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

Diff of /Sprout/ERDB.pm

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

revision 1.69, Fri Sep 29 15:06:17 2006 UTC revision 1.97, Wed May 7 23:08:19 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 190  Line 191 
191    
192  Name of the field. The field name should contain only letters, digits, and hyphens (C<->),  Name of the field. The field name should contain only letters, digits, and hyphens (C<->),
193  and the first character should be a letter. Most underlying databases are case-insensitive  and the first character should be a letter. Most underlying databases are case-insensitive
194  with the respect to field names, so a best practice is to use lower-case letters only.  with the respect to field names, so a best practice is to use lower-case letters only. Finally,
195    the name C<search-relevance> has special meaning for full-text searches and should not be
196    used as a field name.
197    
198  =item type  =item type
199    
# Line 209  Line 212 
212  entity, the fields without a relation attribute are said to belong to the  entity, the fields without a relation attribute are said to belong to the
213  I<primary relation>. This relation has the same name as the entity itself.  I<primary relation>. This relation has the same name as the entity itself.
214    
215    =item searchable
216    
217    If specified, then the field is a candidate for full-text searching. A single full-text
218    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.
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 242  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 286  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 320  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 349  Line 384 
384                     'MM' => 'many-to-many'                     'MM' => 'many-to-many'
385                   );                   );
386    
387  # Table for interpreting string patterns.  # Options for XML input and output.
388    
389    my %XmlOptions = (GroupTags =>  { Relationships => 'Relationship',
390                                      Entities => 'Entity',
391                                      Fields => 'Field',
392                                      Indexes => 'Index',
393                                      IndexFields => 'IndexField'
394                                    },
395                      KeyAttr =>    { Relationship => 'name',
396                                      Entity => 'name',
397                                      Field => 'name'
398                                    },
399                      SuppressEmpty => 1,
400                     );
401    
402  my %PictureTable = ( 'A' => "abcdefghijklmnopqrstuvwxyz",  my %XmlInOpts  = (
403                       '9' => "0123456789",                    ForceArray => ['Field', 'Index', 'IndexField', 'Relationship', 'Entity'],
404                       'X' => "abcdefghijklmnopqrstuvwxyz0123456789",                    ForceContent => 1,
405                       'V' => "aeiou",                    NormalizeSpace => 2,
406                       'K' => "bcdfghjklmnoprstvwxyz"                   );
407    my %XmlOutOpts = (
408                      RootName => 'Database',
409                      XMLDecl => 1,
410                     );                     );
411    
412  =head2 Public Methods  =head2 Public Methods
413    
414  =head3 new  =head3 new
415    
416  C<< my $database = ERDB->new($dbh, $metaFileName); >>      my $database = ERDB->new($dbh, $metaFileName);
417    
418  Create a new ERDB object.  Create a new ERDB object.
419    
# Line 382  Line 433 
433    
434  sub new {  sub new {
435      # Get the parameters.      # Get the parameters.
436      my ($class, $dbh, $metaFileName, $options) = @_;      my ($class, $dbh, $metaFileName, %options) = @_;
437      # Load the meta-data.      # Load the meta-data.
438      my $metaData = _LoadMetaData($metaFileName);      my $metaData = _LoadMetaData($metaFileName);
439      # Create the object.      # Create the object.
# Line 396  Line 447 
447    
448  =head3 ShowMetaData  =head3 ShowMetaData
449    
450  C<< $erdb->ShowMetaData($fileName); >>      $erdb->ShowMetaData($fileName);
451    
452  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
453  the data to be loaded into the relations.  the data to be loaded into the relations.
# Line 437  Line 488 
488    
489  =head3 DisplayMetaData  =head3 DisplayMetaData
490    
491  C<< my $html = $erdb->DisplayMetaData(); >>      my $html = $erdb->DisplayMetaData();
492    
493  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
494  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 498  Line 549 
549          my $entityData = $entityList->{$key};          my $entityData = $entityList->{$key};
550          # If there's descriptive text, display it.          # If there's descriptive text, display it.
551          if (my $notes = $entityData->{Notes}) {          if (my $notes = $entityData->{Notes}) {
552              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
553          }          }
554          # 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.
555            my $relCount = keys %{$relationshipList};
556            if ($relCount > 0) {
557                # First, we set up the relationship subsection.
558          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
559          # Loop through the relationships.          # Loop through the relationships.
560          for my $relationship (sort keys %{$relationshipList}) {          for my $relationship (sort keys %{$relationshipList}) {
# Line 516  Line 570 
570          }          }
571          # Close off the relationship list.          # Close off the relationship list.
572          $retVal .= "</ul>\n";          $retVal .= "</ul>\n";
573            }
574          # Get the entity's relations.          # Get the entity's relations.
575          my $relationList = $entityData->{Relations};          my $relationList = $entityData->{Relations};
576          # Create a header for the relation subsection.          # Create a header for the relation subsection.
# Line 555  Line 610 
610          $retVal .= "</p>\n";          $retVal .= "</p>\n";
611          # If there are notes on this relationship, display them.          # If there are notes on this relationship, display them.
612          if (my $notes = $relationshipStructure->{Notes}) {          if (my $notes = $relationshipStructure->{Notes}) {
613              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
614          }          }
615          # Generate the relationship's relation table.          # Generate the relationship's relation table.
616          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
# Line 589  Line 644 
644    
645  =head3 DumpMetaData  =head3 DumpMetaData
646    
647  C<< $erdb->DumpMetaData(); >>      $erdb->DumpMetaData();
648    
649  Return a dump of the metadata structure.  Return a dump of the metadata structure.
650    
# Line 602  Line 657 
657      return Data::Dumper::Dumper($self->{_metaData});      return Data::Dumper::Dumper($self->{_metaData});
658  }  }
659    
660    =head3 GenerateWikiData
661    
662        my @wikiLines = $erdb->GenerateWikiData();
663    
664    Build a description of the database for the wiki. The database will be
665    organized into a single page, with sections for each entity and relationship.
666    The return value is a list of text lines.
667    
668    =cut
669    
670    sub GenerateWikiData {
671        # Get the parameters.
672        my ($self) = @_;
673        # We'll build the wiki text in here.
674        my @retVal = ();
675        # Get the metadata object.
676        my $metadata = $self->{_metaData};
677        # Get the title string. This will become the page name.
678        my $title = $metadata->{Title}->{content};
679        # Get the entity and relationship lists.
680        my $entityList = $metadata->{Entities};
681        my $relationshipList = $metadata->{Relationships};
682        # Start with the introductory text.
683        push @retVal, WikiTools::Heading(2, "Introduction");
684        if (my $notes = $metadata->{Notes}) {
685            push @retVal, WikiNote($notes->{content});
686        }
687        # Start the entity section.
688        push @retVal, WikiTools::Heading(2, "Entities");
689        # Loop through the entities. Note that unlike the situation with HTML, we
690        # don't need to generate the table of contents manually, just the data
691        # itself.
692        for my $key (sort keys %$entityList) {
693            # Create a header for this entity.
694            push @retVal, "", WikiTools::Heading(3, $key);
695            # Get the entity data.
696            my $entityData = $entityList->{$key};
697            # Plant the notes here, if there are any.
698            if (my $notes = $entityData->{Notes}) {
699                push @retVal, "", WikiNote($notes->{content});
700            }
701            # Get the entity's relations.
702            my $relationList = $entityData->{Relations};
703            # Loop through the relations, displaying them.
704            for my $relation (sort keys %{$relationList}) {
705                my $wikiString = _WikiRelationTable($relation, $relationList->{$relation});
706                push @retVal, $wikiString;
707            }
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        }
725        # Now the entities are documented. Next we do the relationships.
726        push @retVal, WikiTools::Heading(2, "Relationships");
727        for my $key (sort keys %$relationshipList) {
728            my $relationshipData = $relationshipList->{$key};
729            # Create the relationship heading.
730            push @retVal, WikiTools::Heading(3, $key);
731            # Describe the relationship arity. Note there's a bit of trickiness involving recursive
732            # many-to-many relationships. In a normal many-to-many we use two sentences to describe
733            # the arity (one for each direction). This is a bad idea for a recursive relationship,
734            # since both sentences will say the same thing.
735            my $arity = $relationshipData->{arity};
736            my $fromEntity = $relationshipData->{from};
737            my $toEntity = $relationshipData->{to};
738            my @listElements = ();
739            my $boldCode = WikiTools::BoldCode();
740            if ($arity eq "11") {
741                push @listElements, "Each $boldCode$fromEntity$boldCode relates to at most one $boldCode$toEntity$boldCode.";
742            } else {
743                push @listElements, "Each $boldCode$fromEntity$boldCode relates to multiple $boldCode${toEntity}s$boldCode.\n";
744                if ($arity eq "MM" && $fromEntity ne $toEntity) {
745                    push @listElements, "Each $boldCode$toEntity$boldCode relates to multiple $boldCode${fromEntity}s$boldCode.\n";
746                }
747            }
748            push @retVal, WikiTools::List(@listElements);
749            # Plant the notes here, if there are any.
750            if (my $notes = $relationshipData->{Notes}) {
751                push @retVal, "", WikiNote($notes->{content});
752            }
753            # Finally, the relationship table.
754            my $wikiString = _WikiRelationTable($key, $relationshipData->{Relations}->{$key});
755            push @retVal, $wikiString;
756        }
757        # All done. Return the lines.
758        return @retVal;
759    }
760    
761    
762    =head3 CreatePPO
763    
764        ERDB::CreatePPO($erdbXMLFile, $ppoXMLFile);
765    
766    Create a PPO XML file from an ERDB data definition XML file. At the
767    current time, the PPO XML file can be used to create a database with
768    similar functionality. Eventually, the PPO will be able to use the
769    created XML to access the live ERDB database.
770    
771    =over 4
772    
773    =item erdbXMLFile
774    
775    Name of the XML data definition file for the ERDB database. This
776    file must exist.
777    
778    =item ppoXMLFile
779    
780    Output file for the PPO XML definition. If this file exists, it
781    will be overwritten.
782    
783    =back
784    
785    =cut
786    
787    sub CreatePPO {
788        # Get the parameters.
789        my ($erdbXMLFile, $ppoXMLFile) = @_;
790        # First, we want to slurp in the ERDB XML file in its raw form.
791        my $xml = ReadMetaXML($erdbXMLFile);
792        # Create a variable to hold all of the objects in the PPO project.
793        my @objects = ();
794        # Get the relationship hash.
795        my $relationships = $xml->{Relationships};
796        # Loop through the entities.
797        my $entities = $xml->{Entities};
798        for my $entityName (keys %{$entities}) {
799            # Get the entity's data structures.
800            my $entityObject = $entities->{$entityName};
801            # We put the object's fields in here, according to their type.
802            my (@object_refs, @scalars, @indexes, @arrays);
803            # Create the ID field for the entity. We get the key type from the
804            # entity object and compute the corresponding SQL type.
805            my $type = $TypeTable{$entityObject->{keyType}}->{sqlType};
806            push @scalars, { label => 'id', type => $type };
807            # Loop through the entity fields.
808            for my $fieldName ( keys %{$entityObject->{Fields}} ) {
809                # Get the field object.
810                my $fieldObject = $entityObject->{Fields}->{$fieldName};
811                # Convert it to a scalar tag.
812                my $scalar = _CreatePPOField($fieldName, $fieldObject);
813                # If we have a relation, this field is stored in an array.
814                # otherwise, it is a scalar. The array tag has scalars
815                # stored as an XML array. In ERDB, there is only ever one,
816                # but PPO can have more.
817                my $relation = $fieldObject->{relation};
818                if ($relation) {
819                    push @arrays, { scalar => [$scalar] };
820                } else {
821                    push @scalars, $scalar;
822                }
823            }
824            # Loop through the relationships. If this entity is the to-entity
825            # on a relationship of 1M arity, then it is implemented as a PPO
826            # object reference.
827            for my $relationshipName (keys %{$relationships}) {
828                # Get the relationship data.
829                my $relationshipData = $relationships->{$relationshipName};
830                # If we have a from for this entity and an arity of 1M, we
831                # have an object reference.
832                if ($relationshipData->{to} eq $entityName &&
833                    $relationshipData->{arity} eq '1M') {
834                    # Build the object reference tag.
835                    push @object_refs, { label => $relationshipName,
836                                         type => $relationshipData->{from} };
837                }
838            }
839            # Create the indexes.
840            my $indexList = $entityObject->{Indexes};
841            push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
842            # Build the object XML tree.
843            my $object = { label => $entityName,
844                           object_ref => \@object_refs,
845                           scalar => \@scalars,
846                           index => \@indexes,
847                           array => \@arrays
848                          };
849            # Push the object onto the objects list.
850            push @objects, $object;
851        }
852        # Loop through the relationships, searching for MMs. The 1Ms were
853        # already handled by the entity search above.
854        for my $relationshipName (keys %{$relationships}) {
855            # Get this relationship's object.
856            my $relationshipObject = $relationships->{$relationshipName};
857            # Only proceed if it's many-to-many.
858            if ($relationshipObject->{arity} eq 'MM') {
859                # Create the tag lists for the relationship object.
860                my (@object_refs, @scalars, @indexes);
861                # The relationship will be created as an object with object
862                # references for its links to the participating entities.
863                my %links = ( from_link => $relationshipObject->{from},
864                              to_link => $relationshipObject->{to} );
865                for my $link (keys %links) {
866                    # Create an object_ref tag for this piece of the
867                    # relationship (from or to).
868                    my $object_ref = { label => $link,
869                                       type => $links{$link} };
870                    push @object_refs, $object_ref;
871                }
872                # Loop through the intersection data fields, creating scalar tags.
873                # There are no fancy array tags in a relationship.
874                for my $fieldName (keys %{$relationshipObject->{Fields}}) {
875                    my $fieldObject = $relationshipObject->{Fields}->{$fieldName};
876                    push @scalars, _CreatePPOField($fieldName, $fieldObject);
877                }
878                # Finally, the indexes: currently we cannot support the to-index and
879                # from-index in PPO, so we just process the alternate indexes.
880                my $indexList = $relationshipObject->{Indexes};
881                push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
882                # Wrap up all the stuff about this relationship.
883                my $object = { label => $relationshipName,
884                               scalar => \@scalars,
885                               object_ref => \@object_refs,
886                               index => \@indexes
887                             };
888                # Push it into the object list.
889                push @objects, $object;
890            }
891        }
892        # Compute a title.
893        my $title;
894        if ($erdbXMLFile =~ /(\/|^)([^\/]+)DBD\.xml/) {
895            # Here we have a standard file name we can use for a title.
896            $title = $2;
897        } else {
898            # Here the file name is non-standard, so we carve up the
899            # database title.
900            $title = $xml->{Title}->{content};
901            $title =~ s/\s\.,//g;
902        }
903        # Wrap up the XML as a project.
904        my $ppoXML = { project => { label => $title,
905                                    object => \@objects }};
906        # Write out the results.
907        my $ppoString = XML::Simple::XMLout($ppoXML,
908                                            AttrIndent => 1,
909                                            KeepRoot => 1);
910        Tracer::PutFile($ppoXMLFile, [ $ppoString ]);
911    }
912    
913    =head3 FindIndexForEntity
914    
915        my $indexFound = ERDB::FindIndexForEntity($xml, $entityName, $attributeName);
916    
917    This method locates the entry in an entity's index list that begins with the
918    specified attribute name. If the entity has no index list, one will be
919    created. This method works on raw XML, not a live ERDB object.
920    
921    =over 4
922    
923    =item xml
924    
925    The raw XML structure defining the database.
926    
927    =item entityName
928    
929    The name of the relevant entity.
930    
931    =item attributeName
932    
933    The name of the attribute relevant to the search.
934    
935    =item RETURN
936    
937    The numerical index in the index list of the index entry for the specified entity and
938    attribute, or C<undef> if no such index exists.
939    
940    =back
941    
942    =cut
943    
944    sub FindIndexForEntity {
945        # Get the parameters.
946        my ($xml, $entityName, $attributeName) = @_;
947        # Declare the return variable.
948        my $retVal;
949        # Get the named entity.
950        my $entityData = $xml->{Entities}->{$entityName};
951        if (! $entityData) {
952            Confess("Entity $entityName not found in DBD structure.");
953        } else {
954            # Insure it has an index list.
955            if (! exists $entityData->{Indexes}) {
956                $entityData->{Indexes} = [];
957            } else {
958                # Search for the desired index.
959                my $indexList = $entityData->{Indexes};
960                my $n = scalar @{$indexList};
961                Trace("Searching $n indexes in index list for $entityName.") if T(2);
962                # We use an indexed FOR here because we're returning an
963                # index number instead of an object. We do THAT so we can
964                # delete the index from the list if needed.
