Diff of /Sprout/ERDB.pm

-revision 1.6, Wed May  4 03:24:43 2005 UTC
+revision 1.43, Mon May 15 20:01:35 2006 UTC
 Line 2
          use strict;
          use Tracer;
-         use DBKernel;
+     use DBrtns;
          use Data::Dumper;
          use XML::Simple;
          use DBQuery;
          use DBObject;
          use Stats;
          use Time::HiRes qw(gettimeofday);
+     use Digest::MD5 qw(md5_base64);
+     use FIG;
  =head1 Entity-Relationship Database Package
-Line 32
+Line 34
  relation that contains two fields-- the feature ID (C<id>) and the alias name (C<alias>).
  The B<FEATURE> entity also contains an optional virulence number. This is implemented
  as a separate relation C<FeatureVirulence> which contains an ID (C<id>) and a virulence number
- (C<virulence>). If the virulence of a feature I<ABC> is known to be 6, there will be one row in the
+ (C<virulence>). If the virulence of a feature I<ABC> is known to be 6, there will be one row in
- C<FeatureVirulence> relation possessing the value I<ABC> as its ID and 6 as its virulence number.
+ the C<FeatureVirulence> relation possessing the value I<ABC> as its ID and 6 as its virulence
- If the virulence of I<ABC> is not known, there will not be any rows for it in C<FeatureVirulence>.
+ number. If the virulence of I<ABC> is not known, there will not be any rows for it in
+ C<FeatureVirulence>.
  Entities are connected by binary relationships implemented using single relations possessing the
  same name as the relationship itself and that has an I<arity> of 1-to-1 (C<11>), 1-to-many (C<1M>),
-Line 69
+Line 72
  is described in the L</GenerateEntity> and L</GenerateConnection> methods, though it is not yet
  fully implemented.
+ =head2 XML Database Description
+ =head3 Data Types
+ The ERDB system supports the following data types. Note that there are numerous string
+ types depending on the maximum length. Some database packages limit the total number of
+ characters you have in an index key; to insure the database works in all environments,
+ the type of string should be the shortest one possible that supports all the known values.
+ =over 4
+ =item char
+ single ASCII character
+ =item int
+-bit signed integer
+ =item date
+-bit unsigned integer, representing a PERL date/time value
+ =item text
+ long string; Text fields cannot be used in indexes or sorting and do not support the
+ normal syntax of filter clauses, but can be up to a billion character in length
+ =item float
+ double-precision floating-point number
+ =item boolean
+ single-bit numeric value; The value is stored as a 16-bit signed integer (for
+ compatability with certain database packages), but the only values supported are
+and 1.
+ =item key-string
+ variable-length string, maximum 40 characters
+ =item name-string
+ variable-length string, maximum 80 characters
+ =item medium-string
+ variable-length string, maximum 160 characters
+ =item string
+ 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
+ the database is given by the text associated with the B<Title> tag. The display name
+ is only used in the automated documentation. It has no other effect. The entities and
+ relationships are listed inside the B<Entities> and B<Relationships> tags,
+ respectively. None of these tags have attributes.
+     <Database>
+         <Title>... display title here...</Title>
+         <Entities>
+             ... entity definitions here ...
+         </Entities>
+         <Relationships>
+             ... relationship definitions here...
+         </Relationships>
+     </Database>
+ Entities, relationships, indexes, and fields all allow a text tag called B<Notes>.
+ The text inside the B<Notes> tag contains comments that will appear when the database
+ documentation is generated. Within a B<Notes> tag, you may use C<[i]> and C<[/i]> for
+ italics, C<[b]> and C<[/b]> for bold, and C<[p]> for a new paragraph.
+ =head3 Fields
+ Both entities and relationships have fields described by B<Field> tags. A B<Field>
+ tag can have B<Notes> associated with it. The complete set of B<Field> tags for an
+ object mus be inside B<Fields> tags.
+     <Entity ... >
+         <Fields>
+             ... Field tags ...
+         </Fields>
+     </Entity>
+ The attributes for the B<Field> tag are as follows.
+ =over 4
+ =item name
+ 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.
+ =item type
+ Data type of the field. The legal data types are given above.
+ =item relation
+ Name of the relation containing the field. This should only be specified for entity
+ fields. The ERDB system does not support optional fields or multi-occurring fields
+ in the primary relation of an entity. Instead, they are put into secondary relations.
+ So, for example, in the C<Genome> entity, the C<group-name> field indicates a special
+ grouping used to select a subset of the genomes. A given genome may not be in any
+ groups or may be in multiple groups. Therefore, C<group-name> specifies a relation
+ value. The relation name specified must be a valid table name. By convention, it is
+ usually the entity name followed by a qualifying word (e.g. C<GenomeGroup>). In an
+ 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.
+ =back
+ =head3 Indexes
+ An entity can have multiple alternate indexes associated with it. The fields must
+ be from the primary relation. The alternate indexes assist in ordering results
+ from a query. A relationship can have up to two indexes-- a I<to-index> and a
+ I<from-index>. These 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 relationship.
