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

Diff of /Sprout/ERDB.pm

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

revision 1.55, Sat Jun 24 23:49:10 2006 UTC revision 1.94, Thu Dec 6 14:58:03 2007 UTC
# Line 6  Line 6 
6      use Data::Dumper;      use Data::Dumper;
7      use XML::Simple;      use XML::Simple;
8      use DBQuery;      use DBQuery;
9      use DBObject;      use ERDBObject;
10      use Stats;      use Stats;
11      use Time::HiRes qw(gettimeofday);      use Time::HiRes qw(gettimeofday);
12      use Digest::MD5 qw(md5_base64);      use Digest::MD5 qw(md5_base64);
13      use FIG;      use CGI;
14    
15  =head1 Entity-Relationship Database Package  =head1 Entity-Relationship Database Package
16    
# Line 59  Line 59 
59  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
60  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.
61    
62  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
63  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
64  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
65  to generate documentation for the database.  for the database.
66    
67    Special support is provided for text searching. An entity field can be marked as <em>searchable</em>,
68    in which case it will be used to generate a text search index in which the user searches for words
69    in the field instead of a particular field value.
70    
71  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
72  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
73  was inserted by the L</InsertObject> method.  was inserted by the L</InsertObject> method.
74    
 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.  
   
75  =head2 XML Database Description  =head2 XML Database Description
76    
77  =head3 Data Types  =head3 Data Types
# Line 91  Line 91 
91    
92  32-bit signed integer  32-bit signed integer
93    
94    =item counter
95    
96    32-bit unsigned integer
97    
98  =item date  =item date
99    
100  64-bit unsigned integer, representing a PERL date/time value  64-bit unsigned integer, representing a PERL date/time value
# Line 186  Line 190 
190    
191  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<->),
192  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
193  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,
194    the name C<search-relevance> has special meaning for full-text searches and should not be
195    used as a field name.
196    
197  =item type  =item type
198    
# Line 205  Line 211 
211  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
212  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.
213    
214    =item searchable
215    
216    If specified, then the field is a candidate for full-text searching. A single full-text
217    index will be created for each relation with at least one searchable field in it.
218    For best results, this option should only be used for string or text fields.
219    
220    =item special
221    
222    This attribute allows the subclass to assign special meaning for certain fields.
223    The interpretation is up to the subclass itself. Currently, only entity fields
224    can have this attribute.
225    
226  =back  =back
227    
228  =head3 Indexes  =head3 Indexes
229    
230  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
231  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
232  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
233  I<from-index>. These order the results when crossing the relationship. For  I<from-index> that order the results when crossing the relationship. For
234  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
235  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
236  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
237    indexes. A relationship's index must specify only fields in
238  the relationship.  the relationship.
239    
240  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.
241  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
242  using the B<ToIndex> tag.  specified using the B<ToIndex> tag.
243    
244  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>
245  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 238  Line 257 
257    
258  =back  =back
259    
260  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
261    have a B<Unique> attribute. If specified, the index will be generated as a unique
262    index.
263    
264  =head3 Object and Field Names  =head3 Object and Field Names
265    
# Line 282  Line 303 
303    
304  A relationship is described by the C<Relationship> tag. Within a relationship,  A relationship is described by the C<Relationship> tag. Within a relationship,
305  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
306  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
307  the to-index.  the to-index, and an C<Indexes> tag containing the alternate indexes.
308    
309  The C<Relationship> tag has the following attributes.  The C<Relationship> tag has the following attributes.
310    
# Line 316  Line 337 
337    
338  # 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.
339  # "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
340  # 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
341  # 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,
342  # record sizes.  # and "indexMod", if non-zero, is the number of characters to use when the field is specified in an
343  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, dataGen => "StringGen('A')" },  # index
344                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, dataGen => "IntGen(0, 99999999)" },  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",
345                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, dataGen => "StringGen(IntGen(10,250))" },                                 indexMod =>   0, notes => "single ASCII character"},
346                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, dataGen => "StringGen(IntGen(80,1000))" },                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n",
347                    date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, dataGen => "DateGen(-7, 7, IntGen(0,1400))" },                                 indexMod =>   0, notes => "signed 32-bit integer"},
348                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, dataGen => "FloatGen(0.0, 100.0)" },                    counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n",
349                    boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, dataGen => "IntGen(0, 1)" },                                 indexMod =>   0, notes => "unsigned 32-bit integer"},
350                      string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, sort => "",
351                                   indexMod =>   0, notes => "character string, 0 to 255 characters"},
352                      text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, sort => "",
353                                   indexMod => 255, notes => "character string, nearly unlimited length, only first 255 characters are indexed"},
354                      date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, sort => "n",
355                                   indexMod =>   0, notes => "signed, 64-bit integer"},
356                      float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, sort => "g",
357                                   indexMod =>   0, notes => "64-bit double precision floating-point number"},
358                      boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, sort => "n",
359                                   indexMod =>   0, notes => "boolean value: 0 if false, 1 if true"},
360                   'hash-string' =>                   'hash-string' =>
361                               { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, dataGen => "SringGen(22)" },                               { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, sort => "",
362                                   indexMod =>   0, notes => "string stored in digested form, used for certain types of key fields"},
363                   'id-string' =>                   'id-string' =>
364                               { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, dataGen => "SringGen(22)" },                               { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, sort => "",
365                                   indexMod =>   0, notes => "character string, 0 to 25 characters"},
366                   'key-string' =>                   'key-string' =>
367                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, dataGen => "StringGen(IntGen(10,40))" },                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, sort => "",
368                                   indexMod =>   0, notes => "character string, 0 to 40 characters"},
369                   'name-string' =>                   'name-string' =>
370                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, dataGen => "StringGen(IntGen(10,80))" },                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, sort => "",
371                                   indexMod =>   0, notes => "character string, 0 to 80 characters"},
372                   'medium-string' =>                   'medium-string' =>
373                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, dataGen => "StringGen(IntGen(10,160))" },                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",
374                                   indexMod =>   0, notes => "character string, 0 to 160 characters"},
375                     'long-string' =>
376                                 { sqlType => 'VARCHAR(500)',       maxLen => 500,          avglen => 255, sort => "",
377                                   indexMod =>   0, notes => "character string, 0 to 500 characters"},
378                  );                  );
379    
380  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 344  Line 383 
383                     'MM' => 'many-to-many'                     'MM' => 'many-to-many'
384                   );                   );
385    
386  # Table for interpreting string patterns.  # Options for XML input and output.
387    
388    my %XmlOptions = (GroupTags =>  { Relationships => 'Relationship',
389                                      Entities => 'Entity',
390                                      Fields => 'Field',
391                                      Indexes => 'Index',
392                                      IndexFields => 'IndexField'
393                                    },
394                      KeyAttr =>    { Relationship => 'name',
395                                      Entity => 'name',
396                                      Field => 'name'
397                                    },
398                      SuppressEmpty => 1,
399                     );
400    
401  my %PictureTable = ( 'A' => "abcdefghijklmnopqrstuvwxyz",  my %XmlInOpts  = (
402                       '9' => "0123456789",                    ForceArray => ['Field', 'Index', 'IndexField', 'Relationship', 'Entity'],
403                       'X' => "abcdefghijklmnopqrstuvwxyz0123456789",                    ForceContent => 1,
404                       'V' => "aeiou",                    NormalizeSpace => 2,
405                       'K' => "bcdfghjklmnoprstvwxyz"                   );
406    my %XmlOutOpts = (
407                      RootName => 'Database',
408                      XMLDecl => 1,
409                     );                     );
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 391  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 432  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 493  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 511  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 550  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 584  Line 644 
644    
645  =head3 DumpMetaData  =head3 DumpMetaData
646    
647  C<< $erdb->DumpMetaData(); >>      $erdb->DumpMetaData();
648    
649  Return a dump of the metadata structure.  Return a dump of the metadata structure.
650    
# Line 597  Line 657 
657      return Data::Dumper::Dumper($self->{_metaData});      return Data::Dumper::Dumper($self->{_metaData});
658  }  }
659    
660    =head3 CreatePPO
661    
662        ERDB::CreatePPO($erdbXMLFile, $ppoXMLFile);
663    
664    Create a PPO XML file from an ERDB data definition XML file. At the
665    current time, the PPO XML file can be used to create a database with
666    similar functionality. Eventually, the PPO will be able to use the
667    created XML to access the live ERDB database.
668    
669    =over 4
670    
671    =item erdbXMLFile
672    
673    Name of the XML data definition file for the ERDB database. This
674    file must exist.
675    
676    =item ppoXMLFile
677    
678    Output file for the PPO XML definition. If this file exists, it
679    will be overwritten.
680    
681    =back
682    
683    =cut
684    
685    sub CreatePPO {
686        # Get the parameters.
687        my ($erdbXMLFile, $ppoXMLFile) = @_;
688        # First, we want to slurp in the ERDB XML file in its raw form.
689        my $xml = ReadMetaXML($erdbXMLFile);
690        # Create a variable to hold all of the objects in the PPO project.
691        my @objects = ();
692        # Get the relationship hash.
693        my $relationships = $xml->{Relationships};
694        # Loop through the entities.
695        my $entities = $xml->{Entities};
696        for my $entityName (keys %{$entities}) {
697            # Get the entity's data structures.
698            my $entityObject = $entities->{$entityName};
699            # We put the object's fields in here, according to their type.
700            my (@object_refs, @scalars, @indexes, @arrays);
701            # Create the ID field for the entity. We get the key type from the
702            # entity object and compute the corresponding SQL type.
703            my $type = $TypeTable{$entityObject->{keyType}}->{sqlType};
704            push @scalars, { label => 'id', type => $type };
705            # Loop through the entity fields.
706            for my $fieldName ( keys %{$entityObject->{Fields}} ) {
707                # Get the field object.
708                my $fieldObject = $entityObject->{Fields}->{$fieldName};
709                # Convert it to a scalar tag.
710                my $scalar = _CreatePPOField($fieldName, $fieldObject);
711                # If we have a relation, this field is stored in an array.
712                # otherwise, it is a scalar. The array tag has scalars
713                # stored as an XML array. In ERDB, there is only ever one,
714                # but PPO can have more.
715                my $relation = $fieldObject->{relation};
716                if ($relation) {
717                    push @arrays, { scalar => [$scalar] };
718                } else {
719                    push @scalars, $scalar;
720                }
721            }
722            # Loop through the relationships. If this entity is the to-entity
723            # on a relationship of 1M arity, then it is implemented as a PPO
724            # object reference.
725            for my $relationshipName (keys %{$relationships}) {
726                # Get the relationship data.
727                my $relationshipData = $relationships->{$relationshipName};
728                # If we have a from for this entity and an arity of 1M, we
729                # have an object reference.
730                if ($relationshipData->{to} eq $entityName &&
731                    $relationshipData->{arity} eq '1M') {
732                    # Build the object reference tag.
733                    push @object_refs, { label => $relationshipName,
734                                         type => $relationshipData->{from} };
735                }
736            }
737            # Create the indexes.
738            my $indexList = $entityObject->{Indexes};
739            push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
740            # Build the object XML tree.
741            my $object = { label => $entityName,
742                           object_ref => \@object_refs,
743                           scalar => \@scalars,
744                           index => \@indexes,
745                           array => \@arrays
746                          };
747            # Push the object onto the objects list.
748            push @objects, $object;
749        }
750        # Loop through the relationships, searching for MMs. The 1Ms were
751        # already handled by the entity search above.
752        for my $relationshipName (keys %{$relationships}) {
753            # Get this relationship's object.
754            my $relationshipObject = $relationships->{$relationshipName};
755            # Only proceed if it's many-to-many.
756            if ($relationshipObject->{arity} eq 'MM') {
757                # Create the tag lists for the relationship object.
758                my (@object_refs, @scalars, @indexes);
759                # The relationship will be created as an object with object
760                # references for its links to the participating entities.
761                my %links = ( from_link => $relationshipObject->{from},
762                              to_link => $relationshipObject->{to} );
763                for my $link (keys %links) {
764                    # Create an object_ref tag for this piece of the
765                    # relationship (from or to).
766                    my $object_ref = { label => $link,
767                                       type => $links{$link} };
768                    push @object_refs, $object_ref;