965                for (my $i = 0; $i < $n && !defined($retVal); $i++) {
966                    my $index = $indexList->[$i];
967                    my $fields = $index->{IndexFields};
968                    # Technically this IF should be safe (that is, we are guaranteed
969                    # the existence of a "$fields->[0]"), because when we load the XML
970                    # we have SuppressEmpty specified.
971                    if ($fields->[0]->{name} eq $attributeName) {
972                        $retVal = $i;
973                    }
974                }
975            }
976        }
977        Trace("Index for $attributeName of $entityName found at position $retVal.") if defined($retVal) && T(3);
978        Trace("Index for $attributeName not found in $entityName.") if !defined($retVal) && T(3);
979        # Return the result.
980        return $retVal;
981    }
982    
983  =head3 CreateTables  =head3 CreateTables
984    
985  C<< $erdb->CreateTables(); >>      $erdb->CreateTables();
986    
987  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
988  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 621  Line 999 
999      # Loop through the relations.      # Loop through the relations.
1000      for my $relationName (@relNames) {      for my $relationName (@relNames) {
1001          # Create a table for this relation.          # Create a table for this relation.
1002          $self->CreateTable($relationName);          $self->CreateTable($relationName, 1);
1003          Trace("Relation $relationName created.") if T(2);          Trace("Relation $relationName created.") if T(2);
1004      }      }
1005  }  }
1006    
1007  =head3 CreateTable  =head3 CreateTable
1008    
1009  C<< $erdb->CreateTable($tableName, $indexFlag, $estimatedRows); >>      $erdb->CreateTable($tableName, $indexFlag, $estimatedRows);
1010    
1011  Create the table for a relation and optionally create its indexes.  Create the table for a relation and optionally create its indexes.
1012    
# Line 684  Line 1062 
1062      my $estimation = undef;      my $estimation = undef;
1063      if ($estimatedRows) {      if ($estimatedRows) {
1064          $estimation = [$self->EstimateRowSize($relationName), $estimatedRows];          $estimation = [$self->EstimateRowSize($relationName), $estimatedRows];
1065            Trace("$estimation->[1] rows of $estimation->[0] bytes each.") if T(3);
1066      }      }
1067      # Create the table.      # Create the table.
1068      Trace("Creating table $relationName: $fieldThing") if T(2);      Trace("Creating table $relationName: $fieldThing") if T(2);
1069      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);
1070      Trace("Relation $relationName created in database.") if T(2);      Trace("Relation $relationName created in database.") if T(2);
1071      # If we want to build the indexes, we do it here.      # If we want to build the indexes, we do it here. Note that the full-text search
1072        # index will not be built until the table has been loaded.
1073      if ($indexFlag) {      if ($indexFlag) {
1074          $self->CreateIndex($relationName);          $self->CreateIndex($relationName);
1075      }      }
# Line 697  Line 1077 
1077    
1078  =head3 VerifyFields  =head3 VerifyFields
1079    
1080  C<< my $count = $erdb->VerifyFields($relName, \@fieldList); >>      my $count = $erdb->VerifyFields($relName, \@fieldList);
1081    
1082  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
1083  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 740  Line 1120 
1120              my $oldString = $fieldList->[$i];              my $oldString = $fieldList->[$i];
1121              if (length($oldString) > $maxLen) {              if (length($oldString) > $maxLen) {
1122                  # Here it's too big, so we truncate it.                  # Here it's too big, so we truncate it.
1123                  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);
1124                  $fieldList->[$i] = substr $oldString, 0, $maxLen;                  $fieldList->[$i] = substr $oldString, 0, $maxLen;
1125                  $retVal++;                  $retVal++;
1126              }              }
# Line 752  Line 1132 
1132    
1133  =head3 DigestFields  =head3 DigestFields
1134    
1135  C<< $erdb->DigestFields($relName, $fieldList); >>      $erdb->DigestFields($relName, $fieldList);
1136    
1137  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
1138  specified relation.  specified relation.
# Line 792  Line 1172 
1172    
1173  =head3 DigestKey  =head3 DigestKey
1174    
1175  C<< my $digested = $erdb->DigestKey($keyValue); >>      my $digested = $erdb->DigestKey($keyValue);
1176    
1177  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
1178  key-based search into a table with key-type hash-string.  key-based search into a table with key-type hash-string.
# Line 825  Line 1205 
1205    
1206  =head3 CreateIndex  =head3 CreateIndex
1207    
1208  C<< $erdb->CreateIndex($relationName); >>      $erdb->CreateIndex($relationName);
1209    
1210  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
1211  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 846  Line 1226 
1226      for my $indexName (keys %{$indexHash}) {      for my $indexName (keys %{$indexHash}) {
1227          my $indexData = $indexHash->{$indexName};          my $indexData = $indexHash->{$indexName};
1228          # Get the index's field list.          # Get the index's field list.
1229          my @fieldList = _FixNames(@{$indexData->{IndexFields}});          my @rawFields = @{$indexData->{IndexFields}};
1230            # Get a hash of the relation's field types.
1231            my %types = map { $_->{name} => $_->{type} } @{$relationData->{Fields}};
1232            # We need to check for text fields so we can append a length limitation for them. To do
1233            # that, we need the relation's field list.
1234            my $relFields = $relationData->{Fields};
1235            for (my $i = 0; $i <= $#rawFields; $i++) {
1236                # Get the field type.
1237                my $field = $rawFields[$i];
1238                my $type = $types{$field};
1239                # Ask if it requires using prefix notation for the index.
1240                my $mod = $TypeTable{$type}->{indexMod};
1241                Trace("Field $field ($i) in $relationName has type $type and indexMod $mod.") if T(3);
1242                if ($mod) {
1243                    # Append the prefix length to the field name,
1244                    $rawFields[$i] .= "($mod)";
1245                }
1246            }
1247            my @fieldList = _FixNames(@rawFields);
1248          my $flds = join(', ', @fieldList);          my $flds = join(', ', @fieldList);
1249          # Get the index's uniqueness flag.          # Get the index's uniqueness flag.
1250          my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
1251          # Create the index.          # Create the index.
1252          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
1253                                      flds => $flds, unique => $unique);                                      flds => $flds, kind => $unique);
1254          if ($rv) {          if ($rv) {
1255              Trace("Index created: $indexName for $relationName ($flds)") if T(1);              Trace("Index created: $indexName for $relationName ($flds)") if T(1);
1256          } else {          } else {
# Line 861  Line 1259 
1259      }      }
1260  }  }
1261    
1262    =head3 GetSecondaryFields
1263    
1264        my %fieldTuples = $erdb->GetSecondaryFields($entityName);
1265    
1266    This method will return a list of the name and type of each of the secondary
1267    fields for a specified entity. Secondary fields are stored in two-column tables
1268    in addition to the primary entity table. This enables the field to have no value
1269    or to have multiple values.
1270    
1271    =over 4
1272    
1273    =item entityName
1274    
1275    Name of the entity whose secondary fields are desired.
1276    
1277    =item RETURN
1278    
1279    Returns a hash mapping the field names to their field types.
1280    
1281    =back
1282    
1283    =cut
1284    
1285    sub GetSecondaryFields {
1286        # Get the parameters.
1287        my ($self, $entityName) = @_;
1288        # Declare the return variable.
1289        my %retVal = ();
1290        # Look for the entity.
1291        my $table = $self->GetFieldTable($entityName);
1292        # Loop through the fields, pulling out the secondaries.
1293        for my $field (sort keys %{$table}) {
1294            if ($table->{$field}->{relation} ne $entityName) {
1295                # Here we have a secondary field.
1296                $retVal{$field} = $table->{$field}->{type};
1297            }
1298        }
1299        # Return the result.
1300        return %retVal;
1301    }
1302    
1303    =head3 GetFieldRelationName
1304    
1305        my $name = $erdb->GetFieldRelationName($objectName, $fieldName);
1306    
1307    Return the name of the relation containing a specified field.
1308    
1309    =over 4
1310    
1311    =item objectName
1312    
1313    Name of the entity or relationship containing the field.
1314    
1315    =item fieldName
1316    
1317    Name of the relevant field in that entity or relationship.
1318    
1319    =item RETURN
1320    
1321    Returns the name of the database relation containing the field, or C<undef> if
1322    the field does not exist.
1323    
1324    =back
1325    
1326    =cut
1327    
1328    sub GetFieldRelationName {
1329        # Get the parameters.
1330        my ($self, $objectName, $fieldName) = @_;
1331        # Declare the return variable.
1332        my $retVal;
1333        # Get the object field table.
1334        my $table = $self->GetFieldTable($objectName);
1335        # Only proceed if the field exists.
1336        if (exists $table->{$fieldName}) {
1337            # Determine the name of the relation that contains this field.
1338            $retVal = $table->{$fieldName}->{relation};
1339        }
1340        # Return the result.
1341        return $retVal;
1342    }
1343    
1344    =head3 DeleteValue
1345    
1346        my $numDeleted = $erdb->DeleteValue($entityName, $id, $fieldName, $fieldValue);
1347    
1348    Delete secondary field values from the database. This method can be used to delete all
1349    values of a specified field for a particular entity instance, or only a single value.
1350    
1351    Secondary fields are stored in two-column relations separate from an entity's primary
1352    table, and as a result a secondary field can legitimately have no value or multiple
1353    values. Therefore, it makes sense to talk about deleting secondary fields where it
1354    would not make sense for primary fields.
1355    
1356    =over 4
1357    
1358    =item entityName
1359    
1360    Name of the entity from which the fields are to be deleted.
1361    
1362    =item id
1363    
1364    ID of the entity instance to be processed. If the instance is not found, this
1365    method will have no effect. If C<undef> is specified, all values for all of
1366    the entity instances will be deleted.
1367    
1368    =item fieldName
1369    
1370    Name of the field whose values are to be deleted.
1371    
1372    =item fieldValue (optional)
1373    
1374    Value to be deleted. If not specified, then all values of the specified field
1375    will be deleted for the entity instance. If specified, then only the values which
1376    match this parameter will be deleted.
1377    
1378    =item RETURN
1379    
1380    Returns the number of rows deleted.
1381    
1382    =back
1383    
1384    =cut
1385    
1386    sub DeleteValue {
1387        # Get the parameters.
1388        my ($self, $entityName, $id, $fieldName, $fieldValue) = @_;
1389        # Declare the return value.
1390        my $retVal = 0;
1391        # We need to set up an SQL command to do the deletion. First, we
1392        # find the name of the field's relation.
1393        my $table = $self->GetFieldTable($entityName);
1394        my $field = $table->{$fieldName};
1395        my $relation = $field->{relation};
1396        # Make sure this is a secondary field.
1397        if ($relation eq $entityName) {
1398            Confess("Cannot delete values of $fieldName for $entityName.");
1399        } else {
1400            # Set up the SQL command to delete all values.
1401            my $sql = "DELETE FROM $relation";
1402            # Build the filter.
1403            my @filters = ();
1404            my @parms = ();
1405            # Check for a filter by ID.
1406            if (defined $id) {
1407                push @filters, "id = ?";
1408                push @parms, $id;
1409            }
1410            # Check for a filter by value.
1411            if (defined $fieldValue) {
1412                push @filters, "$fieldName = ?";
1413                push @parms, $fieldValue;
1414            }
1415            # Append the filters to the command.
1416            if (@filters) {
1417                $sql .= " WHERE " . join(" AND ", @filters);
1418            }
1419            # Execute the command.
1420            my $dbh = $self->{_dbh};
1421            $retVal = $dbh->SQL($sql, 0, @parms);
1422        }
1423        # Return the result.
1424        return $retVal;
1425    }
1426    
1427  =head3 LoadTables  =head3 LoadTables
1428    
1429  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>      my $stats = $erdb->LoadTables($directoryName, $rebuild);
1430    
1431  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
1432  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 923  Line 1486 
1486    
1487  =head3 GetTableNames  =head3 GetTableNames
1488    
1489  C<< my @names = $erdb->GetTableNames; >>      my @names = $erdb->GetTableNames;
1490    
1491  Return a list of the relations required to implement this database.  Return a list of the relations required to implement this database.
1492    
# Line 940  Line 1503 
1503    
1504  =head3 GetEntityTypes  =head3 GetEntityTypes
1505    
1506  C<< my @names = $erdb->GetEntityTypes; >>      my @names = $erdb->GetEntityTypes;
1507    
1508  Return a list of the entity type names.  Return a list of the entity type names.
1509    
# Line 955  Line 1518 
1518      return sort keys %{$entityList};      return sort keys %{$entityList};
1519  }  }
1520    
1521    =head3 GetDataTypes
1522    
1523        my %types = ERDB::GetDataTypes();
1524    
1525    Return a table of ERDB data types. The table returned is a hash of hashes.
1526    The keys of the big hash are the datatypes. Each smaller hash has several
1527    values used to manage the data. The most interesting is the SQL type (key
1528    C<sqlType>) and the descriptive node (key C<notes>).
1529    
1530    Note that changing the values in the smaller hashes will seriously break
1531    things, so this data should be treated as read-only.
1532    
1533    =cut
1534    
1535    sub GetDataTypes {
1536        return %TypeTable;
1537    }
1538    
1539    
1540  =head3 IsEntity  =head3 IsEntity
1541    
1542  C<< my $flag = $erdb->IsEntity($entityName); >>      my $flag = $erdb->IsEntity($entityName);
1543    
1544  Return TRUE if the parameter is an entity name, else FALSE.  Return TRUE if the parameter is an entity name, else FALSE.
1545    
# Line 984  Line 1566 
1566    
1567  =head3 Get  =head3 Get
1568    
1569  C<< my $query = $erdb->Get(\@objectNames, $filterClause, \@params); >>      my $query = $erdb->Get(\@objectNames, $filterClause, \@params);
1570    
1571  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.
1572  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 992  Line 1574 
1574  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
1575  $genus.  $genus.
1576    
1577  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", [$genus]); >>      $query = $erdb->Get(['Genome'], "Genome(genus) = ?", [$genus]);
1578    
1579  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
1580  parameter representing the parameter value. It would also be possible to code  parameter representing the parameter value. It would also be possible to code
1581    
1582  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>      $query = $erdb->Get(['Genome'], "Genome(genus) = \'$genus\'");
1583    
1584  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
1585  characters inside the variable C<$genus>.  characters inside the variable C<$genus>.
# Line 1009  Line 1591 
1591  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
1592  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,
1593    
1594  C<< $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]); >>      $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]);
1595    
1596  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
1597  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 1045  Line 1627 
1627  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
1628  particular genus and sorts them by species name.  particular genus and sorts them by species name.
1629    
1630  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>      "Genome(genus) = ? ORDER BY Genome(species)"
1631    
1632  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
1633  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 1058  Line 1640 
1640  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
1641  a positive number. So, for example  a positive number. So, for example
1642    
1643  C<< "Genome(genus) = ? ORDER BY Genome(species) LIMIT 10" >>      "Genome(genus) = ? ORDER BY Genome(species) LIMIT 10"
1644    
1645  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
1646  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
1647  use  use
1648    
1649  C<< "LIMIT 10" >>      "LIMIT 10"
1650    
1651  =item params  =item params
1652    
# Line 1085  Line 1667 
1667      my ($suffix, $mappedNameListRef, $mappedNameHashRef) =      my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1668          $self->_SetupSQL($objectNames, $filterClause);          $self->_SetupSQL($objectNames, $filterClause);
1669      # Create the query.      # Create the query.
1670      my $command = "SELECT DISTINCT " . join(".*, ", @{$mappedNameListRef}) .      my $command = "SELECT " . join(".*, ", @{$mappedNameListRef}) .
1671          ".* $suffix";          ".* $suffix";
1672      my $sth = $self->_GetStatementHandle($command, $params);      my $sth = $self->_GetStatementHandle($command, $params);
1673      # 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 1099  Line 1681 
1681      return $retVal;      return $retVal;
1682  }  }
1683    
 =head3 GetFlat  
1684    
 C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>  
1685    
1686  This is a variation of L</GetAll> that asks for only a single field per record and  =head3 Search
1687  returns a single flattened list.  
1688        my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params);
1689    
1690    Perform a full text search with filtering. The search will be against a specified object
1691    in the object name list. That object will get an extra field containing the search
1692    relevance. Note that except for the search expression, the parameters of this method are
1693    the same as those for L</Get> and follow the same rules.
1694    
1695  =over 4  =over 4
1696    
1697    =item searchExpression
1698    
1699    Boolean search expression for the text fields of the target object. The default mode for
1700    a Boolean search expression is OR, but we want the default to be AND, so we will
1701    add a C<+> operator to each word with no other operator before it.
1702    
1703    =item idx
1704    
1705    Index in the I<$objectNames> list of the table to be searched in full-text mode.
1706    
1707  =item objectNames  =item objectNames
1708    
1709  List containing the names of the entity and relationship objects to be retrieved.  List containing the names of the entity and relationship objects to be retrieved.
1710    
1711  =item filterClause  =item filterClause
1712    
1713  WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1714  be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form  be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
1715  B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the  specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
1716  parameter list as additional parameters. The fields in a filter clause can come from primary  in the filter clause should be added to the parameter list as additional parameters. The
1717  entity relations, relationship relations, or secondary entity relations; however, all of the  fields in a filter clause can come from primary entity relations, relationship relations,
1718  entities and relationships involved must be included in the list of object names.  or secondary entity relations; however, all of the entities and relationships involved must
1719    be included in the list of object names.
 =item parameterList  
   
