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

Diff of /Sprout/ERDB.pm

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

revision 1.70, Fri Oct 13 21:45:11 2006 UTC revision 1.89, Thu Apr 12 05:59:41 2007 UTC
# Line 6  Line 6 
6      use Data::Dumper;      use Data::Dumper;
7      use XML::Simple;      use XML::Simple;
8      use DBQuery;      use DBQuery;
9      use DBObject;      use ERDBObject;
10      use Stats;      use Stats;
11      use Time::HiRes qw(gettimeofday);      use Time::HiRes qw(gettimeofday);
12      use Digest::MD5 qw(md5_base64);      use Digest::MD5 qw(md5_base64);
13      use FIG;      use FIG;
14        use CGI;
15    
16  =head1 Entity-Relationship Database Package  =head1 Entity-Relationship Database Package
17    
# Line 59  Line 60 
60  B<start-position>, which indicates where in the contig that the sequence begins. This attribute  B<start-position>, which indicates where in the contig that the sequence begins. This attribute
61  is implemented as the C<start_position> field in the C<IsMadeUpOf> relation.  is implemented as the C<start_position> field in the C<IsMadeUpOf> relation.
62    
63  The database itself is described by an XML file using the F<ERDatabase.xsd> schema. In addition to  The database itself is described by an XML file. In addition to all the data required to define
64  all the data required to define the entities, relationships, and attributes, the schema provides  the entities, relationships, and attributes, the schema provides space for notes describing
65  space for notes describing the data and what it means. These notes are used by L</ShowMetaData>  the data and what it means. These notes are used by L</ShowMetaData> to generate documentation
66  to generate documentation for the database.  for the database.
67    
68    Special support is provided for text searching. An entity field can be marked as <em>searchable</em>,
69    in which case it will be used to generate a text search index in which the user searches for words
70    in the field instead of a particular field value.
71    
72  Finally, every entity and relationship object has a flag indicating if it is new or old. The object  Finally, every entity and relationship object has a flag indicating if it is new or old. The object
73  is considered I<old> if it was loaded by the L</LoadTables> method. It is considered I<new> if it  is considered I<old> if it was loaded by the L</LoadTables> method. It is considered I<new> if it
74  was inserted by the L</InsertObject> method.  was inserted by the L</InsertObject> method.
75    
 To facilitate testing, the ERDB module supports automatic generation of test data. This process  
 is described in the L</GenerateEntity> and L</GenerateConnection> methods, though it is not yet  
 fully implemented.  
   