769                }
770                # Loop through the intersection data fields, creating scalar tags.
771                # There are no fancy array tags in a relationship.
772                for my $fieldName (keys %{$relationshipObject->{Fields}}) {
773                    my $fieldObject = $relationshipObject->{Fields}->{$fieldName};
774                    push @scalars, _CreatePPOField($fieldName, $fieldObject);
775                }
776                # Finally, the indexes: currently we cannot support the to-index and
777                # from-index in PPO, so we just process the alternate indexes.
778                my $indexList = $relationshipObject->{Indexes};
779                push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
780                # Wrap up all the stuff about this relationship.
781                my $object = { label => $relationshipName,
782                               scalar => \@scalars,
783                               object_ref => \@object_refs,
784                               index => \@indexes
785                             };
786                # Push it into the object list.
787                push @objects, $object;
788            }
789        }
790        # Compute a title.
791        my $title;
792        if ($erdbXMLFile =~ /(\/|^)([^\/]+)DBD\.xml/) {
793            # Here we have a standard file name we can use for a title.
794            $title = $2;
795        } else {
796            # Here the file name is non-standard, so we carve up the
797            # database title.
798            $title = $xml->{Title}->{content};
799            $title =~ s/\s\.,//g;
800        }
801        # Wrap up the XML as a project.
802        my $ppoXML = { project => { label => $title,
803                                    object => \@objects }};
804        # Write out the results.
805        my $ppoString = XML::Simple::XMLout($ppoXML,
806                                            AttrIndent => 1,
807                                            KeepRoot => 1);
808        Tracer::PutFile($ppoXMLFile, [ $ppoString ]);
809    }
810    
811    =head3 FindIndexForEntity
812    
813        my $indexFound = ERDB::FindIndexForEntity($xml, $entityName, $attributeName);
814    
815    This method locates the entry in an entity's index list that begins with the
816    specified attribute name. If the entity has no index list, one will be
817    created. This method works on raw XML, not a live ERDB object.
818    
819    =over 4
820    
821    =item xml
822    
823    The raw XML structure defining the database.
824    
825    =item entityName
826    
827    The name of the relevant entity.
828    
829    =item attributeName
830    
831    The name of the attribute relevant to the search.
832    
833    =item RETURN
834    
835    The numerical index in the index list of the index entry for the specified entity and
836    attribute, or C<undef> if no such index exists.
837    
838    =back
839    
840    =cut
841    
842    sub FindIndexForEntity {
843        # Get the parameters.
844        my ($xml, $entityName, $attributeName) = @_;
845        # Declare the return variable.
846        my $retVal;
847        # Get the named entity.
848        my $entityData = $xml->{Entities}->{$entityName};
849        if (! $entityData) {
850            Confess("Entity $entityName not found in DBD structure.");
851        } else {
852            # Insure it has an index list.
853            if (! exists $entityData->{Indexes}) {
854                $entityData->{Indexes} = [];
855            } else {
856                # Search for the desired index.
857                my $indexList = $entityData->{Indexes};
858                my $n = scalar @{$indexList};
859                Trace("Searching $n indexes in index list for $entityName.") if T(2);
860                # We use an indexed FOR here because we're returning an
861                # index number instead of an object. We do THAT so we can
862                # delete the index from the list if needed.
863                for (my $i = 0; $i < $n && !defined($retVal); $i++) {
864                    my $index = $indexList->[$i];
865                    my $fields = $index->{IndexFields};
866                    # Technically this IF should be safe (that is, we are guaranteed
867                    # the existence of a "$fields->[0]"), because when we load the XML
868                    # we have SuppressEmpty specified.
869                    if ($fields->[0]->{name} eq $attributeName) {
870                        $retVal = $i;
871                    }
872                }
873            }
874        }
875        Trace("Index for $attributeName of $entityName found at position $retVal.") if defined($retVal) && T(3);
876        Trace("Index for $attributeName not found in $entityName.") if !defined($retVal) && T(3);
877        # Return the result.
878        return $retVal;
879    }
880    
881  =head3 CreateTables  =head3 CreateTables
882    
883  C<< $erdb->CreateTables(); >>      $erdb->CreateTables();
884    
885  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
886  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 616  Line 897 
897      # Loop through the relations.      # Loop through the relations.
898      for my $relationName (@relNames) {      for my $relationName (@relNames) {
899          # Create a table for this relation.          # Create a table for this relation.
900          $self->CreateTable($relationName);          $self->CreateTable($relationName, 1);
901          Trace("Relation $relationName created.") if T(2);          Trace("Relation $relationName created.") if T(2);
902      }      }
903  }  }
904    
905  =head3 CreateTable  =head3 CreateTable
906    
907  C<< $erdb->CreateTable($tableName, $indexFlag, $estimatedRows); >>      $erdb->CreateTable($tableName, $indexFlag, $estimatedRows);
908    
909  Create the table for a relation and optionally create its indexes.  Create the table for a relation and optionally create its indexes.
910    
# Line 679  Line 960 
960      my $estimation = undef;      my $estimation = undef;
961      if ($estimatedRows) {      if ($estimatedRows) {
962          $estimation = [$self->EstimateRowSize($relationName), $estimatedRows];          $estimation = [$self->EstimateRowSize($relationName), $estimatedRows];
963            Trace("$estimation->[1] rows of $estimation->[0] bytes each.") if T(3);
964      }      }
965      # Create the table.      # Create the table.
966      Trace("Creating table $relationName: $fieldThing") if T(2);      Trace("Creating table $relationName: $fieldThing") if T(2);
967      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);
968      Trace("Relation $relationName created in database.") if T(2);      Trace("Relation $relationName created in database.") if T(2);
969      # If we want to build the indexes, we do it here.      # If we want to build the indexes, we do it here. Note that the full-text search
970        # index will not be built until the table has been loaded.
971      if ($indexFlag) {      if ($indexFlag) {
972          $self->CreateIndex($relationName);          $self->CreateIndex($relationName);
973      }      }
# Line 692  Line 975 
975    
976  =head3 VerifyFields  =head3 VerifyFields
977    
978  C<< my $count = $erdb->VerifyFields($relName, \@fieldList); >>      my $count = $erdb->VerifyFields($relName, \@fieldList);
979    
980  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
981  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 735  Line 1018 
1018              my $oldString = $fieldList->[$i];              my $oldString = $fieldList->[$i];
1019              if (length($oldString) > $maxLen) {              if (length($oldString) > $maxLen) {
1020                  # Here it's too big, so we truncate it.                  # Here it's too big, so we truncate it.
1021                  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);
1022                  $fieldList->[$i] = substr $oldString, 0, $maxLen;                  $fieldList->[$i] = substr $oldString, 0, $maxLen;
1023                  $retVal++;                  $retVal++;
1024              }              }
# Line 747  Line 1030 
1030    
1031  =head3 DigestFields  =head3 DigestFields
1032    
1033  C<< $erdb->DigestFields($relName, $fieldList); >>      $erdb->DigestFields($relName, $fieldList);
1034    
1035  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
1036  specified relation.  specified relation.
# Line 787  Line 1070 
1070    
1071  =head3 DigestKey  =head3 DigestKey
1072    
1073  C<< my $digested = $erdb->DigestKey($keyValue); >>      my $digested = $erdb->DigestKey($keyValue);
1074    
1075  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
1076  key-based search into a table with key-type hash-string.  key-based search into a table with key-type hash-string.
# Line 820  Line 1103 
1103    
1104  =head3 CreateIndex  =head3 CreateIndex
1105    
1106  C<< $erdb->CreateIndex($relationName); >>      $erdb->CreateIndex($relationName);
1107    
1108  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
1109  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 841  Line 1124 
1124      for my $indexName (keys %{$indexHash}) {      for my $indexName (keys %{$indexHash}) {
1125          my $indexData = $indexHash->{$indexName};          my $indexData = $indexHash->{$indexName};
1126          # Get the index's field list.          # Get the index's field list.
1127          my @fieldList = _FixNames(@{$indexData->{IndexFields}});          my @rawFields = @{$indexData->{IndexFields}};
1128            # Get a hash of the relation's field types.
1129            my %types = map { $_->{name} => $_->{type} } @{$relationData->{Fields}};
1130            # We need to check for text fields so we can append a length limitation for them. To do
1131            # that, we need the relation's field list.
1132            my $relFields = $relationData->{Fields};
1133            for (my $i = 0; $i <= $#rawFields; $i++) {
1134                # Get the field type.
1135                my $field = $rawFields[$i];
1136                my $type = $types{$field};
1137                # Ask if it requires using prefix notation for the index.
1138                my $mod = $TypeTable{$type}->{indexMod};
1139                Trace("Field $field ($i) in $relationName has type $type and indexMod $mod.") if T(3);
1140                if ($mod) {
1141                    # Append the prefix length to the field name,
1142                    $rawFields[$i] .= "($mod)";
1143                }
1144            }
1145            my @fieldList = _FixNames(@rawFields);
1146          my $flds = join(', ', @fieldList);          my $flds = join(', ', @fieldList);
1147          # Get the index's uniqueness flag.          # Get the index's uniqueness flag.
1148          my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
1149          # Create the index.          # Create the index.
1150          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
1151                                      flds => $flds, unique => $unique);                                      flds => $flds, kind => $unique);
1152          if ($rv) {          if ($rv) {
1153              Trace("Index created: $indexName for $relationName ($flds)") if T(1);              Trace("Index created: $indexName for $relationName ($flds)") if T(1);
1154          } else {          } else {
# Line 856  Line 1157 
1157      }      }
1158  }  }
1159    
1160    =head3 GetSecondaryFields
1161    
1162        my %fieldTuples = $erdb->GetSecondaryFields($entityName);
1163    
1164    This method will return a list of the name and type of each of the secondary
1165    fields for a specified entity. Secondary fields are stored in two-column tables
1166    in addition to the primary entity table. This enables the field to have no value
1167    or to have multiple values.
1168    
1169    =over 4
1170    
1171    =item entityName
1172    
1173    Name of the entity whose secondary fields are desired.
1174    
1175    =item RETURN
1176    
1177    Returns a hash mapping the field names to their field types.
1178    
1179    =back
1180    
1181    =cut
1182    
1183    sub GetSecondaryFields {
1184        # Get the parameters.
1185        my ($self, $entityName) = @_;
1186        # Declare the return variable.
1187        my %retVal = ();
1188        # Look for the entity.
1189        my $table = $self->GetFieldTable($entityName);
1190        # Loop through the fields, pulling out the secondaries.
1191        for my $field (sort keys %{$table}) {
1192            if ($table->{$field}->{relation} ne $entityName) {
1193                # Here we have a secondary field.
1194                $retVal{$field} = $table->{$field}->{type};
1195            }
1196        }
1197        # Return the result.
1198        return %retVal;
1199    }
1200    
1201    =head3 GetFieldRelationName
1202    
1203        my $name = $erdb->GetFieldRelationName($objectName, $fieldName);
1204    
1205    Return the name of the relation containing a specified field.
1206    
1207    =over 4
1208    
1209    =item objectName
1210    
1211    Name of the entity or relationship containing the field.
1212    
1213    =item fieldName
1214    
1215    Name of the relevant field in that entity or relationship.
1216    
1217    =item RETURN
1218    
1219    Returns the name of the database relation containing the field, or C<undef> if
1220    the field does not exist.
1221    
1222    =back
1223    
1224    =cut
1225    
1226    sub GetFieldRelationName {
1227        # Get the parameters.
1228        my ($self, $objectName, $fieldName) = @_;
1229        # Declare the return variable.
1230        my $retVal;
1231        # Get the object field table.
1232        my $table = $self->GetFieldTable($objectName);
1233        # Only proceed if the field exists.
1234        if (exists $table->{$fieldName}) {
1235            # Determine the name of the relation that contains this field.
1236            $retVal = $table->{$fieldName}->{relation};
1237        }
1238        # Return the result.
1239        return $retVal;
1240    }
1241    
1242    =head3 DeleteValue
1243    
1244        my $numDeleted = $erdb->DeleteValue($entityName, $id, $fieldName, $fieldValue);
1245    
1246    Delete secondary field values from the database. This method can be used to delete all
1247    values of a specified field for a particular entity instance, or only a single value.
1248    
1249    Secondary fields are stored in two-column relations separate from an entity's primary
1250    table, and as a result a secondary field can legitimately have no value or multiple
1251    values. Therefore, it makes sense to talk about deleting secondary fields where it
1252    would not make sense for primary fields.
1253    
1254    =over 4
1255    
1256    =item entityName
1257    
1258    Name of the entity from which the fields are to be deleted.
1259    
1260    =item id
1261    
1262    ID of the entity instance to be processed. If the instance is not found, this
1263    method will have no effect. If C<undef> is specified, all values for all of
1264    the entity instances will be deleted.
1265    
1266    =item fieldName
1267    
1268    Name of the field whose values are to be deleted.
1269    
1270    =item fieldValue (optional)
1271    
1272    Value to be deleted. If not specified, then all values of the specified field
1273    will be deleted for the entity instance. If specified, then only the values which
1274    match this parameter will be deleted.
1275    
1276    =item RETURN
1277    
1278    Returns the number of rows deleted.
1279    
1280    =back
1281    
1282    =cut
1283    
1284    sub DeleteValue {
1285        # Get the parameters.
1286        my ($self, $entityName, $id, $fieldName, $fieldValue) = @_;
1287        # Declare the return value.
1288        my $retVal = 0;
1289        # We need to set up an SQL command to do the deletion. First, we
1290        # find the name of the field's relation.
1291        my $table = $self->GetFieldTable($entityName);
1292        my $field = $table->{$fieldName};
1293        my $relation = $field->{relation};
1294        # Make sure this is a secondary field.
1295        if ($relation eq $entityName) {
1296            Confess("Cannot delete values of $fieldName for $entityName.");
1297        } else {
1298            # Set up the SQL command to delete all values.
1299            my $sql = "DELETE FROM $relation";
1300            # Build the filter.
1301            my @filters = ();
1302            my @parms = ();
1303            # Check for a filter by ID.
1304            if (defined $id) {
1305                push @filters, "id = ?";
1306                push @parms, $id;
1307            }
1308            # Check for a filter by value.
1309            if (defined $fieldValue) {
1310                push @filters, "$fieldName = ?";
1311                push @parms, $fieldValue;
1312            }
1313            # Append the filters to the command.
1314            if (@filters) {
1315                $sql .= " WHERE " . join(" AND ", @filters);
1316            }
1317            # Execute the command.
1318            my $dbh = $self->{_dbh};
1319            $retVal = $dbh->SQL($sql, 0, @parms);
1320        }
1321        # Return the result.
1322        return $retVal;
1323    }
1324    
1325  =head3 LoadTables  =head3 LoadTables
1326    
1327  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>      my $stats = $erdb->LoadTables($directoryName, $rebuild);
1328    
1329  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
1330  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 918  Line 1384 
1384    
1385  =head3 GetTableNames  =head3 GetTableNames