 List of the parameters to be substituted in for the parameters marks in the filter clause.  
1720    
1721  =item field  =item params
1722    
1723  Name of the field to be used to get the elements of the list returned.  Reference to a list of parameter values to be substituted into the filter clause.
1724    
1725  =item RETURN  =item RETURN
1726    
1727  Returns a list of values.  Returns a query object for the specified search.
1728    
1729  =back  =back
1730    
1731  =cut  =cut
1732  #: Return Type @;  
1733  sub GetFlat {  sub Search {
1734      # Get the parameters.      # Get the parameters.
1735      my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;      my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1736      # Construct the query.      # Declare the return variable.
1737      my $query = $self->Get($objectNames, $filterClause, $parameterList);      my $retVal;
1738      # Create the result list.      # Create a safety copy of the parameter list. Note we have to be careful to insure
1739      my @retVal = ();      # a parameter list exists before we copy it.
1740      # Loop through the records, adding the field values found to the result list.      my @myParams = ();
1741      while (my $row = $query->Fetch()) {      if (defined $params) {
1742          push @retVal, $row->Value($field);          @myParams = @{$params};
1743        }
1744        # Get the first object's structure so we have access to the searchable fields.
1745        my $object1Name = $objectNames->[$idx];
1746        my $object1Structure = $self->_GetStructure($object1Name);
1747        # Get the field list.
1748        if (! exists $object1Structure->{searchFields}) {
1749            Confess("No searchable index for $object1Name.");
1750        } else {
1751            # Get the field list.
1752            my @fields = @{$object1Structure->{searchFields}};
1753            # Clean the search expression.
1754            my $actualKeywords = $self->CleanKeywords($searchExpression);
1755            # Prefix a "+" to each uncontrolled word. This converts the default
1756            # search mode from OR to AND.
1757            $actualKeywords =~ s/(^|\s)(\w|")/$1\+$2/g;
1758            Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1759            # We need two match expressions, one for the filter clause and one in the
1760            # query itself. Both will use a parameter mark, so we need to push the
1761            # search expression onto the front of the parameter list twice.
1762            unshift @myParams, $actualKeywords, $actualKeywords;
1763            # Build the match expression.
1764            my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
1765            my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
1766            # Process the SQL stuff.
1767            my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1768                $self->_SetupSQL($objectNames, $filterClause, $matchClause);
1769            # Create the query. Note that the match clause is inserted at the front of
1770            # the select fields.
1771            my $command = "SELECT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .
1772                ".* $suffix";
1773            my $sth = $self->_GetStatementHandle($command, \@myParams);
1774            # Now we create the relation map, which enables DBQuery to determine the order, name
1775            # and mapped name for each object in the query.
1776            my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
1777            # Return the statement object.
1778            $retVal = DBQuery::_new($self, $sth, \@relationMap, $object1Name);
1779        }
1780        return $retVal;
1781    }
1782    
1783    =head3 GetFlat
1784    
1785        my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field);
1786    
1787    This is a variation of L</GetAll> that asks for only a single field per record and
1788    returns a single flattened list.
1789    
1790    =over 4
1791    
1792    =item objectNames
1793    
1794    List containing the names of the entity and relationship objects to be retrieved.
1795    
1796    =item filterClause
1797    
1798    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1799    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
1800    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
1801    parameter list as additional parameters. The fields in a filter clause can come from primary
1802    entity relations, relationship relations, or secondary entity relations; however, all of the
1803    entities and relationships involved must be included in the list of object names.
1804    
1805    =item parameterList
1806    
1807    List of the parameters to be substituted in for the parameters marks in the filter clause.
1808    
1809    =item field
1810    
1811    Name of the field to be used to get the elements of the list returned.
1812    
1813    =item RETURN
1814    
1815    Returns a list of values.
1816    
1817    =back
1818    
1819    =cut
1820    #: Return Type @;
1821    sub GetFlat {
1822        # Get the parameters.
1823        my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
1824        # Construct the query.
1825        my $query = $self->Get($objectNames, $filterClause, $parameterList);
1826        # Create the result list.
1827        my @retVal = ();
1828        # Loop through the records, adding the field values found to the result list.
1829        while (my $row = $query->Fetch()) {
1830            push @retVal, $row->Value($field);
1831      }      }
1832      # Return the list created.      # Return the list created.
1833      return @retVal;      return @retVal;
1834  }  }
1835    
1836    =head3 SpecialFields
1837    
1838        my %specials = $erdb->SpecialFields($entityName);
1839    
1840    Return a hash mapping special fields in the specified entity to the value of their
1841    C<special> attribute. This enables the subclass to get access to the special field
1842    attributes without needed to plumb the internal ERDB data structures.
1843    
1844    =over 4
1845    
1846    =item entityName
1847    
1848    Name of the entity whose special fields are desired.
1849    
1850    =item RETURN
1851    
1852    Returns a hash. The keys of the hash are the special field names, and the values
1853    are the values from each special field's C<special> attribute.
1854    
1855    =back
1856    
1857    =cut
1858    
1859    sub SpecialFields {
1860        # Get the parameters.
1861        my ($self, $entityName) = @_;
1862        # Declare the return variable.
1863        my %retVal = ();
1864        # Find the entity's data structure.
1865        my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1866        # Loop through its fields, adding each special field to the return hash.
1867        my $fieldHash = $entityData->{Fields};
1868        for my $fieldName (keys %{$fieldHash}) {
1869            my $fieldData = $fieldHash->{$fieldName};
1870            if (exists $fieldData->{special}) {
1871                $retVal{$fieldName} = $fieldData->{special};
1872            }
1873        }
1874        # Return the result.
1875        return %retVal;
1876    }
1877    
1878  =head3 Delete  =head3 Delete
1879    
1880  C<< my $stats = $erdb->Delete($entityName, $objectID); >>      my $stats = $erdb->Delete($entityName, $objectID, %options);
1881    
1882  Delete an entity instance from the database. The instance is deleted along with all entity and  Delete an entity instance from the database. The instance is deleted along with all entity and
1883  relationship instances dependent on it. The idea of dependence here is recursive. An object is  relationship instances dependent on it. The definition of I<dependence> is recursive.
1884  always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many  
1885  relationship connected to a dependent entity or the "to" entity connected to a 1-to-many  An object is always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many
1886    relationship connected to a dependent entity or if it is the "to" entity connected to a 1-to-many
1887  dependent relationship.  dependent relationship.
1888    
1889  =over 4  =over 4
# Line 1173  Line 1897 
1897  ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),  ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),
1898  then it is presumed to by a LIKE pattern.  then it is presumed to by a LIKE pattern.
1899    
1900  =item testFlag  =item options
1901    
1902  If TRUE, the delete statements will be traced without being executed.  A hash detailing the options for this delete operation.
1903    
1904  =item RETURN  =item RETURN
1905    
# Line 1184  Line 1908 
1908    
1909  =back  =back
1910    
1911    The permissible options for this method are as follows.
1912    
1913    =over 4
1914    
1915    =item testMode
1916    
1917    If TRUE, then the delete statements will be traced, but no changes will be made to the database.
1918    
1919    =item keepRoot
1920    
1921    If TRUE, then the entity instances will not be deleted, only the dependent records.
1922    
1923    =back
1924    
1925  =cut  =cut
1926  #: Return Type $%;  #: Return Type $%;
1927  sub Delete {  sub Delete {
1928      # Get the parameters.      # Get the parameters.
1929      my ($self, $entityName, $objectID, $testFlag) = @_;      my ($self, $entityName, $objectID, %options) = @_;
1930      # Declare the return variable.      # Declare the return variable.
1931      my $retVal = Stats->new();      my $retVal = Stats->new();
1932      # Get the DBKernel object.      # Get the DBKernel object.
# Line 1205  Line 1943 
1943      # FROM-relationships and entities.      # FROM-relationships and entities.
1944      my @fromPathList = ();      my @fromPathList = ();
1945      my @toPathList = ();      my @toPathList = ();
1946      # This final hash is used to remember what work still needs to be done. We push paths      # This final list is used to remember what work still needs to be done. We push paths
1947      # onto the list, then pop them off to extend the paths. We prime it with the starting      # onto the list, then pop them off to extend the paths. We prime it with the starting
1948      # point. Note that we will work hard to insure that the last item on a path in the      # point. Note that we will work hard to insure that the last item on a path in the
1949      # TODO list is always an entity.      # to-do list is always an entity.
1950      my @todoList = ([$entityName]);      my @todoList = ([$entityName]);
1951      while (@todoList) {      while (@todoList) {
1952          # Get the current path.          # Get the current path.
# Line 1216  Line 1954 
1954          # Copy it into a list.          # Copy it into a list.
1955          my @stackedPath = @{$current};          my @stackedPath = @{$current};
1956          # 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.
1957          my $entityName = pop @stackedPath;          my $myEntityName = pop @stackedPath;
1958          # Add it to the alreadyFound list.          # Add it to the alreadyFound list.
1959          $alreadyFound{$entityName} = 1;          $alreadyFound{$myEntityName} = 1;
1960            # Figure out if we need to delete this entity.
1961            if ($myEntityName ne $entityName || ! $options{keepRoot}) {
1962          # Get the entity data.          # Get the entity data.
1963          my $entityData = $self->_GetStructure($entityName);              my $entityData = $self->_GetStructure($myEntityName);
1964          # 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.  
1965          my $relations = $entityData->{Relations};          my $relations = $entityData->{Relations};
1966          for my $relation (keys %{$relations}) {          for my $relation (keys %{$relations}) {
1967              my @augmentedList = (@stackedPath, $relation);              my @augmentedList = (@stackedPath, $relation);
1968              push @fromPathList, \@augmentedList;              push @fromPathList, \@augmentedList;
1969          }          }
1970            }
1971          # Now we need to look for relationships connected to this entity.          # Now we need to look for relationships connected to this entity.
1972          my $relationshipList = $self->{_metaData}->{Relationships};          my $relationshipList = $self->{_metaData}->{Relationships};
1973          for my $relationshipName (keys %{$relationshipList}) {          for my $relationshipName (keys %{$relationshipList}) {
1974              my $relationship = $relationshipList->{$relationshipName};              my $relationship = $relationshipList->{$relationshipName};
1975              # Check the FROM field. We're only interested if it's us.              # Check the FROM field. We're only interested if it's us.
1976              if ($relationship->{from} eq $entityName) {              if ($relationship->{from} eq $myEntityName) {
1977                  # Add the path to this relationship.                  # Add the path to this relationship.
1978                  my @augmentedList = (@stackedPath, $entityName, $relationshipName);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1979                  push @fromPathList, \@augmentedList;                  push @fromPathList, \@augmentedList;
1980                  # Check the arity. If it's MM we're done. If it's 1M                  # Check the arity. If it's MM we're done. If it's 1M
1981                  # and the target hasn't been seen yet, we want to                  # and the target hasn't been seen yet, we want to
# Line 1254  Line 1994 
1994              }              }
1995              # Now check the TO field. In this case only the relationship needs              # Now check the TO field. In this case only the relationship needs
1996              # deletion.              # deletion.
1997              if ($relationship->{to} eq $entityName) {              if ($relationship->{to} eq $myEntityName) {
1998                  my @augmentedList = (@stackedPath, $entityName, $relationshipName);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1999                  push @toPathList, \@augmentedList;                  push @toPathList, \@augmentedList;
2000              }              }
2001          }          }
2002      }      }
2003      # Create the first qualifier for the WHERE clause. This selects the      # Create the first qualifier for the WHERE clause. This selects the
2004      # 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
2005      # 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
2006      # to the table containing the dependent records to delete.      # to the table containing the dependent records to delete.
2007      my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");      my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
2008      # 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 1301  Line 2041 
2041                  }                  }
2042              }              }
2043              # Now we have our desired DELETE statement.              # Now we have our desired DELETE statement.
2044              if ($testFlag) {              if ($options{testMode}) {
2045                  # Here the user wants to trace without executing.                  # Here the user wants to trace without executing.
2046                  Trace($stmt) if T(0);                  Trace($stmt) if T(0);
2047              } else {              } else {
2048                  # 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
2049                  # if an error occurs, so we just go ahead and do it.                  # if an error occurs, so we just go ahead and do it.
2050                  Trace("Executing delete from $target using '$objectID'.") if T(3);                  Trace("Executing delete from $target using '$objectID'.") if T(3);
2051                  my $rv = $db->SQL($stmt, 0, $objectID);                  my $rv = $db->SQL($stmt, 0, $objectID);
# Line 1320  Line 2060 
2060      return $retVal;      return $retVal;
2061  }  }
2062    
2063  =head3 GetList  =head3 Disconnect
   
