[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 1.102, Tue Sep 9 21:02:10 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                                      Issues => 'Issue',
395                                      Shapes => 'Shape'
396                                    },
397                      KeyAttr =>    { Relationship => 'name',
398                                      Entity => 'name',
399                                      Field => 'name',
400                                      Shape => 'name'
401                                    },
402                      SuppressEmpty => 1,
403                     );
404    
405  my %PictureTable = ( 'A' => "abcdefghijklmnopqrstuvwxyz",  my %XmlInOpts  = (
406                       '9' => "0123456789",                    ForceArray => [qw(Field Index IndexField Relationship Entity Shape)],
407                       'X' => "abcdefghijklmnopqrstuvwxyz0123456789",                    ForceContent => 1,
408                       'V' => "aeiou",                    NormalizeSpace => 2,
409                       'K' => "bcdfghjklmnoprstvwxyz"                   );
410    my %XmlOutOpts = (
411                      RootName => 'Database',
412                      XMLDecl => 1,
413                     );                     );
414    
415  =head2 Public Methods  =head2 Public Methods
416    
417  =head3 new  =head3 new
418    
419  C<< my $database = ERDB->new($dbh, $metaFileName); >>      my $database = ERDB->new($dbh, $metaFileName);
420    
421  Create a new ERDB object.  Create a new ERDB object.
422    
# Line 390  Line 436 
436    
437  sub new {  sub new {
438      # Get the parameters.      # Get the parameters.
439      my ($class, $dbh, $metaFileName, $options) = @_;      my ($class, $dbh, $metaFileName, %options) = @_;
440      # Load the meta-data.      # Load the meta-data.
441      my $metaData = _LoadMetaData($metaFileName);      my $metaData = _LoadMetaData($metaFileName);
442      # Create the object.      # Create the object.
# Line 404  Line 450 
450    
451  =head3 ShowMetaData  =head3 ShowMetaData
452    
453  C<< $erdb->ShowMetaData($fileName); >>      $erdb->ShowMetaData($fileName);
454    
455  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
456  the data to be loaded into the relations.  the data to be loaded into the relations.
# Line 445  Line 491 
491    
492  =head3 DisplayMetaData  =head3 DisplayMetaData
493    
494  C<< my $html = $erdb->DisplayMetaData(); >>      my $html = $erdb->DisplayMetaData();
495    
496  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
497  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 552 
552          my $entityData = $entityList->{$key};          my $entityData = $entityList->{$key};
553          # If there's descriptive text, display it.          # If there's descriptive text, display it.
554          if (my $notes = $entityData->{Notes}) {          if (my $notes = $entityData->{Notes}) {
555              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
556          }          }
557          # 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.
558            my $relCount = keys %{$relationshipList};
559            if ($relCount > 0) {
560                # First, we set up the relationship subsection.
561          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
562          # Loop through the relationships.          # Loop through the relationships.
563          for my $relationship (sort keys %{$relationshipList}) {          for my $relationship (sort keys %{$relationshipList}) {
# Line 524  Line 573 
573          }          }
574          # Close off the relationship list.          # Close off the relationship list.
575          $retVal .= "</ul>\n";          $retVal .= "</ul>\n";
576            }
577          # Get the entity's relations.          # Get the entity's relations.
578          my $relationList = $entityData->{Relations};          my $relationList = $entityData->{Relations};
579          # Create a header for the relation subsection.          # Create a header for the relation subsection.
# Line 563  Line 613 
613          $retVal .= "</p>\n";          $retVal .= "</p>\n";
614          # If there are notes on this relationship, display them.          # If there are notes on this relationship, display them.
615          if (my $notes = $relationshipStructure->{Notes}) {          if (my $notes = $relationshipStructure->{Notes}) {
616              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
617          }          }
618          # Generate the relationship's relation table.          # Generate the relationship's relation table.
619          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
# Line 597  Line 647 
647    
648  =head3 DumpMetaData  =head3 DumpMetaData
649    
650  C<< $erdb->DumpMetaData(); >>      $erdb->DumpMetaData();
651    
652  Return a dump of the metadata structure.  Return a dump of the metadata structure.
653    
# Line 610  Line 660 
660      return Data::Dumper::Dumper($self->{_metaData});      return Data::Dumper::Dumper($self->{_metaData});
661  }  }
662    
663    =head3 GenerateWikiData
664    
665        my @wikiLines = $erdb->GenerateWikiData();
666    
667    Build a description of the database for the wiki. The database will be
668    organized into a single page, with sections for each entity and relationship.
669    The return value is a list of text lines.
670    
671    =cut
672    
673    sub GenerateWikiData {
674        # Get the parameters.
675        my ($self) = @_;
676        # We'll build the wiki text in here.
677        my @retVal = ();
678        # Get the metadata object.
679        my $metadata = $self->{_metaData};
680        # Get the title string. This will become the page name.
681        my $title = $metadata->{Title}->{content};
682        # Get the entity and relationship lists.
683        my $entityList = $metadata->{Entities};
684        my $relationshipList = $metadata->{Relationships};
685        my $shapeList = $metadata->{Shapes};
686        # Start with the introductory text.
687        push @retVal, WikiTools::Heading(2, "Introduction");
688        if (my $notes = $metadata->{Notes}) {
689            push @retVal, WikiNote($notes->{content});
690        }
691        # Generate issue list.
692        if (my $issues = $metadata->{Issues}) {
693            push @retVal, WikiTools::Heading(3, 'Issues');
694            push @retVal, WikiTools::List(map { $_->{content} } @{$issues});
695        }
696        # Start the entity section.
697        push @retVal, WikiTools::Heading(2, "Entities");
698        # Loop through the entities. Note that unlike the situation with HTML, we
699        # don't need to generate the table of contents manually, just the data
700        # itself.
701        for my $key (sort keys %$entityList) {
702            # Create a header for this entity.
703            push @retVal, "", WikiTools::Heading(3, $key);
704            # Get the entity data.
705            my $entityData = $entityList->{$key};
706            # Plant the notes here, if there are any.
707            push @retVal, _ObjectNotes($entityData);
708            # Now we list the entity's relationships (if any). First, we build a list
709            # of the relationships relevant to this entity.
710            my @rels = ();
711            for my $rel (sort keys %$relationshipList) {
712                my $relStructure = $relationshipList->{$rel};
713                if ($relStructure->{from} eq $key || $relStructure->{to} eq $key) {
714                    # Get the relationship sentence.
715                    my $relSentence = _ComputeRelationshipSentence($rel, $relStructure);
716                    # Linkify it.
717                    my $linkedRel = WikiTools::LinkMarkup("#$rel", $rel);
718                    $relSentence =~ s/$rel/$linkedRel/;
719                    push @rels, $relSentence;
720                }
721            }
722            # Add the relationships as a Wiki list.
723            push @retVal, WikiTools::List(@rels);
724            # Get the entity's relations.
725            my $relationList = $entityData->{Relations};
726            # Loop through the relations, displaying them.
727            for my $relation (sort keys %{$relationList}) {
728                my $wikiString = _WikiRelationTable($relation, $relationList->{$relation});
729                push @retVal, $wikiString;
730            }
731        }
732        # Now the entities are documented. Next we do the relationships.
733        push @retVal, WikiTools::Heading(2, "Relationships");
734        for my $key (sort keys %$relationshipList) {
735            my $relationshipData = $relationshipList->{$key};
736            # Create the relationship heading.
737            push @retVal, WikiTools::Heading(3, $key);
738            # Describe the relationship arity. Note there's a bit of trickiness involving recursive
739            # many-to-many relationships. In a normal many-to-many we use two sentences to describe
740            # the arity (one for each direction). This is a bad idea for a recursive relationship,
741            # since both sentences will say the same thing.
742            my $arity = $relationshipData->{arity};
743            my $fromEntity = $relationshipData->{from};
744            my $toEntity = $relationshipData->{to};
745            my @listElements = ();
746            my $boldCode = WikiTools::BoldCode();
747            if ($arity eq "11") {
748                push @listElements, "Each $boldCode$fromEntity$boldCode relates to at most one $boldCode$toEntity$boldCode.";
749            } else {
750                push @listElements, "Each $boldCode$fromEntity$boldCode relates to multiple $boldCode${toEntity}s$boldCode.";
751                if ($arity eq "MM" && $fromEntity ne $toEntity) {
752                    push @listElements, "Each $boldCode$toEntity$boldCode relates to multiple $boldCode${fromEntity}s$boldCode.";
753                }
754            }
755            push @retVal, WikiTools::List(@listElements);
756            # Plant the notes here, if there are any.
757            push @retVal, _ObjectNotes($relationshipData);
758            # Finally, the relationship table.
759            my $wikiString = _WikiRelationTable($key, $relationshipData->{Relations}->{$key});
760            push @retVal, $wikiString;
761        }
762        # Now loop through the miscellaneous shapes.
763        if ($shapeList) {
764            push @retVal, WikiTools::Heading(2, "Miscellaneous");
765            for my $shape (sort keys %$shapeList) {
766                push @retVal, WikiTools::Heading(3, $shape);
767                my $shapeData = $shapeList->{$shape};
768                push @retVal, _ObjectNotes($shapeData);
769            }
770        }
771        # All done. Return the lines.
772        return @retVal;
773    }
774    
775    
776    =head3 CreatePPO
777    
778        ERDB::CreatePPO($erdbXMLFile, $ppoXMLFile);
779    
780    Create a PPO XML file from an ERDB data definition XML file. At the
781    current time, the PPO XML file can be used to create a database with
782    similar functionality. Eventually, the PPO will be able to use the
783    created XML to access the live ERDB database.
784    
785    =over 4
786    
787    =item erdbXMLFile
788    
789    Name of the XML data definition file for the ERDB database. This
790    file must exist.
791    
792    =item ppoXMLFile
793    
794    Output file for the PPO XML definition. If this file exists, it
795    will be overwritten.
796    
797    =back
798    
799    =cut
800    
801    sub CreatePPO {
802        # Get the parameters.
803        my ($erdbXMLFile, $ppoXMLFile) = @_;
804        # First, we want to slurp in the ERDB XML file in its raw form.
805        my $xml = ReadMetaXML($erdbXMLFile);
806        # Create a variable to hold all of the objects in the PPO project.
807        my @objects = ();
808        # Get the relationship hash.
809        my $relationships = $xml->{Relationships};
810        # Loop through the entities.
811        my $entities = $xml->{Entities};
812        for my $entityName (keys %{$entities}) {
813            # Get the entity's data structures.
814            my $entityObject = $entities->{$entityName};
815            # We put the object's fields in here, according to their type.
816            my (@object_refs, @scalars, @indexes, @arrays);
817            # Create the ID field for the entity. We get the key type from the
818            # entity object and compute the corresponding SQL type.
819            my $type = $TypeTable{$entityObject->{keyType}}->{sqlType};
820            push @scalars, { label => 'id', type => $type };
821            # Loop through the entity fields.
822            for my $fieldName ( keys %{$entityObject->{Fields}} ) {
823                # Get the field object.
824                my $fieldObject = $entityObject->{Fields}->{$fieldName};
825                # Convert it to a scalar tag.
826                my $scalar = _CreatePPOField($fieldName, $fieldObject);
827                # If we have a relation, this field is stored in an array.
828                # otherwise, it is a scalar. The array tag has scalars
829                # stored as an XML array. In ERDB, there is only ever one,
830                # but PPO can have more.
831                my $relation = $fieldObject->{relation};
832                if ($relation) {
833                    push @arrays, { scalar => [$scalar] };
834                } else {
835                    push @scalars, $scalar;
836                }
837            }
838            # Loop through the relationships. If this entity is the to-entity
839            # on a relationship of 1M arity, then it is implemented as a PPO
840            # object reference.
841            for my $relationshipName (keys %{$relationships}) {
842                # Get the relationship data.
843                my $relationshipData = $relationships->{$relationshipName};
844                # If we have a from for this entity and an arity of 1M, we
845                # have an object reference.
846                if ($relationshipData->{to} eq $entityName &&
847                    $relationshipData->{arity} eq '1M') {
848                    # Build the object reference tag.
849                    push @object_refs, { label => $relationshipName,
850                                         type => $relationshipData->{from} };
851                }
852            }
853            # Create the indexes.
854            my $indexList = $entityObject->{Indexes};
855            push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
856            # Build the object XML tree.
857            my $object = { label => $entityName,
858                           object_ref => \@object_refs,
859                           scalar => \@scalars,
860                           index => \@indexes,
861                           array => \@arrays
862                          };
863            # Push the object onto the objects list.
864            push @objects, $object;
865        }
866        # Loop through the relationships, searching for MMs. The 1Ms were
867        # already handled by the entity search above.
868        for my $relationshipName (keys %{$relationships}) {
869            # Get this relationship's object.
870            my $relationshipObject = $relationships->{$relationshipName};
871            # Only proceed if it's many-to-many.
872            if ($relationshipObject->{arity} eq 'MM') {
873                # Create the tag lists for the relationship object.
874                my (@object_refs, @scalars, @indexes);
875                # The relationship will be created as an object with object
876                # references for its links to the participating entities.
877                my %links = ( from_link => $relationshipObject->{from},
878                              to_link => $relationshipObject->{to} );
879                for my $link (keys %links) {
880                    # Create an object_ref tag for this piece of the
881                    # relationship (from or to).
882                    my $object_ref = { label => $link,
883                                       type => $links{$link} };
884                    push @object_refs, $object_ref;
885                }
886                # Loop through the intersection data fields, creating scalar tags.
887                # There are no fancy array tags in a relationship.
888                for my $fieldName (keys %{$relationshipObject->{Fields}}) {
889                    my $fieldObject = $relationshipObject->{Fields}->{$fieldName};
890                    push @scalars, _CreatePPOField($fieldName, $fieldObject);
891                }
892                # Finally, the indexes: currently we cannot support the to-index and
893                # from-index in PPO, so we just process the alternate indexes.
894                my $indexList = $relationshipObject->{Indexes};
895                push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
896                # Wrap up all the stuff about this relationship.
897                my $object = { label => $relationshipName,
898                               scalar => \@scalars,
899                               object_ref => \@object_refs,
900                               index => \@indexes
901                             };
902                # Push it into the object list.
903                push @objects, $object;
904            }
905        }
906        # Compute a title.
907        my $title;
908        if ($erdbXMLFile =~ /(\/|^)([^\/]+)DBD\.xml/) {
909            # Here we have a standard file name we can use for a title.
910            $title = $2;
911        } else {
912            # Here the file name is non-standard, so we carve up the
913            # database title.
914            $title = $xml->{Title}->{content};
915            $title =~ s/\s\.,//g;
916        }
917        # Wrap up the XML as a project.
918        my $ppoXML = { project => { label => $title,
919                                    object => \@objects }};
920        # Write out the results.
