[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 1.96, Tue Feb 5 04:52:24 2008 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 CGI;
14        use WikiTools;
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                     'long-string' =>
377                                 { sqlType => 'VARCHAR(500)',       maxLen => 500,          avglen => 255, sort => "",
378                                   indexMod =>   0, notes => "character string, 0 to 500 characters"},
379                  );                  );
380    
381  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 357  Line 384 
384                     'MM' => 'many-to-many'                     'MM' => 'many-to-many'
385                   );                   );
386    
387  # Table for interpreting string patterns.  # Options for XML input and output.
388    
389    my %XmlOptions = (GroupTags =>  { Relationships => 'Relationship',
390                                      Entities => 'Entity',
391                                      Fields => 'Field',
392                                      Indexes => 'Index',
393                                      IndexFields => 'IndexField'
394                                    },
395                      KeyAttr =>    { Relationship => 'name',
396                                      Entity => 'name',
397                                      Field => 'name'
398                                    },
399                      SuppressEmpty => 1,
400                     );
401    
402  my %PictureTable = ( 'A' => "abcdefghijklmnopqrstuvwxyz",  my %XmlInOpts  = (
403                       '9' => "0123456789",                    ForceArray => ['Field', 'Index', 'IndexField', 'Relationship', 'Entity'],
404                       'X' => "abcdefghijklmnopqrstuvwxyz0123456789",                    ForceContent => 1,
405                       'V' => "aeiou",                    NormalizeSpace => 2,
406                       'K' => "bcdfghjklmnoprstvwxyz"                   );
407    my %XmlOutOpts = (
408                      RootName => 'Database',
409                      XMLDecl => 1,
410                     );                     );
411    
412    
413  =head2 Public Methods  =head2 Public Methods
414    
415  =head3 new  =head3 new
416    
417  C<< my $database = ERDB->new($dbh, $metaFileName); >>      my $database = ERDB->new($dbh, $metaFileName);
418    
419  Create a new ERDB object.  Create a new ERDB object.
420    
# Line 390  Line 434 
434    
435  sub new {  sub new {
436      # Get the parameters.      # Get the parameters.
437      my ($class, $dbh, $metaFileName, $options) = @_;      my ($class, $dbh, $metaFileName, %options) = @_;
438      # Load the meta-data.      # Load the meta-data.
439      my $metaData = _LoadMetaData($metaFileName);      my $metaData = _LoadMetaData($metaFileName);
440      # Create the object.      # Create the object.
# Line 404  Line 448 
448    
449  =head3 ShowMetaData  =head3 ShowMetaData
450    
451  C<< $erdb->ShowMetaData($fileName); >>      $erdb->ShowMetaData($fileName);
452    
453  This method outputs a description of the database. This description can be used to help users create  This method outputs a description of the database. This description can be used to help users create
454  the data to be loaded into the relations.  the data to be loaded into the relations.
# Line 445  Line 489 
489    
490  =head3 DisplayMetaData  =head3 DisplayMetaData
491    
492  C<< my $html = $erdb->DisplayMetaData(); >>      my $html = $erdb->DisplayMetaData();
493    
494  Return an HTML description of the database. This description can be used to help users create  Return an HTML description of the database. This description can be used to help users create
495  the data to be loaded into the relations and form queries. The output is raw includable HTML  the data to be loaded into the relations and form queries. The output is raw includable HTML
# Line 506  Line 550 
550          my $entityData = $entityList->{$key};          my $entityData = $entityList->{$key};
551          # If there's descriptive text, display it.          # If there's descriptive text, display it.
552          if (my $notes = $entityData->{Notes}) {          if (my $notes = $entityData->{Notes}) {
553              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
554          }          }
555          # 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.
556            my $relCount = keys %{$relationshipList};
557            if ($relCount > 0) {
558                # First, we set up the relationship subsection.
559          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
560          # Loop through the relationships.          # Loop through the relationships.
561          for my $relationship (sort keys %{$relationshipList}) {          for my $relationship (sort keys %{$relationshipList}) {
# Line 524  Line 571 
571          }          }
572          # Close off the relationship list.          # Close off the relationship list.
573          $retVal .= "</ul>\n";          $retVal .= "</ul>\n";
574            }
575          # Get the entity's relations.          # Get the entity's relations.
576          my $relationList = $entityData->{Relations};          my $relationList = $entityData->{Relations};
577          # Create a header for the relation subsection.          # Create a header for the relation subsection.
# Line 563  Line 611 
611          $retVal .= "</p>\n";          $retVal .= "</p>\n";
612          # If there are notes on this relationship, display them.          # If there are notes on this relationship, display them.
613          if (my $notes = $relationshipStructure->{Notes}) {          if (my $notes = $relationshipStructure->{Notes}) {
614              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
615          }          }
616          # Generate the relationship's relation table.          # Generate the relationship's relation table.
617          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
# Line 597  Line 645 
645    
646  =head3 DumpMetaData  =head3 DumpMetaData
647    
648  C<< $erdb->DumpMetaData(); >>      $erdb->DumpMetaData();
649    
650  Return a dump of the metadata structure.  Return a dump of the metadata structure.
651    
# Line 610  Line 658 
658      return Data::Dumper::Dumper($self->{_metaData});      return Data::Dumper::Dumper($self->{_metaData});
659  }  }
660    
661    =head3 GenerateWikiData
662    
663        my @wikiLines = $erdb->GenerateWikiData();
664    
665    Build a description of the database for the wiki. The database will be
666    organized into a single page, with sections for each entity and relationship.
667    The return value is a list of text lines.
668    
669    =cut
670    
671    sub GenerateWikiData {
672        # Get the parameters.
673        my ($self) = @_;
674        # We'll build the wiki text in here.
675        my @retVal = ();
676        # Get the metadata object.
677        my $metadata = $self->{_metaData};
678        # Get the title string. This will become the page name.
679        my $title = $metadata->{Title}->{content};
680        # Get the entity and relationship lists.
681        my $entityList = $metadata->{Entities};
682        my $relationshipList = $metadata->{Relationships};
683        # Start with the introductory text.
684        push @retVal, WikiTools::Heading(2, "Introduction");
685        if (my $notes = $metadata->{Notes}) {
686            push @retVal, WikiNote($notes->{content});
687        }
688        # Start the entity section.
689        push @retVal, WikiTools::Heading(2, "Entities");
690        # Loop through the entities. Note that unlike the situation with HTML, we
691        # don't need to generate the table of contents manually, just the data
692        # itself.
693        for my $key (sort keys %$entityList) {
694            # Create a header for this entity.
695            push @retVal, "", WikiTools::Heading(3, $key);
696            # Get the entity data.
697            my $entityData = $entityList->{$key};
698            # Plant the notes here, if there are any.
699            if (my $notes = $entityData->{Notes}) {
700                push @retVal, "", WikiNote($notes->{content});
701            }
702            # Get the entity's relations.
703            my $relationList = $entityData->{Relations};
704            # Loop through the relations, displaying them.
705            for my $relation (sort keys %{$relationList}) {
706                my $wikiString = _WikiRelationTable($relation, $relationList->{$relation});
707                push @retVal, $wikiString;
708            }
709            # Now we list the entity's relationships (if any). First, we build a list
710            # of the relationships relevant to this entity.
711            my @rels = ();
712            for my $rel (sort keys %$relationshipList) {
713                my $relStructure = $relationshipList->{$rel};
714                if ($relStructure->{from} eq $key || $relStructure->{to} eq $key) {
715                    # Get the relationship sentence.
716                    my $relSentence = _ComputeRelationshipSentence($rel, $relStructure);
717                    # Linkify it.
718                    my $linkedRel = WikiTools::LinkMarkup("#$rel", $rel);
719                    $relSentence =~ s/$rel/$linkedRel/;
720                    push @rels, $relSentence;
721                }
722            }
723            # Add the relationships as a Wiki list.
724            push @retVal, WikiTools::List(@rels);
725        }
726        # Now the entities are documented. Next we do the relationships.
727        push @retVal, WikiTools::Heading(2, "Relationships");
728        for my $key (sort keys %$relationshipList) {
729            my $relationshipData = $relationshipList->{$key};
730            # Create the relationship heading.
731            push @retVal, WikiTools::Heading(3, $key);
732            # Describe the relationship arity. Note there's a bit of trickiness involving recursive
733            # many-to-many relationships. In a normal many-to-many we use two sentences to describe
734            # the arity (one for each direction). This is a bad idea for a recursive relationship,
735            # since both sentences will say the same thing.
736            my $arity = $relationshipData->{arity};
737            my $fromEntity = $relationshipData->{from};
738            my $toEntity = $relationshipData->{to};
739            my @listElements = ();
740            my $boldCode = WikiTools::BoldCode();
741            if ($arity eq "11") {
742                push @listElements, "Each $boldCode$fromEntity$boldCode relates to at most one $boldCode$toEntity$boldCode.";
743            } else {
744                push @listElements, "Each $boldCode$fromEntity$boldCode relates to multiple $boldCode${toEntity}s$boldCode.\n";
745                if ($arity eq "MM" && $fromEntity ne $toEntity) {
746                    push @listElements, "Each $boldCode$toEntity$boldCode relates to multiple $boldCode${fromEntity}s$boldCode.\n";
747                }
748            }
749            push @retVal, WikiTools::List(@listElements);
750            # Plant the notes here, if there are any.
751            if (my $notes = $relationshipData->{Notes}) {
752                push @retVal, "", WikiNote($notes->{content});
753            }
754            # Finally, the relationship table.
755            my $wikiString = _WikiRelationTable($key, $relationshipData->{Relations}->{$key});
756            push @retVal, $wikiString;
757        }
758        # All done. Return the lines.
759        return @retVal;
760    }
761    
762    
763    =head3 CreatePPO
764    
765        ERDB::CreatePPO($erdbXMLFile, $ppoXMLFile);
766    
767    Create a PPO XML file from an ERDB data definition XML file. At the
768    current time, the PPO XML file can be used to create a database with
769    similar functionality. Eventually, the PPO will be able to use the
770    created XML to access the live ERDB database.
771    
772    =over 4
773    
774    =item erdbXMLFile
775    
776    Name of the XML data definition file for the ERDB database. This
777    file must exist.
778    
779    =item ppoXMLFile
780    
781    Output file for the PPO XML definition. If this file exists, it
782    will be overwritten.
783    
784    =back
785    
786    =cut
787    
788    sub CreatePPO {
789        # Get the parameters.
790        my ($erdbXMLFile, $ppoXMLFile) = @_;
791        # First, we want to slurp in the ERDB XML file in its raw form.
792        my $xml = ReadMetaXML($erdbXMLFile);
793        # Create a variable to hold all of the objects in the PPO project.
794        my @objects = ();
795        # Get the relationship hash.
796        my $relationships = $xml->{Relationships};
797        # Loop through the entities.
798        my $entities = $xml->{Entities};
799        for my $entityName (keys %{$entities}) {
800            # Get the entity's data structures.
801            my $entityObject = $entities->{$entityName};
802            # We put the object's fields in here, according to their type.
803            my (@object_refs, @scalars, @indexes, @arrays);
804            # Create the ID field for the entity. We get the key type from the
805            # entity object and compute the corresponding SQL type.
806            my $type = $TypeTable{$entityObject->{keyType}}->{sqlType};
807            push @scalars, { label => 'id', type => $type };
808            # Loop through the entity fields.
809            for my $fieldName ( keys %{$entityObject->{Fields}} ) {
810                # Get the field object.
811                my $fieldObject = $entityObject->{Fields}->{$fieldName};
812                # Convert it to a scalar tag.
813                my $scalar = _CreatePPOField($fieldName, $fieldObject);
814                # If we have a relation, this field is stored in an array.
815                # otherwise, it is a scalar. The array tag has scalars
816                # stored as an XML array. In ERDB, there is only ever one,
817                # but PPO can have more.
818                my $relation = $fieldObject->{relation};
819                if ($relation) {
820                    push @arrays, { scalar => [$scalar] };
821                } else {
822                    push @scalars, $scalar;
823                }
824            }
825            # Loop through the relationships. If this entity is the to-entity
826            # on a relationship of 1M arity, then it is implemented as a PPO
827            # object reference.
828            for my $relationshipName (keys %{$relationships}) {
829                # Get the relationship data.
830                my $relationshipData = $relationships->{$relationshipName};
831                # If we have a from for this entity and an arity of 1M, we
832                # have an object reference.
833                if ($relationshipData->{to} eq $entityName &&
834                    $relationshipData->{arity} eq '1M') {
835                    # Build the object reference tag.
836                    push @object_refs, { label => $relationshipName,
837                                         type => $relationshipData->{from} };
838                }
839            }
840            # Create the indexes.
841            my $indexList = $entityObject->{Indexes};
842            push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
843            # Build the object XML tree.
844            my $object = { label => $entityName,
845                           object_ref => \@object_refs,
846                           scalar => \@scalars,
847                           index => \@indexes,
848                           array => \@arrays
849                          };
850            # Push the object onto the objects list.
851            push @objects, $object;
852        }
853        # Loop through the relationships, searching for MMs. The 1Ms were
854        # already handled by the entity search above.
855        for my $relationshipName (keys %{$relationships}) {
856            # Get this relationship's object.
857            my $relationshipObject = $relationships->{$relationshipName};
858            # Only proceed if it's many-to-many.
859            if ($relationshipObject->{arity} eq 'MM') {
860                # Create the tag lists for the relationship object.
861                my (@object_refs, @scalars, @indexes);
862                # The relationship will be created as an object with object
863                # references for its links to the participating entities.
864                my %links = ( from_link => $relationshipObject->{from},
865                              to_link => $relationshipObject->{to} );
866                for my $link (keys %links) {
867                    # Create an object_ref tag for this piece of the
868                    # relationship (from or to).
869                    my $object_ref = { label => $link,
870                                       type => $links{$link} };
871                    push @object_refs, $object_ref;
872                }
873                # Loop through the intersection data fields, creating scalar tags.
874                # There are no fancy array tags in a relationship.
875                for my $fieldName (keys %{$relationshipObject->{Fields}}) {
876                    my $fieldObject = $relationshipObject->{Fields}->{$fieldName};
877                    push @scalars, _CreatePPOField($fieldName, $fieldObject);
878                }
879                # Finally, the indexes: currently we cannot support the to-index and
880                # from-index in PPO, so we just process the alternate indexes.
881                my $indexList = $relationshipObject->{Indexes};
882                push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
883                # Wrap up all the stuff about this relationship.
884                my $object = { label => $relationshipName,
885                               scalar => \@scalars,
886                               object_ref => \@object_refs,
887                               index => \@indexes
888                             };
889                # Push it into the object list.