+ The indexes for an entity must be listed inside the B<Indexes> tag. The from-index
+ of a relationship is specified using the B<FromIndex> tag; the to-index is 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
+ the index. The attributes of an B<IndexField> tag are as follows.
+ =over 4
+ =item name
+ Name of the field.
+ =item order
+ Sort order of the field-- C<ascending> or C<descending>.
+ =back
+ The B<Index>, B<FromIndex>, and B<ToIndex> tags themselves have no attributes.
+ =head3 Object and Field Names
+ By convention entity and relationship names use capital casing (e.g. C<Genome> or
+ C<HasRegionsIn>. Most underlying databases, however, are aggressively case-insensitive
+ with respect to relation names, converting them internally to all-upper case or
+ all-lower case.
+ If syntax or parsing errors occur when you try to load or use an ERDB database, the
+ most likely reason is that one of your objects has an SQL reserved word as its name.
+ The list of SQL reserved words keeps increasing; however, most are unlikely to show
+ up as a noun or declarative verb phrase. The exceptions are C<Group>, C<User>,
+ C<Table>, C<Index>, C<Object>, C<Date>, C<Number>, C<Update>, C<Time>, C<Percent>,
+ C<Memo>, C<Order>, and C<Sum>. This problem can crop up in field names as well.
+ Every entity has a field called C<id> that acts as its primary key. Every relationship
+ has fields called C<from-link> and C<to-link> that contain copies of the relevant
+ entity IDs. These are essentially ERDB's reserved words, and should not be used
+ for user-defined field names.
+ =head3 Entities
+ An entity is described by the B<Entity> tag. The entity can contain B<Notes>, an
+ B<Indexes> tag containing one or more secondary indexes, and a B<Fields> tag
+ containing one or more fields. The attributes of the B<Entity> tag are as follows.
+ =over 4
+ =item name
+ Name of the entity. The entity name, by convention, uses capital casing (e.g. C<Genome>
+ or C<GroupBlock>) and should be a noun or noun phrase.
+ =item keyType
+ Data type of the primary key. The primary key is always named C<id>.
+ =back
+ =head3 Relationships
+ 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
+ the to-index.
+ The C<Relationship> tag has the following attributes.
+ =over 4
+ =item name
+ Name of the relationship. The relationship name, by convention, uses capital casing
+ (e.g. C<ContainsRegionIn> or C<HasContig>), and should be a declarative verb
+ phrase, designed to fit between the from-entity and the to-entity (e.g.
+ Block C<ContainsRegionIn> Genome).
+ =item from
+ Name of the entity from which the relationship starts.
+ =item to
+ Name of the entity to which the relationship proceeds.
+ =item arity
+ Relationship type: C<1M> for one-to-many and C<MM> for many-to-many.
+ =back
  =cut
  # GLOBALS
-Line 76
+Line 313
  # Table of information about our datatypes. "sqlType" is the corresponding SQL datatype string.
  # "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.
+ # string is specified in the field definition. "avgLen" is the average byte length for estimating
- my %TypeTable = ( char =>        { sqlType => 'CHAR(1)',                        maxLen => 1,                    dataGen => "StringGen('A')" },
+ # record sizes.
-                                   int =>         { sqlType => 'INTEGER',                        maxLen => 20,                   dataGen => "IntGen(0, 99999999)" },
+ my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, dataGen => "StringGen('A')" },
-                                   string =>  { sqlType => 'VARCHAR(255)',               maxLen => 255,                  dataGen => "StringGen(IntGen(10,250))" },
+                   int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, dataGen => "IntGen(0, 99999999)" },
-                                   text =>        { sqlType => 'TEXT',                           maxLen => 1000000000,   dataGen => "StringGen(IntGen(80,1000))" },
+                   string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, dataGen => "StringGen(IntGen(10,250))" },
-                                   date =>        { sqlType => 'BIGINT',                         maxLen => 80,                   dataGen => "DateGen(-7, 7, IntGen(0,1400))" },
+                   text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, dataGen => "StringGen(IntGen(80,1000))" },
-                                   float =>       { sqlType => 'DOUBLE PRECISION',       maxLen => 40,                   dataGen => "FloatGen(0.0, 100.0)" },
+                   date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, dataGen => "DateGen(-7, 7, IntGen(0,1400))" },
-                                   boolean => { sqlType => 'SMALLINT',                   maxLen => 1,                    dataGen => "IntGen(0, 1)" },
+                   float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, dataGen => "FloatGen(0.0, 100.0)" },
+                   boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, dataGen => "IntGen(0, 1)" },
+                  'hash-string' =>
+                              { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, dataGen => "SringGen(22)" },
                               'key-string' =>
-                                                          { sqlType => 'VARCHAR(40)',            maxLen => 40,                   dataGen => "StringGen(IntGen(10,40))" },
+                              { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, dataGen => "StringGen(IntGen(10,40))" },
                                   'name-string' =>
-                                                          { sqlType => 'VARCHAR(80)',            maxLen => 80,                   dataGen => "StringGen(IntGen(10,80))" },
+                              { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, dataGen => "StringGen(IntGen(10,80))" },
                                   'medium-string' =>
-                                                          { sqlType => 'VARCHAR(160)',           maxLen => 160,                  dataGen => "StringGen(IntGen(10,160))" },
+                              { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, dataGen => "StringGen(IntGen(10,160))" },
                                  );