921        my $ppoString = XML::Simple::XMLout($ppoXML,
922                                            AttrIndent => 1,
923                                            KeepRoot => 1);
924        Tracer::PutFile($ppoXMLFile, [ $ppoString ]);
925    }
926    
927    =head3 FindIndexForEntity
928    
929        my $indexFound = ERDB::FindIndexForEntity($xml, $entityName, $attributeName);
930    
931    This method locates the entry in an entity's index list that begins with the
932    specified attribute name. If the entity has no index list, one will be
933    created. This method works on raw XML, not a live ERDB object.
934    
935    =over 4
936    
937    =item xml
938    
939    The raw XML structure defining the database.
940    
941    =item entityName
942    
943    The name of the relevant entity.
944    
945    =item attributeName
946    
947    The name of the attribute relevant to the search.
948    
949    =item RETURN
950    
951    The numerical index in the index list of the index entry for the specified entity and
952    attribute, or C<undef> if no such index exists.
953    
954    =back
955    
956    =cut
957    
958    sub FindIndexForEntity {
959        # Get the parameters.
960        my ($xml, $entityName, $attributeName) = @_;
961        # Declare the return variable.
962        my $retVal;
963        # Get the named entity.
964        my $entityData = $xml->{Entities}->{$entityName};
965        if (! $entityData) {
966            Confess("Entity $entityName not found in DBD structure.");
967        } else {
968            # Insure it has an index list.
969            if (! exists $entityData->{Indexes}) {
970                $entityData->{Indexes} = [];
971            } else {
972                # Search for the desired index.
973                my $indexList = $entityData->{Indexes};
974                my $n = scalar @{$indexList};
975                Trace("Searching $n indexes in index list for $entityName.") if T(2);
976                # We use an indexed FOR here because we're returning an
977                # index number instead of an object. We do THAT so we can
978                # delete the index from the list if needed.
979                for (my $i = 0; $i < $n && !defined($retVal); $i++) {
980                    my $index = $indexList->[$i];
981                    my $fields = $index->{IndexFields};
982                    # Technically this IF should be safe (that is, we are guaranteed
983                    # the existence of a "$fields->[0]"), because when we load the XML
984                    # we have SuppressEmpty specified.
985                    if ($fields->[0]->{name} eq $attributeName) {
986                        $retVal = $i;
987                    }
988                }
989            }
990        }
991        Trace("Index for $attributeName of $entityName found at position $retVal.") if defined($retVal) && T(3);
992        Trace("Index for $attributeName not found in $entityName.") if !defined($retVal) && T(3);
993        # Return the result.
994        return $retVal;
995    }
996    
997  =head3 CreateTables  =head3 CreateTables
998    
999  C<< $erdb->CreateTables(); >>      $erdb->CreateTables();
1000    
1001  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
1002  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 1013 
1013      # Loop through the relations.      # Loop through the relations.
1014      for my $relationName (@relNames) {      for my $relationName (@relNames) {
1015          # Create a table for this relation.          # Create a table for this relation.
1016          $self->CreateTable($relationName);          $self->CreateTable($relationName, 1);
1017          Trace("Relation $relationName created.") if T(2);          Trace("Relation $relationName created.") if T(2);
1018      }      }
1019  }  }
1020    
1021  =head3 CreateTable  =head3 CreateTable
1022    
1023  C<< $erdb->CreateTable($tableName, $indexFlag, $estimatedRows); >>      $erdb->CreateTable($tableName, $indexFlag, $estimatedRows);
1024    
1025  Create the table for a relation and optionally create its indexes.  Create the table for a relation and optionally create its indexes.
1026    
# Line 678  Line 1062 
1062          # Push the result into the field list.          # Push the result into the field list.
1063          push @fieldList, $fieldString;          push @fieldList, $fieldString;
1064      }      }
     # If this is a root table, add the "new_record" flag. It defaults to 0, so  
     if ($rootFlag) {  
         push @fieldList, "new_record $TypeTable{boolean}->{sqlType} NOT NULL DEFAULT 0";  
     }  
1065      # Convert the field list into a comma-delimited string.      # Convert the field list into a comma-delimited string.
1066      my $fieldThing = join(', ', @fieldList);      my $fieldThing = join(', ', @fieldList);
1067      # Insure the table is not already there.      # Insure the table is not already there.
# Line 692  Line 1072 
1072      my $estimation = undef;      my $estimation = undef;
1073      if ($estimatedRows) {      if ($estimatedRows) {
1074          $estimation = [$self->EstimateRowSize($relationName), $estimatedRows];          $estimation = [$self->EstimateRowSize($relationName), $estimatedRows];
1075            Trace("$estimation->[1] rows of $estimation->[0] bytes each.") if T(3);
1076      }      }
1077      # Create the table.      # Create the table.
1078      Trace("Creating table $relationName: $fieldThing") if T(2);      Trace("Creating table $relationName: $fieldThing") if T(2);
# Line 706  Line 1087 
1087    
1088  =head3 VerifyFields  =head3 VerifyFields
1089    
1090  C<< my $count = $erdb->VerifyFields($relName, \@fieldList); >>      my $count = $erdb->VerifyFields($relName, \@fieldList);
1091    
1092  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
1093  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 1130 
1130              my $oldString = $fieldList->[$i];              my $oldString = $fieldList->[$i];
1131              if (length($oldString) > $maxLen) {              if (length($oldString) > $maxLen) {
1132                  # Here it's too big, so we truncate it.                  # Here it's too big, so we truncate it.
1133                  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);
1134                  $fieldList->[$i] = substr $oldString, 0, $maxLen;                  $fieldList->[$i] = substr $oldString, 0, $maxLen;
1135                  $retVal++;                  $retVal++;
1136              }              }
# Line 761  Line 1142 
1142    
1143  =head3 DigestFields  =head3 DigestFields
1144    
1145  C<< $erdb->DigestFields($relName, $fieldList); >>      $erdb->DigestFields($relName, $fieldList);
1146    
1147  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
1148  specified relation.  specified relation.
# Line 801  Line 1182 
1182    
1183  =head3 DigestKey  =head3 DigestKey
1184    
1185  C<< my $digested = $erdb->DigestKey($keyValue); >>      my $digested = $erdb->DigestKey($keyValue);
1186    
1187  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
1188  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 1215 
1215    
1216  =head3 CreateIndex  =head3 CreateIndex
1217    
1218  C<< $erdb->CreateIndex($relationName); >>      $erdb->CreateIndex($relationName);
1219    
1220  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
1221  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 1236 
1236      for my $indexName (keys %{$indexHash}) {      for my $indexName (keys %{$indexHash}) {
1237          my $indexData = $indexHash->{$indexName};          my $indexData = $indexHash->{$indexName};
1238          # Get the index's field list.          # Get the index's field list.
1239          my @fieldList = _FixNames(@{$indexData->{IndexFields}});          my @rawFields = @{$indexData->{IndexFields}};
1240            # Get a hash of the relation's field types.
1241            my %types = map { $_->{name} => $_->{type} } @{$relationData->{Fields}};
1242            # We need to check for text fields so we can append a length limitation for them. To do
1243            # that, we need the relation's field list.
1244            my $relFields = $relationData->{Fields};
1245            for (my $i = 0; $i <= $#rawFields; $i++) {
1246                # Get the field type.
1247                my $field = $rawFields[$i];
1248                my $type = $types{$field};
1249                # Ask if it requires using prefix notation for the index.
1250                my $mod = $TypeTable{$type}->{indexMod};
1251                Trace("Field $field ($i) in $relationName has type $type and indexMod $mod.") if T(3);
1252                if ($mod) {
1253                    # Append the prefix length to the field name,
1254                    $rawFields[$i] .= "($mod)";
1255                }
1256            }
1257            my @fieldList = _FixNames(@rawFields);
1258          my $flds = join(', ', @fieldList);          my $flds = join(', ', @fieldList);
1259          # Get the index's uniqueness flag.          # Get the index's uniqueness flag.
1260          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
# Line 870  Line 1269 
1269      }      }
1270  }  }
1271    
1272    =head3 GetSecondaryFields
1273    
1274        my %fieldTuples = $erdb->GetSecondaryFields($entityName);
1275    
1276    This method will return a list of the name and type of each of the secondary
1277    fields for a specified entity. Secondary fields are stored in two-column tables
1278    in addition to the primary entity table. This enables the field to have no value
1279    or to have multiple values.
1280    
1281    =over 4
1282    
1283    =item entityName
1284    
1285    Name of the entity whose secondary fields are desired.
1286    
1287    =item RETURN
1288    
1289    Returns a hash mapping the field names to their field types.
1290    
1291    =back
1292    
1293    =cut
1294    
1295    sub GetSecondaryFields {
1296        # Get the parameters.
1297        my ($self, $entityName) = @_;
1298        # Declare the return variable.
1299        my %retVal = ();
1300        # Look for the entity.
1301        my $table = $self->GetFieldTable($entityName);
1302        # Loop through the fields, pulling out the secondaries.
1303        for my $field (sort keys %{$table}) {
1304            if ($table->{$field}->{relation} ne $entityName) {
1305                # Here we have a secondary field.
1306                $retVal{$field} = $table->{$field}->{type};
1307            }
1308        }
1309        # Return the result.
1310        return %retVal;
1311    }
1312    
1313    =head3 GetFieldRelationName
1314    
1315        my $name = $erdb->GetFieldRelationName($objectName, $fieldName);
1316    
1317    Return the name of the relation containing a specified field.
1318    
1319    =over 4
1320    
1321    =item objectName
1322    
1323    Name of the entity or relationship containing the field.
1324    
1325    =item fieldName
1326    
1327    Name of the relevant field in that entity or relationship.
1328    
1329    =item RETURN
1330    
1331    Returns the name of the database relation containing the field, or C<undef> if
1332    the field does not exist.
1333    
1334    =back
1335    
1336    =cut
1337    
1338    sub GetFieldRelationName {
1339        # Get the parameters.
1340        my ($self, $objectName, $fieldName) = @_;
1341        # Declare the return variable.
1342        my $retVal;
1343        # Get the object field table.
1344        my $table = $self->GetFieldTable($objectName);
1345        # Only proceed if the field exists.
1346        if (exists $table->{$fieldName}) {
1347            # Determine the name of the relation that contains this field.
1348            $retVal = $table->{$fieldName}->{relation};
1349        }
1350        # Return the result.
1351        return $retVal;
1352    }
1353    
1354    =head3 DeleteValue
1355    
1356        my $numDeleted = $erdb->DeleteValue($entityName, $id, $fieldName, $fieldValue);
1357    
1358    Delete secondary field values from the database. This method can be used to delete all
1359    values of a specified field for a particular entity instance, or only a single value.
1360    
1361    Secondary fields are stored in two-column relations separate from an entity's primary
1362    table, and as a result a secondary field can legitimately have no value or multiple
1363    values. Therefore, it makes sense to talk about deleting secondary fields where it
1364    would not make sense for primary fields.
1365    
1366    =over 4
1367    
1368    =item entityName
1369    
1370    Name of the entity from which the fields are to be deleted.
1371    
1372    =item id
1373    
1374    ID of the entity instance to be processed. If the instance is not found, this
1375    method will have no effect. If C<undef> is specified, all values for all of
1376    the entity instances will be deleted.
1377    
1378    =item fieldName
1379    
1380    Name of the field whose values are to be deleted.
1381    
1382    =item fieldValue (optional)
1383    
1384    Value to be deleted. If not specified, then all values of the specified field
1385    will be deleted for the entity instance. If specified, then only the values which
1386    match this parameter will be deleted.
1387    
1388    =item RETURN
1389    
1390    Returns the number of rows deleted.
1391    
1392    =back
1393    
1394    =cut
1395    
1396    sub DeleteValue {
1397        # Get the parameters.
1398        my ($self, $entityName, $id, $fieldName, $fieldValue) = @_;
1399        # Declare the return value.
1400        my $retVal = 0;
1401        # We need to set up an SQL command to do the deletion. First, we
1402        # find the name of the field's relation.
1403        my $table = $self->GetFieldTable($entityName);
1404        my $field = $table->{$fieldName};
1405        my $relation = $field->{relation};
1406        # Make sure this is a secondary field.
1407        if ($relation eq $entityName) {
1408            Confess("Cannot delete values of $fieldName for $entityName.");
1409        } else {
1410            # Set up the SQL command to delete all values.
1411            my $sql = "DELETE FROM $relation";
1412            # Build the filter.
1413            my @filters = ();
1414            my @parms = ();
1415            # Check for a filter by ID.
1416            if (defined $id) {
1417                push @filters, "id = ?";
1418                push @parms, $id;
1419            }
1420            # Check for a filter by value.
1421            if (defined $fieldValue) {
1422                push @filters, "$fieldName = ?";
1423                push @parms, $fieldValue;
1424            }
1425            # Append the filters to the command.
1426            if (@filters) {
1427                $sql .= " WHERE " . join(" AND ", @filters);
1428            }
1429            # Execute the command.
1430            my $dbh = $self->{_dbh};
1431            $retVal = $dbh->SQL($sql, 0, @parms);
1432        }
1433        # Return the result.
1434        return $retVal;
1435    }
1436    
1437  =head3 LoadTables  =head3 LoadTables
1438    
1439  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>      my $stats = $erdb->LoadTables($directoryName, $rebuild);
1440    
1441  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
1442  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 1496 
1496    
1497  =head3 GetTableNames  =head3 GetTableNames
1498    
1499  C<< my @names = $erdb->GetTableNames; >>      my @names = $erdb->GetTableNames;
1500    
1501  Return a list of the relations required to implement this database.  Return a list of the relations required to implement this database.
1502    
# Line 949  Line 1513 
1513    
1514  =head3 GetEntityTypes  =head3 GetEntityTypes
1515    
1516  C<< my @names = $erdb->GetEntityTypes; >>      my @names = $erdb->GetEntityTypes;
1517    
1518  Return a list of the entity type names.  Return a list of the entity type names.
1519    
# Line 964  Line 1528 
1528      return sort keys %{$entityList};      return sort keys %{$entityList};
1529  }  }
1530    
1531    
1532    =head3 GetConnectingRelationships
1533    
1534        my @list = $erdb->GetConnectingRelationships($entityName);
1535    
1536    Return a list of the relationships connected to the specified entity.
1537    
1538    =over 4
1539    
1540    =item entityName
1541    
1542    Entity whose connected relationships are desired.
1543    
1544    =item RETURN
1545    
1546    Returns a list of the relationships that originate from the entity.
1547    If the entity is on the from end, it will return the relationship
1548    name. If the entity is on the to end it will return the converse of
1549    the relationship name.
1550    
1551    =back
1552    
1553    =cut
1554    
1555    sub GetConnectingRelationships {
1556        # Get the parameters.
1557        my ($self, $entityName) = @_;
1558        # Declare the return variable.