890                push @objects, $object;
891            }
892        }
893        # Compute a title.
894        my $title;
895        if ($erdbXMLFile =~ /(\/|^)([^\/]+)DBD\.xml/) {
896            # Here we have a standard file name we can use for a title.
897            $title = $2;
898        } else {
899            # Here the file name is non-standard, so we carve up the
900            # database title.
901            $title = $xml->{Title}->{content};
902            $title =~ s/\s\.,//g;
903        }
904        # Wrap up the XML as a project.
905        my $ppoXML = { project => { label => $title,
906                                    object => \@objects }};
907        # Write out the results.
908        my $ppoString = XML::Simple::XMLout($ppoXML,
909                                            AttrIndent => 1,
910                                            KeepRoot => 1);
911        Tracer::PutFile($ppoXMLFile, [ $ppoString ]);
912    }
913    
914    =head3 FindIndexForEntity
915    
916        my $indexFound = ERDB::FindIndexForEntity($xml, $entityName, $attributeName);
917    
918    This method locates the entry in an entity's index list that begins with the
919    specified attribute name. If the entity has no index list, one will be
920    created. This method works on raw XML, not a live ERDB object.
921    
922    =over 4
923    
924    =item xml
925    
926    The raw XML structure defining the database.
927    
928    =item entityName
929    
930    The name of the relevant entity.
931    
932    =item attributeName
933    
934    The name of the attribute relevant to the search.
935    
936    =item RETURN
937    
938    The numerical index in the index list of the index entry for the specified entity and
939    attribute, or C<undef> if no such index exists.
940    
941    =back
942    
943    =cut
944    
945    sub FindIndexForEntity {
946        # Get the parameters.
947        my ($xml, $entityName, $attributeName) = @_;
948        # Declare the return variable.
949        my $retVal;
950        # Get the named entity.
951        my $entityData = $xml->{Entities}->{$entityName};
952        if (! $entityData) {
953            Confess("Entity $entityName not found in DBD structure.");
954        } else {
955            # Insure it has an index list.
956            if (! exists $entityData->{Indexes}) {
957                $entityData->{Indexes} = [];
958            } else {
959                # Search for the desired index.
960                my $indexList = $entityData->{Indexes};
961                my $n = scalar @{$indexList};
962                Trace("Searching $n indexes in index list for $entityName.") if T(2);
963                # We use an indexed FOR here because we're returning an
964                # index number instead of an object. We do THAT so we can
965                # delete the index from the list if needed.
966                for (my $i = 0; $i < $n && !defined($retVal); $i++) {
967                    my $index = $indexList->[$i];
968                    my $fields = $index->{IndexFields};
969                    # Technically this IF should be safe (that is, we are guaranteed
970                    # the existence of a "$fields->[0]"), because when we load the XML
971                    # we have SuppressEmpty specified.
972                    if ($fields->[0]->{name} eq $attributeName) {
973                        $retVal = $i;
974                    }
975                }
976            }
977        }
978        Trace("Index for $attributeName of $entityName found at position $retVal.") if defined($retVal) && T(3);
979        Trace("Index for $attributeName not found in $entityName.") if !defined($retVal) && T(3);
980        # Return the result.
981        return $retVal;
982    }
983    
984  =head3 CreateTables  =head3 CreateTables
985    
986  C<< $erdb->CreateTables(); >>      $erdb->CreateTables();
987    
988  This method creates the tables for the database from the metadata structure loaded by the  This method creates the tables for the database from the metadata structure loaded by the
989  constructor. It is expected this function will only be used on rare occasions, when the  constructor. It is expected this function will only be used on rare occasions, when the
# Line 629  Line 1000 
1000      # Loop through the relations.      # Loop through the relations.
1001      for my $relationName (@relNames) {      for my $relationName (@relNames) {
1002          # Create a table for this relation.          # Create a table for this relation.
1003          $self->CreateTable($relationName);          $self->CreateTable($relationName, 1);
1004          Trace("Relation $relationName created.") if T(2);          Trace("Relation $relationName created.") if T(2);
1005      }      }
1006  }  }
1007    
1008  =head3 CreateTable  =head3 CreateTable
1009    
1010  C<< $erdb->CreateTable($tableName, $indexFlag, $estimatedRows); >>      $erdb->CreateTable($tableName, $indexFlag, $estimatedRows);
1011    
1012  Create the table for a relation and optionally create its indexes.  Create the table for a relation and optionally create its indexes.
1013    
# Line 692  Line 1063 
1063      my $estimation = undef;      my $estimation = undef;
1064      if ($estimatedRows) {      if ($estimatedRows) {
1065          $estimation = [$self->EstimateRowSize($relationName), $estimatedRows];          $estimation = [$self->EstimateRowSize($relationName), $estimatedRows];
1066            Trace("$estimation->[1] rows of $estimation->[0] bytes each.") if T(3);
1067      }      }
1068      # Create the table.      # Create the table.
1069      Trace("Creating table $relationName: $fieldThing") if T(2);      Trace("Creating table $relationName: $fieldThing") if T(2);
# Line 706  Line 1078 
1078    
1079  =head3 VerifyFields  =head3 VerifyFields
1080    
1081  C<< my $count = $erdb->VerifyFields($relName, \@fieldList); >>      my $count = $erdb->VerifyFields($relName, \@fieldList);
1082    
1083  Run through the list of proposed field values, insuring that all the character fields are  Run through the list of proposed field values, insuring that all the character fields are
1084  below the maximum length. If any fields are too long, they will be truncated in place.  below the maximum length. If any fields are too long, they will be truncated in place.
# Line 749  Line 1121 
1121              my $oldString = $fieldList->[$i];              my $oldString = $fieldList->[$i];
1122              if (length($oldString) > $maxLen) {              if (length($oldString) > $maxLen) {
1123                  # Here it's too big, so we truncate it.                  # Here it's too big, so we truncate it.
1124                  Trace("Truncating field $i in relation $relName to $maxLen characters from \"$oldString\".") if T(1);                  Trace("Truncating field $i ($fieldTypes->[$i]->{name}) in relation $relName to $maxLen characters from \"$oldString\".") if T(1);
1125                  $fieldList->[$i] = substr $oldString, 0, $maxLen;                  $fieldList->[$i] = substr $oldString, 0, $maxLen;
1126                  $retVal++;                  $retVal++;
1127              }              }
# Line 761  Line 1133 
1133    
1134  =head3 DigestFields  =head3 DigestFields
1135    
1136  C<< $erdb->DigestFields($relName, $fieldList); >>      $erdb->DigestFields($relName, $fieldList);
1137    
1138  Digest the strings in the field list that correspond to data type C<hash-string> in the  Digest the strings in the field list that correspond to data type C<hash-string> in the
1139  specified relation.  specified relation.
# Line 801  Line 1173 
1173    
1174  =head3 DigestKey  =head3 DigestKey
1175    
1176  C<< my $digested = $erdb->DigestKey($keyValue); >>      my $digested = $erdb->DigestKey($keyValue);
1177    
1178  Return the digested value of a symbolic key. The digested value can then be plugged into a  Return the digested value of a symbolic key. The digested value can then be plugged into a
1179  key-based search into a table with key-type hash-string.  key-based search into a table with key-type hash-string.
# Line 834  Line 1206 
1206    
1207  =head3 CreateIndex  =head3 CreateIndex
1208    
1209  C<< $erdb->CreateIndex($relationName); >>      $erdb->CreateIndex($relationName);
1210    
1211  Create the indexes for a relation. If a table is being loaded from a large source file (as  Create the indexes for a relation. If a table is being loaded from a large source file (as
1212  is the case in L</LoadTable>), it is sometimes best to create the indexes after the load.  is the case in L</LoadTable>), it is sometimes best to create the indexes after the load.
# Line 855  Line 1227 
1227      for my $indexName (keys %{$indexHash}) {      for my $indexName (keys %{$indexHash}) {
1228          my $indexData = $indexHash->{$indexName};          my $indexData = $indexHash->{$indexName};
1229          # Get the index's field list.          # Get the index's field list.
1230          my @fieldList = _FixNames(@{$indexData->{IndexFields}});          my @rawFields = @{$indexData->{IndexFields}};
1231            # Get a hash of the relation's field types.
1232            my %types = map { $_->{name} => $_->{type} } @{$relationData->{Fields}};
1233            # We need to check for text fields so we can append a length limitation for them. To do
1234            # that, we need the relation's field list.
1235            my $relFields = $relationData->{Fields};
1236            for (my $i = 0; $i <= $#rawFields; $i++) {
1237                # Get the field type.
1238                my $field = $rawFields[$i];
1239                my $type = $types{$field};
1240                # Ask if it requires using prefix notation for the index.
1241                my $mod = $TypeTable{$type}->{indexMod};
1242                Trace("Field $field ($i) in $relationName has type $type and indexMod $mod.") if T(3);
1243                if ($mod) {
1244                    # Append the prefix length to the field name,
1245                    $rawFields[$i] .= "($mod)";
1246                }
1247            }
1248            my @fieldList = _FixNames(@rawFields);
1249          my $flds = join(', ', @fieldList);          my $flds = join(', ', @fieldList);
1250          # Get the index's uniqueness flag.          # Get the index's uniqueness flag.
1251          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
# Line 870  Line 1260 
1260      }      }
1261  }  }
1262    
1263    =head3 GetSecondaryFields
1264    
1265        my %fieldTuples = $erdb->GetSecondaryFields($entityName);
1266    
1267    This method will return a list of the name and type of each of the secondary
1268    fields for a specified entity. Secondary fields are stored in two-column tables
1269    in addition to the primary entity table. This enables the field to have no value
1270    or to have multiple values.
1271    
1272    =over 4
1273    
1274    =item entityName
1275    
1276    Name of the entity whose secondary fields are desired.
1277    
1278    =item RETURN
1279    
1280    Returns a hash mapping the field names to their field types.
1281    
1282    =back
1283    
1284    =cut
1285    
1286    sub GetSecondaryFields {
1287        # Get the parameters.
1288        my ($self, $entityName) = @_;
1289        # Declare the return variable.
1290        my %retVal = ();
1291        # Look for the entity.
1292        my $table = $self->GetFieldTable($entityName);
1293        # Loop through the fields, pulling out the secondaries.
1294        for my $field (sort keys %{$table}) {
1295            if ($table->{$field}->{relation} ne $entityName) {
1296                # Here we have a secondary field.
1297                $retVal{$field} = $table->{$field}->{type};
1298            }
1299        }
1300        # Return the result.
1301        return %retVal;
1302    }
1303    
1304    =head3 GetFieldRelationName
1305    
1306        my $name = $erdb->GetFieldRelationName($objectName, $fieldName);
1307    
1308    Return the name of the relation containing a specified field.
1309    
1310    =over 4
1311    
1312    =item objectName
1313    
1314    Name of the entity or relationship containing the field.
1315    
1316    =item fieldName
1317    
1318    Name of the relevant field in that entity or relationship.
1319    
1320    =item RETURN
1321    
1322    Returns the name of the database relation containing the field, or C<undef> if
1323    the field does not exist.
1324    
1325    =back
1326    
1327    =cut
1328    
1329    sub GetFieldRelationName {
1330        # Get the parameters.
1331        my ($self, $objectName, $fieldName) = @_;
1332        # Declare the return variable.
1333        my $retVal;
1334        # Get the object field table.
1335        my $table = $self->GetFieldTable($objectName);
1336        # Only proceed if the field exists.
1337        if (exists $table->{$fieldName}) {
1338            # Determine the name of the relation that contains this field.
1339            $retVal = $table->{$fieldName}->{relation};
1340        }
1341        # Return the result.
1342        return $retVal;
1343    }
1344    
1345    =head3 DeleteValue
1346    
1347        my $numDeleted = $erdb->DeleteValue($entityName, $id, $fieldName, $fieldValue);
1348    
1349    Delete secondary field values from the database. This method can be used to delete all
1350    values of a specified field for a particular entity instance, or only a single value.
1351    
1352    Secondary fields are stored in two-column relations separate from an entity's primary
1353    table, and as a result a secondary field can legitimately have no value or multiple
1354    values. Therefore, it makes sense to talk about deleting secondary fields where it
1355    would not make sense for primary fields.
1356    
1357    =over 4
1358    
1359    =item entityName
1360    
1361    Name of the entity from which the fields are to be deleted.
1362    
1363    =item id
1364    
1365    ID of the entity instance to be processed. If the instance is not found, this
1366    method will have no effect. If C<undef> is specified, all values for all of
1367    the entity instances will be deleted.
1368    
1369    =item fieldName
1370    
1371    Name of the field whose values are to be deleted.
1372    
1373    =item fieldValue (optional)
1374    
1375    Value to be deleted. If not specified, then all values of the specified field
1376    will be deleted for the entity instance. If specified, then only the values which
1377    match this parameter will be deleted.
1378    
1379    =item RETURN
1380    
1381    Returns the number of rows deleted.
1382    
1383    =back
1384    
1385    =cut
1386    
1387    sub DeleteValue {
1388        # Get the parameters.
1389        my ($self, $entityName, $id, $fieldName, $fieldValue) = @_;
1390        # Declare the return value.
1391        my $retVal = 0;
1392        # We need to set up an SQL command to do the deletion. First, we
1393        # find the name of the field's relation.
1394        my $table = $self->GetFieldTable($entityName);
1395        my $field = $table->{$fieldName};
1396        my $relation = $field->{relation};
1397        # Make sure this is a secondary field.
1398        if ($relation eq $entityName) {
1399            Confess("Cannot delete values of $fieldName for $entityName.");
1400        } else {
1401            # Set up the SQL command to delete all values.
1402            my $sql = "DELETE FROM $relation";
1403            # Build the filter.
1404            my @filters = ();
1405            my @parms = ();
1406            # Check for a filter by ID.
1407            if (defined $id) {
1408                push @filters, "id = ?";
1409                push @parms, $id;
1410            }
1411            # Check for a filter by value.
1412            if (defined $fieldValue) {
1413                push @filters, "$fieldName = ?";
1414                push @parms, $fieldValue;
1415            }
1416            # Append the filters to the command.
1417            if (@filters) {
1418                $sql .= " WHERE " . join(" AND ", @filters);
1419            }
1420            # Execute the command.
1421            my $dbh = $self->{_dbh};
1422            $retVal = $dbh->SQL($sql, 0, @parms);
1423        }
1424        # Return the result.