  # Table translating arities into natural language.
-Line 145
+Line 385
  =head3 ShowMetaData
- C<< $database->ShowMetaData($fileName); >>
+ C<< $erdb->ShowMetaData($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 282
+Line 522
                  # 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};
-Line 300
+Line 540
  =head3 DumpMetaData
- C<< $database->DumpMetaData(); >>
+ C<< $erdb->DumpMetaData(); >>
  Return a dump of the metadata structure.
-Line 315
+Line 555
  =head3 CreateTables
- C<< $datanase->CreateTables(); >>
+ C<< $erdb->CreateTables(); >>
  This method creates the tables for the database from the metadata structure loaded by the
  constructor. It is expected this function will only be used on rare occasions, when the
-Line 327
+Line 567
  sub CreateTables {
          # Get the parameters.
          my ($self) = @_;
-         my $metadata = $self->{_metaData};
+     # Get the relation names.
-         my $dbh = $self->{_dbh};
+     my @relNames = $self->GetTableNames();
-         # Loop through the entities.
+     # Loop through the relations.
-         my $entityHash = $metadata->{Entities};
+     for my $relationName (@relNames) {
-         for my $entityName (keys %{$entityHash}) {
-                 my $entityData = $entityHash->{$entityName};
-                 # Tell the user what we're doing.
-                 Trace("Creating relations for entity $entityName.") if T(1);
-                 # Loop through the entity's relations.
-                 for my $relationName (keys %{$entityData->{Relations}}) {
                          # Create a table for this relation.
                          $self->CreateTable($relationName);
-                         Trace("Relation $relationName created.") if T(1);
+         Trace("Relation $relationName created.") if T(2);
-                 }
-         }
-         # Loop through the relationships.
-         my $relationshipTable = $metadata->{Relationships};
-         for my $relationshipName (keys %{$metadata->{Relationships}}) {
-                 # Create a table for this relationship.
-                 Trace("Creating relationship $relationshipName.") if T(1);
-                 $self->CreateTable($relationshipName);
          }
  }
  =head3 CreateTable
- C<< $database->CreateTable($tableName, $indexFlag); >>
+ C<< $erdb->CreateTable($tableName, $indexFlag, $estimatedRows); >>
  Create the table for a relation and optionally create its indexes.
-Line 363
+Line 589
  Name of the relation (which will also be the table name).
- =item $indexFlag
+ =item indexFlag
  TRUE if the indexes for the relation should be created, else FALSE. If FALSE,
  L</CreateIndexes> must be called later to bring the indexes into existence.
+ =item estimatedRows (optional)
+ If specified, the estimated maximum number of rows for the relation. This
+ information allows the creation of tables using storage engines that are
+ faster but require size estimates, such as MyISAM.
  =back
  =cut
  sub CreateTable {
          # Get the parameters.
-         my ($self, $relationName, $indexFlag) = @_;
+     my ($self, $relationName, $indexFlag, $estimatedRows) = @_;
          # Get the database handle.
          my $dbh = $self->{_dbh};
          # Get the relation data and determine whether or not the relation is primary.
-Line 398
+Line 630
          # Insure the table is not already there.
          $dbh->drop_table(tbl => $relationName);
          Trace("Table $relationName dropped.") if T(2);
+     # If there are estimated rows, create an estimate so we can take advantage of
+     # faster DB technologies.
+     my $estimation = undef;
+     if ($estimatedRows) {
+         $estimation = [$self->EstimateRowSize($relationName), $estimatedRows];
+     }
          # Create the table.
          Trace("Creating table $relationName: $fieldThing") if T(2);
-         $dbh->create_table(tbl => $relationName, flds => $fieldThing);
+     $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);
          Trace("Relation $relationName created in database.") if T(2);
          # If we want to build the indexes, we do it here.
          if ($indexFlag) {
-Line 408
+Line 646
          }
  }
+ =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] = md5_base64($fieldList->[$i]);
+         }
+     }
+ }
  =head3 CreateIndex
- C<< $database->CreateIndex($relationName); >>
+ C<< $erdb->CreateIndex($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 best to create the indexes after the load. If that is
+ is the case in L</LoadTable>), it is sometimes best to create the indexes after the load.
- the case, then L</CreateTable> should be called with the index flag set to FALSE, and this
+ If that is the case, then L</CreateTable> should be called with the index flag set to
- method used after the load to create the indexes for the table.
+ FALSE, and this method used after the load to create the indexes for the table.
