[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 1.90, Fri Apr 27 22:19:49 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                  );                  );
376    
377  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 344  Line 380 
380                     'MM' => 'many-to-many'                     'MM' => 'many-to-many'
381                   );                   );
382    
383  # Table for interpreting string patterns.  # Options for XML input and output.
384    
385    my %XmlOptions = (GroupTags =>  { Relationships => 'Relationship',
386                                      Entities => 'Entity',
387                                      Fields => 'Field',
388                                      Indexes => 'Index',
389                                      IndexFields => 'IndexField'
390                                    },
391                      KeyAttr =>    { Relationship => 'name',
392                                      Entity => 'name',
393                                      Field => 'name'
394                                    },
395                      SuppressEmpty => 1,
396                     );
397    
398  my %PictureTable = ( 'A' => "abcdefghijklmnopqrstuvwxyz",  my %XmlInOpts  = (
399                       '9' => "0123456789",                    ForceArray => ['Field', 'Index', 'IndexField', 'Relationship', 'Entity'],
400                       'X' => "abcdefghijklmnopqrstuvwxyz0123456789",                    ForceContent => 1,
401                       'V' => "aeiou",                    NormalizeSpace => 2,
402                       'K' => "bcdfghjklmnoprstvwxyz"                   );
403    my %XmlOutOpts = (
404                      RootName => 'Database',
405                      XMLDecl => 1,
406                     );                     );
407    
408    
409  =head2 Public Methods  =head2 Public Methods
410    
411  =head3 new  =head3 new
# Line 493  Line 546 
546          my $entityData = $entityList->{$key};          my $entityData = $entityList->{$key};
547          # If there's descriptive text, display it.          # If there's descriptive text, display it.
548          if (my $notes = $entityData->{Notes}) {          if (my $notes = $entityData->{Notes}) {
549              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
550          }          }
551          # 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.
552            my $relCount = keys %{$relationshipList};
553            if ($relCount > 0) {
554                # First, we set up the relationship subsection.
555          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
556          # Loop through the relationships.          # Loop through the relationships.
557          for my $relationship (sort keys %{$relationshipList}) {          for my $relationship (sort keys %{$relationshipList}) {
# Line 511  Line 567 
567          }          }
568          # Close off the relationship list.          # Close off the relationship list.
569          $retVal .= "</ul>\n";          $retVal .= "</ul>\n";
570            }
571          # Get the entity's relations.          # Get the entity's relations.
572          my $relationList = $entityData->{Relations};          my $relationList = $entityData->{Relations};
573          # Create a header for the relation subsection.          # Create a header for the relation subsection.
# Line 550  Line 607 
607          $retVal .= "</p>\n";          $retVal .= "</p>\n";
608          # If there are notes on this relationship, display them.          # If there are notes on this relationship, display them.
609          if (my $notes = $relationshipStructure->{Notes}) {          if (my $notes = $relationshipStructure->{Notes}) {
610              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
611          }          }
612          # Generate the relationship's relation table.          # Generate the relationship's relation table.
613          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
# Line 597  Line 654 
654      return Data::Dumper::Dumper($self->{_metaData});      return Data::Dumper::Dumper($self->{_metaData});
655  }  }
656    
657    =head3 CreatePPO
658    
659    C<< ERDB::CreatePPO($erdbXMLFile, $ppoXMLFile); >>
660    
661    Create a PPO XML file from an ERDB data definition XML file. At the
662    current time, the PPO XML file can be used to create a database with
663    similar functionality. Eventually, the PPO will be able to use the
664    created XML to access the live ERDB database.
665    
666    =over 4
667    
668    =item erdbXMLFile
669    
670    Name of the XML data definition file for the ERDB database. This
671    file must exist.
672    
673    =item ppoXMLFile
674    
675    Output file for the PPO XML definition. If this file exists, it
676    will be overwritten.
677    
678    =back
679    
680    =cut
681    
682    sub CreatePPO {
683        # Get the parameters.
