Diff of /Sprout/ERDB.pm

-revision 1.76, Wed Nov 15 12:08:26 2006 UTC
+revision 1.94, Thu Dec  6 14:58:03 2007 UTC
 Line 6
      use Data::Dumper;
      use XML::Simple;
      use DBQuery;
-     use DBObject;
+     use ERDBObject;
      use Stats;
      use Time::HiRes qw(gettimeofday);
      use Digest::MD5 qw(md5_base64);
-     use FIG;
      use CGI;
  =head1 Entity-Relationship Database Package
-Line 228
+Line 227
  =head3 Indexes
- An entity can have multiple alternate indexes associated with it. The fields must
+ An entity can have multiple alternate indexes associated with it. The fields in an
- all be from the same relation. The alternate indexes assist in ordering results
+ index must all be from the same relation. The alternate indexes assist in searching
- from a query. A relationship can have up to two indexes-- a I<to-index> and a
+ on fields other than the entity ID. A relationship has at least two indexes-- a I<to-index> and a
- I<from-index>. These order the results when crossing the relationship. For
+ I<from-index> that order the results when crossing the relationship. For
  example, in the relationship C<HasContig> from C<Genome> to C<Contig>, the
  from-index would order the contigs of a ganome, and the to-index would order
- the genomes of a contig. A relationship's index must specify only fields in
+ the genomes of a contig. In addition, it can have zero or more alternate
+ indexes. A relationship's index must specify only fields in
  the relationship.
- The indexes for an entity must be listed inside the B<Indexes> tag. The from-index
+ The alternate indexes for an entity or relationship must be listed inside the B<Indexes> tag.
- of a relationship is specified using the B<FromIndex> tag; the to-index is specified
+ The from-index of a relationship is specified using the B<FromIndex> tag; the to-index is
- using the B<ToIndex> tag.
+ specified using the B<ToIndex> tag.
  Each index can contain a B<Notes> tag. In addition, it will have an B<IndexFields>
  tag containing the B<IndexField> tags. These specify, in order, the fields used in
 Line 257
  =back
- The B<Index>, B<FromIndex>, and B<ToIndex> tags themselves have no attributes.
+ The B<FromIndex>, and B<ToIndex> tags have no attributes. The B<Index> tag can
+ have a B<Unique> attribute. If specified, the index will be generated as a unique
+ index.
  =head3 Object and Field Names
-Line 301
+Line 303
  A relationship is described by the C<Relationship> tag. Within a relationship,
  there can be a C<Notes> tag, a C<Fields> tag containing the intersection data
- fields, a C<FromIndex> tag containing the from-index, and a C<ToIndex> tag containing
+ fields, a C<FromIndex> tag containing the from-index, a C<ToIndex> tag containing
- the to-index.
+ the to-index, and an C<Indexes> tag containing the alternate indexes.
  The C<Relationship> tag has the following attributes.
-Line 370
+Line 372
                   'medium-string' =>
                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",
                                 indexMod =>   0, notes => "character string, 0 to 160 characters"},
+                  'long-string' =>
+                              { sqlType => 'VARCHAR(500)',       maxLen => 500,          avglen => 255, sort => "",
+                                indexMod =>   0, notes => "character string, 0 to 500 characters"},
                  );
  # Table translating arities into natural language.
-Line 394
+Line 399
                   );
  my %XmlInOpts  = (
-                   ForceArray => ['Field', 'Index', 'IndexField'],
+                   ForceArray => ['Field', 'Index', 'IndexField', 'Relationship', 'Entity'],
                    ForceContent => 1,
                    NormalizeSpace => 2,
                   );
-Line 408
+Line 413
  =head3 new
- C<< my $database = ERDB->new($dbh, $metaFileName); >>
+     my $database = ERDB->new($dbh, $metaFileName);
  Create a new ERDB object.
-Line 442
+Line 447
  =head3 ShowMetaData
- C<< $erdb->ShowMetaData($fileName); >>
+     $erdb->ShowMetaData($fileName);
  This method outputs a description of the database. This description can be used to help users create
  the data to be loaded into the relations.
-Line 483
+Line 488
  =head3 DisplayMetaData
- C<< my $html = $erdb->DisplayMetaData(); >>
+     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
-Line 546
+Line 551
          if (my $notes = $entityData->{Notes}) {
              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
          }
-         # Now we want a list of the entity's relationships. First, we set up the relationship subsection.
+         # See if we need a list of the entity's relationships.
+         my $relCount = keys %{$relationshipList};
+         if ($relCount > 0) {
+             # First, we set up the relationship subsection.
          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
          # Loop through the relationships.
          for my $relationship (sort keys %{$relationshipList}) {
-Line 562
+Line 570
          }
          # Close off the relationship list.
          $retVal .= "</ul>\n";
+         }
          # Get the entity's relations.
          my $relationList = $entityData->{Relations};
          # Create a header for the relation subsection.
-Line 635
+Line 644
  =head3 DumpMetaData
- C<< $erdb->DumpMetaData(); >>
+     $erdb->DumpMetaData();
  Return a dump of the metadata structure.
-Line 648
+Line 657
      return Data::Dumper::Dumper($self->{_metaData});
  }
+ =head3 CreatePPO
+     ERDB::CreatePPO($erdbXMLFile, $ppoXMLFile);
+ Create a PPO XML file from an ERDB data definition XML file. At the
+ current time, the PPO XML file can be used to create a database with
+ similar functionality. Eventually, the PPO will be able to use the
+ created XML to access the live ERDB database.
+ =over 4
+ =item erdbXMLFile
+ Name of the XML data definition file for the ERDB database. This
+ file must exist.
+ =item ppoXMLFile
+ Output file for the PPO XML definition. If this file exists, it
+ will be overwritten.
+ =back
+ =cut
+ sub CreatePPO {
+     # Get the parameters.
+     my ($erdbXMLFile, $ppoXMLFile) = @_;
+     # First, we want to slurp in the ERDB XML file in its raw form.
+     my $xml = ReadMetaXML($erdbXMLFile);
+     # Create a variable to hold all of the objects in the PPO project.
+     my @objects = ();
+     # Get the relationship hash.
+     my $relationships = $xml->{Relationships};
+     # Loop through the entities.
+     my $entities = $xml->{Entities};
+     for my $entityName (keys %{$entities}) {
+         # Get the entity's data structures.
+         my $entityObject = $entities->{$entityName};
+         # We put the object's fields in here, according to their type.
+         my (@object_refs, @scalars, @indexes, @arrays);
+         # Create the ID field for the entity. We get the key type from the
+         # entity object and compute the corresponding SQL type.
+         my $type = $TypeTable{$entityObject->{keyType}}->{sqlType};
+         push @scalars, { label => 'id', type => $type };
+         # Loop through the entity fields.
+         for my $fieldName ( keys %{$entityObject->{Fields}} ) {
+             # Get the field object.