76  =head2 XML Database Description  =head2 XML Database Description
77    
78  =head3 Data Types  =head3 Data Types
# Line 217  Line 218 
218  index will be created for each relation with at least one searchable field in it.  index will be created for each relation with at least one searchable field in it.
219  For best results, this option should only be used for string or text fields.  For best results, this option should only be used for string or text fields.
220    
221    =item special
222    
223    This attribute allows the subclass to assign special meaning for certain fields.
224    The interpretation is up to the subclass itself. Currently, only entity fields
225    can have this attribute.
226    
227  =back  =back
228    
229  =head3 Indexes  =head3 Indexes
230    
231  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
232  be from the primary relation. The alternate indexes assist in ordering results  index must all be from the same relation. The alternate indexes assist in searching
233  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
234  I<from-index>. These order the results when crossing the relationship. For  I<from-index> that order the results when crossing the relationship. For
235  example, in the relationship C<HasContig> from C<Genome> to C<Contig>, the  example, in the relationship C<HasContig> from C<Genome> to C<Contig>, the
236  from-index would order the contigs of a ganome, and the to-index would order  from-index would order the contigs of a ganome, and the to-index would order
237  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
238    indexes. A relationship's index must specify only fields in
239  the relationship.  the relationship.
240    
241  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.
242  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
243  using the B<ToIndex> tag.  specified using the B<ToIndex> tag.
244    
245  Each index can contain a B<Notes> tag. In addition, it will have an B<IndexFields>  Each index can contain a B<Notes> tag. In addition, it will have an B<IndexFields>
246  tag containing the B<IndexField> tags. These specify, in order, the fields used in  tag containing the B<IndexField> tags. These specify, in order, the fields used in
# Line 250  Line 258 
258    
259  =back  =back
260    
261  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
262    have a B<Unique> attribute. If specified, the index will be generated as a unique
263    index.
264    
265  =head3 Object and Field Names  =head3 Object and Field Names
266    
# Line 294  Line 304 
304    
305  A relationship is described by the C<Relationship> tag. Within a relationship,  A relationship is described by the C<Relationship> tag. Within a relationship,
306  there can be a C<Notes> tag, a C<Fields> tag containing the intersection data  there can be a C<Notes> tag, a C<Fields> tag containing the intersection data
307  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
308  the to-index.  the to-index, and an C<Indexes> tag containing the alternate indexes.
309    
310  The C<Relationship> tag has the following attributes.  The C<Relationship> tag has the following attributes.
311    
# Line 328  Line 338 
338    
339  # Table of information about our datatypes. "sqlType" is the corresponding SQL datatype string.  # Table of information about our datatypes. "sqlType" is the corresponding SQL datatype string.
340  # "maxLen" is the maximum permissible length of the incoming string data used to populate a field  # "maxLen" is the maximum permissible length of the incoming string data used to populate a field
341  # of the specified type. "dataGen" is PERL string that will be evaluated if no test data generation  # of the specified type. "avgLen" is the average byte length for estimating
342  # string is specified in the field definition. "avgLen" is the average byte length for estimating  # record sizes. "sort" is the key modifier for the sort command, "notes" is a type description,
343  # record sizes. "sort" is the key modifier for the sort command.  # and "indexMod", if non-zero, is the number of characters to use when the field is specified in an
344  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",  dataGen => "StringGen('A')" },  # index
345                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n", dataGen => "IntGen(0, 99999999)" },  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",
346                    counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n", dataGen => "IntGen(0, 99999999)" },                                 indexMod =>   0, notes => "single ASCII character"},
347                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, sort => "",  dataGen => "StringGen(IntGen(10,250))" },                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n",
348                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, sort => "",  dataGen => "StringGen(IntGen(80,1000))" },                                 indexMod =>   0, notes => "signed 32-bit integer"},
349                    date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, sort => "n", dataGen => "DateGen(-7, 7, IntGen(0,1400))" },                    counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n",
350                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, sort => "g", dataGen => "FloatGen(0.0, 100.0)" },                                 indexMod =>   0, notes => "unsigned 32-bit integer"},
351                    boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, sort => "n", dataGen => "IntGen(0, 1)" },                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, sort => "",
352                                   indexMod =>   0, notes => "character string, 0 to 255 characters"},
353                      text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, sort => "",
354                                   indexMod => 255, notes => "character string, nearly unlimited length, only first 255 characters are indexed"},
355                      date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, sort => "n",
356                                   indexMod =>   0, notes => "signed, 64-bit integer"},
357                      float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, sort => "g",
358                                   indexMod =>   0, notes => "64-bit double precision floating-point number"},
359                      boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, sort => "n",
360                                   indexMod =>   0, notes => "boolean value: 0 if false, 1 if true"},
361                   'hash-string' =>                   'hash-string' =>
362                               { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, sort => "",  dataGen => "SringGen(22)" },                               { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, sort => "",
363                                   indexMod =>   0, notes => "string stored in digested form, used for certain types of key fields"},
364                   'id-string' =>                   'id-string' =>
365                               { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, sort => "",  dataGen => "SringGen(22)" },                               { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, sort => "",
366                                   indexMod =>   0, notes => "character string, 0 to 25 characters"},
367                   'key-string' =>                   'key-string' =>
368                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, sort => "",  dataGen => "StringGen(IntGen(10,40))" },                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, sort => "",
369                                   indexMod =>   0, notes => "character string, 0 to 40 characters"},
370                   'name-string' =>                   'name-string' =>
371                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, sort => "",  dataGen => "StringGen(IntGen(10,80))" },                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, sort => "",
372                                   indexMod =>   0, notes => "character string, 0 to 80 characters"},
373                   'medium-string' =>                   'medium-string' =>
374                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",  dataGen => "StringGen(IntGen(10,160))" },                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",
375                                   indexMod =>   0, notes => "character string, 0 to 160 characters"},
376                  );                  );
377    
378  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 357  Line 381 
381                     'MM' => 'many-to-many'                     'MM' => 'many-to-many'
382                   );                   );
383    
384  # Table for interpreting string patterns.  # Options for XML input and output.
385    
386    my %XmlOptions = (GroupTags =>  { Relationships => 'Relationship',
387                                      Entities => 'Entity',
388                                      Fields => 'Field',
389                                      Indexes => 'Index',
390                                      IndexFields => 'IndexField'
391                                    },
392                      KeyAttr =>    { Relationship => 'name',
393                                      Entity => 'name',
394                                      Field => 'name'
395                                    },
396                      SuppressEmpty => 1,
397                     );
398    
399  my %PictureTable = ( 'A' => "abcdefghijklmnopqrstuvwxyz",  my %XmlInOpts  = (
400                       '9' => "0123456789",                    ForceArray => ['Field', 'Index', 'IndexField', 'Relationship', 'Entity'],
401                       'X' => "abcdefghijklmnopqrstuvwxyz0123456789",                    ForceContent => 1,
402                       'V' => "aeiou",                    NormalizeSpace => 2,
403                       'K' => "bcdfghjklmnoprstvwxyz"                   );
404    my %XmlOutOpts = (
405                      RootName => 'Database',
406                      XMLDecl => 1,
407                     );                     );
408    
409    
410  =head2 Public Methods  =head2 Public Methods
411    
412  =head3 new  =head3 new
# Line 506  Line 547 
547          my $entityData = $entityList->{$key};          my $entityData = $entityList->{$key};
548          # If there's descriptive text, display it.          # If there's descriptive text, display it.
549          if (my $notes = $entityData->{Notes}) {          if (my $notes = $entityData->{Notes}) {
550              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
551          }          }
552          # 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.
553            my $relCount = keys %{$relationshipList};
554            if ($relCount > 0) {
555                # First, we set up the relationship subsection.
556          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
557          # Loop through the relationships.          # Loop through the relationships.
558          for my $relationship (sort keys %{$relationshipList}) {          for my $relationship (sort keys %{$relationshipList}) {
# Line 524  Line 568 
568          }          }
569          # Close off the relationship list.          # Close off the relationship list.
570          $retVal .= "</ul>\n";          $retVal .= "</ul>\n";
571            }
572          # Get the entity's relations.          # Get the entity's relations.
573          my $relationList = $entityData->{Relations};          my $relationList = $entityData->{Relations};
574          # Create a header for the relation subsection.          # Create a header for the relation subsection.
# Line 563  Line 608 
608          $retVal .= "</p>\n";          $retVal .= "</p>\n";
609          # If there are notes on this relationship, display them.          # If there are notes on this relationship, display them.
610          if (my $notes = $relationshipStructure->{Notes}) {          if (my $notes = $relationshipStructure->{Notes}) {
611              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
612          }          }
613          # Generate the relationship's relation table.          # Generate the relationship's relation table.
614          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
# Line 610  Line 655 
655      return Data::Dumper::Dumper($self->{_metaData});      return Data::Dumper::Dumper($self->{_metaData});
656  }  }
657    
658    =head3 CreatePPO
659    
660    C<< ERDB::CreatePPO($erdbXMLFile, $ppoXMLFile); >>
661    
662    Create a PPO XML file from an ERDB data definition XML file. At the
663    current time, the PPO XML file can be used to create a database with
664    similar functionality. Eventually, the PPO will be able to use the
665    created XML to access the live ERDB database.
666    
667    =over 4
668    
669    =item erdbXMLFile
670    
671    Name of the XML data definition file for the ERDB database. This
672    file must exist.
673    
674    =item ppoXMLFile
675    
676    Output file for the PPO XML definition. If this file exists, it
677    will be overwritten.
678    
679    =back
680    
681    =cut
682    
683    sub CreatePPO {
684        # Get the parameters.
685        my ($erdbXMLFile, $ppoXMLFile) = @_;
686        # First, we want to slurp in the ERDB XML file in its raw form.
687        my $xml = ReadMetaXML($erdbXMLFile);
688        # Create a variable to hold all of the objects in the PPO project.
689        my @objects = ();
690        # Get the relationship hash.
691        my $relationships = $xml->{Relationships};
692        # Loop through the entities.
693        my $entities = $xml->{Entities};
694        for my $entityName (keys %{$entities}) {
695            # Get the entity's data structures.
696            my $entityObject = $entities->{$entityName};
697            # We put the object's fields in here, according to their type.
698            my (@object_refs, @scalars, @indexes, @arrays);
699            # Create the ID field for the entity. We get the key type from the
700            # entity object and compute the corresponding SQL type.
701            my $type = $TypeTable{$entityObject->{keyType}}->{sqlType};
702            push @scalars, { label => 'id', type => $type };
703            # Loop through the entity fields.
704            for my $fieldName ( keys %{$entityObject->{Fields}} ) {
705                # Get the field object.
706                my $fieldObject = $entityObject->{Fields}->{$fieldName};
707                # Convert it to a scalar tag.
708                my $scalar = _CreatePPOField($fieldName, $fieldObject);
709                # If we have a relation, this field is stored in an array.
710                # otherwise, it is a scalar. The array tag has scalars
711                # stored as an XML array. In ERDB, there is only ever one,
712                # but PPO can have more.
713                my $relation = $fieldObject->{relation};
714                if ($relation) {
715                    push @arrays, { scalar => [$scalar] };
716                } else {
717                    push @scalars, $scalar;
718                }
719            }
720            # Loop through the relationships. If this entity is the to-entity
721            # on a relationship of 1M arity, then it is implemented as a PPO
722            # object reference.
723            for my $relationshipName (keys %{$relationships}) {
724                # Get the relationship data.
725                my $relationshipData = $relationships->{$relationshipName};
726                # If we have a from for this entity and an arity of 1M, we
727                # have an object reference.
728                if ($relationshipData->{to} eq $entityName &&
729                    $relationshipData->{arity} eq '1M') {
730                    # Build the object reference tag.
731                    push @object_refs, { label => $relationshipName,
732                                         type => $relationshipData->{from} };
733                }
734            }
735            # Create the indexes.
736            my $indexList = $entityObject->{Indexes};
737            push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
738            # Build the object XML tree.
739            my $object = { label => $entityName,
740                           object_ref => \@object_refs,
741                           scalar => \@scalars,
742                           index => \@indexes,
743                           array => \@arrays
744                          };
745            # Push the object onto the objects list.
746            push @objects, $object;
747        }
748        # Loop through the relationships, searching for MMs. The 1Ms were
749        # already handled by the entity search above.
750        for my $relationshipName (keys %{$relationships}) {
751            # Get this relationship's object.
752            my $relationshipObject = $relationships->{$relationshipName};
753            # Only proceed if it's many-to-many.
754            if ($relationshipObject->{arity} eq 'MM') {
755                # Create the tag lists for the relationship object.
756                my (@object_refs, @scalars, @indexes);
757                # The relationship will be created as an object with object
758                # references for its links to the participating entities.
759                my %links = ( from => $relationshipObject->{from},
760                              to => $relationshipObject->{to} );
761                for my $link (keys %links) {
762                    # Create an object_ref tag for this piece of the
763                    # relationship (from or to).
764                    my $object_ref = { label => $link,
765                                       type => $links{$link} };
766                    push @object_refs, $object_ref;
767                }
768                # Loop through the intersection data fields, creating scalar tags.
769                # There are no fancy array tags in a relationship.
770                for my $fieldName (keys %{$relationshipObject->{Fields}}) {
771                    my $fieldObject = $relationshipObject->{Fields}->{$fieldName};
772                    push @scalars, _CreatePPOField($fieldName, $fieldObject);
773                }
774                # Finally, the indexes: currently we cannot support the to-index and
775                # from-index in PPO, so we just process the alternate indexes.
776                my $indexList = $relationshipObject->{Indexes};
777                push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
778                # Wrap up all the stuff about this relationship.
779                my $object = { label => $relationshipName,
780                               scalar => \@scalars,
781                               object_ref => \@object_refs,
782                               index => \@indexes
783                             };
784                # Push it into the object list.
785                push @objects, $object;
786            }
787        }
788        # Compute a title.
789        my $title;
790        if ($erdbXMLFile =~ /\/([^\/]+)DBD\.xml/) {
791            # Here we have a standard file name we can use for a title.
792            $title = $1;
793        } else {
794            # Here the file name is non-standard, so we carve up the
795            # database title.
796            $title = $xml->{Title}->{content};
797            $title =~ s/\s\.,//g;
798        }
799        # Wrap up the XML as a project.
800        my $ppoXML = { project => { label => $title,
801                                    object => \@objects }};
802        # Write out the results.
803        my $ppoString = XML::Simple::XMLout($ppoXML,
804                                            AttrIndent => 1,
805                                            KeepRoot => 1);
806        Tracer::PutFile($ppoXMLFile, [ $ppoString ]);
807    }
808    
809    
810    
811    =head3 FindIndexForEntity
812    
813    C<< my $indexFound = ERDB::FindIndexForEntity($xml, $entityName, $attributeName); >>
814    
815    This method locates the entry in an entity's index list that begins with the
816    specified attribute name. If the entity has no index list, one will be
817    created. This method works on raw XML, not a live ERDB object.
818    
819    =over 4
820    
821    =item xml
822    
823    The raw XML structure defining the database.
824    
825    =item entityName
826    
827    The name of the relevant entity.
828    
829    =item attributeName
830    
831    The name of the attribute relevant to the search.
832    
833    =item RETURN
834    
835    The numerical index in the index list of the index entry for the specified entity and
836    attribute, or C<undef> if no such index exists.
837    
838    =back
839    
840    =cut
841    
842    sub FindIndexForEntity {
843        # Get the parameters.
844        my ($xml, $entityName, $attributeName) = @_;
845        # Declare the return variable.
846        my $retVal;
847        # Get the named entity.
848        my $entityData = $xml->{Entities}->{$entityName};
849        if (! $entityData) {
850            Confess("Entity $entityName not found in DBD structure.");
851        } else {
852            # Insure it has an index list.
853            if (! exists $entityData->{Indexes}) {
854                $entityData->{Indexes} = [];
855            } else {
856                # Search for the desired index.
857                my $indexList = $entityData->{Indexes};
858                my $n = scalar @{$indexList};
859                Trace("Searching $n indexes in index list for $entityName.") if T(2);
860                # We use an indexed FOR here because we're returning an
861                # index number instead of an object. We do THAT so we can
862                # delete the index from the list if needed.
863                for (my $i = 0; $i < $n && !defined($retVal); $i++) {
864                    my $index = $indexList->[$i];
865                    my $fields = $index->{IndexFields};
866                    # Technically this IF should be safe (that is, we are guaranteed
867                    # the existence of a "$fields->[0]"), because when we load the XML
868                    # we have SuppressEmpty specified.
869                    if ($fields->[0]->{name} eq $attributeName) {
870                        $retVal = $i;
871                    }
872                }
873            }
874        }
875        Trace("Index for $attributeName of $entityName found at position $retVal.") if defined($retVal) && T(3);
876        Trace("Index for $attributeName not found in $entityName.") if !defined($retVal) && T(3);
877        # Return the result.
878        return $retVal;
879    }
880    
881  =head3 CreateTables  =head3 CreateTables
882    
883  C<< $erdb->CreateTables(); >>  C<< $erdb->CreateTables(); >>