 C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>  
2064    
2065  Return a list of object descriptors for the specified objects as determined by the      $erdb->Disconnect($relationshipName, $originEntityName, $originEntityID);
 specified filter clause.  
2066    
2067  This method is essentially the same as L</Get> except it returns a list of objects rather  Disconnect an entity instance from all the objects to which it is related. This
2068  than a query object that can be used to get the results one record at a time.  will delete each relationship instance that connects to the specified entity.
2069    
2070  =over 4  =over 4
2071    
2072  =item objectNames  =item relationshipName
   
 List containing the names of the entity and relationship objects to be retrieved.  
   
 =item filterClause  
   
 WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  
 be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be  
 specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified  
 in the filter clause should be added to the parameter list as additional parameters. The  
 fields in a filter clause can come from primary entity relations, relationship relations,  
 or secondary entity relations; however, all of the entities and relationships involved must  
 be included in the list of object names.  
   
 The filter clause can also specify a sort order. To do this, simply follow the filter string  
 with an ORDER BY clause. For example, the following filter string gets all genomes for a  
 particular genus and sorts them by species name.  
   
 C<< "Genome(genus) = ? ORDER BY Genome(species)" >>  
2073    
2074  The rules for field references in a sort order are the same as those for field references in the  Name of the relationship whose instances are to be deleted.
 filter clause in general; however, odd things may happen if a sort field is from a secondary  
 relation.  
2075    
2076  =item params  =item originEntityName
2077    
2078  Reference to a list of parameter values to be substituted into the filter clause.  Name of the entity that is to be disconnected.
2079    
2080  =item RETURN  =item originEntityID
2081    
2082  Returns a list of B<DBObject>s that satisfy the query conditions.  ID of the entity that is to be disconnected.
2083    
2084  =back  =back
2085    
2086  =cut  =cut
2087  #: Return Type @%  
2088  sub GetList {  sub Disconnect {
2089      # Get the parameters.      # Get the parameters.
2090      my ($self, $objectNames, $filterClause, $params) = @_;      my ($self, $relationshipName, $originEntityName, $originEntityID) = @_;
2091      # Declare the return variable.      # Get the relationship descriptor.
2092      my @retVal = ();      my $structure = $self->_GetStructure($relationshipName);
2093      # Perform the query.      # Insure we have a relationship.
2094      my $query = $self->Get($objectNames, $filterClause, $params);      if (! exists $structure->{from}) {
2095      # Loop through the results.          Confess("$relationshipName is not a relationship in the database.");
2096      while (my $object = $query->Fetch) {      } else {
2097          push @retVal, $object;          # Get the database handle.
2098            my $dbh = $self->{_dbh};
2099            # We'll set this value to 1 if we find our entity.
2100            my $found = 0;
2101            # Loop through the ends of the relationship.
2102            for my $dir ('from', 'to') {
2103                if ($structure->{$dir} eq $originEntityName) {
2104                    $found = 1;
2105                    # Here we want to delete all relationship instances on this side of the
2106                    # entity instance.
2107                    Trace("Disconnecting in $dir direction with ID \"$originEntityID\".");
2108                    # We do this delete in batches to keep it from dragging down the
2109                    # server.
2110                    my $limitClause = ($FIG_Config::delete_limit ? "LIMIT $FIG_Config::delete_limit" : "");
2111                    my $done = 0;
2112                    while (! $done) {
2113                        # Do the delete.
2114                        my $rows = $dbh->SQL("DELETE FROM $relationshipName WHERE ${dir}_link = ? $limitClause", 0, $originEntityID);
2115                        # See if we're done. We're done if no rows were found or the delete is unlimited.
2116                        $done = ($rows == 0 || ! $limitClause);
2117                    }
2118                }
2119            }
2120            # Insure we found the entity on at least one end.
2121            if (! $found) {
2122                Confess("Entity \"$originEntityName\" does not use $relationshipName.");
2123            }
2124      }      }
     # Return the result.  
     return @retVal;  
2125  }  }
2126    
2127  =head3 GetCount  =head3 DeleteRow
2128    
2129  C<< my $count = $erdb->GetCount(\@objectNames, $filter, \@params); >>      $erdb->DeleteRow($relationshipName, $fromLink, $toLink, \%values);
2130    
2131  Return the number of rows found by a specified query. This method would  Delete a row from a relationship. In most cases, only the from-link and to-link are
2132  normally be used to count the records in a single table. For example, in a  needed; however, for relationships with intersection data values can be specified
2133  genetics database  for the other fields using a hash.
2134    
2135      my $count = $erdb->GetCount(['Genome'], 'Genome(genus-species) LIKE ?', ['homo %']);  =over 4
2136    
2137  would return the number of genomes for the genus I<homo>. It is conceivable, however,  =item relationshipName
 to use it to return records based on a join. For example,  
2138    
2139      my $count = $erdb->GetCount(['HasFeature', 'Genome'], 'Genome(genus-species) LIKE ?',  Name of the relationship from which the row is to be deleted.
                                 ['homo %']);  
2140    
2141  would return the number of features for genomes in the genus I<homo>. Note that  =item fromLink
 only the rows from the first table are counted. If the above command were  
2142    
2143      my $count = $erdb->GetCount(['Genome', 'Feature'], 'Genome(genus-species) LIKE ?',  ID of the entity instance in the From direction.
                                 ['homo %']);  
2144    
2145  it would return the number of genomes, not the number of genome/feature pairs.  =item toLink
2146    
2147    ID of the entity instance in the To direction.
2148    
2149    =item values
2150    
2151    Reference to a hash of other values to be used for filtering the delete.
2152    
2153    =back
2154    
2155    =cut
2156    
2157    sub DeleteRow {
2158        # Get the parameters.
2159        my ($self, $relationshipName, $fromLink, $toLink, $values) = @_;
2160        # Create a hash of all the filter information.
2161        my %filter = ('from-link' => $fromLink, 'to-link' => $toLink);
2162        if (defined $values) {
2163            for my $key (keys %{$values}) {
2164                $filter{$key} = $values->{$key};
2165            }
2166        }
2167        # Build an SQL statement out of the hash.
2168        my @filters = ();
2169        my @parms = ();
2170        for my $key (keys %filter) {
2171            push @filters, _FixName($key) . " = ?";
2172            push @parms, $filter{$key};
2173        }
2174        Trace("Parms for delete row are " . join(", ", map { "\"$_\"" } @parms) . ".") if T(SQL => 4);
2175        my $command = "DELETE FROM $relationshipName WHERE " .
2176                      join(" AND ", @filters);
2177        # Execute it.
2178        my $dbh = $self->{_dbh};
2179        $dbh->SQL($command, undef, @parms);
2180    }
2181    
2182    =head3 DeleteLike
2183    
2184        my $deleteCount = $erdb->DeleteLike($relName, $filter, \@parms);
2185    
2186    Delete all the relationship rows that satisfy a particular filter condition. Unlike a normal
2187    filter, only fields from the relationship itself can be used.
2188    
2189  =over 4  =over 4
2190    
2191  =item objectNames  =item relName
2192    
2193  Reference to a list of the objects (entities and relationships) included in the  Name of the relationship whose records are to be deleted.
 query.  
2194    
2195  =item filter  =item filter
2196    
2197  A filter clause for restricting the query. The rules are the same as for the L</Get>  A filter clause (L</Get>-style) for the delete query.
 method.  
2198    
2199  =item params  =item parms
2200    
2201  Reference to a list of the parameter values to be substituted for the parameter marks  Reference to a list of parameters for the filter clause.
 in the filter.  
2202    
2203  =item RETURN  =item RETURN
2204    
2205  Returns a count of the number of records in the first table that would satisfy  Returns a count of the number of rows deleted.
 the query.  
2206    
2207  =back  =back
2208    
2209  =cut  =cut
2210    
2211  sub GetCount {  sub DeleteLike {
2212      # Get the parameters.      # Get the parameters.
2213      my ($self, $objectNames, $filter, $params) = @_;      my ($self, $objectName, $filter, $parms) = @_;
     # Insure the params argument is an array reference if the caller left it off.  
     if (! defined($params)) {  
         $params = [];  
     }  
2214      # Declare the return variable.      # Declare the return variable.
2215      my $retVal;      my $retVal;
2216      # Find out if we're counting an entity or a relationship.      # Insure the parms argument is an array reference if the caller left it off.
2217      my $countedField;      if (! defined($parms)) {
2218      if ($self->IsEntity($objectNames->[0])) {          $parms = [];
2219          $countedField = "id";      }
2220        # Insure we have a relationship. The main reason for this is if we delete an entity
2221        # instance we have to yank out a bunch of other stuff with it.
2222        if ($self->IsEntity($objectName)) {
2223            Confess("Cannot use DeleteLike on $objectName, because it is not a relationship.");
2224      } else {      } else {
2225          # For a relationship we count the to-link because it's usually more          # Create the SQL command suffix to get the desierd records.
2226          # numerous. Note we're automatically converting to the SQL form          my ($suffix) = $self->_SetupSQL([$objectName], $filter);
2227          # of the field name (to_link vs. to-link).          # Convert it to a DELETE command.
2228          $countedField = "to_link";          my $command = "DELETE $suffix";
2229      }          # Execute the command.
2230      # Create the SQL command suffix to get the desired records.          my $dbh = $self->{_dbh};
2231      my ($suffix, $mappedNameListRef, $mappedNameHashRef) = $self->_SetupSQL($objectNames,          my $result = $dbh->SQL($command, 0, @{$parms});
2232                                                                              $filter);          # Check the results. Note we convert the "0D0" result to a real zero.
2233      # Prefix it with text telling it we want a record count.          # A failure causes an abnormal termination, so the caller isn't going to
2234      my $firstObject = $mappedNameListRef->[0];          # worry about it.
2235      my $command = "SELECT COUNT($firstObject.$countedField) $suffix";          if (! defined $result) {
2236      # Prepare and execute the command.              Confess("Error deleting from $objectName: " . $dbh->errstr());
2237      my $sth = $self->_GetStatementHandle($command, $params);          } elsif ($result == 0) {
2238      # Get the count value.              $retVal = 0;
     ($retVal) = $sth->fetchrow_array();  
     # Check for a problem.  
     if (! defined($retVal)) {  
         if ($sth->err) {  
             # Here we had an SQL error.  
             Confess("Error retrieving row count: " . $sth->errstr());  
2239          } else {          } else {
2240              # Here we have no result.              $retVal = $result;
             Confess("No result attempting to retrieve row count.");  
2241          }          }
2242      }      }
2243      # Return the result.      # Return the result count.
2244      return $retVal;      return $retVal;
2245  }  }
2246    
2247  =head3 ComputeObjectSentence  =head3 SortNeeded
2248    
2249  C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>      my $parms = $erdb->SortNeeded($relationName);
2250    
2251  Check an object name, and if it is a relationship convert it to a relationship sentence.  Return the pipe command for the sort that should be applied to the specified
2252    relation when creating the load file.
2253    
2254  =over 4  For example, if the load file should be sorted ascending by the first
2255    field, this method would return
2256    
2257  =item objectName      sort -k1 -t"\t"
2258    
2259  Name of the entity or relationship.  If the first field is numeric, the method would return
2260    
2261  =item RETURN      sort -k1n -t"\t"
2262    
2263  Returns a string containing the entity name or a relationship sentence.  Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate
2264    keys using a sort.
2265    
2266  =back  =over 4
2267    
2268  =cut  =item relationName
2269    
2270  sub ComputeObjectSentence {  Name of the relation to be examined.
2271      # Get the parameters.  
2272      my ($self, $objectName) = @_;  =item
2273    
2274    Returns the sort command to use for sorting the relation, suitable for piping.
2275    
2276    =back
2277    
2278    =cut
2279    #: Return Type $;
2280    sub SortNeeded {
2281        # Get the parameters.
2282        my ($self, $relationName) = @_;
2283        # Declare a descriptor to hold the names of the key fields.
2284        my @keyNames = ();
2285        # Get the relation structure.
2286        my $relationData = $self->_FindRelation($relationName);
2287        # Find out if the relation is a primary entity relation,
2288        # a relationship relation, or a secondary entity relation.
2289        my $entityTable = $self->{_metaData}->{Entities};
2290        my $relationshipTable = $self->{_metaData}->{Relationships};
2291        if (exists $entityTable->{$relationName}) {
2292            # Here we have a primary entity relation.
2293            push @keyNames, "id";
2294        } elsif (exists $relationshipTable->{$relationName}) {
2295            # Here we have a relationship. We sort using the FROM index.
2296            my $relationshipData = $relationshipTable->{$relationName};
2297            my $index = $relationData->{Indexes}->{idxFrom};
2298            push @keyNames, @{$index->{IndexFields}};
2299        } else {
2300            # Here we have a secondary entity relation, so we have a sort on the ID field.
2301            push @keyNames, "id";
2302        }
2303        # Now we parse the key names into sort parameters. First, we prime the return
2304        # string.
2305        my $retVal = "sort -t\"\t\" ";
2306        # Get the relation's field list.
2307        my @fields = @{$relationData->{Fields}};
2308        # Loop through the keys.
2309        for my $keyData (@keyNames) {
2310            # Get the key and the ordering.
2311            my ($keyName, $ordering);
2312            if ($keyData =~ /^([^ ]+) DESC/) {
2313                ($keyName, $ordering) = ($1, "descending");
2314            } else {
2315                ($keyName, $ordering) = ($keyData, "ascending");
2316            }
2317            # Find the key's position and type.
2318            my $fieldSpec;
2319            for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {
2320                my $thisField = $fields[$i];
2321                if ($thisField->{name} eq $keyName) {
2322                    # Get the sort modifier for this field type. The modifier
2323                    # decides whether we're using a character, numeric, or
2324                    # floating-point sort.
2325                    my $modifier = $TypeTable{$thisField->{type}}->{sort};
2326                    # If the index is descending for this field, denote we want
2327                    # to reverse the sort order on this field.
2328                    if ($ordering eq 'descending') {
2329                        $modifier .= "r";
2330                    }
2331                    # Store the position and modifier into the field spec, which
2332                    # will stop the inner loop. Note that the field number is
2333                    # 1-based in the sort command, so we have to increment the
2334                    # index.
2335                    $fieldSpec = ($i + 1) . $modifier;
2336                }
2337            }
2338            # Add this field to the sort command.
2339            $retVal .= " -k$fieldSpec";
2340        }
2341        # Return the result.
2342        return $retVal;
2343    }
2344    
2345    =head3 GetList
2346    
2347        my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params);
2348    
2349    Return a list of object descriptors for the specified objects as determined by the
2350    specified filter clause.
2351    
2352    This method is essentially the same as L</Get> except it returns a list of objects rather
2353    than a query object that can be used to get the results one record at a time.
2354    
2355    =over 4
2356    
2357    =item objectNames
2358    
2359    List containing the names of the entity and relationship objects to be retrieved.
2360    
2361    =item filterClause
2362    
2363    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
2364    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
2365    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
2366    in the filter clause should be added to the parameter list as additional parameters. The
2367    fields in a filter clause can come from primary entity relations, relationship relations,
2368    or secondary entity relations; however, all of the entities and relationships involved must
2369    be included in the list of object names.
2370    
2371    The filter clause can also specify a sort order. To do this, simply follow the filter string