1559        my @retVal;
1560        # Get the relationship list.
1561        my $relationships = $self->{_metaData}->{Relationships};
1562        # Find the entity.
1563        my $entity = $self->{_metaData}->{Entities}->{$entityName};
1564        # Only proceed if the entity exists.
1565        if (! defined $entity) {
1566            Trace("Entity $entityName not found.") if T(3);
1567        } else {
1568            # Loop through the relationships.
1569            my @rels = keys %$relationships;
1570            Trace(scalar(@rels) . " relationships found in connection search.") if T(3);
1571            for my $relationshipName (@rels) {
1572                my $relationship = $relationships->{$relationshipName};
1573                if ($relationship->{from} eq $entityName) {
1574                    # Here we have a forward relationship.
1575                    push @retVal, $relationshipName;
1576                } elsif ($relationship->{to} eq $entityName) {
1577                    # Here we have a backward relationship. In this case, the
1578                    # converse relationship name is preferred if it exists.
1579                    my $converse = $relationship->{converse} || $relationshipName;
1580                    push @retVal, $converse;
1581                }
1582            }
1583        }
1584        # Return the result.
1585        return @retVal;
1586    }
1587    
1588    
1589    =head3 GetDataTypes
1590    
1591        my %types = ERDB::GetDataTypes();
1592    
1593    Return a table of ERDB data types. The table returned is a hash of hashes.
1594    The keys of the big hash are the datatypes. Each smaller hash has several
1595    values used to manage the data. The most interesting is the SQL type (key
1596    C<sqlType>) and the descriptive node (key C<notes>).
1597    
1598    Note that changing the values in the smaller hashes will seriously break
1599    things, so this data should be treated as read-only.
1600    
1601    =cut
1602    
1603    sub GetDataTypes {
1604        return %TypeTable;
1605    }
1606    
1607    
1608  =head3 IsEntity  =head3 IsEntity
1609    
1610  C<< my $flag = $erdb->IsEntity($entityName); >>      my $flag = $erdb->IsEntity($entityName);
1611    
1612  Return TRUE if the parameter is an entity name, else FALSE.  Return TRUE if the parameter is an entity name, else FALSE.
1613    
# Line 993  Line 1634 
1634    
1635  =head3 Get  =head3 Get
1636    
1637  C<< my $query = $erdb->Get(\@objectNames, $filterClause, \@params); >>      my $query = $erdb->Get(\@objectNames, $filterClause, \@params);
1638    
1639  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.
1640  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 1642 
1642  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
1643  $genus.  $genus.
1644    
1645  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", [$genus]); >>      $query = $erdb->Get(['Genome'], "Genome(genus) = ?", [$genus]);
1646    
1647  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
1648  parameter representing the parameter value. It would also be possible to code  parameter representing the parameter value. It would also be possible to code
1649    
1650  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>      $query = $erdb->Get(['Genome'], "Genome(genus) = \'$genus\'");
1651    
1652  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
1653  characters inside the variable C<$genus>.  characters inside the variable C<$genus>.
# Line 1018  Line 1659 
1659  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
1660  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,
1661    
1662  C<< $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]); >>      $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]);
1663    
1664  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
1665  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 1695 
1695  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
1696  particular genus and sorts them by species name.  particular genus and sorts them by species name.
1697    
1698  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>      "Genome(genus) = ? ORDER BY Genome(species)"
1699    
1700  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
1701  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 1708 
1708  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
1709  a positive number. So, for example  a positive number. So, for example
1710    
1711  C<< "Genome(genus) = ? ORDER BY Genome(species) LIMIT 10" >>      "Genome(genus) = ? ORDER BY Genome(species) LIMIT 10"
1712    
1713  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
1714  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
1715  use  use
1716    
1717  C<< "LIMIT 10" >>      "LIMIT 10"
1718    
1719  =item params  =item params
1720    
# Line 1094  Line 1735 
1735      my ($suffix, $mappedNameListRef, $mappedNameHashRef) =      my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1736          $self->_SetupSQL($objectNames, $filterClause);          $self->_SetupSQL($objectNames, $filterClause);
1737      # Create the query.      # Create the query.
1738      my $command = "SELECT DISTINCT " . join(".*, ", @{$mappedNameListRef}) .      my $command = "SELECT " . join(".*, ", @{$mappedNameListRef}) .
1739          ".* $suffix";          ".* $suffix";
1740      my $sth = $self->_GetStatementHandle($command, $params);      my $sth = $self->_GetStatementHandle($command, $params);
1741      # 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 1749 
1749      return $retVal;      return $retVal;
1750  }  }
1751    
1752    
1753    
1754  =head3 Search  =head3 Search
1755    
1756  C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>      my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params);
1757    
1758  Perform a full text search with filtering. The search will be against a specified object  Perform a full text search with filtering. The search will be against a specified object
1759  in the object name list. That object will get an extra field containing the search  in the object name list. That object will get an extra field containing the search
# Line 1121  Line 1764 
1764    
1765  =item searchExpression  =item searchExpression
1766    
1767  Boolean search expression for the text fields of the target object.  Boolean search expression for the text fields of the target object. The default mode for
1768    a Boolean search expression is OR, but we want the default to be AND, so we will
1769    add a C<+> operator to each word with no other operator before it.
1770    
1771  =item idx  =item idx
1772    
# Line 1158  Line 1803 
1803      my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;      my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1804      # Declare the return variable.      # Declare the return variable.
1805      my $retVal;      my $retVal;
1806      # Create a safety copy of the parameter list.      # Create a safety copy of the parameter list. Note we have to be careful to insure
1807      my @myParams = @{$params};      # a parameter list exists before we copy it.
1808        my @myParams = ();
1809        if (defined $params) {
1810            @myParams = @{$params};
1811        }
1812      # 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.
1813      my $object1Name = $objectNames->[$idx];      my $object1Name = $objectNames->[$idx];
1814      my $object1Structure = $self->_GetStructure($object1Name);      my $object1Structure = $self->_GetStructure($object1Name);
# Line 1169  Line 1818 
1818      } else {      } else {
1819          # Get the field list.          # Get the field list.
1820          my @fields = @{$object1Structure->{searchFields}};          my @fields = @{$object1Structure->{searchFields}};
1821            # Clean the search expression.
1822            my $actualKeywords = $self->CleanKeywords($searchExpression);
1823            # Prefix a "+" to each uncontrolled word. This converts the default
1824            # search mode from OR to AND.
1825            $actualKeywords =~ s/(^|\s)(\w|")/$1\+$2/g;
1826            Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1827          # 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
1828          # 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
1829          # search expression onto the front of the parameter list twice.          # search expression onto the front of the parameter list twice.
1830          unshift @myParams, $searchExpression, $searchExpression;          unshift @myParams, $actualKeywords, $actualKeywords;
1831          # Build the match expression.          # Build the match expression.
1832          my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;          my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
1833          my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";          my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
# Line 1181  Line 1836 
1836              $self->_SetupSQL($objectNames, $filterClause, $matchClause);              $self->_SetupSQL($objectNames, $filterClause, $matchClause);
1837          # 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
1838          # the select fields.          # the select fields.
1839          my $command = "SELECT DISTINCT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .          my $command = "SELECT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .
1840              ".* $suffix";              ".* $suffix";
1841          my $sth = $self->_GetStatementHandle($command, \@myParams);          my $sth = $self->_GetStatementHandle($command, \@myParams);
1842          # 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 1850 
1850    
1851  =head3 GetFlat  =head3 GetFlat
1852    
1853  C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>      my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field);
1854    
1855  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
1856  returns a single flattened list.  returns a single flattened list.
# Line 1246  Line 1901 
1901      return @retVal;      return @retVal;
1902  }  }
1903    
1904  =head3 Delete  =head3 SpecialFields
1905    
1906  C<< my $stats = $erdb->Delete($entityName, $objectID); >>      my %specials = $erdb->SpecialFields($entityName);
1907    
1908  Delete an entity instance from the database. The instance is deleted along with all entity and  Return a hash mapping special fields in the specified entity to the value of their
1909  relationship instances dependent on it. The idea of dependence here is recursive. An object is  C<special> attribute. This enables the subclass to get access to the special field
1910  always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many  attributes without needed to plumb the internal ERDB data structures.
 relationship connected to a dependent entity or the "to" entity connected to a 1-to-many  
 dependent relationship.  
1911    
1912  =over 4  =over 4
1913    
1914  =item entityName  =item entityName
1915    
1916  Name of the entity type for the instance being deleted.  Name of the entity whose special fields are desired.
1917    
1918  =item objectID  =item RETURN
1919    
1920  ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),  Returns a hash. The keys of the hash are the special field names, and the values
1921  then it is presumed to by a LIKE pattern.  are the values from each special field's C<special> attribute.
1922    
1923  =item testFlag  =back
1924    
1925    =cut
1926    
1927    sub SpecialFields {
1928        # Get the parameters.
1929        my ($self, $entityName) = @_;
1930        # Declare the return variable.
1931        my %retVal = ();
1932        # Find the entity's data structure.
1933        my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1934        # Loop through its fields, adding each special field to the return hash.
1935        my $fieldHash = $entityData->{Fields};
1936        for my $fieldName (keys %{$fieldHash}) {
1937            my $fieldData = $fieldHash->{$fieldName};
1938            if (exists $fieldData->{special}) {
1939                $retVal{$fieldName} = $fieldData->{special};
1940            }
1941        }
1942        # Return the result.
1943        return %retVal;
1944    }
1945    
1946    =head3 Delete
1947    
1948        my $stats = $erdb->Delete($entityName, $objectID, %options);
1949    
1950    Delete an entity instance from the database. The instance is deleted along with all entity and
1951    relationship instances dependent on it. The definition of I<dependence> is recursive.
1952    
1953    An object is always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many
1954    relationship connected to a dependent entity or if it is the "to" entity connected to a 1-to-many
1955    dependent relationship.
1956    
1957    =over 4
1958    
1959    =item entityName
1960    
1961    Name of the entity type for the instance being deleted.
1962    
1963    =item objectID
1964    
1965    ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),
1966    then it is presumed to by a LIKE pattern.
1967    
1968    =item options
1969    
1970  If TRUE, the delete statements will be traced without being executed.  A hash detailing the options for this delete operation.
1971    
1972  =item RETURN  =item RETURN
1973    
# Line 1278  Line 1976 
1976    
1977  =back  =back
1978    
1979    The permissible options for this method are as follows.
1980    
1981    =over 4
1982    
1983    =item testMode
1984    
1985    If TRUE, then the delete statements will be traced, but no changes will be made to the database.
1986    
1987    =item keepRoot
1988    
1989    If TRUE, then the entity instances will not be deleted, only the dependent records.
1990    
1991    =back
1992    
1993  =cut  =cut
1994  #: Return Type $%;  #: Return Type $%;
1995  sub Delete {  sub Delete {
1996      # Get the parameters.      # Get the parameters.
1997      my ($self, $entityName, $objectID, $testFlag) = @_;      my ($self, $entityName, $objectID, %options) = @_;
1998      # Declare the return variable.      # Declare the return variable.
1999      my $retVal = Stats->new();      my $retVal = Stats->new();
2000      # Get the DBKernel object.      # Get the DBKernel object.
# Line 1299  Line 2011 
2011      # FROM-relationships and entities.      # FROM-relationships and entities.
2012      my @fromPathList = ();      my @fromPathList = ();
2013      my @toPathList = ();      my @toPathList = ();
2014      # This final hash is used to remember what work still needs to be done. We push paths      # This final list is used to remember what work still needs to be done. We push paths
2015      # onto the list, then pop them off to extend the paths. We prime it with the starting      # onto the list, then pop them off to extend the paths. We prime it with the starting
2016      # point. Note that we will work hard to insure that the last item on a path in the      # point. Note that we will work hard to insure that the last item on a path in the
2017      # TODO list is always an entity.      # to-do list is always an entity.
2018      my @todoList = ([$entityName]);      my @todoList = ([$entityName]);
2019      while (@todoList) {      while (@todoList) {
2020          # Get the current path.          # Get the current path.
# Line 1310  Line 2022 
2022          # Copy it into a list.          # Copy it into a list.
2023          my @stackedPath = @{$current};          my @stackedPath = @{$current};
2024          # 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.
2025          my $entityName = pop @stackedPath;          my $myEntityName = pop @stackedPath;
2026          # Add it to the alreadyFound list.          # Add it to the alreadyFound list.
2027          $alreadyFound{$entityName} = 1;          $alreadyFound{$myEntityName} = 1;
2028            # Figure out if we need to delete this entity.
2029            if ($myEntityName ne $entityName || ! $options{keepRoot}) {
2030          # Get the entity data.          # Get the entity data.
2031          my $entityData = $self->_GetStructure($entityName);              my $entityData = $self->_GetStructure($myEntityName);
2032          # 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.  
2033          my $relations = $entityData->{Relations};          my $relations = $entityData->{Relations};
2034          for my $relation (keys %{$relations}) {          for my $relation (keys %{$relations}) {
2035              my @augmentedList = (@stackedPath, $relation);              my @augmentedList = (@stackedPath, $relation);
2036              push @fromPathList, \@augmentedList;              push @fromPathList, \@augmentedList;
2037          }          }
2038            }
2039          # Now we need to look for relationships connected to this entity.          # Now we need to look for relationships connected to this entity.
2040          my $relationshipList = $self->{_metaData}->{Relationships};          my $relationshipList = $self->{_metaData}->{Relationships};
2041          for my $relationshipName (keys %{$relationshipList}) {          for my $relationshipName (keys %{$relationshipList}) {
2042              my $relationship = $relationshipList->{$relationshipName};              my $relationship = $relationshipList->{$relationshipName};
2043              # Check the FROM field. We're only interested if it's us.              # Check the FROM field. We're only interested if it's us.
2044              if ($relationship->{from} eq $entityName) {              if ($relationship->{from} eq $myEntityName) {
2045                  # Add the path to this relationship.                  # Add the path to this relationship.
2046                  my @augmentedList = (@stackedPath, $entityName, $relationshipName);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
2047                  push @fromPathList, \@augmentedList;                  push @fromPathList, \@augmentedList;
2048                  # Check the arity. If it's MM we're done. If it's 1M                  # Check the arity. If it's MM we're done. If it's 1M
2049                  # and the target hasn't been seen yet, we want to                  # and the target hasn't been seen yet, we want to
# Line 1348  Line 2062 
2062              }              }
2063              # Now check the TO field. In this case only the relationship needs              # Now check the TO field. In this case only the relationship needs
2064              # deletion.              # deletion.
2065              if ($relationship->{to} eq $entityName) {              if ($relationship->{to} eq $myEntityName) {
2066                  my @augmentedList = (@stackedPath, $entityName, $relationshipName);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
2067                  push @toPathList, \@augmentedList;                  push @toPathList, \@augmentedList;
2068              }              }
2069          }          }
2070      }      }
2071      # Create the first qualifier for the WHERE clause. This selects the      # Create the first qualifier for the WHERE clause. This selects the
2072      # 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
2073      # 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
2074      # to the table containing the dependent records to delete.      # to the table containing the dependent records to delete.
