params
+ Reference to a list of the values to be substituted in for the parameter marks.
  =item RETURN
- Returns an estimate of the row size for the specified relation.
+ Returns a prepared and executed statement handle from which the caller can extract
+ results.
  =back
  =cut
- #: Return Type $;
- sub EstimateRowSize {
+ sub _GetStatementHandle {
      # Get the parameters.
-     my ($self, $relName) = @_;
+     my ($self, $command, $params) = @_;
-     # Declare the return variable.
+     # Trace the query.
-     my $retVal = 0;
+     Trace("SQL query: $command") if T(SQL => 3);
-     # Find the relation descriptor.
+     Trace("PARMS: '" . (join "', '", @{$params}) . "'") if (T(SQL => 4) && (@{$params} > 0));
-     my $relation = $self->_FindRelation($relName);
+     # Get the database handle.
-     # Get the list of fields.
+     my $dbh = $self->{_dbh};
-     for my $fieldData (@{$relation->{Fields}}) {
+     # Prepare the command.
-         # Get the field type and add its length.
+     my $sth = $dbh->prepare_command($command);
-         my $fieldLen = $TypeTable{$fieldData->{type}}->{avgLen};
+     # Execute it with the parameters bound in.
-         $retVal += $fieldLen;
+     $sth->execute(@{$params}) || Confess("SELECT error" . $sth->errstr());
-     }
+     # Return the statement handle.
-     # Return the result.
+     return $sth;
-     return $retVal;
  }
- =head2 Internal Utility Methods
+ =head3 _GetLoadStats
- =head3 GetLoadStats
  Return a blank statistics object for use by the load methods.
-Line 1636
+Line 2983
  =cut
  sub _GetLoadStats {
-     return Stats->new('records');
+     return Stats->new();
  }
- =head3 GenerateFields
+ =head3 _GenerateFields
  Generate field values from a field structure and store in a specified table. The field names
  are first sorted by pass count, certain pre-defined fields are removed from the list, and
-Line 1713
+Line 3060
      }
  }
- =head3 DumpRelation
+ =head3 _DumpRelation
  Dump the specified relation's to the specified output file in tab-delimited format.
-Line 1763
+Line 3110
      close DTXOUT;
  }
- =head3 GetStructure
+ =head3 _GetStructure
  Get the data structure for a specified entity or relationship.
-Line 1802
+Line 3149
      return $retVal;
  }
- =head3 GetRelationTable
+ =head3 _GetRelationTable
  Get the list of relations for a specified entity or relationship.
-Line 1831
+Line 3180
      return $objectData->{Relations};
  }
- =head3 GetFieldTable
+ =head3 _ValidateFieldNames
- Get the field structure for a specified entity or relationship.
- This is an instance method.
- =over 4
- =item objectName
- Name of the desired entity or relationship.
- =item RETURN
- The table containing the field descriptors for the specified object.
- =back
- =cut
- sub _GetFieldTable {
-     # Get the parameters.
-     my ($self, $objectName) = @_;
-     # Get the descriptor from the metadata.
-     my $objectData = $self->_GetStructure($objectName);
-     # Return the object's field table.
-     return $objectData->{Fields};
- }
- =head3 ValidateFieldNames
  Determine whether or not the field names are valid. A description of the problems with the names
  will be written to the standard error output. If there is an error, this method will abort. This is
-Line 1915
+Line 3235
      }
  }
- =head3 LoadRelation
+ =head3 _LoadRelation
  Load a relation from the data in a tab-delimited disk file. The load will only take place if a disk
  file with the same name as the relation exists in the specified directory.
-Line 1975
+Line 3295
      return $retVal;
  }
- =head3 LoadMetaData
+ =head3 _LoadMetaData
  This method loads the data describing this database from an XML file into a metadata structure.
  The resulting structure is a set of nested hash tables containing all the information needed to
-Line 2213
+Line 3533
              # Determine if this relationship has our entity in one of its link fields.
              my $fromEntity = $relationship->{from};
              my $toEntity = $relationship->{to};
-             Trace("Join check for relationship $relationshipName from $fromEntity to $toEntity.") if T(4);
+             Trace("Join check for relationship $relationshipName from $fromEntity to $toEntity.") if T(Joins => 4);
              if ($fromEntity eq $entityName) {
                  if ($toEntity eq $entityName) {
                      # Here the relationship is recursive.
-Line 2302
+Line 3622
      return $metadata;
  }
- =head3 CreateRelationshipIndex
+ =head3 _CreateRelationshipIndex
  Create an index for a relationship's relation.
-Line 2347
+Line 3667
      _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);
  }
- =head3 AddIndex
+ =head3 _AddIndex
  Add an index to a relation structure.
-Line 2393
+Line 3713
      $relationStructure->{Indexes}->{$indexName} = $newIndex;
  }
- =head3 FixupFields
+ =head3 _FixupFields