684        my ($erdbXMLFile, $ppoXMLFile) = @_;
685        # First, we want to slurp in the ERDB XML file in its raw form.
686        my $xml = ReadMetaXML($erdbXMLFile);
687        # Create a variable to hold all of the objects in the PPO project.
688        my @objects = ();
689        # Get the relationship hash.
690        my $relationships = $xml->{Relationships};
691        # Loop through the entities.
692        my $entities = $xml->{Entities};
693        for my $entityName (keys %{$entities}) {
694            # Get the entity's data structures.
695            my $entityObject = $entities->{$entityName};
696            # We put the object's fields in here, according to their type.
697            my (@object_refs, @scalars, @indexes, @arrays);
698            # Create the ID field for the entity. We get the key type from the
699            # entity object and compute the corresponding SQL type.
700            my $type = $TypeTable{$entityObject->{keyType}}->{sqlType};
701            push @scalars, { label => 'id', type => $type };
702            # Loop through the entity fields.
703            for my $fieldName ( keys %{$entityObject->{Fields}} ) {
704                # Get the field object.
705                my $fieldObject = $entityObject->{Fields}->{$fieldName};
706                # Convert it to a scalar tag.
707                my $scalar = _CreatePPOField($fieldName, $fieldObject);
708                # If we have a relation, this field is stored in an array.
709                # otherwise, it is a scalar. The array tag has scalars
710                # stored as an XML array. In ERDB, there is only ever one,
711                # but PPO can have more.
712                my $relation = $fieldObject->{relation};
713                if ($relation) {
714                    push @arrays, { scalar => [$scalar] };
715                } else {
716                    push @scalars, $scalar;
717                }
718            }
719            # Loop through the relationships. If this entity is the to-entity
720            # on a relationship of 1M arity, then it is implemented as a PPO
721            # object reference.
722            for my $relationshipName (keys %{$relationships}) {
723                # Get the relationship data.
724                my $relationshipData = $relationships->{$relationshipName};
725                # If we have a from for this entity and an arity of 1M, we
726                # have an object reference.
727                if ($relationshipData->{to} eq $entityName &&
728                    $relationshipData->{arity} eq '1M') {
729                    # Build the object reference tag.
730                    push @object_refs, { label => $relationshipName,
731                                         type => $relationshipData->{from} };
732                }
733            }
734            # Create the indexes.
735            my $indexList = $entityObject->{Indexes};
736            push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
737            # Build the object XML tree.
738            my $object = { label => $entityName,
739                           object_ref => \@object_refs,
740                           scalar => \@scalars,
741                           index => \@indexes,
742                           array => \@arrays
743                          };
744            # Push the object onto the objects list.
745            push @objects, $object;
746        }
747        # Loop through the relationships, searching for MMs. The 1Ms were
748        # already handled by the entity search above.
749        for my $relationshipName (keys %{$relationships}) {
750            # Get this relationship's object.
751            my $relationshipObject = $relationships->{$relationshipName};
752            # Only proceed if it's many-to-many.
753            if ($relationshipObject->{arity} eq 'MM') {
754                # Create the tag lists for the relationship object.
755                my (@object_refs, @scalars, @indexes);
756                # The relationship will be created as an object with object
757                # references for its links to the participating entities.
758                my %links = ( from_link => $relationshipObject->{from},
759                              to_link => $relationshipObject->{to} );
760                for my $link (keys %links) {
761                    # Create an object_ref tag for this piece of the
762                    # relationship (from or to).
763                    my $object_ref = { label => $link,
764                                       type => $links{$link} };
765                    push @object_refs, $object_ref;
766                }
767                # Loop through the intersection data fields, creating scalar tags.
768                # There are no fancy array tags in a relationship.
769                for my $fieldName (keys %{$relationshipObject->{Fields}}) {
770                    my $fieldObject = $relationshipObject->{Fields}->{$fieldName};
771                    push @scalars, _CreatePPOField($fieldName, $fieldObject);
772                }
773                # Finally, the indexes: currently we cannot support the to-index and
774                # from-index in PPO, so we just process the alternate indexes.