2075      my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");      my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
2076      # 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 2109 
2109                  }                  }
2110              }              }
2111              # Now we have our desired DELETE statement.              # Now we have our desired DELETE statement.
2112              if ($testFlag) {              if ($options{testMode}) {
2113                  # Here the user wants to trace without executing.                  # Here the user wants to trace without executing.
2114                  Trace($stmt) if T(0);                  Trace($stmt) if T(0);
2115              } else {              } else {
2116                  # 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
2117                  # if an error occurs, so we just go ahead and do it.                  # if an error occurs, so we just go ahead and do it.
2118                  Trace("Executing delete from $target using '$objectID'.") if T(3);                  Trace("Executing delete from $target using '$objectID'.") if T(3);
2119                  my $rv = $db->SQL($stmt, 0, $objectID);                  my $rv = $db->SQL($stmt, 0, $objectID);
# Line 1414  Line 2128 
2128      return $retVal;      return $retVal;
2129  }  }
2130    
2131    =head3 Disconnect
2132    
2133        $erdb->Disconnect($relationshipName, $originEntityName, $originEntityID);
2134    
2135    Disconnect an entity instance from all the objects to which it is related. This
2136    will delete each relationship instance that connects to the specified entity.
2137    
2138    =over 4
2139    
2140    =item relationshipName
2141    
2142    Name of the relationship whose instances are to be deleted.
2143    
2144    =item originEntityName
2145    
2146    Name of the entity that is to be disconnected.
2147    
2148    =item originEntityID
2149    
2150    ID of the entity that is to be disconnected.
2151    
2152    =back
2153    
2154    =cut
2155    
2156    sub Disconnect {
2157        # Get the parameters.
2158        my ($self, $relationshipName, $originEntityName, $originEntityID) = @_;
2159        # Get the relationship descriptor.
2160        my $structure = $self->_GetStructure($relationshipName);
2161        # Insure we have a relationship.
2162        if (! exists $structure->{from}) {
2163            Confess("$relationshipName is not a relationship in the database.");
2164        } else {
2165            # Get the database handle.
2166            my $dbh = $self->{_dbh};
2167            # We'll set this value to 1 if we find our entity.
2168            my $found = 0;
2169            # Loop through the ends of the relationship.
2170            for my $dir ('from', 'to') {
2171                if ($structure->{$dir} eq $originEntityName) {
2172                    $found = 1;
2173                    # Here we want to delete all relationship instances on this side of the
2174                    # entity instance.
2175                    Trace("Disconnecting in $dir direction with ID \"$originEntityID\".");
2176                    # We do this delete in batches to keep it from dragging down the
2177                    # server.
2178                    my $limitClause = ($FIG_Config::delete_limit ? "LIMIT $FIG_Config::delete_limit" : "");
2179                    my $done = 0;
2180                    while (! $done) {
2181                        # Do the delete.
2182                        my $rows = $dbh->SQL("DELETE FROM $relationshipName WHERE ${dir}_link = ? $limitClause", 0, $originEntityID);
2183                        # See if we're done. We're done if no rows were found or the delete is unlimited.
2184                        $done = ($rows == 0 || ! $limitClause);
2185                    }
2186                }
2187            }
2188            # Insure we found the entity on at least one end.
2189            if (! $found) {
2190                Confess("Entity \"$originEntityName\" does not use $relationshipName.");
2191            }
2192        }
2193    }
2194    
2195    =head3 DeleteRow
2196    
2197        $erdb->DeleteRow($relationshipName, $fromLink, $toLink, \%values);
2198    
2199    Delete a row from a relationship. In most cases, only the from-link and to-link are
2200    needed; however, for relationships with intersection data values can be specified
2201    for the other fields using a hash.
2202    
2203    =over 4
2204    
2205    =item relationshipName
2206    
2207    Name of the relationship from which the row is to be deleted.
2208    
2209    =item fromLink
2210    
2211    ID of the entity instance in the From direction.
2212    
2213    =item toLink
2214    
2215    ID of the entity instance in the To direction.
2216    
2217    =item values
2218    
2219    Reference to a hash of other values to be used for filtering the delete.
2220    
2221    =back
2222    
2223    =cut
2224    
2225    sub DeleteRow {
2226        # Get the parameters.
2227        my ($self, $relationshipName, $fromLink, $toLink, $values) = @_;
2228        # Create a hash of all the filter information.
2229        my %filter = ('from-link' => $fromLink, 'to-link' => $toLink);
2230        if (defined $values) {
2231            for my $key (keys %{$values}) {
2232                $filter{$key} = $values->{$key};
2233            }
2234        }
2235        # Build an SQL statement out of the hash.
2236        my @filters = ();
2237        my @parms = ();
2238        for my $key (keys %filter) {
2239            push @filters, _FixName($key) . " = ?";
2240            push @parms, $filter{$key};
2241        }
2242        Trace("Parms for delete row are " . join(", ", map { "\"$_\"" } @parms) . ".") if T(SQL => 4);
2243        my $command = "DELETE FROM $relationshipName WHERE " .
2244                      join(" AND ", @filters);
2245        # Execute it.
2246        my $dbh = $self->{_dbh};
2247        $dbh->SQL($command, undef, @parms);
2248    }
2249    
2250    =head3 DeleteLike
2251    
2252        my $deleteCount = $erdb->DeleteLike($relName, $filter, \@parms);
2253    
2254    Delete all the relationship rows that satisfy a particular filter condition. Unlike a normal
2255    filter, only fields from the relationship itself can be used.
2256    
2257    =over 4
2258    
2259    =item relName
2260    
2261    Name of the relationship whose records are to be deleted.
2262    
2263    =item filter
2264    
2265    A filter clause (L</Get>-style) for the delete query.
2266    
2267    =item parms
2268    
2269    Reference to a list of parameters for the filter clause.
2270    
2271    =item RETURN
2272    
2273    Returns a count of the number of rows deleted.
2274    
2275    =back
2276    
2277    =cut
2278    
2279    sub DeleteLike {
2280        # Get the parameters.
2281        my ($self, $objectName, $filter, $parms) = @_;
2282        # Declare the return variable.
2283        my $retVal;
2284        # Insure the parms argument is an array reference if the caller left it off.
2285        if (! defined($parms)) {
2286            $parms = [];
2287        }
2288        # Insure we have a relationship. The main reason for this is if we delete an entity
2289        # instance we have to yank out a bunch of other stuff with it.
2290        if ($self->IsEntity($objectName)) {
2291            Confess("Cannot use DeleteLike on $objectName, because it is not a relationship.");
2292        } else {
2293            # Create the SQL command suffix to get the desierd records.
2294            my ($suffix) = $self->_SetupSQL([$objectName], $filter);
2295            # Convert it to a DELETE command.
2296            my $command = "DELETE $suffix";
2297            # Execute the command.
2298            my $dbh = $self->{_dbh};
2299            my $result = $dbh->SQL($command, 0, @{$parms});
2300            # Check the results. Note we convert the "0D0" result to a real zero.
2301            # A failure causes an abnormal termination, so the caller isn't going to
2302            # worry about it.
2303            if (! defined $result) {
2304                Confess("Error deleting from $objectName: " . $dbh->errstr());
2305            } elsif ($result == 0) {
2306                $retVal = 0;
2307            } else {
2308                $retVal = $result;
2309            }
2310        }
2311        # Return the result count.
2312        return $retVal;
2313    }
2314    
2315  =head3 SortNeeded  =head3 SortNeeded
2316    
2317  C<< my $parms = $erdb->SortNeeded($relationName); >>      my $parms = $erdb->SortNeeded($relationName);
2318    
2319  Return the pipe command for the sort that should be applied to the specified  Return the pipe command for the sort that should be applied to the specified
2320  relation when creating the load file.  relation when creating the load file.
# Line 1464  Line 2362 
2362      } elsif (exists $relationshipTable->{$relationName}) {      } elsif (exists $relationshipTable->{$relationName}) {
2363          # Here we have a relationship. We sort using the FROM index.          # Here we have a relationship. We sort using the FROM index.
2364          my $relationshipData = $relationshipTable->{$relationName};          my $relationshipData = $relationshipTable->{$relationName};
2365          my $index = $relationData->{Indexes}->{"idx${relationName}From"};          my $index = $relationData->{Indexes}->{idxFrom};
2366          push @keyNames, @{$index->{IndexFields}};          push @keyNames, @{$index->{IndexFields}};
2367      } else {      } else {
2368          # 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 1472  Line 2370 
2370      }      }
2371      # Now we parse the key names into sort parameters. First, we prime the return      # Now we parse the key names into sort parameters. First, we prime the return
2372      # string.      # string.
2373      my $retVal = "sort -t\"\t\" ";      my $retVal = "sort -S 1G -T\"$FIG_Config::temp\" -t\"\t\" ";
2374      # Get the relation's field list.      # Get the relation's field list.
2375      my @fields = @{$relationData->{Fields}};      my @fields = @{$relationData->{Fields}};
2376      # Loop through the keys.      # Loop through the keys.
# Line 1502  Line 2400 
2400                  # will stop the inner loop. Note that the field number is                  # will stop the inner loop. Note that the field number is
2401                  # 1-based in the sort command, so we have to increment the                  # 1-based in the sort command, so we have to increment the
2402                  # index.                  # index.
2403                  $fieldSpec = ($i + 1) . $modifier;                  my $realI = $i + 1;
2404                    $fieldSpec = "$realI,$realI$modifier";
2405              }              }
2406          }          }
2407          # Add this field to the sort command.          # Add this field to the sort command.
# Line 1514  Line 2413 
2413    
2414  =head3 GetList  =head3 GetList
2415    
2416  C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>      my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params);
2417    
2418  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
2419  specified filter clause.  specified filter clause.
# Line 1542  Line 2441 
2441  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
2442  particular genus and sorts them by species name.  particular genus and sorts them by species name.
2443    
2444  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>      "Genome(genus) = ? ORDER BY Genome(species)"
2445    
2446  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
2447  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 2453 
2453    
2454  =item RETURN  =item RETURN
2455    
2456  Returns a list of B<DBObject>s that satisfy the query conditions.  Returns a list of B<ERDBObject>s that satisfy the query conditions.
2457    
2458  =back  =back
2459    
# Line 1577  Line 2476 
2476    
2477  =head3 GetCount  =head3 GetCount
2478    
2479  C<< my $count = $erdb->GetCount(\@objectNames, $filter, \@params); >>      my $count = $erdb->GetCount(\@objectNames, $filter, \@params);
2480    
2481  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
2482  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 2569 
2569    
2570  =head3 ComputeObjectSentence  =head3 ComputeObjectSentence
2571    
2572  C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>      my $sentence = $erdb->ComputeObjectSentence($objectName);
2573    
2574  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.
2575    
# Line 1705  Line 2604 
2604    
2605  =head3 DumpRelations  =head3 DumpRelations
2606    
2607  C<< $erdb->DumpRelations($outputDirectory); >>      $erdb->DumpRelations($outputDirectory);
2608    
2609  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.
2610  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 2646 
2646    
2647  =head3 InsertValue  =head3 InsertValue
2648    
2649  C<< $erdb->InsertValue($entityID, $fieldName, $value); >>      $erdb->InsertValue($entityID, $fieldName, $value);
2650    
2651  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
2652  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 2709 
2709    
2710  =head3 InsertObject  =head3 InsertObject
2711    
2712  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>      $erdb->InsertObject($objectType, \%fieldHash);
2713    
2714  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
2715  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 2718 
2718  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
2719  C<ZP_00210270.1> and C<gi|46206278>.  C<ZP_00210270.1> and C<gi|46206278>.
2720    
2721  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']});
2722    
2723  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
2724  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>.
2725    
2726  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'});
2727    
2728  =over 4  =over 4
2729    
# Line 1836  Line 2735 
2735    
2736  Hash of field names to values.  Hash of field names to values.
2737    
 =item RETURN  
   
 Returns 1 if successful, 0 if an error occurred.  
   
2738  =back  =back
2739    
2740  =cut  =cut
# Line 1897  Line 2792 
2792                  push @missing, $fieldName;                  push @missing, $fieldName;
2793              }              }
2794          }          }
         # If we are the primary relation, add the new-record flag.  
         if ($relationName eq $newObjectType) {  
             push @valueList, 1;  
             push @fieldNameList, "new_record";  
         }  
2795          # Only proceed if there are no missing fields.          # Only proceed if there are no missing fields.
2796          if (@missing > 0) {          if (@missing > 0) {
2797              Trace("Relation $relationName for $newObjectType skipped due to missing fields: " .              Trace("Relation $relationName for $newObjectType skipped due to missing fields: " .
# Line 1938  Line 2828 
2828                  $retVal = $sth->execute(@parameterList);                  $retVal = $sth->execute(@parameterList);
2829                  if (!$retVal) {                  if (!$retVal) {
2830                      my $errorString = $sth->errstr();                      my $errorString = $sth->errstr();
2831                      Trace("Insert error: $errorString.") if T(0);                      Confess("Error inserting into $relationName: $errorString");
2832                    } else {
2833                        Trace("Insert successful using $parameterList[0].") if T(3);
2834                  }                  }
2835              }              }
2836          }          }
2837      }      }
2838      # Return the success indicator.      # Return a 1 for backward compatability.
2839      return $retVal;      return 1;
2840    }
2841    
2842    =head3 UpdateEntity
2843    
2844        $erdb->UpdateEntity($entityName, $id, \%fields);
2845    
2846    Update the values of an entity. This is an unprotected update, so it should only be
2847    done if the database resides on a database server.
2848    
2849    =over 4
2850    
2851    =item entityName
2852    
2853    Name of the entity to update. (This is the entity type.)
2854    
2855    =item id
2856    
2857    ID of the entity to update. If no entity exists with this ID, an error will be thrown.
2858    
2859    =item fields
2860    
2861    Reference to a hash mapping field names to their new values. All of the fields named
2862    must be in the entity's primary relation, and they cannot any of them be the ID field.
2863    
2864    =back
2865    
2866    =cut
2867    
2868    sub UpdateEntity {
2869        # Get the parameters.
2870        my ($self, $entityName, $id, $fields) = @_;
2871        # Get a list of the field names being updated.
2872        my @fieldList = keys %{$fields};
2873        # Verify that the fields exist.
2874        my $checker = $self->GetFieldTable($entityName);
2875        for my $field (@fieldList) {
2876            if ($field eq 'id') {
2877                Confess("Cannot update the ID field for entity $entityName.");
2878            } elsif ($checker->{$field}->{relation} ne $entityName) {
2879                Confess("Cannot find $field in primary relation of $entityName.");
2880            }
2881        }
2882        # Build the SQL statement.