  =cut
-Line 436
+Line 769
                  # Get the index's uniqueness flag.
                  my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');
                  # Create the index.
-                 $dbh->create_index(idx => $indexName, tbl => $relationName, flds => $flds, unique => $unique);
+         my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
+                                     flds => $flds, unique => $unique);
+         if ($rv) {
                  Trace("Index created: $indexName for $relationName ($flds)") if T(1);
+         } else {
+             Confess("Error creating index $indexName for $relationName using ($flds): " . $dbh->error_message());
+         }
          }
  }
  =head3 LoadTables
- C<< my $stats = $database->LoadTables($directoryName, $rebuild); >>
+ C<< 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 486
+Line 824
          $directoryName =~ s!/\\$!!;
          # Declare the return variable.
          my $retVal = Stats->new();
-         # Get the metadata structure.
+     # Get the relation names.
-         my $metaData = $self->{_metaData};
+     my @relNames = $self->GetTableNames();
-         # Loop through the entities.
+     for my $relationName (@relNames) {
-         for my $entity (values %{$metaData->{Entities}}) {
-                 # Loop through the entity's relations.
-                 for my $relationName (keys %{$entity->{Relations}}) {
                          # Try to load this relation.
                          my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);
                          # Accumulate the statistics.
                          $retVal->Accumulate($result);
                  }
-         }
-         # Loop through the relationships.
-         for my $relationshipName (keys %{$metaData->{Relationships}}) {
-                 # Try to load this relationship's relation.
-                 my $result = $self->_LoadRelation($directoryName, $relationshipName, $rebuild);
-                 # Accumulate the statistics.
-                 $retVal->Accumulate($result);
-         }
          # Add the duration of the load to the statistical object.
          $retVal->Add('duration', gettimeofday - $startTime);
          # Return the accumulated statistics.
          return $retVal;
  }
  =head3 GetTableNames
- C<< my @names = $database->GetTableNames; >>
+ C<< my @names = $erdb->GetTableNames; >>
  Return a list of the relations required to implement this database.
-Line 530
+Line 858
  =head3 GetEntityTypes
- C<< my @names = $database->GetEntityTypes; >>
+ C<< my @names = $erdb->GetEntityTypes; >>
  Return a list of the entity type names.
-Line 545
+Line 873
          return sort keys %{$entityList};
  }
+ =head3 IsEntity
+ C<< my $flag = $erdb->IsEntity($entityName); >>
+ Return TRUE if the parameter is an entity name, else FALSE.
+ =over 4
+ =item entityName
+ Object name to be tested.
+ =item RETURN
+ Returns TRUE if the specified string is an entity name, else FALSE.
+ =back
+ =cut
+ sub IsEntity {
+     # Get the parameters.
+     my ($self, $entityName) = @_;
+     # Test to see if it's an entity.
+     return exists $self->{_metaData}->{Entities}->{$entityName};
+ }
  =head3 Get
- C<< my $query = $database->Get(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>
+ C<< my $query = $erdb->Get(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>
  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 555
+Line 910
  following call requests all B<Genome> objects for the genus specified in the variable
  $genus.
- C<< $query = $sprout->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
- C<< $query = $sprout->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>
+ C<< $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 572
+Line 927
  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 = $sprout->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 605
+Line 965
  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.
+ 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" >>
+ 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 param1, param2, ..., paramN
  Parameter values to be substituted into the filter clause.
-Line 624
+Line 999
  sub Get {
          # Get the parameters.
          my ($self, $objectNames, $filterClause, @params) = @_;
+     # Adjust the list of object names to account for multiple occurrences of the
+     # same object. We start with a hash table keyed on object name that will
+     # return the object suffix. The first time an object is encountered it will
+     # not be found in the hash. The next time the hash will map the object name
+     # to 2, then 3, and so forth.
+     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 {
+             # Here we've seen the object before. We construct a new name using
+             # the suffix from the hash and update the hash.
+             my $mappedName = "$objectName$suffix";
+             $objectHash{$objectName} = $suffix + 1;
+             # The FROM list has the object name followed by the mapped name. This
+             # tells SQL it's still the same table, but we're using a different name
+             # for it to avoid confusion.
+             push @fromList, "$objectName $mappedName";
+             # The mapped-name list contains the real mapped name.
+             push @mappedNameList, $mappedName;
+             # Finally, enable us to get back from the mapped name to the object name.
+             $mappedNameHash{$mappedName} = $objectName;
+         }
+     }
          # Construct the SELECT statement. The general pattern is
          #
          # SELECT name1.*, name2.*, ... nameN.* FROM name1, name2, ... nameN
          #
          my $dbh = $self->{_dbh};
-         my $command = "SELECT DISTINCT " . join('.*, ', @{$objectNames}) . ".* FROM " .
+     my $command = "SELECT DISTINCT " . join('.*, ', @mappedNameList) . ".* FROM " .