+             my $fieldObject = $entityObject->{Fields}->{$fieldName};
+             # Convert it to a scalar tag.
+             my $scalar = _CreatePPOField($fieldName, $fieldObject);
+             # If we have a relation, this field is stored in an array.
+             # otherwise, it is a scalar. The array tag has scalars
+             # stored as an XML array. In ERDB, there is only ever one,
+             # but PPO can have more.
+             my $relation = $fieldObject->{relation};
+             if ($relation) {
+                 push @arrays, { scalar => [$scalar] };
+             } else {
+                 push @scalars, $scalar;
+             }
+         }
+         # Loop through the relationships. If this entity is the to-entity
+         # on a relationship of 1M arity, then it is implemented as a PPO
+         # object reference.
+         for my $relationshipName (keys %{$relationships}) {
+             # Get the relationship data.
+             my $relationshipData = $relationships->{$relationshipName};
+             # If we have a from for this entity and an arity of 1M, we
+             # have an object reference.
+             if ($relationshipData->{to} eq $entityName &&
+                 $relationshipData->{arity} eq '1M') {
+                 # Build the object reference tag.
+                 push @object_refs, { label => $relationshipName,
+                                      type => $relationshipData->{from} };
+             }
+         }
+         # Create the indexes.
+         my $indexList = $entityObject->{Indexes};
+         push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
+         # Build the object XML tree.
+         my $object = { label => $entityName,
+                        object_ref => \@object_refs,
+                        scalar => \@scalars,
+                        index => \@indexes,
+                        array => \@arrays
+                       };
+         # Push the object onto the objects list.
+         push @objects, $object;
+     }
+     # Loop through the relationships, searching for MMs. The 1Ms were
+     # already handled by the entity search above.
+     for my $relationshipName (keys %{$relationships}) {
+         # Get this relationship's object.
+         my $relationshipObject = $relationships->{$relationshipName};
+         # Only proceed if it's many-to-many.
+         if ($relationshipObject->{arity} eq 'MM') {
+             # Create the tag lists for the relationship object.
+             my (@object_refs, @scalars, @indexes);
+             # The relationship will be created as an object with object
+             # references for its links to the participating entities.
+             my %links = ( from_link => $relationshipObject->{from},
+                           to_link => $relationshipObject->{to} );
+             for my $link (keys %links) {
+                 # Create an object_ref tag for this piece of the
+                 # relationship (from or to).
+                 my $object_ref = { label => $link,
+                                    type => $links{$link} };
+                 push @object_refs, $object_ref;
+             }
+             # Loop through the intersection data fields, creating scalar tags.
+             # There are no fancy array tags in a relationship.
+             for my $fieldName (keys %{$relationshipObject->{Fields}}) {
+                 my $fieldObject = $relationshipObject->{Fields}->{$fieldName};
+                 push @scalars, _CreatePPOField($fieldName, $fieldObject);
+             }
+             # Finally, the indexes: currently we cannot support the to-index and
+             # from-index in PPO, so we just process the alternate indexes.
+             my $indexList = $relationshipObject->{Indexes};
+             push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
+             # Wrap up all the stuff about this relationship.
+             my $object = { label => $relationshipName,
+                            scalar => \@scalars,
+                            object_ref => \@object_refs,
+                            index => \@indexes
+                          };
+             # Push it into the object list.
+             push @objects, $object;
+         }
+     }
+     # Compute a title.
+     my $title;
+     if ($erdbXMLFile =~ /(\/|^)([^\/]+)DBD\.xml/) {
+         # Here we have a standard file name we can use for a title.
+         $title = $2;
+     } else {
+         # Here the file name is non-standard, so we carve up the
+         # database title.
+         $title = $xml->{Title}->{content};
+         $title =~ s/\s\.,//g;
+     }
+     # Wrap up the XML as a project.
+     my $ppoXML = { project => { label => $title,
+                                 object => \@objects }};
+     # Write out the results.
+     my $ppoString = XML::Simple::XMLout($ppoXML,
+                                         AttrIndent => 1,
+                                         KeepRoot => 1);
+     Tracer::PutFile($ppoXMLFile, [ $ppoString ]);
+ }
  =head3 FindIndexForEntity
- C<< my $indexFound = ERDB::FindIndexForEntity($xml, $entityName, $attributeName); >>
+     my $indexFound = ERDB::FindIndexForEntity($xml, $entityName, $attributeName);
  This method locates the entry in an entity's index list that begins with the
  specified attribute name. If the entity has no index list, one will be
-Line 720
+Line 880
  =head3 CreateTables
- C<< $erdb->CreateTables(); >>
+     $erdb->CreateTables();
  This method creates the tables for the database from the metadata structure loaded by the
  constructor. It is expected this function will only be used on rare occasions, when the
-Line 737
+Line 897
      # Loop through the relations.
      for my $relationName (@relNames) {
          # Create a table for this relation.
-         $self->CreateTable($relationName);
+         $self->CreateTable($relationName, 1);
          Trace("Relation $relationName created.") if T(2);
      }
  }
  =head3 CreateTable
- C<< $erdb->CreateTable($tableName, $indexFlag, $estimatedRows); >>
+     $erdb->CreateTable($tableName, $indexFlag, $estimatedRows);
  Create the table for a relation and optionally create its indexes.
-Line 800
+Line 960
      my $estimation = undef;
      if ($estimatedRows) {
          $estimation = [$self->EstimateRowSize($relationName), $estimatedRows];
+         Trace("$estimation->[1] rows of $estimation->[0] bytes each.") if T(3);
      }
      # Create the table.
      Trace("Creating table $relationName: $fieldThing") if T(2);
-Line 814
+Line 975
  =head3 VerifyFields
- C<< my $count = $erdb->VerifyFields($relName, \@fieldList); >>
+     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.
-Line 857
+Line 1018
              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);
+                 Trace("Truncating field $i ($fieldTypes->[$i]->{name}) in relation $relName to $maxLen characters from \"$oldString\".") if T(1);
                  $fieldList->[$i] = substr $oldString, 0, $maxLen;
                  $retVal++;
              }
-Line 869
+Line 1030
  =head3 DigestFields
- C<< $erdb->DigestFields($relName, $fieldList); >>
+     $erdb->DigestFields($relName, $fieldList);
  Digest the strings in the field list that correspond to data type C<hash-string> in the
  specified relation.
-Line 909
+Line 1070
  =head3 DigestKey
- C<< my $digested = $erdb->DigestKey($keyValue); >>
+     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.
-Line 942
+Line 1103
  =head3 CreateIndex
- C<< $erdb->CreateIndex($relationName); >>
+     $erdb->CreateIndex($relationName);
  Create the indexes for a relation. If a table is being loaded from a large source file (as
  is the case in L</LoadTable>), it is sometimes best to create the indexes after the load.