2883        my @sets = ();
2884        my @valueList = ();
2885        for my $field (@fieldList) {
2886            push @sets, _FixName($field) . " = ?";
2887            push @valueList, $fields->{$field};
2888        }
2889        my $command = "UPDATE $entityName SET " . join(", ", @sets) . " WHERE id = ?";
2890        # Add the ID to the list of binding values.
2891        push @valueList, $id;
2892        # Call SQL to do the work.
2893        my $rows = $self->{_dbh}->SQL($command, 0, @valueList);
2894        # Check for errors.
2895        if ($rows == 0) {
2896            Confess("Entity $id of type $entityName not found.");
2897        }
2898  }  }
2899    
2900  =head3 LoadTable  =head3 LoadTable
2901    
2902  C<< my %results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>      my $results = $erdb->LoadTable($fileName, $relationName, %options);
2903    
2904  Load data from a tab-delimited file into a specified table, optionally re-creating the table  Load data from a tab-delimited file into a specified table, optionally re-creating the table
2905  first.  first.
# Line 1964  Line 2914 
2914    
2915  Name of the relation to be loaded. This is the same as the table name.  Name of the relation to be loaded. This is the same as the table name.
2916    
2917  =item truncateFlag  =item options
2918    
2919  TRUE if the table should be dropped and re-created, else FALSE  A hash of load options.
2920    
2921  =item RETURN  =item RETURN
2922    
# Line 1974  Line 2924 
2924    
2925  =back  =back
2926    
2927    The permissible options are as follows.
2928    
2929    =over 4
2930    
2931    =item truncate
2932    
2933    If TRUE, then the table will be erased before loading.
2934    
2935    =item mode
2936    
2937    Mode in which the load should operate, either C<low_priority> or C<concurrent>.
2938    This option is only applicable to a MySQL database.
2939    
2940    =item partial
2941    
2942    If TRUE, then it is assumed that this is a partial load, and the table will not
2943    be analyzed and compacted at the end.
2944    
2945    =back
2946    
2947  =cut  =cut
2948  sub LoadTable {  sub LoadTable {
2949      # Get the parameters.      # Get the parameters.
2950      my ($self, $fileName, $relationName, $truncateFlag) = @_;      my ($self, $fileName, $relationName, %options) = @_;
2951      # Create the statistical return object.      # Create the statistical return object.
2952      my $retVal = _GetLoadStats();      my $retVal = _GetLoadStats();
2953      # Trace the fact of the load.      # Trace the fact of the load.
# Line 1989  Line 2959 
2959      # Get the relation data.      # Get the relation data.
2960      my $relation = $self->_FindRelation($relationName);      my $relation = $self->_FindRelation($relationName);
2961      # Check the truncation flag.      # Check the truncation flag.
2962      if ($truncateFlag) {      if ($options{truncate}) {
2963          Trace("Creating table $relationName") if T(2);          Trace("Creating table $relationName") if T(2);
2964          # 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,
2965          # 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
2966          # leave extra room. We postulate a minimum row count of 1000 to          # leave extra room. We postulate a minimum row count of 1000 to
2967          # prevent problems with incoming empty load files.          # prevent problems with incoming empty load files.
2968          my $rowSize = $self->EstimateRowSize($relationName);          my $rowSize = $self->EstimateRowSize($relationName);
2969          my $estimate = FIG::max($fileSize * 1.5 / $rowSize, 1000);          my $estimate = $fileSize * 8 / $rowSize;
2970            if ($estimate < 1000) {
2971                $estimate = 1000;
2972            }
2973          # Re-create the table without its index.          # Re-create the table without its index.
2974          $self->CreateTable($relationName, 0, $estimate);          $self->CreateTable($relationName, 0, $estimate);
2975          # 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 2985 
2985      # Load the table.      # Load the table.
2986      my $rv;      my $rv;
2987      eval {      eval {
2988          $rv = $dbh->load_table(file => $fileName, tbl => $relationName);          $rv = $dbh->load_table(file => $fileName, tbl => $relationName, style => $options{mode});
2989      };      };
2990      if (!defined $rv) {      if (!defined $rv) {
2991          $retVal->AddMessage($@) if ($@);          $retVal->AddMessage($@) if ($@);
2992          $retVal->AddMessage("Table load failed for $relationName using $fileName.");          $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2993          Trace("Table load failed for $relationName.") if T(1);          Trace("Table load failed for $relationName.") if T(1);
2994      } else {      } else {
2995          # Here we successfully loaded the table.          # Here we successfully loaded the table.
2996          $retVal->Add("tables");          $retVal->Add("tables");
2997          my $size = -s $fileName;          my $size = -s $fileName;
2998          Trace("$size bytes loaded into $relationName.") if T(2);          Trace("$size bytes loaded into $relationName.") if T(2);
2999            $retVal->Add("bytes", $size);
3000          # If we're rebuilding, we need to create the table indexes.          # If we're rebuilding, we need to create the table indexes.
3001          if ($truncateFlag) {          if ($options{truncate}) {
3002              # Indexes are created here for PostGres. For PostGres, indexes are              # Indexes are created here for PostGres. For PostGres, indexes are
3003              # best built at the end. For MySQL, the reverse is true.              # best built at the end. For MySQL, the reverse is true.
3004              if (! $dbh->{_preIndex}) {              if (! $dbh->{_preIndex}) {
# Line 2038  Line 3012 
3012              # 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.
3013              # 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
3014              # primary relations are allowed that privilege.              # primary relations are allowed that privilege.
3015                Trace("Checking for full-text index on $relationName.") if T(2);
3016              if ($self->_IsPrimary($relationName)) {              if ($self->_IsPrimary($relationName)) {
3017                  # 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');  
                 }  
3018              }              }
3019          }          }
3020      }      }
3021      # Analyze the table to improve performance.      # Analyze the table to improve performance.
3022        if (! $options{partial}) {
3023      Trace("Analyzing and compacting $relationName.") if T(3);      Trace("Analyzing and compacting $relationName.") if T(3);
3024      $dbh->vacuum_it($relationName);          $self->Analyze($relationName);
3025        }
3026      Trace("$relationName load completed.") if T(3);      Trace("$relationName load completed.") if T(3);
3027      # Return the statistics.      # Return the statistics.
3028      return $retVal;      return $retVal;
3029  }  }
3030    
3031  =head3 GenerateEntity  =head3 Analyze
3032    
3033  C<< my $fieldHash = $erdb->GenerateEntity($id, $type, \%values); >>      $erdb->Analyze($tableName);
3034    
3035  Generate the data for a new entity instance. This method creates a field hash suitable for  Analyze and compact a table in the database. This is useful after a load
3036  passing as a parameter to L</InsertObject>. The ID is specified by the callr, but the rest  to improve the performance of the indexes.
 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.  
3037    
3038  =over 4  =over 4
3039    
3040  =item id  =item tableName
3041    
3042  ID to assign to the new entity.  Name of the table to be analyzed and compacted.
3043    
3044  =item type  =back
3045    
3046  Type name for the new entity.  =cut
3047    
3048  =item values  sub Analyze {
3049        # Get the parameters.
3050        my ($self, $tableName) = @_;
3051        # Analyze the table.
3052        $self->{_dbh}->vacuum_it($tableName);
3053    }
3054    
3055    =head3 TruncateTable
3056    
3057        $erdb->TruncateTable($table);
3058    
3059  Hash containing additional values that might be needed by the data generation methods (optional).  Delete all rows from a table quickly. This uses the built-in SQL
3060    C<TRUNCATE> statement, which effectively drops and re-creates a table
3061    with all its settings intact.
3062    
3063    =over 4
3064    
3065    =item table
3066    
3067    Name of the table to be cleared.
3068    
3069  =back  =back
3070    
3071  =cut  =cut
3072    
3073  sub GenerateEntity {  sub TruncateTable {
3074      # Get the parameters.      # Get the parameters.
3075      my ($self, $id, $type, $values) = @_;      my ($self, $table) = @_;
3076      # Create the return hash.      # Get the database handle.
3077      my $this = { id => $id };      my $dbh = $self->{_dbh};
3078      # Get the metadata structure.      # Execute a truncation comment.
3079      my $metadata = $self->{_metaData};      $dbh->SQL("TRUNCATE TABLE $table");
3080      # Get this entity's list of fields.  }
3081      if (!exists $metadata->{Entities}->{$type}) {  
3082          Confess("Unrecognized entity type $type in GenerateEntity.");  
3083      } else {  =head3 CreateSearchIndex
3084          my $entity = $metadata->{Entities}->{$type};  
3085          my $fields = $entity->{Fields};      $erdb->CreateSearchIndex($objectName);
3086          # Generate data from the fields.  
3087          _GenerateFields($this, $fields, $type, $values);  Check for a full-text search index on the specified entity or relationship object, and
3088    if one is required, rebuild it.
3089    
3090    =over 4
3091    
3092    =item objectName
3093    
3094    Name of the entity or relationship to be indexed.
3095    
3096    =back
3097    
3098    =cut
3099    
3100    sub CreateSearchIndex {
3101        # Get the parameters.
3102        my ($self, $objectName) = @_;
3103        # Get the relation's entity/relationship structure.
3104        my $structure = $self->_GetStructure($objectName);
3105        # Get the database handle.
3106        my $dbh = $self->{_dbh};
3107        Trace("Checking for search fields in $objectName.") if T(3);
3108        # Check for a searchable fields list.
3109        if (exists $structure->{searchFields}) {
3110            # Here we know that we need to create a full-text search index.
3111            # Get an SQL-formatted field name list.
3112            my $fields = join(", ", _FixNames(@{$structure->{searchFields}}));
3113            # Create the index. If it already exists, it will be dropped.
3114            $dbh->create_index(tbl => $objectName, idx => "search_idx",
3115                               flds => $fields, kind => 'fulltext');
3116            Trace("Index created for $fields in $objectName.") if T(2);
3117        }
3118    }
3119    
3120    =head3 DropRelation
3121    
3122        $erdb->DropRelation($relationName);
3123    
3124    Physically drop a relation from the database.
3125    
3126    =over 4
3127    
3128    =item relationName
3129    
3130    Name of the relation to drop. If it does not exist, this method will have
3131    no effect.
3132    
3133    =back
3134    
3135    =cut
3136    
3137    sub DropRelation {
3138        # Get the parameters.
3139        my ($self, $relationName) = @_;
3140        # Get the database handle.
3141        my $dbh = $self->{_dbh};
3142        # Drop the relation. The method used here has no effect if the relation
3143        # does not exist.
3144        Trace("Invoking DB Kernel to drop $relationName.") if T(3);
3145        $dbh->drop_table(tbl => $relationName);
3146    }
3147    
3148    =head3 MatchSqlPattern
3149    
3150        my $matched = ERDB::MatchSqlPattern($value, $pattern);
3151    
3152    Determine whether or not a specified value matches an SQL pattern. An SQL
3153    pattern has two wild card characters: C<%> that matches multiple characters,
3154    and C<_> that matches a single character. These can be escaped using a
3155    backslash (C<\>). We pull this off by converting the SQL pattern to a
3156    PERL regular expression. As per SQL rules, the match is case-insensitive.
3157    
3158    =over 4
3159    
3160    =item value
3161    
3162    Value to be matched against the pattern. Note that an undefined or empty
3163    value will not match anything.
3164    
3165    =item pattern
3166    
3167    SQL pattern against which to match the value. An undefined or empty pattern will
3168    match everything.
3169    
3170    =item RETURN
3171    
3172    Returns TRUE if the value and pattern match, else FALSE.
3173    
3174    =back
3175    
3176    =cut
3177    
3178    sub MatchSqlPattern {
3179        # Get the parameters.
3180        my ($value, $pattern) = @_;
3181        # Declare the return variable.
3182        my $retVal;
3183        # Insure we have a pattern.
3184        if (! defined($pattern) || $pattern eq "") {
3185            $retVal = 1;
3186        } else {
3187            # Break the pattern into pieces around the wildcard characters. Because we
3188            # use parentheses in the split function's delimiter expression, we'll get
3189            # list elements for the delimiters as well as the rest of the string.
3190            my @pieces = split /([_%]|\\[_%])/, $pattern;
3191            # Check some fast special cases.
3192            if ($pattern eq '%') {
3193                # A null pattern matches everything.
3194                $retVal = 1;
3195            } elsif (@pieces == 1) {
3196                # No wildcards, so we have a literal comparison. Note we're case-insensitive.
3197                $retVal = (lc($value) eq lc($pattern));
3198            } elsif (@pieces == 2 && $pieces[1] eq '%') {
3199                # A wildcard at the end, so we have a substring match. This is also case-insensitive.
3200                $retVal = (lc(substr($value, 0, length($pieces[0]))) eq lc($pieces[0]));
3201            } else {
3202                # Okay, we have to do it the hard way. Convert each piece to a PERL pattern.
3203                my $realPattern = "";
3204                for my $piece (@pieces) {
3205                    # Determine the type of piece.
3206                    if ($piece eq "") {
3207                        # Empty pieces are ignored.
3208                    } elsif ($piece eq "%") {
3209                        # Here we have a multi-character wildcard. Note that it can match
3210                        # zero or more characters.
3211                        $realPattern .= ".*"
3212                    } elsif ($piece eq "_") {
3213                        # Here we have a single-character wildcard.
3214                        $realPattern .= ".";
3215                    } elsif ($piece eq "\\%" || $piece eq "\\_") {
3216                        # This is an escape sequence (which is a rare thing, actually).
3217                        $realPattern .= substr($piece, 1, 1);
3218                    } else {
3219                        # Here we have raw text.
3220                        $realPattern .= quotemeta($piece);
3221                    }
3222      }      }
3223      # Return the hash created.              # Do the match.
3224      return $this;              $retVal = ($value =~ /^$realPattern$/i ? 1 : 0);
3225            }
3226        }
3227        # Return the result.
3228        return $retVal;
3229  }  }
3230    
3231  =head3 GetEntity  =head3 GetEntity
3232    
3233  C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>      my $entityObject = $erdb->GetEntity($entityType, $ID);
3234    
3235  Return an object describing the entity instance with a specified ID.  Return an object describing the entity instance with a specified ID.
3236    
# Line 2137  Line 3246 
3246    
3247  =item RETURN  =item RETURN
3248    
3249  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
3250  instance is found with the specified key.  instance is found with the specified key.
3251    
3252  =back  =back
# Line 2151  Line 3260 
3260      my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);      my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);
3261      # Get the first (and only) object.      # Get the first (and only) object.
3262      my $retVal = $query->Fetch();      my $retVal = $query->Fetch();
3263        if (T(3)) {
3264            if ($retVal) {
3265                Trace("Entity $entityType \"$ID\" found.");
3266            } else {
3267                Trace("Entity $entityType \"$ID\" not found.");
3268            }
3269        }
3270      # Return the result.      # Return the result.