  This method fixes the field list for an entity or relationship. It will add the caller-specified
  relation name to fields that do not have a name and set the C<PrettySort> value as specified.
-Line 2431
+Line 3751
          # Here it doesn't, so we create a new one.
          $structure->{Fields} = { };
      } else {
-         # Here we have a field list. Loop through its fields.
+         # Here we have a field list. We need to track the searchable fields, so we
+         # create a list for stashing them.
+         my @textFields = ();
+         # Loop through the fields.
          my $fieldStructures = $structure->{Fields};
          for my $fieldName (keys %{$fieldStructures}) {
              Trace("Processing field $fieldName of $defaultRelationName.") if T(4);
-Line 2445
+Line 3768
                  # The data generator will use the default for the field's type.
                  $fieldData->{DataGen} = { content => $TypeTable{$type}->{dataGen} };
              }
+             # Check for searchability.
+             if ($fieldData->{searchable}) {
+                 # Only allow this for a primary relation.
+                 if ($fieldData->{relation} ne $defaultRelationName) {
+                     Confess("Field $fieldName of $defaultRelationName is in secondary relations and cannot be searchable.");
+                 } else {
+                     push @textFields, $fieldName;
+                 }
+             }
              # Plug in the defaults for the optional data generation parameters.
              Tracer::MergeOptions($fieldData->{DataGen}, { testCount => 1, pass => 0 });
              # Add the PrettySortValue.
              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);
          }
+         # If there are searchable fields, remember the fact.
+         if (@textFields) {
+             $structure->{searchFields} = \@textFields;
+         }
      }
  }
- =head3 FixName
+ =head3 _FixName
  Fix the incoming field name so that it is a legal SQL column name.
-Line 2482
+Line 3818
      return $fieldName;
  }
- =head3 FixNames
+ =head3 _FixNames
  Fix all the field names in a list.
-Line 2513
+Line 3849
      return @result;
  }
- =head3 AddField
+ =head3 _AddField
  Add a field to a field list.
-Line 2548
+Line 3884
      $fieldList->{$fieldName} = $fieldStructure;
  }
- =head3 ReOrderRelationTable
+ =head3 _ReOrderRelationTable
  This method will take a relation table and re-sort it according to the implicit ordering of the
  C<PrettySort> property. Instead of a hash based on field names, it will return a list of fields.
-Line 2609
+Line 3945
  }
- =head3 IsPrimary
+ =head3 _IsPrimary
  Return TRUE if a specified relation is a primary relation, else FALSE. A relation is primary
  if it has the same name as an entity or relationship.
-Line 2645
+Line 3981
      return $retVal;
  }
- =head3 FindRelation
+ =head3 _FindRelation
  Return the descriptor for the specified relation.
-Line 2676
+Line 4012
  =head2 HTML Documentation Utility Methods
- =head3 ComputeRelationshipSentence
+ =head3 _ComputeRelationshipSentence
  The relationship sentence consists of the relationship name between the names of the
  two related entities and an arity indicator.
-Line 2714
+Line 4050
      return $result;
  }
- =head3 ComputeRelationshipHeading
+ =head3 _ComputeRelationshipHeading
  The relationship heading is the L<relationship sentence|/ComputeRelationshipSentence> with the entity
  names hyperlinked to the appropriate entity sections of the document.
-Line 2751
+Line 4087
      return $result;
  }
- =head3 ShowRelationTable
+ =head3 _ShowRelationTable
  Generate the HTML string for a particular relation. The relation's data will be formatted as an HTML
  table with three columns-- the field name, the field type, and the field description.
-Line 2812
+Line 4148
      $htmlString .= "</ul>\n";
  }
- =head3 OpenFieldTable
+ =head3 _OpenFieldTable
  This method creates the header string for the field table generated by L</ShowMetaData>.
-Line 2837
+Line 4173
      return _OpenTable($tablename, 'Field', 'Type', 'Description');
  }
- =head3 OpenTable
+ =head3 _OpenTable
  This method creates the header string for an HTML table.
-Line 2877
+Line 4213
      return $htmlString;
  }
- =head3 CloseTable
+ =head3 _CloseTable
  This method returns the HTML for closing a table.
-Line 2889
+Line 4225
      return "</table></p>\n";
  }
- =head3 ShowField
+ =head3 _ShowField
  This method returns the HTML for displaying a row of field information in a field table.
-Line 2924
+Line 4260
      return $htmlString;
  }
- =head3 HTMLNote
+ =head3 _HTMLNote
  Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
  supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.

 Legend:



Removed from v.1.27
 


changed lines


 
Added in v.1.71
 Legend:



Removed from v.1.27
 


changed lines


 
Added in v.1.71
-Removed from v.1.27
+Added in v.1.71

MCS Webmaster	ViewVC Help
Powered by ViewVC 1.0.3