775                my $indexList = $relationshipObject->{Indexes};
776                push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
777                # Wrap up all the stuff about this relationship.
778                my $object = { label => $relationshipName,
779                               scalar => \@scalars,
780                               object_ref => \@object_refs,
781                               index => \@indexes
782                             };
783                # Push it into the object list.
784                push @objects, $object;
785            }
786        }
787        # Compute a title.
788        my $title;
789        if ($erdbXMLFile =~ /(\/|^)([^\/]+)DBD\.xml/) {
790            # Here we have a standard file name we can use for a title.
791            $title = $2;
792        } else {
793            # Here the file name is non-standard, so we carve up the
794            # database title.
795            $title = $xml->{Title}->{content};
796            $title =~ s/\s\.,//g;
797        }
798        # Wrap up the XML as a project.
799        my $ppoXML = { project => { label => $title,
800                                    object => \@objects }};
801        # Write out the results.
802        my $ppoString = XML::Simple::XMLout($ppoXML,
803                                            AttrIndent => 1,
804                                            KeepRoot => 1);
805        Tracer::PutFile($ppoXMLFile, [ $ppoString ]);
806    }
807    
808    =head3 FindIndexForEntity
809    
810    C<< my $indexFound = ERDB::FindIndexForEntity($xml, $entityName, $attributeName); >>
811    
812    This method locates the entry in an entity's index list that begins with the
813    specified attribute name. If the entity has no index list, one will be
814    created. This method works on raw XML, not a live ERDB object.
815    
816    =over 4
817    
818    =item xml
819    
820    The raw XML structure defining the database.
821    
822    =item entityName
823    
824    The name of the relevant entity.
825    
826    =item attributeName
827    
828    The name of the attribute relevant to the search.
829    
830    =item RETURN
831    
832    The numerical index in the index list of the index entry for the specified entity and
833    attribute, or C<undef> if no such index exists.
834    
835    =back
836    
837    =cut
838    
839    sub FindIndexForEntity {
840        # Get the parameters.
841        my ($xml, $entityName, $attributeName) = @_;
842        # Declare the return variable.
843        my $retVal;
844        # Get the named entity.
845        my $entityData = $xml->{Entities}->{$entityName};
846        if (! $entityData) {
847            Confess("Entity $entityName not found in DBD structure.");
848        } else {
849            # Insure it has an index list.
850            if (! exists $entityData->{Indexes}) {
851                $entityData->{Indexes} = [];
852            } else {
853                # Search for the desired index.
854                my $indexList = $entityData->{Indexes};
855                my $n = scalar @{$indexList};
856                Trace("Searching $n indexes in index list for $entityName.") if T(2);
857                # We use an indexed FOR here because we're returning an
858                # index number instead of an object. We do THAT so we can
859                # delete the index from the list if needed.
860                for (my $i = 0; $i < $n && !defined($retVal); $i++) {
861                    my $index = $indexList->[$i];
862                    my $fields = $index->{IndexFields};
863                    # Technically this IF should be safe (that is, we are guaranteed
864                    # the existence of a "$fields->[0]"), because when we load the XML
865                    # we have SuppressEmpty specified.
866                    if ($fields->[0]->{name} eq $attributeName) {
867                        $retVal = $i;
868                    }
869                }
870            }
871        }
872        Trace("Index for $attributeName of $entityName found at position $retVal.") if defined($retVal) && T(3);
873        Trace("Index for $attributeName not found in $entityName.") if !defined($retVal) && T(3);
874        # Return the result.
875        return $retVal;
876    }
877    
878  =head3 CreateTables  =head3 CreateTables
879    
880  C<< $erdb->CreateTables(); >>  C<< $erdb->CreateTables(); >>
# Line 616  Line 894 
894      # Loop through the relations.      # Loop through the relations.
895      for my $relationName (@relNames) {      for my $relationName (@relNames) {
896          # Create a table for this relation.          # Create a table for this relation.