1386    
1387  C<< my @names = $erdb->GetTableNames; >>      my @names = $erdb->GetTableNames;
1388    
1389  Return a list of the relations required to implement this database.  Return a list of the relations required to implement this database.
1390    
# Line 935  Line 1401 
1401    
1402  =head3 GetEntityTypes  =head3 GetEntityTypes
1403    
1404  C<< my @names = $erdb->GetEntityTypes; >>      my @names = $erdb->GetEntityTypes;
1405    
1406  Return a list of the entity type names.  Return a list of the entity type names.
1407    
# Line 950  Line 1416 
1416      return sort keys %{$entityList};      return sort keys %{$entityList};
1417  }  }
1418    
1419    =head3 GetDataTypes
1420    
1421        my %types = ERDB::GetDataTypes();
1422    
1423    Return a table of ERDB data types. The table returned is a hash of hashes.
1424    The keys of the big hash are the datatypes. Each smaller hash has several
1425    values used to manage the data. The most interesting is the SQL type (key
1426    C<sqlType>) and the descriptive node (key C<notes>).
1427    
1428    Note that changing the values in the smaller hashes will seriously break
1429    things, so this data should be treated as read-only.
1430    
1431    =cut
1432    
1433    sub GetDataTypes {
1434        return %TypeTable;
1435    }
1436    
1437    
1438  =head3 IsEntity  =head3 IsEntity
1439    
1440  C<< my $flag = $erdb->IsEntity($entityName); >>      my $flag = $erdb->IsEntity($entityName);
1441    
1442  Return TRUE if the parameter is an entity name, else FALSE.  Return TRUE if the parameter is an entity name, else FALSE.
1443    
# Line 979  Line 1464 
1464    
1465  =head3 Get  =head3 Get
1466    
1467  C<< my $query = $erdb->Get(\@objectNames, $filterClause, \@params); >>      my $query = $erdb->Get(\@objectNames, $filterClause, \@params);
1468    
1469  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.
1470  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 987  Line 1472 
1472  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
1473  $genus.  $genus.
1474    
1475  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", [$genus]); >>      $query = $erdb->Get(['Genome'], "Genome(genus) = ?", [$genus]);
1476    
1477  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
1478  parameter representing the parameter value. It would also be possible to code  parameter representing the parameter value. It would also be possible to code
1479    
1480  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>      $query = $erdb->Get(['Genome'], "Genome(genus) = \'$genus\'");
1481    
1482  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
1483  characters inside the variable C<$genus>.  characters inside the variable C<$genus>.
# Line 1004  Line 1489 
1489  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
1490  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,
1491    
1492  C<< $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]); >>      $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]);
1493    
1494  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
1495  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 1040  Line 1525 
1525  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
1526  particular genus and sorts them by species name.  particular genus and sorts them by species name.
1527    
1528  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>      "Genome(genus) = ? ORDER BY Genome(species)"
1529    
1530  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
1531  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 1053  Line 1538 
1538  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
1539  a positive number. So, for example  a positive number. So, for example
1540    
1541  C<< "Genome(genus) = ? ORDER BY Genome(species) LIMIT 10" >>      "Genome(genus) = ? ORDER BY Genome(species) LIMIT 10"
1542    
1543  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
1544  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
1545  use  use
1546    
1547  C<< "LIMIT 10" >>      "LIMIT 10"
1548    
1549  =item params  =item params
1550    
# Line 1080  Line 1565 
1565      my ($suffix, $mappedNameListRef, $mappedNameHashRef) =      my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1566          $self->_SetupSQL($objectNames, $filterClause);          $self->_SetupSQL($objectNames, $filterClause);
1567      # Create the query.      # Create the query.
1568      my $command = "SELECT DISTINCT " . join(".*, ", @{$mappedNameListRef}) .      my $command = "SELECT " . join(".*, ", @{$mappedNameListRef}) .
1569          ".* $suffix";          ".* $suffix";
1570      my $sth = $self->_GetStatementHandle($command, $params);      my $sth = $self->_GetStatementHandle($command, $params);
1571      # 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 1094  Line 1579 
1579      return $retVal;      return $retVal;
1580  }  }
1581    
1582    
1583    
1584    =head3 Search
1585    
1586        my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params);
1587    
1588    Perform a full text search with filtering. The search will be against a specified object
1589    in the object name list. That object will get an extra field containing the search
1590    relevance. Note that except for the search expression, the parameters of this method are
1591    the same as those for L</Get> and follow the same rules.
1592    
1593    =over 4
1594    
1595    =item searchExpression
1596    
1597    Boolean search expression for the text fields of the target object. The default mode for
1598    a Boolean search expression is OR, but we want the default to be AND, so we will
1599    add a C<+> operator to each word with no other operator before it.
1600    
1601    =item idx
1602    
1603    Index in the I<$objectNames> list of the table to be searched in full-text mode.
1604    
1605    =item objectNames
1606    
1607    List containing the names of the entity and relationship objects to be retrieved.
1608    
1609    =item filterClause
1610    
1611    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1612    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
1613    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
1614    in the filter clause should be added to the parameter list as additional parameters. The
1615    fields in a filter clause can come from primary entity relations, relationship relations,
1616    or secondary entity relations; however, all of the entities and relationships involved must
1617    be included in the list of object names.
1618    
1619    =item params
1620    
1621    Reference to a list of parameter values to be substituted into the filter clause.
1622    
1623    =item RETURN
1624    
1625    Returns a query object for the specified search.
1626    
1627    =back
1628    
1629    =cut
1630    
1631    sub Search {
1632        # Get the parameters.
1633        my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1634        # Declare the return variable.
1635        my $retVal;
1636        # Create a safety copy of the parameter list. Note we have to be careful to insure
1637        # a parameter list exists before we copy it.
1638        my @myParams = ();
1639        if (defined $params) {
1640            @myParams = @{$params};
1641        }
1642        # Get the first object's structure so we have access to the searchable fields.
1643        my $object1Name = $objectNames->[$idx];
1644        my $object1Structure = $self->_GetStructure($object1Name);
1645        # Get the field list.
1646        if (! exists $object1Structure->{searchFields}) {
1647            Confess("No searchable index for $object1Name.");
1648        } else {
1649            # Get the field list.
1650            my @fields = @{$object1Structure->{searchFields}};
1651            # Clean the search expression.
1652            my $actualKeywords = $self->CleanKeywords($searchExpression);
1653            # Prefix a "+" to each uncontrolled word. This converts the default
1654            # search mode from OR to AND.
1655            $actualKeywords =~ s/(^|\s)(\w|")/$1\+$2/g;
1656            Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1657            # We need two match expressions, one for the filter clause and one in the
1658            # query itself. Both will use a parameter mark, so we need to push the
1659            # search expression onto the front of the parameter list twice.
1660            unshift @myParams, $actualKeywords, $actualKeywords;
1661            # Build the match expression.
1662            my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
1663            my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
1664            # Process the SQL stuff.
1665            my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1666                $self->_SetupSQL($objectNames, $filterClause, $matchClause);
1667            # Create the query. Note that the match clause is inserted at the front of
1668            # the select fields.
1669            my $command = "SELECT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .
1670                ".* $suffix";
1671            my $sth = $self->_GetStatementHandle($command, \@myParams);
1672            # Now we create the relation map, which enables DBQuery to determine the order, name
1673            # and mapped name for each object in the query.
1674            my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
1675            # Return the statement object.
1676            $retVal = DBQuery::_new($self, $sth, \@relationMap, $object1Name);
1677        }
1678        return $retVal;
1679    }
1680    
1681  =head3 GetFlat  =head3 GetFlat
1682    
1683  C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>      my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field);
1684    
1685  This is a variation of L</GetAll> that asks for only a single field per record and  This is a variation of L</GetAll> that asks for only a single field per record and
1686  returns a single flattened list.  returns a single flattened list.
# Line 1147  Line 1731 
1731      return @retVal;      return @retVal;
1732  }  }
1733    
1734    =head3 SpecialFields
1735    
1736        my %specials = $erdb->SpecialFields($entityName);
1737    
1738    Return a hash mapping special fields in the specified entity to the value of their
1739    C<special> attribute. This enables the subclass to get access to the special field
1740    attributes without needed to plumb the internal ERDB data structures.
1741    
1742    =over 4
1743    
1744    =item entityName
1745    
1746    Name of the entity whose special fields are desired.
1747    
1748    =item RETURN
1749    
1750    Returns a hash. The keys of the hash are the special field names, and the values
1751    are the values from each special field's C<special> attribute.
1752    
1753    =back
1754    
1755    =cut
1756    
1757    sub SpecialFields {
1758        # Get the parameters.
1759        my ($self, $entityName) = @_;
1760        # Declare the return variable.
1761        my %retVal = ();
1762        # Find the entity's data structure.
1763        my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1764        # Loop through its fields, adding each special field to the return hash.
1765        my $fieldHash = $entityData->{Fields};
1766        for my $fieldName (keys %{$fieldHash}) {
1767            my $fieldData = $fieldHash->{$fieldName};
1768            if (exists $fieldData->{special}) {
1769                $retVal{$fieldName} = $fieldData->{special};
1770            }
1771        }
1772        # Return the result.
1773        return %retVal;
1774    }
1775    
1776  =head3 Delete  =head3 Delete
1777    
1778  C<< my $stats = $erdb->Delete($entityName, $objectID); >>      my $stats = $erdb->Delete($entityName, $objectID, %options);
1779    
1780  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
1781  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.
1782  always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many  
1783  relationship connected to a dependent entity or 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
1784    relationship connected to a dependent entity or if it is the "to" entity connected to a 1-to-many
1785  dependent relationship.  dependent relationship.
1786    
1787  =over 4  =over 4
# Line 1168  Line 1795 
1795  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<%>),
1796  then it is presumed to by a LIKE pattern.  then it is presumed to by a LIKE pattern.
1797    
1798  =item testFlag  =item options
1799    
1800  If TRUE, the delete statements will be traced without being executed.  A hash detailing the options for this delete operation.
1801    
1802  =item RETURN  =item RETURN
1803    
# Line 1179  Line 1806 
1806    
1807  =back  =back
1808    
1809    The permissible options for this method are as follows.
1810    
1811    =over 4
1812    
1813    =item testMode
1814    
1815    If TRUE, then the delete statements will be traced, but no changes will be made to the database.
1816    
1817    =item keepRoot
1818    
1819    If TRUE, then the entity instances will not be deleted, only the dependent records.
1820    
1821    =back
1822    
1823  =cut  =cut
1824  #: Return Type $%;  #: Return Type $%;
1825  sub Delete {  sub Delete {
1826      # Get the parameters.      # Get the parameters.
1827      my ($self, $entityName, $objectID, $testFlag) = @_;      my ($self, $entityName, $objectID, %options) = @_;
1828      # Declare the return variable.      # Declare the return variable.
1829      my $retVal = Stats->new();      my $retVal = Stats->new();
1830      # Get the DBKernel object.      # Get the DBKernel object.
# Line 1200  Line 1841 
1841      # FROM-relationships and entities.      # FROM-relationships and entities.
1842      my @fromPathList = ();      my @fromPathList = ();
1843      my @toPathList = ();      my @toPathList = ();
1844      # This final hash is used to remember what work still needs to be done. We push paths      # This final list is used to remember what work still needs to be done. We push paths
1845      # onto the list, then pop them off to extend the paths. We prime it with the starting      # onto the list, then pop them off to extend the paths. We prime it with the starting
1846      # point. Note that we will work hard to insure that the last item on a path in the      # point. Note that we will work hard to insure that the last item on a path in the
1847      # TODO list is always an entity.      # to-do list is always an entity.
1848      my @todoList = ([$entityName]);      my @todoList = ([$entityName]);
1849      while (@todoList) {      while (@todoList) {
1850          # Get the current path.          # Get the current path.
# Line 1211  Line 1852 
1852          # Copy it into a list.          # Copy it into a list.
1853          my @stackedPath = @{$current};          my @stackedPath = @{$current};
1854          # 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.
1855          my $entityName = pop @stackedPath;          my $myEntityName = pop @stackedPath;
1856          # Add it to the alreadyFound list.          # Add it to the alreadyFound list.
1857          $alreadyFound{$entityName} = 1;          $alreadyFound{$myEntityName} = 1;
1858            # Figure out if we need to delete this entity.
1859            if ($myEntityName ne $entityName || ! $options{keepRoot}) {
1860          # Get the entity data.          # Get the entity data.
1861          my $entityData = $self->_GetStructure($entityName);              my $entityData = $self->_GetStructure($myEntityName);
1862          # 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.  
1863          my $relations = $entityData->{Relations};          my $relations = $entityData->{Relations};
1864          for my $relation (keys %{$relations}) {          for my $relation (keys %{$relations}) {
1865              my @augmentedList = (@stackedPath, $relation);              my @augmentedList = (@stackedPath, $relation);
1866              push @fromPathList, \@augmentedList;              push @fromPathList, \@augmentedList;
1867          }          }
1868            }
1869          # Now we need to look for relationships connected to this entity.          # Now we need to look for relationships connected to this entity.
1870          my $relationshipList = $self->{_metaData}->{Relationships};          my $relationshipList = $self->{_metaData}->{Relationships};
1871          for my $relationshipName (keys %{$relationshipList}) {          for my $relationshipName (keys %{$relationshipList}) {
1872              my $relationship = $relationshipList->{$relationshipName};              my $relationship = $relationshipList->{$relationshipName};
1873              # Check the FROM field. We're only interested if it's us.              # Check the FROM field. We're only interested if it's us.
1874              if ($relationship->{from} eq $entityName) {              if ($relationship->{from} eq $myEntityName) {
1875                  # Add the path to this relationship.                  # Add the path to this relationship.
1876                  my @augmentedList = (@stackedPath, $entityName, $relationshipName);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1877                  push @fromPathList, \@augmentedList;                  push @fromPathList, \@augmentedList;
1878                  # Check the arity. If it's MM we're done. If it's 1M                  # Check the arity. If it's MM we're done. If it's 1M
1879                  # and the target hasn't been seen yet, we want to                  # and the target hasn't been seen yet, we want to
# Line 1249  Line 1892 
1892              }              }