-Line 966
+Line 1127
          my @rawFields = @{$indexData->{IndexFields}};
          # Get a hash of the relation's field types.
          my %types = map { $_->{name} => $_->{type} } @{$relationData->{Fields}};
-         # We need to check for text fields. We need a append a length limitation for them. To do
+         # We need to check for text fields so we can append a length limitation for them. To do
          # that, we need the relation's field list.
          my $relFields = $relationData->{Fields};
          for (my $i = 0; $i <= $#rawFields; $i++) {
-Line 998
+Line 1159
  =head3 GetSecondaryFields
- C<< my %fieldTuples = $erdb->GetSecondaryFields($entityName); >>
+     my %fieldTuples = $erdb->GetSecondaryFields($entityName);
  This method will return a list of the name and type of each of the secondary
  fields for a specified entity. Secondary fields are stored in two-column tables
-Line 1039
+Line 1200
  =head3 GetFieldRelationName
- C<< my $name = $erdb->GetFieldRelationName($objectName, $fieldName); >>
+     my $name = $erdb->GetFieldRelationName($objectName, $fieldName);
  Return the name of the relation containing a specified field.
-Line 1080
+Line 1241
  =head3 DeleteValue
- C<< my $numDeleted = $erdb->DeleteValue($entityName, $id, $fieldName, $fieldValue); >>
+     my $numDeleted = $erdb->DeleteValue($entityName, $id, $fieldName, $fieldValue);
  Delete secondary field values from the database. This method can be used to delete all
  values of a specified field for a particular entity instance, or only a single value.
-Line 1163
+Line 1324
  =head3 LoadTables
- C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>
+     my $stats = $erdb->LoadTables($directoryName, $rebuild);
  This method will load the database tables from a directory. The tables must already have been created
  in the database. (This can be done by calling L</CreateTables>.) The caller passes in a directory name;
-Line 1223
+Line 1384
  =head3 GetTableNames
- C<< my @names = $erdb->GetTableNames; >>
+     my @names = $erdb->GetTableNames;
  Return a list of the relations required to implement this database.
-Line 1240
+Line 1401
  =head3 GetEntityTypes
- C<< my @names = $erdb->GetEntityTypes; >>
+     my @names = $erdb->GetEntityTypes;
  Return a list of the entity type names.
-Line 1257
+Line 1418
  =head3 GetDataTypes
- C<< my %types = ERDB::GetDataTypes(); >>
+     my %types = ERDB::GetDataTypes();
  Return a table of ERDB data types. The table returned is a hash of hashes.
  The keys of the big hash are the datatypes. Each smaller hash has several
-Line 1276
+Line 1437
  =head3 IsEntity
- C<< my $flag = $erdb->IsEntity($entityName); >>
+     my $flag = $erdb->IsEntity($entityName);
  Return TRUE if the parameter is an entity name, else FALSE.
-Line 1303
+Line 1464
  =head3 Get
- C<< my $query = $erdb->Get(\@objectNames, $filterClause, \@params); >>
+     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 1311
+Line 1472
  following call requests all B<Genome> objects for the genus specified in the variable
  $genus.
- C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", [$genus]); >>
+     $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
- C<< $query = $erdb->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>
+     $query = $erdb->Get(['Genome'], "Genome(genus) = \'$genus\'");
  however, this version of the call would generate a syntax error if there were any quote
  characters inside the variable C<$genus>.
-Line 1328
+Line 1489
  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]); >>
+     $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.
-Line 1364
+Line 1525
  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)" >>
+     "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.
-Line 1377
+Line 1538
  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" >>
+     "Genome(genus) = ? ORDER BY Genome(species) LIMIT 10"
  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" >>
+     "LIMIT 10"
  =item params
-Line 1404
+Line 1565
      my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
          $self->_SetupSQL($objectNames, $filterClause);
      # Create the query.
-     my $command = "SELECT DISTINCT " . join(".*, ", @{$mappedNameListRef}) .
+     my $command = "SELECT " . join(".*, ", @{$mappedNameListRef}) .
          ".* $suffix";
      my $sth = $self->_GetStatementHandle($command, $params);
      # Now we create the relation map, which enables DBQuery to determine the order, name
-Line 1418
+Line 1579
      return $retVal;
  }
  =head3 Search
- C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>
+     my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params);
  Perform a full text search with filtering. The search will be against a specified object
  in the object name list. That object will get an extra field containing the search
-Line 1489
+Line 1652
          my $actualKeywords = $self->CleanKeywords($searchExpression);
          # Prefix a "+" to each uncontrolled word. This converts the default
          # search mode from OR to AND.
-         $actualKeywords =~ s/(^|\s)(\w)/$1\+$2/g;
+         $actualKeywords =~ s/(^|\s)(\w|")/$1\+$2/g;
          Trace("Actual keywords for search are\n$actualKeywords") if T(3);
          # 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
-Line 1503
+Line 1666
              $self->_SetupSQL($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}) .
+         my $command = "SELECT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .
              ".* $suffix";
          my $sth = $self->_GetStatementHandle($command, \@myParams);
          # Now we create the relation map, which enables DBQuery to determine the order, name
-Line 1517
+Line 1680
  =head3 GetFlat
- C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>
+     my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field);
  This is a variation of L</GetAll> that asks for only a single field per record and
  returns a single flattened list.
-Line 1570
+Line 1733
  =head3 SpecialFields
- C<< my %specials = $erdb->SpecialFields($entityName); >>
+     my %specials = $erdb->SpecialFields($entityName);
  Return a hash mapping special fields in the specified entity to the value of their
  C<special> attribute. This enables the subclass to get access to the special field
-Line 1612
+Line 1775
  =head3 Delete
- C<< my $stats = $erdb->Delete($entityName, $objectID); >>
+     my $stats = $erdb->Delete($entityName, $objectID, %options);
  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
+ relationship instances dependent on it. The definition of I<dependence> is recursive.
- 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
+ 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 if it is the "to" entity connected to a 1-to-many
  dependent relationship.
  =over 4
-Line 1631
+Line 1795
  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
+ =item options
- If TRUE, the delete statements will be traced without being executed.
+ A hash detailing the options for this delete operation.
  =item RETURN
-Line 1642
+Line 1806
  =back
+ The permissible options for this method are as follows.
+ =over 4
+ =item testMode
+ If TRUE, then the delete statements will be traced, but no changes will be made to the database.
+ =item keepRoot
+ If TRUE, then the entity instances will not be deleted, only the dependent records.
+ =back
  =cut
  #: Return Type $%;
  sub Delete {
      # Get the parameters.
-     my ($self, $entityName, $objectID, $testFlag) = @_;
+     my ($self, $entityName, $objectID, %options) = @_;
      # Declare the return variable.
      my $retVal = Stats->new();
      # Get the DBKernel object.
-Line 1663
+Line 1841
      # FROM-relationships and entities.
      my @fromPathList = ();
      my @toPathList = ();
-     # This final hash is used to remember what work still needs to be done. We push paths
+     # This final list is used to remember what work still needs to be done. We push paths
      # onto the list, then pop them off to extend the paths. We prime it with the starting
      # point. Note that we will work hard to insure that the last item on a path in the
      # to-do list is always an entity.
-Line 1674
+Line 1852
          # Copy it into a list.
          my @stackedPath = @{$current};
          # Pull off the last item on the path. It will always be an entity.
-         my $entityName = pop @stackedPath;
+         my $myEntityName = pop @stackedPath;
          # Add it to the alreadyFound list.
-         $alreadyFound{$entityName} = 1;
+         $alreadyFound{$myEntityName} = 1;
+         # Figure out if we need to delete this entity.