1425        return $retVal;
1426    }
1427    
1428  =head3 LoadTables  =head3 LoadTables
1429    
1430  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>      my $stats = $erdb->LoadTables($directoryName, $rebuild);
1431    
1432  This method will load the database tables from a directory. The tables must already have been created  This method will load the database tables from a directory. The tables must already have been created
1433  in the database. (This can be done by calling L</CreateTables>.) The caller passes in a directory name;  in the database. (This can be done by calling L</CreateTables>.) The caller passes in a directory name;
# Line 932  Line 1487 
1487    
1488  =head3 GetTableNames  =head3 GetTableNames
1489    
1490  C<< my @names = $erdb->GetTableNames; >>      my @names = $erdb->GetTableNames;
1491    
1492  Return a list of the relations required to implement this database.  Return a list of the relations required to implement this database.
1493    
# Line 949  Line 1504 
1504    
1505  =head3 GetEntityTypes  =head3 GetEntityTypes
1506    
1507  C<< my @names = $erdb->GetEntityTypes; >>      my @names = $erdb->GetEntityTypes;
1508    
1509  Return a list of the entity type names.  Return a list of the entity type names.
1510    
# Line 964  Line 1519 
1519      return sort keys %{$entityList};      return sort keys %{$entityList};
1520  }  }
1521    
1522    =head3 GetDataTypes
1523    
1524        my %types = ERDB::GetDataTypes();
1525    
1526    Return a table of ERDB data types. The table returned is a hash of hashes.
1527    The keys of the big hash are the datatypes. Each smaller hash has several
1528    values used to manage the data. The most interesting is the SQL type (key
1529    C<sqlType>) and the descriptive node (key C<notes>).
1530    
1531    Note that changing the values in the smaller hashes will seriously break
1532    things, so this data should be treated as read-only.
1533    
1534    =cut
1535    
1536    sub GetDataTypes {
1537        return %TypeTable;
1538    }
1539    
1540    
1541  =head3 IsEntity  =head3 IsEntity
1542    
1543  C<< my $flag = $erdb->IsEntity($entityName); >>      my $flag = $erdb->IsEntity($entityName);
1544    
1545  Return TRUE if the parameter is an entity name, else FALSE.  Return TRUE if the parameter is an entity name, else FALSE.
1546    
# Line 993  Line 1567 
1567    
1568  =head3 Get  =head3 Get
1569    
1570  C<< my $query = $erdb->Get(\@objectNames, $filterClause, \@params); >>      my $query = $erdb->Get(\@objectNames, $filterClause, \@params);
1571    
1572  This method returns a query object for entities of a specified type using a specified filter.  This method returns a query object for entities of a specified type using a specified filter.
1573  The filter is a standard WHERE/ORDER BY clause with question marks as parameter markers and each  The filter is a standard WHERE/ORDER BY clause with question marks as parameter markers and each
# Line 1001  Line 1575 
1575  following call requests all B<Genome> objects for the genus specified in the variable  following call requests all B<Genome> objects for the genus specified in the variable
1576  $genus.  $genus.
1577    
1578  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", [$genus]); >>      $query = $erdb->Get(['Genome'], "Genome(genus) = ?", [$genus]);
1579    
1580  The WHERE clause contains a single question mark, so there is a single additional  The WHERE clause contains a single question mark, so there is a single additional
1581  parameter representing the parameter value. It would also be possible to code  parameter representing the parameter value. It would also be possible to code
1582    
1583  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>      $query = $erdb->Get(['Genome'], "Genome(genus) = \'$genus\'");
1584    
1585  however, this version of the call would generate a syntax error if there were any quote  however, this version of the call would generate a syntax error if there were any quote
1586  characters inside the variable C<$genus>.  characters inside the variable C<$genus>.
# Line 1018  Line 1592 
1592  It is possible to specify multiple entity and relationship names in order to retrieve more than  It is possible to specify multiple entity and relationship names in order to retrieve more than
1593  one object's data at the same time, which allows highly complex joined queries. For example,  one object's data at the same time, which allows highly complex joined queries. For example,
1594    
1595  C<< $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]); >>      $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]);
1596    
1597  If multiple names are specified, then the query processor will automatically determine a  If multiple names are specified, then the query processor will automatically determine a
1598  join path between the entities and relationships. The algorithm used is very simplistic.  join path between the entities and relationships. The algorithm used is very simplistic.
# Line 1054  Line 1628 
1628  with an ORDER BY clause. For example, the following filter string gets all genomes for a  with an ORDER BY clause. For example, the following filter string gets all genomes for a
1629  particular genus and sorts them by species name.  particular genus and sorts them by species name.
1630    
1631  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>      "Genome(genus) = ? ORDER BY Genome(species)"
1632    
1633  Note that the case is important. Only an uppercase "ORDER BY" with a single space will  Note that the case is important. Only an uppercase "ORDER BY" with a single space will
1634  be processed. The idea is to make it less likely to find the verb by accident.  be processed. The idea is to make it less likely to find the verb by accident.
# Line 1067  Line 1641 
1641  be the last thing in the filter clause, and it contains only the word "LIMIT" followed by  be the last thing in the filter clause, and it contains only the word "LIMIT" followed by
1642  a positive number. So, for example  a positive number. So, for example
1643    
1644  C<< "Genome(genus) = ? ORDER BY Genome(species) LIMIT 10" >>      "Genome(genus) = ? ORDER BY Genome(species) LIMIT 10"
1645    
1646  will only return the first ten genomes for the specified genus. The ORDER BY clause is not  will only return the first ten genomes for the specified genus. The ORDER BY clause is not
1647  required. For example, to just get the first 10 genomes in the B<Genome> table, you could  required. For example, to just get the first 10 genomes in the B<Genome> table, you could
1648  use  use
1649    
1650  C<< "LIMIT 10" >>      "LIMIT 10"
1651    
1652  =item params  =item params
1653    
# Line 1094  Line 1668 
1668      my ($suffix, $mappedNameListRef, $mappedNameHashRef) =      my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1669          $self->_SetupSQL($objectNames, $filterClause);          $self->_SetupSQL($objectNames, $filterClause);
1670      # Create the query.      # Create the query.
1671      my $command = "SELECT DISTINCT " . join(".*, ", @{$mappedNameListRef}) .      my $command = "SELECT " . join(".*, ", @{$mappedNameListRef}) .
1672          ".* $suffix";          ".* $suffix";
1673      my $sth = $self->_GetStatementHandle($command, $params);      my $sth = $self->_GetStatementHandle($command, $params);
1674      # Now we create the relation map, which enables DBQuery to determine the order, name      # Now we create the relation map, which enables DBQuery to determine the order, name
# Line 1108  Line 1682 
1682      return $retVal;      return $retVal;
1683  }  }
1684    
1685    
1686    
1687  =head3 Search  =head3 Search
1688    
1689  C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>      my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params);
1690    
1691  Perform a full text search with filtering. The search will be against a specified object  Perform a full text search with filtering. The search will be against a specified object
1692  in the object name list. That object will get an extra field containing the search  in the object name list. That object will get an extra field containing the search
# Line 1121  Line 1697 
1697    
1698  =item searchExpression  =item searchExpression
1699    
1700  Boolean search expression for the text fields of the target object.  Boolean search expression for the text fields of the target object. The default mode for
1701    a Boolean search expression is OR, but we want the default to be AND, so we will
1702    add a C<+> operator to each word with no other operator before it.
1703    
1704  =item idx  =item idx
1705    
# Line 1158  Line 1736 
1736      my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;      my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1737      # Declare the return variable.      # Declare the return variable.
1738      my $retVal;      my $retVal;
1739      # Create a safety copy of the parameter list.      # Create a safety copy of the parameter list. Note we have to be careful to insure
1740      my @myParams = @{$params};      # a parameter list exists before we copy it.
1741        my @myParams = ();
1742        if (defined $params) {
1743            @myParams = @{$params};
1744        }
1745      # 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.
1746      my $object1Name = $objectNames->[$idx];      my $object1Name = $objectNames->[$idx];
1747      my $object1Structure = $self->_GetStructure($object1Name);      my $object1Structure = $self->_GetStructure($object1Name);
# Line 1169  Line 1751 
1751      } else {      } else {
1752          # Get the field list.          # Get the field list.
1753          my @fields = @{$object1Structure->{searchFields}};          my @fields = @{$object1Structure->{searchFields}};
1754            # Clean the search expression.
1755            my $actualKeywords = $self->CleanKeywords($searchExpression);
1756            # Prefix a "+" to each uncontrolled word. This converts the default
1757            # search mode from OR to AND.
1758            $actualKeywords =~ s/(^|\s)(\w|")/$1\+$2/g;
1759            Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1760          # 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
1761          # 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
1762          # search expression onto the front of the parameter list twice.          # search expression onto the front of the parameter list twice.
1763          unshift @myParams, $searchExpression, $searchExpression;          unshift @myParams, $actualKeywords, $actualKeywords;
1764          # Build the match expression.          # Build the match expression.
1765          my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;          my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
1766          my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";          my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
# Line 1181  Line 1769 
1769              $self->_SetupSQL($objectNames, $filterClause, $matchClause);              $self->_SetupSQL($objectNames, $filterClause, $matchClause);
1770          # Create the query. Note that the match clause is inserted at the front of          # Create the query. Note that the match clause is inserted at the front of
1771          # the select fields.          # the select fields.
1772          my $command = "SELECT DISTINCT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .          my $command = "SELECT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .
1773              ".* $suffix";              ".* $suffix";
1774          my $sth = $self->_GetStatementHandle($command, \@myParams);          my $sth = $self->_GetStatementHandle($command, \@myParams);
1775          # Now we create the relation map, which enables DBQuery to determine the order, name          # Now we create the relation map, which enables DBQuery to determine the order, name
# Line 1195  Line 1783 
1783    
1784  =head3 GetFlat  =head3 GetFlat
1785    
1786  C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>      my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field);
1787    
1788  This is a variation of L</GetAll> that asks for only a single field per record and  This is a variation of L</GetAll> that asks for only a single field per record and
1789  returns a single flattened list.  returns a single flattened list.
# Line 1246  Line 1834 
1834      return @retVal;      return @retVal;
1835  }  }
1836    
1837    =head3 SpecialFields
1838    
1839        my %specials = $erdb->SpecialFields($entityName);
1840    
1841    Return a hash mapping special fields in the specified entity to the value of their
1842    C<special> attribute. This enables the subclass to get access to the special field
1843    attributes without needed to plumb the internal ERDB data structures.
1844    
1845    =over 4
1846    
1847    =item entityName
1848    
1849    Name of the entity whose special fields are desired.
1850    
1851    =item RETURN
1852    
1853    Returns a hash. The keys of the hash are the special field names, and the values
1854    are the values from each special field's C<special> attribute.
1855    
1856    =back
1857    
1858    =cut
1859    
1860    sub SpecialFields {
1861        # Get the parameters.
1862        my ($self, $entityName) = @_;
1863        # Declare the return variable.
1864        my %retVal = ();
1865        # Find the entity's data structure.
1866        my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1867        # Loop through its fields, adding each special field to the return hash.
1868        my $fieldHash = $entityData->{Fields};
1869        for my $fieldName (keys %{$fieldHash}) {
1870            my $fieldData = $fieldHash->{$fieldName};
1871            if (exists $fieldData->{special}) {
1872                $retVal{$fieldName} = $fieldData->{special};
1873            }
1874        }
1875        # Return the result.
1876        return %retVal;
1877    }
1878    
1879  =head3 Delete  =head3 Delete
1880    
1881  C<< my $stats = $erdb->Delete($entityName, $objectID); >>      my $stats = $erdb->Delete($entityName, $objectID, %options);
1882    
1883  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
1884  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.
1885  always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many  
1886  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
1887    relationship connected to a dependent entity or if it is the "to" entity connected to a 1-to-many
1888  dependent relationship.  dependent relationship.
1889    
1890  =over 4  =over 4
# Line 1267  Line 1898 
1898  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<%>),
1899  then it is presumed to by a LIKE pattern.  then it is presumed to by a LIKE pattern.
1900    
1901  =item testFlag  =item options
1902    
1903  If TRUE, the delete statements will be traced without being executed.  A hash detailing the options for this delete operation.
1904    
1905  =item RETURN  =item RETURN
1906    
# Line 1278  Line 1909 
1909    
1910  =back  =back
1911    
1912    The permissible options for this method are as follows.
1913    
1914    =over 4
1915    
1916    =item testMode
1917    
1918    If TRUE, then the delete statements will be traced, but no changes will be made to the database.
1919    
1920    =item keepRoot
1921    
1922    If TRUE, then the entity instances will not be deleted, only the dependent records.
1923    
1924    =back
1925    
1926  =cut  =cut
1927  #: Return Type $%;  #: Return Type $%;
1928  sub Delete {  sub Delete {
1929      # Get the parameters.      # Get the parameters.
1930      my ($self, $entityName, $objectID, $testFlag) = @_;      my ($self, $entityName, $objectID, %options) = @_;
1931      # Declare the return variable.      # Declare the return variable.
1932      my $retVal = Stats->new();      my $retVal = Stats->new();
1933      # Get the DBKernel object.      # Get the DBKernel object.
# Line 1299  Line 1944 
1944      # FROM-relationships and entities.      # FROM-relationships and entities.
1945      my @fromPathList = ();      my @fromPathList = ();
1946      my @toPathList = ();      my @toPathList = ();
1947      # This final hash is used to remember what work still needs to be done. We push paths      # This final list is used to remember what work still needs to be done. We push paths
1948      # onto the list, then pop them off to extend the paths. We prime it with the starting      # onto the list, then pop them off to extend the paths. We prime it with the starting
1949      # point. Note that we will work hard to insure that the last item on a path in the      # point. Note that we will work hard to insure that the last item on a path in the
1950      # TODO list is always an entity.      # to-do list is always an entity.
1951      my @todoList = ([$entityName]);      my @todoList = ([$entityName]);
1952      while (@todoList) {      while (@todoList) {
1953          # Get the current path.          # Get the current path.
# Line 1310  Line 1955 
1955          # Copy it into a list.          # Copy it into a list.
1956          my @stackedPath = @{$current};          my @stackedPath = @{$current};
1957          # 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.
1958          my $entityName = pop @stackedPath;          my $myEntityName = pop @stackedPath;
1959          # Add it to the alreadyFound list.          # Add it to the alreadyFound list.
1960          $alreadyFound{$entityName} = 1;          $alreadyFound{$myEntityName} = 1;
1961            # Figure out if we need to delete this entity.
1962            if ($myEntityName ne $entityName || ! $options{keepRoot}) {
1963          # Get the entity data.          # Get the entity data.