-                                 join(', ', @{$objectNames});
+                 join(', ', @fromList);
          # Check for a filter clause.
          if ($filterClause) {
                  # Here we have one, so we convert its field names and add it to the query. First,
-Line 638
+Line 1056
                  my $filterString = $filterClause;
                  # Next, we sort the object names by length. This helps protect us from finding
                  # object names inside other object names when we're doing our search and replace.
-                 my @sortedNames = sort { length($b) - length($a) } @{$objectNames};
+         my @sortedNames = sort { length($b) - length($a) } @mappedNameList;
                  # We will also keep a list of conditions to add to the WHERE clause in order to link
                  # entities and relationships as well as primary relations to secondary ones.
                  my @joinWhere = ();
                  # The final preparatory step is to create a hash table of relation names. The
-                 # table begins with the relation names already in the SELECT command.
+         # table begins with the relation names already in the SELECT command. We may
-                 my %fromNames = ();
+         # need to add relations later if there is filtering on a field in a secondary
-                 for my $objectName (@sortedNames) {
+         # relation. The secondary relations are the ones that contain multiply-
-                         $fromNames{$objectName} = 1;
+         # 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 $objectName (@sortedNames) {
+         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 $objectName;
+             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);
+             my $fieldList = $self->GetFieldTable($objectName);
                          # Find the field references for this object.
-                         while ($filterString =~ m/$objectName\(([^)]*)\)/g) {
+             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.
-Line 671
+Line 1092
                                  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 $fromNames{$relationName}) {
+                     if (!exists $fromNames{$mappedRelationName}) {
                                                  # Add the relation to the FROM clause.
+                         if ($mappedRelationName eq $relationName) {
+                             # The name is un-mapped, so we add it without
+                             # any frills.
                                                  $command .= ", $relationName";
-                                                 # Create its join sub-clause.
                                                  push @joinWhere, "$objectName.id = $relationName.id";
-                                                 # Denote we have it available for future fields.
+                         } else {
-                                                 $fromNames{$relationName} = 1;
+                             # Here we have a mapping situation.
+                             $command .= ", $relationName $mappedRelationName";
+                             push @joinWhere, "$mappedRelationName.id = $mappedName.id";
+                         }
+                         # Denote we have this relation available for future fields.
+                         $fromNames{$mappedRelationName} = 1;
                                          }
                                          # Form an SQL field reference from the relation name and the field name.
-                                         my $sqlReference = "$relationName." . _FixName($fieldName);
+                     my $sqlReference = "$mappedRelationName." . _FixName($fieldName);
                                          # Put it into the filter string in place of the old value.
                                          substr($filterString, $pos, $len) = $sqlReference;
                                          # Reposition the search.
-Line 695
+Line 1131
                  # is more than one object in the object list. We start with the first object and
                  # run through the objects after it. Note also that we make a safety copy of the
                  # list before running through it.
-                 my @objectList = @{$objectNames};
+         my @mappedObjectList = @mappedNameList;
-                 my $lastObject = shift @objectList;
+         my $lastMappedObject = shift @mappedObjectList;
                  # Get the join table.
                  my $joinTable = $self->{_metaData}->{Joins};
                  # Loop through the object list.
-                 for my $thisObject (@objectList) {
+         for my $thisMappedObject (@mappedObjectList) {
-                         # Look for a join.
+             # 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 $lastObject to $thisObject.");
+                 Confess("No join exists to connect from $lastMappedObject to $thisMappedObject.");
                          } else {
-                                 # Get the join clause and add it to the WHERE list.
+                 # Get the join clause.
-                                 push @joinWhere, $joinTable->{$joinKey};
+                 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.
-                                 $lastObject = $thisObject;
+                 $lastMappedObject = $thisMappedObject;
                          }
                  }
-                 # Now we need to handle the whole ORDER BY thing. We'll put the order by clause
+         # Now we need to handle the whole ORDER BY / LIMIT thing. The important part
-                 # in the following variable.
+         # here is we want the filter clause to be empty if there's no WHERE filter.
+         # We'll put the ORDER BY / LIMIT clauses in the following variable.
                  my $orderClause = "";
-                 # Locate the ORDER BY verb (if any).
+         # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy
-                 if ($filterString =~ m/^(.*)ORDER BY/g) {
+         # operator so that we find the first occurrence of either verb.
-                         # Here we have an ORDER BY verb. Split it off of the filter string.
+         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;
-                         $orderClause = substr($filterString, $pos);
+             $orderClause = $2 . substr($filterString, $pos);
                          $filterString = $1;
                  }
                  # Add the filter and the join clauses (if any) to the SELECT command.
                  if ($filterString) {
+             Trace("Filter string is \"$filterString\".") if T(4);
                          push @joinWhere, "($filterString)";
                  }
                  if (@joinWhere) {
                          $command .= " WHERE " . join(' AND ', @joinWhere);
                  }
-                 # Add the sort clause (if any) to the SELECT command.