+         if ($myEntityName ne $entityName || ! $options{keepRoot}) {
          # Get the entity data.
-         my $entityData = $self->_GetStructure($entityName);
+             my $entityData = $self->_GetStructure($myEntityName);
-         # The first task is to loop through the entity's relation. A DELETE command will
+             # Loop through the entity's relations. A DELETE command will be needed for each of them.
-         # 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 $entityName) {
+             if ($relationship->{from} eq $myEntityName) {
                  # Add the path to this relationship.
-                 my @augmentedList = (@stackedPath, $entityName, $relationshipName);
+                 my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
                  push @fromPathList, \@augmentedList;
                  # Check the arity. If it's MM we're done. If it's 1M
                  # and the target hasn't been seen yet, we want to
-Line 1712
+Line 1892
              }
              # Now check the TO field. In this case only the relationship needs
              # deletion.
-             if ($relationship->{to} eq $entityName) {
+             if ($relationship->{to} eq $myEntityName) {
-                 my @augmentedList = (@stackedPath, $entityName, $relationshipName);
+                 my @augmentedList = (@stackedPath, $myEntityName, $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
+     # from a dependent table, we construct a join path 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
-Line 1759
+Line 1939
                  }
              }
              # Now we have our desired DELETE statement.
-             if ($testFlag) {
+             if ($options{testMode}) {
                  # 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
+                 # Here we can delete. Note that the SQL method dies with a confession
                  # 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);
-Line 1778
+Line 1958
      return $retVal;
  }
+ =head3 Disconnect
+     $erdb->Disconnect($relationshipName, $originEntityName, $originEntityID);
+ Disconnect an entity instance from all the objects to which it is related. This
+ will delete each relationship instance that connects to the specified entity.
+ =over 4
+ =item relationshipName
+ Name of the relationship whose instances are to be deleted.
+ =item originEntityName
+ Name of the entity that is to be disconnected.
+ =item originEntityID
+ ID of the entity that is to be disconnected.
+ =back
+ =cut
+ sub Disconnect {
+     # Get the parameters.
+     my ($self, $relationshipName, $originEntityName, $originEntityID) = @_;
+     # Get the relationship descriptor.
+     my $structure = $self->_GetStructure($relationshipName);
+     # Insure we have a relationship.
+     if (! exists $structure->{from}) {
+         Confess("$relationshipName is not a relationship in the database.");
+     } else {
+         # Get the database handle.
+         my $dbh = $self->{_dbh};
+         # We'll set this value to 1 if we find our entity.
+         my $found = 0;
+         # Loop through the ends of the relationship.
+         for my $dir ('from', 'to') {
+             if ($structure->{$dir} eq $originEntityName) {
+                 # Delete all relationship instances on this side of the entity instance.
+                 Trace("Disconnecting in $dir direction with ID \"$originEntityID\".");
+                 $dbh->SQL("DELETE FROM $relationshipName WHERE ${dir}_link = ?", 0, $originEntityID);
+                 $found = 1;
+             }
+         }
+         # Insure we found the entity on at least one end.
+         if (! $found) {
+             Confess("Entity \"$originEntityName\" does not use $relationshipName.");
+         }
+     }
+ }
+ =head3 DeleteRow
+     $erdb->DeleteRow($relationshipName, $fromLink, $toLink, \%values);
+ Delete a row from a relationship. In most cases, only the from-link and to-link are
+ needed; however, for relationships with intersection data values can be specified
+ for the other fields using a hash.
+ =over 4
+ =item relationshipName
+ Name of the relationship from which the row is to be deleted.
+ =item fromLink
+ ID of the entity instance in the From direction.
+ =item toLink
+ ID of the entity instance in the To direction.
+ =item values
+ Reference to a hash of other values to be used for filtering the delete.
+ =back
+ =cut
+ sub DeleteRow {
+     # Get the parameters.
+     my ($self, $relationshipName, $fromLink, $toLink, $values) = @_;
+     # Create a hash of all the filter information.
+     my %filter = ('from-link' => $fromLink, 'to-link' => $toLink);
+     if (defined $values) {
+         for my $key (keys %{$values}) {
+             $filter{$key} = $values->{$key};
+         }
+     }
+     # Build an SQL statement out of the hash.
+     my @filters = ();
+     my @parms = ();
+     for my $key (keys %filter) {
+         push @filters, _FixName($key) . " = ?";
+         push @parms, $filter{$key};
+     }
+     Trace("Parms for delete row are " . join(", ", map { "\"$_\"" } @parms) . ".") if T(SQL => 4);
+     my $command = "DELETE FROM $relationshipName WHERE " .
+                   join(" AND ", @filters);
+     # Execute it.
+     my $dbh = $self->{_dbh};
+     $dbh->SQL($command, undef, @parms);
+ }
+ =head3 DeleteLike
+     my $deleteCount = $erdb->DeleteLike($relName, $filter, \@parms);
+ Delete all the relationship rows that satisfy a particular filter condition. Unlike a normal
+ filter, only fields from the relationship itself can be used.
+ =over 4
+ =item relName
+ Name of the relationship whose records are to be deleted.
+ =item filter
+ A filter clause (L</Get>-style) for the delete query.
+ =item parms
+ Reference to a list of parameters for the filter clause.
+ =item RETURN
+ Returns a count of the number of rows deleted.
+ =back
+ =cut
+ sub DeleteLike {
+     # Get the parameters.
+     my ($self, $objectName, $filter, $parms) = @_;
+     # Declare the return variable.
+     my $retVal;
+     # Insure the parms argument is an array reference if the caller left it off.
+     if (! defined($parms)) {
+         $parms = [];
+     }
+     # Insure we have a relationship. The main reason for this is if we delete an entity
+     # instance we have to yank out a bunch of other stuff with it.
+     if ($self->IsEntity($objectName)) {
+         Confess("Cannot use DeleteLike on $objectName, because it is not a relationship.");
+     } else {
+         # Create the SQL command suffix to get the desierd records.
+         my ($suffix) = $self->_SetupSQL([$objectName], $filter);
+         # Convert it to a DELETE command.
+         my $command = "DELETE $suffix";
+         # Execute the command.
+         my $dbh = $self->{_dbh};
+         my $result = $dbh->SQL($command, 0, @{$parms});
+         # Check the results. Note we convert the "0D0" result to a real zero.
+         # A failure causes an abnormal termination, so the caller isn't going to
+         # worry about it.