1964          my $entityData = $self->_GetStructure($entityName);              my $entityData = $self->_GetStructure($myEntityName);
1965          # 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.  
1966          my $relations = $entityData->{Relations};          my $relations = $entityData->{Relations};
1967          for my $relation (keys %{$relations}) {          for my $relation (keys %{$relations}) {
1968              my @augmentedList = (@stackedPath, $relation);              my @augmentedList = (@stackedPath, $relation);
1969              push @fromPathList, \@augmentedList;              push @fromPathList, \@augmentedList;
1970          }          }
1971            }
1972          # Now we need to look for relationships connected to this entity.          # Now we need to look for relationships connected to this entity.
1973          my $relationshipList = $self->{_metaData}->{Relationships};          my $relationshipList = $self->{_metaData}->{Relationships};
1974          for my $relationshipName (keys %{$relationshipList}) {          for my $relationshipName (keys %{$relationshipList}) {
1975              my $relationship = $relationshipList->{$relationshipName};              my $relationship = $relationshipList->{$relationshipName};
1976              # Check the FROM field. We're only interested if it's us.              # Check the FROM field. We're only interested if it's us.
1977              if ($relationship->{from} eq $entityName) {              if ($relationship->{from} eq $myEntityName) {
1978                  # Add the path to this relationship.                  # Add the path to this relationship.
1979                  my @augmentedList = (@stackedPath, $entityName, $relationshipName);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1980                  push @fromPathList, \@augmentedList;                  push @fromPathList, \@augmentedList;
1981                  # Check the arity. If it's MM we're done. If it's 1M                  # Check the arity. If it's MM we're done. If it's 1M
1982                  # and the target hasn't been seen yet, we want to                  # and the target hasn't been seen yet, we want to
# Line 1348  Line 1995 
1995              }              }
1996              # Now check the TO field. In this case only the relationship needs              # Now check the TO field. In this case only the relationship needs
1997              # deletion.              # deletion.
1998              if ($relationship->{to} eq $entityName) {              if ($relationship->{to} eq $myEntityName) {
1999                  my @augmentedList = (@stackedPath, $entityName, $relationshipName);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
2000                  push @toPathList, \@augmentedList;                  push @toPathList, \@augmentedList;
2001              }              }
2002          }          }
2003      }      }
2004      # Create the first qualifier for the WHERE clause. This selects the      # Create the first qualifier for the WHERE clause. This selects the
2005      # 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
2006      # 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
2007      # to the table containing the dependent records to delete.      # to the table containing the dependent records to delete.
2008      my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");      my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
2009      # 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 2042 
2042                  }                  }
2043              }              }
2044              # Now we have our desired DELETE statement.              # Now we have our desired DELETE statement.
2045              if ($testFlag) {              if ($options{testMode}) {
2046                  # Here the user wants to trace without executing.                  # Here the user wants to trace without executing.
2047                  Trace($stmt) if T(0);                  Trace($stmt) if T(0);
2048              } else {              } else {
2049                  # 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
2050                  # if an error occurs, so we just go ahead and do it.                  # if an error occurs, so we just go ahead and do it.
2051                  Trace("Executing delete from $target using '$objectID'.") if T(3);                  Trace("Executing delete from $target using '$objectID'.") if T(3);
2052                  my $rv = $db->SQL($stmt, 0, $objectID);                  my $rv = $db->SQL($stmt, 0, $objectID);
# Line 1414  Line 2061 
2061      return $retVal;      return $retVal;
2062  }  }
2063    
2064  =head3 SortNeeded  =head3 Disconnect
2065    
2066  C<< my $parms = $erdb->SortNeeded($relationName); >>      $erdb->Disconnect($relationshipName, $originEntityName, $originEntityID);
2067    
2068  Return the pipe command for the sort that should be applied to the specified  Disconnect an entity instance from all the objects to which it is related. This
2069  relation when creating the load file.  will delete each relationship instance that connects to the specified entity.
2070    
2071    =over 4
2072    
2073    =item relationshipName
2074    
2075    Name of the relationship whose instances are to be deleted.
2076    
2077    =item originEntityName
2078    
2079    Name of the entity that is to be disconnected.
2080    
2081    =item originEntityID
2082    
2083    ID of the entity that is to be disconnected.
2084    
2085    =back
2086    
2087    =cut
2088    
2089    sub Disconnect {
2090        # Get the parameters.
2091        my ($self, $relationshipName, $originEntityName, $originEntityID) = @_;
2092        # Get the relationship descriptor.
2093        my $structure = $self->_GetStructure($relationshipName);
2094        # Insure we have a relationship.
2095        if (! exists $structure->{from}) {
2096            Confess("$relationshipName is not a relationship in the database.");
2097        } else {
2098            # Get the database handle.
2099            my $dbh = $self->{_dbh};
2100            # We'll set this value to 1 if we find our entity.
2101            my $found = 0;
2102            # Loop through the ends of the relationship.
2103            for my $dir ('from', 'to') {
2104                if ($structure->{$dir} eq $originEntityName) {
2105                    $found = 1;
2106                    # Here we want to delete all relationship instances on this side of the
2107                    # entity instance.
2108                    Trace("Disconnecting in $dir direction with ID \"$originEntityID\".");
2109                    # We do this delete in batches to keep it from dragging down the
2110                    # server.
2111                    my $limitClause = ($FIG_Config::delete_limit ? "LIMIT $FIG_Config::delete_limit" : "");
2112                    my $done = 0;
2113                    while (! $done) {
2114                        # Do the delete.
2115                        my $rows = $dbh->SQL("DELETE FROM $relationshipName WHERE ${dir}_link = ? $limitClause", 0, $originEntityID);
2116                        # See if we're done. We're done if no rows were found or the delete is unlimited.
2117                        $done = ($rows == 0 || ! $limitClause);
2118                    }
2119                }
2120            }
2121            # Insure we found the entity on at least one end.
2122            if (! $found) {
2123                Confess("Entity \"$originEntityName\" does not use $relationshipName.");
2124            }
2125        }
2126    }
2127    
2128    =head3 DeleteRow
2129    
2130        $erdb->DeleteRow($relationshipName, $fromLink, $toLink, \%values);
2131    
2132    Delete a row from a relationship. In most cases, only the from-link and to-link are
2133    needed; however, for relationships with intersection data values can be specified
2134    for the other fields using a hash.
2135    
2136    =over 4
2137    
2138    =item relationshipName
2139    
2140    Name of the relationship from which the row is to be deleted.
2141    
2142    =item fromLink
2143    
2144    ID of the entity instance in the From direction.
2145    
2146    =item toLink
2147    
2148    ID of the entity instance in the To direction.
2149    
2150    =item values
2151    
2152    Reference to a hash of other values to be used for filtering the delete.
2153    
2154    =back
2155    
2156    =cut
2157    
2158    sub DeleteRow {
2159        # Get the parameters.
2160        my ($self, $relationshipName, $fromLink, $toLink, $values) = @_;
2161        # Create a hash of all the filter information.
2162        my %filter = ('from-link' => $fromLink, 'to-link' => $toLink);
2163        if (defined $values) {
2164            for my $key (keys %{$values}) {
2165                $filter{$key} = $values->{$key};
2166            }
2167        }
2168        # Build an SQL statement out of the hash.
2169        my @filters = ();
2170        my @parms = ();
2171        for my $key (keys %filter) {
2172            push @filters, _FixName($key) . " = ?";
2173            push @parms, $filter{$key};
2174        }
2175        Trace("Parms for delete row are " . join(", ", map { "\"$_\"" } @parms) . ".") if T(SQL => 4);
2176        my $command = "DELETE FROM $relationshipName WHERE " .
2177                      join(" AND ", @filters);
2178        # Execute it.
2179        my $dbh = $self->{_dbh};
2180        $dbh->SQL($command, undef, @parms);
2181    }
2182    
2183    =head3 DeleteLike
2184    
2185        my $deleteCount = $erdb->DeleteLike($relName, $filter, \@parms);
2186    
2187    Delete all the relationship rows that satisfy a particular filter condition. Unlike a normal
2188    filter, only fields from the relationship itself can be used.
2189    
2190    =over 4
2191    
2192    =item relName
2193    
2194    Name of the relationship whose records are to be deleted.
2195    
2196    =item filter
2197    
2198    A filter clause (L</Get>-style) for the delete query.
2199    
2200    =item parms
2201    
2202    Reference to a list of parameters for the filter clause.
2203    
2204    =item RETURN
2205    
2206    Returns a count of the number of rows deleted.
2207    
2208    =back
2209    
2210    =cut
2211    
2212    sub DeleteLike {
2213        # Get the parameters.
2214        my ($self, $objectName, $filter, $parms) = @_;
2215        # Declare the return variable.
2216        my $retVal;
2217        # Insure the parms argument is an array reference if the caller left it off.
2218        if (! defined($parms)) {
2219            $parms = [];
2220        }
2221        # Insure we have a relationship. The main reason for this is if we delete an entity
2222        # instance we have to yank out a bunch of other stuff with it.
2223        if ($self->IsEntity($objectName)) {
2224            Confess("Cannot use DeleteLike on $objectName, because it is not a relationship.");
2225        } else {
2226            # Create the SQL command suffix to get the desierd records.
2227            my ($suffix) = $self->_SetupSQL([$objectName], $filter);
2228            # Convert it to a DELETE command.
2229            my $command = "DELETE $suffix";
2230            # Execute the command.
2231            my $dbh = $self->{_dbh};
2232            my $result = $dbh->SQL($command, 0, @{$parms});
2233            # Check the results. Note we convert the "0D0" result to a real zero.
2234            # A failure causes an abnormal termination, so the caller isn't going to
2235            # worry about it.
2236            if (! defined $result) {
2237                Confess("Error deleting from $objectName: " . $dbh->errstr());
2238            } elsif ($result == 0) {
2239                $retVal = 0;
2240            } else {
2241                $retVal = $result;
2242            }
2243        }
2244        # Return the result count.
2245        return $retVal;
2246    }
2247    
2248    =head3 SortNeeded
2249    
2250        my $parms = $erdb->SortNeeded($relationName);
2251    
2252    Return the pipe command for the sort that should be applied to the specified
2253    relation when creating the load file.
2254    
2255  For example, if the load file should be sorted ascending by the first  For example, if the load file should be sorted ascending by the first
2256  field, this method would return  field, this method would return
# Line 1464  Line 2295 
2295      } elsif (exists $relationshipTable->{$relationName}) {      } elsif (exists $relationshipTable->{$relationName}) {
2296          # Here we have a relationship. We sort using the FROM index.          # Here we have a relationship. We sort using the FROM index.
2297          my $relationshipData = $relationshipTable->{$relationName};          my $relationshipData = $relationshipTable->{$relationName};
2298          my $index = $relationData->{Indexes}->{"idx${relationName}From"};          my $index = $relationData->{Indexes}->{idxFrom};
2299          push @keyNames, @{$index->{IndexFields}};          push @keyNames, @{$index->{IndexFields}};
2300      } else {      } else {
2301          # 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 1514  Line 2345 
2345    
2346  =head3 GetList  =head3 GetList
2347    
2348  C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>      my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params);
2349    
2350  Return a list of object descriptors for the specified objects as determined by the  Return a list of object descriptors for the specified objects as determined by the
2351  specified filter clause.  specified filter clause.
# Line 1542  Line 2373 
2373  with an ORDER BY clause. For example, the following filter string gets all genomes for a  with an ORDER BY clause. For example, the following filter string gets all genomes for a
2374  particular genus and sorts them by species name.  particular genus and sorts them by species name.
2375    
2376  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>      "Genome(genus) = ? ORDER BY Genome(species)"
2377    
2378  The rules for field references in a sort order are the same as those for field references in the  The rules for field references in a sort order are the same as those for field references in the
2379  filter clause in general; however, odd things may happen if a sort field is from a secondary  filter clause in general; however, odd things may happen if a sort field is from a secondary
# Line 1554  Line 2385 
2385    
2386  =item RETURN  =item RETURN
2387    
2388  Returns a list of B<DBObject>s that satisfy the query conditions.  Returns a list of B<ERDBObject>s that satisfy the query conditions.
2389    
2390  =back  =back
2391    
# Line 1577  Line 2408 
2408    
2409  =head3 GetCount  =head3 GetCount
2410    
2411  C<< my $count = $erdb->GetCount(\@objectNames, $filter, \@params); >>      my $count = $erdb->GetCount(\@objectNames, $filter, \@params);
2412    
2413  Return the number of rows found by a specified query. This method would  Return the number of rows found by a specified query. This method would
2414  normally be used to count the records in a single table. For example, in a  normally be used to count the records in a single table. For example, in a
# Line 1670  Line 2501 
2501    
2502  =head3 ComputeObjectSentence  =head3 ComputeObjectSentence
2503    
2504  C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>      my $sentence = $erdb->ComputeObjectSentence($objectName);
2505    
2506  Check an object name, and if it is a relationship convert it to a relationship sentence.  Check an object name, and if it is a relationship convert it to a relationship sentence.
2507    
# Line 1705  Line 2536 
2536    
2537  =head3 DumpRelations  =head3 DumpRelations
2538    
2539  C<< $erdb->DumpRelations($outputDirectory); >>      $erdb->DumpRelations($outputDirectory);
2540    
2541  Write the contents of all the relations to tab-delimited files in the specified directory.  Write the contents of all the relations to tab-delimited files in the specified directory.
2542  Each file will have the same name as the relation dumped, with an extension of DTX.  Each file will have the same name as the relation dumped, with an extension of DTX.
# Line 1747  Line 2578 
2578    
2579  =head3 InsertValue  =head3 InsertValue
2580    
2581  C<< $erdb->InsertValue($entityID, $fieldName, $value); >>      $erdb->InsertValue($entityID, $fieldName, $value);
2582    
2583  This method will insert a new value into the database. The value must be one  This method will insert a new value into the database. The value must be one
2584  associated with a secondary relation, since primary values cannot be inserted:  associated with a secondary relation, since primary values cannot be inserted:
# Line 1810  Line 2641 
2641    
2642  =head3 InsertObject  =head3 InsertObject
2643    
2644  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>      $erdb->InsertObject($objectType, \%fieldHash);
2645    
2646  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
2647  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 1819  Line 2650 
2650  example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases  example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases
2651  C<ZP_00210270.1> and C<gi|46206278>.  C<ZP_00210270.1> and C<gi|46206278>.
2652    
2653  C<< $erdb->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>      $erdb->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']});
2654    
2655  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
2656  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
2657    
2658  C<< $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>      $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'});
2659    
2660  =over 4  =over 4
2661    
# Line 1836  Line 2667 
2667    
2668  Hash of field names to values.  Hash of field names to values.
2669    
 =item RETURN  
   
 Returns 1 if successful, 0 if an error occurred.  