+         # Add the sort or limit clause (if any) to the SELECT command.
                  if ($orderClause) {
-                         $command .= " ORDER BY $orderClause";
+             $command .= " $orderClause";
                  }
          }
-         Trace("SQL query: $command") if T(2);
+     Trace("SQL query: $command") if T(SQL => 3);
-         Trace("PARMS: '" . (join "', '", @params) . "'") if (T(3) && (@params > 0));
+     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());
+     # 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 = ();
+     for my $mappedName (@mappedNameList) {
+         push @relationMap, [$mappedName, $mappedNameHash{$mappedName}];
+     }
          # Return the statement object.
-         my $retVal = DBQuery::_new($self, $sth, @{$objectNames});
+     my $retVal = DBQuery::_new($self, $sth, \@relationMap);
+     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 GetList
- C<< my @dbObjects = $database->GetList(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>
+ C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>
  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
- that a query object that can be used to get the results one record at a time.
+ than a query object that can be used to get the results one record at a time.
- =over 4
  =over 4
-Line 812
+Line 1429
  =head3 ComputeObjectSentence
- C<< my $sentence = $database->ComputeObjectSentence($objectName); >>
+ C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>
  Check an object name, and if it is a relationship convert it to a relationship sentence.
-Line 847
+Line 1464
  =head3 DumpRelations
- C<< $database->DumpRelations($outputDirectory); >>
+ C<< $erdb->DumpRelations($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 889
+Line 1506
  =head3 InsertObject
- C<< my $ok = $database->InsertObject($objectType, \%fieldHash); >>
+ C<< my $ok = $erdb->InsertObject($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 898
+Line 1515
  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<< $database->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>
+ C<< $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<< $database->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 1028
+Line 1645
  =head3 LoadTable
- C<< my %results = $database->LoadTable($fileName, $relationName, $truncateFlag); >>
+ C<< my %results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>
- Load data from a tab-delimited file into a specified table, optionally re-creating the table first.
+ Load data from a tab-delimited file into a specified table, optionally re-creating the table
+ first.
  =over 4
-Line 1048
+Line 1666
  =item RETURN
- Returns a statistical object containing the number of records read and a list of the error messages.
+ Returns a statistical object containing a list of the error messages.
  =back
-Line 1059
+Line 1677
          # Create the statistical return object.
          my $retVal = _GetLoadStats();
          # Trace the fact of the load.
-         Trace("Loading table $relationName from $fileName") if T(1);
+     Trace("Loading table $relationName from $fileName") if T(2);
          # Get the database handle.
          my $dbh = $self->{_dbh};
+     # Get the input file size.
+     my $fileSize = -s $fileName;
          # Get the relation data.
          my $relation = $self->_FindRelation($relationName);
          # Check the truncation flag.
          if ($truncateFlag) {
-                 Trace("Creating table $relationName") if T(1);
+         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
+         # 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);
                  # Re-create the table without its index.
-                 $self->CreateTable($relationName, 0);
+         $self->CreateTable($relationName, 0, $estimate);
+         # If this is a pre-index DBMS, create the index here.
+         if ($dbh->{_preIndex}) {
+             eval {
+                 $self->CreateIndex($relationName);
+             };
+             if ($@) {
+                 $retVal->AddMessage($@);
+             }
+         }
          }
-         # Determine whether or not this is a primary relation. Primary relations have an extra
-         # field indicating whether or not a given object is new or was loaded from the flat files.
-         my $primary = $self->_IsPrimary($relationName);
-         # Get the number of fields in this relation.
-         my @fieldList = @{$relation->{Fields}};
-         my $fieldCount = @fieldList;
-         # Record the number of expected fields.
-         my $expectedFields = $fieldCount + ($primary ? 1 : 0);
-         # Start a database transaction.
-         $dbh->begin_tran;
-         # Open the relation file. We need to create a cleaned-up copy before loading.
-         open TABLEIN, '<', $fileName;
-         my $tempName = "$fileName.tbl";
-         open TABLEOUT, '>', $tempName;
-         # Loop through the file.
-         while (<TABLEIN>) {
-                 # Chop off the new-line character.
-                 my $record = $_;
-                 chomp $record;
-         # Only proceed if the record is non-blank.
-         if ($record) {
-             # Escape all the backslashes found in the line.
-             $record =~ s/\\/\\\\/g;
-             # Eliminate any trailing tabs.
-             chop $record while substr($record, -1) eq "\t";
-             # If this is a primary relation, add a 0 for the new-record flag (indicating that
-             # this record is not new, but part of the original load).
-             if ($primary) {
-                 $record .= "\t0";
-             }
-             # Write the record.
-             print TABLEOUT "$record\n";
-             # Count the record read.
-             my $count = $retVal->Add('records');
-             my $len = length $record;
-             Trace("Record $count written with $len characters.") if T(4);
-         }
-         }
-         # Close the files.