+         if (! defined $result) {
+             Confess("Error deleting from $objectName: " . $dbh->errstr());
+         } elsif ($result == 0) {
+             $retVal = 0;
+         } else {
+             $retVal = $result;
+         }
+     }
+     # Return the result count.
+     return $retVal;
+ }
  =head3 SortNeeded
- C<< my $parms = $erdb->SortNeeded($relationName); >>
+     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.
-Line 1878
+Line 2232
  =head3 GetList
- C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>
+     my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params);
  Return a list of object descriptors for the specified objects as determined by the
  specified filter clause.
-Line 1906
+Line 2260
  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)" >>
+     "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
-Line 1918
+Line 2272
  =item RETURN
- Returns a list of B<DBObject>s that satisfy the query conditions.
+ Returns a list of B<ERDBObject>s that satisfy the query conditions.
  =back
-Line 1941
+Line 2295
  =head3 GetCount
- C<< my $count = $erdb->GetCount(\@objectNames, $filter, \@params); >>
+     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
-Line 2034
+Line 2388
  =head3 ComputeObjectSentence
- C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>
+     my $sentence = $erdb->ComputeObjectSentence($objectName);
  Check an object name, and if it is a relationship convert it to a relationship sentence.
-Line 2069
+Line 2423
  =head3 DumpRelations
- C<< $erdb->DumpRelations($outputDirectory); >>
+     $erdb->DumpRelations($outputDirectory);
  Write the contents of all the relations to tab-delimited files in the specified directory.
  Each file will have the same name as the relation dumped, with an extension of DTX.
-Line 2111
+Line 2465
  =head3 InsertValue
- C<< $erdb->InsertValue($entityID, $fieldName, $value); >>
+     $erdb->InsertValue($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:
-Line 2174
+Line 2528
  =head3 InsertObject
- C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>
+     $erdb->InsertObject($objectType, \%fieldHash);
  Insert an object into the database. The object is defined by a type name and then a hash
  of field names to values. Field values in the primary relation are represented by scalars.
-Line 2183
+Line 2537
  example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases
  C<ZP_00210270.1> and C<gi|46206278>.
- C<< $erdb->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>
+     $erdb->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']});
  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'}); >>
+     $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 2200
+Line 2554
  Hash of field names to values.
- =item RETURN
- Returns 1 if successful, 0 if an error occurred.
  =back
  =cut
-Line 2302
+Line 2652
                  $retVal = $sth->execute(@parameterList);
                  if (!$retVal) {
                      my $errorString = $sth->errstr();
-                     Trace("Insert error: $errorString.") if T(0);
+                     Confess("Error inserting into $relationName: $errorString");
+                 } else {
+                     Trace("Insert successful using $parameterList[0].") if T(3);
                  }
              }
          }
      }
-     # Return the success indicator.
+     # Return a 1 for backward compatability.
-     return $retVal;
+     return 1;
+ }
+ =head3 UpdateEntity
+     $erdb->UpdateEntity($entityName, $id, \%fields);
+ Update the values of an entity. This is an unprotected update, so it should only be
+ done if the database resides on a database server.
+ =over 4
+ =item entityName
+ Name of the entity to update. (This is the entity type.)
+ =item id
+ ID of the entity to update. If no entity exists with this ID, an error will be thrown.
+ =item fields
+ Reference to a hash mapping field names to their new values. All of the fields named
+ must be in the entity's primary relation, and they cannot any of them be the ID field.
+ =back
+ =cut
+ sub UpdateEntity {
+     # Get the parameters.
+     my ($self, $entityName, $id, $fields) = @_;
+     # Get a list of the field names being updated.
+     my @fieldList = keys %{$fields};
+     # Verify that the fields exist.
+     my $checker = $self->GetFieldTable($entityName);
+     for my $field (@fieldList) {
+         if ($field eq 'id') {
+             Confess("Cannot update the ID field for entity $entityName.");
+         } elsif ($checker->{$field}->{relation} ne $entityName) {
+             Confess("Cannot find $field in primary relation of $entityName.");
+         }
+     }
+     # Build the SQL statement.
+     my @sets = ();
+     my @valueList = ();
+     for my $field (@fieldList) {
+         push @sets, _FixName($field) . " = ?";
+         push @valueList, $fields->{$field};
+     }
+     my $command = "UPDATE $entityName SET " . join(", ", @sets) . " WHERE id = ?";
+     # Add the ID to the list of binding values.
+     push @valueList, $id;
+     # Call SQL to do the work.
+     my $rows = $self->{_dbh}->SQL($command, 0, @valueList);
+     # Check for errors.
+     if ($rows == 0) {
+         Confess("Entity $id of type $entityName not found.");
+     }
  }
  =head3 LoadTable
- C<< my %results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>
+     my $results = $erdb->LoadTable($fileName, $relationName, $truncateFlag);
  Load data from a tab-delimited file into a specified table, optionally re-creating the table
  first.
-Line 2356
+Line 2766
      if ($truncateFlag) {
          Trace("Creating table $relationName") if T(2);
          # Compute the row count estimate. We take the size of the load file,
-         # divide it by the estimated row size, and then multiply by 1.5 to
+         # divide it by the estimated row size, and then multiply by 2 to
          # leave extra room. We postulate a minimum row count of 1000 to
          # prevent problems with incoming empty load files.
          my $rowSize = $self->EstimateRowSize($relationName);
-         my $estimate = FIG::max($fileSize * 1.5 / $rowSize, 1000);
+         my $estimate = $fileSize * 8 / $rowSize;
+         if ($estimate < 1000) {
+             $estimate = 1000;
+         }
          # Re-create the table without its index.
          $self->CreateTable($relationName, 0, $estimate);
          # If this is a pre-index DBMS, create the index here.
-Line 2402
+Line 2815
              # 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.
+             Trace("Checking for full-text index on $relationName.") if T(2);
              if ($self->_IsPrimary($relationName)) {
-                 # Get the relation's entity/relationship structure.
+                 $self->CreateSearchIndex($relationName);
-                 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",
-                                        flds => $fields, kind => 'fulltext');
-                 }
              }
          }
      }
-Line 2425
+Line 2829
      return $retVal;
  }
+ =head3 CreateSearchIndex
+     $erdb->CreateSearchIndex($objectName);
+ Check for a full-text search index on the specified entity or relationship object, and
+ if one is required, rebuild it.
+ =over 4
+ =item objectName
+ Name of the entity or relationship to be indexed.
+ =back
+ =cut
+ sub CreateSearchIndex {
+     # Get the parameters.
+     my ($self, $objectName) = @_;
+     # Get the relation's entity/relationship structure.
+     my $structure = $self->_GetStructure($objectName);
+     # Get the database handle.
+     my $dbh = $self->{_dbh};
+     Trace("Checking for search fields in $objectName.") if T(3);
+     # 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 $fields = join(", ", _FixNames(@{$structure->{searchFields}}));
+         # Create the index. If it already exists, it will be dropped.