3271      return $retVal;      return $retVal;
3272  }  }
3273    
3274  =head3 GetChoices  =head3 GetChoices
3275    
3276  C<< my @values = $erdb->GetChoices($entityName, $fieldName); >>      my @values = $erdb->GetChoices($entityName, $fieldName);
3277    
3278  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
3279  specified entity.  specified entity.
# Line 2212  Line 3328 
3328    
3329  =head3 GetEntityValues  =head3 GetEntityValues
3330    
3331  C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>      my @values = $erdb->GetEntityValues($entityType, $ID, \@fields);
3332    
3333  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
3334  does not exist, an empty list is returned.  does not exist, an empty list is returned.
# Line 2256  Line 3372 
3372    
3373  =head3 GetAll  =head3 GetAll
3374    
3375  C<< my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>      my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count);
3376    
3377  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
3378  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 3386 
3386  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
3387  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
3388  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
3389  feature ID followed by all of its aliases.  feature ID followed by all of its essentiality determinations.
3390    
3391  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)']);
3392    
3393  =over 4  =over 4
3394    
# Line 2343  Line 3459 
3459          push @retVal, \@rowData;          push @retVal, \@rowData;
3460          $fetched++;          $fetched++;
3461      }      }
3462      Trace("$fetched rows returned in GetAll.") if T(SQL => 4);      Trace("$fetched rows returned in GetAll.") if T(SQL => 4);
3463      # Return the resulting list.      # Return the resulting list.
3464      return @retVal;      return @retVal;
3465    }
3466    
3467    =head3 Exists
3468    
3469        my $found = $sprout->Exists($entityName, $entityID);
3470    
3471    Return TRUE if an entity exists, else FALSE.
3472    
3473    =over 4
3474    
3475    =item entityName
3476    
3477    Name of the entity type (e.g. C<Feature>) relevant to the existence check.
3478    
3479    =item entityID
3480    
3481    ID of the entity instance whose existence is to be checked.
3482    
3483    =item RETURN
3484    
3485    Returns TRUE if the entity instance exists, else FALSE.
3486    
3487    =back
3488    
3489    =cut
3490    #: Return Type $;
3491    sub Exists {
3492        # Get the parameters.
3493        my ($self, $entityName, $entityID) = @_;
3494        # Check for the entity instance.
3495        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
3496        my $testInstance = $self->GetEntity($entityName, $entityID);
3497        # Return an existence indicator.
3498        my $retVal = ($testInstance ? 1 : 0);
3499        return $retVal;
3500    }
3501    
3502    =head3 EstimateRowSize
3503    
3504        my $rowSize = $erdb->EstimateRowSize($relName);
3505    
3506    Estimate the row size of the specified relation. The estimated row size is computed by adding
3507    up the average length for each data type.
3508    
3509    =over 4
3510    
3511    =item relName
3512    
3513    Name of the relation whose estimated row size is desired.
3514    
3515    =item RETURN
3516    
3517    Returns an estimate of the row size for the specified relation.
3518    
3519    =back
3520    
3521    =cut
3522    #: Return Type $;
3523    sub EstimateRowSize {
3524        # Get the parameters.
3525        my ($self, $relName) = @_;
3526        # Declare the return variable.
3527        my $retVal = 0;
3528        # Find the relation descriptor.
3529        my $relation = $self->_FindRelation($relName);
3530        # Get the list of fields.
3531        for my $fieldData (@{$relation->{Fields}}) {
3532            # Get the field type and add its length.
3533            my $fieldLen = $TypeTable{$fieldData->{type}}->{avgLen};
3534            $retVal += $fieldLen;
3535        }
3536        # Return the result.
3537        return $retVal;
3538    }
3539    
3540    =head3 GetFieldTable
3541    
3542        my $fieldHash = $self->GetFieldTable($objectnName);
3543    
3544    Get the field structure for a specified entity or relationship.
3545    
3546    =over 4
3547    
3548    =item objectName
3549    
3550    Name of the desired entity or relationship.
3551    
3552    =item RETURN
3553    
3554    The table containing the field descriptors for the specified object.
3555    
3556    =back
3557    
3558    =cut
3559    
3560    sub GetFieldTable {
3561        # Get the parameters.
3562        my ($self, $objectName) = @_;
3563        # Get the descriptor from the metadata.
3564        my $objectData = $self->_GetStructure($objectName);
3565        # Return the object's field table.
3566        return $objectData->{Fields};
3567    }
3568    
3569    =head3 SplitKeywords
3570    
3571        my @keywords = ERDB::SplitKeywords($keywordString);
3572    
3573    This method returns a list of the positive keywords in the specified
3574    keyword string. All of the operators will have been stripped off,
3575    and if the keyword is preceded by a minus operator (C<->), it will
3576    not be in the list returned. The idea here is to get a list of the
3577    keywords the user wants to see. The list will be processed to remove
3578    duplicates.
3579    
3580    It is possible to create a string that confuses this method. For example
3581    
3582        frog toad -frog
3583    
3584    would return both C<frog> and C<toad>. If this is a problem we can deal
3585    with it later.
3586    
3587    =over 4
3588    
3589    =item keywordString
3590    
3591    The keyword string to be parsed.
3592    
3593    =item RETURN
3594    
3595    Returns a list of the words in the keyword string the user wants to
3596    see.
3597    
3598    =back
3599    
3600    =cut
3601    
3602    sub SplitKeywords {
3603        # Get the parameters.
3604        my ($keywordString) = @_;
3605        # Make a safety copy of the string. (This helps during debugging.)
3606        my $workString = $keywordString;
3607        # Convert operators we don't care about to spaces.
3608        $workString =~ tr/+"()<>/ /;
3609        # Split the rest of the string along space boundaries. Note that we
3610        # eliminate any words that are zero length or begin with a minus sign.
3611        my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
3612        # Use a hash to remove duplicates.
3613        my %words = map { $_ => 1 } @wordList;
3614        # Return the result.
3615        return sort keys %words;
3616    }
3617    
3618    =head3 ValidateFieldName
3619    
3620        my $okFlag = ERDB::ValidateFieldName($fieldName);
3621    
3622    Return TRUE if the specified field name is valid, else FALSE. Valid field names must
3623    be hyphenated words subject to certain restrictions.
3624    
3625    =over 4
3626    
3627    =item fieldName
3628    
3629    Field name to be validated.
3630    
3631    =item RETURN
3632    
3633    Returns TRUE if the field name is valid, else FALSE.
3634    
3635    =back
3636    
3637    =cut
3638    
3639    sub ValidateFieldName {
3640        # Get the parameters.
3641        my ($fieldName) = @_;
3642        # Declare the return variable. The field name is valid until we hear
3643        # differently.
3644        my $retVal = 1;
3645        # Compute the maximum name length.
3646        my $maxLen = $TypeTable{'name-string'}->{maxLen};
3647        # Look for bad stuff in the name.
3648        if ($fieldName =~ /--/) {
3649            # Here we have a doubled minus sign.
3650            Trace("Field name $fieldName has a doubled hyphen.") if T(1);
3651            $retVal = 0;
3652        } elsif ($fieldName !~ /^[A-Za-z]/) {
3653            # Here the field name is missing the initial letter.
3654            Trace("Field name $fieldName does not begin with a letter.") if T(1);
3655            $retVal = 0;
3656        } elsif (length($fieldName) > $maxLen) {
3657            # Here the field name is too long.
3658            Trace("Maximum field name length is $maxLen. Field name must be truncated to " . substr($fieldName,0, $maxLen) . ".");
3659        } else {
3660            # Strip out the minus signs. Everything remaining must be a letter,
3661            # underscore, or digit.
3662            my $strippedName = $fieldName;
3663            $strippedName =~ s/-//g;
3664            if ($strippedName !~ /^(\w|\d)+$/) {
3665                Trace("Field name $fieldName contains illegal characters.") if T(1);
3666                $retVal = 0;
3667            }
3668        }
3669        # Return the result.
3670        return $retVal;
3671    }
3672    
3673    =head3 ReadMetaXML
3674    
3675        my $rawMetaData = ERDB::ReadDBD($fileName);
3676    
3677    This method reads a raw database definition XML file and returns it.
3678    Normally, the metadata used by the ERDB system has been processed and
3679    modified to make it easier to load and retrieve the data; however,
3680    this method can be used to get the data in its raw form.
3681    
3682    =over 4
3683    
3684    =item fileName
3685    
3686    Name of the XML file to read.
3687    
3688    =item RETURN
3689    
3690    Returns a hash reference containing the raw XML data from the specified file.
3691    
3692    =back
3693    
3694    =cut
3695    
3696    sub ReadMetaXML {
3697        # Get the parameters.
3698        my ($fileName) = @_;
3699        # Read the XML.
3700        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
3701        Trace("XML metadata loaded from file $fileName.") if T(1);
3702        # Return the result.
3703        return $retVal;
3704    }
3705    
3706    =head3 GetEntityFieldHash
3707    
3708        my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName);
3709    
3710    Get the field hash of the named entity in the specified raw XML structure.
3711    The field hash may not exist, in which case we need to create it.
3712    
3713    =over 4
3714    
3715    =item structure
3716    
3717    Raw XML structure defininng the database. This is not the run-time XML used by
3718    an ERDB object, since that has all sorts of optimizations built-in.
3719    
3720    =item entityName
3721    
3722    Name of the entity whose field structure is desired.
3723    
3724    =item RETURN
3725    
3726    Returns the field hash used to define the entity's fields.
3727    
3728    =back
3729    
3730    =cut
3731    
3732    sub GetEntityFieldHash {
3733        # Get the parameters.
3734        my ($structure, $entityName) = @_;
3735        # Get the entity structure.
3736        my $entityData = $structure->{Entities}->{$entityName};
3737        # Look for a field structure.
3738        my $retVal = $entityData->{Fields};
3739        # If it doesn't exist, create it.
3740        if (! defined($retVal)) {
3741            $entityData->{Fields} = {};
3742            $retVal = $entityData->{Fields};
3743        }
3744        # Return the result.
3745        return $retVal;
3746  }  }
3747    
3748  =head3 Exists  =head3 WriteMetaXML
3749    
3750  C<< my $found = $sprout->Exists($entityName, $entityID); >>      ERDB::WriteMetaXML($structure, $fileName);
3751    
3752  Return TRUE if an entity exists, else FALSE.  Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
3753    used to update the database definition. It must be used with care, however, since it
3754    will only work on a raw structure, not on the processed structure created by an ERDB
3755    constructor.
3756    
3757  =over 4  =over 4
3758    
3759  =item entityName  =item structure
3760    
3761  Name of the entity type (e.g. C<Feature>) relevant to the existence check.  XML structure to be written to the file.
3762    
3763  =item entityID  =item fileName
3764    
3765  ID of the entity instance whose existence is to be checked.  Name of the output file to which the updated XML should be stored.
3766    
3767    =back
3768    
3769    =cut
3770    
3771    sub WriteMetaXML {
3772        # Get the parameters.
3773        my ($structure, $fileName) = @_;
3774        # Compute the output.
3775        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
3776        # Write it to the file.
3777        my $xmlOut = Open(undef, ">$fileName");
3778        print $xmlOut $fileString;
3779    }
3780    
3781    
3782    =head3 HTMLNote
3783    
3784    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
3785    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
3786    Except for C<[p]>, all the codes are closed by slash-codes. So, for
3787    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
3788    
3789        my $realHtml = ERDB::HTMLNote($dataString);
3790    
3791    =over 4
3792    
3793    =item dataString
3794    
3795    String to convert to HTML.
3796    
3797  =item RETURN  =item RETURN
3798    
3799  Returns TRUE if the entity instance exists, else FALSE.  An HTML string derived from the input string.
3800    
3801  =back  =back
3802    
3803  =cut  =cut
3804  #: Return Type $;  
3805  sub Exists {  sub HTMLNote {
3806      # Get the parameters.      # Get the parameter.
3807      my ($self, $entityName, $entityID) = @_;      my ($dataString) = @_;
3808      # Check for the entity instance.      # HTML-escape the text.
3809      Trace("Checking existence of $entityName with ID=$entityID.") if T(4);      my $retVal = CGI::escapeHTML($dataString);
3810      my $testInstance = $self->GetEntity($entityName, $entityID);      # Substitute the bulletin board codes.
3811      # Return an existence indicator.      $retVal =~ s!\[(/?[bi])\]!<$1>!g;
3812      my $retVal = ($testInstance ? 1 : 0);      $retVal =~ s!\[p\]!</p><p>!g;
3813        $retVal =~ s!\[link\s+([^\]]+)\]!<a href="$1">!g;
3814        $retVal =~ s!\[/link\]!</a>!g;
3815        # Return the result.
3816      return $retVal;      return $retVal;
3817  }  }
3818    
3819  =head3 EstimateRowSize  =head3 WikiNote
3820    
3821  C<< my $rowSize = $erdb->EstimateRowSize($relName); >>  Convert a note or comment to Wiki text by replacing some bulletin-board codes with HTML. The codes
3822    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
3823    Except for C<[p]>, all the codes are closed by slash-codes. So, for
3824    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
3825    
3826  Estimate the row size of the specified relation. The estimated row size is computed by adding      my $wikiText = ERDB::WikiNote($dataString);
 up the average length for each data type.  
3827    
3828  =over 4  =over 4
3829    
3830  =item relName  =item dataString
3831    
3832  Name of the relation whose estimated row size is desired.  String to convert to Wiki text.
3833    
3834  =item RETURN  =item RETURN
3835    
3836  Returns an estimate of the row size for the specified relation.  An Wiki text string derived from the input string.
3837    
3838  =back  =back
3839    
3840  =cut  =cut
3841  #: Return Type $;  
3842  sub EstimateRowSize {  sub WikiNote {
3843      # Get the parameters.      # Get the parameter.
3844      my ($self, $relName) = @_;      my ($dataString) = @_;
3845      # Declare the return variable.      # HTML-escape the text.
3846      my $retVal = 0;      my $retVal = CGI::escapeHTML($dataString);
3847      # Find the relation descriptor.      # Substitute the bulletin board codes.
3848      my $relation = $self->_FindRelation($relName);      my $italic = WikiTools::ItalicCode();
3849      # Get the list of fields.      $retVal =~ s/\[\/?i\]/$italic/g;
3850      for my $fieldData (@{$relation->{Fields}}) {      my $bold = WikiTools::BoldCode();
3851          # Get the field type and add its length.      $retVal =~ s/\[\/?b\]/$bold/g;
3852          my $fieldLen = $TypeTable{$fieldData->{type}}->{avgLen};      # Paragraph breaks are the same no matter which Wiki you're using.