1893              # Now check the TO field. In this case only the relationship needs              # Now check the TO field. In this case only the relationship needs
1894              # deletion.              # deletion.
1895              if ($relationship->{to} eq $entityName) {              if ($relationship->{to} eq $myEntityName) {
1896                  my @augmentedList = (@stackedPath, $entityName, $relationshipName);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1897                  push @toPathList, \@augmentedList;                  push @toPathList, \@augmentedList;
1898              }              }
1899          }          }
1900      }      }
1901      # Create the first qualifier for the WHERE clause. This selects the      # Create the first qualifier for the WHERE clause. This selects the
1902      # 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
1903      # 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
1904      # to the table containing the dependent records to delete.      # to the table containing the dependent records to delete.
1905      my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");      my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
1906      # 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 1296  Line 1939 
1939                  }                  }
1940              }              }
1941              # Now we have our desired DELETE statement.              # Now we have our desired DELETE statement.
1942              if ($testFlag) {              if ($options{testMode}) {
1943                  # Here the user wants to trace without executing.                  # Here the user wants to trace without executing.
1944                  Trace($stmt) if T(0);                  Trace($stmt) if T(0);
1945              } else {              } else {
1946                  # 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
1947                  # if an error occurs, so we just go ahead and do it.                  # if an error occurs, so we just go ahead and do it.
1948                  Trace("Executing delete from $target using '$objectID'.") if T(3);                  Trace("Executing delete from $target using '$objectID'.") if T(3);
1949                  my $rv = $db->SQL($stmt, 0, $objectID);                  my $rv = $db->SQL($stmt, 0, $objectID);
# Line 1315  Line 1958 
1958      return $retVal;      return $retVal;
1959  }  }
1960    
1961    =head3 Disconnect
1962    
1963        $erdb->Disconnect($relationshipName, $originEntityName, $originEntityID);
1964    
1965    Disconnect an entity instance from all the objects to which it is related. This
1966    will delete each relationship instance that connects to the specified entity.
1967    
1968    =over 4
1969    
1970    =item relationshipName
1971    
1972    Name of the relationship whose instances are to be deleted.
1973    
1974    =item originEntityName
1975    
1976    Name of the entity that is to be disconnected.
1977    
1978    =item originEntityID
1979    
1980    ID of the entity that is to be disconnected.
1981    
1982    =back
1983    
1984    =cut
1985    
1986    sub Disconnect {
1987        # Get the parameters.
1988        my ($self, $relationshipName, $originEntityName, $originEntityID) = @_;
1989        # Get the relationship descriptor.
1990        my $structure = $self->_GetStructure($relationshipName);
1991        # Insure we have a relationship.
1992        if (! exists $structure->{from}) {
1993            Confess("$relationshipName is not a relationship in the database.");
1994        } else {
1995            # Get the database handle.
1996            my $dbh = $self->{_dbh};
1997            # We'll set this value to 1 if we find our entity.
1998            my $found = 0;
1999            # Loop through the ends of the relationship.
2000            for my $dir ('from', 'to') {
2001                if ($structure->{$dir} eq $originEntityName) {
2002                    # Delete all relationship instances on this side of the entity instance.
2003                    Trace("Disconnecting in $dir direction with ID \"$originEntityID\".");
2004                    $dbh->SQL("DELETE FROM $relationshipName WHERE ${dir}_link = ?", 0, $originEntityID);
2005                    $found = 1;
2006                }
2007            }
2008            # Insure we found the entity on at least one end.
2009            if (! $found) {
2010                Confess("Entity \"$originEntityName\" does not use $relationshipName.");
2011            }
2012        }
2013    }
2014    
2015    =head3 DeleteRow
2016    
2017        $erdb->DeleteRow($relationshipName, $fromLink, $toLink, \%values);
2018    
2019    Delete a row from a relationship. In most cases, only the from-link and to-link are
2020    needed; however, for relationships with intersection data values can be specified
2021    for the other fields using a hash.
2022    
2023    =over 4
2024    
2025    =item relationshipName
2026    
2027    Name of the relationship from which the row is to be deleted.
2028    
2029    =item fromLink
2030    
2031    ID of the entity instance in the From direction.
2032    
2033    =item toLink
2034    
2035    ID of the entity instance in the To direction.
2036    
2037    =item values
2038    
2039    Reference to a hash of other values to be used for filtering the delete.
2040    
2041    =back
2042    
2043    =cut
2044    
2045    sub DeleteRow {
2046        # Get the parameters.
2047        my ($self, $relationshipName, $fromLink, $toLink, $values) = @_;
2048        # Create a hash of all the filter information.
2049        my %filter = ('from-link' => $fromLink, 'to-link' => $toLink);
2050        if (defined $values) {
2051            for my $key (keys %{$values}) {
2052                $filter{$key} = $values->{$key};
2053            }
2054        }
2055        # Build an SQL statement out of the hash.
2056        my @filters = ();
2057        my @parms = ();
2058        for my $key (keys %filter) {
2059            push @filters, _FixName($key) . " = ?";
2060            push @parms, $filter{$key};
2061        }
2062        Trace("Parms for delete row are " . join(", ", map { "\"$_\"" } @parms) . ".") if T(SQL => 4);
2063        my $command = "DELETE FROM $relationshipName WHERE " .
2064                      join(" AND ", @filters);
2065        # Execute it.
2066        my $dbh = $self->{_dbh};
2067        $dbh->SQL($command, undef, @parms);
2068    }
2069    
2070    =head3 DeleteLike
2071    
2072        my $deleteCount = $erdb->DeleteLike($relName, $filter, \@parms);
2073    
2074    Delete all the relationship rows that satisfy a particular filter condition. Unlike a normal
2075    filter, only fields from the relationship itself can be used.
2076    
2077    =over 4
2078    
2079    =item relName
2080    
2081    Name of the relationship whose records are to be deleted.
2082    
2083    =item filter
2084    
2085    A filter clause (L</Get>-style) for the delete query.
2086    
2087    =item parms
2088    
2089    Reference to a list of parameters for the filter clause.
2090    
2091    =item RETURN
2092    
2093    Returns a count of the number of rows deleted.
2094    
2095    =back
2096    
2097    =cut
2098    
2099    sub DeleteLike {
2100        # Get the parameters.
2101        my ($self, $objectName, $filter, $parms) = @_;
2102        # Declare the return variable.
2103        my $retVal;
2104        # Insure the parms argument is an array reference if the caller left it off.
2105        if (! defined($parms)) {
2106            $parms = [];
2107        }
2108        # Insure we have a relationship. The main reason for this is if we delete an entity
2109        # instance we have to yank out a bunch of other stuff with it.
2110        if ($self->IsEntity($objectName)) {
2111            Confess("Cannot use DeleteLike on $objectName, because it is not a relationship.");
2112        } else {
2113            # Create the SQL command suffix to get the desierd records.
2114            my ($suffix) = $self->_SetupSQL([$objectName], $filter);
2115            # Convert it to a DELETE command.
2116            my $command = "DELETE $suffix";
2117            # Execute the command.
2118            my $dbh = $self->{_dbh};
2119            my $result = $dbh->SQL($command, 0, @{$parms});
2120            # Check the results. Note we convert the "0D0" result to a real zero.
2121            # A failure causes an abnormal termination, so the caller isn't going to
2122            # worry about it.
2123            if (! defined $result) {
2124                Confess("Error deleting from $objectName: " . $dbh->errstr());
2125            } elsif ($result == 0) {
2126                $retVal = 0;
2127            } else {
2128                $retVal = $result;
2129            }
2130        }
2131        # Return the result count.
2132        return $retVal;
2133    }
2134    
2135    =head3 SortNeeded
2136    
2137        my $parms = $erdb->SortNeeded($relationName);
2138    
2139    Return the pipe command for the sort that should be applied to the specified
2140    relation when creating the load file.
2141    
2142    For example, if the load file should be sorted ascending by the first
2143    field, this method would return
2144    
2145        sort -k1 -t"\t"
2146    
2147    If the first field is numeric, the method would return
2148    
2149        sort -k1n -t"\t"
2150    
2151    Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate
2152    keys using a sort.
2153    
2154    =over 4
2155    
2156    =item relationName
2157    
2158    Name of the relation to be examined.
2159    
2160    =item
2161    
2162    Returns the sort command to use for sorting the relation, suitable for piping.
2163    
2164    =back
2165    
2166    =cut
2167    #: Return Type $;
2168    sub SortNeeded {
2169        # Get the parameters.
2170        my ($self, $relationName) = @_;
2171        # Declare a descriptor to hold the names of the key fields.
2172        my @keyNames = ();
2173        # Get the relation structure.
2174        my $relationData = $self->_FindRelation($relationName);
2175        # Find out if the relation is a primary entity relation,
2176        # a relationship relation, or a secondary entity relation.
2177        my $entityTable = $self->{_metaData}->{Entities};
2178        my $relationshipTable = $self->{_metaData}->{Relationships};
2179        if (exists $entityTable->{$relationName}) {
2180            # Here we have a primary entity relation.
2181            push @keyNames, "id";
2182        } elsif (exists $relationshipTable->{$relationName}) {
2183            # Here we have a relationship. We sort using the FROM index.
2184            my $relationshipData = $relationshipTable->{$relationName};
2185            my $index = $relationData->{Indexes}->{idxFrom};
2186            push @keyNames, @{$index->{IndexFields}};
2187        } else {
2188            # Here we have a secondary entity relation, so we have a sort on the ID field.
2189            push @keyNames, "id";
2190        }
2191        # Now we parse the key names into sort parameters. First, we prime the return
2192        # string.
2193        my $retVal = "sort -t\"\t\" ";
2194        # Get the relation's field list.
2195        my @fields = @{$relationData->{Fields}};
2196        # Loop through the keys.
2197        for my $keyData (@keyNames) {
2198            # Get the key and the ordering.
2199            my ($keyName, $ordering);
2200            if ($keyData =~ /^([^ ]+) DESC/) {
2201                ($keyName, $ordering) = ($1, "descending");
2202            } else {
2203                ($keyName, $ordering) = ($keyData, "ascending");
2204            }
2205            # Find the key's position and type.
2206            my $fieldSpec;
2207            for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {
2208                my $thisField = $fields[$i];
2209                if ($thisField->{name} eq $keyName) {
2210                    # Get the sort modifier for this field type. The modifier
2211                    # decides whether we're using a character, numeric, or
2212                    # floating-point sort.
2213                    my $modifier = $TypeTable{$thisField->{type}}->{sort};
2214                    # If the index is descending for this field, denote we want
2215                    # to reverse the sort order on this field.
2216                    if ($ordering eq 'descending') {
2217                        $modifier .= "r";
2218                    }
2219                    # Store the position and modifier into the field spec, which
2220                    # will stop the inner loop. Note that the field number is
2221                    # 1-based in the sort command, so we have to increment the
2222                    # index.
2223                    $fieldSpec = ($i + 1) . $modifier;
2224                }
2225            }
2226            # Add this field to the sort command.
2227            $retVal .= " -k$fieldSpec";
2228        }
2229        # Return the result.
2230        return $retVal;
2231    }
2232    
2233  =head3 GetList  =head3 GetList
2234    
2235  C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>      my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params);
2236    
2237  Return a list of object descriptors for the specified objects as determined by the  Return a list of object descriptors for the specified objects as determined by the
2238  specified filter clause.  specified filter clause.
# Line 1345  Line 2260 
2260  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
2261  particular genus and sorts them by species name.  particular genus and sorts them by species name.
2262    
2263  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>      "Genome(genus) = ? ORDER BY Genome(species)"
2264    
2265  The rules for field references in a sort order are the same as those for field references in the  The rules for field references in a sort order are the same as those for field references in the
2266  filter clause in general; however, odd things may happen if a sort field is from a secondary  filter clause in general; however, odd things may happen if a sort field is from a secondary
# Line 1357  Line 2272 
2272    
2273  =item RETURN  =item RETURN
2274    
2275  Returns a list of B<DBObject>s that satisfy the query conditions.  Returns a list of B<ERDBObject>s that satisfy the query conditions.
2276    
2277  =back  =back
2278    
# Line 1380  Line 2295 
2295    
2296  =head3 GetCount  =head3 GetCount
2297    
2298  C<< my $count = $erdb->GetCount(\@objectNames, $filter, \@params); >>      my $count = $erdb->GetCount(\@objectNames, $filter, \@params);
2299    
2300  Return the number of rows found by a specified query. This method would  Return the number of rows found by a specified query. This method would
2301  normally be used to count the records in a single table. For example, in a  normally be used to count the records in a single table. For example, in a
# Line 1431  Line 2346 
2346  sub GetCount {  sub GetCount {
2347      # Get the parameters.      # Get the parameters.
2348      my ($self, $objectNames, $filter, $params) = @_;      my ($self, $objectNames, $filter, $params) = @_;
2349        # Insure the params argument is an array reference if the caller left it off.
2350        if (! defined($params)) {
2351            $params = [];
2352        }
2353      # Declare the return variable.      # Declare the return variable.
2354      my $retVal;      my $retVal;
2355      # Find out if we're counting an entity or a relationship.      # Find out if we're counting an entity or a relationship.
# Line 1469  Line 2388 
2388    
2389  =head3 ComputeObjectSentence  =head3 ComputeObjectSentence
2390    
2391  C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>      my $sentence = $erdb->ComputeObjectSentence($objectName);
2392    
2393  Check an object name, and if it is a relationship convert it to a relationship sentence.  Check an object name, and if it is a relationship convert it to a relationship sentence.
2394    
# Line 1504  Line 2423 
2423    
2424  =head3 DumpRelations  =head3 DumpRelations
2425    
2426  C<< $erdb->DumpRelations($outputDirectory); >>      $erdb->DumpRelations($outputDirectory);
2427    
2428  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.
2429  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 1546  Line 2465 
2465    
2466  =head3 InsertValue  =head3 InsertValue
2467    
2468  C<< $erdb->InsertValue($entityID, $fieldName, $value); >>      $erdb->InsertValue($entityID, $fieldName, $value);
2469    
2470  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
2471  associated with a secondary relation, since primary values cannot be inserted:  associated with a secondary relation, since primary values cannot be inserted:
# Line 1609  Line 2528 
2528    
2529  =head3 InsertObject  =head3 InsertObject
2530    
2531  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>      $erdb->InsertObject($objectType, \%fieldHash);
2532    
2533  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
2534  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 1618  Line 2537 
2537  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
2538  C<ZP_00210270.1> and C<gi|46206278>.  C<ZP_00210270.1> and C<gi|46206278>.
2539    
2540  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']});
2541    
2542  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
2543  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>.
2544    
2545  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'});
2546    
2547  =over 4  =over 4
2548    
# Line 1635  Line 2554 
2554    
2555  Hash of field names to values.  Hash of field names to values.
2556    
 =item RETURN  
   