+         $dbh->create_index(tbl => $objectName, idx => "search_idx",
+                            flds => $fields, kind => 'fulltext');
+         Trace("Index created for $fields in $objectName.") if T(2);
+     }
+ }
  =head3 DropRelation
- C<< $erdb->DropRelation($relationName); >>
+     $erdb->DropRelation($relationName);
  Physically drop a relation from the database.
-Line 2453
+Line 2894
      $dbh->drop_table(tbl => $relationName);
  }
+ =head3 MatchSqlPattern
+     my $matched = ERDB::MatchSqlPattern($value, $pattern);
+ Determine whether or not a specified value matches an SQL pattern. An SQL
+ pattern has two wild card characters: C<%> that matches multiple characters,
+ and C<_> that matches a single character. These can be escaped using a
+ backslash (C<\>). We pull this off by converting the SQL pattern to a
+ PERL regular expression. As per SQL rules, the match is case-insensitive.
+ =over 4
+ =item value
+ Value to be matched against the pattern. Note that an undefined or empty
+ value will not match anything.
+ =item pattern
+ SQL pattern against which to match the value. An undefined or empty pattern will
+ match everything.
+ =item RETURN
+ Returns TRUE if the value and pattern match, else FALSE.
+ =back
+ =cut
+ sub MatchSqlPattern {
+     # Get the parameters.
+     my ($value, $pattern) = @_;
+     # Declare the return variable.
+     my $retVal;
+     # Insure we have a pattern.
+     if (! defined($pattern) || $pattern eq "") {
+         $retVal = 1;
+     } else {
+         # Break the pattern into pieces around the wildcard characters. Because we
+         # use parentheses in the split function's delimiter expression, we'll get
+         # list elements for the delimiters as well as the rest of the string.
+         my @pieces = split /([_%]|\\[_%])/, $pattern;
+         # Check some fast special cases.
+         if ($pattern eq '%') {
+             # A null pattern matches everything.
+             $retVal = 1;
+         } elsif (@pieces == 1) {
+             # No wildcards, so we have a literal comparison. Note we're case-insensitive.
+             $retVal = (lc($value) eq lc($pattern));
+         } elsif (@pieces == 2 && $pieces[1] eq '%') {
+             # A wildcard at the end, so we have a substring match. This is also case-insensitive.
+             $retVal = (lc(substr($value, 0, length($pieces[0]))) eq lc($pieces[0]));
+         } else {
+             # Okay, we have to do it the hard way. Convert each piece to a PERL pattern.
+             my $realPattern = "";
+             for my $piece (@pieces) {
+                 # Determine the type of piece.
+                 if ($piece eq "") {
+                     # Empty pieces are ignored.
+                 } elsif ($piece eq "%") {
+                     # Here we have a multi-character wildcard. Note that it can match
+                     # zero or more characters.
+                     $realPattern .= ".*"
+                 } elsif ($piece eq "_") {
+                     # Here we have a single-character wildcard.
+                     $realPattern .= ".";
+                 } elsif ($piece eq "\\%" || $piece eq "\\_") {
+                     # This is an escape sequence (which is a rare thing, actually).
+                     $realPattern .= substr($piece, 1, 1);
+                 } else {
+                     # Here we have raw text.
+                     $realPattern .= quotemeta($piece);
+                 }
+             }
+             # Do the match.
+             $retVal = ($value =~ /^$realPattern$/i ? 1 : 0);
+         }
+     }
+     # Return the result.
+     return $retVal;
+ }
  =head3 GetEntity
- C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>
+     my $entityObject = $erdb->GetEntity($entityType, $ID);
  Return an object describing the entity instance with a specified ID.
-Line 2471
+Line 2995
  =item RETURN
- Returns a B<DBObject> representing the desired entity instance, or an undefined value if no
+ Returns a B<ERDBObject> representing the desired entity instance, or an undefined value if no
  instance is found with the specified key.
  =back
-Line 2491
+Line 3015
  =head3 GetChoices
- C<< my @values = $erdb->GetChoices($entityName, $fieldName); >>
+     my @values = $erdb->GetChoices($entityName, $fieldName);
  Return a list of all the values for the specified field that are represented in the
  specified entity.
-Line 2546
+Line 3070
  =head3 GetEntityValues
- C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>
+     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.
-Line 2590
+Line 3114
  =head3 GetAll
- C<< my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>
+     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
-Line 2604
+Line 3128
  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.
+ feature ID followed by all of its essentiality determinations.
- C<< $query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>
+     @query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(essential)']);
  =over 4
-Line 2684
+Line 3208
  =head3 Exists
- C<< my $found = $sprout->Exists($entityName, $entityID); >>
+     my $found = $sprout->Exists($entityName, $entityID);
  Return TRUE if an entity exists, else FALSE.
-Line 2719
+Line 3243
  =head3 EstimateRowSize
- C<< my $rowSize = $erdb->EstimateRowSize($relName); >>
+     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.
-Line 2757
+Line 3281
  =head3 GetFieldTable
- C<< my $fieldHash = $self->GetFieldTable($objectnName); >>
+     my $fieldHash = $self->GetFieldTable($objectnName);
  Get the field structure for a specified entity or relationship.
-Line 2786
+Line 3310
  =head3 SplitKeywords
- C<< my @keywords = ERDB::SplitKeywords($keywordString); >>
+     my @keywords = ERDB::SplitKeywords($keywordString);
  This method returns a list of the positive keywords in the specified
  keyword string. All of the operators will have been stripped off,
-Line 2835
+Line 3359
  =head3 ValidateFieldName
- C<< my $okFlag = ERDB::ValidateFieldName($fieldName); >>
+     my $okFlag = ERDB::ValidateFieldName($fieldName);
  Return TRUE if the specified field name is valid, else FALSE. Valid field names must
  be hyphenated words subject to certain restrictions.
-Line 2860
+Line 3384
      # Declare the return variable. The field name is valid until we hear
      # differently.
      my $retVal = 1;
+     # Compute the maximum name length.
+     my $maxLen = $TypeTable{'name-string'}->{maxLen};
      # Look for bad stuff in the name.
      if ($fieldName =~ /--/) {
          # Here we have a doubled minus sign.
-Line 2869
+Line 3395
          # Here the field name is missing the initial letter.
          Trace("Field name $fieldName does not begin with a letter.") if T(1);
          $retVal = 0;
+     } elsif (length($fieldName) > $maxLen) {
+         # Here the field name is too long.
+         Trace("Maximum field name length is $maxLen. Field name must be truncated to " . substr($fieldName,0, $maxLen) . ".");
      } else {
          # Strip out the minus signs. Everything remaining must be a letter,
          # underscore, or digit.
-Line 2885
+Line 3414
  =head3 ReadMetaXML
- C<< my $rawMetaData = ERDB::ReadDBD($fileName); >>
+     my $rawMetaData = ERDB::ReadDBD($fileName);
  This method reads a raw database definition XML file and returns it.