3853          $retVal += $fieldLen;      $retVal =~ s!\[p\]!\n\n!g;
3854        # Now we do the links, which are complicated by the need to know two
3855        # things: the target URL and the text.
3856        while ($retVal =~ /\[link\s+([^\]]+)\]([^\[]+)\[\/link\]/g) {
3857            # Replace the matched string with the Wiki markup for links. Note that
3858            # $-[0] is the starting position of the match for the entire expression,
3859            # and $+[0] is past the ending position.
3860            substr $retVal, $-[0], $+[0] - $-[0], WikiTools::LinkMarkup($1, $2);
3861      }      }
3862      # Return the result.      # Return the result.
3863      return $retVal;      return $retVal;
3864  }  }
3865    
3866  =head3 GetFieldTable  =head3 BeginTran
3867    
3868  C<< my $fieldHash = $self->GetFieldTable($objectnName); >>      $erdb->BeginTran();
3869    
3870  Get the field structure for a specified entity or relationship.  Start a database transaction.
3871    
3872    =cut
3873    
3874    sub BeginTran {
3875        my ($self) = @_;
3876        $self->{_dbh}->begin_tran();
3877    
3878    }
3879    
3880    =head3 CommitTran
3881    
3882        $erdb->CommitTran();
3883    
3884    Commit an active database transaction.
3885    
3886    =cut
3887    
3888    sub CommitTran {
3889        my ($self) = @_;
3890        $self->{_dbh}->commit_tran();
3891    }
3892    
3893    =head3 RollbackTran
3894    
3895        $erdb->RollbackTran();
3896    
3897    Roll back an active database transaction.
3898    
3899    =cut
3900    
3901    sub RollbackTran {
3902        my ($self) = @_;
3903        $self->{_dbh}->roll_tran();
3904    }
3905    
3906    =head3 UpdateField
3907    
3908        my $count = $erdb->UpdateField($objectNames, $fieldName, $oldValue, $newValue, $filter, $parms);
3909    
3910    Update all occurrences of a specific field value to a new value. The number of rows changed will be
3911    returned.
3912    
3913  =over 4  =over 4
3914    
3915  =item objectName  =item fieldName
3916    
3917  Name of the desired entity or relationship.  Name of the field in standard I<objectName>C<(>I<fieldName>C<)> format.
3918    
3919    =item oldValue
3920    
3921    Value to be modified. All occurrences of this value in the named field will be replaced by the
3922    new value.
3923    
3924    =item newValue
3925    
3926    New value to be substituted for the old value when it's found.
3927    
3928    =item filter
3929    
3930    A standard ERDB filter clause (see L</Get>). The filter will be applied before any substitutions take place.
3931    
3932    =item parms
3933    
3934    Reference to a list of parameter values in the filter.
3935    
3936  =item RETURN  =item RETURN
3937    
3938  The table containing the field descriptors for the specified object.  Returns the number of rows modified.
3939    
3940  =back  =back
3941    
3942  =cut  =cut
3943    
3944  sub GetFieldTable {  sub UpdateField {
3945      # Get the parameters.      # Get the parameters.
3946      my ($self, $objectName) = @_;      my ($self, $fieldName, $oldValue, $newValue, $filter, $parms) = @_;
3947      # Get the descriptor from the metadata.      # Get the object and field names from the field name parameter.
3948      my $objectData = $self->_GetStructure($objectName);      $fieldName =~ /^([^(]+)\(([^)]+)\)/;
3949      # Return the object's field table.      my $objectName = $1;
3950      return $objectData->{Fields};      my $realFieldName = _FixName($2);
3951        # Add the old value to the filter. Note we allow the possibility that no
3952        # filter was specified.
3953        my $realFilter = "$fieldName = ?";
3954        if ($filter) {
3955            $realFilter .= " AND $filter";
3956        }
3957        # Format the query filter.
3958        my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
3959            $self->_SetupSQL([$objectName], $realFilter);
3960        # Create the query. Since there is only one object name, the mapped-name data is not
3961        # necessary. Neither is the FROM clause.
3962        $suffix =~ s/^FROM.+WHERE\s+//;
3963        # Create the update statement.
3964        my $command = "UPDATE $objectName SET $realFieldName = ? WHERE $suffix";
3965        # Get the database handle.
3966        my $dbh = $self->{_dbh};
3967        # Add the old and new values to the parameter list. Note we allow the possibility that
3968        # there are no user-supplied parameters.
3969        my @params = ($newValue, $oldValue);
3970        if (defined $parms) {
3971            push @params, @{$parms};
3972        }
3973        # Execute the update.
3974        my $retVal = $dbh->SQL($command, 0, @params);
3975        # Make the funky zero a real zero.
3976        if ($retVal == 0) {
3977            $retVal = 0;
3978  }  }
3979        # Return the result.
3980        return $retVal;
3981    }
3982    
3983    
3984  =head2 Data Mining Methods  =head2 Data Mining Methods
3985    
3986  =head3 GetUsefulCrossValues  =head3 GetUsefulCrossValues
3987    
3988  C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>      my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship);
3989    
3990  Return a list of the useful attributes that would be returned by a B<Cross> call  Return a list of the useful attributes that would be returned by a B<Cross> call
3991  from an entity of the source entity type through the specified relationship. This  from an entity of the source entity type through the specified relationship. This
# Line 2515  Line 4046 
4046    
4047  =head3 FindColumn  =head3 FindColumn
4048    
4049  C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>      my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier);
4050    
4051  Return the location a desired column in a data mining header line. The data  Return the location a desired column in a data mining header line. The data
4052  mining header line is a tab-separated list of column names. The column  mining header line is a tab-separated list of column names. The column
# Line 2573  Line 4104 
4104    
4105  =head3 ParseColumns  =head3 ParseColumns
4106    
4107  C<< my @columns = ERDB::ParseColumns($line); >>      my @columns = ERDB::ParseColumns($line);
4108    
4109  Convert the specified data line to a list of columns.  Convert the specified data line to a list of columns.
4110    
# Line 2603  Line 4134 
4134      return @retVal;      return @retVal;
4135  }  }
4136    
4137    =head2 Virtual Methods
4138    
4139    =head3 _CreatePPOIndex
4140    
4141        my $index = ERDB::_CreatePPOIndex($indexObject);
4142    
4143    Convert the XML for an ERDB index to the XML structure for a PPO
4144    index.
4145    
4146    =over 4
4147    
4148    =item indexObject
4149    
4150    ERDB XML structure for an index.
4151    
4152    =item RETURN
4153    
4154    PPO XML structure for the same index.
4155    
4156    =back
4157    
4158    =cut
4159    
4160    sub _CreatePPOIndex {
4161        # Get the parameters.
4162        my ($indexObject) = @_;
4163        # The incoming index contains a list of the index fields in the IndexFields
4164        # member. We loop through it to create the index tags.
4165        my @fields = map { { label => _FixName($_->{name}) } } @{$indexObject->{IndexFields}};
4166        # Wrap the fields in attribute tags.
4167        my $retVal = { attribute => \@fields };
4168        # Return the result.
4169        return $retVal;
4170    }
4171    
4172    =head3 _CreatePPOField
4173    
4174        my $fieldXML = ERDB::_CreatePPOField($fieldName, $fieldObject);
4175    
4176    Convert the ERDB XML structure for a field to a PPO scalar XML structure.
4177    
4178    =over 4
4179    
4180    =item fieldName
4181    
4182    Name of the scalar field.
4183    
4184    =item fieldObject
4185    
4186    ERDB XML structure describing the field.
4187    
4188    =item RETURN
4189    
4190    Returns a PPO XML structure for the same field.
4191    
4192    =back
4193    
4194    =cut
4195    
4196    sub _CreatePPOField {
4197        # Get the parameters.
4198        my ($fieldName, $fieldObject) = @_;
4199        # Get the field type.
4200        my $type = $TypeTable{$fieldObject->{type}}->{sqlType};
4201        # Fix up the field name.
4202        $fieldName = _FixName($fieldName);
4203        # Build the scalar tag.
4204        my $retVal = { label => $fieldName, type => $type };
4205        # Return the result.
4206        return $retVal;
4207    }
4208    
4209    =head3 CleanKeywords
4210    
4211        my $cleanedString = $erdb->CleanKeywords($searchExpression);
4212    
4213    Clean up a search expression or keyword list. This is a virtual method that may
4214    be overridden by the subclass. The base-class method removes extra spaces
4215    and converts everything to lower case.
4216    
4217    =over 4
4218    
4219    =item searchExpression
4220    
4221    Search expression or keyword list to clean. Note that a search expression may
4222    contain boolean operators which need to be preserved. This includes leading
4223    minus signs.
4224    
4225    =item RETURN
4226    
4227    Cleaned expression or keyword list.
4228    
4229    =back
4230    
4231    =cut
4232    
4233    sub CleanKeywords {
4234        # Get the parameters.
4235        my ($self, $searchExpression) = @_;
4236        # Lower-case the expression and copy it into the return variable. Note that we insure we
4237        # don't accidentally end up with an undefined value.
4238        my $retVal = lc($searchExpression || "");
4239        # Remove extra spaces.
4240        $retVal =~ s/\s+/ /g;
4241        $retVal =~ s/(^\s+)|(\s+$)//g;
4242        # Return the result.
4243        return $retVal;
4244    }
4245    
4246    =head3 GetSourceObject
4247    
4248        my $source = $erdb->GetSourceObject($entityName);
4249    
4250    Return the object to be used in loading special attributes of the specified entity. The
4251    algorithm for loading special attributes is stored in the C<DataGen> elements of the
4252    XML
4253    
4254  =head2 Internal Utility Methods  =head2 Internal Utility Methods
4255    
4256  =head3 _RelationMap  =head3 _RelationMap
4257    
4258  C<< my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef); >>      my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
4259    
4260  Create the relation map for an SQL query. The relation map is used by B<DBObject>  Create the relation map for an SQL query. The relation map is used by B<ERDBObject>
4261  to determine how to interpret the results of the query.  to determine how to interpret the results of the query.
4262    
4263  =over 4  =over 4
# Line 2626  Line 4274 
4274  =item RETURN  =item RETURN
4275    
4276  Returns a list of 2-tuples. Each tuple consists of an object name as used in the  Returns a list of 2-tuples. Each tuple consists of an object name as used in the
4277  query followed by the actual name of that object. This enables the B<DBObject> to  query followed by the actual name of that object. This enables the B<ERDBObject> to
4278  determine the order of the tables in the query and which object name belongs to each  determine the order of the tables in the query and which object name belongs to each
4279  mapped object name. Most of the time these two values are the same; however, if a  mapped object name. Most of the time these two values are the same; however, if a
4280  relation occurs twice in the query, the relation name in the field list and WHERE  relation occurs twice in the query, the relation name in the field list and WHERE
# Line 2920  Line 4568 
4568  sub _GetStatementHandle {  sub _GetStatementHandle {
4569      # Get the parameters.      # Get the parameters.
4570      my ($self, $command, $params) = @_;      my ($self, $command, $params) = @_;
4571        Confess("Invalid parameter list.") if (! defined($params) || ref($params) ne 'ARRAY');
4572      # Trace the query.      # Trace the query.
4573      Trace("SQL query: $command") if T(SQL => 3);      Trace("SQL query: $command") if T(SQL => 3);
4574      Trace("PARMS: '" . (join "', '", @{$params}) . "'") if (T(SQL => 4) && (@{$params} > 0));      Trace("PARMS: '" . (join "', '", @{$params}) . "'") if (T(SQL => 4) && (@{$params} > 0));
# Line 2928  Line 4577 
4577      # Prepare the command.      # Prepare the command.
4578      my $sth = $dbh->prepare_command($command);      my $sth = $dbh->prepare_command($command);
4579      # Execute it with the parameters bound in.      # Execute it with the parameters bound in.
4580      $sth->execute(@{$params}) || Confess("SELECT error" . $sth->errstr());      $sth->execute(@{$params}) || Confess("SELECT error:  " . $sth->errstr());
4581      # Return the statement handle.      # Return the statement handle.
4582      return $sth;      return $sth;
4583  }  }
# Line 2945  Line 4594 
4594      return Stats->new();      return Stats->new();
4595  }  }
4596    
 =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;  
             }  
         }  
     }  
 }  
   
4597  =head3 _DumpRelation  =head3 _DumpRelation
4598    
4599  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.
4600    
4601  This is an instance method.  This is an instance method.
4602    
# Line 3166  Line 4741 
4741          for my $object (values %{$metadata->{$section}}) {          for my $object (values %{$metadata->{$section}}) {
4742              # Loop through the object's fields.              # Loop through the object's fields.
4743              for my $fieldName (keys %{$object->{Fields}}) {              for my $fieldName (keys %{$object->{Fields}}) {
4744                  # Now we make some initial validations.                  # If this field name is invalid, set the return value to zero
4745                  if ($fieldName =~ /--/) {                  # so we know we encountered an error.
4746                      # Here we have a doubled minus sign.                  if (! ValidateFieldName($fieldName)) {
                     print STDERR "Field name $fieldName has a doubled hyphen.\n";  
                     $retVal = 0;  
                 } elsif ($fieldName !~ /^[A-Za-z]/) {  
                     # Here the field name is missing the initial letter.  
                     print STDERR "Field name $fieldName does not begin with a letter.\n";  
                     $retVal = 0;  
                 } else {  
                     # Strip out the minus signs. Everything remaining must be a letter  
                     # or digit.  
                     my $strippedName = $fieldName;  
                     $strippedName =~ s/-//g;  
                     if ($strippedName !~ /^[A-Za-z0-9]+$/) {  
                         print STDERR "Field name $fieldName contains illegal characters.\n";  
4747                          $retVal = 0;                          $retVal = 0;
4748                      }                      }
4749                  }                  }
4750              }              }
4751          }          }
     }  
4752      # If an error was found, fail.      # If an error was found, fail.
4753      if ($retVal  == 0) {      if ($retVal  == 0) {
4754          Confess("Errors found in field names.");          Confess("Errors found in field names.");
# Line 3245  Line 4806 
4806      # be a null string.      # be a null string.
4807      if ($fileName ne "") {      if ($fileName ne "") {
4808          # Load the relation from the file.          # Load the relation from the file.
4809          $retVal = $self->LoadTable($fileName, $relationName, $rebuild);          $retVal = $self->LoadTable($fileName, $relationName, truncate => $rebuild);
4810      } elsif ($rebuild) {      } elsif ($rebuild) {
4811          # 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.
4812          $self->CreateTable($relationName, 1);          $self->CreateTable($relationName, 1);
# Line 3254  Line 4815 
4815      return $retVal;      return $retVal;
4816  }  }
4817    
4818    
4819  =head3 _LoadMetaData  =head3 _LoadMetaData
4820    
4821        my $metadata = ERDB::_LoadMetaData($filename);
4822    
4823  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.