2372    with an ORDER BY clause. For example, the following filter string gets all genomes for a
2373    particular genus and sorts them by species name.
2374    
2375        "Genome(genus) = ? ORDER BY Genome(species)"
2376    
2377    The rules for field references in a sort order are the same as those for field references in the
2378    filter clause in general; however, odd things may happen if a sort field is from a secondary
2379    relation.
2380    
2381    =item params
2382    
2383    Reference to a list of parameter values to be substituted into the filter clause.
2384    
2385    =item RETURN
2386    
2387    Returns a list of B<ERDBObject>s that satisfy the query conditions.
2388    
2389    =back
2390    
2391    =cut
2392    #: Return Type @%
2393    sub GetList {
2394        # Get the parameters.
2395        my ($self, $objectNames, $filterClause, $params) = @_;
2396        # Declare the return variable.
2397        my @retVal = ();
2398        # Perform the query.
2399        my $query = $self->Get($objectNames, $filterClause, $params);
2400        # Loop through the results.
2401        while (my $object = $query->Fetch) {
2402            push @retVal, $object;
2403        }
2404        # Return the result.
2405        return @retVal;
2406    }
2407    
2408    =head3 GetCount
2409    
2410        my $count = $erdb->GetCount(\@objectNames, $filter, \@params);
2411    
2412    Return the number of rows found by a specified query. This method would
2413    normally be used to count the records in a single table. For example, in a
2414    genetics database
2415    
2416        my $count = $erdb->GetCount(['Genome'], 'Genome(genus-species) LIKE ?', ['homo %']);
2417    
2418    would return the number of genomes for the genus I<homo>. It is conceivable, however,
2419    to use it to return records based on a join. For example,
2420    
2421        my $count = $erdb->GetCount(['HasFeature', 'Genome'], 'Genome(genus-species) LIKE ?',
2422                                    ['homo %']);
2423    
2424    would return the number of features for genomes in the genus I<homo>. Note that
2425    only the rows from the first table are counted. If the above command were
2426    
2427        my $count = $erdb->GetCount(['Genome', 'Feature'], 'Genome(genus-species) LIKE ?',
2428                                    ['homo %']);
2429    
2430    it would return the number of genomes, not the number of genome/feature pairs.
2431    
2432    =over 4
2433    
2434    =item objectNames
2435    
2436    Reference to a list of the objects (entities and relationships) included in the
2437    query.
2438    
2439    =item filter
2440    
2441    A filter clause for restricting the query. The rules are the same as for the L</Get>
2442    method.
2443    
2444    =item params
2445    
2446    Reference to a list of the parameter values to be substituted for the parameter marks
2447    in the filter.
2448    
2449    =item RETURN
2450    
2451    Returns a count of the number of records in the first table that would satisfy
2452    the query.
2453    
2454    =back
2455    
2456    =cut
2457    
2458    sub GetCount {
2459        # Get the parameters.
2460        my ($self, $objectNames, $filter, $params) = @_;
2461        # Insure the params argument is an array reference if the caller left it off.
2462        if (! defined($params)) {
2463            $params = [];
2464        }
2465        # Declare the return variable.
2466        my $retVal;
2467        # Find out if we're counting an entity or a relationship.
2468        my $countedField;
2469        if ($self->IsEntity($objectNames->[0])) {
2470            $countedField = "id";
2471        } else {
2472            # For a relationship we count the to-link because it's usually more
2473            # numerous. Note we're automatically converting to the SQL form
2474            # of the field name (to_link vs. to-link).
2475            $countedField = "to_link";
2476        }
2477        # Create the SQL command suffix to get the desired records.
2478        my ($suffix, $mappedNameListRef, $mappedNameHashRef) = $self->_SetupSQL($objectNames,
2479                                                                                $filter);
2480        # Prefix it with text telling it we want a record count.
2481        my $firstObject = $mappedNameListRef->[0];
2482        my $command = "SELECT COUNT($firstObject.$countedField) $suffix";
2483        # Prepare and execute the command.
2484        my $sth = $self->_GetStatementHandle($command, $params);
2485        # Get the count value.
2486        ($retVal) = $sth->fetchrow_array();
2487        # Check for a problem.
2488        if (! defined($retVal)) {
2489            if ($sth->err) {
2490                # Here we had an SQL error.
2491                Confess("Error retrieving row count: " . $sth->errstr());
2492            } else {
2493                # Here we have no result.
2494                Confess("No result attempting to retrieve row count.");
2495            }
2496        }
2497        # Return the result.
2498        return $retVal;
2499    }
2500    
2501    =head3 ComputeObjectSentence
2502    
2503        my $sentence = $erdb->ComputeObjectSentence($objectName);
2504    
2505    Check an object name, and if it is a relationship convert it to a relationship sentence.
2506    
2507    =over 4
2508    
2509    =item objectName
2510    
2511    Name of the entity or relationship.
2512    
2513    =item RETURN
2514    
2515    Returns a string containing the entity name or a relationship sentence.
2516    
2517    =back
2518    
2519    =cut
2520    
2521    sub ComputeObjectSentence {
2522        # Get the parameters.
2523        my ($self, $objectName) = @_;
2524      # Set the default return value.      # Set the default return value.
2525      my $retVal = $objectName;      my $retVal = $objectName;
2526      # Look for the object as a relationship.      # Look for the object as a relationship.
# Line 1513  Line 2535 
2535    
2536  =head3 DumpRelations  =head3 DumpRelations
2537    
2538  C<< $erdb->DumpRelations($outputDirectory); >>      $erdb->DumpRelations($outputDirectory);
2539    
2540  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.
2541  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 1555  Line 2577 
2577    
2578  =head3 InsertValue  =head3 InsertValue
2579    
2580  C<< $erdb->InsertValue($entityID, $fieldName, $value); >>      $erdb->InsertValue($entityID, $fieldName, $value);
2581    
2582  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
2583  associated with a secondary relation, since primary values cannot be inserted:  associated with a secondary relation, since primary values cannot be inserted:
# Line 1618  Line 2640 
2640    
2641  =head3 InsertObject  =head3 InsertObject
2642    
2643  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>      $erdb->InsertObject($objectType, \%fieldHash);
2644    
2645  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
2646  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 1627  Line 2649 
2649  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
2650  C<ZP_00210270.1> and C<gi|46206278>.  C<ZP_00210270.1> and C<gi|46206278>.
2651    
2652  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']});
2653    
2654  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
2655  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>.
2656    
2657  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'});
2658    
2659  =over 4  =over 4
2660    
# Line 1644  Line 2666 
2666    
2667  Hash of field names to values.  Hash of field names to values.
2668    
 =item RETURN  
   
 Returns 1 if successful, 0 if an error occurred.  
   
2669  =back  =back
2670    
2671  =cut  =cut
# Line 1746  Line 2764 
2764                  $retVal = $sth->execute(@parameterList);                  $retVal = $sth->execute(@parameterList);
2765                  if (!$retVal) {                  if (!$retVal) {
2766                      my $errorString = $sth->errstr();                      my $errorString = $sth->errstr();
2767                      Trace("Insert error: $errorString.") if T(0);                      Confess("Error inserting into $relationName: $errorString");
2768                    } else {
2769                        Trace("Insert successful using $parameterList[0].") if T(3);
2770                  }                  }
2771              }              }
2772          }          }
2773      }      }
2774      # Return the success indicator.      # Return a 1 for backward compatability.
2775      return $retVal;      return 1;
2776  }  }
2777    
2778  =head3 LoadTable  =head3 UpdateEntity
2779    
2780  C<< my %results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>      $erdb->UpdateEntity($entityName, $id, \%fields);
2781    
2782  Load data from a tab-delimited file into a specified table, optionally re-creating the table  Update the values of an entity. This is an unprotected update, so it should only be
2783  first.  done if the database resides on a database server.
2784    
2785    =over 4
2786    
2787    =item entityName
2788    
2789    Name of the entity to update. (This is the entity type.)
2790    
2791    =item id
2792    
2793    ID of the entity to update. If no entity exists with this ID, an error will be thrown.
2794    
2795    =item fields
2796    
2797    Reference to a hash mapping field names to their new values. All of the fields named
2798    must be in the entity's primary relation, and they cannot any of them be the ID field.
2799    
2800    =back
2801    
2802    =cut
2803    
2804    sub UpdateEntity {
2805        # Get the parameters.
2806        my ($self, $entityName, $id, $fields) = @_;
2807        # Get a list of the field names being updated.
2808        my @fieldList = keys %{$fields};
2809        # Verify that the fields exist.
2810        my $checker = $self->GetFieldTable($entityName);
2811        for my $field (@fieldList) {
2812            if ($field eq 'id') {
2813                Confess("Cannot update the ID field for entity $entityName.");
2814            } elsif ($checker->{$field}->{relation} ne $entityName) {
2815                Confess("Cannot find $field in primary relation of $entityName.");
2816            }
2817        }
2818        # Build the SQL statement.
2819        my @sets = ();
2820        my @valueList = ();
2821        for my $field (@fieldList) {
2822            push @sets, _FixName($field) . " = ?";
2823            push @valueList, $fields->{$field};
2824        }
2825        my $command = "UPDATE $entityName SET " . join(", ", @sets) . " WHERE id = ?";
2826        # Add the ID to the list of binding values.
2827        push @valueList, $id;
2828        # Call SQL to do the work.
2829        my $rows = $self->{_dbh}->SQL($command, 0, @valueList);
2830        # Check for errors.
2831        if ($rows == 0) {
2832            Confess("Entity $id of type $entityName not found.");
2833        }
2834    }
2835    
2836    =head3 LoadTable
2837    
2838        my $results = $erdb->LoadTable($fileName, $relationName, %options);
2839    
2840    Load data from a tab-delimited file into a specified table, optionally re-creating the table
2841    first.
2842    
2843  =over 4  =over 4
2844    
# Line 1772  Line 2850 
2850    
2851  Name of the relation to be loaded. This is the same as the table name.  Name of the relation to be loaded. This is the same as the table name.
2852    
2853  =item truncateFlag  =item options
2854    
2855  TRUE if the table should be dropped and re-created, else FALSE  A hash of load options.
2856    
2857  =item RETURN  =item RETURN
2858    
# Line 1782  Line 2860 
2860    
2861  =back  =back
2862    
2863    The permissible options are as follows.
2864    
2865    =over 4
2866    
2867    =item truncate
2868    
2869    If TRUE, then the table will be erased before loading.
2870    
2871    =item mode
2872    
2873    Mode in which the load should operate, either C<low_priority> or C<concurrent>.
2874    This option is only applicable to a MySQL database.
2875    
2876    =item partial
2877    
2878    If TRUE, then it is assumed that this is a partial load, and the table will not
2879    be analyzed and compacted at the end.
2880    
2881    =back
2882    
2883  =cut  =cut
2884  sub LoadTable {  sub LoadTable {
2885      # Get the parameters.      # Get the parameters.
2886      my ($self, $fileName, $relationName, $truncateFlag) = @_;      my ($self, $fileName, $relationName, %options) = @_;
2887      # Create the statistical return object.      # Create the statistical return object.
2888      my $retVal = _GetLoadStats();      my $retVal = _GetLoadStats();
2889      # Trace the fact of the load.      # Trace the fact of the load.
# Line 1797  Line 2895 
2895      # Get the relation data.      # Get the relation data.
2896      my $relation = $self->_FindRelation($relationName);      my $relation = $self->_FindRelation($relationName);
2897      # Check the truncation flag.      # Check the truncation flag.
2898      if ($truncateFlag) {      if ($options{truncate}) {
2899          Trace("Creating table $relationName") if T(2);          Trace("Creating table $relationName") if T(2);
2900          # 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,
2901          # 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
2902          # leave extra room. We postulate a minimum row count of 1000 to          # leave extra room. We postulate a minimum row count of 1000 to
2903          # prevent problems with incoming empty load files.          # prevent problems with incoming empty load files.
2904          my $rowSize = $self->EstimateRowSize($relationName);          my $rowSize = $self->EstimateRowSize($relationName);
2905          my $estimate = FIG::max($fileSize * 1.5 / $rowSize, 1000);          my $estimate = $fileSize * 8 / $rowSize;
2906            if ($estimate < 1000) {
2907                $estimate = 1000;
2908            }
2909          # Re-create the table without its index.          # Re-create the table without its index.
2910          $self->CreateTable($relationName, 0, $estimate);          $self->CreateTable($relationName, 0, $estimate);
2911          # If this is a pre-index DBMS, create the index here.          # If this is a pre-index DBMS, create the index here.
# Line 1820  Line 2921 
2921      # Load the table.      # Load the table.
2922      my $rv;      my $rv;
2923      eval {      eval {
2924          $rv = $dbh->load_table(file => $fileName, tbl => $relationName);          $rv = $dbh->load_table(file => $fileName, tbl => $relationName, style => $options{mode});
2925      };      };
2926      if (!defined $rv) {      if (!defined $rv) {
2927          $retVal->AddMessage($@) if ($@);          $retVal->AddMessage($@) if ($@);
2928          $retVal->AddMessage("Table load failed for $relationName using $fileName.");          $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2929          Trace("Table load failed for $relationName.") if T(1);          Trace("Table load failed for $relationName.") if T(1);
2930      } else {      } else {
2931          # Here we successfully loaded the table.          # Here we successfully loaded the table.
2932          $retVal->Add("tables");          $retVal->Add("tables");
2933          my $size = -s $fileName;          my $size = -s $fileName;
2934          Trace("$size bytes loaded into $relationName.") if T(2);          Trace("$size bytes loaded into $relationName.") if T(2);
2935            $retVal->Add("bytes", $size);
2936          # If we're rebuilding, we need to create the table indexes.          # If we're rebuilding, we need to create the table indexes.
2937          if ($truncateFlag && ! $dbh->{_preIndex}) {          if ($options{truncate}) {
2938                # Indexes are created here for PostGres. For PostGres, indexes are
2939                # best built at the end. For MySQL, the reverse is true.
2940                if (! $dbh->{_preIndex}) {
2941              eval {              eval {
2942                  $self->CreateIndex($relationName);                  $self->CreateIndex($relationName);
2943              };              };
# Line 1840  Line 2945 
2945                  $retVal->AddMessage($@);                  $retVal->AddMessage($@);
2946              }              }
2947          }          }
2948                # The full-text index (if any) is always built last, even for MySQL.
2949                # First we need to see if this table has a full-text index. Only
2950                # primary relations are allowed that privilege.
2951                Trace("Checking for full-text index on $relationName.") if T(2);
2952                if ($self->_IsPrimary($relationName)) {
2953                    $self->CreateSearchIndex($relationName);
2954                }
2955            }
2956      }      }
2957      # Analyze the table to improve performance.      # Analyze the table to improve performance.
2958        if (! $options{partial}) {
2959      Trace("Analyzing and compacting $relationName.") if T(3);      Trace("Analyzing and compacting $relationName.") if T(3);
2960      $dbh->vacuum_it($relationName);      $dbh->vacuum_it($relationName);
2961        }
2962      Trace("$relationName load completed.") if T(3);      Trace("$relationName load completed.") if T(3);
2963      # Return the statistics.      # Return the statistics.
2964      return $retVal;      return $retVal;
2965  }  }
2966    
2967  =head3 GenerateEntity  =head3 CreateSearchIndex
2968    
2969  C<< my $fieldHash = $erdb->GenerateEntity($id, $type, \%values); >>      $erdb->CreateSearchIndex($objectName);
2970    
2971  Generate the data for a new entity instance. This method creates a field hash suitable for  Check for a full-text search index on the specified entity or relationship object, and
2972  passing as a parameter to L</InsertObject>. The ID is specified by the callr, but the rest  if one is required, rebuild it.
 of the fields are generated using information in the database schema.  
   