 Returns 1 if successful, 0 if an error occurred.  
   
2557  =back  =back
2558    
2559  =cut  =cut
# Line 1737  Line 2652 
2652                  $retVal = $sth->execute(@parameterList);                  $retVal = $sth->execute(@parameterList);
2653                  if (!$retVal) {                  if (!$retVal) {
2654                      my $errorString = $sth->errstr();                      my $errorString = $sth->errstr();
2655                      Trace("Insert error: $errorString.") if T(0);                      Confess("Error inserting into $relationName: $errorString");
2656                    } else {
2657                        Trace("Insert successful using $parameterList[0].") if T(3);
2658                  }                  }
2659              }              }
2660          }          }
2661      }      }
2662      # Return the success indicator.      # Return a 1 for backward compatability.
2663      return $retVal;      return 1;
2664    }
2665    
2666    =head3 UpdateEntity
2667    
2668        $erdb->UpdateEntity($entityName, $id, \%fields);
2669    
2670    Update the values of an entity. This is an unprotected update, so it should only be
2671    done if the database resides on a database server.
2672    
2673    =over 4
2674    
2675    =item entityName
2676    
2677    Name of the entity to update. (This is the entity type.)
2678    
2679    =item id
2680    
2681    ID of the entity to update. If no entity exists with this ID, an error will be thrown.
2682    
2683    =item fields
2684    
2685    Reference to a hash mapping field names to their new values. All of the fields named
2686    must be in the entity's primary relation, and they cannot any of them be the ID field.
2687    
2688    =back
2689    
2690    =cut
2691    
2692    sub UpdateEntity {
2693        # Get the parameters.
2694        my ($self, $entityName, $id, $fields) = @_;
2695        # Get a list of the field names being updated.
2696        my @fieldList = keys %{$fields};
2697        # Verify that the fields exist.
2698        my $checker = $self->GetFieldTable($entityName);
2699        for my $field (@fieldList) {
2700            if ($field eq 'id') {
2701                Confess("Cannot update the ID field for entity $entityName.");
2702            } elsif ($checker->{$field}->{relation} ne $entityName) {
2703                Confess("Cannot find $field in primary relation of $entityName.");
2704            }
2705        }
2706        # Build the SQL statement.
2707        my @sets = ();
2708        my @valueList = ();
2709        for my $field (@fieldList) {
2710            push @sets, _FixName($field) . " = ?";
2711            push @valueList, $fields->{$field};
2712        }
2713        my $command = "UPDATE $entityName SET " . join(", ", @sets) . " WHERE id = ?";
2714        # Add the ID to the list of binding values.
2715        push @valueList, $id;
2716        # Call SQL to do the work.
2717        my $rows = $self->{_dbh}->SQL($command, 0, @valueList);
2718        # Check for errors.
2719        if ($rows == 0) {
2720            Confess("Entity $id of type $entityName not found.");
2721        }
2722  }  }
2723    
2724  =head3 LoadTable  =head3 LoadTable
2725    
2726  C<< my %results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>      my $results = $erdb->LoadTable($fileName, $relationName, $truncateFlag);
2727    
2728  Load data from a tab-delimited file into a specified table, optionally re-creating the table  Load data from a tab-delimited file into a specified table, optionally re-creating the table
2729  first.  first.
# Line 1791  Line 2766 
2766      if ($truncateFlag) {      if ($truncateFlag) {
2767          Trace("Creating table $relationName") if T(2);          Trace("Creating table $relationName") if T(2);
2768          # 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,
2769          # 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
2770          # leave extra room. We postulate a minimum row count of 1000 to          # leave extra room. We postulate a minimum row count of 1000 to
2771          # prevent problems with incoming empty load files.          # prevent problems with incoming empty load files.
2772          my $rowSize = $self->EstimateRowSize($relationName);          my $rowSize = $self->EstimateRowSize($relationName);
2773          my $estimate = FIG::max($fileSize * 1.5 / $rowSize, 1000);          my $estimate = $fileSize * 8 / $rowSize;
2774            if ($estimate < 1000) {
2775                $estimate = 1000;
2776            }
2777          # Re-create the table without its index.          # Re-create the table without its index.
2778          $self->CreateTable($relationName, 0, $estimate);          $self->CreateTable($relationName, 0, $estimate);
2779          # If this is a pre-index DBMS, create the index here.          # If this is a pre-index DBMS, create the index here.
# Line 1815  Line 2793 
2793      };      };
2794      if (!defined $rv) {      if (!defined $rv) {
2795          $retVal->AddMessage($@) if ($@);          $retVal->AddMessage($@) if ($@);
2796          $retVal->AddMessage("Table load failed for $relationName using $fileName.");          $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2797          Trace("Table load failed for $relationName.") if T(1);          Trace("Table load failed for $relationName.") if T(1);
2798      } else {      } else {
2799          # Here we successfully loaded the table.          # Here we successfully loaded the table.
# Line 1823  Line 2801 
2801          my $size = -s $fileName;          my $size = -s $fileName;
2802          Trace("$size bytes loaded into $relationName.") if T(2);          Trace("$size bytes loaded into $relationName.") if T(2);
2803          # If we're rebuilding, we need to create the table indexes.          # If we're rebuilding, we need to create the table indexes.
2804          if ($truncateFlag && ! $dbh->{_preIndex}) {          if ($truncateFlag) {
2805                # Indexes are created here for PostGres. For PostGres, indexes are
2806                # best built at the end. For MySQL, the reverse is true.
2807                if (! $dbh->{_preIndex}) {
2808              eval {              eval {
2809                  $self->CreateIndex($relationName);                  $self->CreateIndex($relationName);
2810              };              };
# Line 1831  Line 2812 
2812                  $retVal->AddMessage($@);                  $retVal->AddMessage($@);
2813              }              }
2814          }          }
2815                # The full-text index (if any) is always built last, even for MySQL.
2816                # First we need to see if this table has a full-text index. Only
2817                # primary relations are allowed that privilege.
2818                Trace("Checking for full-text index on $relationName.") if T(2);
2819                if ($self->_IsPrimary($relationName)) {
2820                    $self->CreateSearchIndex($relationName);
2821                }
2822            }
2823      }      }
2824      # Analyze the table to improve performance.      # Analyze the table to improve performance.
2825        Trace("Analyzing and compacting $relationName.") if T(3);
2826      $dbh->vacuum_it($relationName);      $dbh->vacuum_it($relationName);
2827        Trace("$relationName load completed.") if T(3);
2828      # Return the statistics.      # Return the statistics.
2829      return $retVal;      return $retVal;
2830  }  }
2831    
2832  =head3 GenerateEntity  =head3 CreateSearchIndex
2833    
2834  C<< my $fieldHash = $erdb->GenerateEntity($id, $type, \%values); >>      $erdb->CreateSearchIndex($objectName);
2835    
2836  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
2837  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.  
2838    
2839  =over 4  =over 4
2840    
2841  =item id  =item objectName
2842    
2843  ID to assign to the new entity.  Name of the entity or relationship to be indexed.
2844    
2845  =item type  =back
2846    
2847  Type name for the new entity.  =cut
2848    
2849  =item values  sub CreateSearchIndex {
2850        # Get the parameters.
2851        my ($self, $objectName) = @_;
2852        # Get the relation's entity/relationship structure.
2853        my $structure = $self->_GetStructure($objectName);
2854        # Get the database handle.
2855        my $dbh = $self->{_dbh};
2856        Trace("Checking for search fields in $objectName.") if T(3);
2857        # Check for a searchable fields list.
2858        if (exists $structure->{searchFields}) {
2859            # Here we know that we need to create a full-text search index.
2860            # Get an SQL-formatted field name list.
2861            my $fields = join(", ", _FixNames(@{$structure->{searchFields}}));
2862            # Create the index. If it already exists, it will be dropped.
2863            $dbh->create_index(tbl => $objectName, idx => "search_idx",
2864                               flds => $fields, kind => 'fulltext');
2865            Trace("Index created for $fields in $objectName.") if T(2);
2866        }
2867    }
2868    
2869    =head3 DropRelation
2870    
2871        $erdb->DropRelation($relationName);
2872    
2873    Physically drop a relation from the database.
2874    
2875    =over 4
2876    
2877    =item relationName
2878    
2879  Hash containing additional values that might be needed by the data generation methods (optional).  Name of the relation to drop. If it does not exist, this method will have
2880    no effect.
2881    
2882  =back  =back
2883    
2884  =cut  =cut
2885    
2886  sub GenerateEntity {  sub DropRelation {
2887      # Get the parameters.      # Get the parameters.
2888      my ($self, $id, $type, $values) = @_;      my ($self, $relationName) = @_;
2889      # Create the return hash.      # Get the database handle.
2890      my $this = { id => $id };      my $dbh = $self->{_dbh};
2891      # Get the metadata structure.      # Drop the relation. The method used here has no effect if the relation
2892      my $metadata = $self->{_metaData};      # does not exist.
2893      # Get this entity's list of fields.      Trace("Invoking DB Kernel to drop $relationName.") if T(3);
2894      if (!exists $metadata->{Entities}->{$type}) {      $dbh->drop_table(tbl => $relationName);
2895          Confess("Unrecognized entity type $type in GenerateEntity.");  }
2896      } else {  
2897          my $entity = $metadata->{Entities}->{$type};  =head3 MatchSqlPattern
2898          my $fields = $entity->{Fields};  
2899          # Generate data from the fields.      my $matched = ERDB::MatchSqlPattern($value, $pattern);
2900          _GenerateFields($this, $fields, $type, $values);  
2901    Determine whether or not a specified value matches an SQL pattern. An SQL
2902    pattern has two wild card characters: C<%> that matches multiple characters,
2903    and C<_> that matches a single character. These can be escaped using a
2904    backslash (C<\>). We pull this off by converting the SQL pattern to a
2905    PERL regular expression. As per SQL rules, the match is case-insensitive.
2906    
2907    =over 4
2908    
2909    =item value
2910    
2911    Value to be matched against the pattern. Note that an undefined or empty
2912    value will not match anything.
2913    
2914    =item pattern
2915    
2916    SQL pattern against which to match the value. An undefined or empty pattern will
2917    match everything.
2918    
2919    =item RETURN
2920    
2921    Returns TRUE if the value and pattern match, else FALSE.
2922    
2923    =back
2924    
2925    =cut
2926    
2927    sub MatchSqlPattern {
2928        # Get the parameters.
2929        my ($value, $pattern) = @_;
2930        # Declare the return variable.
2931        my $retVal;
2932        # Insure we have a pattern.
2933        if (! defined($pattern) || $pattern eq "") {
2934            $retVal = 1;
2935        } else {
2936            # Break the pattern into pieces around the wildcard characters. Because we
2937            # use parentheses in the split function's delimiter expression, we'll get
2938            # list elements for the delimiters as well as the rest of the string.
2939            my @pieces = split /([_%]|\\[_%])/, $pattern;
2940            # Check some fast special cases.
2941            if ($pattern eq '%') {
2942                # A null pattern matches everything.
2943                $retVal = 1;
2944            } elsif (@pieces == 1) {
2945                # No wildcards, so we have a literal comparison. Note we're case-insensitive.
2946                $retVal = (lc($value) eq lc($pattern));
2947            } elsif (@pieces == 2 && $pieces[1] eq '%') {
2948                # A wildcard at the end, so we have a substring match. This is also case-insensitive.
2949                $retVal = (lc(substr($value, 0, length($pieces[0]))) eq lc($pieces[0]));
2950            } else {
2951                # Okay, we have to do it the hard way. Convert each piece to a PERL pattern.
2952                my $realPattern = "";
2953                for my $piece (@pieces) {
2954                    # Determine the type of piece.
2955                    if ($piece eq "") {
2956                        # Empty pieces are ignored.
2957                    } elsif ($piece eq "%") {
2958                        # Here we have a multi-character wildcard. Note that it can match
2959                        # zero or more characters.
2960                        $realPattern .= ".*"
2961                    } elsif ($piece eq "_") {
2962                        # Here we have a single-character wildcard.
2963                        $realPattern .= ".";
2964                    } elsif ($piece eq "\\%" || $piece eq "\\_") {
2965                        # This is an escape sequence (which is a rare thing, actually).
2966                        $realPattern .= substr($piece, 1, 1);
2967                    } else {
2968                        # Here we have raw text.
2969                        $realPattern .= quotemeta($piece);
2970                    }
2971                }
2972                # Do the match.
2973                $retVal = ($value =~ /^$realPattern$/i ? 1 : 0);
2974      }      }
2975      # Return the hash created.      }
2976      return $this;      # Return the result.
2977        return $retVal;
2978  }  }
2979    
2980  =head3 GetEntity  =head3 GetEntity
2981    
2982  C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>      my $entityObject = $erdb->GetEntity($entityType, $ID);
2983    
2984  Return an object describing the entity instance with a specified ID.  Return an object describing the entity instance with a specified ID.
2985    
# Line 1914  Line 2995 
2995    
2996  =item RETURN  =item RETURN
2997    
2998  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
2999  instance is found with the specified key.  instance is found with the specified key.
3000    
3001  =back  =back
# Line 1932  Line 3013 
3013      return $retVal;      return $retVal;
3014  }  }
3015    
3016  =head3 GetEntityValues  =head3 GetChoices
   