# Line 629  Line 897 
897      # Loop through the relations.      # Loop through the relations.
898      for my $relationName (@relNames) {      for my $relationName (@relNames) {
899          # Create a table for this relation.          # Create a table for this relation.
900          $self->CreateTable($relationName);          $self->CreateTable($relationName, 1);
901          Trace("Relation $relationName created.") if T(2);          Trace("Relation $relationName created.") if T(2);
902      }      }
903  }  }
# Line 855  Line 1123 
1123      for my $indexName (keys %{$indexHash}) {      for my $indexName (keys %{$indexHash}) {
1124          my $indexData = $indexHash->{$indexName};          my $indexData = $indexHash->{$indexName};
1125          # Get the index's field list.          # Get the index's field list.
1126          my @fieldList = _FixNames(@{$indexData->{IndexFields}});          my @rawFields = @{$indexData->{IndexFields}};
1127            # Get a hash of the relation's field types.
1128            my %types = map { $_->{name} => $_->{type} } @{$relationData->{Fields}};
1129            # We need to check for text fields so we can append a length limitation for them. To do
1130            # that, we need the relation's field list.
1131            my $relFields = $relationData->{Fields};
1132            for (my $i = 0; $i <= $#rawFields; $i++) {
1133                # Get the field type.
1134                my $field = $rawFields[$i];
1135                my $type = $types{$field};
1136                # Ask if it requires using prefix notation for the index.
1137                my $mod = $TypeTable{$type}->{indexMod};
1138                Trace("Field $field ($i) in $relationName has type $type and indexMod $mod.") if T(3);
1139                if ($mod) {
1140                    # Append the prefix length to the field name,
1141                    $rawFields[$i] .= "($mod)";
1142                }
1143            }
1144            my @fieldList = _FixNames(@rawFields);
1145          my $flds = join(', ', @fieldList);          my $flds = join(', ', @fieldList);
1146          # Get the index's uniqueness flag.          # Get the index's uniqueness flag.
1147          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
# Line 870  Line 1156 
1156      }      }
1157  }  }
1158    
1159    =head3 GetSecondaryFields
1160    
1161    C<< my %fieldTuples = $erdb->GetSecondaryFields($entityName); >>
1162    
1163    This method will return a list of the name and type of each of the secondary
1164    fields for a specified entity. Secondary fields are stored in two-column tables
1165    in addition to the primary entity table. This enables the field to have no value
1166    or to have multiple values.
1167    
1168    =over 4
1169    
1170    =item entityName
1171    
1172    Name of the entity whose secondary fields are desired.
1173    
1174    =item RETURN
1175    
1176    Returns a hash mapping the field names to their field types.
1177    
1178    =back
1179    
1180    =cut
1181    
1182    sub GetSecondaryFields {
1183        # Get the parameters.
1184        my ($self, $entityName) = @_;
1185        # Declare the return variable.
1186        my %retVal = ();
1187        # Look for the entity.
1188        my $table = $self->GetFieldTable($entityName);
1189        # Loop through the fields, pulling out the secondaries.
1190        for my $field (sort keys %{$table}) {
1191            if ($table->{$field}->{relation} ne $entityName) {
1192                # Here we have a secondary field.
1193                $retVal{$field} = $table->{$field}->{type};
1194            }
1195        }
1196        # Return the result.
1197        return %retVal;
1198    }
1199    
1200    =head3 GetFieldRelationName
1201    
1202    C<< my $name = $erdb->GetFieldRelationName($objectName, $fieldName); >>
1203    
1204    Return the name of the relation containing a specified field.
1205    
1206    =over 4
1207    
1208    =item objectName
1209    
1210    Name of the entity or relationship containing the field.
1211    
1212    =item fieldName
1213    
1214    Name of the relevant field in that entity or relationship.
1215    
1216    =item RETURN
1217    
1218    Returns the name of the database relation containing the field, or C<undef> if
1219    the field does not exist.
1220    
1221    =back
1222    
1223    =cut
1224    
1225    sub GetFieldRelationName {
1226        # Get the parameters.
1227        my ($self, $objectName, $fieldName) = @_;
1228        # Declare the return variable.
1229        my $retVal;
1230        # Get the object field table.
1231        my $table = $self->GetFieldTable($objectName);
1232        # Only proceed if the field exists.
1233        if (exists $table->{$fieldName}) {
1234            # Determine the name of the relation that contains this field.
1235            $retVal = $table->{$fieldName}->{relation};
1236        }
1237        # Return the result.
1238        return $retVal;
1239    }
1240    
1241    =head3 DeleteValue
1242    
1243    C<< my $numDeleted = $erdb->DeleteValue($entityName, $id, $fieldName, $fieldValue); >>
1244    
1245    Delete secondary field values from the database. This method can be used to delete all
1246    values of a specified field for a particular entity instance, or only a single value.
1247    
1248    Secondary fields are stored in two-column relations separate from an entity's primary
1249    table, and as a result a secondary field can legitimately have no value or multiple
1250    values. Therefore, it makes sense to talk about deleting secondary fields where it
1251    would not make sense for primary fields.
1252    
1253    =over 4
1254    
1255    =item entityName
1256    
1257    Name of the entity from which the fields are to be deleted.
1258    
1259    =item id
1260    
1261    ID of the entity instance to be processed. If the instance is not found, this
1262    method will have no effect. If C<undef> is specified, all values for all of
1263    the entity instances will be deleted.
1264    
1265    =item fieldName
1266    
1267    Name of the field whose values are to be deleted.
1268    
1269    =item fieldValue (optional)
1270    
1271    Value to be deleted. If not specified, then all values of the specified field
1272    will be deleted for the entity instance. If specified, then only the values which
1273    match this parameter will be deleted.
1274    
1275    =item RETURN
1276    
1277    Returns the number of rows deleted.
1278    
1279    =back
1280    
1281    =cut
1282    
1283    sub DeleteValue {
1284        # Get the parameters.
1285        my ($self, $entityName, $id, $fieldName, $fieldValue) = @_;
1286        # Declare the return value.
1287        my $retVal = 0;
1288        # We need to set up an SQL command to do the deletion. First, we
1289        # find the name of the field's relation.
1290        my $table = $self->GetFieldTable($entityName);
1291        my $field = $table->{$fieldName};
1292        my $relation = $field->{relation};
1293        # Make sure this is a secondary field.
1294        if ($relation eq $entityName) {
1295            Confess("Cannot delete values of $fieldName for $entityName.");
1296        } else {
1297            # Set up the SQL command to delete all values.
1298            my $sql = "DELETE FROM $relation";
1299            # Build the filter.
1300            my @filters = ();
1301            my @parms = ();
1302            # Check for a filter by ID.
1303            if (defined $id) {
1304                push @filters, "id = ?";
1305                push @parms, $id;
1306            }
1307            # Check for a filter by value.
1308            if (defined $fieldValue) {
1309                push @filters, "$fieldName = ?";
1310                push @parms, $fieldValue;
1311            }
1312            # Append the filters to the command.
1313            if (@filters) {
1314                $sql .= " WHERE " . join(" AND ", @filters);
1315            }
1316            # Execute the command.
1317            my $dbh = $self->{_dbh};
1318            $retVal = $dbh->SQL($sql, 0, @parms);
1319        }
1320        # Return the result.
1321        return $retVal;
1322    }
1323    
1324  =head3 LoadTables  =head3 LoadTables
1325    
1326  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>
# Line 964  Line 1415 
1415      return sort keys %{$entityList};      return sort keys %{$entityList};
1416  }  }
1417    
1418    =head3 GetDataTypes
1419    
1420    C<< my %types = ERDB::GetDataTypes(); >>
1421    
1422    Return a table of ERDB data types. The table returned is a hash of hashes.
1423    The keys of the big hash are the datatypes. Each smaller hash has several
1424    values used to manage the data. The most interesting is the SQL type (key
1425    C<sqlType>) and the descriptive node (key C<notes>).
1426    
1427    Note that changing the values in the smaller hashes will seriously break
1428    things, so this data should be treated as read-only.
1429    
1430    =cut
1431    
1432    sub GetDataTypes {
1433        return %TypeTable;
1434    }
1435    
1436    
1437  =head3 IsEntity  =head3 IsEntity
1438    
1439  C<< my $flag = $erdb->IsEntity($entityName); >>  C<< my $flag = $erdb->IsEntity($entityName); >>
# Line 1108  Line 1578 
1578      return $retVal;      return $retVal;
1579  }  }
1580    
1581    
1582    
1583  =head3 Search  =head3 Search
1584    
1585  C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>  C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>
# Line 1121  Line 1593 
1593    
1594  =item searchExpression  =item searchExpression
1595    
1596  Boolean search expression for the text fields of the target object.  Boolean search expression for the text fields of the target object. The default mode for
1597    a Boolean search expression is OR, but we want the default to be AND, so we will
1598    add a C<+> operator to each word with no other operator before it.
1599    
1600  =item idx  =item idx
1601    
# Line 1158  Line 1632 
1632      my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;      my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1633      # Declare the return variable.      # Declare the return variable.
1634      my $retVal;      my $retVal;
1635      # Create a safety copy of the parameter list.      # Create a safety copy of the parameter list. Note we have to be careful to insure
1636      my @myParams = @{$params};      # a parameter list exists before we copy it.
1637        my @myParams = ();
1638        if (defined $params) {
1639            @myParams = @{$params};
1640        }
1641      # Get the first object's structure so we have access to the searchable fields.      # Get the first object's structure so we have access to the searchable fields.
1642      my $object1Name = $objectNames->[$idx];      my $object1Name = $objectNames->[$idx];
1643      my $object1Structure = $self->_GetStructure($object1Name);      my $object1Structure = $self->_GetStructure($object1Name);
# Line 1169  Line 1647 
1647      } else {      } else {
1648          # Get the field list.          # Get the field list.
1649          my @fields = @{$object1Structure->{searchFields}};          my @fields = @{$object1Structure->{searchFields}};
1650            # Clean the search expression.
1651            my $actualKeywords = $self->CleanKeywords($searchExpression);
1652            # Prefix a "+" to each uncontrolled word. This converts the default
1653            # search mode from OR to AND.
1654            $actualKeywords =~ s/(^|\s)(\w|")/$1\+$2/g;
1655            Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1656          # We need two match expressions, one for the filter clause and one in the          # We need two match expressions, one for the filter clause and one in the
1657          # query itself. Both will use a parameter mark, so we need to push the          # query itself. Both will use a parameter mark, so we need to push the
1658          # search expression onto the front of the parameter list twice.          # search expression onto the front of the parameter list twice.
1659          unshift @myParams, $searchExpression, $searchExpression;          unshift @myParams, $actualKeywords, $actualKeywords;
1660          # Build the match expression.          # Build the match expression.
1661          my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;          my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
1662          my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";          my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
# Line 1246  Line 1730 
1730      return @retVal;      return @retVal;
1731  }  }
1732    
1733    =head3 SpecialFields
1734    
1735    C<< my %specials = $erdb->SpecialFields($entityName); >>
1736    
1737    Return a hash mapping special fields in the specified entity to the value of their
1738    C<special> attribute. This enables the subclass to get access to the special field
1739    attributes without needed to plumb the internal ERDB data structures.
1740    
1741    =over 4
1742    
1743    =item entityName
1744    
1745    Name of the entity whose special fields are desired.
1746    
1747    =item RETURN
1748    
1749    Returns a hash. The keys of the hash are the special field names, and the values
1750    are the values from each special field's C<special> attribute.
1751    
1752    =back
1753    
1754    =cut
1755    
1756    sub SpecialFields {
1757        # Get the parameters.
1758        my ($self, $entityName) = @_;
1759        # Declare the return variable.
1760        my %retVal = ();
1761        # Find the entity's data structure.
1762        my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1763        # Loop through its fields, adding each special field to the return hash.
1764        my $fieldHash = $entityData->{Fields};
1765        for my $fieldName (keys %{$fieldHash}) {
1766            my $fieldData = $fieldHash->{$fieldName};
1767            if (exists $fieldData->{special}) {
1768                $retVal{$fieldName} = $fieldData->{special};
1769            }
1770        }
1771        # Return the result.
1772        return %retVal;
1773    }
1774    
1775  =head3 Delete  =head3 Delete
1776    
1777  C<< my $stats = $erdb->Delete($entityName, $objectID); >>  C<< my $stats = $erdb->Delete($entityName, $objectID, %options); >>
1778    
1779  Delete an entity instance from the database. The instance is deleted along with all entity and  Delete an entity instance from the database. The instance is deleted along with all entity and
1780  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.
1781  always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many  
1782  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
1783    relationship connected to a dependent entity or if it is the "to" entity connected to a 1-to-many
1784  dependent relationship.  dependent relationship.
1785    
1786  =over 4  =over 4
# Line 1267  Line 1794 
1794  ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),  ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),
1795  then it is presumed to by a LIKE pattern.  then it is presumed to by a LIKE pattern.
1796    
1797  =item testFlag  =item options
1798    
1799  If TRUE, the delete statements will be traced without being executed.  A hash detailing the options for this delete operation.
1800    
1801  =item RETURN  =item RETURN
1802    
# Line 1278  Line 1805 
1805    
1806  =back  =back
1807    
1808    The permissible options for this method are as follows.
1809    
1810    =over 4
1811    
1812    =item testMode
1813    
1814    If TRUE, then the delete statements will be traced, but no changes will be made to the database.
1815    
1816    =item keepRoot
1817    
1818    If TRUE, then the entity instances will not be deleted, only the dependent records.
1819    
1820    =back
1821    
1822  =cut  =cut
1823  #: Return Type $%;  #: Return Type $%;
1824  sub Delete {  sub Delete {
1825      # Get the parameters.      # Get the parameters.
1826      my ($self, $entityName, $objectID, $testFlag) = @_;      my ($self, $entityName, $objectID, %options) = @_;
1827      # Declare the return variable.      # Declare the return variable.
1828      my $retVal = Stats->new();      my $retVal = Stats->new();
1829      # Get the DBKernel object.      # Get the DBKernel object.
# Line 1299  Line 1840 
1840      # FROM-relationships and entities.      # FROM-relationships and entities.
1841      my @fromPathList = ();      my @fromPathList = ();
1842      my @toPathList = ();      my @toPathList = ();
1843      # This final hash is used to remember what work still needs to be done. We push paths      # This final list is used to remember what work still needs to be done. We push paths
1844      # onto the list, then pop them off to extend the paths. We prime it with the starting      # onto the list, then pop them off to extend the paths. We prime it with the starting
1845      # point. Note that we will work hard to insure that the last item on a path in the      # point. Note that we will work hard to insure that the last item on a path in the
1846      # TODO list is always an entity.      # to-do list is always an entity.
1847      my @todoList = ([$entityName]);      my @todoList = ([$entityName]);
1848      while (@todoList) {      while (@todoList) {
1849          # Get the current path.          # Get the current path.
# Line 1310  Line 1851 
1851          # Copy it into a list.          # Copy it into a list.
1852          my @stackedPath = @{$current};          my @stackedPath = @{$current};
1853          # Pull off the last item on the path. It will always be an entity.          # Pull off the last item on the path. It will always be an entity.
1854          my $entityName = pop @stackedPath;          my $myEntityName = pop @stackedPath;
1855          # Add it to the alreadyFound list.          # Add it to the alreadyFound list.
1856          $alreadyFound{$entityName} = 1;          $alreadyFound{$myEntityName} = 1;
1857            # Figure out if we need to delete this entity.
1858            if ($myEntityName ne $entityName || ! $options{keepRoot}) {
1859          # Get the entity data.          # Get the entity data.
1860          my $entityData = $self->_GetStructure($entityName);              my $entityData = $self->_GetStructure($myEntityName);
1861          # 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.  
1862          my $relations = $entityData->{Relations};          my $relations = $entityData->{Relations};
1863          for my $relation (keys %{$relations}) {          for my $relation (keys %{$relations}) {
1864              my @augmentedList = (@stackedPath, $relation);              my @augmentedList = (@stackedPath, $relation);
1865              push @fromPathList, \@augmentedList;              push @fromPathList, \@augmentedList;
1866          }          }
1867            }
1868          # Now we need to look for relationships connected to this entity.          # Now we need to look for relationships connected to this entity.
1869          my $relationshipList = $self->{_metaData}->{Relationships};          my $relationshipList = $self->{_metaData}->{Relationships};
1870          for my $relationshipName (keys %{$relationshipList}) {          for my $relationshipName (keys %{$relationshipList}) {
1871              my $relationship = $relationshipList->{$relationshipName};              my $relationship = $relationshipList->{$relationshipName};
1872              # Check the FROM field. We're only interested if it's us.              # Check the FROM field. We're only interested if it's us.
1873              if ($relationship->{from} eq $entityName) {              if ($relationship->{from} eq $myEntityName) {
1874                  # Add the path to this relationship.                  # Add the path to this relationship.
1875                  my @augmentedList = (@stackedPath, $entityName, $relationshipName);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1876                  push @fromPathList, \@augmentedList;                  push @fromPathList, \@augmentedList;
1877                  # Check the arity. If it's MM we're done. If it's 1M                  # Check the arity. If it's MM we're done. If it's 1M
1878                  # and the target hasn't been seen yet, we want to                  # and the target hasn't been seen yet, we want to
# Line 1348  Line 1891 
1891              }              }
1892              # Now check the TO field. In this case only the relationship needs              # Now check the TO field. In this case only the relationship needs
1893              # deletion.              # deletion.
1894              if ($relationship->{to} eq $entityName) {              if ($relationship->{to} eq $myEntityName) {
1895                  my @augmentedList = (@stackedPath, $entityName, $relationshipName);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1896                  push @toPathList, \@augmentedList;                  push @toPathList, \@augmentedList;
1897              }              }
1898          }          }
1899      }      }
1900      # Create the first qualifier for the WHERE clause. This selects the      # Create the first qualifier for the WHERE clause. This selects the
1901      # keys of the primary entity records to be deleted. When we're deleting      # keys of the primary entity records to be deleted. When we're deleting
1902      # 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
1903      # to the table containing the dependent records to delete.      # to the table containing the dependent records to delete.
1904      my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");      my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
1905      # We need to make two passes. The first is through the to-list, and      # We need to make two passes. The first is through the to-list, and
# Line 1395  Line 1938 
1938                  }                  }
1939              }              }
1940              # Now we have our desired DELETE statement.              # Now we have our desired DELETE statement.
1941              if ($testFlag) {              if ($options{testMode}) {
1942                  # Here the user wants to trace without executing.                  # Here the user wants to trace without executing.
1943                  Trace($stmt) if T(0);                  Trace($stmt) if T(0);
1944              } else {              } else {
1945                  # 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
1946                  # if an error occurs, so we just go ahead and do it.                  # if an error occurs, so we just go ahead and do it.
1947                  Trace("Executing delete from $target using '$objectID'.") if T(3);                  Trace("Executing delete from $target using '$objectID'.") if T(3);
1948                  my $rv = $db->SQL($stmt, 0, $objectID);                  my $rv = $db->SQL($stmt, 0, $objectID);
# Line 1414  Line 1957 
1957      return $retVal;      return $retVal;
1958  }  }
1959    
1960  =head3 SortNeeded  =head3 Disconnect
   