   
2670  =back  =back
2671    
2672  =cut  =cut
# Line 1938  Line 2765 
2765                  $retVal = $sth->execute(@parameterList);                  $retVal = $sth->execute(@parameterList);
2766                  if (!$retVal) {                  if (!$retVal) {
2767                      my $errorString = $sth->errstr();                      my $errorString = $sth->errstr();
2768                      Trace("Insert error: $errorString.") if T(0);                      Confess("Error inserting into $relationName: $errorString");
2769                    } else {
2770                        Trace("Insert successful using $parameterList[0].") if T(3);
2771                  }                  }
2772              }              }
2773          }          }
2774      }      }
2775      # Return the success indicator.      # Return a 1 for backward compatability.
2776      return $retVal;      return 1;
2777    }
2778    
2779    =head3 UpdateEntity
2780    
2781        $erdb->UpdateEntity($entityName, $id, \%fields);
2782    
2783    Update the values of an entity. This is an unprotected update, so it should only be
2784    done if the database resides on a database server.
2785    
2786    =over 4
2787    
2788    =item entityName
2789    
2790    Name of the entity to update. (This is the entity type.)
2791    
2792    =item id
2793    
2794    ID of the entity to update. If no entity exists with this ID, an error will be thrown.
2795    
2796    =item fields
2797    
2798    Reference to a hash mapping field names to their new values. All of the fields named
2799    must be in the entity's primary relation, and they cannot any of them be the ID field.
2800    
2801    =back
2802    
2803    =cut
2804    
2805    sub UpdateEntity {
2806        # Get the parameters.
2807        my ($self, $entityName, $id, $fields) = @_;
2808        # Get a list of the field names being updated.
2809        my @fieldList = keys %{$fields};
2810        # Verify that the fields exist.
2811        my $checker = $self->GetFieldTable($entityName);
2812        for my $field (@fieldList) {
2813            if ($field eq 'id') {
2814                Confess("Cannot update the ID field for entity $entityName.");
2815            } elsif ($checker->{$field}->{relation} ne $entityName) {
2816                Confess("Cannot find $field in primary relation of $entityName.");
2817            }
2818        }
2819        # Build the SQL statement.
2820        my @sets = ();
2821        my @valueList = ();
2822        for my $field (@fieldList) {
2823            push @sets, _FixName($field) . " = ?";
2824            push @valueList, $fields->{$field};
2825        }
2826        my $command = "UPDATE $entityName SET " . join(", ", @sets) . " WHERE id = ?";
2827        # Add the ID to the list of binding values.
2828        push @valueList, $id;
2829        # Call SQL to do the work.
2830        my $rows = $self->{_dbh}->SQL($command, 0, @valueList);
2831        # Check for errors.
2832        if ($rows == 0) {
2833            Confess("Entity $id of type $entityName not found.");
2834        }
2835  }  }
2836    
2837  =head3 LoadTable  =head3 LoadTable
2838    
2839  C<< my %results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>      my $results = $erdb->LoadTable($fileName, $relationName, %options);
2840    
2841  Load data from a tab-delimited file into a specified table, optionally re-creating the table  Load data from a tab-delimited file into a specified table, optionally re-creating the table
2842  first.  first.
# Line 1964  Line 2851 
2851    
2852  Name of the relation to be loaded. This is the same as the table name.  Name of the relation to be loaded. This is the same as the table name.
2853    
2854  =item truncateFlag  =item options
2855    
2856  TRUE if the table should be dropped and re-created, else FALSE  A hash of load options.
2857    
2858  =item RETURN  =item RETURN
2859    
# Line 1974  Line 2861 
2861    
2862  =back  =back
2863    
2864    The permissible options are as follows.
2865    
2866    =over 4
2867    
2868    =item truncate
2869    
2870    If TRUE, then the table will be erased before loading.
2871    
2872    =item mode
2873    
2874    Mode in which the load should operate, either C<low_priority> or C<concurrent>.
2875    This option is only applicable to a MySQL database.
2876    
2877    =item partial
2878    
2879    If TRUE, then it is assumed that this is a partial load, and the table will not
2880    be analyzed and compacted at the end.
2881    
2882    =back
2883    
2884  =cut  =cut
2885  sub LoadTable {  sub LoadTable {
2886      # Get the parameters.      # Get the parameters.
2887      my ($self, $fileName, $relationName, $truncateFlag) = @_;      my ($self, $fileName, $relationName, %options) = @_;
2888      # Create the statistical return object.      # Create the statistical return object.
2889      my $retVal = _GetLoadStats();      my $retVal = _GetLoadStats();
2890      # Trace the fact of the load.      # Trace the fact of the load.
# Line 1989  Line 2896 
2896      # Get the relation data.      # Get the relation data.
2897      my $relation = $self->_FindRelation($relationName);      my $relation = $self->_FindRelation($relationName);
2898      # Check the truncation flag.      # Check the truncation flag.
2899      if ($truncateFlag) {      if ($options{truncate}) {
2900          Trace("Creating table $relationName") if T(2);          Trace("Creating table $relationName") if T(2);
2901          # Compute the row count estimate. We take the size of the load file,          # Compute the row count estimate. We take the size of the load file,
2902          # divide it by the estimated row size, and then multiply by 1.5 to          # divide it by the estimated row size, and then multiply by 2 to
2903          # leave extra room. We postulate a minimum row count of 1000 to          # leave extra room. We postulate a minimum row count of 1000 to
2904          # prevent problems with incoming empty load files.          # prevent problems with incoming empty load files.
2905          my $rowSize = $self->EstimateRowSize($relationName);          my $rowSize = $self->EstimateRowSize($relationName);
2906          my $estimate = FIG::max($fileSize * 1.5 / $rowSize, 1000);          my $estimate = $fileSize * 8 / $rowSize;
2907            if ($estimate < 1000) {
2908                $estimate = 1000;
2909            }
2910          # Re-create the table without its index.          # Re-create the table without its index.
2911          $self->CreateTable($relationName, 0, $estimate);          $self->CreateTable($relationName, 0, $estimate);
2912          # If this is a pre-index DBMS, create the index here.          # If this is a pre-index DBMS, create the index here.
# Line 2012  Line 2922 
2922      # Load the table.      # Load the table.
2923      my $rv;      my $rv;
2924      eval {      eval {
2925          $rv = $dbh->load_table(file => $fileName, tbl => $relationName);          $rv = $dbh->load_table(file => $fileName, tbl => $relationName, style => $options{mode});
2926      };      };
2927      if (!defined $rv) {      if (!defined $rv) {
2928          $retVal->AddMessage($@) if ($@);          $retVal->AddMessage($@) if ($@);
2929          $retVal->AddMessage("Table load failed for $relationName using $fileName.");          $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2930          Trace("Table load failed for $relationName.") if T(1);          Trace("Table load failed for $relationName.") if T(1);
2931      } else {      } else {
2932          # Here we successfully loaded the table.          # Here we successfully loaded the table.
2933          $retVal->Add("tables");          $retVal->Add("tables");
2934          my $size = -s $fileName;          my $size = -s $fileName;
2935          Trace("$size bytes loaded into $relationName.") if T(2);          Trace("$size bytes loaded into $relationName.") if T(2);
2936            $retVal->Add("bytes", $size);
2937          # If we're rebuilding, we need to create the table indexes.          # If we're rebuilding, we need to create the table indexes.
2938          if ($truncateFlag) {          if ($options{truncate}) {
2939              # Indexes are created here for PostGres. For PostGres, indexes are              # Indexes are created here for PostGres. For PostGres, indexes are
2940              # best built at the end. For MySQL, the reverse is true.              # best built at the end. For MySQL, the reverse is true.
2941              if (! $dbh->{_preIndex}) {              if (! $dbh->{_preIndex}) {
# Line 2038  Line 2949 
2949              # 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.
2950              # 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
2951              # primary relations are allowed that privilege.              # primary relations are allowed that privilege.
2952                Trace("Checking for full-text index on $relationName.") if T(2);
2953              if ($self->_IsPrimary($relationName)) {              if ($self->_IsPrimary($relationName)) {
2954                  # 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');  
                 }  
2955              }              }
2956          }          }
2957      }      }
2958      # Analyze the table to improve performance.      # Analyze the table to improve performance.
2959        if (! $options{partial}) {
2960      Trace("Analyzing and compacting $relationName.") if T(3);      Trace("Analyzing and compacting $relationName.") if T(3);
2961      $dbh->vacuum_it($relationName);      $dbh->vacuum_it($relationName);
2962        }
2963      Trace("$relationName load completed.") if T(3);      Trace("$relationName load completed.") if T(3);
2964      # Return the statistics.      # Return the statistics.
2965      return $retVal;      return $retVal;
2966  }  }
2967    
2968  =head3 GenerateEntity  =head3 CreateSearchIndex
2969    
2970  C<< my $fieldHash = $erdb->GenerateEntity($id, $type, \%values); >>      $erdb->CreateSearchIndex($objectName);
2971    
2972  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
2973  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.  
2974    
2975  =over 4  =over 4
2976    
2977  =item id  =item objectName
2978    
2979  ID to assign to the new entity.  Name of the entity or relationship to be indexed.
2980    
2981  =item type  =back
2982    
2983  Type name for the new entity.  =cut
2984    
2985  =item values  sub CreateSearchIndex {
2986        # Get the parameters.
2987        my ($self, $objectName) = @_;
2988        # Get the relation's entity/relationship structure.
2989        my $structure = $self->_GetStructure($objectName);
2990        # Get the database handle.
2991        my $dbh = $self->{_dbh};
2992        Trace("Checking for search fields in $objectName.") if T(3);
2993        # Check for a searchable fields list.
2994        if (exists $structure->{searchFields}) {
2995            # Here we know that we need to create a full-text search index.
2996            # Get an SQL-formatted field name list.
2997            my $fields = join(", ", _FixNames(@{$structure->{searchFields}}));
2998            # Create the index. If it already exists, it will be dropped.
2999            $dbh->create_index(tbl => $objectName, idx => "search_idx",
3000                               flds => $fields, kind => 'fulltext');
3001            Trace("Index created for $fields in $objectName.") if T(2);
3002        }
3003    }
3004    
3005    =head3 DropRelation
3006    
3007        $erdb->DropRelation($relationName);
3008    
3009    Physically drop a relation from the database.
3010    
3011    =over 4
3012    
3013    =item relationName
3014    
3015  Hash containing additional values that might be needed by the data generation methods (optional).  Name of the relation to drop. If it does not exist, this method will have
3016    no effect.
3017    
3018  =back  =back
3019    
3020  =cut  =cut
3021    
3022  sub GenerateEntity {  sub DropRelation {
3023      # Get the parameters.      # Get the parameters.
3024      my ($self, $id, $type, $values) = @_;      my ($self, $relationName) = @_;
3025      # Create the return hash.      # Get the database handle.
3026      my $this = { id => $id };      my $dbh = $self->{_dbh};
3027      # Get the metadata structure.      # Drop the relation. The method used here has no effect if the relation
3028      my $metadata = $self->{_metaData};      # does not exist.
3029      # Get this entity's list of fields.      Trace("Invoking DB Kernel to drop $relationName.") if T(3);
3030      if (!exists $metadata->{Entities}->{$type}) {      $dbh->drop_table(tbl => $relationName);
3031          Confess("Unrecognized entity type $type in GenerateEntity.");  }
3032      } else {  
3033          my $entity = $metadata->{Entities}->{$type};  =head3 MatchSqlPattern
3034          my $fields = $entity->{Fields};  
3035          # Generate data from the fields.      my $matched = ERDB::MatchSqlPattern($value, $pattern);
3036          _GenerateFields($this, $fields, $type, $values);  
3037    Determine whether or not a specified value matches an SQL pattern. An SQL
3038    pattern has two wild card characters: C<%> that matches multiple characters,
3039    and C<_> that matches a single character. These can be escaped using a
3040    backslash (C<\>). We pull this off by converting the SQL pattern to a
3041    PERL regular expression. As per SQL rules, the match is case-insensitive.
3042    
3043    =over 4
3044    
3045    =item value
3046    
3047    Value to be matched against the pattern. Note that an undefined or empty
3048    value will not match anything.
3049    
3050    =item pattern
3051    
3052    SQL pattern against which to match the value. An undefined or empty pattern will
3053    match everything.
3054    
3055    =item RETURN
3056    
3057    Returns TRUE if the value and pattern match, else FALSE.
3058    
3059    =back
3060    
3061    =cut
3062    
3063    sub MatchSqlPattern {
3064        # Get the parameters.
3065        my ($value, $pattern) = @_;
3066        # Declare the return variable.
3067        my $retVal;
3068        # Insure we have a pattern.
3069        if (! defined($pattern) || $pattern eq "") {
3070            $retVal = 1;
3071        } else {
3072            # Break the pattern into pieces around the wildcard characters. Because we
3073            # use parentheses in the split function's delimiter expression, we'll get
3074            # list elements for the delimiters as well as the rest of the string.
3075            my @pieces = split /([_%]|\\[_%])/, $pattern;
3076            # Check some fast special cases.
3077            if ($pattern eq '%') {
3078                # A null pattern matches everything.
3079                $retVal = 1;
3080            } elsif (@pieces == 1) {
3081                # No wildcards, so we have a literal comparison. Note we're case-insensitive.
3082                $retVal = (lc($value) eq lc($pattern));
3083            } elsif (@pieces == 2 && $pieces[1] eq '%') {
3084                # A wildcard at the end, so we have a substring match. This is also case-insensitive.
3085                $retVal = (lc(substr($value, 0, length($pieces[0]))) eq lc($pieces[0]));
3086            } else {
3087                # Okay, we have to do it the hard way. Convert each piece to a PERL pattern.
3088                my $realPattern = "";
3089                for my $piece (@pieces) {
3090                    # Determine the type of piece.
3091                    if ($piece eq "") {
3092                        # Empty pieces are ignored.
3093                    } elsif ($piece eq "%") {
3094                        # Here we have a multi-character wildcard. Note that it can match
3095                        # zero or more characters.
3096                        $realPattern .= ".*"
3097                    } elsif ($piece eq "_") {
3098                        # Here we have a single-character wildcard.
3099                        $realPattern .= ".";
3100                    } elsif ($piece eq "\\%" || $piece eq "\\_") {
3101                        # This is an escape sequence (which is a rare thing, actually).