 C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>  
3017    
3018  Return a list of values from a specified entity instance.      my @values = $erdb->GetChoices($entityName, $fieldName);
3019    
3020  =over 4  Return a list of all the values for the specified field that are represented in the
3021    specified entity.
3022    
3023  =item entityType  Note that if the field is not indexed, then this will be a very slow operation.
3024    
3025  Entity type name.  =over 4
3026    
3027  =item ID  =item entityName
3028    
3029  ID of the desired entity.  Name of an entity in the database.
3030    
3031  =item fields  =item fieldName
3032    
3033  List of field names, each of the form I<objectName>C<(>I<fieldName>C<)>.  Name of a field belonging to the entity. This is a raw field name without
3034    the standard parenthesized notation used in most calls.
3035    
3036  =item RETURN  =item RETURN
3037    
3038  Returns a flattened list of the values of the specified fields for the specified entity.  Returns a list of the distinct values for the specified field in the database.
3039    
3040  =back  =back
3041    
3042  =cut  =cut
3043    
3044  sub GetEntityValues {  sub GetChoices {
3045      # Get the parameters.      # Get the parameters.
3046      my ($self, $entityType, $ID, $fields) = @_;      my ($self, $entityName, $fieldName) = @_;
3047      # Get the specified entity.      # Declare the return variable.
3048      my $entity = $self->GetEntity($entityType, $ID);      my @retVal;
3049      # Declare the return list.      # Get the entity data structure.
3050      my @retVal = ();      my $entityData = $self->_GetStructure($entityName);
3051      # If we found the entity, push the values into the return list.      # Get the field.
3052      if ($entity) {      my $fieldHash = $entityData->{Fields};
3053          push @retVal, $entity->Values($fields);      if (! exists $fieldHash->{$fieldName}) {
3054      }          Confess("$fieldName not found in $entityName.");
3055      # Return the result.      } else {
3056      return @retVal;          # Get the name of the relation containing the field.
3057            my $relation = $fieldHash->{$fieldName}->{relation};
3058            # Fix up the field name.
3059            my $realName = _FixName($fieldName);
3060            # Get the database handle.
3061            my $dbh = $self->{_dbh};
3062            # Query the database.
3063            my $results = $dbh->SQL("SELECT DISTINCT $realName FROM $relation");
3064            # Clean the results. They are stored as a list of lists, and we just want the one list.
3065            @retVal = sort map { $_->[0] } @{$results};
3066        }
3067        # Return the result.
3068        return @retVal;
3069    }
3070    
3071    =head3 GetEntityValues
3072    
3073        my @values = $erdb->GetEntityValues($entityType, $ID, \@fields);
3074    
3075    Return a list of values from a specified entity instance. If the entity instance
3076    does not exist, an empty list is returned.
3077    
3078    =over 4
3079    
3080    =item entityType
3081    
3082    Entity type name.
3083    
3084    =item ID
3085    
3086    ID of the desired entity.
3087    
3088    =item fields
3089    
3090    List of field names, each of the form I<objectName>C<(>I<fieldName>C<)>.
3091    
3092    =item RETURN
3093    
3094    Returns a flattened list of the values of the specified fields for the specified entity.
3095    
3096    =back
3097    
3098    =cut
3099    
3100    sub GetEntityValues {
3101        # Get the parameters.
3102        my ($self, $entityType, $ID, $fields) = @_;
3103        # Get the specified entity.
3104        my $entity = $self->GetEntity($entityType, $ID);
3105        # Declare the return list.
3106        my @retVal = ();
3107        # If we found the entity, push the values into the return list.
3108        if ($entity) {
3109            push @retVal, $entity->Values($fields);
3110        }
3111        # Return the result.
3112        return @retVal;
3113  }  }
3114    
3115  =head3 GetAll  =head3 GetAll
3116    
3117  C<< my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>      my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count);
3118    
3119  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
3120  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 1991  Line 3128 
3128  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
3129  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
3130  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
3131  feature ID followed by all of its aliases.  feature ID followed by all of its essentiality determinations.
3132    
3133  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)']);
3134    
3135  =over 4  =over 4
3136    
# Line 2071  Line 3208 
3208    
3209  =head3 Exists  =head3 Exists
3210    
3211  C<< my $found = $sprout->Exists($entityName, $entityID); >>      my $found = $sprout->Exists($entityName, $entityID);
3212    
3213  Return TRUE if an entity exists, else FALSE.  Return TRUE if an entity exists, else FALSE.
3214    
# Line 2106  Line 3243 
3243    
3244  =head3 EstimateRowSize  =head3 EstimateRowSize
3245    
3246  C<< my $rowSize = $erdb->EstimateRowSize($relName); >>      my $rowSize = $erdb->EstimateRowSize($relName);
3247    
3248  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
3249  up the average length for each data type.  up the average length for each data type.
# Line 2144  Line 3281 
3281    
3282  =head3 GetFieldTable  =head3 GetFieldTable
3283    
3284  C<< my $fieldHash = $self->GetFieldTable($objectnName); >>      my $fieldHash = $self->GetFieldTable($objectnName);
3285    
3286  Get the field structure for a specified entity or relationship.  Get the field structure for a specified entity or relationship.
3287    
# Line 2171  Line 3308 
3308      return $objectData->{Fields};      return $objectData->{Fields};
3309  }  }
3310    
3311    =head3 SplitKeywords
3312    
3313        my @keywords = ERDB::SplitKeywords($keywordString);
3314    
3315    This method returns a list of the positive keywords in the specified
3316    keyword string. All of the operators will have been stripped off,
3317    and if the keyword is preceded by a minus operator (C<->), it will
3318    not be in the list returned. The idea here is to get a list of the
3319    keywords the user wants to see. The list will be processed to remove
3320    duplicates.
3321    
3322    It is possible to create a string that confuses this method. For example
3323    
3324        frog toad -frog
3325    
3326    would return both C<frog> and C<toad>. If this is a problem we can deal
3327    with it later.
3328    
3329    =over 4
3330    
3331    =item keywordString
3332    
3333    The keyword string to be parsed.
3334    
3335    =item RETURN
3336    
3337    Returns a list of the words in the keyword string the user wants to
3338    see.
3339    
3340    =back
3341    
3342    =cut
3343    
3344    sub SplitKeywords {
3345        # Get the parameters.
3346        my ($keywordString) = @_;
3347        # Make a safety copy of the string. (This helps during debugging.)
3348        my $workString = $keywordString;
3349        # Convert operators we don't care about to spaces.
3350        $workString =~ tr/+"()<>/ /;
3351        # Split the rest of the string along space boundaries. Note that we
3352        # eliminate any words that are zero length or begin with a minus sign.
3353        my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
3354        # Use a hash to remove duplicates.
3355        my %words = map { $_ => 1 } @wordList;
3356        # Return the result.
3357        return sort keys %words;
3358    }
3359    
3360    =head3 ValidateFieldName
3361    
3362        my $okFlag = ERDB::ValidateFieldName($fieldName);
3363    
3364    Return TRUE if the specified field name is valid, else FALSE. Valid field names must
3365    be hyphenated words subject to certain restrictions.
3366    
3367    =over 4
3368    
3369    =item fieldName
3370    
3371    Field name to be validated.
3372    
3373    =item RETURN
3374    
3375    Returns TRUE if the field name is valid, else FALSE.
3376    
3377    =back
3378    
3379    =cut
3380    
3381    sub ValidateFieldName {
3382        # Get the parameters.
3383        my ($fieldName) = @_;
3384        # Declare the return variable. The field name is valid until we hear
3385        # differently.
3386        my $retVal = 1;
3387        # Compute the maximum name length.
3388        my $maxLen = $TypeTable{'name-string'}->{maxLen};
3389        # Look for bad stuff in the name.
3390        if ($fieldName =~ /--/) {
3391            # Here we have a doubled minus sign.
3392            Trace("Field name $fieldName has a doubled hyphen.") if T(1);
3393            $retVal = 0;
3394        } elsif ($fieldName !~ /^[A-Za-z]/) {
3395            # Here the field name is missing the initial letter.
3396            Trace("Field name $fieldName does not begin with a letter.") if T(1);
3397            $retVal = 0;
3398        } elsif (length($fieldName) > $maxLen) {
3399            # Here the field name is too long.
3400            Trace("Maximum field name length is $maxLen. Field name must be truncated to " . substr($fieldName,0, $maxLen) . ".");
3401        } else {
3402            # Strip out the minus signs. Everything remaining must be a letter,
3403            # underscore, or digit.
3404            my $strippedName = $fieldName;
3405            $strippedName =~ s/-//g;
3406            if ($strippedName !~ /^(\w|\d)+$/) {
3407                Trace("Field name $fieldName contains illegal characters.") if T(1);
3408                $retVal = 0;
3409            }
3410        }
3411        # Return the result.
3412        return $retVal;
3413    }
3414    
3415    =head3 ReadMetaXML
3416    
3417        my $rawMetaData = ERDB::ReadDBD($fileName);
3418    
3419    This method reads a raw database definition XML file and returns it.
3420    Normally, the metadata used by the ERDB system has been processed and
3421    modified to make it easier to load and retrieve the data; however,
3422    this method can be used to get the data in its raw form.
3423    
3424    =over 4
3425    
3426    =item fileName
3427    
3428    Name of the XML file to read.
3429    
3430    =item RETURN
3431    
3432    Returns a hash reference containing the raw XML data from the specified file.
3433    
3434    =back
3435    
3436    =cut
3437    
3438    sub ReadMetaXML {
3439        # Get the parameters.
3440        my ($fileName) = @_;
3441        # Read the XML.
3442        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
3443        Trace("XML metadata loaded from file $fileName.") if T(1);
3444        # Return the result.
3445        return $retVal;
3446    }
3447    
3448    =head3 GetEntityFieldHash
3449    
3450        my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName);
3451    
3452    Get the field hash of the named entity in the specified raw XML structure.
3453    The field hash may not exist, in which case we need to create it.
3454    
3455    =over 4
3456    
3457    =item structure
3458    
3459    Raw XML structure defininng the database. This is not the run-time XML used by
3460    an ERDB object, since that has all sorts of optimizations built-in.
3461    
3462    =item entityName
3463    
3464    Name of the entity whose field structure is desired.
3465    
3466    =item RETURN
3467    
3468    Returns the field hash used to define the entity's fields.
3469    
3470    =back
3471    
3472    =cut
3473    
3474    sub GetEntityFieldHash {
3475        # Get the parameters.
3476        my ($structure, $entityName) = @_;
3477        # Get the entity structure.
3478        my $entityData = $structure->{Entities}->{$entityName};
3479        # Look for a field structure.
3480        my $retVal = $entityData->{Fields};
3481        # If it doesn't exist, create it.
3482        if (! defined($retVal)) {
3483            $entityData->{Fields} = {};
3484            $retVal = $entityData->{Fields};
3485        }
3486        # Return the result.
3487        return $retVal;
3488    }
3489    
3490    =head3 WriteMetaXML
3491    
3492        ERDB::WriteMetaXML($structure, $fileName);
3493    
3494    Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
3495    used to update the database definition. It must be used with care, however, since it
3496    will only work on a raw structure, not on the processed structure created by an ERDB
3497    constructor.
3498    
3499    =over 4
3500    
3501    =item structure
3502    
3503    XML structure to be written to the file.
3504    
3505    =item fileName
3506    
3507    Name of the output file to which the updated XML should be stored.
3508    
3509    =back
3510    
3511    =cut
3512    
3513    sub WriteMetaXML {
3514        # Get the parameters.
3515        my ($structure, $fileName) = @_;
3516        # Compute the output.
3517        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
3518        # Write it to the file.
3519        my $xmlOut = Open(undef, ">$fileName");
3520        print $xmlOut $fileString;
3521    }
3522    
3523    
3524    =head3 HTMLNote
3525    
3526    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
3527    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
3528    Except for C<[p]>, all the codes are closed by slash-codes. So, for
3529    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
3530    
3531        my $realHtml = ERDB::HTMLNote($dataString);
3532    
3533    =over 4
3534    
3535    =item dataString
3536    
3537    String to convert to HTML.
3538    
3539    =item RETURN
3540    
3541    An HTML string derived from the input string.
3542    
3543    =back
3544    
3545    =cut
3546    
3547    sub HTMLNote {
3548        # Get the parameter.
3549        my ($dataString) = @_;
3550        # HTML-escape the text.
3551        my $retVal = CGI::escapeHTML($dataString);
3552        # Substitute the bulletin board codes.
3553        $retVal =~ s!\[(/?[bi])\]!<$1>!g;
3554        $retVal =~ s!\[p\]!</p><p>!g;
3555        $retVal =~ s!\[link\s+([^\]]+)\]!<a href="$1">!g;
3556        $retVal =~ s!\[/link\]!</a>!g;
3557        # Return the result.
3558        return $retVal;
3559    }
3560    
3561    =head3 BeginTran
3562    
3563        $erdb->BeginTran();
3564    
3565    Start a database transaction.
3566    
3567    =cut
3568    
3569    sub BeginTran {
3570        my ($self) = @_;
3571        $self->{_dbh}->begin_tran();
3572    
3573    }
3574    
3575    =head3 CommitTran
3576    
3577        $erdb->CommitTran();
3578    
3579    Commit an active database transaction.
3580    
3581    =cut
3582    
3583    sub CommitTran {
3584        my ($self) = @_;
3585        $self->{_dbh}->commit_tran();
3586    }
3587    
3588    =head3 RollbackTran
3589    
3590        $erdb->RollbackTran();
3591    
3592    Roll back an active database transaction.
3593    
3594    =cut
3595    
3596    sub RollbackTran {
3597        my ($self) = @_;
3598        $self->{_dbh}->roll_tran();
3599    }
3600    
3601    =head3 UpdateField
3602    
3603        my $count = $erdb->UpdateField($objectNames, $fieldName, $oldValue, $newValue, $filter, $parms);
3604    
3605    Update all occurrences of a specific field value to a new value. The number of rows changed will be
3606    returned.
3607    
3608    =over 4
3609    
3610    =item fieldName
3611    
3612    Name of the field in standard I<objectName>C<(>I<fieldName>C<)> format.
3613    
3614    =item oldValue
3615    
3616    Value to be modified. All occurrences of this value in the named field will be replaced by the
3617    new value.
3618    
3619    =item newValue
3620    
3621    New value to be substituted for the old value when it's found.
3622    
3623    =item filter
3624    
3625    A standard ERDB filter clause (see L</Get>). The filter will be applied before any substitutions take place.
3626    
3627    =item parms
3628    
3629    Reference to a list of parameter values in the filter.
3630    
3631    =item RETURN
3632    
3633    Returns the number of rows modified.
3634    
3635    =back
3636    
3637    =cut
3638    
3639    sub UpdateField {
3640        # Get the parameters.
3641        my ($self, $fieldName, $oldValue, $newValue, $filter, $parms) = @_;
3642        # Get the object and field names from the field name parameter.
3643        $fieldName =~ /^([^(]+)\(([^)]+)\)/;
3644        my $objectName = $1;
3645        my $realFieldName = _FixName($2);
3646        # Add the old value to the filter. Note we allow the possibility that no
3647        # filter was specified.
3648        my $realFilter = "$fieldName = ?";
3649        if ($filter) {
3650            $realFilter .= " AND $filter";
3651        }
3652        # Format the query filter.
3653        my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
3654            $self->_SetupSQL([$objectName], $realFilter);
3655        # Create the query. Since there is only one object name, the mapped-name data is not
3656        # necessary. Neither is the FROM clause.
3657        $suffix =~ s/^FROM.+WHERE\s+//;
3658        # Create the update statement.
3659        my $command = "UPDATE $objectName SET $realFieldName = ? WHERE $suffix";
3660        # Get the database handle.
3661        my $dbh = $self->{_dbh};
3662        # Add the old and new values to the parameter list. Note we allow the possibility that
3663        # there are no user-supplied parameters.
3664        my @params = ($newValue, $oldValue);
3665        if (defined $parms) {
3666            push @params, @{$parms};
3667        }
3668        # Execute the update.
3669        my $retVal = $dbh->SQL($command, 0, @params);
3670        # Make the funky zero a real zero.
3671        if ($retVal == 0) {
3672            $retVal = 0;
3673        }
3674        # Return the result.
3675        return $retVal;
3676    }
3677    
3678    
3679  =head2 Data Mining Methods  =head2 Data Mining Methods
3680    
3681  =head3 GetUsefulCrossValues  =head3 GetUsefulCrossValues
3682    
3683  C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>      my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship);
3684    
3685  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
3686  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 2236  Line 3741 
3741    
3742  =head3 FindColumn  =head3 FindColumn
3743    
3744  C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>      my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier);
3745    
3746  Return the location a desired column in a data mining header line. The data  Return the location a desired column in a data mining header line. The data
3747  mining header line is a tab-separated list of column names. The column  mining header line is a tab-separated list of column names. The column
# Line 2294  Line 3799 
3799    
3800  =head3 ParseColumns  =head3 ParseColumns
3801    
3802  C<< my @columns = ERDB::ParseColumns($line); >>      my @columns = ERDB::ParseColumns($line);
3803    
3804  Convert the specified data line to a list of columns.  Convert the specified data line to a list of columns.
3805    
# Line 2324  Line 3829 
3829      return @retVal;      return @retVal;
3830  }  }
3831    
3832    =head2 Virtual Methods
3833    
3834    =head3 _CreatePPOIndex
3835    
3836        my $index = ERDB::_CreatePPOIndex($indexObject);
3837    
3838    Convert the XML for an ERDB index to the XML structure for a PPO
3839    index.
3840    
3841    =over 4
3842    
3843    ERDB XML structure for an index.
3844    
3845    =item RETURN
3846    
3847    PPO XML structure for the same index.
3848    
3849    =back
3850    
3851    =cut
3852    
3853    sub _CreatePPOIndex {
3854        # Get the parameters.
3855        my ($indexObject) = @_;
3856        # The incoming index contains a list of the index fields in the IndexFields
3857        # member. We loop through it to create the index tags.
3858        my @fields = map { { label => _FixName($_->{name}) } } @{$indexObject->{IndexFields}};
3859        # Wrap the fields in attribute tags.
3860        my $retVal = { attribute => \@fields };
3861        # Return the result.
3862        return $retVal;
3863    }
3864    
3865    =head3 _CreatePPOField
3866    
3867        my $fieldXML = ERDB::_CreatePPOField($fieldName, $fieldObject);
3868    
3869    Convert the ERDB XML structure for a field to a PPO scalar XML structure.
3870    
3871    =over 4
3872    
3873    =item fieldName
3874    
3875    Name of the scalar field.
3876    
3877    =item fieldObject
3878    
3879    ERDB XML structure describing the field.
3880    
3881    =item RETURN
3882    
3883    Returns a PPO XML structure for the same field.
3884    
3885    =back
3886    
3887    =cut
3888    
3889    sub _CreatePPOField {
3890        # Get the parameters.
3891        my ($fieldName, $fieldObject) = @_;
3892        # Get the field type.
3893        my $type = $TypeTable{$fieldObject->{type}}->{sqlType};
3894        # Fix up the field name.
3895        $fieldName = _FixName($fieldName);
3896        # Build the scalar tag.
3897        my $retVal = { label => $fieldName, type => $type };
3898        # Return the result.
3899        return $retVal;
3900    }
3901    
3902    =head3 CleanKeywords
3903    
3904        my $cleanedString = $erdb->CleanKeywords($searchExpression);
3905    
3906    Clean up a search expression or keyword list. This is a virtual method that may
3907    be overridden by the subclass. The base-class method removes extra spaces
3908    and converts everything to lower case.
3909    
3910    =over 4