 C<< my $parms = $erdb->SortNeeded($relationName); >>  
   
 Return the pipe command for the sort that should be applied to the specified  
 relation when creating the load file.  
   
 For example, if the load file should be sorted ascending by the first  
 field, this method would return  
1961    
1962      sort -k1 -t"\t"  C<< $erdb->Disconnect($relationshipName, $originEntityName, $originEntityID); >>
1963    
1964  If the first field is numeric, the method would return  Disconnect an entity instance from all the objects to which it is related. This
1965    will delete each relationship instance that connects to the specified entity.
1966    
1967      sort -k1n -t"\t"  =over 4
1968    
1969  Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate  =item relationshipName
 keys using a sort.  
1970    
1971  =over 4  Name of the relationship whose instances are to be deleted.
1972    
1973  =item relationName  =item originEntityName
1974    
1975  Name of the relation to be examined.  Name of the entity that is to be disconnected.
1976    
1977  =item  =item originEntityID
1978    
1979  Returns the sort command to use for sorting the relation, suitable for piping.  ID of the entity that is to be disconnected.
1980    
1981  =back  =back
1982    
1983  =cut  =cut
1984  #: Return Type $;  
1985  sub SortNeeded {  sub Disconnect {
1986      # Get the parameters.      # Get the parameters.
1987      my ($self, $relationName) = @_;      my ($self, $relationshipName, $originEntityName, $originEntityID) = @_;
1988      # Declare a descriptor to hold the names of the key fields.      # Get the relationship descriptor.
1989      my @keyNames = ();      my $structure = $self->_GetStructure($relationshipName);
1990      # Get the relation structure.      # Insure we have a relationship.
1991      my $relationData = $self->_FindRelation($relationName);      if (! exists $structure->{from}) {
1992      # Find out if the relation is a primary entity relation,          Confess("$relationshipName is not a relationship in the database.");
1993      # a relationship relation, or a secondary entity relation.      } else {
1994      my $entityTable = $self->{_metaData}->{Entities};          # Get the database handle.
1995      my $relationshipTable = $self->{_metaData}->{Relationships};          my $dbh = $self->{_dbh};
1996      if (exists $entityTable->{$relationName}) {          # We'll set this value to 1 if we find our entity.
1997          # Here we have a primary entity relation.          my $found = 0;
1998          push @keyNames, "id";          # Loop through the ends of the relationship.
1999      } elsif (exists $relationshipTable->{$relationName}) {          for my $dir ('from', 'to') {
2000          # Here we have a relationship. We sort using the FROM index.              if ($structure->{$dir} eq $originEntityName) {
2001                    # Delete all relationship instances on this side of the entity instance.
2002                    Trace("Disconnecting in $dir direction with ID \"$originEntityID\".");
2003                    $dbh->SQL("DELETE FROM $relationshipName WHERE ${dir}_link = ?", 0, $originEntityID);
2004                    $found = 1;
2005                }
2006            }
2007            # Insure we found the entity on at least one end.
2008            if (! $found) {
2009                Confess("Entity \"$originEntityName\" does not use $relationshipName.");
2010            }
2011        }
2012    }
2013    
2014    =head3 DeleteRow
2015    
2016    C<< $erdb->DeleteRow($relationshipName, $fromLink, $toLink, \%values); >>
2017    
2018    Delete a row from a relationship. In most cases, only the from-link and to-link are
2019    needed; however, for relationships with intersection data values can be specified
2020    for the other fields using a hash.
2021    
2022    =over 4
2023    
2024    =item relationshipName
2025    
2026    Name of the relationship from which the row is to be deleted.
2027    
2028    =item fromLink
2029    
2030    ID of the entity instance in the From direction.
2031    
2032    =item toLink
2033    
2034    ID of the entity instance in the To direction.
2035    
2036    =item values
2037    
2038    Reference to a hash of other values to be used for filtering the delete.
2039    
2040    =back
2041    
2042    =cut
2043    
2044    sub DeleteRow {
2045        # Get the parameters.
2046        my ($self, $relationshipName, $fromLink, $toLink, $values) = @_;
2047        # Create a hash of all the filter information.
2048        my %filter = ('from-link' => $fromLink, 'to-link' => $toLink);
2049        if (defined $values) {
2050            for my $key (keys %{$values}) {
2051                $filter{$key} = $values->{$key};
2052            }
2053        }
2054        # Build an SQL statement out of the hash.
2055        my @filters = ();
2056        my @parms = ();
2057        for my $key (keys %filter) {
2058            push @filters, _FixName($key) . " = ?";
2059            push @parms, $filter{$key};
2060        }
2061        Trace("Parms for delete row are " . join(", ", map { "\"$_\"" } @parms) . ".") if T(SQL => 4);
2062        my $command = "DELETE FROM $relationshipName WHERE " .
2063                      join(" AND ", @filters);
2064        # Execute it.
2065        my $dbh = $self->{_dbh};
2066        $dbh->SQL($command, undef, @parms);
2067    }
2068    
2069    =head3 SortNeeded
2070    
2071    C<< my $parms = $erdb->SortNeeded($relationName); >>
2072    
2073    Return the pipe command for the sort that should be applied to the specified
2074    relation when creating the load file.
2075    
2076    For example, if the load file should be sorted ascending by the first
2077    field, this method would return
2078    
2079        sort -k1 -t"\t"
2080    
2081    If the first field is numeric, the method would return
2082    
2083        sort -k1n -t"\t"
2084    
2085    Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate
2086    keys using a sort.
2087    
2088    =over 4
2089    
2090    =item relationName
2091    
2092    Name of the relation to be examined.
2093    
2094    =item
2095    
2096    Returns the sort command to use for sorting the relation, suitable for piping.
2097    
2098    =back
2099    
2100    =cut
2101    #: Return Type $;
2102    sub SortNeeded {
2103        # Get the parameters.
2104        my ($self, $relationName) = @_;
2105        # Declare a descriptor to hold the names of the key fields.
2106        my @keyNames = ();
2107        # Get the relation structure.
2108        my $relationData = $self->_FindRelation($relationName);
2109        # Find out if the relation is a primary entity relation,
2110        # a relationship relation, or a secondary entity relation.
2111        my $entityTable = $self->{_metaData}->{Entities};
2112        my $relationshipTable = $self->{_metaData}->{Relationships};
2113        if (exists $entityTable->{$relationName}) {
2114            # Here we have a primary entity relation.
2115            push @keyNames, "id";
2116        } elsif (exists $relationshipTable->{$relationName}) {
2117            # Here we have a relationship. We sort using the FROM index.
2118          my $relationshipData = $relationshipTable->{$relationName};          my $relationshipData = $relationshipTable->{$relationName};
2119          my $index = $relationData->{Indexes}->{"idx${relationName}From"};          my $index = $relationData->{Indexes}->{idxFrom};
2120          push @keyNames, @{$index->{IndexFields}};          push @keyNames, @{$index->{IndexFields}};
2121      } else {      } else {
2122          # Here we have a secondary entity relation, so we have a sort on the ID field.          # Here we have a secondary entity relation, so we have a sort on the ID field.
# Line 1554  Line 2206 
2206    
2207  =item RETURN  =item RETURN
2208    
2209  Returns a list of B<DBObject>s that satisfy the query conditions.  Returns a list of B<ERDBObject>s that satisfy the query conditions.
2210    
2211  =back  =back
2212    
# Line 1810  Line 2462 
2462    
2463  =head3 InsertObject  =head3 InsertObject
2464    
2465  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>  C<< $erdb->InsertObject($objectType, \%fieldHash); >>
2466    
2467  Insert an object into the database. The object is defined by a type name and then a hash  Insert an object into the database. The object is defined by a type name and then a hash
2468  of field names to values. Field values in the primary relation are represented by scalars.  of field names to values. Field values in the primary relation are represented by scalars.
# Line 1836  Line 2488 
2488    
2489  Hash of field names to values.  Hash of field names to values.
2490    
 =item RETURN  
   
 Returns 1 if successful, 0 if an error occurred.  
   