  Normally, the metadata used by the ERDB system has been processed and
-Line 2918
+Line 3447
  =head3 GetEntityFieldHash
- C<< my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName); >>
+     my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName);
  Get the field hash of the named entity in the specified raw XML structure.
  The field hash may not exist, in which case we need to create it.
-Line 2960
+Line 3489
  =head3 WriteMetaXML
- C<< ERDB::WriteMetaXML($structure, $fileName); >>
+     ERDB::WriteMetaXML($structure, $fileName);
  Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
  used to update the database definition. It must be used with care, however, since it
-Line 2999
+Line 3528
  Except for C<[p]>, all the codes are closed by slash-codes. So, for
  example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
- C<< my $realHtml = ERDB::HTMLNote($dataString); >>
+     my $realHtml = ERDB::HTMLNote($dataString);
  =over 4
-Line 3023
+Line 3552
      # Substitute the bulletin board codes.
      $retVal =~ s!\[(/?[bi])\]!<$1>!g;
      $retVal =~ s!\[p\]!</p><p>!g;
+     $retVal =~ s!\[link\s+([^\]]+)\]!<a href="$1">!g;
+     $retVal =~ s!\[/link\]!</a>!g;
+     # Return the result.
+     return $retVal;
+ }
+ =head3 BeginTran
+     $erdb->BeginTran();
+ Start a database transaction.
+ =cut
+ sub BeginTran {
+     my ($self) = @_;
+     $self->{_dbh}->begin_tran();
+ }
+ =head3 CommitTran
+     $erdb->CommitTran();
+ Commit an active database transaction.
+ =cut
+ sub CommitTran {
+     my ($self) = @_;
+     $self->{_dbh}->commit_tran();
+ }
+ =head3 RollbackTran
+     $erdb->RollbackTran();
+ Roll back an active database transaction.
+ =cut
+ sub RollbackTran {
+     my ($self) = @_;
+     $self->{_dbh}->roll_tran();
+ }
+ =head3 UpdateField
+     my $count = $erdb->UpdateField($objectNames, $fieldName, $oldValue, $newValue, $filter, $parms);
+ Update all occurrences of a specific field value to a new value. The number of rows changed will be
+ returned.
+ =over 4
+ =item fieldName
+ Name of the field in standard I<objectName>C<(>I<fieldName>C<)> format.
+ =item oldValue
+ Value to be modified. All occurrences of this value in the named field will be replaced by the
+ new value.
+ =item newValue
+ New value to be substituted for the old value when it's found.
+ =item filter
+ A standard ERDB filter clause (see L</Get>). The filter will be applied before any substitutions take place.
+ =item parms
+ Reference to a list of parameter values in the filter.
+ =item RETURN
+ Returns the number of rows modified.
+ =back
+ =cut
+ sub UpdateField {
+     # Get the parameters.
+     my ($self, $fieldName, $oldValue, $newValue, $filter, $parms) = @_;
+     # Get the object and field names from the field name parameter.
+     $fieldName =~ /^([^(]+)\(([^)]+)\)/;
+     my $objectName = $1;
+     my $realFieldName = _FixName($2);
+     # Add the old value to the filter. Note we allow the possibility that no
+     # filter was specified.
+     my $realFilter = "$fieldName = ?";
+     if ($filter) {
+         $realFilter .= " AND $filter";
+     }
+     # Format the query filter.
+     my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
+         $self->_SetupSQL([$objectName], $realFilter);
+     # Create the query. Since there is only one object name, the mapped-name data is not
+     # necessary. Neither is the FROM clause.
+     $suffix =~ s/^FROM.+WHERE\s+//;
+     # Create the update statement.
+     my $command = "UPDATE $objectName SET $realFieldName = ? WHERE $suffix";
+     # Get the database handle.
+     my $dbh = $self->{_dbh};
+     # Add the old and new values to the parameter list. Note we allow the possibility that
+     # there are no user-supplied parameters.
+     my @params = ($newValue, $oldValue);
+     if (defined $parms) {
+         push @params, @{$parms};
+     }
+     # Execute the update.
+     my $retVal = $dbh->SQL($command, 0, @params);
+     # Make the funky zero a real zero.
+     if ($retVal == 0) {
+         $retVal = 0;
+     }
      # Return the result.
      return $retVal;
  }
-Line 3032
+Line 3680
  =head3 GetUsefulCrossValues
- C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>
+     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
-Line 3093
+Line 3741
  =head3 FindColumn
- C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>
+     my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier);
  Return the location a desired column in a data mining header line. The data
  mining header line is a tab-separated list of column names. The column
-Line 3151
+Line 3799
  =head3 ParseColumns
- C<< my @columns = ERDB::ParseColumns($line); >>
+     my @columns = ERDB::ParseColumns($line);
  Convert the specified data line to a list of columns.
-Line 3183
+Line 3831
  =head2 Virtual Methods
+ =head3 _CreatePPOIndex
+     my $index = ERDB::_CreatePPOIndex($indexObject);
+ Convert the XML for an ERDB index to the XML structure for a PPO
+ index.
+ =over 4
+ ERDB XML structure for an index.
+ =item RETURN
+ PPO XML structure for the same index.
+ =back
+ =cut
+ sub _CreatePPOIndex {
+     # Get the parameters.
+     my ($indexObject) = @_;
+     # The incoming index contains a list of the index fields in the IndexFields
+     # member. We loop through it to create the index tags.
+     my @fields = map { { label => _FixName($_->{name}) } } @{$indexObject->{IndexFields}};
+     # Wrap the fields in attribute tags.
+     my $retVal = { attribute => \@fields };
+     # Return the result.
+     return $retVal;
+ }
+ =head3 _CreatePPOField
+     my $fieldXML = ERDB::_CreatePPOField($fieldName, $fieldObject);
+ Convert the ERDB XML structure for a field to a PPO scalar XML structure.
+ =over 4
+ =item fieldName
+ Name of the scalar field.
+ =item fieldObject
+ ERDB XML structure describing the field.
+ =item RETURN
+ Returns a PPO XML structure for the same field.
+ =back
+ =cut
+ sub _CreatePPOField {
+     # Get the parameters.
+     my ($fieldName, $fieldObject) = @_;
+     # Get the field type.
+     my $type = $TypeTable{$fieldObject->{type}}->{sqlType};
+     # Fix up the field name.
+     $fieldName = _FixName($fieldName);
+     # Build the scalar tag.
+     my $retVal = { label => $fieldName, type => $type };
+     # Return the result.