 Each data type has a default algorithm for generating random test data. This can be overridden  
 by including a B<DataGen> element in the field. If this happens, the content of the element is  
 executed as a PERL program in the context of this module. The element may make use of a C<$this>  
 variable which contains the field hash as it has been built up to the current point. If any  
 fields are dependent on other fields, the C<pass> attribute can be used to control the order  
 in which the fields are generated. A field with a high data pass number will be generated after  
 a field with a lower one. If any external values are needed, they should be passed in via the  
 optional third parameter, which will be available to the data generation script under the name  
 C<$value>. Several useful utility methods are provided for generating random values, including  
 L</IntGen>, L</StringGen>, L</FloatGen>, and L</DateGen>. Note that dates are stored and generated  
 in the form of a timestamp number rather than a string.  
2973    
2974  =over 4  =over 4
2975    
2976  =item id  =item objectName
2977    
2978  ID to assign to the new entity.  Name of the entity or relationship to be indexed.
2979    
2980  =item type  =back
2981    
2982  Type name for the new entity.  =cut
2983    
2984  =item values  sub CreateSearchIndex {
2985        # Get the parameters.
2986        my ($self, $objectName) = @_;
2987        # Get the relation's entity/relationship structure.
2988        my $structure = $self->_GetStructure($objectName);
2989        # Get the database handle.
2990        my $dbh = $self->{_dbh};
2991        Trace("Checking for search fields in $objectName.") if T(3);
2992        # Check for a searchable fields list.
2993        if (exists $structure->{searchFields}) {
2994            # Here we know that we need to create a full-text search index.
2995            # Get an SQL-formatted field name list.
2996            my $fields = join(", ", _FixNames(@{$structure->{searchFields}}));
2997            # Create the index. If it already exists, it will be dropped.
2998            $dbh->create_index(tbl => $objectName, idx => "search_idx",
2999                               flds => $fields, kind => 'fulltext');
3000            Trace("Index created for $fields in $objectName.") if T(2);
3001        }
3002    }
3003    
3004    =head3 DropRelation
3005    
3006        $erdb->DropRelation($relationName);
3007    
3008    Physically drop a relation from the database.
3009    
3010  Hash containing additional values that might be needed by the data generation methods (optional).  =over 4
3011    
3012    =item relationName
3013    
3014    Name of the relation to drop. If it does not exist, this method will have
3015    no effect.
3016    
3017  =back  =back
3018    
3019  =cut  =cut
3020    
3021  sub GenerateEntity {  sub DropRelation {
3022      # Get the parameters.      # Get the parameters.
3023      my ($self, $id, $type, $values) = @_;      my ($self, $relationName) = @_;
3024      # Create the return hash.      # Get the database handle.
3025      my $this = { id => $id };      my $dbh = $self->{_dbh};
3026      # Get the metadata structure.      # Drop the relation. The method used here has no effect if the relation
3027      my $metadata = $self->{_metaData};      # does not exist.
3028      # Get this entity's list of fields.      Trace("Invoking DB Kernel to drop $relationName.") if T(3);
3029      if (!exists $metadata->{Entities}->{$type}) {      $dbh->drop_table(tbl => $relationName);
3030          Confess("Unrecognized entity type $type in GenerateEntity.");  }
3031      } else {  
3032          my $entity = $metadata->{Entities}->{$type};  =head3 MatchSqlPattern
3033          my $fields = $entity->{Fields};  
3034          # Generate data from the fields.      my $matched = ERDB::MatchSqlPattern($value, $pattern);
3035          _GenerateFields($this, $fields, $type, $values);  
3036    Determine whether or not a specified value matches an SQL pattern. An SQL
3037    pattern has two wild card characters: C<%> that matches multiple characters,
3038    and C<_> that matches a single character. These can be escaped using a
3039    backslash (C<\>). We pull this off by converting the SQL pattern to a
3040    PERL regular expression. As per SQL rules, the match is case-insensitive.
3041    
3042    =over 4
3043    
3044    =item value
3045    
3046    Value to be matched against the pattern. Note that an undefined or empty
3047    value will not match anything.
3048    
3049    =item pattern
3050    
3051    SQL pattern against which to match the value. An undefined or empty pattern will
3052    match everything.
3053    
3054    =item RETURN
3055    
3056    Returns TRUE if the value and pattern match, else FALSE.
3057    
3058    =back
3059    
3060    =cut
3061    
3062    sub MatchSqlPattern {
3063        # Get the parameters.
3064        my ($value, $pattern) = @_;
3065        # Declare the return variable.
3066        my $retVal;
3067        # Insure we have a pattern.
3068        if (! defined($pattern) || $pattern eq "") {
3069            $retVal = 1;
3070        } else {
3071            # Break the pattern into pieces around the wildcard characters. Because we
3072            # use parentheses in the split function's delimiter expression, we'll get
3073            # list elements for the delimiters as well as the rest of the string.
3074            my @pieces = split /([_%]|\\[_%])/, $pattern;
3075            # Check some fast special cases.
3076            if ($pattern eq '%') {
3077                # A null pattern matches everything.
3078                $retVal = 1;
3079            } elsif (@pieces == 1) {
3080                # No wildcards, so we have a literal comparison. Note we're case-insensitive.
3081                $retVal = (lc($value) eq lc($pattern));
3082            } elsif (@pieces == 2 && $pieces[1] eq '%') {
3083                # A wildcard at the end, so we have a substring match. This is also case-insensitive.
3084                $retVal = (lc(substr($value, 0, length($pieces[0]))) eq lc($pieces[0]));
3085            } else {
3086                # Okay, we have to do it the hard way. Convert each piece to a PERL pattern.
3087                my $realPattern = "";
3088                for my $piece (@pieces) {
3089                    # Determine the type of piece.
3090                    if ($piece eq "") {
3091                        # Empty pieces are ignored.
3092                    } elsif ($piece eq "%") {
3093                        # Here we have a multi-character wildcard. Note that it can match
3094                        # zero or more characters.
3095                        $realPattern .= ".*"
3096                    } elsif ($piece eq "_") {
3097                        # Here we have a single-character wildcard.
3098                        $realPattern .= ".";
3099                    } elsif ($piece eq "\\%" || $piece eq "\\_") {
3100                        # This is an escape sequence (which is a rare thing, actually).
3101                        $realPattern .= substr($piece, 1, 1);
3102                    } else {
3103                        # Here we have raw text.
3104                        $realPattern .= quotemeta($piece);
3105                    }
3106      }      }
3107      # Return the hash created.              # Do the match.
3108      return $this;              $retVal = ($value =~ /^$realPattern$/i ? 1 : 0);
3109            }
3110        }
3111        # Return the result.
3112        return $retVal;
3113  }  }
3114    
3115  =head3 GetEntity  =head3 GetEntity
3116    
3117  C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>      my $entityObject = $erdb->GetEntity($entityType, $ID);
3118    
3119  Return an object describing the entity instance with a specified ID.  Return an object describing the entity instance with a specified ID.
3120    
# Line 1925  Line 3130 
3130    
3131  =item RETURN  =item RETURN
3132    
3133  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
3134  instance is found with the specified key.  instance is found with the specified key.
3135    
3136  =back  =back
# Line 1945  Line 3150 
3150    
3151  =head3 GetChoices  =head3 GetChoices
3152    
3153  C<< my @values = $erdb->GetChoices($entityName, $fieldName); >>      my @values = $erdb->GetChoices($entityName, $fieldName);
3154    
3155  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
3156  specified entity.  specified entity.
# Line 2000  Line 3205 
3205    
3206  =head3 GetEntityValues  =head3 GetEntityValues
3207    
3208  C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>      my @values = $erdb->GetEntityValues($entityType, $ID, \@fields);
3209    
3210  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
3211  does not exist, an empty list is returned.  does not exist, an empty list is returned.
# Line 2044  Line 3249 
3249    
3250  =head3 GetAll  =head3 GetAll
3251    
3252  C<< my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>      my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count);
3253    
3254  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
3255  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 2058  Line 3263 
3263  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
3264  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
3265  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
3266  feature ID followed by all of its aliases.  feature ID followed by all of its essentiality determinations.
3267    
3268  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)']);
3269    
3270  =over 4  =over 4
3271    
# Line 2138  Line 3343 
3343    
3344  =head3 Exists  =head3 Exists
3345    
3346  C<< my $found = $sprout->Exists($entityName, $entityID); >>      my $found = $sprout->Exists($entityName, $entityID);
3347    
3348  Return TRUE if an entity exists, else FALSE.  Return TRUE if an entity exists, else FALSE.
3349    
# Line 2173  Line 3378 
3378    
3379  =head3 EstimateRowSize  =head3 EstimateRowSize
3380    
3381  C<< my $rowSize = $erdb->EstimateRowSize($relName); >>      my $rowSize = $erdb->EstimateRowSize($relName);
3382    
3383  Estimate the row size of the specified relation. The estimated row size is computed by adding  Estimate the row size of the specified relation. The estimated row size is computed by adding
3384  up the average length for each data type.  up the average length for each data type.
# Line 2211  Line 3416 
3416    
3417  =head3 GetFieldTable  =head3 GetFieldTable
3418    
3419  C<< my $fieldHash = $self->GetFieldTable($objectnName); >>      my $fieldHash = $self->GetFieldTable($objectnName);
3420    
3421  Get the field structure for a specified entity or relationship.  Get the field structure for a specified entity or relationship.
3422    
# Line 2238  Line 3443 
3443      return $objectData->{Fields};      return $objectData->{Fields};
3444  }  }
3445    
3446    =head3 SplitKeywords
3447    
3448        my @keywords = ERDB::SplitKeywords($keywordString);
3449    
3450    This method returns a list of the positive keywords in the specified
3451    keyword string. All of the operators will have been stripped off,
3452    and if the keyword is preceded by a minus operator (C<->), it will
3453    not be in the list returned. The idea here is to get a list of the
3454    keywords the user wants to see. The list will be processed to remove
3455    duplicates.
3456    
3457    It is possible to create a string that confuses this method. For example
3458    
3459        frog toad -frog
3460    
3461    would return both C<frog> and C<toad>. If this is a problem we can deal
3462    with it later.
3463    
3464    =over 4
3465    
3466    =item keywordString
3467    
3468    The keyword string to be parsed.
3469    
3470    =item RETURN
3471    
3472    Returns a list of the words in the keyword string the user wants to
3473    see.
3474    
3475    =back
3476    
3477    =cut
3478    
3479    sub SplitKeywords {
3480        # Get the parameters.
3481        my ($keywordString) = @_;
3482        # Make a safety copy of the string. (This helps during debugging.)
3483        my $workString = $keywordString;
3484        # Convert operators we don't care about to spaces.
3485        $workString =~ tr/+"()<>/ /;
3486        # Split the rest of the string along space boundaries. Note that we
3487        # eliminate any words that are zero length or begin with a minus sign.
3488        my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
3489        # Use a hash to remove duplicates.
3490        my %words = map { $_ => 1 } @wordList;
3491        # Return the result.
3492        return sort keys %words;
3493    }
3494    
3495    =head3 ValidateFieldName
3496    
3497        my $okFlag = ERDB::ValidateFieldName($fieldName);
3498    
3499    Return TRUE if the specified field name is valid, else FALSE. Valid field names must
3500    be hyphenated words subject to certain restrictions.
3501    
3502    =over 4
3503    
3504    =item fieldName
3505    
3506    Field name to be validated.
3507    
3508    =item RETURN
3509    
3510    Returns TRUE if the field name is valid, else FALSE.
3511    
3512    =back
3513    
3514    =cut
3515    
3516    sub ValidateFieldName {
3517        # Get the parameters.
3518        my ($fieldName) = @_;
3519        # Declare the return variable. The field name is valid until we hear
3520        # differently.
3521        my $retVal = 1;
3522        # Compute the maximum name length.
3523        my $maxLen = $TypeTable{'name-string'}->{maxLen};
3524        # Look for bad stuff in the name.
3525        if ($fieldName =~ /--/) {
3526            # Here we have a doubled minus sign.
3527            Trace("Field name $fieldName has a doubled hyphen.") if T(1);
3528            $retVal = 0;
3529        } elsif ($fieldName !~ /^[A-Za-z]/) {
3530            # Here the field name is missing the initial letter.
3531            Trace("Field name $fieldName does not begin with a letter.") if T(1);
3532            $retVal = 0;
3533        } elsif (length($fieldName) > $maxLen) {
3534            # Here the field name is too long.
3535            Trace("Maximum field name length is $maxLen. Field name must be truncated to " . substr($fieldName,0, $maxLen) . ".");
3536        } else {
3537            # Strip out the minus signs. Everything remaining must be a letter,
3538            # underscore, or digit.
3539            my $strippedName = $fieldName;
3540            $strippedName =~ s/-//g;
3541            if ($strippedName !~ /^(\w|\d)+$/) {
3542                Trace("Field name $fieldName contains illegal characters.") if T(1);
3543                $retVal = 0;
3544            }
3545        }
3546        # Return the result.
3547        return $retVal;
3548    }
3549    
3550    =head3 ReadMetaXML
3551    
3552        my $rawMetaData = ERDB::ReadDBD($fileName);
3553    
3554    This method reads a raw database definition XML file and returns it.
3555    Normally, the metadata used by the ERDB system has been processed and
3556    modified to make it easier to load and retrieve the data; however,
3557    this method can be used to get the data in its raw form.
3558    
3559    =over 4
3560    
3561    =item fileName
3562    
3563    Name of the XML file to read.
3564    
3565    =item RETURN
3566    
3567    Returns a hash reference containing the raw XML data from the specified file.
3568    
3569    =back
3570    
3571    =cut
3572    
3573    sub ReadMetaXML {
3574        # Get the parameters.
3575        my ($fileName) = @_;
3576        # Read the XML.
3577        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
3578        Trace("XML metadata loaded from file $fileName.") if T(1);
3579        # Return the result.
3580        return $retVal;
3581    }
3582    
3583    =head3 GetEntityFieldHash
3584    
3585        my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName);
3586    
3587    Get the field hash of the named entity in the specified raw XML structure.
3588    The field hash may not exist, in which case we need to create it.
3589    
3590    =over 4
3591    
3592    =item structure
3593    
3594    Raw XML structure defininng the database. This is not the run-time XML used by
3595    an ERDB object, since that has all sorts of optimizations built-in.
3596    
3597    =item entityName
3598    
3599    Name of the entity whose field structure is desired.
3600    
3601    =item RETURN
3602    
3603    Returns the field hash used to define the entity's fields.
3604    
3605    =back
3606    
3607    =cut
3608    
3609    sub GetEntityFieldHash {
3610        # Get the parameters.
3611        my ($structure, $entityName) = @_;
3612        # Get the entity structure.
3613        my $entityData = $structure->{Entities}->{$entityName};
3614        # Look for a field structure.
3615        my $retVal = $entityData->{Fields};
3616        # If it doesn't exist, create it.
3617        if (! defined($retVal)) {
3618            $entityData->{Fields} = {};
3619            $retVal = $entityData->{Fields};
3620        }
3621        # Return the result.
3622        return $retVal;
3623    }
3624    
3625    =head3 WriteMetaXML
3626    
3627        ERDB::WriteMetaXML($structure, $fileName);
3628    
3629    Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
3630    used to update the database definition. It must be used with care, however, since it
3631    will only work on a raw structure, not on the processed structure created by an ERDB
3632    constructor.
3633    
3634    =over 4
3635    
3636    =item structure
3637    
3638    XML structure to be written to the file.
3639    
3640    =item fileName
3641    
3642    Name of the output file to which the updated XML should be stored.
3643    
3644    =back
3645    
3646    =cut
3647    
3648    sub WriteMetaXML {
3649        # Get the parameters.
3650        my ($structure, $fileName) = @_;
3651        # Compute the output.
3652        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
3653        # Write it to the file.
3654        my $xmlOut = Open(undef, ">$fileName");
3655        print $xmlOut $fileString;
3656    }
3657    
3658    
3659    =head3 HTMLNote
3660    
3661    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
3662    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
3663    Except for C<[p]>, all the codes are closed by slash-codes. So, for
3664    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
3665    
3666        my $realHtml = ERDB::HTMLNote($dataString);
3667    
3668    =over 4
3669    
3670    =item dataString
3671    
3672    String to convert to HTML.
3673    
3674    =item RETURN
3675    
3676    An HTML string derived from the input string.
3677    
3678    =back
3679    
3680    =cut
3681    
3682    sub HTMLNote {
3683        # Get the parameter.
3684        my ($dataString) = @_;
3685        # HTML-escape the text.
3686        my $retVal = CGI::escapeHTML($dataString);
3687        # Substitute the bulletin board codes.
3688        $retVal =~ s!\[(/?[bi])\]!<$1>!g;
3689        $retVal =~ s!\[p\]!</p><p>!g;
3690        $retVal =~ s!\[link\s+([^\]]+)\]!<a href="$1">!g;
3691        $retVal =~ s!\[/link\]!</a>!g;
3692        # Return the result.
3693        return $retVal;
3694    }
3695    
3696    =head3 WikiNote
3697    
3698    Convert a note or comment to Wiki text by replacing some bulletin-board codes with HTML. The codes
3699    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
3700    Except for C<[p]>, all the codes are closed by slash-codes. So, for
3701    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
3702    
3703        my $wikiText = ERDB::WikiNote($dataString);
3704    
3705    =over 4
3706    
3707    =item dataString
3708    
3709    String to convert to Wiki text.
3710    
3711    =item RETURN
3712    
3713    An Wiki text string derived from the input string.
3714    
3715    =back
3716    
3717    =cut
3718    
3719    sub WikiNote {
3720        # Get the parameter.
3721        my ($dataString) = @_;
3722        # HTML-escape the text.
3723        my $retVal = CGI::escapeHTML($dataString);
3724        # Substitute the bulletin board codes.
3725        my $italic = WikiTools::ItalicCode();
3726        $retVal =~ s/\[\/?i\]/$italic/g;
3727        my $bold = WikiTools::BoldCode();
3728        $retVal =~ s/\[\/?b\]/$bold/g;
3729        # Paragraph breaks are the same no matter which Wiki you're using.
3730        $retVal =~ s!\[p\]!\n\n!g;
3731        # Now we do the links, which are complicated by the need to know two
3732        # things: the target URL and the text.
3733        while ($retVal =~ /\[link\s+([^\]]+)\]([^\[]+)\[\/link\]/g) {
3734            # Replace the matched string with the Wiki markup for links. Note that
3735            # $-[0] is the starting position of the match for the entire expression,
3736            # and $+[0] is past the ending position.
3737            substr $retVal, $-[0], $+[0] - $-[0], WikiTools::LinkMarkup($1, $2);
3738        }
3739        # Return the result.
3740        return $retVal;
3741    }
3742    
3743    =head3 BeginTran
3744    
3745        $erdb->BeginTran();
3746    
3747    Start a database transaction.
3748    
3749    =cut
3750    
3751    sub BeginTran {
3752        my ($self) = @_;
3753        $self->{_dbh}->begin_tran();
3754    
3755    }
3756    
3757    =head3 CommitTran
3758    
3759        $erdb->CommitTran();
3760    
3761    Commit an active database transaction.
3762    
3763    =cut
3764    
3765    sub CommitTran {
3766        my ($self) = @_;
3767        $self->{_dbh}->commit_tran();
3768    }
3769    
3770    =head3 RollbackTran
3771    
3772        $erdb->RollbackTran();
3773    
3774    Roll back an active database transaction.
3775    
3776    =cut
3777    
3778    sub RollbackTran {
3779        my ($self) = @_;
3780        $self->{_dbh}->roll_tran();
3781    }
3782    
3783    =head3 UpdateField
3784    
3785        my $count = $erdb->UpdateField($objectNames, $fieldName, $oldValue, $newValue, $filter, $parms);
3786    
3787    Update all occurrences of a specific field value to a new value. The number of rows changed will be
3788    returned.
3789    
3790    =over 4
3791    
3792    =item fieldName
3793    
3794    Name of the field in standard I<objectName>C<(>I<fieldName>C<)> format.
3795    
3796    =item oldValue
3797    
3798    Value to be modified. All occurrences of this value in the named field will be replaced by the
3799    new value.
3800    
3801    =item newValue
3802    
3803    New value to be substituted for the old value when it's found.
3804    
3805    =item filter
3806    
3807    A standard ERDB filter clause (see L</Get>). The filter will be applied before any substitutions take place.
3808    
3809    =item parms
3810    
3811    Reference to a list of parameter values in the filter.
3812    
3813    =item RETURN
3814    
3815    Returns the number of rows modified.
3816    
3817    =back
3818    
3819    =cut
3820    
3821    sub UpdateField {
3822        # Get the parameters.
3823        my ($self, $fieldName, $oldValue, $newValue, $filter, $parms) = @_;
3824        # Get the object and field names from the field name parameter.
3825        $fieldName =~ /^([^(]+)\(([^)]+)\)/;
3826        my $objectName = $1;
3827        my $realFieldName = _FixName($2);
3828        # Add the old value to the filter. Note we allow the possibility that no
3829        # filter was specified.
3830        my $realFilter = "$fieldName = ?";
3831        if ($filter) {
3832            $realFilter .= " AND $filter";
3833        }
3834        # Format the query filter.
3835        my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
3836            $self->_SetupSQL([$objectName], $realFilter);
3837        # Create the query. Since there is only one object name, the mapped-name data is not
3838        # necessary. Neither is the FROM clause.
3839        $suffix =~ s/^FROM.+WHERE\s+//;
3840        # Create the update statement.
3841        my $command = "UPDATE $objectName SET $realFieldName = ? WHERE $suffix";
3842        # Get the database handle.
3843        my $dbh = $self->{_dbh};
3844        # Add the old and new values to the parameter list. Note we allow the possibility that
3845        # there are no user-supplied parameters.
3846        my @params = ($newValue, $oldValue);
3847        if (defined $parms) {
3848            push @params, @{$parms};
3849        }
3850        # Execute the update.
3851        my $retVal = $dbh->SQL($command, 0, @params);
3852        # Make the funky zero a real zero.
3853        if ($retVal == 0) {
3854            $retVal = 0;
3855        }
3856        # Return the result.
3857        return $retVal;
3858    }
3859    
3860    
3861  =head2 Data Mining Methods  =head2 Data Mining Methods
3862    
3863  =head3 GetUsefulCrossValues  =head3 GetUsefulCrossValues
3864    
3865  C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>      my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship);
3866    
3867  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
3868  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 2298  Line 3918 
3918      # Push these onto the return list.      # Push these onto the return list.
3919      push @retVal, sort @fieldList2;      push @retVal, sort @fieldList2;
3920      # Return the result.      # Return the result.
3921      return @retVal;      return @retVal;
3922    }
3923    
3924    =head3 FindColumn
3925    
3926        my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier);
3927    
3928    Return the location a desired column in a data mining header line. The data
3929    mining header line is a tab-separated list of column names. The column
3930    identifier is either the numerical index of a column or the actual column
3931    name.
3932    
3933    =over 4
3934    
3935    =item headerLine
3936    
3937    The header line from a data mining command, which consists of a tab-separated
3938    list of column names.
3939    
3940    =item columnIdentifier
3941    
3942    Either the ordinal number of the desired column (1-based), or the name of the
3943    desired column.
3944    
3945    =item RETURN
3946    
3947    Returns the array index (0-based) of the desired column.
3948    
3949    =back
3950    
3951    =cut
3952    
3953    sub FindColumn {
3954        # Get the parameters.
3955        my ($headerLine, $columnIdentifier) = @_;
3956        # Declare the return variable.
3957        my $retVal;
3958        # Split the header line into column names.
3959        my @headers = ParseColumns($headerLine);
3960        # Determine whether we have a number or a name.
3961        if ($columnIdentifier =~ /^\d+$/) {
3962            # Here we have a number. Subtract 1 and validate the result.
3963            $retVal = $columnIdentifier - 1;
3964            if ($retVal < 0 || $retVal > $#headers) {
3965                Confess("Invalid column identifer \"$columnIdentifier\": value out of range.");
3966            }
3967        } else {
3968            # Here we have a name. We need to find it in the list.
3969            for (my $i = 0; $i <= $#headers && ! defined($retVal); $i++) {
3970                if ($headers[$i] eq $columnIdentifier) {
3971                    $retVal = $i;
3972                }
3973            }
3974            if (! defined($retVal)) {
3975                Confess("Invalid column identifier \"$columnIdentifier\": value not found.");
3976            }
3977        }
3978        # Return the result.
3979        return $retVal;
3980    }
3981    
3982    =head3 ParseColumns
3983    
3984        my @columns = ERDB::ParseColumns($line);
3985    
3986    Convert the specified data line to a list of columns.
3987    
3988    =over 4
3989    
3990    =item line
3991    
3992    A data mining input, consisting of a tab-separated list of columns terminated by a
3993    new-line.
3994    
3995    =item RETURN
3996    
3997    Returns a list consisting of the column values.
3998    
3999    =back
4000    
4001    =cut
4002    
4003    sub ParseColumns {
4004        # Get the parameters.
4005        my ($line) = @_;
4006        # Chop off the line-end.
4007        chomp $line;
4008        # Split it into a list.
4009        my @retVal = split(/\t/, $line);
4010        # Return the result.
4011        return @retVal;
4012    }
4013    
4014    =head2 Virtual Methods
4015    
4016    =head3 _CreatePPOIndex
4017    
4018        my $index = ERDB::_CreatePPOIndex($indexObject);
4019    
4020    Convert the XML for an ERDB index to the XML structure for a PPO
4021    index.
4022    
4023    =over 4
4024    
4025    =item indexObject
4026    
4027    ERDB XML structure for an index.
4028    
4029    =item RETURN
4030    
4031    PPO XML structure for the same index.
4032    
4033    =back
4034    
4035    =cut
4036    
4037    sub _CreatePPOIndex {
4038        # Get the parameters.
4039        my ($indexObject) = @_;
4040        # The incoming index contains a list of the index fields in the IndexFields
4041        # member. We loop through it to create the index tags.
4042        my @fields = map { { label => _FixName($_->{name}) } } @{$indexObject->{IndexFields}};
4043        # Wrap the fields in attribute tags.
4044        my $retVal = { attribute => \@fields };
4045        # Return the result.
4046        return $retVal;
4047    }
4048    
4049    =head3 _CreatePPOField
4050    
4051        my $fieldXML = ERDB::_CreatePPOField($fieldName, $fieldObject);
4052    
4053    Convert the ERDB XML structure for a field to a PPO scalar XML structure.
4054    
4055    =over 4
4056    
4057    =item fieldName
4058    
4059    Name of the scalar field.
4060    
4061    =item fieldObject
4062    
4063    ERDB XML structure describing the field.
4064    
4065    =item RETURN
4066    
4067    Returns a PPO XML structure for the same field.
4068    
4069    =back
4070    
4071    =cut
4072    
4073    sub _CreatePPOField {
4074        # Get the parameters.
4075        my ($fieldName, $fieldObject) = @_;
4076        # Get the field type.
4077        my $type = $TypeTable{$fieldObject->{type}}->{sqlType};
4078        # Fix up the field name.
4079        $fieldName = _FixName($fieldName);
4080        # Build the scalar tag.
4081        my $retVal = { label => $fieldName, type => $type };
4082        # Return the result.
4083        return $retVal;
4084  }  }
4085    
4086  =head3 FindColumn  =head3 CleanKeywords
4087    
4088  C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>      my $cleanedString = $erdb->CleanKeywords($searchExpression);
4089    
4090  Return the location a desired column in a data mining header line. The data  Clean up a search expression or keyword list. This is a virtual method that may
4091  mining header line is a tab-separated list of column names. The column  be overridden by the subclass. The base-class method removes extra spaces
4092  identifier is either the numerical index of a column or the actual column  and converts everything to lower case.
 name.  
4093    
4094  =over 4  =over 4
4095    
4096  =item headerLine  =item searchExpression
   