3911    
3912    =item searchExpression
3913    
3914    Search expression or keyword list to clean. Note that a search expression may
3915    contain boolean operators which need to be preserved. This includes leading
3916    minus signs.
3917    
3918    =item RETURN
3919    
3920    Cleaned expression or keyword list.
3921    
3922    =back
3923    
3924    =cut
3925    
3926    sub CleanKeywords {
3927        # Get the parameters.
3928        my ($self, $searchExpression) = @_;
3929        # Lower-case the expression and copy it into the return variable. Note that we insure we
3930        # don't accidentally end up with an undefined value.
3931        my $retVal = lc($searchExpression || "");
3932        # Remove extra spaces.
3933        $retVal =~ s/\s+/ /g;
3934        $retVal =~ s/(^\s+)|(\s+$)//g;
3935        # Return the result.
3936        return $retVal;
3937    }
3938    
3939    =head3 GetSourceObject
3940    
3941        my $source = $erdb->GetSourceObject($entityName);
3942    
3943    Return the object to be used in loading special attributes of the specified entity. The
3944    algorithm for loading special attributes is stored in the C<DataGen> elements of the
3945    XML
3946    
3947  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3948    
3949  =head3 SetupSQL  =head3 _RelationMap
3950    
3951        my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
3952    
3953    Create the relation map for an SQL query. The relation map is used by B<ERDBObject>
3954    to determine how to interpret the results of the query.
3955    
3956    =over 4
3957    
3958    =item mappedNameHashRef
3959    
3960    Reference to a hash that maps modified object names to real object names.
3961    
3962    =item mappedNameListRef
3963    
3964    Reference to a list of modified object names in the order they appear in the
3965    SELECT list.
3966    
3967    =item RETURN
3968    
3969    Returns a list of 2-tuples. Each tuple consists of an object name as used in the
3970    query followed by the actual name of that object. This enables the B<ERDBObject> to
3971    determine the order of the tables in the query and which object name belongs to each
3972    mapped object name. Most of the time these two values are the same; however, if a
3973    relation occurs twice in the query, the relation name in the field list and WHERE
3974    clause will use a mapped name (generally the actual relation name with a numeric
3975    suffix) that does not match the actual relation name.
3976    
3977    =back
3978    
3979    =cut
3980    
3981    sub _RelationMap {
3982        # Get the parameters.
3983        my ($mappedNameHashRef, $mappedNameListRef) = @_;
3984        # Declare the return variable.
3985        my @retVal = ();
3986        # Build the map.
3987        for my $mappedName (@{$mappedNameListRef}) {
3988            push @retVal, [$mappedName, $mappedNameHashRef->{$mappedName}];
3989        }
3990        # Return it.
3991        return @retVal;
3992    }
3993    
3994    
3995    =head3 _SetupSQL
3996    
3997  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
3998  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 2346  Line 4012 
4012  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
4013  optionally the C<ORDER BY> and C<LIMIT> clauses.  optionally the C<ORDER BY> and C<LIMIT> clauses.
4014    
4015    =item matchClause
4016    
4017    An optional full-text search clause. If specified, it will be inserted at the
4018    front of the WHERE clause. It should already be SQL-formatted; that is, the
4019    field names should be in the form I<table>C<.>I<fieldName>.
4020    
4021  =item RETURN  =item RETURN
4022    
4023  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 2358  Line 4030 
4030  =cut  =cut
4031    
4032  sub _SetupSQL {  sub _SetupSQL {
4033      my ($self, $objectNames, $filterClause) = @_;      my ($self, $objectNames, $filterClause, $matchClause) = @_;
4034      # 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
4035      # 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
4036      # 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 2407  Line 4079 
4079      # FROM name1, name2, ... nameN      # FROM name1, name2, ... nameN
4080      #      #
4081      my $suffix = "FROM " . join(', ', @fromList);      my $suffix = "FROM " . join(', ', @fromList);
4082        # Now for the WHERE. First, we need a place for the filter string.
4083        my $filterString = "";
4084        # We will also keep a list of conditions to add to the WHERE clause in order to link
4085        # entities and relationships as well as primary relations to secondary ones.
4086        my @joinWhere = ();
4087      # Check for a filter clause.      # Check for a filter clause.
4088      if ($filterClause) {      if ($filterClause) {
4089          # 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,
4090          # We create a copy of the filter string we can work with.          # We create a copy of the filter string we can work with.
4091          my $filterString = $filterClause;          $filterString = $filterClause;
4092          # Next, we sort the object names by length. This helps protect us from finding          # Next, we sort the object names by length. This helps protect us from finding
4093          # object names inside other object names when we're doing our search and replace.          # object names inside other object names when we're doing our search and replace.
4094          my @sortedNames = sort { length($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 = ();  
4095          # 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
4096          # 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
4097          # 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 2485  Line 4159 
4159                  }                  }
4160              }              }
4161          }          }
4162        }
4163          # 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
4164          # 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
4165          # 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
4166          # list before running through it.      # list before running through it, because we shift off the first object before
4167        # processing the rest.
4168          my @mappedObjectList = @mappedNameList;          my @mappedObjectList = @mappedNameList;
4169          my $lastMappedObject = shift @mappedObjectList;          my $lastMappedObject = shift @mappedObjectList;
4170          # Get the join table.          # Get the join table.
# Line 2517  Line 4193 
4193          # 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.
4194          # We'll put the ORDER BY / LIMIT clauses in the following variable.          # We'll put the ORDER BY / LIMIT clauses in the following variable.
4195          my $orderClause = "";          my $orderClause = "";
4196        # This is only necessary if we have a filter string in which the ORDER BY
4197        # and LIMIT clauses can live.
4198        if ($filterString) {
4199          # 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
4200          # operator so that we find the first occurrence of either verb.          # operator so that we find the first occurrence of either verb.
4201          if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {          if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {
# Line 2525  Line 4204 
4204              $orderClause = $2 . substr($filterString, $pos);              $orderClause = $2 . substr($filterString, $pos);
4205              $filterString = $1;              $filterString = $1;
4206          }          }
4207          # Add the filter and the join clauses (if any) to the SELECT command.      }
4208        # All the things that are supposed to be in the WHERE clause of the
4209        # SELECT command need to be put into @joinWhere so we can string them
4210        # together. We begin with the match clause. This is important,
4211        # because the match clause's parameter mark must precede any parameter
4212        # marks in the filter string.
4213        if ($matchClause) {
4214            push @joinWhere, $matchClause;
4215        }
4216        # Add the filter string. We put it in parentheses to avoid operator
4217        # precedence problems with the match clause or the joins.
4218          if ($filterString) {          if ($filterString) {
4219              Trace("Filter string is \"$filterString\".") if T(4);              Trace("Filter string is \"$filterString\".") if T(4);
4220              push @joinWhere, "($filterString)";              push @joinWhere, "($filterString)";
4221          }          }
4222        # String it all together into a big filter clause.
4223          if (@joinWhere) {          if (@joinWhere) {
4224              $suffix .= " WHERE " . join(' AND ', @joinWhere);              $suffix .= " WHERE " . join(' AND ', @joinWhere);
4225          }          }
4226          # Add the sort or limit clause (if any) to the SELECT command.      # Add the sort or limit clause (if any).
4227          if ($orderClause) {          if ($orderClause) {
4228              $suffix .= " $orderClause";              $suffix .= " $orderClause";
4229          }          }
     }  
4230      # Return the suffix, the mapped name list, and the mapped name hash.      # Return the suffix, the mapped name list, and the mapped name hash.
4231      return ($suffix, \@mappedNameList, \%mappedNameHash);      return ($suffix, \@mappedNameList, \%mappedNameHash);
4232  }  }
4233    
4234  =head3 GetStatementHandle  =head3 _GetStatementHandle
4235    
4236  This method will prepare and execute an SQL query, returning the statement handle.  This method will prepare and execute an SQL query, returning the statement handle.
4237  The main reason for doing this here is so that everybody who does SQL queries gets  The main reason for doing this here is so that everybody who does SQL queries gets
# Line 2572  Line 4261 
4261  sub _GetStatementHandle {  sub _GetStatementHandle {
4262      # Get the parameters.      # Get the parameters.
4263      my ($self, $command, $params) = @_;      my ($self, $command, $params) = @_;
4264        Confess("Invalid parameter list.") if (! defined($params) || ref($params) ne 'ARRAY');
4265      # Trace the query.      # Trace the query.
4266      Trace("SQL query: $command") if T(SQL => 3);      Trace("SQL query: $command") if T(SQL => 3);
4267      Trace("PARMS: '" . (join "', '", @{$params}) . "'") if (T(SQL => 4) && (@{$params} > 0));      Trace("PARMS: '" . (join "', '", @{$params}) . "'") if (T(SQL => 4) && (@{$params} > 0));
# Line 2580  Line 4270 
4270      # Prepare the command.      # Prepare the command.
4271      my $sth = $dbh->prepare_command($command);      my $sth = $dbh->prepare_command($command);
4272      # Execute it with the parameters bound in.      # Execute it with the parameters bound in.
4273      $sth->execute(@{$params}) || Confess("SELECT error" . $sth->errstr());      $sth->execute(@{$params}) || Confess("SELECT error:  " . $sth->errstr());
4274      # Return the statement handle.      # Return the statement handle.
4275      return $sth;      return $sth;
4276  }  }
4277    
4278  =head3 GetLoadStats  =head3 _GetLoadStats
4279    
4280  Return a blank statistics object for use by the load methods.  Return a blank statistics object for use by the load methods.
4281    
# Line 2597  Line 4287 
4287      return Stats->new();      return Stats->new();
4288  }  }
4289    
4290  =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  
4291    
4292  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.
4293    
4294  This is an instance method.  This is an instance method.
4295    
# Line 2721  Line 4337 
4337      close DTXOUT;      close DTXOUT;
4338  }  }
4339    
4340  =head3 GetStructure  =head3 _GetStructure
4341    
4342  Get the data structure for a specified entity or relationship.  Get the data structure for a specified entity or relationship.
4343    
# Line 2760  Line 4376 
4376      return $retVal;      return $retVal;
4377  }  }
4378    
4379  =head3 GetRelationTable  
4380    
4381    =head3 _GetRelationTable
4382    
4383  Get the list of relations for a specified entity or relationship.  Get the list of relations for a specified entity or relationship.
4384    
# Line 2789  Line 4407 
4407      return $objectData->{Relations};      return $objectData->{Relations};
4408  }  }
4409    
4410  =head3 ValidateFieldNames  =head3 _ValidateFieldNames
4411    
4412  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
4413  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 2816  Line 4434 
4434          for my $object (values %{$metadata->{$section}}) {          for my $object (values %{$metadata->{$section}}) {
4435              # Loop through the object's fields.              # Loop through the object's fields.
4436              for my $fieldName (keys %{$object->{Fields}}) {              for my $fieldName (keys %{$object->{Fields}}) {
4437                  # Now we make some initial validations.                  # If this field name is invalid, set the return value to zero
4438                  if ($fieldName =~ /--/) {                  # so we know we encountered an error.
4439                      # Here we have a doubled minus sign.                  if (! ValidateFieldName($fieldName)) {
                     print STDERR "Field name $fieldName has a doubled hyphen.\n";  
4440                      $retVal = 0;                      $retVal = 0;
                 } elsif ($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";  
                         $retVal = 0;  
                     }  
4441                  }                  }
4442              }              }
4443          }          }
# Line 2844  Line 4448 
4448      }      }
4449  }  }
4450    
4451  =head3 LoadRelation  =head3 _LoadRelation
4452    
4453  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
4454  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 2904  Line 4508 
4508      return $retVal;      return $retVal;
4509  }  }
4510    
4511  =head3 LoadMetaData  
4512    =head3 _LoadMetaData
4513    
4514        my $metadata = ERDB::_LoadMetaData($filename);
4515    
4516  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.
4517  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 2929  Line 4536 
4536  sub _LoadMetaData {  sub _LoadMetaData {
4537      # Get the parameters.      # Get the parameters.
4538      my ($filename) = @_;      my ($filename) = @_;
4539      Trace("Reading Sprout DBD from $filename.") if T(2);      Trace("Reading DBD from $filename.") if T(2);
4540      # 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
4541      # get the exact structure we want.      # get the exact structure we want.
4542      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 $filename.") if T(1);  
4543      # Before we go any farther, we need to validate the field and object names. If an error is found,      # Before we go any farther, we need to validate the field and object names. If an error is found,
4544      # the method below will fail.      # the method below will fail.
4545      _ValidateFieldNames($metadata);      _ValidateFieldNames($metadata);
# Line 3068  Line 4662 
4662              if ($found == 0) {              if ($found == 0) {
4663                  push @{$indexList}, { IndexFields => [ {name => 'id', order => 'ascending'} ] };                  push @{$indexList}, { IndexFields => [ {name => 'id', order => 'ascending'} ] };
4664              }              }
4665              # Now we need to convert the relation's index list to an index table. We begin by creating              # Attach all the indexes to the relation.
4666              # an empty table in the relation structure.              _ProcessIndexes($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++;  
             }  
4667          }          }
4668          # Finally, we add the relation structure to the entity.          # Finally, we add the relation structure to the entity.
4669          $entityStructure->{Relations} = $relationTable;          $entityStructure->{Relations} = $relationTable;
# Line 3092  Line 4677 
4677          _FixupFields($relationshipStructure, $relationshipName, 2, 3);          _FixupFields($relationshipStructure, $relationshipName, 2, 3);
4678          # Format a description for the FROM field.          # Format a description for the FROM field.
4679          my $fromEntity = $relationshipStructure->{from};          my $fromEntity = $relationshipStructure->{from};
4680          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].";
4681          # Get the FROM entity's key type.          # Get the FROM entity's key type.
4682          my $fromType = $entityList->{$fromEntity}->{keyType};          my $fromType = $entityList->{$fromEntity}->{keyType};
4683          # Add the FROM field.          # Add the FROM field.
# Line 3102  Line 4687 
4687                                                      PrettySort => 1});                                                      PrettySort => 1});
4688          # Format a description for the TO field.          # Format a description for the TO field.
4689          my $toEntity = $relationshipStructure->{to};          my $toEntity = $relationshipStructure->{to};
4690          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].";
4691          # Get the TO entity's key type.          # Get the TO entity's key type.
4692          my $toType = $entityList->{$toEntity}->{keyType};          my $toType = $entityList->{$toEntity}->{keyType};
4693          # Add the TO field.          # Add the TO field.
# Line 3114  Line 4699 
4699          my $thisRelation = { Fields => _ReOrderRelationTable($relationshipStructure->{Fields}),          my $thisRelation = { Fields => _ReOrderRelationTable($relationshipStructure->{Fields}),
4700                               Indexes => { } };                               Indexes => { } };
4701          $relationshipStructure->{Relations} = { $relationshipName => $thisRelation };          $relationshipStructure->{Relations} = { $relationshipName => $thisRelation };
4702    
4703            # Add the alternate indexes (if any). This MUST be done before the FROM and
4704            # TO indexes, because it erases the relation's index list.
4705            if (exists $relationshipStructure->{Indexes}) {
4706                _ProcessIndexes($relationshipStructure->{Indexes}, $thisRelation);
4707            }
4708            # Add the relation to the master table.
4709          # Create the FROM and TO indexes.          # Create the FROM and TO indexes.
4710          _CreateRelationshipIndex("From", $relationshipName, $relationshipStructure);          _CreateRelationshipIndex("From", $relationshipName, $relationshipStructure);
4711          _CreateRelationshipIndex("To", $relationshipName, $relationshipStructure);          _CreateRelationshipIndex("To", $relationshipName, $relationshipStructure);
         # Add the relation to the master table.  
4712          $masterRelationTable{$relationshipName} = $thisRelation;          $masterRelationTable{$relationshipName} = $thisRelation;
4713      }      }
4714      # Now store the master relation table in the metadata structure.      # Now store the master relation table in the metadata structure.
# Line 3204  Line 4795 
4795                  for my $otherName (@bothList) {                  for my $otherName (@bothList) {
4796                      Trace("Setting up relationship joins to recursive relationship $otherName with $relationshipName.") if T(metadata => 4);                      Trace("Setting up relationship joins to recursive relationship $otherName with $relationshipName.") if T(metadata => 4);
4797                      # Join from the left.                      # Join from the left.
4798                      $joinTable{"$relationshipName/$otherName"} =                      $joinTable{"$relationshipName/$otherName"} =
4799                          "$linkField = $otherName.from_link";                          "$linkField = $otherName.from_link";
4800                      # Join from the right.                      # Join from the right.
4801                      $joinTable{"$otherName/$relationshipName"} =                      $joinTable{"$otherName/$relationshipName"} =
4802                          "$otherName.to_link = $linkField";                          "$otherName.to_link = $linkField";
                 }  
             }  
         }  
         # Create entity joins for the recursive relationships. Unlike the non-recursive  
         # joins, the direction makes a difference with the recursive joins. This can give  
         # rise to situations where we can't create the path we want; however, it is always  
         # possible to get the same effect using multiple queries.  
         for my $relationshipName (@bothList) {  
             Trace("Setting up entity joins to recursive relationship $relationshipName with $entityName.") if T(metadata => 4);  
             # Join to the entity from each direction.  
             $joinTable{"$entityName/$relationshipName"} =  
                 "$entityName.id = $relationshipName.from_link";  
             $joinTable{"$relationshipName/$entityName"} =  
                 "$relationshipName.to_link = $entityName.id";  
         }  
     }  
     # Add the join table to the structure.  
     $metadata->{Joins} = \%joinTable;  
     # Return the slurped and fixed-up structure.  
     return $metadata;  
 }  
   