+     return $retVal;
+ }
  =head3 CleanKeywords
- C<< my $cleanedString = $erdb->CleanKeywords($searchExpression); >>
+     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
-Line 3222
+Line 3938
  =head3 GetSourceObject
- C<< my $source = $erdb->GetSourceObject($entityName); >>
+     my $source = $erdb->GetSourceObject($entityName);
  Return the object to be used in loading special attributes of the specified entity. The
  algorithm for loading special attributes is stored in the C<DataGen> elements of the
-Line 3232
+Line 3948
  =head3 _RelationMap
- C<< my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef); >>
+     my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
- Create the relation map for an SQL query. The relation map is used by B<DBObject>
+ Create the relation map for an SQL query. The relation map is used by B<ERDBObject>
  to determine how to interpret the results of the query.
  =over 4
-Line 3251
+Line 3967
  =item RETURN
  Returns a list of 2-tuples. Each tuple consists of an object name as used in the
- query followed by the actual name of that object. This enables the B<DBObject> to
+ query followed by the actual name of that object. This enables the B<ERDBObject> to
  determine the order of the tables in the query and which object name belongs to each
  mapped object name. Most of the time these two values are the same; however, if a
  relation occurs twice in the query, the relation name in the field list and WHERE
-Line 3545
+Line 4261
  sub _GetStatementHandle {
      # Get the parameters.
      my ($self, $command, $params) = @_;
+     Confess("Invalid parameter list.") if (! defined($params) || ref($params) ne 'ARRAY');
      # Trace the query.
      Trace("SQL query: $command") if T(SQL => 3);
      Trace("PARMS: '" . (join "', '", @{$params}) . "'") if (T(SQL => 4) && (@{$params} > 0));
-Line 3794
+Line 4511
  =head3 _LoadMetaData
+     my $metadata = ERDB::_LoadMetaData($filename);
  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
  load or use the database. The schema for the XML file is F<ERDatabase.xml>.
-Line 3943
+Line 4662
              if ($found == 0) {
                  push @{$indexList}, { IndexFields => [ {name => 'id', order => 'ascending'} ] };
              }
-             # Now we need to convert the relation's index list to an index table. We begin by creating
+             # Attach all the indexes to the relation.
-             # an empty table in the relation structure.
+             _ProcessIndexes($indexList, $relation);
-             $relation->{Indexes} = { };
-             # Loop through the indexes.
-             my $count = 0;
-             for my $index (@{$indexList}) {
-                 # Add this index to the index table.
-                 _AddIndex("idx$count", $relation, $index);
-                 # Increment the counter so that the next index has a different name.
-                 $count++;
-             }
          }
          # Finally, we add the relation structure to the entity.
          $entityStructure->{Relations} = $relationTable;
-Line 3967
+Line 4677
          _FixupFields($relationshipStructure, $relationshipName, 2, 3);
          # Format a description for the FROM field.
          my $fromEntity = $relationshipStructure->{from};
-         my $fromComment = "<b>id</b> of the source <b><a href=\"#$fromEntity\">$fromEntity</a></b>.";
+         my $fromComment = "[b]id[/b] of the source [b][link #$fromEntity]$fromEntity\[/link][/b].";
          # Get the FROM entity's key type.
          my $fromType = $entityList->{$fromEntity}->{keyType};
          # Add the FROM field.
-Line 3977
+Line 4687
                                                      PrettySort => 1});
          # Format a description for the TO field.
          my $toEntity = $relationshipStructure->{to};
-         my $toComment = "<b>id</b> of the target <b><a href=\"#$toEntity\">$toEntity</a></b>.";
+         my $toComment = "[b]id[/b] of the target [b][link #$toEntity]$toEntity\[/link][/b].";
          # Get the TO entity's key type.
          my $toType = $entityList->{$toEntity}->{keyType};
          # Add the TO field.
-Line 3989
+Line 4699
          my $thisRelation = { Fields => _ReOrderRelationTable($relationshipStructure->{Fields}),
                               Indexes => { } };
          $relationshipStructure->{Relations} = { $relationshipName => $thisRelation };
+         # Add the alternate indexes (if any). This MUST be done before the FROM and
+         # TO indexes, because it erases the relation's index list.
+         if (exists $relationshipStructure->{Indexes}) {
+             _ProcessIndexes($relationshipStructure->{Indexes}, $thisRelation);
+         }
+         # Add the relation to the master table.
          # Create the FROM and TO indexes.
          _CreateRelationshipIndex("From", $relationshipName, $relationshipStructure);
          _CreateRelationshipIndex("To", $relationshipName, $relationshipStructure);
-         # Add the relation to the master table.
          $masterRelationTable{$relationshipName} = $thisRelation;
      }
      # Now store the master relation table in the metadata structure.
-Line 4151
+Line 4867
      _AddIndex("idx$indexKey", $relationStructure, $newIndex);
  }
+ =head3 _ProcessIndexes
+     ERDB::_ProcessIndexes($indexList, $relation);
+ Build the data structures for the specified indexes in the specified relation.
+ =over 4
+ =item indexList
+ Reference to a list of indexes. Each index is a hash reference containing an optional
+ C<Notes> value that describes the index and an C<IndexFields> value that is a reference
+ to a list of index field structures. An index field structure, in turn, is a reference
+ to a hash that contains a C<name> attribute for the field name and an C<order>
+ attribute that specifies either C<ascending> or C<descending>. In this sense the
+ index list encapsulates the XML C<Indexes> structure in the database definition.
+ =item relation
+ The structure that describes the current relation. The new index descriptors will
+ be stored in the structure's C<Indexes> member. Any previous data in the structure
+ will be lost.
+ =back
+ =cut
+ sub _ProcessIndexes {
+     # Get the parameters.
+     my ($indexList, $relation) = @_;
+     # Now we need to convert the relation's index list to an index table. We begin by creating
+     # an empty table in the relation structure.
+     $relation->{Indexes} = { };
+     # Loop through the indexes.
+     my $count = 0;
+     for my $index (@{$indexList}) {
+         # Add this index to the index table.
+         _AddIndex("idx$count", $relation, $index);
+         # Increment the counter so that the next index has a different name.
+         $count++;
+     }
+ }
  =head3 _AddIndex
  Add an index to a relation structure.
-Line 4680
+Line 5439
      # Compute the number of columns.
      my $colCount = @colNames;
      # Generate the title row.
-     my $htmlString = "<p><table border=\"2\"><tr><td colspan=\"$colCount\" align=\"center\">$tablename</td></tr>\n";
+     my $htmlString = "<table border=\"2\"><tr><td colspan=\"$colCount\" align=\"center\">$tablename</td></tr>\n";
      # Loop through the columns, adding the column header rows.
      $htmlString .= "<tr>";
      for my $colName (@colNames) {
-Line 4699
+Line 5458
  =cut
  sub _CloseTable {
-     return "</table></p>\n";
+     return "</table>\n";
  }
  =head3 _ShowField

 Legend:



Removed from v.1.76
 


changed lines


 
Added in v.1.94
 Legend:



Removed from v.1.76
 


changed lines


 
Added in v.1.94
-Removed from v.1.76
+Added in v.1.94

MCS Webmaster	ViewVC Help
Powered by ViewVC 1.0.3