3102                        $realPattern .= substr($piece, 1, 1);
3103                    } else {
3104                        # Here we have raw text.
3105                        $realPattern .= quotemeta($piece);
3106      }      }
3107      # Return the hash created.              }
3108      return $this;              # Do the match.
3109                $retVal = ($value =~ /^$realPattern$/i ? 1 : 0);
3110            }
3111        }
3112        # Return the result.
3113        return $retVal;
3114  }  }
3115    
3116  =head3 GetEntity  =head3 GetEntity
3117    
3118  C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>      my $entityObject = $erdb->GetEntity($entityType, $ID);
3119    
3120  Return an object describing the entity instance with a specified ID.  Return an object describing the entity instance with a specified ID.
3121    
# Line 2137  Line 3131 
3131    
3132  =item RETURN  =item RETURN
3133    
3134  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
3135  instance is found with the specified key.  instance is found with the specified key.
3136    
3137  =back  =back
# Line 2157  Line 3151 
3151    
3152  =head3 GetChoices  =head3 GetChoices
3153    
3154  C<< my @values = $erdb->GetChoices($entityName, $fieldName); >>      my @values = $erdb->GetChoices($entityName, $fieldName);
3155    
3156  Return a list of all the values for the specified field that are represented in the  Return a list of all the values for the specified field that are represented in the
3157  specified entity.  specified entity.
# Line 2212  Line 3206 
3206    
3207  =head3 GetEntityValues  =head3 GetEntityValues
3208    
3209  C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>      my @values = $erdb->GetEntityValues($entityType, $ID, \@fields);
3210    
3211  Return a list of values from a specified entity instance. If the entity instance  Return a list of values from a specified entity instance. If the entity instance
3212  does not exist, an empty list is returned.  does not exist, an empty list is returned.
# Line 2256  Line 3250 
3250    
3251  =head3 GetAll  =head3 GetAll
3252    
3253  C<< my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>      my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count);
3254    
3255  Return a list of values taken from the objects returned by a query. The first three  Return a list of values taken from the objects returned by a query. The first three
3256  parameters correspond to the parameters of the L</Get> method. The final parameter is  parameters correspond to the parameters of the L</Get> method. The final parameter is
# Line 2270  Line 3264 
3264  fields specified returns multiple values, they are flattened in with the rest. For  fields specified returns multiple values, they are flattened in with the rest. For
3265  example, the following call will return a list of the features in a particular  example, the following call will return a list of the features in a particular
3266  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
3267  feature ID followed by all of its aliases.  feature ID followed by all of its essentiality determinations.
3268    
3269  C<< $query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>      @query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(essential)']);
3270    
3271  =over 4  =over 4
3272    
# Line 2350  Line 3344 
3344    
3345  =head3 Exists  =head3 Exists
3346    
3347  C<< my $found = $sprout->Exists($entityName, $entityID); >>      my $found = $sprout->Exists($entityName, $entityID);
3348    
3349  Return TRUE if an entity exists, else FALSE.  Return TRUE if an entity exists, else FALSE.
3350    
# Line 2385  Line 3379 
3379    
3380  =head3 EstimateRowSize  =head3 EstimateRowSize
3381    
3382  C<< my $rowSize = $erdb->EstimateRowSize($relName); >>      my $rowSize = $erdb->EstimateRowSize($relName);
3383    
3384  Estimate the row size of the specified relation. The estimated row size is computed by adding  Estimate the row size of the specified relation. The estimated row size is computed by adding
3385  up the average length for each data type.  up the average length for each data type.
# Line 2423  Line 3417 
3417    
3418  =head3 GetFieldTable  =head3 GetFieldTable
3419    
3420  C<< my $fieldHash = $self->GetFieldTable($objectnName); >>      my $fieldHash = $self->GetFieldTable($objectnName);
3421    
3422  Get the field structure for a specified entity or relationship.  Get the field structure for a specified entity or relationship.
3423    
# Line 2450  Line 3444 
3444      return $objectData->{Fields};      return $objectData->{Fields};
3445  }  }
3446    
3447  =head2 Data Mining Methods  =head3 SplitKeywords
3448    
3449  =head3 GetUsefulCrossValues      my @keywords = ERDB::SplitKeywords($keywordString);
3450    
3451  C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>  This method returns a list of the positive keywords in the specified
3452    keyword string. All of the operators will have been stripped off,
3453    and if the keyword is preceded by a minus operator (C<->), it will
3454    not be in the list returned. The idea here is to get a list of the
3455    keywords the user wants to see. The list will be processed to remove
3456    duplicates.
3457    
3458  Return a list of the useful attributes that would be returned by a B<Cross> call  It is possible to create a string that confuses this method. For example
 from an entity of the source entity type through the specified relationship. This  
 means it will return the fields of the target entity type and the intersection data  
 fields in the relationship. Only primary table fields are returned. In other words,  
 the field names returned will be for fields where there is always one and only one  
 value.  
3459    
3460  =over 4      frog toad -frog
3461    
3462  =item sourceEntity  would return both C<frog> and C<toad>. If this is a problem we can deal
3463    with it later.
3464    
3465  Name of the entity from which the relationship crossing will start.  =over 4
3466    
3467  =item relationship  =item keywordString
3468    
3469  Name of the relationship being crossed.  The keyword string to be parsed.
3470    
3471  =item RETURN  =item RETURN
3472    
3473  Returns a list of field names in Sprout field format (I<objectName>C<(>I<fieldName>C<)>.  Returns a list of the words in the keyword string the user wants to
3474    see.
3475    
3476  =back  =back
3477    
3478  =cut  =cut
3479  #: Return Type @;  
3480  sub GetUsefulCrossValues {  sub SplitKeywords {
3481      # Get the parameters.      # Get the parameters.
3482      my ($self, $sourceEntity, $relationship) = @_;      my ($keywordString) = @_;
3483      # Declare the return variable.      # Make a safety copy of the string. (This helps during debugging.)
3484      my @retVal = ();      my $workString = $keywordString;
3485      # Determine the target entity for the relationship. This is whichever entity is not      # Convert operators we don't care about to spaces.
3486      # the source entity. So, if the source entity is the FROM, we'll get the name of      $workString =~ tr/+"()<>/ /;
3487      # the TO, and vice versa.      # Split the rest of the string along space boundaries. Note that we
3488      my $relStructure = $self->_GetStructure($relationship);      # eliminate any words that are zero length or begin with a minus sign.
3489      my $targetEntityType = ($relStructure->{from} eq $sourceEntity ? "to" : "from");      my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
3490      my $targetEntity = $relStructure->{$targetEntityType};      # Use a hash to remove duplicates.
3491      # Get the field table for the entity.      my %words = map { $_ => 1 } @wordList;
     my $entityFields = $self->GetFieldTable($targetEntity);  
     # The field table is a hash. The hash key is the field name. The hash value is a structure.  
     # For the entity fields, the key aspect of the target structure is that the {relation} value  
     # must match the entity name.  
     my @fieldList = map { "$targetEntity($_)" } grep { $entityFields->{$_}->{relation} eq $targetEntity }  
                         keys %{$entityFields};  
     # Push the fields found onto the return variable.  
     push @retVal, sort @fieldList;  
     # Get the field table for the relationship.  
     my $relationshipFields = $self->GetFieldTable($relationship);  
     # Here we have a different rule. We want all the fields other than "from-link" and "to-link".  
     # This may end up being an empty set.  
     my @fieldList2 = map { "$relationship($_)" } grep { $_ ne "from-link" && $_ ne "to-link" }  
                         keys %{$relationshipFields};  
     # Push these onto the return list.  
     push @retVal, sort @fieldList2;  
3492      # Return the result.      # Return the result.
3493      return @retVal;      return sort keys %words;
3494  }  }
3495    
3496  =head3 FindColumn  =head3 ValidateFieldName
3497    
3498  C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>      my $okFlag = ERDB::ValidateFieldName($fieldName);
3499    
3500  Return the location a desired column in a data mining header line. The data  Return TRUE if the specified field name is valid, else FALSE. Valid field names must
3501  mining header line is a tab-separated list of column names. The column  be hyphenated words subject to certain restrictions.
 identifier is either the numerical index of a column or the actual column  
 name.  
3502    
3503  =over 4  =over 4
3504    
3505  =item headerLine  =item fieldName
3506    
3507    Field name to be validated.
3508    
3509    =item RETURN
3510    
3511    Returns TRUE if the field name is valid, else FALSE.
3512    
3513    =back
3514    
3515    =cut
3516    
3517    sub ValidateFieldName {
3518        # Get the parameters.
3519        my ($fieldName) = @_;
3520        # Declare the return variable. The field name is valid until we hear
3521        # differently.
3522        my $retVal = 1;
3523        # Compute the maximum name length.
3524        my $maxLen = $TypeTable{'name-string'}->{maxLen};
3525        # Look for bad stuff in the name.
3526        if ($fieldName =~ /--/) {
3527            # Here we have a doubled minus sign.
3528            Trace("Field name $fieldName has a doubled hyphen.") if T(1);
3529            $retVal = 0;
3530        } elsif ($fieldName !~ /^[A-Za-z]/) {
3531            # Here the field name is missing the initial letter.
3532            Trace("Field name $fieldName does not begin with a letter.") if T(1);
3533            $retVal = 0;
3534        } elsif (length($fieldName) > $maxLen) {
3535            # Here the field name is too long.
3536            Trace("Maximum field name length is $maxLen. Field name must be truncated to " . substr($fieldName,0, $maxLen) . ".");
3537        } else {
3538            # Strip out the minus signs. Everything remaining must be a letter,
3539            # underscore, or digit.
3540            my $strippedName = $fieldName;
3541            $strippedName =~ s/-//g;
3542            if ($strippedName !~ /^(\w|\d)+$/) {
3543                Trace("Field name $fieldName contains illegal characters.") if T(1);
3544                $retVal = 0;
3545            }
3546        }
3547        # Return the result.
3548        return $retVal;
3549    }
3550    
3551    =head3 ReadMetaXML
3552    
3553        my $rawMetaData = ERDB::ReadDBD($fileName);
3554    
3555    This method reads a raw database definition XML file and returns it.
3556    Normally, the metadata used by the ERDB system has been processed and
3557    modified to make it easier to load and retrieve the data; however,
3558    this method can be used to get the data in its raw form.
3559    
3560    =over 4
3561    
3562    =item fileName
3563    
3564    Name of the XML file to read.
3565    
3566    =item RETURN
3567    
3568    Returns a hash reference containing the raw XML data from the specified file.
3569    
3570    =back
3571    
3572    =cut
3573    
3574    sub ReadMetaXML {
3575        # Get the parameters.
3576        my ($fileName) = @_;
3577        # Read the XML.
3578        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
3579        Trace("XML metadata loaded from file $fileName.") if T(1);
3580        # Return the result.
3581        return $retVal;
3582    }
3583    
3584    =head3 GetEntityFieldHash
3585    
3586        my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName);
3587    
3588    Get the field hash of the named entity in the specified raw XML structure.
3589    The field hash may not exist, in which case we need to create it.
3590    
3591    =over 4
3592    
3593    =item structure
3594    
3595    Raw XML structure defininng the database. This is not the run-time XML used by
3596    an ERDB object, since that has all sorts of optimizations built-in.
3597    
3598    =item entityName
3599    
3600    Name of the entity whose field structure is desired.
3601    
3602    =item RETURN
3603    
3604    Returns the field hash used to define the entity's fields.
3605    
3606    =back
3607    
3608    =cut
3609    
3610    sub GetEntityFieldHash {
3611        # Get the parameters.
3612        my ($structure, $entityName) = @_;
3613        # Get the entity structure.
3614        my $entityData = $structure->{Entities}->{$entityName};
3615        # Look for a field structure.
3616        my $retVal = $entityData->{Fields};
3617        # If it doesn't exist, create it.
3618        if (! defined($retVal)) {
3619            $entityData->{Fields} = {};
3620            $retVal = $entityData->{Fields};
3621        }
3622        # Return the result.
3623        return $retVal;
3624    }
3625    
3626    =head3 WriteMetaXML
3627    
3628        ERDB::WriteMetaXML($structure, $fileName);
3629    
3630    Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
3631    used to update the database definition. It must be used with care, however, since it
3632    will only work on a raw structure, not on the processed structure created by an ERDB
3633    constructor.
3634    
3635    =over 4
3636    
3637    =item structure
3638    
3639    XML structure to be written to the file.
3640    
3641    =item fileName
3642    
3643    Name of the output file to which the updated XML should be stored.
3644    
3645    =back
3646    
3647    =cut
3648    
3649    sub WriteMetaXML {
3650        # Get the parameters.
3651        my ($structure, $fileName) = @_;
3652        # Compute the output.
3653        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
3654        # Write it to the file.
3655        my $xmlOut = Open(undef, ">$fileName");
3656        print $xmlOut $fileString;
3657    }
3658    
3659    
3660    =head3 HTMLNote
3661    
3662    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
3663    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
3664    Except for C<[p]>, all the codes are closed by slash-codes. So, for
3665    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
3666    
3667        my $realHtml = ERDB::HTMLNote($dataString);
3668    
3669    =over 4
3670    
3671    =item dataString
3672    
3673    String to convert to HTML.
3674    
3675    =item RETURN
3676    
3677    An HTML string derived from the input string.
3678    
3679    =back
3680    
3681    =cut
3682    
3683    sub HTMLNote {
3684        # Get the parameter.
3685        my ($dataString) = @_;
3686        # HTML-escape the text.
3687        my $retVal = CGI::escapeHTML($dataString);
3688        # Substitute the bulletin board codes.
3689        $retVal =~ s!\[(/?[bi])\]!<$1>!g;
3690        $retVal =~ s!\[p\]!</p><p>!g;
3691        $retVal =~ s!\[link\s+([^\]]+)\]!<a href="$1">!g;
3692        $retVal =~ s!\[/link\]!</a>!g;
3693        # Return the result.
3694        return $retVal;
3695    }
3696    
3697    =head3 WikiNote
3698    
3699    Convert a note or comment to Wiki text by replacing some bulletin-board codes with HTML. The codes
3700    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
3701    Except for C<[p]>, all the codes are closed by slash-codes. So, for
3702    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
3703    
3704        my $wikiText = ERDB::WikiNote($dataString);
3705    
3706    =over 4
3707    
3708    =item dataString
3709    
3710    String to convert to Wiki text.
3711    
3712    =item RETURN
3713    
3714    An Wiki text string derived from the input string.
3715    
3716    =back
3717    
3718    =cut
3719    
3720    sub WikiNote {
3721        # Get the parameter.