 The header line from a data mining command, which consists of a tab-separated  
 list of column names.  
   
 =item columnIdentifier  
4097    
4098  Either the ordinal number of the desired column (1-based), or the name of the  Search expression or keyword list to clean. Note that a search expression may
4099  desired column.  contain boolean operators which need to be preserved. This includes leading
4100    minus signs.
4101    
4102  =item RETURN  =item RETURN
4103    
4104  Returns the array index (0-based) of the desired column.  Cleaned expression or keyword list.
4105    
4106  =back  =back
4107    
4108  =cut  =cut
4109    
4110  sub FindColumn {  sub CleanKeywords {
4111      # Get the parameters.      # Get the parameters.
4112      my ($headerLine, $columnIdentifier) = @_;      my ($self, $searchExpression) = @_;
4113      # Declare the return variable.      # Lower-case the expression and copy it into the return variable. Note that we insure we
4114      my $retVal;      # don't accidentally end up with an undefined value.
4115      # Split the header line into column names.      my $retVal = lc($searchExpression || "");
4116      my @headers = ParseColumns($headerLine);      # Remove extra spaces.
4117      # Determine whether we have a number or a name.      $retVal =~ s/\s+/ /g;
4118      if ($columnIdentifier =~ /^\d+$/) {      $retVal =~ s/(^\s+)|(\s+$)//g;
         # Here we have a number. Subtract 1 and validate the result.  
         $retVal = $columnIdentifier - 1;  
         if ($retVal < 0 || $retVal > $#headers) {  
             Confess("Invalid column identifer \"$columnIdentifier\": value out of range.");  
         }  
     } else {  
         # Here we have a name. We need to find it in the list.  
         for (my $i = 0; $i <= $#headers && ! defined($retVal); $i++) {  
             if ($headers[$i] eq $columnIdentifier) {  
                 $retVal = $i;  
             }  
         }  
         if (! defined($retVal)) {  
             Confess("Invalid column identifier \"$columnIdentifier\": value not found.");  
         }  
     }  
4119      # Return the result.      # Return the result.
4120      return $retVal;      return $retVal;
4121  }  }
4122    
4123  =head3 ParseColumns  =head3 GetSourceObject
4124    
4125  C<< my @columns = ERDB::ParseColumns($line); >>      my $source = $erdb->GetSourceObject($entityName);
4126    
4127  Convert the specified data line to a list of columns.  Return the object to be used in loading special attributes of the specified entity. The
4128    algorithm for loading special attributes is stored in the C<DataGen> elements of the
4129    XML
4130    
4131    =head2 Internal Utility Methods
4132    
4133    =head3 _RelationMap
4134    
4135        my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
4136    
4137    Create the relation map for an SQL query. The relation map is used by B<ERDBObject>
4138    to determine how to interpret the results of the query.
4139    
4140  =over 4  =over 4
4141    
4142  =item line  =item mappedNameHashRef
4143    
4144  A data mining input, consisting of a tab-separated list of columns terminated by a  Reference to a hash that maps modified object names to real object names.
4145  new-line.  
4146    =item mappedNameListRef
4147    
4148    Reference to a list of modified object names in the order they appear in the
4149    SELECT list.
4150    
4151  =item RETURN  =item RETURN
4152    
4153  Returns a list consisting of the column values.  Returns a list of 2-tuples. Each tuple consists of an object name as used in the
4154    query followed by the actual name of that object. This enables the B<ERDBObject> to
4155    determine the order of the tables in the query and which object name belongs to each
4156    mapped object name. Most of the time these two values are the same; however, if a
4157    relation occurs twice in the query, the relation name in the field list and WHERE
4158    clause will use a mapped name (generally the actual relation name with a numeric
4159    suffix) that does not match the actual relation name.
4160    
4161  =back  =back
4162    
4163  =cut  =cut
4164    
4165  sub ParseColumns {  sub _RelationMap {
4166      # Get the parameters.      # Get the parameters.
4167      my ($line) = @_;      my ($mappedNameHashRef, $mappedNameListRef) = @_;
4168      # Chop off the line-end.      # Declare the return variable.
4169      chomp $line;      my @retVal = ();
4170      # Split it into a list.      # Build the map.
4171      my @retVal = split(/\t/, $line);      for my $mappedName (@{$mappedNameListRef}) {
4172      # Return the result.          push @retVal, [$mappedName, $mappedNameHashRef->{$mappedName}];
4173        }
4174        # Return it.
4175      return @retVal;      return @retVal;
4176  }  }
4177    
 =head2 Internal Utility Methods  
4178    
4179  =head3 SetupSQL  =head3 _SetupSQL
4180    
4181  Process a list of object names and a filter clause so that they can be used to  Process a list of object names and a filter clause so that they can be used to
4182  build an SQL statement. This method takes in a reference to a list of object names  build an SQL statement. This method takes in a reference to a list of object names
# Line 2413  Line 4196 
4196  A string containing the WHERE clause for the query (without the C<WHERE>) and also  A string containing the WHERE clause for the query (without the C<WHERE>) and also
4197  optionally the C<ORDER BY> and C<LIMIT> clauses.  optionally the C<ORDER BY> and C<LIMIT> clauses.
4198    
4199    =item matchClause
4200    
4201    An optional full-text search clause. If specified, it will be inserted at the
4202    front of the WHERE clause. It should already be SQL-formatted; that is, the
4203    field names should be in the form I<table>C<.>I<fieldName>.
4204    
4205  =item RETURN  =item RETURN
4206    
4207  Returns a three-element list. The first element is the SQL statement suffix, beginning  Returns a three-element list. The first element is the SQL statement suffix, beginning
# Line 2425  Line 4214 
4214  =cut  =cut
4215    
4216  sub _SetupSQL {  sub _SetupSQL {
4217      my ($self, $objectNames, $filterClause) = @_;      my ($self, $objectNames, $filterClause, $matchClause) = @_;
4218      # Adjust the list of object names to account for multiple occurrences of the      # Adjust the list of object names to account for multiple occurrences of the
4219      # same object. We start with a hash table keyed on object name that will      # same object. We start with a hash table keyed on object name that will
4220      # return the object suffix. The first time an object is encountered it will      # return the object suffix. The first time an object is encountered it will
# Line 2474  Line 4263 
4263      # FROM name1, name2, ... nameN      # FROM name1, name2, ... nameN
4264      #      #
4265      my $suffix = "FROM " . join(', ', @fromList);      my $suffix = "FROM " . join(', ', @fromList);
4266        # Now for the WHERE. First, we need a place for the filter string.
4267        my $filterString = "";
4268        # We will also keep a list of conditions to add to the WHERE clause in order to link
4269        # entities and relationships as well as primary relations to secondary ones.
4270        my @joinWhere = ();
4271      # Check for a filter clause.      # Check for a filter clause.
4272      if ($filterClause) {      if ($filterClause) {
4273          # Here we have one, so we convert its field names and add it to the query. First,          # Here we have one, so we convert its field names and add it to the query. First,
4274          # We create a copy of the filter string we can work with.          # We create a copy of the filter string we can work with.
4275          my $filterString = $filterClause;          $filterString = $filterClause;
4276          # Next, we sort the object names by length. This helps protect us from finding          # Next, we sort the object names by length. This helps protect us from finding
4277          # object names inside other object names when we're doing our search and replace.          # object names inside other object names when we're doing our search and replace.
4278          my @sortedNames = sort { length($b) - length($a) } @mappedNameList;          my @sortedNames = sort { length($b) - length($a) } @mappedNameList;
         # We will also keep a list of conditions to add to the WHERE clause in order to link  
         # entities and relationships as well as primary relations to secondary ones.  
         my @joinWhere = ();  
4279          # The final preparatory step is to create a hash table of relation names. The          # The final preparatory step is to create a hash table of relation names. The
4280          # table begins with the relation names already in the SELECT command. We may          # table begins with the relation names already in the SELECT command. We may
4281          # need to add relations later if there is filtering on a field in a secondary          # need to add relations later if there is filtering on a field in a secondary
# Line 2552  Line 4343 
4343                  }                  }
4344              }              }
4345          }          }
4346        }
4347          # The next step is to join the objects together. We only need to do this if there          # The next step is to join the objects together. We only need to do this if there
4348          # is more than one object in the object list. We start with the first object and          # is more than one object in the object list. We start with the first object and
4349          # run through the objects after it. Note also that we make a safety copy of the          # run through the objects after it. Note also that we make a safety copy of the
4350          # list before running through it.      # list before running through it, because we shift off the first object before
4351        # processing the rest.
4352          my @mappedObjectList = @mappedNameList;          my @mappedObjectList = @mappedNameList;
4353          my $lastMappedObject = shift @mappedObjectList;          my $lastMappedObject = shift @mappedObjectList;
4354          # Get the join table.          # Get the join table.
# Line 2584  Line 4377 
4377          # here is we want the filter clause to be empty if there's no WHERE filter.          # here is we want the filter clause to be empty if there's no WHERE filter.
4378          # We'll put the ORDER BY / LIMIT clauses in the following variable.          # We'll put the ORDER BY / LIMIT clauses in the following variable.
4379          my $orderClause = "";          my $orderClause = "";
4380        # This is only necessary if we have a filter string in which the ORDER BY
4381        # and LIMIT clauses can live.
4382        if ($filterString) {
4383          # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy          # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy
4384          # operator so that we find the first occurrence of either verb.          # operator so that we find the first occurrence of either verb.
4385          if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {          if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {
# Line 2592  Line 4388 
4388              $orderClause = $2 . substr($filterString, $pos);              $orderClause = $2 . substr($filterString, $pos);
4389              $filterString = $1;              $filterString = $1;
4390          }          }
4391          # Add the filter and the join clauses (if any) to the SELECT command.      }
4392        # All the things that are supposed to be in the WHERE clause of the
4393        # SELECT command need to be put into @joinWhere so we can string them
4394        # together. We begin with the match clause. This is important,
4395        # because the match clause's parameter mark must precede any parameter
4396        # marks in the filter string.
4397        if ($matchClause) {
4398            push @joinWhere, $matchClause;
4399        }
4400        # Add the filter string. We put it in parentheses to avoid operator
4401        # precedence problems with the match clause or the joins.
4402          if ($filterString) {          if ($filterString) {
4403              Trace("Filter string is \"$filterString\".") if T(4);              Trace("Filter string is \"$filterString\".") if T(4);
4404              push @joinWhere, "($filterString)";              push @joinWhere, "($filterString)";
4405          }          }
4406        # String it all together into a big filter clause.
4407          if (@joinWhere) {          if (@joinWhere) {
4408              $suffix .= " WHERE " . join(' AND ', @joinWhere);              $suffix .= " WHERE " . join(' AND ', @joinWhere);
4409          }          }
4410          # Add the sort or limit clause (if any) to the SELECT command.      # Add the sort or limit clause (if any).
4411          if ($orderClause) {          if ($orderClause) {
4412              $suffix .= " $orderClause";              $suffix .= " $orderClause";
4413          }          }
     }  
4414      # Return the suffix, the mapped name list, and the mapped name hash.      # Return the suffix, the mapped name list, and the mapped name hash.
4415      return ($suffix, \@mappedNameList, \%mappedNameHash);      return ($suffix, \@mappedNameList, \%mappedNameHash);
4416  }  }
4417    
4418  =head3 GetStatementHandle  =head3 _GetStatementHandle
4419    
4420  This method will prepare and execute an SQL query, returning the statement handle.  This method will prepare and execute an SQL query, returning the statement handle.
4421  The main reason for doing this here is so that everybody who does SQL queries gets  The main reason for doing this here is so that everybody who does SQL queries gets
# Line 2639  Line 4445 
4445  sub _GetStatementHandle {  sub _GetStatementHandle {
4446      # Get the parameters.      # Get the parameters.
4447      my ($self, $command, $params) = @_;      my ($self, $command, $params) = @_;
4448        Confess("Invalid parameter list.") if (! defined($params) || ref($params) ne 'ARRAY');
4449      # Trace the query.      # Trace the query.
4450      Trace("SQL query: $command") if T(SQL => 3);      Trace("SQL query: $command") if T(SQL => 3);
4451      Trace("PARMS: '" . (join "', '", @{$params}) . "'") if (T(SQL => 4) && (@{$params} > 0));      Trace("PARMS: '" . (join "', '", @{$params}) . "'") if (T(SQL => 4) && (@{$params} > 0));
# Line 2647  Line 4454 
4454      # Prepare the command.      # Prepare the command.
4455      my $sth = $dbh->prepare_command($command);      my $sth = $dbh->prepare_command($command);
4456      # Execute it with the parameters bound in.      # Execute it with the parameters bound in.
4457      $sth->execute(@{$params}) || Confess("SELECT error" . $sth->errstr());      $sth->execute(@{$params}) || Confess("SELECT error:  " . $sth->errstr());
4458      # Return the statement handle.      # Return the statement handle.
4459      return $sth;      return $sth;
4460  }  }
4461    
4462  =head3 GetLoadStats  =head3 _GetLoadStats
4463    
4464  Return a blank statistics object for use by the load methods.  Return a blank statistics object for use by the load methods.
4465    
# Line 2664  Line 4471 
4471      return Stats->new();      return Stats->new();
4472  }  }
4473    
4474  =head3 GenerateFields  =head3 _DumpRelation
   
 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;  
             }  
         }  
     }  
 }  
   
 =head3 DumpRelation  
4475    
4476  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.
4477    
4478  This is an instance method.  This is an instance method.
4479    
# Line 2788  Line 4521 
4521      close DTXOUT;      close DTXOUT;
4522  }  }
4523    
4524  =head3 GetStructure  =head3 _GetStructure
4525    
4526  Get the data structure for a specified entity or relationship.  Get the data structure for a specified entity or relationship.
4527    
# Line 2827  Line 4560 
4560      return $retVal;      return $retVal;
4561  }  }
4562    
4563  =head3 GetRelationTable  
4564    
4565    =head3 _GetRelationTable
4566    
4567  Get the list of relations for a specified entity or relationship.  Get the list of relations for a specified entity or relationship.
4568    
# Line 2856  Line 4591 
4591      return $objectData->{Relations};      return $objectData->{Relations};
4592  }  }
4593    
4594  =head3 ValidateFieldNames  =head3 _ValidateFieldNames
4595    
4596  Determine whether or not the field names are valid. A description of the problems with the names  Determine whether or not the field names are valid. A description of the problems with the names
4597  will be written to the standard error output. If there is an error, this method will abort. This is  will be written to the standard error output. If there is an error, this method will abort. This is
# Line 2883  Line 4618 
4618          for my $object (values %{$metadata->{$section}}) {          for my $object (values %{$metadata->{$section}}) {
4619              # Loop through the object's fields.              # Loop through the object's fields.
4620              for my $fieldName (keys %{$object->{Fields}}) {              for my $fieldName (keys %{$object->{Fields}}) {
4621                  # Now we make some initial validations.                  # If this field name is invalid, set the return value to zero
4622                  if ($fieldName =~ /--/) {                  # so we know we encountered an error.
4623                      # Here we have a doubled minus sign.                  if (! ValidateFieldName($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";  
4624                          $retVal = 0;                          $retVal = 0;
4625                      }                      }
4626                  }                  }
4627              }              }
4628          }          }
     }  
4629      # If an error was found, fail.      # If an error was found, fail.
4630      if ($retVal  == 0) {      if ($retVal  == 0) {
4631          Confess("Errors found in field names.");          Confess("Errors found in field names.");
4632      }      }
4633  }  }
4634    
4635  =head3 LoadRelation  =head3 _LoadRelation
4636    
4637  Load a relation from the data in a tab-delimited disk file. The load will only take place if a disk  Load a relation from the data in a tab-delimited disk file. The load will only take place if a disk
4638  file with the same name as the relation exists in the specified directory.  file with the same name as the relation exists in the specified directory.
# Line 2962  Line 4683 
4683      # be a null string.      # be a null string.
4684      if ($fileName ne "") {      if ($fileName ne "") {
4685          # Load the relation from the file.          # Load the relation from the file.
4686          $retVal = $self->LoadTable($fileName, $relationName, $rebuild);          $retVal = $self->LoadTable($fileName, $relationName, truncate => $rebuild);
4687      } elsif ($rebuild) {      } elsif ($rebuild) {
4688          # 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.
4689          $self->CreateTable($relationName, 1);          $self->CreateTable($relationName, 1);
# Line 2971  Line 4692 
4692      return $retVal;      return $retVal;
4693  }  }
4694    
4695  =head3 LoadMetaData  
4696    =head3 _LoadMetaData
4697    
4698        my $metadata = ERDB::_LoadMetaData($filename);
4699    
4700  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.
4701  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
# Line 2996  Line 4720 
4720  sub _LoadMetaData {  sub _LoadMetaData {
4721      # Get the parameters.      # Get the parameters.
4722      my ($filename) = @_;      my ($filename) = @_;
4723      Trace("Reading Sprout DBD from $filename.") if T(2);      Trace("Reading DBD from $filename.") if T(2);
4724      # 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
4725      # get the exact structure we want.      # get the exact structure we want.
4726      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 $filename.") if T(1);  
4727      # Before we go any farther, we need to validate the field and object names. If an error is found,      # Before we go any farther, we need to validate the field and object names. If an error is found,
4728      # the method below will fail.      # the method below will fail.
4729      _ValidateFieldNames($metadata);      _ValidateFieldNames($metadata);
# Line 3135  Line 4846 
4846              if ($found == 0) {              if ($found == 0) {
4847                  push @{$indexList}, { IndexFields => [ {name => 'id', order => 'ascending'} ] };                  push @{$indexList}, { IndexFields => [ {name => 'id', order => 'ascending'} ] };
4848              }              }
4849              # Now we need to convert the relation's index list to an index table. We begin by creating              # Attach all the indexes to the relation.
4850              # an empty table in the relation structure.              _ProcessIndexes($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++;  
             }  
4851          }          }
4852          # Finally, we add the relation structure to the entity.          # Finally, we add the relation structure to the entity.
4853          $entityStructure->{Relations} = $relationTable;          $entityStructure->{Relations} = $relationTable;
# Line 3159  Line 4861 
4861          _FixupFields($relationshipStructure, $relationshipName, 2, 3);          _FixupFields($relationshipStructure, $relationshipName, 2, 3);
4862          # Format a description for the FROM field.          # Format a description for the FROM field.
4863          my $fromEntity = $relationshipStructure->{from};          my $fromEntity = $relationshipStructure->{from};
4864          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].";
4865          # Get the FROM entity's key type.          # Get the FROM entity's key type.
4866          my $fromType = $entityList->{$fromEntity}->{keyType};          my $fromType = $entityList->{$fromEntity}->{keyType};
4867          # Add the FROM field.          # Add the FROM field.
# Line 3169  Line 4871 
4871                                                      PrettySort => 1});                                                      PrettySort => 1});
4872          # Format a description for the TO field.          # Format a description for the TO field.
4873          my $toEntity = $relationshipStructure->{to};          my $toEntity = $relationshipStructure->{to};
4874          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].";
4875          # Get the TO entity's key type.          # Get the TO entity's key type.
4876          my $toType = $entityList->{$toEntity}->{keyType};          my $toType = $entityList->{$toEntity}->{keyType};
4877          # Add the TO field.          # Add the TO field.
# Line 3181  Line 4883 
4883          my $thisRelation = { Fields => _ReOrderRelationTable($relationshipStructure->{Fields}),          my $thisRelation = { Fields => _ReOrderRelationTable($relationshipStructure->{Fields}),
4884                               Indexes => { } };                               Indexes => { } };
4885          $relationshipStructure->{Relations} = { $relationshipName => $thisRelation };          $relationshipStructure->{Relations} = { $relationshipName => $thisRelation };
4886    
4887            # Add the alternate indexes (if any). This MUST be done before the FROM and
4888            # TO indexes, because it erases the relation's index list.
4889            if (exists $relationshipStructure->{Indexes}) {
4890                _ProcessIndexes($relationshipStructure->{Indexes}, $thisRelation);
4891            }
4892            # Add the relation to the master table.
4893          # Create the FROM and TO indexes.          # Create the FROM and TO indexes.
4894          _CreateRelationshipIndex("From", $relationshipName, $relationshipStructure);          _CreateRelationshipIndex("From", $relationshipName, $relationshipStructure);
4895          _CreateRelationshipIndex("To", $relationshipName, $relationshipStructure);          _CreateRelationshipIndex("To", $relationshipName, $relationshipStructure);
         # Add the relation to the master table.  
4896          $masterRelationTable{$relationshipName} = $thisRelation;          $masterRelationTable{$relationshipName} = $thisRelation;
4897      }      }
4898      # Now store the master relation table in the metadata structure.      # Now store the master relation table in the metadata structure.
# Line 3298  Line 5006 
5006      return $metadata;      return $metadata;
5007  }  }
5008    
5009  =head3 SortNeeded  =head3 _CreateRelationshipIndex
   
 C<< my $parms = $erdb->SortNeeded($relationName); >>  
   
 Return the pipe command for the sort that should be applied to the specified  
 relation when creating the load file.  
   
 For example, if the load file should be sorted ascending by the first  
 field, this method would return  
   
     sort -k1 -t"\t"  
   
 If the first field is numeric, the method would return  
   
     sort -k1n -t"\t"  
   
 Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate  
 keys using a sort.  
   
 =over 4  
   
 =item relationName  
   
 Name of the relation to be examined.  
   
 =item  
   
 Returns the sort command to use for sorting the relation, suitable for piping.  
   