4824  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
4825  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 4843 
4843  sub _LoadMetaData {  sub _LoadMetaData {
4844      # Get the parameters.      # Get the parameters.
4845      my ($filename) = @_;      my ($filename) = @_;
4846      Trace("Reading Sprout DBD from $filename.") if T(2);      Trace("Reading DBD from $filename.") if T(2);
4847      # 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
4848      # get the exact structure we want.      # get the exact structure we want.
4849      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 $filename.") if T(1);  
4850      # Before we go any farther, we need to validate the field and object names. If an error is found,      # Before we go any farther, we need to validate the field and object names. If an error is found,
4851      # the method below will fail.      # the method below will fail.
4852      _ValidateFieldNames($metadata);      _ValidateFieldNames($metadata);
# Line 3418  Line 4969 
4969              if ($found == 0) {              if ($found == 0) {
4970                  push @{$indexList}, { IndexFields => [ {name => 'id', order => 'ascending'} ] };                  push @{$indexList}, { IndexFields => [ {name => 'id', order => 'ascending'} ] };
4971              }              }
4972              # Now we need to convert the relation's index list to an index table. We begin by creating              # Attach all the indexes to the relation.
4973              # an empty table in the relation structure.              _ProcessIndexes($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++;  
             }  
4974          }          }
4975          # Finally, we add the relation structure to the entity.          # Finally, we add the relation structure to the entity.
4976          $entityStructure->{Relations} = $relationTable;          $entityStructure->{Relations} = $relationTable;
# Line 3442  Line 4984 
4984          _FixupFields($relationshipStructure, $relationshipName, 2, 3);          _FixupFields($relationshipStructure, $relationshipName, 2, 3);
4985          # Format a description for the FROM field.          # Format a description for the FROM field.
4986          my $fromEntity = $relationshipStructure->{from};          my $fromEntity = $relationshipStructure->{from};
4987          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].";
4988          # Get the FROM entity's key type.          # Get the FROM entity's key type.
4989          my $fromType = $entityList->{$fromEntity}->{keyType};          my $fromType = $entityList->{$fromEntity}->{keyType};
4990          # Add the FROM field.          # Add the FROM field.
# Line 3452  Line 4994 
4994                                                      PrettySort => 1});                                                      PrettySort => 1});
4995          # Format a description for the TO field.          # Format a description for the TO field.
4996          my $toEntity = $relationshipStructure->{to};          my $toEntity = $relationshipStructure->{to};
4997          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].";
4998          # Get the TO entity's key type.          # Get the TO entity's key type.
4999          my $toType = $entityList->{$toEntity}->{keyType};          my $toType = $entityList->{$toEntity}->{keyType};
5000          # Add the TO field.          # Add the TO field.
# Line 3464  Line 5006 
5006          my $thisRelation = { Fields => _ReOrderRelationTable($relationshipStructure->{Fields}),          my $thisRelation = { Fields => _ReOrderRelationTable($relationshipStructure->{Fields}),
5007                               Indexes => { } };                               Indexes => { } };
5008          $relationshipStructure->{Relations} = { $relationshipName => $thisRelation };          $relationshipStructure->{Relations} = { $relationshipName => $thisRelation };
5009    
5010            # Add the alternate indexes (if any). This MUST be done before the FROM and
5011            # TO indexes, because it erases the relation's index list.
5012            if (exists $relationshipStructure->{Indexes}) {
5013                _ProcessIndexes($relationshipStructure->{Indexes}, $thisRelation);
5014            }
5015            # Add the relation to the master table.
5016          # Create the FROM and TO indexes.          # Create the FROM and TO indexes.
5017          _CreateRelationshipIndex("From", $relationshipName, $relationshipStructure);          _CreateRelationshipIndex("From", $relationshipName, $relationshipStructure);
5018          _CreateRelationshipIndex("To", $relationshipName, $relationshipStructure);          _CreateRelationshipIndex("To", $relationshipName, $relationshipStructure);
         # Add the relation to the master table.  
5019          $masterRelationTable{$relationshipName} = $thisRelation;          $masterRelationTable{$relationshipName} = $thisRelation;
5020      }      }
5021      # Now store the master relation table in the metadata structure.      # Now store the master relation table in the metadata structure.
# Line 3623  Line 5171 
5171          $newIndex->{Unique} = 'true';          $newIndex->{Unique} = 'true';
5172      }      }
5173      # Add the index to the relation.      # Add the index to the relation.
5174      _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);      _AddIndex("idx$indexKey", $relationStructure, $newIndex);
5175    }
5176    
5177    =head3 _ProcessIndexes
5178    
5179        ERDB::_ProcessIndexes($indexList, $relation);
5180    
5181    Build the data structures for the specified indexes in the specified relation.
5182    
5183    =over 4
5184    
5185    =item indexList
5186    
5187    Reference to a list of indexes. Each index is a hash reference containing an optional
5188    C<Notes> value that describes the index and an C<IndexFields> value that is a reference
5189    to a list of index field structures. An index field structure, in turn, is a reference
5190    to a hash that contains a C<name> attribute for the field name and an C<order>
5191    attribute that specifies either C<ascending> or C<descending>. In this sense the
5192    index list encapsulates the XML C<Indexes> structure in the database definition.
5193    
5194    =item relation
5195    
5196    The structure that describes the current relation. The new index descriptors will
5197    be stored in the structure's C<Indexes> member. Any previous data in the structure
5198    will be lost.
5199    
5200    =back
5201    
5202    =cut
5203    
5204    sub _ProcessIndexes {
5205        # Get the parameters.
5206        my ($indexList, $relation) = @_;
5207        # Now we need to convert the relation's index list to an index table. We begin by creating
5208        # an empty table in the relation structure.
5209        $relation->{Indexes} = { };
5210        # Loop through the indexes.
5211        my $count = 0;
5212        for my $index (@{$indexList}) {
5213            # Add this index to the index table.
5214            _AddIndex("idx$count", $relation, $index);
5215            # Increment the counter so that the next index has a different name.
5216            $count++;
5217        }
5218  }  }
5219    
5220  =head3 _AddIndex  =head3 _AddIndex
# Line 3722  Line 5313 
5313              my $type = $fieldData->{type};              my $type = $fieldData->{type};
5314              # Plug in a relation name if it is needed.              # Plug in a relation name if it is needed.
5315              Tracer::MergeOptions($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} };  
             }  
5316              # Check for searchability.              # Check for searchability.
5317              if ($fieldData->{searchable}) {              if ($fieldData->{searchable}) {
5318                  # Only allow this for a primary relation.                  # Only allow this for a primary relation.
# Line 3736  Line 5322 
5322                      push @textFields, $fieldName;                      push @textFields, $fieldName;
5323                  }                  }
5324              }              }
             # Plug in the defaults for the optional data generation parameters.  
             Tracer::MergeOptions($fieldData->{DataGen}, { testCount => 1, pass => 0 });  
5325              # Add the PrettySortValue.              # Add the PrettySortValue.
5326              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);
5327          }          }
# Line 3969  Line 5553 
5553      return $retVal;      return $retVal;
5554  }  }
5555    
5556  =head2 HTML Documentation Utility Methods  =head2 Documentation Utility Methods
5557    
5558  =head3 _ComputeRelationshipSentence  =head3 _ComputeRelationshipSentence
5559    
# Line 4001  Line 5585 
5585      # Get the parameters.      # Get the parameters.
5586      my ($relationshipName, $relationshipStructure) = @_;      my ($relationshipName, $relationshipStructure) = @_;
5587      # Format the relationship sentence.      # Format the relationship sentence.
5588      my $result = "$relationshipStructure->{from} <b>$relationshipName</b> $relationshipStructure->{to}";      my $result = "$relationshipStructure->{from} $relationshipName $relationshipStructure->{to}";
5589      # Compute the arity.      # Compute the arity.
5590      my $arityCode = $relationshipStructure->{arity};      my $arityCode = $relationshipStructure->{arity};
5591      my $arity = $ArityTable{$arityCode};      my $arity = $ArityTable{$arityCode};
# Line 4046  Line 5630 
5630      return $result;      return $result;
5631  }  }
5632    
5633    =head3 _WikiRelationTable
5634    
5635    Generate the Wiki text for a particular relation. The relation's data will be formatted as a
5636    table with three columns-- the field name, the field type, and the field description.
5637    
5638    This is a static method.
5639    
5640    =over 4
5641    
5642    =item relationName
5643    
5644    Name of the relation being formatted.
5645    
5646    =item relationData
5647    
5648    Hash containing the relation's fields and indexes.
5649    
5650    =item RETURN
5651    
5652    Returns a Wiki string that can be used to display the relation name and all of its fields.
5653    
5654    =back
5655    
5656    =cut
5657    
5658    sub _WikiRelationTable {
5659        # Get the parameters.
5660        my ($relationName, $relationData) = @_;
5661        # We'll create a list of lists in here, then call WikiTools::Table to
5662        # convert it into a table.
5663        my @rows = ();
5664        # Push in the header row.
5665        push @rows, [qw(Field Type Description)];
5666        # Loop through the fields.
5667        for my $field (@{$relationData->{Fields}}) {
5668            # Create this field's row. We always have a name and type.
5669            my @row = ($field->{name}, $field->{type});
5670            # If we have a description, add it as the third column.
5671            if (exists $field->{Notes}) {
5672                push @row, WikiNote($field->{Notes}->{content});
5673            }
5674            # Push this row onto the table list.
5675            push @rows, \@row;
5676        }
5677        # Store the rows as a Wiki table with a level-4 heading.
5678        my $retVal = join("\n\n", WikiTools::Heading(4, "$relationName Table"),
5679                          WikiTools::Table(@rows));
5680        # Now we show the relation's indexes. These are formatted as another
5681        # table.
5682        @rows = ();
5683        # Push in the header row.
5684        push @rows, [qw(Index Unique Fields Notes)];
5685        # Get the index hash.
5686        my $indexTable = $relationData->{Indexes};
5687        # Loop through the indexes. For an entity, there is always at least one index.
5688        # For a relationship, there are at least two. The upshot is we don't need to
5689        # worry about accidentally generating a frivolous table here.
5690        for my $indexName (sort keys %$indexTable) {
5691            my $indexData = $indexTable->{$indexName};
5692            # Determine whether or not the index is unique.
5693            my $unique = ((exists $indexData->{Unique} && $indexData->{Unique} eq "true") ?
5694                          "yes" : "");
5695            # Get the field list.
5696            my $fields = join(', ', @{$indexData->{IndexFields}});
5697            # Get the note text.
5698            my $description = "";
5699            if (my $note = $indexData->{Notes}) {
5700                $description = WikiNote($note->{content});
5701            }
5702            # Format this row.
5703            my @row = ($indexName, $unique, $fields, $description);
5704            push @rows, \@row;
5705        }
5706        # Add the index list to the result.
5707        $retVal .= "\n\n" . WikiTools::Table(@rows);
5708    }
5709    
5710  =head3 _ShowRelationTable  =head3 _ShowRelationTable
5711    
5712  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 5757 
5757          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";
5758          # Add any note text.          # Add any note text.
5759          if (my $note = $indexData->{Notes}) {          if (my $note = $indexData->{Notes}) {
5760              $htmlString .= "<li>" . _HTMLNote($note->{content}) . "</li>\n";              $htmlString .= "<li>" . HTMLNote($note->{content}) . "</li>\n";
5761          }          }
5762          # Add the fiield list.          # Add the fiield list.
5763          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";
# Line 4162  Line 5823 
5823      # Compute the number of columns.      # Compute the number of columns.
5824      my $colCount = @colNames;      my $colCount = @colNames;
5825      # Generate the title row.      # Generate the title row.
5826      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";
5827      # Loop through the columns, adding the column header rows.      # Loop through the columns, adding the column header rows.
5828      $htmlString .= "<tr>";      $htmlString .= "<tr>";
5829      for my $colName (@colNames) {      for my $colName (@colNames) {
# Line 4181  Line 5842 
5842  =cut  =cut
5843    
5844  sub _CloseTable {  sub _CloseTable {
5845      return "</table></p>\n";      return "</table>\n";
5846  }  }
5847    
5848  =head3 _ShowField  =head3 _ShowField
# Line 4211  Line 5872 
5872      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>";
5873      # If we have content, add it as a third column.      # If we have content, add it as a third column.
5874      if (exists $fieldData->{Notes}) {      if (exists $fieldData->{Notes}) {
5875          $htmlString .= "<td>" . _HTMLNote($fieldData->{Notes}->{content}) . "</td>";          $htmlString .= "<td>" . HTMLNote($fieldData->{Notes}->{content}) . "</td>";
5876      }      }
5877      # Close off the row.      # Close off the row.
5878      $htmlString .= "</tr>\n";      $htmlString .= "</tr>\n";
# Line 4219  Line 5880 
5880      return $htmlString;      return $htmlString;
5881  }  }
5882    
5883  =head3 _HTMLNote  =head3 _ObjectNotes
   
 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  
5884    
5885  C<< my $string = StringGen($pattern1, $pattern2, ... $patternN); >>      my @noteParagraphs = _ObjectNotes($objectData);
5886    
5887  Returns a random string derived from a randomly-chosen format pattern. The pattern  Return a list of the notes and asides for an entity or relationship in
5888  can either be a number (indicating the number of characters desired, or the letter  Wiki format.
 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.  
5889    
5890  =over 4  =over 4
5891    
5892  =item pattern1, pattern2, ... patternN  =item objectData
5893    
5894  List of patterns to be used to generate string values.  The metadata for the desired entity or relationship.
5895    
5896  =item RETURN  =item RETURN
5897    
5898  A single string generated from a pattern.  Returns a list of text paragraphs in Wiki markup form.
5899    
5900  =back  =back
5901    
5902  =cut  =cut
5903    
5904  sub StringGen {  sub _ObjectNotes {
5905      # Get the parameters.      # Get the parameters.
5906      my @patterns = @_;      my ($objectData) = @_;
     # Choose the appropriate pattern.  
     my $chosenPattern = RandParam(@patterns);  
5907      # Declare the return variable.      # Declare the return variable.
5908      my $retVal = "";      my @retVal;
5909      # Determine whether this is a count or a picture pattern.      # Loop through the types of notes.
5910      if ($chosenPattern =~ m/^\d+/) {      for my $noteType (qw(Notes Asides)) {
5911          # Here we have a count. Get the string of source characters.          my $text = $objectData->{$noteType};
5912          my $letterString = $PictureTable{'X'};          if ($text) {
5913          my $stringLen = length $letterString;              push @retVal, "", WikiNote($text->{content});
         # 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;  
5914      }      }
     # Return the string formed.  
     return $retVal;  
5915  }  }
   
 =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;  
5916      # Return the result.      # 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.  
5917      return @retVal;      return @retVal;
5918  }  }
5919    

Legend:
Removed from v.1.70  
changed lines
  Added in v.1.102

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3