2491  =back  =back
2492    
2493  =cut  =cut
# Line 1938  Line 2586 
2586                  $retVal = $sth->execute(@parameterList);                  $retVal = $sth->execute(@parameterList);
2587                  if (!$retVal) {                  if (!$retVal) {
2588                      my $errorString = $sth->errstr();                      my $errorString = $sth->errstr();
2589                      Trace("Insert error: $errorString.") if T(0);                      Confess("Error inserting into $relationName: $errorString");
2590                    } else {
2591                        Trace("Insert successful using $parameterList[0].") if T(3);
2592                  }                  }
2593              }              }
2594          }          }
2595      }      }
2596      # Return the success indicator.      # Return a 1 for backward compatability.
2597      return $retVal;      return 1;
2598    }
2599    
2600    =head3 UpdateEntity
2601    
2602    C<< $erdb->UpdateEntity($entityName, $id, \%fields); >>
2603    
2604    Update the values of an entity. This is an unprotected update, so it should only be
2605    done if the database resides on a database server.
2606    
2607    =over 4
2608    
2609    =item entityName
2610    
2611    Name of the entity to update. (This is the entity type.)
2612    
2613    =item id
2614    
2615    ID of the entity to update. If no entity exists with this ID, an error will be thrown.
2616    
2617    =item fields
2618    
2619    Reference to a hash mapping field names to their new values. All of the fields named
2620    must be in the entity's primary relation, and they cannot any of them be the ID field.
2621    
2622    =back
2623    
2624    =cut
2625    
2626    sub UpdateEntity {
2627        # Get the parameters.
2628        my ($self, $entityName, $id, $fields) = @_;
2629        # Get a list of the field names being updated.
2630        my @fieldList = keys %{$fields};
2631        # Verify that the fields exist.
2632        my $checker = $self->GetFieldTable($entityName);
2633        for my $field (@fieldList) {
2634            if ($field eq 'id') {
2635                Confess("Cannot update the ID field for entity $entityName.");
2636            } elsif ($checker->{$field}->{relation} ne $entityName) {
2637                Confess("Cannot find $field in primary relation of $entityName.");
2638            }
2639        }
2640        # Build the SQL statement.
2641        my @sets = ();
2642        my @valueList = ();
2643        for my $field (@fieldList) {
2644            push @sets, _FixName($field) . " = ?";
2645            push @valueList, $fields->{$field};
2646        }
2647        my $command = "UPDATE $entityName SET " . join(", ", @sets) . " WHERE id = ?";
2648        # Add the ID to the list of binding values.
2649        push @valueList, $id;
2650        # Call SQL to do the work.
2651        my $rows = $self->{_dbh}->SQL($command, 0, @valueList);
2652        # Check for errors.
2653        if ($rows == 0) {
2654            Confess("Entity $id of type $entityName not found.");
2655        }
2656  }  }
2657    
2658  =head3 LoadTable  =head3 LoadTable
2659    
2660  C<< my %results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>  C<< my $results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>
2661    
2662  Load data from a tab-delimited file into a specified table, optionally re-creating the table  Load data from a tab-delimited file into a specified table, optionally re-creating the table
2663  first.  first.
# Line 2016  Line 2724 
2724      };      };
2725      if (!defined $rv) {      if (!defined $rv) {
2726          $retVal->AddMessage($@) if ($@);          $retVal->AddMessage($@) if ($@);
2727          $retVal->AddMessage("Table load failed for $relationName using $fileName.");          $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2728          Trace("Table load failed for $relationName.") if T(1);          Trace("Table load failed for $relationName.") if T(1);
2729      } else {      } else {
2730          # Here we successfully loaded the table.          # Here we successfully loaded the table.
# Line 2038  Line 2746 
2746              # The full-text index (if any) is always built last, even for MySQL.              # The full-text index (if any) is always built last, even for MySQL.
2747              # First we need to see if this table has a full-text index. Only              # First we need to see if this table has a full-text index. Only
2748              # primary relations are allowed that privilege.              # primary relations are allowed that privilege.
2749                Trace("Checking for full-text index on $relationName.") if T(2);
2750              if ($self->_IsPrimary($relationName)) {              if ($self->_IsPrimary($relationName)) {
2751                  # 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 => $relationName, idx => "search_idx_$relationName",  
                                        flds => $fields, kind => 'fulltext');  
                 }  
2752              }              }
2753          }          }
2754      }      }
# Line 2061  Line 2760 
2760      return $retVal;      return $retVal;
2761  }  }
2762    
2763  =head3 GenerateEntity  =head3 CreateSearchIndex
2764    
2765  C<< my $fieldHash = $erdb->GenerateEntity($id, $type, \%values); >>  C<< $erdb->CreateSearchIndex($objectName); >>
2766    
2767  Generate the data for a new entity instance. This method creates a field hash suitable for  Check for a full-text search index on the specified entity or relationship object, and
2768  passing as a parameter to L</InsertObject>. The ID is specified by the callr, but the rest  if one is required, rebuild it.
 of the fields are generated using information in the database schema.  
   