 =back  
   
 =cut  
 #: Return Type $;  
 sub SortNeeded {  
     # Get the parameters.  
     my ($self, $relationName) = @_;  
     # Declare a descriptor to hold the names of the key fields.  
     my @keyNames = ();  
     # Get the relation structure.  
     my $relationData = $self->_FindRelation($relationName);  
     # Find out if the relation is a primary entity relation,  
     # a relationship relation, or a secondary entity relation.  
     my $entityTable = $self->{_metaData}->{Entities};  
     my $relationshipTable = $self->{_metaData}->{Relationships};  
     if (exists $entityTable->{$relationName}) {  
         # Here we have a primary entity relation.  
         push @keyNames, "id";  
     } elsif (exists $relationshipTable->{$relationName}) {  
         # Here we have a relationship. We sort using the FROM index.  
         my $relationshipData = $relationshipTable->{$relationName};  
         my $index = $relationData->{Indexes}->{"idx${relationName}From"};  
         push @keyNames, @{$index->{IndexFields}};  
     } else {  
         # Here we have a secondary entity relation, so we have a sort on the ID field.  
         push @keyNames, "id";  
     }  
     # Now we parse the key names into sort parameters. First, we prime the return  
     # string.  
     my $retVal = "sort -t\"\t\" ";  
     # Get the relation's field list.  
     my @fields = @{$relationData->{Fields}};  
     # Loop through the keys.  
     for my $keyData (@keyNames) {  
         # Get the key and the ordering.  
         my ($keyName, $ordering);  
         if ($keyData =~ /^([^ ]+) DESC/) {  
             ($keyName, $ordering) = ($1, "descending");  
         } else {  
             ($keyName, $ordering) = ($keyData, "ascending");  
         }  
         # Find the key's position and type.  
         my $fieldSpec;  
         for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {  
             my $thisField = $fields[$i];  
             if ($thisField->{name} eq $keyName) {  
                 # Get the sort modifier for this field type. The modifier  
                 # decides whether we're using a character, numeric, or  
                 # floating-point sort.  
                 my $modifier = $TypeTable{$thisField->{type}}->{sort};  
                 # If the index is descending for this field, denote we want  
                 # to reverse the sort order on this field.  
                 if ($ordering eq 'descending') {  
                     $modifier .= "r";  
                 }  
                 # Store the position and modifier into the field spec, which  
                 # will stop the inner loop. Note that the field number is  
                 # 1-based in the sort command, so we have to increment the  
                 # index.  
                 $fieldSpec = ($i + 1) . $modifier;  
             }  
         }  
         # Add this field to the sort command.  
         $retVal .= " -k$fieldSpec";  
     }  
     # Return the result.  
     return $retVal;  
 }  
   
 =head3 CreateRelationshipIndex  
5010    
5011  Create an index for a relationship's relation.  Create an index for a relationship's relation.
5012    
# Line 3437  Line 5047 
5047      if ($relationshipStructure->{arity} eq "1M" && $indexKey eq "To") {      if ($relationshipStructure->{arity} eq "1M" && $indexKey eq "To") {
5048          $newIndex->{Unique} = 'true';          $newIndex->{Unique} = 'true';
5049      }      }
5050      # Add the index to the relation.      # Add the index to the relation.
5051      _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);      _AddIndex("idx$indexKey", $relationStructure, $newIndex);
5052    }
5053    
5054    =head3 _ProcessIndexes
5055    
5056        ERDB::_ProcessIndexes($indexList, $relation);
5057    
5058    Build the data structures for the specified indexes in the specified relation.
5059    
5060    =over 4
5061    
5062    =item indexList
5063    
5064    Reference to a list of indexes. Each index is a hash reference containing an optional
5065    C<Notes> value that describes the index and an C<IndexFields> value that is a reference
5066    to a list of index field structures. An index field structure, in turn, is a reference
5067    to a hash that contains a C<name> attribute for the field name and an C<order>
5068    attribute that specifies either C<ascending> or C<descending>. In this sense the
5069    index list encapsulates the XML C<Indexes> structure in the database definition.
5070    
5071    =item relation
5072    
5073    The structure that describes the current relation. The new index descriptors will
5074    be stored in the structure's C<Indexes> member. Any previous data in the structure
5075    will be lost.
5076    
5077    =back
5078    
5079    =cut
5080    
5081    sub _ProcessIndexes {
5082        # Get the parameters.
5083        my ($indexList, $relation) = @_;
5084        # Now we need to convert the relation's index list to an index table. We begin by creating
5085        # an empty table in the relation structure.
5086        $relation->{Indexes} = { };
5087        # Loop through the indexes.
5088        my $count = 0;
5089        for my $index (@{$indexList}) {
5090            # Add this index to the index table.
5091            _AddIndex("idx$count", $relation, $index);
5092            # Increment the counter so that the next index has a different name.
5093            $count++;
5094        }
5095  }  }
5096    
5097  =head3 AddIndex  =head3 _AddIndex
5098    
5099  Add an index to a relation structure.  Add an index to a relation structure.
5100    
# Line 3487  Line 5140 
5140      $relationStructure->{Indexes}->{$indexName} = $newIndex;      $relationStructure->{Indexes}->{$indexName} = $newIndex;
5141  }  }
5142    
5143  =head3 FixupFields  =head3 _FixupFields
5144    
5145  This method fixes the field list for an entity or relationship. It will add the caller-specified  This method fixes the field list for an entity or relationship. It will add the caller-specified
5146  relation name to fields that do not have a name and set the C<PrettySort> value as specified.  relation name to fields that do not have a name and set the C<PrettySort> value as specified.
# Line 3525  Line 5178 
5178          # Here it doesn't, so we create a new one.          # Here it doesn't, so we create a new one.
5179          $structure->{Fields} = { };          $structure->{Fields} = { };
5180      } else {      } else {
5181          # Here we have a field list. Loop through its fields.          # Here we have a field list. We need to track the searchable fields, so we
5182            # create a list for stashing them.
5183            my @textFields = ();
5184            # Loop through the fields.
5185          my $fieldStructures = $structure->{Fields};          my $fieldStructures = $structure->{Fields};
5186          for my $fieldName (keys %{$fieldStructures}) {          for my $fieldName (keys %{$fieldStructures}) {
5187              Trace("Processing field $fieldName of $defaultRelationName.") if T(4);              Trace("Processing field $fieldName of $defaultRelationName.") if T(4);
# Line 3534  Line 5190 
5190              my $type = $fieldData->{type};              my $type = $fieldData->{type};
5191              # Plug in a relation name if it is needed.              # Plug in a relation name if it is needed.
5192              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });
5193              # Plug in a data generator if we need one.              # Check for searchability.
5194              if (!exists $fieldData->{DataGen}) {              if ($fieldData->{searchable}) {
5195                  # The data generator will use the default for the field's type.                  # Only allow this for a primary relation.
5196                  $fieldData->{DataGen} = { content => $TypeTable{$type}->{dataGen} };                  if ($fieldData->{relation} ne $defaultRelationName) {
5197                        Confess("Field $fieldName of $defaultRelationName is in secondary relations and cannot be searchable.");
5198                    } else {
5199                        push @textFields, $fieldName;
5200                    }
5201              }              }
             # Plug in the defaults for the optional data generation parameters.  
             Tracer::MergeOptions($fieldData->{DataGen}, { testCount => 1, pass => 0 });  
5202              # Add the PrettySortValue.              # Add the PrettySortValue.
5203              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);
5204          }          }
5205            # If there are searchable fields, remember the fact.
5206            if (@textFields) {
5207                $structure->{searchFields} = \@textFields;
5208            }
5209      }      }
5210  }  }
5211    
5212  =head3 FixName  =head3 _FixName
5213    
5214  Fix the incoming field name so that it is a legal SQL column name.  Fix the incoming field name so that it is a legal SQL column name.
5215    
# Line 3576  Line 5238 
5238      return $fieldName;      return $fieldName;
5239  }  }
5240    
5241  =head3 FixNames  =head3 _FixNames
5242    
5243  Fix all the field names in a list.  Fix all the field names in a list.
5244    
# Line 3607  Line 5269 
5269      return @result;      return @result;
5270  }  }
5271    
5272  =head3 AddField  =head3 _AddField
5273    
5274  Add a field to a field list.  Add a field to a field list.
5275    
# Line 3642  Line 5304 
5304      $fieldList->{$fieldName} = $fieldStructure;      $fieldList->{$fieldName} = $fieldStructure;
5305  }  }
5306    
5307  =head3 ReOrderRelationTable  =head3 _ReOrderRelationTable
5308    
5309  This method will take a relation table and re-sort it according to the implicit ordering of the  This method will take a relation table and re-sort it according to the implicit ordering of the
5310  C<PrettySort> property. Instead of a hash based on field names, it will return a list of fields.  C<PrettySort> property. Instead of a hash based on field names, it will return a list of fields.
# Line 3703  Line 5365 
5365    
5366  }  }
5367    
5368  =head3 IsPrimary  =head3 _IsPrimary
5369    
5370  Return TRUE if a specified relation is a primary relation, else FALSE. A relation is primary  Return TRUE if a specified relation is a primary relation, else FALSE. A relation is primary
5371  if it has the same name as an entity or relationship.  if it has the same name as an entity or relationship.
# Line 3739  Line 5401 
5401      return $retVal;      return $retVal;
5402  }  }
5403    
5404  =head3 FindRelation  =head3 _FindRelation
5405    
5406  Return the descriptor for the specified relation.  Return the descriptor for the specified relation.
5407    
# Line 3770  Line 5432 
5432    
5433  =head2 HTML Documentation Utility Methods  =head2 HTML Documentation Utility Methods
5434    
5435  =head3 ComputeRelationshipSentence  =head3 _ComputeRelationshipSentence
5436    
5437  The relationship sentence consists of the relationship name between the names of the  The relationship sentence consists of the relationship name between the names of the
5438  two related entities and an arity indicator.  two related entities and an arity indicator.
# Line 3800  Line 5462 
5462      # Get the parameters.      # Get the parameters.
5463      my ($relationshipName, $relationshipStructure) = @_;      my ($relationshipName, $relationshipStructure) = @_;
5464      # Format the relationship sentence.      # Format the relationship sentence.
5465      my $result = "$relationshipStructure->{from} <b>$relationshipName</b> $relationshipStructure->{to}";      my $result = "$relationshipStructure->{from} $relationshipName $relationshipStructure->{to}";
5466      # Compute the arity.      # Compute the arity.
5467      my $arityCode = $relationshipStructure->{arity};      my $arityCode = $relationshipStructure->{arity};
5468      my $arity = $ArityTable{$arityCode};      my $arity = $ArityTable{$arityCode};
# Line 3808  Line 5470 
5470      return $result;      return $result;
5471  }  }
5472    
5473  =head3 ComputeRelationshipHeading  =head3 _ComputeRelationshipHeading
5474    
5475  The relationship heading is the L<relationship sentence|/ComputeRelationshipSentence> with the entity  The relationship heading is the L<relationship sentence|/ComputeRelationshipSentence> with the entity
5476  names hyperlinked to the appropriate entity sections of the document.  names hyperlinked to the appropriate entity sections of the document.
# Line 3845  Line 5507 
5507      return $result;      return $result;
5508  }  }
5509    
5510  =head3 ShowRelationTable  =head3 _WikiRelationTable
5511    
5512    Generate the Wiki text for a particular relation. The relation's data will be formatted as a
5513    table with three columns-- the field name, the field type, and the field description.
5514    
5515    This is a static method.
5516    
5517    =over 4
5518    
5519    =item relationName
5520    
5521    Name of the relation being formatted.
5522    
5523    =item relationData
5524    
5525    Hash containing the relation's fields and indexes.
5526    
5527    =item RETURN
5528    
5529    Returns a Wiki string that can be used to display the relation name and all of its fields.
5530    
5531    =back
5532    
5533    =cut
5534    
5535    sub _WikiRelationTable {
5536        # Get the parameters.
5537        my ($relationName, $relationData) = @_;
5538        # We'll create a list of lists in here, then call WikiTools::Table to
5539        # convert it into a table.
5540        my @rows = ();
5541        # Push in the header row.
5542        push @rows, [qw(Field Type Description)];
5543        # Loop through the fields.
5544        for my $field (@{$relationData->{Fields}}) {
5545            # Create this field's row. We always have a name and type.
5546            my @row = ($field->{name}, $field->{type});
5547            # If we have a description, add it as the third column.
5548            if (exists $field->{Notes}) {
5549                push @row, WikiNote($field->{Notes}->{content});
5550            }
5551            # Push this row onto the table list.
5552            push @rows, \@row;
5553        }
5554        # Store the rows as a Wiki table.
5555        my $retVal = WikiTools::Table(@rows);
5556        # Now we show the relation's indexes. These are formatted as another
5557        # table.
5558        @rows = ();
5559        # Push in the header row.
5560        push @rows, [qw(Index Unique Fields Notes)];
5561        # Get the index hash.
5562        my $indexTable = $relationData->{Indexes};
5563        # Loop through the indexes. For an entity, there is always at least one index.
5564        # For a relationship, there are at least two. The upshot is we don't need to
5565        # worry about accidentally generating a frivolous table here.
5566        for my $indexName (sort keys %$indexTable) {
5567            my $indexData = $indexTable->{$indexName};
5568            # Determine whether or not the index is unique.
5569            my $unique = ((exists $indexData->{Unique} && $indexData->{Unique} eq "true") ?
5570                          "yes" : "");
5571            # Get the field list.
5572            my $fields = join(', ', @{$indexData->{IndexFields}});
5573            # Get the note text.
5574            my $description = "";
5575            if (my $note = $indexData->{Notes}) {
5576                $description = WikiNote($note->{content});
5577            }
5578            # Format this row.
5579            my @row = ($indexName, $unique, $fields, $description);
5580            push @rows, \@row;
5581        }
5582        # Add the index list to the result.
5583        $retVal .= "\n\n" . WikiTools::Table(@rows);
5584    }
5585    
5586    
5587    =head3 _ShowRelationTable
5588    
5589  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
5590  table with three columns-- the field name, the field type, and the field description.  table with three columns-- the field name, the field type, and the field description.
# Line 3895  Line 5634 
5634          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";
5635          # Add any note text.          # Add any note text.
5636          if (my $note = $indexData->{Notes}) {          if (my $note = $indexData->{Notes}) {
5637              $htmlString .= "<li>" . _HTMLNote($note->{content}) . "</li>\n";              $htmlString .= "<li>" . HTMLNote($note->{content}) . "</li>\n";
5638          }          }
5639          # Add the fiield list.          # Add the fiield list.
5640          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";
# Line 3906  Line 5645 
5645      $htmlString .= "</ul>\n";      $htmlString .= "</ul>\n";
5646  }  }
5647    
5648  =head3 OpenFieldTable  =head3 _OpenFieldTable
5649    
5650  This method creates the header string for the field table generated by L</ShowMetaData>.  This method creates the header string for the field table generated by L</ShowMetaData>.
5651    
# Line 3931  Line 5670 
5670      return _OpenTable($tablename, 'Field', 'Type', 'Description');      return _OpenTable($tablename, 'Field', 'Type', 'Description');
5671  }  }
5672    
5673  =head3 OpenTable  =head3 _OpenTable
5674    
5675  This method creates the header string for an HTML table.  This method creates the header string for an HTML table.
5676    
# Line 3961  Line 5700 
5700      # Compute the number of columns.      # Compute the number of columns.
5701      my $colCount = @colNames;      my $colCount = @colNames;
5702      # Generate the title row.      # Generate the title row.
5703      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";
5704      # Loop through the columns, adding the column header rows.      # Loop through the columns, adding the column header rows.
5705      $htmlString .= "<tr>";      $htmlString .= "<tr>";
5706      for my $colName (@colNames) {      for my $colName (@colNames) {
# Line 3971  Line 5710 
5710      return $htmlString;      return $htmlString;
5711  }  }
5712    
5713  =head3 CloseTable  =head3 _CloseTable
5714    
5715  This method returns the HTML for closing a table.  This method returns the HTML for closing a table.
5716    
# Line 3980  Line 5719 
5719  =cut  =cut
5720    
5721  sub _CloseTable {  sub _CloseTable {
5722      return "</table></p>\n";      return "</table>\n";
5723  }  }
5724    
5725  =head3 ShowField  =head3 _ShowField
5726    
5727  This method returns the HTML for displaying a row of field information in a field table.  This method returns the HTML for displaying a row of field information in a field table.
5728    
# Line 4010  Line 5749 
5749      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>";
5750      # If we have content, add it as a third column.      # If we have content, add it as a third column.
5751      if (exists $fieldData->{Notes}) {      if (exists $fieldData->{Notes}) {
5752          $htmlString .= "<td>" . _HTMLNote($fieldData->{Notes}->{content}) . "</td>";          $htmlString .= "<td>" . HTMLNote($fieldData->{Notes}->{content}) . "</td>";
5753      }      }
5754      # Close off the row.      # Close off the row.
5755      $htmlString .= "</tr>\n";      $htmlString .= "</tr>\n";
# Line 4018  Line 5757 
5757      return $htmlString;      return $htmlString;
5758  }  }
5759    
 =head3 HTMLNote  
   
 Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes  
 supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.  
 Except for C<[p]>, all the codes are closed by slash-codes. So, for  
 example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.  
   
 This is a static method.  
   
 =over 4  
   
 =item dataString  
   
 String to convert to HTML.  
   
 =item RETURN  
   
 An HTML string derived from the input string.  
   
 =back  
   
 =cut  
   
 sub _HTMLNote {  
     # Get the parameter.  
     my ($dataString) = @_;  
     # Substitute the codes.  
     $dataString =~ s!\[(/?[bi])\]!<$1>!g;  
     $dataString =~ s!\[p\]!</p><p>!g;  
     # Return the result.  
     return $dataString;  
 }  
   
 =head2 Data Generation Utilities  
   
 =head3 IntGen  
   
 C<< my $integer = IntGen($min, $max); >>  
   
 Returns a random number between the specified minimum and maximum (inclusive).  
   
 =over 4  
   
 =item min  
   
 Minimum permissible return value.  
   
 =item max  
   
 Maximum permissible return value.  
   
 =item RETURN  
   
 Returns a value no lower than the minimum and no greater than the maximum.  
   
 =back  
   
 =cut  
   
 sub IntGen {  
     # Get the parameters.  
     my ($min, $max) = @_;  
     # Determine the range of possible values. Note we put some space well above the  
     # maximum value to give it a fighting chance of apppearing in the list.  
     my $span = $max + 0.99 - $min;  
     # Create an integer in the range.  
     my $retVal = $min + int(rand($span));  
     # Return the result.  
     return $retVal;  
 }  
   
 =head3 RandChar  
   
 C<< my $char = RandChar($sourceString); >>  
   
 Select a random character from a string.  
   
 =over 4  
   
 =item sourceString  
   
 String from which the random character should be selected.  
   
 =item RETURN  
   
 Returns a single character from the incoming string.  
   
 =back  
   
 =cut  
   
 sub RandChar {  
     # Get the parameter.  
     my ($sourceString) = @_;  
     # Select a random character.  
     my $retVal = IntGen(0, (length $sourceString) - 1);  
     # Return it.  
     return substr($sourceString, $retVal, 1);  
 }  
   
 =head3 RandChars  
   
 C<< my $string = RandChars($sourceString, $length); >>  
   
 Create a string from characters taken from a source string.  
   
 =over 4  
   
 =item sourceString  
   
 String