3722        my ($dataString) = @_;
3723        # HTML-escape the text.
3724        my $retVal = CGI::escapeHTML($dataString);
3725        # Substitute the bulletin board codes.
3726        my $italic = WikiTools::ItalicCode();
3727        $retVal =~ s/\[\/?i\]/$italic/g;
3728        my $bold = WikiTools::BoldCode();
3729        $retVal =~ s/\[\/?b\]/$bold/g;
3730        # Paragraph breaks are the same no matter which Wiki you're using.
3731        $retVal =~ s!\[p\]!\n\n!g;
3732        # Now we do the links, which are complicated by the need to know two
3733        # things: the target URL and the text.
3734        while ($retVal =~ /\[link\s+([^\]]+)\]([^\[]+)\[\/link\]/g) {
3735            # Replace the matched string with the Wiki markup for links. Note that
3736            # $-[0] is the starting position of the match for the entire expression,
3737            # and $+[0] is past the ending position.
3738            substr $retVal, $-[0], $+[0] - $-[0], WikiTools::LinkMarkup($1, $2);
3739        }
3740        # Return the result.
3741        return $retVal;
3742    }
3743    
3744    =head3 BeginTran
3745    
3746        $erdb->BeginTran();
3747    
3748    Start a database transaction.
3749    
3750    =cut
3751    
3752    sub BeginTran {
3753        my ($self) = @_;
3754        $self->{_dbh}->begin_tran();
3755    
3756    }
3757    
3758    =head3 CommitTran
3759    
3760        $erdb->CommitTran();
3761    
3762    Commit an active database transaction.
3763    
3764    =cut
3765    
3766    sub CommitTran {
3767        my ($self) = @_;
3768        $self->{_dbh}->commit_tran();
3769    }
3770    
3771    =head3 RollbackTran
3772    
3773        $erdb->RollbackTran();
3774    
3775    Roll back an active database transaction.
3776    
3777    =cut
3778    
3779    sub RollbackTran {
3780        my ($self) = @_;
3781        $self->{_dbh}->roll_tran();
3782    }
3783    
3784    =head3 UpdateField
3785    
3786        my $count = $erdb->UpdateField($objectNames, $fieldName, $oldValue, $newValue, $filter, $parms);
3787    
3788    Update all occurrences of a specific field value to a new value. The number of rows changed will be
3789    returned.
3790    
3791    =over 4
3792    
3793    =item fieldName
3794    
3795    Name of the field in standard I<objectName>C<(>I<fieldName>C<)> format.
3796    
3797    =item oldValue
3798    
3799    Value to be modified. All occurrences of this value in the named field will be replaced by the
3800    new value.
3801    
3802    =item newValue
3803    
3804    New value to be substituted for the old value when it's found.
3805    
3806    =item filter
3807    
3808    A standard ERDB filter clause (see L</Get>). The filter will be applied before any substitutions take place.
3809    
3810    =item parms
3811    
3812    Reference to a list of parameter values in the filter.
3813    
3814    =item RETURN
3815    
3816    Returns the number of rows modified.
3817    
3818    =back
3819    
3820    =cut
3821    
3822    sub UpdateField {
3823        # Get the parameters.
3824        my ($self, $fieldName, $oldValue, $newValue, $filter, $parms) = @_;
3825        # Get the object and field names from the field name parameter.
3826        $fieldName =~ /^([^(]+)\(([^)]+)\)/;
3827        my $objectName = $1;
3828        my $realFieldName = _FixName($2);
3829        # Add the old value to the filter. Note we allow the possibility that no
3830        # filter was specified.
3831        my $realFilter = "$fieldName = ?";
3832        if ($filter) {
3833            $realFilter .= " AND $filter";
3834        }
3835        # Format the query filter.
3836        my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
3837            $self->_SetupSQL([$objectName], $realFilter);
3838        # Create the query. Since there is only one object name, the mapped-name data is not
3839        # necessary. Neither is the FROM clause.
3840        $suffix =~ s/^FROM.+WHERE\s+//;
3841        # Create the update statement.
3842        my $command = "UPDATE $objectName SET $realFieldName = ? WHERE $suffix";
3843        # Get the database handle.
3844        my $dbh = $self->{_dbh};
3845        # Add the old and new values to the parameter list. Note we allow the possibility that
3846        # there are no user-supplied parameters.
3847        my @params = ($newValue, $oldValue);
3848        if (defined $parms) {
3849            push @params, @{$parms};
3850        }
3851        # Execute the update.
3852        my $retVal = $dbh->SQL($command, 0, @params);
3853        # Make the funky zero a real zero.
3854        if ($retVal == 0) {
3855            $retVal = 0;
3856        }
3857        # Return the result.
3858        return $retVal;
3859    }
3860    
3861    
3862    =head2 Data Mining Methods
3863    
3864    =head3 GetUsefulCrossValues
3865    
3866        my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship);
3867    
3868    Return a list of the useful attributes that would be returned by a B<Cross> call
3869    from an entity of the source entity type through the specified relationship. This
3870    means it will return the fields of the target entity type and the intersection data
3871    fields in the relationship. Only primary table fields are returned. In other words,
3872    the field names returned will be for fields where there is always one and only one
3873    value.
3874    
3875    =over 4
3876    
3877    =item sourceEntity
3878    
3879    Name of the entity from which the relationship crossing will start.
3880    
3881    =item relationship
3882    
3883    Name of the relationship being crossed.
3884    
3885    =item RETURN
3886    
3887    Returns a list of field names in Sprout field format (I<objectName>C<(>I<fieldName>C<)>.
3888    
3889    =back
3890    
3891    =cut
3892    #: Return Type @;
3893    sub GetUsefulCrossValues {
3894        # Get the parameters.
3895        my ($self, $sourceEntity, $relationship) = @_;
3896        # Declare the return variable.
3897        my @retVal = ();
3898        # Determine the target entity for the relationship. This is whichever entity is not
3899        # the source entity. So, if the source entity is the FROM, we'll get the name of
3900        # the TO, and vice versa.
3901        my $relStructure = $self->_GetStructure($relationship);
3902        my $targetEntityType = ($relStructure->{from} eq $sourceEntity ? "to" : "from");
3903        my $targetEntity = $relStructure->{$targetEntityType};
3904        # Get the field table for the entity.
3905        my $entityFields = $self->GetFieldTable($targetEntity);
3906        # The field table is a hash. The hash key is the field name. The hash value is a structure.
3907        # For the entity fields, the key aspect of the target structure is that the {relation} value
3908        # must match the entity name.
3909        my @fieldList = map { "$targetEntity($_)" } grep { $entityFields->{$_}->{relation} eq $targetEntity }
3910                            keys %{$entityFields};
3911        # Push the fields found onto the return variable.
3912        push @retVal, sort @fieldList;
3913        # Get the field table for the relationship.
3914        my $relationshipFields = $self->GetFieldTable($relationship);
3915        # Here we have a different rule. We want all the fields other than "from-link" and "to-link".
3916        # This may end up being an empty set.
3917        my @fieldList2 = map { "$relationship($_)" } grep { $_ ne "from-link" && $_ ne "to-link" }
3918                            keys %{$relationshipFields};
3919        # Push these onto the return list.
3920        push @retVal, sort @fieldList2;
3921        # Return the result.
3922        return @retVal;
3923    }
3924    
3925    =head3 FindColumn
3926    
3927        my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier);
3928    
3929    Return the location a desired column in a data mining header line. The data
3930    mining header line is a tab-separated list of column names. The column
3931    identifier is either the numerical index of a column or the actual column
3932    name.
3933    
3934    =over 4
3935    
3936    =item headerLine
3937    
3938  The header line from a data mining command, which consists of a tab-separated  The header line from a data mining command, which consists of a tab-separated
3939  list of column names.  list of column names.
# Line 2573  Line 3982 
3982    
3983  =head3 ParseColumns  =head3 ParseColumns
3984    
3985  C<< my @columns = ERDB::ParseColumns($line); >>      my @columns = ERDB::ParseColumns($line);
3986    
3987  Convert the specified data line to a list of columns.  Convert the specified data line to a list of columns.
3988    
# Line 2603  Line 4012 
4012      return @retVal;      return @retVal;
4013  }  }
4014    
4015    =head2 Virtual Methods
4016    
4017    =head3 _CreatePPOIndex
4018    
4019        my $index = ERDB::_CreatePPOIndex($indexObject);
4020    
4021    Convert the XML for an ERDB index to the XML structure for a PPO
4022    index.
4023    
4024    =over 4
4025    
4026    =item indexObject
4027    
4028    ERDB XML structure for an index.
4029    
4030    =item RETURN
4031    
4032    PPO XML structure for the same index.
4033    
4034    =back
4035    
4036    =cut
4037    
4038    sub _CreatePPOIndex {
4039        # Get the parameters.
4040        my ($indexObject) = @_;
4041        # The incoming index contains a list of the index fields in the IndexFields
4042        # member. We loop through it to create the index tags.
4043        my @fields = map { { label => _FixName($_->{name}) } } @{$indexObject->{IndexFields}};
4044        # Wrap the fields in attribute tags.
4045        my $retVal = { attribute => \@fields };
4046        # Return the result.
4047        return $retVal;
4048    }
4049    
4050    =head3 _CreatePPOField
4051    
4052        my $fieldXML = ERDB::_CreatePPOField($fieldName, $fieldObject);
4053    
4054    Convert the ERDB XML structure for a field to a PPO scalar XML structure.
4055    
4056    =over 4
4057    
4058    =item fieldName
4059    
4060    Name of the scalar field.
4061    
4062    =item fieldObject
4063    
4064    ERDB XML structure describing the field.
4065    
4066    =item RETURN
4067    
4068    Returns a PPO XML structure for the same field.
4069    
4070    =back
4071    
4072    =cut
4073    
4074    sub _CreatePPOField {
4075        # Get the parameters.
4076        my ($fieldName, $fieldObject) = @_;
4077        # Get the field type.
4078        my $type = $TypeTable{$fieldObject->{type}}->{sqlType};
4079        # Fix up the field name.
4080        $fieldName = _FixName($fieldName);
4081        # Build the scalar tag.
4082        my $retVal = { label => $fieldName, type => $type };
4083        # Return the result.
4084        return $retVal;
4085    }
4086    
4087    =head3 CleanKeywords
4088    
4089        my $cleanedString = $erdb->CleanKeywords($searchExpression);
4090    
4091    Clean up a search expression or keyword list. This is a virtual method that may
4092    be overridden by the subclass. The base-class method removes extra spaces
4093    and converts everything to lower case.
4094    
4095    =over 4
4096    
4097    =item searchExpression
4098    
4099    Search expression or keyword list to clean. Note that a search expression may
4100    contain boolean operators which need to be preserved. This includes leading
4101    minus signs.
4102    
4103    =item RETURN
4104    
4105    Cleaned expression or keyword list.
4106    
4107    =back
4108    
4109    =cut
4110    
4111    sub CleanKeywords {
4112        # Get the parameters.
4113        my ($self, $searchExpression) = @_;
4114        # Lower-case the expression and copy it into the return variable. Note that we insure we
4115        # don't accidentally end up with an undefined value.
4116        my $retVal = lc($searchExpression || "");
4117        # Remove extra spaces.
4118        $retVal =~ s/\s+/ /g;
4119        $retVal =~ s/(^\s+)|(\s+$)//g;
4120        # Return the result.
4121        return $retVal;
4122    }
4123    
4124    =head3 GetSourceObject
4125    
4126        my $source = $erdb->GetSourceObject($entityName);
4127    
4128    Return the object to be used in loading special attributes of the specified entity. The
4129    algorithm for loading special attributes is stored in the C<DataGen> elements of the
4130    XML
4131    
4132  =head2 Internal Utility Methods  =head2 Internal Utility Methods
4133    
4134  =head3 _RelationMap  =head3 _RelationMap
4135    
4136  C<< my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef); >>      my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
4137    
4138  Create the relation map for an SQL query. The relation map is used by B<DBObject>  Create the relation map for an SQL query. The relation map is used by B<ERDBObject>
4139  to determine how to interpret the results of the query.  to determine how to interpret the results of the query.
4140    
4141  =over 4  =over 4
# Line 2626  Line 4152 
4152  =item RETURN  =item RETURN
4153    
4154  Returns a list of 2-tuples. Each tuple consists of an object name as used in the  Returns a list of 2-tuples. Each tuple consists of an object name as used in the
4155  query followed by the actual name of that object. This enables the B<DBObject> to  query followed by the actual name of that object. This enables the B<ERDBObject> to
4156  determine the order of the tables in the query and which object name belongs to each  determine the order of the tables in the query and which object name belongs to each
4157  mapped object name. Most of the time these two values are the same; however, if a  mapped object name. Most of the time these two values are the same; however, if a
4158  relation occurs twice in the query, the relation name in the field list and WHERE  relation occurs twice in the query, the relation name in the field list and WHERE
# Line 2920  Line 4446 
4446  sub _GetStatementHandle {  sub _GetStatementHandle {
4447      # Get the parameters.      # Get the parameters.
4448      my ($self, $command, $params) = @_;      my ($self, $command, $params) = @_;
4449        Confess("Invalid parameter list.") if (! defined($params) || ref($params) ne 'ARRAY');
4450      # Trace the query.      # Trace the query.
4451      Trace("SQL query: $command") if T(SQL => 3);      Trace("SQL query: $command") if T(SQL => 3);
4452      Trace("PARMS: '" . (join "', '", @{$params}) . "'") if (T(SQL => 4) && (@{$params} > 0));      Trace("PARMS: '" . (join "', '", @{$params}) . "'") if (T(SQL => 4) && (@{$params} > 0));
# Line 2928  Line 4455 
4455      # Prepare the command.      # Prepare the command.
4456      my $sth = $dbh->prepare_command($command);      my $sth = $dbh->prepare_command($command);
4457      # Execute it with the parameters bound in.      # Execute it with the parameters bound in.
4458      $sth->execute(@{$params}) || Confess("SELECT error" . $sth->errstr());      $sth->execute(@{$params}) || Confess("SELECT error:  " . $sth->errstr());
4459      # Return the statement handle.      # Return the statement handle.
4460      return $sth;      return $sth;
4461  }  }
# Line 2945  Line 4472 
4472      return Stats->new();      return Stats->new();
4473  }  }
4474    
 =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;  
             }  
         }  
     }  
 }  
   
4475  =head3 _DumpRelation  =head3 _DumpRelation
4476    
4477  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.