 =head3 SortNeeded  
   
 C<< my $flag = $erdb->SortNeeded($relationName); >>  
   
 Return TRUE if the specified relation should be sorted during loading to remove duplicate keys,  
 else FALSE.  
   
 =over 4  
   
 =item relationName  
   
 Name of the relation to be examined.  
   
 =item RETURN  
   
 Returns TRUE if the relation needs a sort, else FALSE.  
   
 =back  
   
 =cut  
 #: Return Type $;  
 sub SortNeeded {  
     # Get the parameters.  
     my ($self, $relationName) = @_;  
     # Declare the return variable.  
     my $retVal = 0;  
     # Find out if the relation is a primary entity relation.  
     my $entityTable = $self->{_metaData}->{Entities};  
     if (exists $entityTable->{$relationName}) {  
         my $keyType = $entityTable->{$relationName}->{keyType};  
         Trace("Relation $relationName found in entity table with key type $keyType.") if T(3);  
         # If the key is not a hash string, we must do the sort.  
         if ($keyType ne 'hash-string') {  
             $retVal = 1;  
4803          }          }
4804      }      }
4805      # Return the result.          }
4806      return $retVal;          # Create entity joins for the recursive relationships. Unlike the non-recursive
4807            # joins, the direction makes a difference with the recursive joins. This can give
4808            # rise to situations where we can't create the path we want; however, it is always
4809            # possible to get the same effect using multiple queries.
4810            for my $relationshipName (@bothList) {
4811                Trace("Setting up entity joins to recursive relationship $relationshipName with $entityName.") if T(metadata => 4);
4812                # Join to the entity from each direction.
4813                $joinTable{"$entityName/$relationshipName"} =
4814                    "$entityName.id = $relationshipName.from_link";
4815                $joinTable{"$relationshipName/$entityName"} =
4816                    "$relationshipName.to_link = $entityName.id";
4817            }
4818        }
4819        # Add the join table to the structure.
4820        $metadata->{Joins} = \%joinTable;
4821        # Return the slurped and fixed-up structure.
4822        return $metadata;
4823  }  }
4824    
4825  =head3 CreateRelationshipIndex  =head3 _CreateRelationshipIndex
4826    
4827  Create an index for a relationship's relation.  Create an index for a relationship's relation.
4828    
# Line 3313  Line 4864 
4864          $newIndex->{Unique} = 'true';          $newIndex->{Unique} = 'true';
4865      }      }
4866      # Add the index to the relation.      # Add the index to the relation.
4867      _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);      _AddIndex("idx$indexKey", $relationStructure, $newIndex);
4868    }
4869    
4870    =head3 _ProcessIndexes
4871    
4872        ERDB::_ProcessIndexes($indexList, $relation);
4873    
4874    Build the data structures for the specified indexes in the specified relation.
4875    
4876    =over 4
4877    
4878    =item indexList
4879    
4880    Reference to a list of indexes. Each index is a hash reference containing an optional
4881    C<Notes> value that describes the index and an C<IndexFields> value that is a reference
4882    to a list of index field structures. An index field structure, in turn, is a reference
4883    to a hash that contains a C<name> attribute for the field name and an C<order>
4884    attribute that specifies either C<ascending> or C<descending>. In this sense the
4885    index list encapsulates the XML C<Indexes> structure in the database definition.
4886    
4887    =item relation
4888    
4889    The structure that describes the current relation. The new index descriptors will
4890    be stored in the structure's C<Indexes> member. Any previous data in the structure
4891    will be lost.
4892    
4893    =back
4894    
4895    =cut
4896    
4897    sub _ProcessIndexes {
4898        # Get the parameters.
4899        my ($indexList, $relation) = @_;
4900        # Now we need to convert the relation's index list to an index table. We begin by creating
4901        # an empty table in the relation structure.
4902        $relation->{Indexes} = { };
4903        # Loop through the indexes.
4904        my $count = 0;
4905        for my $index (@{$indexList}) {
4906            # Add this index to the index table.
4907            _AddIndex("idx$count", $relation, $index);
4908            # Increment the counter so that the next index has a different name.
4909            $count++;
4910        }
4911  }  }
4912    
4913  =head3 AddIndex  =head3 _AddIndex
4914    
4915  Add an index to a relation structure.  Add an index to a relation structure.
4916    
# Line 3362  Line 4956 
4956      $relationStructure->{Indexes}->{$indexName} = $newIndex;      $relationStructure->{Indexes}->{$indexName} = $newIndex;
4957  }  }
4958    
4959  =head3 FixupFields  =head3 _FixupFields
4960    
4961  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
4962  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 3400  Line 4994 
4994          # Here it doesn't, so we create a new one.          # Here it doesn't, so we create a new one.
4995          $structure->{Fields} = { };          $structure->{Fields} = { };
4996      } else {      } else {
4997          # 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
4998            # create a list for stashing them.
4999            my @textFields = ();
5000            # Loop through the fields.
5001          my $fieldStructures = $structure->{Fields};          my $fieldStructures = $structure->{Fields};
5002          for my $fieldName (keys %{$fieldStructures}) {          for my $fieldName (keys %{$fieldStructures}) {
5003              Trace("Processing field $fieldName of $defaultRelationName.") if T(4);              Trace("Processing field $fieldName of $defaultRelationName.") if T(4);
# Line 3409  Line 5006 
5006              my $type = $fieldData->{type};              my $type = $fieldData->{type};
5007              # Plug in a relation name if it is needed.              # Plug in a relation name if it is needed.
5008              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });
5009              # Plug in a data generator if we need one.              # Check for searchability.
5010              if (!exists $fieldData->{DataGen}) {              if ($fieldData->{searchable}) {
5011                  # The data generator will use the default for the field's type.                  # Only allow this for a primary relation.
5012                  $fieldData->{DataGen} = { content => $TypeTable{$type}->{dataGen} };                  if ($fieldData->{relation} ne $defaultRelationName) {
5013                        Confess("Field $fieldName of $defaultRelationName is in secondary relations and cannot be searchable.");
5014                    } else {
5015                        push @textFields, $fieldName;
5016                    }
5017              }              }
             # Plug in the defaults for the optional data generation parameters.  
             Tracer::MergeOptions($fieldData->{DataGen}, { testCount => 1, pass => 0 });  
5018              # Add the PrettySortValue.              # Add the PrettySortValue.
5019              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);
5020          }          }
5021            # If there are searchable fields, remember the fact.
5022            if (@textFields) {
5023                $structure->{searchFields} = \@textFields;
5024            }
5025      }      }
5026  }  }
5027    
5028  =head3 FixName  =head3 _FixName
5029    
5030  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.
5031    
# Line 3451  Line 5054 
5054      return $fieldName;      return $fieldName;
5055  }  }
5056    
5057  =head3 FixNames  =head3 _FixNames
5058    
5059  Fix all the field names in a list.  Fix all the field names in a list.
5060    
# Line 3482  Line 5085 
5085      return @result;      return @result;
5086  }  }
5087    
5088  =head3 AddField  =head3 _AddField
5089    
5090  Add a field to a field list.  Add a field to a field list.
5091    
# Line 3517  Line 5120 
5120      $fieldList->{$fieldName} = $fieldStructure;      $fieldList->{$fieldName} = $fieldStructure;
5121  }  }
5122    
5123  =head3 ReOrderRelationTable  =head3 _ReOrderRelationTable
5124    
5125  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
5126  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 3578  Line 5181 
5181    
5182  }  }
5183    
5184  =head3 IsPrimary  =head3 _IsPrimary
5185    
5186  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
5187  if it has the same name as an entity or relationship.  if it has the same name as an entity or relationship.
# Line 3614  Line 5217 
5217      return $retVal;      return $retVal;
5218  }  }
5219    
5220  =head3 FindRelation  =head3 _FindRelation
5221    
5222  Return the descriptor for the specified relation.  Return the descriptor for the specified relation.
5223    
# Line 3645  Line 5248 
5248    
5249  =head2 HTML Documentation Utility Methods  =head2 HTML Documentation Utility Methods
5250    
5251  =head3 ComputeRelationshipSentence  =head3 _ComputeRelationshipSentence
5252    
5253  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
5254  two related entities and an arity indicator.  two related entities and an arity indicator.
# Line 3683  Line 5286 
5286      return $result;      return $result;
5287  }  }
5288    
5289  =head3 ComputeRelationshipHeading  =head3 _ComputeRelationshipHeading
5290    
5291  The relationship heading is the L<relationship sentence|/ComputeRelationshipSentence> with the entity  The relationship heading is the L<relationship sentence|/ComputeRelationshipSentence> with the entity
5292  names hyperlinked to the appropriate entity sections of the document.  names hyperlinked to the appropriate entity sections of the document.
# Line 3720  Line 5323 
5323      return $result;      return $result;
5324  }  }
5325    
5326  =head3 ShowRelationTable  =head3 _ShowRelationTable
5327    
5328  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
5329  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 3770  Line 5373 
5373          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";
5374          # Add any note text.          # Add any note text.
5375          if (my $note = $indexData->{Notes}) {          if (my $note = $indexData->{Notes}) {
5376              $htmlString .= "<li>" . _HTMLNote($note->{content}) . "</li>\n";              $htmlString .= "<li>" . HTMLNote($note->{content}) . "</li>\n";
5377          }          }
5378          # Add the fiield list.          # Add the fiield list.
5379          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";
# Line 3781  Line 5384 
5384      $htmlString .= "</ul>\n";      $htmlString .= "</ul>\n";
5385  }  }
5386    
5387  =head3 OpenFieldTable  =head3 _OpenFieldTable
5388    
5389  This method creates the header string for the field table generated by L</ShowMetaData>.  This method creates the header string for the field table generated by L</ShowMetaData>.
5390    
# Line 3806  Line 5409 
5409      return _OpenTable($tablename, 'Field', 'Type', 'Description');      return _OpenTable($tablename, 'Field', 'Type', 'Description');
5410  }  }
5411    
5412  =head3 OpenTable  =head3 _OpenTable
5413    
5414  This method creates the header string for an HTML table.  This method creates the header string for an HTML table.
5415    
# Line 3836  Line 5439 
5439      # Compute the number of columns.      # Compute the number of columns.
5440      my $colCount = @colNames;      my $colCount = @colNames;
5441      # Generate the title row.      # Generate the title row.
5442      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";
5443      # Loop through the columns, adding the column header rows.      # Loop through the columns, adding the column header rows.
5444      $htmlString .= "<tr>";      $htmlString .= "<tr>";
5445      for my $colName (@colNames) {      for my $colName (@colNames) {
# Line 3846  Line 5449 
5449      return $htmlString;      return $htmlString;
5450  }  }
5451    
5452  =head3 CloseTable  =head3 _CloseTable
5453    
5454  This method returns the HTML for closing a table.  This method returns the HTML for closing a table.
5455    
# Line 3855  Line 5458 
5458  =cut  =cut
5459    
5460  sub _CloseTable {  sub _CloseTable {
5461      return "</table></p>\n";      return "</table>\n";
5462  }  }
5463    
5464  =head3 ShowField  =head3 _ShowField
5465    
5466  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.
5467    
# Line 3885  Line 5488 
5488      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>";
5489      # If we have content, add it as a third column.      # If we have content, add it as a third column.
5490      if (exists $fieldData->{Notes}) {      if (exists $fieldData->{Notes}) {
5491          $htmlString .= "<td>" . _HTMLNote($fieldData->{Notes}->{content}) . "</td>";          $htmlString .= "<td>" . HTMLNote($fieldData->{Notes}->{content}) . "</td>";
5492      }      }
5493      # Close off the row.      # Close off the row.
5494      $htmlString .= "</tr>\n";      $htmlString .= "</tr>\n";
# Line 3893  Line 5496 
5496      return $htmlString;      return $htmlString;
5497  }  }
5498    
 =head3 HTMLNote  
   
 Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes  
 supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.  
 Except for C<[p]>, all the codes are closed by slash-codes. So, for  
 example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.  
   
 This is a static method.  
   
 =over 4  
   
 =item dataString  
   
 String to convert to HTML.  
   
 =item RETURN  
   
 An HTML string derived from the input string.  
   
 =back  
   
 =cut  
   
 sub _HTMLNote {  
     # Get the parameter.  
     my ($dataString) = @_;  
     # Substitute the codes.  
     $dataString =~ s!\[(/?[bi])\]!<$1>!g;  
     $dataString =~ s!\[p\]!</p><p>!g;  
     # Return the result.  
     return $dataString;  
 }  
   
 =head2 Data Generation Utilities  
   
 =head3 IntGen  
   
 C<< my $integer = IntGen($min, $max); >>  
   
 Returns a random number between the specified minimum and maximum (inclusive).  
   
 =over 4  
   
 =item min  
   
 Minimum permissible return value.  
   
 =item max  
   
 Maximum permissible return value.  
   
 =item RETURN  
   
 Returns a value no lower than the minimum and no greater than the maximum.  
   
 =back  
   
 =cut  
   
 sub IntGen {  
     # Get the parameters.  
     my ($min, $max) = @_;  
     # Determine the range of possible values. Note we put some space well above the  
     # maximum value to give it a fighting chance of apppearing in the list.  
     my $span = $max + 0.99 - $min;  
     # Create an integer in the range.  
     my $retVal = $min + int(rand($span));  
     # Return the result.  
     return $retVal;  
 }  
   
 =head3 RandChar  
   
 C<< my $char = RandChar($sourceString); >>  
   
 Select a random character from a string.  
   
 =over 4  
   
 =item sourceString  
   
 String from which the random character should be selected.  
   
 =item RETURN  
   
 Returns a single character from the incoming string.  
   
 =back  
   
 =cut  
   
 sub RandChar {  
     # Get the parameter.  
     my ($sourceString) = @_;  
     # Select a random character.  
     my $retVal = IntGen(0, (length $sourceString) - 1);  
     # Return it.  
     return substr($sourceString, $retVal, 1);  
 }  
   
 =head3 RandChars  
   
 C<< my $string = RandChars($sourceString, $length); >>  
   
 Create a string from characters taken from a source string.  
   
 =over 4  
   
 =item sourceString  
   
 String from which the random characters should be selected.  
   
 =item length  
   
 Number of characters to put in the output string.  
   
 =item RETURN  
   
 Returns a string of the specified length consisting of characters taken from the  
 source string.  
   
 =back  
   
 =cut  
   
 sub RandChars {  
     # Get the parameters.  
     my ($sourceString, $length) = @_;  
     # Call RandChar repeatedly to generate the string.  
     my $retVal = "";  
     for (my $i = 0; $i < $length; $i++) {  
         $retVal .= RandChar($sourceString);  
     }  
     # Return the result.  
     return $retVal;  
 }  
   
 =head3 RandParam  
   
 C<< my $value = RandParam($parm1, $parm2, ... $parmN); >>  
   
 Return a randomly-selected value from the parameter list.  
   
 =over 4  
   
 =item parm1, parm2, ... parmN  
   
 List of values of which one will be selected.  
   
 =item RETURN  
   
 Returns a randomly-chosen value from the specified list.  
   
 =back  
   
 =cut  
   
 sub RandParam {  
     # Get the parameter.  
     my @parms = @_;  
     # Choose a random parameter from the list.  
     my $chosenIndex = IntGen(0, $#parms);  
     return $parms[$chosenIndex];  
 }  
   
 =head3 StringGen  
   
 C<< my $string = StringGen($pattern1, $pattern2, ... $patternN); >>  
   
 Returns a random string derived from a randomly-chosen format pattern. The pattern  
 can either be a number (indicating the number of characters desired, or the letter  
 C<P> followed by a picture. The picture should contain C<A> when a letter is desired,  
 C<9> when a digit is desired, C<V> when a vowel is desired, C<K> when a consonant is  
 desired, and C<X> when a letter or a digit is desired. Any other character will be  
 translated as a literal.  
   
 =over 4  
   
 =item pattern1, pattern2, ... patternN  
   
 List of patterns to be used to generate string values.  
   
 =item RETURN  
   
 A single string generated from a pattern.  
   
 =back  
   
 =cut  
   
 sub StringGen {  
     # Get the parameters.  
     my @patterns = @_;  
     # Choose the appropriate pattern.  
     my $chosenPattern = RandParam(@patterns);  
     # Declare the return variable.  
     my $retVal = "";  
     # Determine whether this is a count or a picture pattern.  
     if ($chosenPattern =~ m/^\d+/) {  
         # Here we have a count. Get the string of source characters.  
         my $letterString = $PictureTable{'X'};  
         my $stringLen = length $letterString;  
         # Save the number of characters we have to generate.  
         my $charsLeft = $chosenPattern;  
         # Loop until the return variable is full.  
         while ($charsLeft > 0) {  
             # Generate a random position in the soruce string.  
             my $stringIndex = IntGen(0, $stringLen - 1);  
             # Compute the number of characters to pull out of the source string.  
             my $chunkSize = $stringLen - $stringIndex;  
             if ($chunkSize > $charsLeft) { $chunkSize = $charsLeft; }  
             # Stuff this chunk into the return value.  
             $retVal .= substr($letterString, $stringIndex, $chunkSize);  
             # Record the data moved.  
             $charsLeft -= $chunkSize;  
         }  
     } elsif ($chosenPattern =~ m/^P/) {  
         # Here we have a picture string. We will move through the picture one  
         # character at a time generating data.  
         for (my $i = 1; $i < length $chosenPattern; $i++) {  
             # Get this picture character.  
             my $chr = substr($chosenPattern, $i, 1);  
             # Check to see if the picture char is one we recognize.  
             if (exists $PictureTable{$chr}) {  
                 # Choose a random character from the available values for this  
                 # picture character.  
                 $retVal .= RandChar($PictureTable{$chr});  
             } else {  
                 # Copy in the picture character as a literal.  
                 $retVal .= $chr;  
             }  
         }  
     } else {  
         # Here we have neither a picture string or a letter count, so we treat  
         # the string as a literal.  
         $retVal = $chosenPattern;  
     }  
     # Return the string formed.  
     return $retVal;  
 }  
   
 =head3 DateGen  
   
 C<< my $date = DateGen($startDayOffset, $endDayOffset, $minutes); >>  
   
 Return a numeric timestamp within the specified range of days with the specified minute  
 value. The range of days is specified relevant to the current day. Thus, the call  
   
 C<< my $date = DateGen(-1, 5, 720); >>  
   
 will return a timestamp at noon (72 minutes past midnight) sometime during the week that  
 began on the preceding day. If you want a random minute of the day, simply combine with  
 a call to L</IntGen>, as follows.  
   
 C<< my $date = DateGen(-1, 5, IntGen(0, 1439)); >>  
   
 =over 4  
   
 =item startDayOffset  
   
 The earliest day that can be returned, relative to the current day.  
   
 =item endDayOffset  
   
 The latest day that can be returned, related to the current day.  
   
 =item minutes  
   
 Number of minutes into the selected day that should be used.  
   
 =back  
   
 =cut  
   
 sub DateGen {  
     # Get the parameters.  
     my ($startDayOffset, $endDayOffset, $minutes) = @_;  
     # Get midnight of the current day.  
     my $now = time();  
     my ($sec, $min, $hour) = localtime($now);  
     my $today = $now - (($hour * 60 + $min) * 60 + $sec);  
     # Compute the day we want.  
     my $newDay = IntGen($startDayOffset, $endDayOffset) * 86400 + $today;  
     # Add the minutes.  
     my $retVal = $newDay + $minutes * 60;  
     # Return the result.  
     return $retVal;  
 }  
   
 =head3 FloatGen  
   
 C<< my $number = FloatGen($min, $max); >>  
   
 Return a random floating-point number greater than or equal to the specified minimum and  
 less than the specified maximum.  
   
 =over 4  
   
 =item min  
   
 Minimum permissible value for the number returned.  
   
 =item max  
   
 Maximum permissible value for the number returned.  
   
 =item RETURN  
   
 Returns a floating-point number anywhere in the specified range.  
   
 =back  
   
 =cut  
   
 sub FloatGen {  
     # Get the parameters.  
     my ($min, $max) = @_;  
     # Generate the result.  
     my $retVal = rand($max - $min) + $min;  
     return $retVal;  
 }  
   
 =head3 ListGen  
   
 C<< my @list = ListGen($pattern, $count); >>  
   
 Return a list containing a fixed number of randomly-generated strings.  
   
 =over 4  
   
 =item pattern  
   
 A pattern (in the form expected by L</StringGen>) that should be used to generate the  
 strings in the list.  
   
 =item count  
   
 The number of list entries to generate.  
   
 =item RETURN  
   
 Returns a list consisting of the specified number of strings.  
   
 =back  
   
 =cut  
   
 sub ListGen {  
     # Get the parameters.  
     my ($pattern, $count) = @_;  
     # Generate the list.  
     my @retVal = ();  
     for (my $i = 0; $i < $count; $i++) {  
         push @retVal, StringGen($pattern);  
     }  
     # Return it.  
     return @retVal;  
 }  
   
5499  1;  1;

Legend:
Removed from v.1.55  
changed lines
  Added in v.1.94

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3