 Each data type has a default algorithm for generating random test data. This can be overridden  
 by including a B<DataGen> element in the field. If this happens, the content of the element is  
 executed as a PERL program in the context of this module. The element may make use of a C<$this>  
 variable which contains the field hash as it has been built up to the current point. If any  
 fields are dependent on other fields, the C<pass> attribute can be used to control the order  
 in which the fields are generated. A field with a high data pass number will be generated after  
 a field with a lower one. If any external values are needed, they should be passed in via the  
 optional third parameter, which will be available to the data generation script under the name  
 C<$value>. Several useful utility methods are provided for generating random values, including  
 L</IntGen>, L</StringGen>, L</FloatGen>, and L</DateGen>. Note that dates are stored and generated  
 in the form of a timestamp number rather than a string.  
2769    
2770  =over 4  =over 4
2771    
2772  =item id  =item objectName
2773    
2774  ID to assign to the new entity.  Name of the entity or relationship to be indexed.
2775    
2776  =item type  =back
2777    
2778  Type name for the new entity.  =cut
2779    
2780  =item values  sub CreateSearchIndex {
2781        # Get the parameters.
2782        my ($self, $objectName) = @_;
2783        # Get the relation's entity/relationship structure.
2784        my $structure = $self->_GetStructure($objectName);
2785        # Get the database handle.
2786        my $dbh = $self->{_dbh};
2787        Trace("Checking for search fields in $objectName.") if T(3);
2788        # Check for a searchable fields list.
2789        if (exists $structure->{searchFields}) {
2790            # Here we know that we need to create a full-text search index.
2791            # Get an SQL-formatted field name list.
2792            my $fields = join(", ", _FixNames(@{$structure->{searchFields}}));
2793            # Create the index. If it already exists, it will be dropped.
2794            $dbh->create_index(tbl => $objectName, idx => "search_idx",
2795                               flds => $fields, kind => 'fulltext');
2796            Trace("Index created for $fields in $objectName.") if T(2);
2797        }
2798    }
2799    
2800    =head3 DropRelation
2801    
2802    C<< $erdb->DropRelation($relationName); >>
2803    
2804  Hash containing additional values that might be needed by the data generation methods (optional).  Physically drop a relation from the database.
2805    
2806    =over 4
2807    
2808    =item relationName
2809    
2810    Name of the relation to drop. If it does not exist, this method will have
2811    no effect.
2812    
2813  =back  =back
2814    
2815  =cut  =cut
2816    
2817  sub GenerateEntity {  sub DropRelation {
2818      # Get the parameters.      # Get the parameters.
2819      my ($self, $id, $type, $values) = @_;      my ($self, $relationName) = @_;
2820      # Create the return hash.      # Get the database handle.
2821      my $this = { id => $id };      my $dbh = $self->{_dbh};
2822      # Get the metadata structure.      # Drop the relation. The method used here has no effect if the relation
2823      my $metadata = $self->{_metaData};      # does not exist.
2824      # Get this entity's list of fields.      Trace("Invoking DB Kernel to drop $relationName.") if T(3);
2825      if (!exists $metadata->{Entities}->{$type}) {      $dbh->drop_table(tbl => $relationName);
2826          Confess("Unrecognized entity type $type in GenerateEntity.");  }
2827    
2828    =head3 MatchSqlPattern
2829    
2830    C<< my $matched = ERDB::MatchSqlPattern($value, $pattern); >>
2831    
2832    Determine whether or not a specified value matches an SQL pattern. An SQL
2833    pattern has two wild card characters: C<%> that matches multiple characters,
2834    and C<_> that matches a single character. These can be escaped using a
2835    backslash (C<\>). We pull this off by converting the SQL pattern to a
2836    PERL regular expression. As per SQL rules, the match is case-insensitive.
2837    
2838    =over 4
2839    
2840    =item value
2841    
2842    Value to be matched against the pattern. Note that an undefined or empty
2843    value will not match anything.
2844    
2845    =item pattern
2846    
2847    SQL pattern against which to match the value. An undefined or empty pattern will
2848    match everything.
2849    
2850    =item RETURN
2851    
2852    Returns TRUE if the value and pattern match, else FALSE.
2853    
2854    =back
2855    
2856    =cut
2857    
2858    sub MatchSqlPattern {
2859        # Get the parameters.
2860        my ($value, $pattern) = @_;
2861        # Declare the return variable.
2862        my $retVal;
2863        # Insure we have a pattern.
2864        if (! defined($pattern) || $pattern eq "") {
2865            $retVal = 1;
2866        } else {
2867            # Break the pattern into pieces around the wildcard characters. Because we
2868            # use parentheses in the split function's delimiter expression, we'll get
2869            # list elements for the delimiters as well as the rest of the string.
2870            my @pieces = split /([_%]|\\[_%])/, $pattern;
2871            # Check some fast special cases.
2872            if ($pattern eq '%') {
2873                # A null pattern matches everything.
2874                $retVal = 1;
2875            } elsif (@pieces == 1) {
2876                # No wildcards, so we have a literal comparison. Note we're case-insensitive.
2877                $retVal = (lc($value) eq lc($pattern));
2878            } elsif (@pieces == 2 && $pieces[1] eq '%') {
2879                # A wildcard at the end, so we have a substring match. This is also case-insensitive.
2880                $retVal = (lc(substr($value, 0, length($pieces[0]))) eq lc($pieces[0]));
2881            } else {
2882                # Okay, we have to do it the hard way. Convert each piece to a PERL pattern.
2883                my $realPattern = "";
2884                for my $piece (@pieces) {
2885                    # Determine the type of piece.
2886                    if ($piece eq "") {
2887                        # Empty pieces are ignored.
2888                    } elsif ($piece eq "%") {
2889                        # Here we have a multi-character wildcard. Note that it can match
2890                        # zero or more characters.
2891                        $realPattern .= ".*"
2892                    } elsif ($piece eq "_") {
2893                        # Here we have a single-character wildcard.
2894                        $realPattern .= ".";
2895                    } elsif ($piece eq "\\%" || $piece eq "\\_") {
2896                        # This is an escape sequence (which is a rare thing, actually).
2897                        $realPattern .= substr($piece, 1, 1);
2898      } else {      } else {
2899          my $entity = $metadata->{Entities}->{$type};                      # Here we have raw text.
2900          my $fields = $entity->{Fields};                      $realPattern .= quotemeta($piece);
         # Generate data from the fields.  
         _GenerateFields($this, $fields, $type, $values);  
2901      }      }
2902      # Return the hash created.              }
2903      return $this;              # Do the match.
2904                $retVal = ($value =~ /^$realPattern$/i ? 1 : 0);
2905            }
2906        }
2907        # Return the result.
2908        return $retVal;
2909  }  }
2910    
2911  =head3 GetEntity  =head3 GetEntity
# Line 2137  Line 2926 
2926    
2927  =item RETURN  =item RETURN
2928    
2929  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
2930  instance is found with the specified key.  instance is found with the specified key.
2931    
2932  =back  =back
# Line 2272  Line 3061 
3061  spreadsheet cell, and each feature will be represented by a list containing the  spreadsheet cell, and each feature will be represented by a list containing the
3062  feature ID followed by all of its aliases.  feature ID followed by all of its aliases.
3063    
3064  C<< $query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>  C<< @query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>
3065    
3066  =over 4  =over 4
3067    
# Line 2450  Line 3239 
3239      return $objectData->{Fields};      return $objectData->{Fields};
3240  }  }
3241    
3242    =head3 SplitKeywords
3243    
3244    C<< my @keywords = ERDB::SplitKeywords($keywordString); >>
3245    
3246    This method returns a list of the positive keywords in the specified
3247    keyword string. All of the operators will have been stripped off,
3248    and if the keyword is preceded by a minus operator (C<->), it will
3249    not be in the list returned. The idea here is to get a list of the
3250    keywords the user wants to see. The list will be processed to remove
3251    duplicates.
3252    
3253    It is possible to create a string that confuses this method. For example
3254    
3255        frog toad -frog
3256    
3257    would return both C<frog> and C<toad>. If this is a problem we can deal
3258    with it later.
3259    
3260    =over 4
3261    
3262    =item keywordString
3263    
3264    The keyword string to be parsed.
3265    
3266    =item RETURN
3267    
3268    Returns a list of the words in the keyword string the user wants to
3269    see.
3270    
3271    =back
3272    
3273    =cut
3274    
3275    sub SplitKeywords {
3276        # Get the parameters.
3277        my ($keywordString) = @_;
3278        # Make a safety copy of the string. (This helps during debugging.)
3279        my $workString = $keywordString;
3280        # Convert operators we don't care about to spaces.
3281        $workString =~ tr/+"()<>/ /;
3282        # Split the rest of the string along space boundaries. Note that we
3283        # eliminate any words that are zero length or begin with a minus sign.
3284        my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
3285        # Use a hash to remove duplicates.
3286        my %words = map { $_ => 1 } @wordList;
3287        # Return the result.
3288        return sort keys %words;
3289    }
3290    
3291    =head3 ValidateFieldName
3292    
3293    C<< my $okFlag = ERDB::ValidateFieldName($fieldName); >>
3294    
3295    Return TRUE if the specified field name is valid, else FALSE. Valid field names must
3296    be hyphenated words subject to certain restrictions.
3297    
3298    =over 4
3299    
3300    =item fieldName
3301    
3302    Field name to be validated.
3303    
3304    =item RETURN
3305    
3306    Returns TRUE if the field name is valid, else FALSE.
3307    
3308    =back
3309    
3310    =cut
3311    
3312    sub ValidateFieldName {
3313        # Get the parameters.
3314        my ($fieldName) = @_;
3315        # Declare the return variable. The field name is valid until we hear
3316        # differently.
3317        my $retVal = 1;
3318        # Compute the maximum name length.
3319        my $maxLen = $TypeTable{'name-string'}->{maxLen};
3320        # Look for bad stuff in the name.
3321        if ($fieldName =~ /--/) {
3322            # Here we have a doubled minus sign.
3323            Trace("Field name $fieldName has a doubled hyphen.") if T(1);
3324            $retVal = 0;
3325        } elsif ($fieldName !~ /^[A-Za-z]/) {
3326            # Here the field name is missing the initial letter.
3327            Trace("Field name $fieldName does not begin with a letter.") if T(1);
3328            $retVal = 0;
3329        } elsif (length($fieldName) > $maxLen) {
3330            # Here the field name is too long.
3331            Trace("Maximum field name length is $maxLen. Field name must be truncated to " . substr($fieldName,0, $maxLen) . ".");
3332        } else {
3333            # Strip out the minus signs. Everything remaining must be a letter,
3334            # underscore, or digit.
3335            my $strippedName = $fieldName;
3336            $strippedName =~ s/-//g;
3337            if ($strippedName !~ /^(\w|\d)+$/) {
3338                Trace("Field name $fieldName contains illegal characters.") if T(1);
3339                $retVal = 0;
3340            }
3341        }
3342        # Return the result.
3343        return $retVal;
3344    }
3345    
3346    =head3 ReadMetaXML
3347    
3348    C<< my $rawMetaData = ERDB::ReadDBD($fileName); >>
3349    
3350    This method reads a raw database definition XML file and returns it.
3351    Normally, the metadata used by the ERDB system has been processed and
3352    modified to make it easier to load and retrieve the data; however,
3353    this method can be used to get the data in its raw form.
3354    
3355    =over 4
3356    
3357    =item fileName
3358    
3359    Name of the XML file to read.
3360    
3361    =item RETURN
3362    
3363    Returns a hash reference containing the raw XML data from the specified file.
3364    
3365    =back
3366    
3367    =cut
3368    
3369    sub ReadMetaXML {
3370        # Get the parameters.
3371        my ($fileName) = @_;
3372        # Read the XML.
3373        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
3374        Trace("XML metadata loaded from file $fileName.") if T(1);
3375        # Return the result.
3376        return $retVal;
3377    }
3378    
3379    =head3 GetEntityFieldHash
3380    
3381    C<< my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName); >>
3382    
3383    Get the field hash of the named entity in the specified raw XML structure.
3384    The field hash may not exist, in which case we need to create it.
3385    
3386    =over 4
3387    
3388    =item structure
3389    
3390    Raw XML structure defininng the database. This is not the run-time XML used by
3391    an ERDB object, since that has all sorts of optimizations built-in.
3392    
3393    =item entityName
3394    
3395    Name of the entity whose field structure is desired.
3396    
3397    =item RETURN
3398    
3399    Returns the field hash used to define the entity's fields.
3400    
3401    =back
3402    
3403    =cut
3404    
3405    sub GetEntityFieldHash {
3406        # Get the parameters.
3407        my ($structure, $entityName) = @_;
3408        # Get the entity structure.
3409        my $entityData = $structure->{Entities}->{$entityName};
3410        # Look for a field structure.
3411        my $retVal = $entityData->{Fields};
3412        # If it doesn't exist, create it.
3413        if (! defined($retVal)) {
3414            $entityData->{Fields} = {};
3415            $retVal = $entityData->{Fields};
3416        }
3417        # Return the result.
3418        return $retVal;
3419    }
3420    
3421    =head3 WriteMetaXML
3422    
3423    C<< ERDB::WriteMetaXML($structure, $fileName); >>
3424    
3425    Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
3426    used to update the database definition. It must be used with care, however, since it
3427    will only work on a raw structure, not on the processed structure created by an ERDB
3428    constructor.
3429    
3430    =over 4
3431    
3432    =item structure
3433    
3434    XML structure to be written to the file.
3435    
3436    =item fileName
3437    
3438    Name of the output file to which the updated XML should be stored.
3439    
3440    =back
3441    
3442    =cut
3443    
3444    sub WriteMetaXML {
3445        # Get the parameters.
3446        my ($structure, $fileName) = @_;
3447        # Compute the output.
3448        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
3449        # Write it to the file.
3450        my $xmlOut = Open(undef, ">$fileName");
3451        print $xmlOut $fileString;
3452    }
3453    
3454    
3455    =head3 HTMLNote
3456    
3457    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
3458    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
3459    Except for C<[p]>, all the codes are closed by slash-codes. So, for
3460    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
3461    
3462    C<< my $realHtml = ERDB::HTMLNote($dataString); >>
3463    
3464    =over 4
3465    
3466    =item dataString
3467    
3468    String to convert to HTML.
3469    
3470    =item RETURN
3471    
3472    An HTML string derived from the input string.
3473    
3474    =back
3475    
3476    =cut
3477    
3478    sub HTMLNote {
3479        # Get the parameter.
3480        my ($dataString) = @_;
3481        # HTML-escape the text.
3482        my $retVal = CGI::escapeHTML($dataString);
3483        # Substitute the bulletin board codes.
3484        $retVal =~ s!\[(/?[bi])\]!<$1>!g;
3485        $retVal =~ s!\[p\]!</p><p>!g;
3486        $retVal =~ s!\[link\s+([^\]]+)\]!<a href="$1">!g;
3487        $retVal =~ s!\[/link\]!</a>!g;
3488        # Return the result.
3489        return $retVal;
3490    }
3491    
3492    =head3 BeginTran
3493    
3494    C<< $erdb->BeginTran(); >>
3495    
3496    Start a database transaction.
3497    
3498    =cut
3499    
3500    sub BeginTran {
3501        my ($self) = @_;
3502        $self->{_dbh}->begin_tran();
3503    
3504    }
3505    
3506    =head3 CommitTran
3507    
3508    C<< $erdb->CommitTran(); >>
3509    
3510    Commit an active database transaction.
3511    
3512    =cut
3513    
3514    sub CommitTran {
3515        my ($self) = @_;
3516        $self->{_dbh}->commit_tran();
3517    }
3518    
3519    =head3 RollbackTran
3520    
3521    C<< $erdb->RollbackTran(); >>
3522    
3523    Roll back an active database transaction.
3524    
3525    =cut
3526    
3527    sub RollbackTran {
3528        my ($self) = @_;
3529        $self->{_dbh}->roll_tran();
3530    }
3531    
3532    
3533  =head2 Data Mining Methods  =head2 Data Mining Methods
3534    
3535  =head3 GetUsefulCrossValues  =head3 GetUsefulCrossValues
# Line 2603  Line 3683 
3683      return @retVal;      return @retVal;
3684  }  }
3685    
3686    =head2 Virtual Methods
3687    
3688    =head3 _CreatePPOIndex
3689    
3690    C<< my $index = ERDB::_CreatePPOIndex($indexObject); >>
3691    
3692    Convert the XML for an ERDB index to the XML structure for a PPO
3693    index.
3694    
3695    =over 4
3696    
3697    ERDB XML structure for an index.
3698    
3699    =item RETURN
3700    
3701    PPO XML structure for the same index.
3702    
3703    =back
3704    
3705    =cut
3706    
3707    sub _CreatePPOIndex {
3708        # Get the parameters.
3709        my ($indexObject) = @_;
3710        # The incoming index contains a list of the index fields in the IndexFields
3711        # member. We loop through it to create the index tags.
3712        my @fields = map { { label => _FixName($_->{name}) } } @{$indexObject->{IndexFields}};
3713        # Wrap the fields in attribute tags.
3714        my $retVal = { attribute => \@fields };
3715        # Return the result.
3716        return $retVal;
3717    }
3718    
3719    =head3 _CreatePPOField
3720    
3721    C<< my $fieldXML = ERDB::_CreatePPOField($fieldName, $fieldObject); >>
3722    
3723    Convert the ERDB XML structure for a field to a PPO scalar XML structure.
3724    
3725    =over 4
3726    
3727    =item fieldName
3728    
3729    Name of the scalar field.
3730    
3731    =item fieldObject
3732    
3733    ERDB XML structure describing the field.
3734    
3735    =item RETURN
3736    
3737    Returns a PPO XML structure for the same field.
3738    
3739    =back
3740    
3741    =cut
3742    
3743    sub _CreatePPOField {
3744        # Get the parameters.
3745        my ($fieldName, $fieldObject) = @_;
3746        # Get the field type.
3747        my $type = $TypeTable{$fieldObject->{type}}->{sqlType};
3748        # Fix up the field name.
3749        $fieldName = _FixName($fieldName);
3750        # Build the scalar tag.
3751        my $retVal = { label => $fieldName, type => $type };
3752        # Return the result.
3753        return $retVal;
3754    }
3755    
3756    =head3 CleanKeywords
3757    
3758    C<< my $cleanedString = $erdb->CleanKeywords($searchExpression); >>
3759    
3760    Clean up a search expression or keyword list. This is a virtual method that may
3761    be overridden by the subclass. The base-class method removes extra spaces
3762    and converts everything to lower case.
3763    
3764    =over 4
3765    
3766    =item searchExpression
3767    
3768    Search expression or keyword list to clean. Note that a search expression may
3769    contain boolean operators which need to be preserved. This includes leading
3770    minus signs.
3771    
3772    =item RETURN
3773    
3774    Cleaned expression or keyword list.
3775    
3776    =back
3777    
3778    =cut
3779    
3780    sub CleanKeywords {
3781        # Get the parameters.
3782        my ($self, $searchExpression) = @_;
3783        # Lower-case the expression and copy it into the return variable. Note that we insure we
3784        # don't accidentally end up with an undefined value.
3785        my $retVal = lc($searchExpression || "");
3786        # Remove extra spaces.
3787        $retVal =~ s/\s+/ /g;
3788        $retVal =~ s/(^\s+)|(\s+$)//g;
3789        # Return the result.
3790        return $retVal;
3791    }
3792    
3793    =head3 GetSourceObject
3794    
3795    C<< my $source = $erdb->GetSourceObject($entityName); >>
3796    
3797    Return the object to be used in loading special attributes of the specified entity. The
3798    algorithm for loading special attributes is stored in the C<DataGen> elements of the
3799    XML
3800    
3801  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3802    
3803  =head3 _RelationMap  =head3 _RelationMap
3804    
3805  C<< my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef); >>  C<< my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef); >>
3806    
3807  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>
3808  to determine how to interpret the results of the query.  to determine how to interpret the results of the query.
3809    
3810  =over 4  =over 4
# Line 2626  Line 3821 
3821  =item RETURN  =item RETURN
3822    
3823  Returns a list of 2-tuples. Each tuple consists of an object name as used in the  Returns a list of 2-tuples. Each tuple consists of an object name as used in the
3824  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
3825  determine the order of the tables in the query and which object name belongs to each  determine the order of the tables in the query and which object name belongs to each
3826  mapped object name. Most of the time these two values are the same; however, if a  mapped object name. Most of the time these two values are the same; however, if a
3827  relation occurs twice in the query, the relation name in the field list and WHERE  relation occurs twice in the query, the relation name in the field list and WHERE
# Line 2928  Line 4123 
4123      # Prepare the command.      # Prepare the command.
4124      my $sth = $dbh->prepare_command($command);      my $sth = $dbh->prepare_command($command);
4125      # Execute it with the parameters bound in.      # Execute it with the parameters bound in.
4126      $sth->execute(@{$params}) || Confess("SELECT error" . $sth->errstr());      $sth->execute(@{$params}) || Confess("SELECT error:  " . $sth->errstr());
4127      # Return the statement handle.      # Return the statement handle.
4128      return $sth;      return $sth;
4129  }  }
# Line 2945  Line 4140 
4140      return Stats->new();      return Stats->new();
4141  }  }
4142    
 =head3 _GenerateFields  
   
 Generate field values from a field structure and store in a specified table. The field names  
 are first sorted by pass count, certain pre-defined fields are removed from the list, and  
 then we rip through them evaluation the data generation string. Fields in the primary relation  
 are stored as scalars; fields in secondary relations are stored as value lists.  
   
 This is a static method.  
   