4478    
4479  This is an instance method.  This is an instance method.
4480    
# Line 3166  Line 4619 
4619          for my $object (values %{$metadata->{$section}}) {          for my $object (values %{$metadata->{$section}}) {
4620              # Loop through the object's fields.              # Loop through the object's fields.
4621              for my $fieldName (keys %{$object->{Fields}}) {              for my $fieldName (keys %{$object->{Fields}}) {
4622                  # Now we make some initial validations.                  # If this field name is invalid, set the return value to zero
4623                  if ($fieldName =~ /--/) {                  # so we know we encountered an error.
4624                      # Here we have a doubled minus sign.                  if (! ValidateFieldName($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";  
4625                      $retVal = 0;                      $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";  
                         $retVal = 0;  
                     }  
4626                  }                  }
4627              }              }
4628          }          }
# Line 3245  Line 4684 
4684      # be a null string.      # be a null string.
4685      if ($fileName ne "") {      if ($fileName ne "") {
4686          # Load the relation from the file.          # Load the relation from the file.
4687          $retVal = $self->LoadTable($fileName, $relationName, $rebuild);          $retVal = $self->LoadTable($fileName, $relationName, truncate => $rebuild);
4688      } elsif ($rebuild) {      } elsif ($rebuild) {
4689          # Here we are rebuilding, but no file exists, so we just re-create the table.          # Here we are rebuilding, but no file exists, so we just re-create the table.
4690          $self->CreateTable($relationName, 1);          $self->CreateTable($relationName, 1);
# Line 3254  Line 4693 
4693      return $retVal;      return $retVal;
4694  }  }
4695    
4696    
4697  =head3 _LoadMetaData  =head3 _LoadMetaData
4698    
4699        my $metadata = ERDB::_LoadMetaData($filename);
4700    
4701  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.
4702  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
4703  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 4721 
4721  sub _LoadMetaData {  sub _LoadMetaData {
4722      # Get the parameters.      # Get the parameters.
4723      my ($filename) = @_;      my ($filename) = @_;
4724      Trace("Reading Sprout DBD from $filename.") if T(2);      Trace("Reading DBD from $filename.") if T(2);
4725      # 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
4726      # get the exact structure we want.      # get the exact structure we want.
4727      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 $filename.") if T(1);  
4728      # Before we go any farther, we need to validate the field and object names. If an error is found,      # Before we go any farther, we need to validate the field and object names. If an error is found,
4729      # the method below will fail.      # the method below will fail.
4730      _ValidateFieldNames($metadata);      _ValidateFieldNames($metadata);
# Line 3418  Line 4847 
4847              if ($found == 0) {              if ($found == 0) {
4848                  push @{$indexList}, { IndexFields => [ {name => 'id', order => 'ascending'} ] };                  push @{$indexList}, { IndexFields => [ {name => 'id', order => 'ascending'} ] };
4849              }              }
4850              # Now we need to convert the relation's index list to an index table. We begin by creating              # Attach all the indexes to the relation.
4851              # an empty table in the relation structure.              _ProcessIndexes($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++;  
             }  
4852          }          }
4853          # Finally, we add the relation structure to the entity.          # Finally, we add the relation structure to the entity.
4854          $entityStructure->{Relations} = $relationTable;          $entityStructure->{Relations} = $relationTable;
# Line 3442  Line 4862 
4862          _FixupFields($relationshipStructure, $relationshipName, 2, 3);          _FixupFields($relationshipStructure, $relationshipName, 2, 3);
4863          # Format a description for the FROM field.          # Format a description for the FROM field.
4864          my $fromEntity = $relationshipStructure->{from};          my $fromEntity = $relationshipStructure->{from};
4865          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].";
4866          # Get the FROM entity's key type.          # Get the FROM entity's key type.
4867          my $fromType = $entityList->{$fromEntity}->{keyType};          my $fromType = $entityList->{$fromEntity}->{keyType};
4868          # Add the FROM field.          # Add the FROM field.
# Line 3452  Line 4872 
4872                                                      PrettySort => 1});                                                      PrettySort => 1});
4873          # Format a description for the TO field.          # Format a description for the TO field.
4874          my $toEntity = $relationshipStructure->{to};          my $toEntity = $relationshipStructure->{to};
4875          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].";
4876          # Get the TO entity's key type.          # Get the TO entity's key type.
4877          my $toType = $entityList->{$toEntity}->{keyType};          my $toType = $entityList->{$toEntity}->{keyType};
4878          # Add the TO field.          # Add the TO field.
# Line 3464  Line 4884 
4884          my $thisRelation = { Fields => _ReOrderRelationTable($relationshipStructure->{Fields}),          my $thisRelation = { Fields => _ReOrderRelationTable($relationshipStructure->{Fields}),
4885                               Indexes => { } };                               Indexes => { } };
4886          $relationshipStructure->{Relations} = { $relationshipName => $thisRelation };          $relationshipStructure->{Relations} = { $relationshipName => $thisRelation };
4887    
4888            # Add the alternate indexes (if any). This MUST be done before the FROM and
4889            # TO indexes, because it erases the relation's index list.
4890            if (exists $relationshipStructure->{Indexes}) {
4891                _ProcessIndexes($relationshipStructure->{Indexes}, $thisRelation);
4892            }
4893            # Add the relation to the master table.
4894          # Create the FROM and TO indexes.          # Create the FROM and TO indexes.
4895          _CreateRelationshipIndex("From", $relationshipName, $relationshipStructure);          _CreateRelationshipIndex("From", $relationshipName, $relationshipStructure);
4896          _CreateRelationshipIndex("To", $relationshipName, $relationshipStructure);          _CreateRelationshipIndex("To", $relationshipName, $relationshipStructure);
         # Add the relation to the master table.  
4897          $masterRelationTable{$relationshipName} = $thisRelation;          $masterRelationTable{$relationshipName} = $thisRelation;
4898      }      }
4899      # Now store the master relation table in the metadata structure.      # Now store the master relation table in the metadata structure.
# Line 3622  Line 5048 
5048      if ($relationshipStructure->{arity} eq "1M" && $indexKey eq "To") {      if ($relationshipStructure->{arity} eq "1M" && $indexKey eq "To") {
5049          $newIndex->{Unique} = 'true';          $newIndex->{Unique} = 'true';
5050      }      }
5051      # Add the index to the relation.      # Add the index to the relation.
5052      _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);      _AddIndex("idx$indexKey", $relationStructure, $newIndex);
5053    }
5054    
5055    =head3 _ProcessIndexes
5056    
5057        ERDB::_ProcessIndexes($indexList, $relation);
5058    
5059    Build the data structures for the specified indexes in the specified relation.
5060    
5061    =over 4
5062    
5063    =item indexList
5064    
5065    Reference to a list of indexes. Each index is a hash reference containing an optional
5066    C<Notes> value that describes the index and an C<IndexFields> value that is a reference
5067    to a list of index field structures. An index field structure, in turn, is a reference
5068    to a hash that contains a C<name> attribute for the field name and an C<order>
5069    attribute that specifies either C<ascending> or C<descending>. In this sense the
5070    index list encapsulates the XML C<Indexes> structure in the database definition.
5071    
5072    =item relation
5073    
5074    The structure that describes the current relation. The new index descriptors will
5075    be stored in the structure's C<Indexes> member. Any previous data in the structure
5076    will be lost.
5077    
5078    =back
5079    
5080    =cut
5081    
5082    sub _ProcessIndexes {
5083        # Get the parameters.
5084        my ($indexList, $relation) = @_;
5085        # Now we need to convert the relation's index list to an index table. We begin by creating
5086        # an empty table in the relation structure.
5087        $relation->{Indexes} = { };
5088        # Loop through the indexes.
5089        my $count = 0;
5090        for my $index (@{$indexList}) {
5091            # Add this index to the index table.
5092            _AddIndex("idx$count", $relation, $index);
5093            # Increment the counter so that the next index has a different name.
5094            $count++;
5095        }
5096  }  }
5097    
5098  =head3 _AddIndex  =head3 _AddIndex
# Line 3722  Line 5191 
5191              my $type = $fieldData->{type};              my $type = $fieldData->{type};
5192              # Plug in a relation name if it is needed.              # Plug in a relation name if it is needed.
5193              Tracer::MergeOptions($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} };  
             }  
5194              # Check for searchability.              # Check for searchability.
5195              if ($fieldData->{searchable}) {              if ($fieldData->{searchable}) {
5196                  # Only allow this for a primary relation.                  # Only allow this for a primary relation.
# Line 3736  Line 5200 
5200                      push @textFields, $fieldName;                      push @textFields, $fieldName;
5201                  }                  }
5202              }              }
             # Plug in the defaults for the optional data generation parameters.  
             Tracer::MergeOptions($fieldData->{DataGen}, { testCount => 1, pass => 0 });  
5203              # Add the PrettySortValue.              # Add the PrettySortValue.
5204              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);
5205          }          }
# Line 4001  Line 5463 
5463      # Get the parameters.      # Get the parameters.
5464      my ($relationshipName, $relationshipStructure) = @_;      my ($relationshipName, $relationshipStructure) = @_;
5465      # Format the relationship sentence.      # Format the relationship sentence.
5466      my $result = "$relationshipStructure->{from} <b>$relationshipName</b> $relationshipStructure->{to}";      my $result = "$relationshipStructure->{from} $relationshipName $relationshipStructure->{to}";
5467      # Compute the arity.      # Compute the arity.
5468      my $arityCode = $relationshipStructure->{arity};      my $arityCode = $relationshipStructure->{arity};
5469      my $arity = $ArityTable{$arityCode};      my $arity = $ArityTable{$arityCode};
# Line 4046  Line 5508 
5508      return $result;      return $result;
5509  }  }
5510    
5511    =head3 _WikiRelationTable
5512    
5513    Generate the Wiki text for a particular relation. The relation's data will be formatted as a
5514    table with three columns-- the field name, the field type, and the field description.
5515    
5516    This is a static method.
5517    
5518    =over 4
5519    
5520    =item relationName
5521    
5522    Name of the relation being formatted.
5523    
5524    =item relationData
5525    
5526    Hash containing the relation's fields and indexes.
5527    
5528    =item RETURN
5529    
5530    Returns a Wiki string that can be used to display the relation name and all of its fields.
5531    
5532    =back
5533    
5534    =cut
5535    
5536    sub _WikiRelationTable {
5537        # Get the parameters.
5538        my ($relationName, $relationData) = @_;
5539        # We'll create a list of lists in here, then call WikiTools::Table to
5540        # convert it into a table.
5541        my @rows = ();
5542        # Push in the header row.
5543        push @rows, [qw(Field Type Description)];
5544        # Loop through the fields.
5545        for my $field (@{$relationData->{Fields}}) {
5546            # Create this field's row. We always have a name and type.
5547            my @row = ($field->{name}, $field->{type});
5548            # If we have a description, add it as the third column.
5549            if (exists $field->{Notes}) {
5550                push @row, WikiNote($field->{Notes}->{content});
5551            }
5552            # Push this row onto the table list.
5553            push @rows, \@row;
5554        }
5555        # Store the rows as a Wiki table.
5556        my $retVal = WikiTools::Table(@rows);
5557        # Now we show the relation's indexes. These are formatted as another
5558        # table.
5559        @rows = ();
5560        # Push in the header row.
5561        push @rows, [qw(Index Unique Fields Notes)];
5562        # Get the index hash.
5563        my $indexTable = $relationData->{Indexes};
5564        # Loop through the indexes. For an entity, there is always at least one index.
5565        # For a relationship, there are at least two. The upshot is we don't need to
5566        # worry about accidentally generating a frivolous table here.
5567        for my $indexName (sort keys %$indexTable) {
5568            my $indexData = $indexTable->{$indexName};
5569            # Determine whether or not the index is unique.
5570            my $unique = ((exists $indexData->{Unique} && $indexData->{Unique} eq "true") ?
5571                          "yes" : "");
5572            # Get the field list.
5573            my $fields = join(', ', @{$indexData->{IndexFields}});
5574            # Get the note text.
5575            my $description = "";
5576            if (my $note = $indexData->{Notes}) {
5577                $description = WikiNote($note->{content});
5578            }
5579            # Format this row.
5580            my @row = ($indexName, $unique, $fields, $description);
5581            push @rows, \@row;
5582        }
5583        # Add the index list to the result.
5584        $retVal .= "\n\n" . WikiTools::Table(@rows);
5585    }
5586    
5587    
5588  =head3 _ShowRelationTable  =head3 _ShowRelationTable
5589    
5590  Generate the HTML string for a particular relation. The relation's data will be formatted as an HTML  Generate the HTML string for a particular relation. The relation's data will be formatted as an HTML
# Line 4096  Line 5635 
5635          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";
5636          # Add any note text.          # Add any note text.
5637          if (my $note = $indexData->{Notes}) {          if (my $note = $indexData->{Notes}) {
5638              $htmlString .= "<li>" . _HTMLNote($note->{content}) . "</li>\n";              $htmlString .= "<li>" . HTMLNote($note->{content}) . "</li>\n";
5639          }          }
5640          # Add the fiield list.          # Add the fiield list.
5641          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";
# Line 4162  Line 5701 
5701      # Compute the number of columns.      # Compute the number of columns.
5702      my $colCount = @colNames;      my $colCount = @colNames;
5703      # Generate the title row.      # Generate the title row.
5704      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";
5705      # Loop through the columns, adding the column header rows.      # Loop through the columns, adding the column header rows.
5706      $htmlString .= "<tr>";      $htmlString .= "<tr>";
5707      for my $colName (@colNames) {      for my $colName (@colNames) {
# Line 4181  Line 5720 
5720  =cut  =cut
5721    
5722  sub _CloseTable {  sub _CloseTable {
5723      return "</table></p>\n";      return "</table>\n";
5724  }  }
5725    
5726  =head3 _ShowField  =head3 _ShowField
# Line 4211  Line 5750 
5750      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>";
5751      # If we have content, add it as a third column.      # If we have content, add it as a third column.
5752      if (exists $fieldData->{Notes}) {      if (exists $fieldData->{Notes}) {
5753          $htmlString .= "<td>" . _HTMLNote($fieldData->{Notes}->{content}) . "</td>";          $htmlString .= "<td>" . HTMLNote($fieldData->{Notes}->{content}) . "</td>";
5754      }      }
5755      # Close off the row.      # Close off the row.
5756      $htmlString .= "</tr>\n";      $htmlString .= "</tr>\n";
# Line 4219  Line 5758 
5758      return $htmlString;      return $htmlString;
5759  }  }
5760    
 =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;  
 }  
   
5761  1;  1;

Legend:
Removed from v.1.70  
changed lines
  Added in v.1.96

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3