-         close TABLEIN;
-         close TABLEOUT;
-     Trace("Temporary file $tempName created.") if T(4);
      # Load the table.
          my $rv;
          eval {
-                 $rv = $dbh->load_table(file => $tempName, tbl => $relationName);
+         $rv = $dbh->load_table(file => $fileName, tbl => $relationName);
          };
          if (!defined $rv) {
          $retVal->AddMessage($@) if ($@);
-         $retVal->AddMessage("Table load failed for $relationName using $tempName.");
+         $retVal->AddMessage("Table load failed for $relationName using $fileName.");
                  Trace("Table load failed for $relationName.") if T(1);
          } else {
-                 # Here we successfully loaded the table. Trace the number of records loaded.
+         # Here we successfully loaded the table.
-                 Trace("$retVal->{records} records read for $relationName.") if T(1);
+         $retVal->Add("tables");
+         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) {
+         if ($truncateFlag && ! $dbh->{_preIndex}) {
                          eval {
                                  $self->CreateIndex($relationName);
                          };
-Line 1134
+Line 1729
                          }
                  }
          }
-         # Commit the database changes.
+     # Analyze the table to improve performance.
-         $dbh->commit_tran;
+     $dbh->vacuum_it($relationName);
-         # Delete the temporary file.
-         unlink $tempName;
          # Return the statistics.
          return $retVal;
  }
  =head3 GenerateEntity
- C<< my $fieldHash = $database->GenerateEntity($id, $type, \%values); >>
+ C<< my $fieldHash = $erdb->GenerateEntity($id, $type, \%values); >>
  Generate the data for a new entity instance. This method creates a field hash suitable for
  passing as a parameter to L</InsertObject>. The ID is specified by the callr, but the rest
-Line 1202
+Line 1795
  =head3 GetEntity
- C<< my $entityObject = $sprout->GetEntity($entityType, $ID); >>
+ C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>
  Return an object describing the entity instance with a specified ID.
-Line 1238
+Line 1831
  =head3 GetEntityValues
- C<< my @values = GetEntityValues($entityType, $ID, \@fields); >>
+ C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>
  Return a list of values from a specified entity instance.
-Line 1279
+Line 1872
          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 $parameterList eq "ARRAY") {
+         @parmList = @{$parameterList};
+     } else {
+         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++;
+     }
+     # Return the resulting list.
+     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};
+ }
+ =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;
+ }
  =head2 Internal Utility Methods
  =head3 GetLoadStats
-Line 1290
+Line 2102
  =cut
  sub _GetLoadStats {
-         return Stats->new('records');
+     return Stats->new();
  }
  =head3 GenerateFields
-Line 1485
+Line 2297
          return $objectData->{Relations};
  }
- =head3 GetFieldTable
- Get the field structure for a specified entity or relationship.
- This is an instance method.
- =over 4
- =item objectName
- Name of the desired entity or relationship.
- =item RETURN
- The table containing the field descriptors for the specified object.
- =back
- =cut
- sub _GetFieldTable {
-         # Get the parameters.
-         my ($self, $objectName) = @_;
-         # Get the descriptor from the metadata.
-         my $objectData = $self->_GetStructure($objectName);
-         # Return the object's field table.
-         return $objectData->{Fields};
- }
  =head3 ValidateFieldNames
  Determine whether or not the field names are valid. A description of the problems with the names
-Line 1654
+Line 2437
  sub _LoadMetaData {
          # Get the parameters.
          my ($filename) = @_;
+     Trace("Reading Sprout DBD from $filename.") if T(2);
          # Slurp the XML file into a variable. Extensive use of options is used to insure we
          # get the exact structure we want.
          my $metadata = XML::Simple::XMLin($filename,
-Line 1681
+Line 2465
          for my $entityName (keys %{$entityList}) {
                  my $entityStructure = $entityList->{$entityName};
                  #
-                 # The first step is to run creating all the entity's default values. For C<Field> elements,
+         # The first step is to create all the entity's default values. For C<Field> elements,
                  # the relation name must be added where it is not specified. For relationships,
                  # the B<from-link> and B<to-link> fields must be inserted, and for entities an B<id>
                  # field must be added to each relation. Finally, each field will have a C<PrettySort> attribute
-Line 1860
+Line 2644
                  my @fromList = ();
                  my @toList = ();
                  my @bothList = ();
-                 Trace("Join table build for $entityName.") if T(3);
+         Trace("Join table build for $entityName.") if T(metadata => 4);
                  for my $relationshipName (keys %{$relationshipList}) {
                          my $relationship = $relationshipList->{$relationshipName};
                          # 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(3);
+             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.