 =over 4  
   
 =item this  
   
 Hash table into which the field values should be placed.  
   
 =item fields  
   
 Field structure from which the field descriptors should be taken.  
   
 =item type  
   
 Type name of the object whose fields are being generated.  
   
 =item values (optional)  
   
 Reference to a value structure from which additional values can be taken.  
   
 =item from (optiona)  
   
 Reference to the source entity instance if relationship data is being generated.  
   
 =item to (optional)  
   
 Reference to the target entity instance if relationship data is being generated.  
   
 =back  
   
 =cut  
   
 sub _GenerateFields {  
     # Get the parameters.  
     my ($this, $fields, $type, $values, $from, $to) = @_;  
     # Sort the field names by pass number.  
     my @fieldNames = sort { $fields->{$a}->{DataGen}->{pass} <=> $fields->{$b}->{DataGen}->{pass} } keys %{$fields};  
     # Loop through the field names, generating data.  
     for my $name (@fieldNames) {  
         # Only proceed if this field needs to be generated.  
         if (!exists $this->{$name}) {  
             # Get this field's data generation descriptor.  
             my $fieldDescriptor = $fields->{$name};  
             my $data = $fieldDescriptor->{DataGen};  
             # Get the code to generate the field value.  
             my $codeString = $data->{content};  
             # Determine whether or not this field is in the primary relation.  
             if ($fieldDescriptor->{relation} eq $type) {  
                 # Here we have a primary relation field. Store the field value as  
                 # a scalar.  
                 $this->{$name} = eval($codeString);  
             } else {  
                 # Here we have a secondary relation field. Create a null list  
                 # and push the desired number of field values onto it.  
                 my @fieldValues = ();  
                 my $count = IntGen(0,$data->{testCount});  
                 for (my $i = 0; $i < $count; $i++) {  
                     my $newValue = eval($codeString);  
                     push @fieldValues, $newValue;  
                 }  
                 # Store the value list in the main hash.  
                 $this->{$name} = \@fieldValues;  
             }  
         }  
     }  
 }  
   
4143  =head3 _DumpRelation  =head3 _DumpRelation
4144    
4145  Dump the specified relation's to the specified output file in tab-delimited format.  Dump the specified relation to the specified output file in tab-delimited format.
4146    
4147  This is an instance method.  This is an instance method.
4148    
# Line 3162  Line 4283 
4283      my $retVal = 1;      my $retVal = 1;
4284      # Loop through the sections of the database definition.      # Loop through the sections of the database definition.
4285      for my $section ('Entities', 'Relationships') {      for my $section ('Entities', 'Relationships') {
4286          # Loop through the objects in this section.          # Loop through the objects in this section.
4287          for my $object (values %{$metadata->{$section}}) {          for my $object (values %{$metadata->{$section}}) {
4288              # Loop through the object's fields.              # Loop through the object's fields.
4289              for my $fieldName (keys %{$object->{Fields}}) {              for my $fieldName (keys %{$object->{Fields}}) {
4290                  # Now we make some initial validations.                  # If this field name is invalid, set the return value to zero
4291                  if ($fieldName =~ /--/) {                  # so we know we encountered an error.
4292                      # Here we have a doubled minus sign.                  if (! ValidateFieldName($fieldName)) {
                     print STDERR "Field name $fieldName has a doubled hyphen.\n";  
                     $retVal = 0;  
                 } elsif ($fieldName !~ /^[A-Za-z]/) {  
                     # Here the field name is missing the initial letter.  
                     print STDERR "Field name $fieldName does not begin with a letter.\n";  
                     $retVal = 0;  
                 } else {  
                     # Strip out the minus signs. Everything remaining must be a letter  
                     # or digit.  
                     my $strippedName = $fieldName;  
                     $strippedName =~ s/-//g;  
                     if ($strippedName !~ /^[A-Za-z0-9]+$/) {  
                         print STDERR "Field name $fieldName contains illegal characters.\n";  
4293                          $retVal = 0;                          $retVal = 0;
4294                      }                      }
4295                  }                  }
4296              }              }
4297          }          }
     }  
4298      # If an error was found, fail.      # If an error was found, fail.
4299      if ($retVal  == 0) {      if ($retVal  == 0) {
4300          Confess("Errors found in field names.");          Confess("Errors found in field names.");
# Line 3254  Line 4361 
4361      return $retVal;      return $retVal;
4362  }  }
4363    
4364    
4365  =head3 _LoadMetaData  =head3 _LoadMetaData
4366    
4367    C<< my $metadata = ERDB::_LoadMetaData($filename); >>
4368    
4369  This method loads the data describing this database from an XML file into a metadata structure.  This method loads the data describing this database from an XML file into a metadata structure.
4370  The resulting structure is a set of nested hash tables containing all the information needed to  The resulting structure is a set of nested hash tables containing all the information needed to
4371  load or use the database. The schema for the XML file is F<ERDatabase.xml>.  load or use the database. The schema for the XML file is F<ERDatabase.xml>.
# Line 3279  Line 4389 
4389  sub _LoadMetaData {  sub _LoadMetaData {
4390      # Get the parameters.      # Get the parameters.
4391      my ($filename) = @_;      my ($filename) = @_;
4392      Trace("Reading Sprout DBD from $filename.") if T(2);      Trace("Reading DBD from $filename.") if T(2);
4393      # Slurp the XML file into a variable. Extensive use of options is used to insure we      # Slurp the XML file into a variable. Extensive use of options is used to insure we
4394      # get the exact structure we want.      # get the exact structure we want.
4395      my $metadata = XML::Simple::XMLin($filename,      my $metadata = ReadMetaXML($filename);
                                       GroupTags => { Relationships => 'Relationship',  
                                                      Entities => 'Entity',  
                                                      Fields => 'Field',  
                                                      Indexes => 'Index',  
                                                      IndexFields => 'IndexField'},  
                                       KeyAttr => { Relationship => 'name',  
                                                    Entity => 'name',  
                                                    Field => 'name'},  
                                       ForceArray => ['Field', 'Index', 'IndexField'],  
                                       ForceContent => 1,  
                                       NormalizeSpace => 2  
                                       );  
     Trace("XML metadata loaded from file $filename.") if T(1);  
4396      # Before we go any farther, we need to validate the field and object names. If an error is found,      # Before we go any farther, we need to validate the field and object names. If an error is found,
4397      # the method below will fail.      # the method below will fail.
4398      _ValidateFieldNames($metadata);      _ValidateFieldNames($metadata);
# Line 3418  Line 4515 
4515              if ($found == 0) {              if ($found == 0) {
4516                  push @{$indexList}, { IndexFields => [ {name => 'id', order => 'ascending'} ] };                  push @{$indexList}, { IndexFields => [ {name => 'id', order => 'ascending'} ] };
4517              }              }
4518              # Now we need to convert the relation's index list to an index table. We begin by creating              # Attach all the indexes to the relation.
4519              # an empty table in the relation structure.              _ProcessIndexes($indexList, $relation);
             $relation->{Indexes} = { };  
             # Loop through the indexes.  
             my $count = 0;  
             for my $index (@{$indexList}) {  
                 # Add this index to the index table.  
                 _AddIndex("idx$relationName$count", $relation, $index);  
                 # Increment the counter so that the next index has a different name.  
                 $count++;  
             }  
4520          }          }
4521          # Finally, we add the relation structure to the entity.          # Finally, we add the relation structure to the entity.
4522          $entityStructure->{Relations} = $relationTable;          $entityStructure->{Relations} = $relationTable;
# Line 3442  Line 4530 
4530          _FixupFields($relationshipStructure, $relationshipName, 2, 3);          _FixupFields($relationshipStructure, $relationshipName, 2, 3);
4531          # Format a description for the FROM field.          # Format a description for the FROM field.
4532          my $fromEntity = $relationshipStructure->{from};          my $fromEntity = $relationshipStructure->{from};
4533          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].";
4534          # Get the FROM entity's key type.          # Get the FROM entity's key type.
4535          my $fromType = $entityList->{$fromEntity}->{keyType};          my $fromType = $entityList->{$fromEntity}->{keyType};
4536          # Add the FROM field.          # Add the FROM field.
# Line 3452  Line 4540 
4540                                                      PrettySort => 1});                                                      PrettySort => 1});
4541          # Format a description for the TO field.          # Format a description for the TO field.
4542          my $toEntity = $relationshipStructure->{to};          my $toEntity = $relationshipStructure->{to};
4543          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].";
4544          # Get the TO entity's key type.          # Get the TO entity's key type.
4545          my $toType = $entityList->{$toEntity}->{keyType};          my $toType = $entityList->{$toEntity}->{keyType};
4546          # Add the TO field.          # Add the TO field.
# Line 3464  Line 4552 
4552          my $thisRelation = { Fields => _ReOrderRelationTable($relationshipStructure->{Fields}),          my $thisRelation = { Fields => _ReOrderRelationTable($relationshipStructure->{Fields}),
4553                               Indexes => { } };                               Indexes => { } };
4554          $relationshipStructure->{Relations} = { $relationshipName => $thisRelation };          $relationshipStructure->{Relations} = { $relationshipName => $thisRelation };
4555    
4556            # Add the alternate indexes (if any). This MUST be done before the FROM and
4557            # TO indexes, because it erases the relation's index list.
4558            if (exists $relationshipStructure->{Indexes}) {
4559                _ProcessIndexes($relationshipStructure->{Indexes}, $thisRelation);
4560            }
4561            # Add the relation to the master table.
4562          # Create the FROM and TO indexes.          # Create the FROM and TO indexes.
4563          _CreateRelationshipIndex("From", $relationshipName, $relationshipStructure);          _CreateRelationshipIndex("From", $relationshipName, $relationshipStructure);
4564          _CreateRelationshipIndex("To", $relationshipName, $relationshipStructure);          _CreateRelationshipIndex("To", $relationshipName, $relationshipStructure);
         # Add the relation to the master table.  
4565          $masterRelationTable{$relationshipName} = $thisRelation;          $masterRelationTable{$relationshipName} = $thisRelation;
4566      }      }
4567      # Now store the master relation table in the metadata structure.      # Now store the master relation table in the metadata structure.
# Line 3623  Line 4717 
4717          $newIndex->{Unique} = 'true';          $newIndex->{Unique} = 'true';
4718      }      }
4719      # Add the index to the relation.      # Add the index to the relation.
4720      _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);      _AddIndex("idx$indexKey", $relationStructure, $newIndex);
4721    }
4722    
4723    =head3 _ProcessIndexes
4724    
4725    C<< ERDB::_ProcessIndexes($indexList, $relation); >>
4726    
4727    Build the data structures for the specified indexes in the specified relation.
4728    
4729    =over 4
4730    
4731    =item indexList
4732    
4733    Reference to a list of indexes. Each index is a hash reference containing an optional
4734    C<Notes> value that describes the index and an C<IndexFields> value that is a reference
4735    to a list of index field structures. An index field structure, in turn, is a reference
4736    to a hash that contains a C<name> attribute for the field name and an C<order>
4737    attribute that specifies either C<ascending> or C<descending>. In this sense the
4738    index list encapsulates the XML C<Indexes> structure in the database definition.
4739    
4740    =item relation
4741    
4742    The structure that describes the current relation. The new index descriptors will
4743    be stored in the structure's C<Indexes> member. Any previous data in the structure
4744    will be lost.
4745    
4746    =back
4747    
4748    =cut
4749    
4750    sub _ProcessIndexes {
4751        # Get the parameters.
4752        my ($indexList, $relation) = @_;
4753        # Now we need to convert the relation's index list to an index table. We begin by creating
4754        # an empty table in the relation structure.
4755        $relation->{Indexes} = { };
4756        # Loop through the indexes.
4757        my $count = 0;
4758        for my $index (@{$indexList}) {
4759            # Add this index to the index table.
4760            _AddIndex("idx$count", $relation, $index);
4761            # Increment the counter so that the next index has a different name.
4762            $count++;
4763        }
4764  }  }
4765    
4766  =head3 _AddIndex  =head3 _AddIndex
# Line 3722  Line 4859 
4859              my $type = $fieldData->{type};              my $type = $fieldData->{type};
4860              # Plug in a relation name if it is needed.              # Plug in a relation name if it is needed.
4861              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });
             # Plug in a data generator if we need one.  
             if (!exists $fieldData->{DataGen}) {  
                 # The data generator will use the default for the field's type.  
                 $fieldData->{DataGen} = { content => $TypeTable{$type}->{dataGen} };  
             }  
4862              # Check for searchability.              # Check for searchability.
4863              if ($fieldData->{searchable}) {              if ($fieldData->{searchable}) {
4864                  # Only allow this for a primary relation.                  # Only allow this for a primary relation.
# Line 3736  Line 4868 
4868                      push @textFields, $fieldName;                      push @textFields, $fieldName;
4869                  }                  }
4870              }              }
             # Plug in the defaults for the optional data generation parameters.  
             Tracer::MergeOptions($fieldData->{DataGen}, { testCount => 1, pass => 0 });  
4871              # Add the PrettySortValue.              # Add the PrettySortValue.
4872              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);
4873          }          }
# Line 4096  Line 5226 
5226          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";
5227          # Add any note text.          # Add any note text.
5228          if (my $note = $indexData->{Notes}) {          if (my $note = $indexData->{Notes}) {
5229              $htmlString .= "<li>" . _HTMLNote($note->{content}) . "</li>\n";              $htmlString .= "<li>" . HTMLNote($note->{content}) . "</li>\n";
5230          }          }
5231          # Add the fiield list.          # Add the fiield list.
5232          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";
# Line 4162  Line 5292 
5292      # Compute the number of columns.      # Compute the number of columns.
5293      my $colCount = @colNames;      my $colCount = @colNames;
5294      # Generate the title row.      # Generate the title row.
5295      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";
5296      # Loop through the columns, adding the column header rows.      # Loop through the columns, adding the column header rows.
5297      $htmlString .= "<tr>";      $htmlString .= "<tr>";
5298      for my $colName (@colNames) {      for my $colName (@colNames) {
# Line 4181  Line 5311 
5311  =cut  =cut
5312    
5313  sub _CloseTable {  sub _CloseTable {
5314      return "</table></p>\n";      return "</table>\n";
5315  }  }
5316    
5317  =head3 _ShowField  =head3 _ShowField
# Line 4211  Line 5341 
5341      my $htmlString = "<tr><th align=\"left\">$fieldData->{name}</th><td>$fieldData->{type}</td>";      my $htmlString = "<tr><th align=\"left\">$fieldData->{name}</th><td>$fieldData->{type}</td>";
5342      # If we have content, add it as a third column.      # If we have content, add it as a third column.
5343      if (exists $fieldData->{Notes}) {      if (exists $fieldData->{Notes}) {
5344          $htmlString .= "<td>" . _HTMLNote($fieldData->{Notes}->{content}) . "</td>";          $htmlString .= "<td>" . HTMLNote($fieldData->{Notes}->{content}) . "</td>";
5345      }      }
5346      # Close off the row.      # Close off the row.
5347      $htmlString .= "</tr>\n";      $htmlString .= "</tr>\n";
# Line 4219  Line 5349 
5349      return $htmlString;      return $htmlString;
5350  }  }
5351    
 =head3 _HTMLNote  
   
 Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes  
 supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.  
 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.  
   
 This is a static method.  
   
 =over 4  
   
 =item dataString  
   
 String to convert to HTML.  
   
 =item RETURN  
   
 An HTML string derived from the input string.  
   
 =back  
   
 =cut  
   
 sub _HTMLNote {  
     # Get the parameter.  
     my ($dataString) = @_;  
     # Substitute the codes.  
     $dataString =~ s!\[(/?[bi])\]!<$1>!g;  
     $dataString =~ s!\[p\]!</p><p>!g;  
     # Return the result.  
     return $dataString;  
 }  
   
 =head2 Data Generation Utilities  
   
 =head3 IntGen  
   
 C<< my $integer = IntGen($min, $max); >>  
   
 Returns a random number between the specified minimum and maximum (inclusive).  
   
 =over 4  
   
 =item min  
   
 Minimum permissible return value.  
   
 =item max  
   
 Maximum permissible return value.  
   
 =item RETURN  
   
 Returns a value no lower than the minimum and no greater than the maximum.  
   
 =back  
   
 =cut  
   
 sub IntGen {  
     # Get the parameters.  
     my ($min, $max) = @_;  
     # Determine the range of possible values. Note we put some space well above the  
     # maximum value to give it a fighting chance of apppearing in the list.  
     my $span = $max + 0.99 - $min;  
     # Create an integer in the range.  
     my $retVal = $min + int(rand($span));  
     # Return the result.  
     return $retVal;  
 }  
   
 =head3 RandChar  
   
 C<< my $char = RandChar($sourceString); >>  
   
 Select a random character from a string.  
   
 =over 4  
   
 =item sourceString  
   
 String from which the random character should be selected.  
   
 =item RETURN  
   
 Returns a single character from the incoming string.  
   
 =back  
   
 =cut  
   
 sub RandChar {  
     # Get the parameter.  
     my ($sourceString) = @_;  
     # Select a random character.  
     my $retVal = IntGen(0, (length $sourceString) - 1);  
     # Return it.  
     return substr($sourceString, $retVal, 1);  
 }  
   
 =head3 RandChars  
   
 C<< my $string = RandChars($sourceString, $length); >>  
   
 Create a string from characters taken from a source string.  
   
 =over 4  
   
 =item sourceString  
   
 String from which the random characters should be selected.  
   
 =item length  
   
 Number of characters to put in the output string.  
   
 =item RETURN  
   
 Returns a string of the specified length consisting of characters taken from the  
 source string.  
   
 =back  
   
 =cut  
   
 sub RandChars {  
     # Get the parameters.  
     my ($sourceString, $length) = @_;  
     # Call RandChar repeatedly to generate the string.  
     my $retVal = "";  
     for (my $i = 0; $i < $length; $i++) {  
         $retVal .= RandChar($sourceString);  
     }  
     # Return the result.  
     return $retVal;  
 }  
   
 =head3 RandParam  
   
 C<< my $value = RandParam($parm1, $parm2, ... $parmN); >>  
   
 Return a randomly-selected value from the parameter list.  
   
 =over 4  
   
 =item parm1, parm2, ... parmN  
   
 List of values of which one will be selected.  
   
 =item RETURN  
   
 Returns a randomly-chosen value from the specified list.  
   
 =back  
   
 =cut  
   
 sub RandParam {  
     # Get the parameter.  
     my @parms = @_;  
     # Choose a random parameter from the list.  
     my $chosenIndex = IntGen(0, $#parms);  
     return $parms[$chosenIndex];  
 }  
   
 =head3 StringGen  
   
 C<< my $string = StringGen($pattern1, $pattern2, ... $patternN); >>  
   
 Returns a random string derived from a randomly-chosen format pattern. The pattern  
 can either be a number (indicating the number of characters desired, or the letter  
 C<P> followed by a picture. The picture should contain C<A> when a letter is desired,  
 C<9> when a digit is desired, C<V> when a vowel is desired, C<K> when a consonant is  
 desired, and C<X> when a letter or a digit is desired. Any other character will be  
 translated as a literal.  
   
 =over 4  
   
 =item pattern1, pattern2, ... patternN  
   
 List of patterns to be used to generate string values.  
   
 =item RETURN  
   
 A single string generated from a pattern.  
   
 =back  
   
 =cut  
   
 sub StringGen {  
     # Get the parameters.  
     my @patterns = @_;  
     # Choose the appropriate pattern.  
     my $chosenPattern = RandParam(@patterns);  
     # Declare the return variable.  
     my $retVal = "";  
     # Determine whether this is a count or a picture pattern.  
     if ($chosenPattern =~ m/^\d+/) {  
         # Here we have a count. Get the string of source characters.  
         my $letterString = $PictureTable{'X'};  
         my $stringLen = length $letterString;  
         # Save the number of characters we have to generate.  
         my $charsLeft = $chosenPattern;  
         # Loop until the return variable is full.  
         while ($charsLeft > 0) {  
             # Generate a random position in the soruce string.  
             my $stringIndex = IntGen(0, $stringLen - 1);  
             # Compute the number of characters to pull out of the source string.  
             my $chunkSize = $stringLen - $stringIndex;  
             if ($chunkSize > $charsLeft) { $chunkSize = $charsLeft; }  
             # Stuff this chunk into the return value.  
             $retVal .= substr($letterString, $stringIndex, $chunkSize);  
             # Record the data moved.  
             $charsLeft -= $chunkSize;  
         }  
     } elsif ($chosenPattern =~ m/^P/) {  
         # Here we have a picture string. We will move through the picture one  
         # character at a time generating data.  
         for (my $i = 1; $i < length $chosenPattern; $i++) {  
             # Get this picture character.  
             my $chr = substr($chosenPattern, $i, 1);  
             # Check to see if the picture char is one we recognize.  
             if (exists $PictureTable{$chr}) {  
                 # Choose a random character from the available values for this  
                 # picture character.  
                 $retVal .= RandChar($PictureTable{$chr});  
             } else {  
                 # Copy in the picture character as a literal.  
                 $retVal .= $chr;  
             }  
         }  
     } else {  
         # Here we have neither a picture string or a letter count, so we treat  
         # the string as a literal.  
         $retVal = $chosenPattern;  
     }  
     # Return the string formed.  
     return $retVal;  
 }  
   
 =head3 DateGen  
   
 C<< my $date = DateGen($startDayOffset, $endDayOffset, $minutes); >>  
   
 Return a numeric timestamp within the specified range of days with the specified minute  
 value. The range of days is specified relevant to the current day. Thus, the call  
   
 C<< my $date = DateGen(-1, 5, 720); >>  
   
 will return a timestamp at noon (72 minutes past midnight) sometime during the week that  
 began on the preceding day. If you want a random minute of the day, simply combine with  
 a call to L</IntGen>, as follows.  
   
 C<< my $date = DateGen(-1, 5, IntGen(0, 1439)); >>  
   
 =over 4  
   
 =item startDayOffset  
   
 The earliest day that can be returned, relative to the current day.  
   
 =item endDayOffset  
   
 The latest day that can be returned, related to the current day.  
   
 =item minutes  
   
 Number of minutes into the selected day that should be used.  
   
 =back  
   
 =cut  
   
 sub DateGen {  
     # Get the parameters.  
     my ($startDayOffset, $endDayOffset, $minutes) = @_;  
     # Get midnight of the current day.  
     my $now = time();  
     my ($sec, $min, $hour) = localtime($now);  
     my $today = $now - (($hour * 60 + $min) * 60 + $sec);  
     # Compute the day we want.  
     my $newDay = IntGen($startDayOffset, $endDayOffset) * 86400 + $today;  
     # Add the minutes.  
     my $retVal = $newDay + $minutes * 60;  
     # Return the result.  
     return $retVal;  
 }  
   
 =head3 FloatGen  
   
 C<< my $number = FloatGen($min, $max); >>  
   
 Return a random floating-point number greater than or equal to the specified minimum and  
 less than the specified maximum.  
   
 =over 4  
   
 =item min  
   
 Minimum permissible value for the number returned.  
   
 =item max  
   
 Maximum permissible value for the number returned.  
   
 =item RETURN  
   
 Returns a floating-point number anywhere in the specified range.  
   
 =back  
   
 =cut  
   
 sub FloatGen {  
     # Get the parameters.  
     my ($min, $max) = @_;  
     # Generate the result.  
     my $retVal = rand($max - $min) + $min;  
     return $retVal;  
 }  
   
 =head3 ListGen  
   
 C<< my @list = ListGen($pattern, $count); >>  
   
 Return a list containing a fixed number of randomly-generated strings.  
   
 =over 4  
   
 =item pattern  
   
 A pattern (in the form expected by L</StringGen>) that should be used to generate the  
 strings in the list.  
   
 =item count  
   
 The number of list entries to generate.  
   
 =item RETURN  
   
 Returns a list consisting of the specified number of strings.  
   
 =back  
   
 =cut  
   
 sub ListGen {  
     # Get the parameters.  
     my ($pattern, $count) = @_;  
     # Generate the list.  
     my @retVal = ();  
     for (my $i = 0; $i < $count; $i++) {  
         push @retVal, StringGen($pattern);  
     }  
     # Return it.  
     return @retVal;  
 }  
   
5352  1;  1;

Legend:
Removed from v.1.70  
changed lines
  Added in v.1.89

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3