                                          push @bothList, $relationshipName;
-                                         Trace("Relationship $relationshipName put in both-list.") if T(3);
+                     Trace("Relationship $relationshipName put in both-list.") if T(metadata => 4);
                                  } else {
                                          # Here the relationship comes from the entity.
                                          push @fromList, $relationshipName;
-                                         Trace("Relationship $relationshipName put in from-list.") if T(3);
+                     Trace("Relationship $relationshipName put in from-list.") if T(metadata => 4);
                                  }
                          } elsif ($toEntity eq $entityName) {
                                  # Here the relationship goes to the entity.
                                  push @toList, $relationshipName;
-                                 Trace("Relationship $relationshipName put in to-list.") if T(3);
+                 Trace("Relationship $relationshipName put in to-list.") if T(metadata => 4);
                          }
                  }
                  # Create the nonrecursive joins. Note that we build two hashes for running
-Line 1896
+Line 2680
                                  # Create joins between the entity and this relationship.
                                  my $linkField = "$relationshipName.${linkType}_link";
                                  my $joinClause = "$entityName.id = $linkField";
-                                 Trace("Entity join clause is $joinClause for $entityName and $relationshipName.") if T(4);
+                 Trace("Entity join clause is $joinClause for $entityName and $relationshipName.") if T(metadata => 4);
                                  $joinTable{"$entityName/$relationshipName"} = $joinClause;
                                  $joinTable{"$relationshipName/$entityName"} = $joinClause;
                                  # Create joins between this relationship and the other relationships.
-Line 1917
+Line 2701
                                                          # relationship and itself are prohibited.
                                                          my $relJoinClause = "$otherName.${otherType}_link = $linkField";
                                                          $joinTable{$joinKey} = $relJoinClause;
-                                                         Trace("Relationship join clause is $relJoinClause for $joinKey.") if T(4);
+                             Trace("Relationship join clause is $relJoinClause for $joinKey.") if T(metadata => 4);
                                                  }
                                          }
                                  }
-Line 1926
+Line 2710
                                  # relationship can only be ambiguous with another recursive relationship,
                                  # and the incoming relationship from the outer loop is never recursive.
                                  for my $otherName (@bothList) {
-                                         Trace("Setting up relationship joins to recursive relationship $otherName with $relationshipName.") if T(3);
+                     Trace("Setting up relationship joins to recursive relationship $otherName with $relationshipName.") if T(metadata => 4);
                                          # Join from the left.
                                          $joinTable{"$relationshipName/$otherName"} =
                                                  "$linkField = $otherName.from_link";
-Line 1941
+Line 2725
                  # rise to situations where we can't create the path we want; however, it is always
                  # possible to get the same effect using multiple queries.
                  for my $relationshipName (@bothList) {
-                         Trace("Setting up entity joins to recursive relationship $relationshipName with $entityName.") if T(3);
+             Trace("Setting up entity joins to recursive relationship $relationshipName with $entityName.") if T(metadata => 4);
                          # Join to the entity from each direction.
                          $joinTable{"$entityName/$relationshipName"} =
                                  "$entityName.id = $relationshipName.from_link";
-Line 1955
+Line 2739
          return $metadata;
  }
+ =head3 SortNeeded
+ C<< my $flag = $erdb->SortNeeded($relationName); >>
+ Return TRUE if the specified relation should be sorted during loading to remove duplicate keys,
+ else FALSE.
+ =over 4
+ =item relationName
+ Name of the relation to be examined.
+ =item RETURN
+ Returns TRUE if the relation needs a sort, else FALSE.
+ =back
+ =cut
+ #: Return Type $;
+ sub SortNeeded {
+     # Get the parameters.
+     my ($self, $relationName) = @_;
+     # Declare the return variable.
+     my $retVal = 0;
+     # Find out if the relation is a primary entity relation.
+     my $entityTable = $self->{_metaData}->{Entities};
+     if (exists $entityTable->{$relationName}) {
+         my $keyType = $entityTable->{$relationName}->{keyType};
+         Trace("Relation $relationName found in entity table with key type $keyType.") if T(3);
+         # If the key is not a hash string, we must do the sort.
+         if ($keyType ne 'hash-string') {
+             $retVal = 1;
+         }
+     }
+     # Return the result.
+     return $retVal;
+ }
  =head3 CreateRelationshipIndex
  Create an index for a relationship's relation.
-Line 1992
+Line 2816
          # index descriptor does not exist, it will be created automatically so we can add
          # the field to it.
          unshift @{$newIndex->{IndexFields}}, $firstField;
+     # If this is a one-to-many relationship, the "To" index is unique.
+     if ($relationshipStructure->{arity} eq "1M" && $indexKey eq "To") {
+         $newIndex->{Unique} = 'true';
+     }
          # Add the index to the relation.
          _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);
  }
-Line 2083
+Line 2911
                  # Here we have a field list. Loop through its fields.
                  my $fieldStructures = $structure->{Fields};
                  for my $fieldName (keys %{$fieldStructures}) {
+             Trace("Processing field $fieldName of $defaultRelationName.") if T(4);
                          my $fieldData = $fieldStructures->{$fieldName};
                          # Get the field type.
                          my $type = $fieldData->{type};

 Legend:



Removed from v.1.6
 


changed lines


 
Added in v.1.43
 Legend:



Removed from v.1.6
 


changed lines


 
Added in v.1.43
-Removed from v.1.6
+Added in v.1.43

MCS Webmaster	ViewVC Help
Powered by ViewVC 1.0.3