897          $self->CreateTable($relationName);          $self->CreateTable($relationName, 1);
898          Trace("Relation $relationName created.") if T(2);          Trace("Relation $relationName created.") if T(2);
899      }      }
900  }  }
# Line 684  Line 962 
962      Trace("Creating table $relationName: $fieldThing") if T(2);      Trace("Creating table $relationName: $fieldThing") if T(2);
963      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);
964      Trace("Relation $relationName created in database.") if T(2);      Trace("Relation $relationName created in database.") if T(2);
965      # If we want to build the indexes, we do it here.      # If we want to build the indexes, we do it here. Note that the full-text search
966        # index will not be built until the table has been loaded.
967      if ($indexFlag) {      if ($indexFlag) {
968          $self->CreateIndex($relationName);          $self->CreateIndex($relationName);
969      }      }
# Line 841  Line 1120 
1120      for my $indexName (keys %{$indexHash}) {      for my $indexName (keys %{$indexHash}) {
1121          my $indexData = $indexHash->{$indexName};          my $indexData = $indexHash->{$indexName};
1122          # Get the index's field list.          # Get the index's field list.
1123          my @fieldList = _FixNames(@{$indexData->{IndexFields}});          my @rawFields = @{$indexData->{IndexFields}};
1124            # Get a hash of the relation's field types.
1125            my %types = map { $_->{name} => $_->{type} } @{$relationData->{Fields}};
1126            # We need to check for text fields so we can append a length limitation for them. To do
1127            # that, we need the relation's field list.
1128            my $relFields = $relationData->{Fields};
1129            for (my $i = 0; $i <= $#rawFields; $i++) {
1130                # Get the field type.
1131                my $field = $rawFields[$i];
1132                my $type = $types{$field};
1133                # Ask if it requires using prefix notation for the index.
1134                my $mod = $TypeTable{$type}->{indexMod};
1135                Trace("Field $field ($i) in $relationName has type $type and indexMod $mod.") if T(3);
1136                if ($mod) {
1137                    # Append the prefix length to the field name,
1138                    $rawFields[$i] .= "($mod)";
1139                }
1140            }
1141            my @fieldList = _FixNames(@rawFields);
1142          my $flds = join(', ', @fieldList);          my $flds = join(', ', @fieldList);
1143          # Get the index's uniqueness flag.          # Get the index's uniqueness flag.
1144          my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
1145          # Create the index.          # Create the index.
1146          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
1147                                      flds => $flds, unique => $unique);                                      flds => $flds, kind => $unique);
1148          if ($rv) {          if ($rv) {
1149              Trace("Index created: $indexName for $relationName ($flds)") if T(1);              Trace("Index created: $indexName for $relationName ($flds)") if T(1);
1150          } else {          } else {
# Line 856  Line 1153 
1153      }      }
1154  }  }
1155    
1156    =head3 GetSecondaryFields
1157    
1158    C<< my %fieldTuples = $erdb->GetSecondaryFields($entityName); >>
1159    
1160    This method will return a list of the name and type of each of the secondary
1161    fields for a specified entity. Secondary fields are stored in two-column tables
1162    in addition to the primary entity table. This enables the field to have no value
1163    or to have multiple values.
1164    
1165    =over 4
1166    
1167    =item entityName
1168    
1169    Name of the entity whose secondary fields are desired.
1170    
1171    =item RETURN
1172    
1173    Returns a hash mapping the field names to their field types.
1174    
1175    =back
1176    
1177    =cut
1178    
1179    sub GetSecondaryFields {
1180        # Get the parameters.
1181        my ($self, $entityName) = @_;
1182        # Declare the return variable.
1183        my %retVal = ();
1184        # Look for the entity.
1185        my $table = $self->GetFieldTable($entityName);
1186        # Loop through the fields, pulling out the secondaries.
1187        for my $field (sort keys %{$table}) {
1188            if ($table->{$field}->{relation} ne $entityName) {
1189                # Here we have a secondary field.
1190                $retVal{$field} = $table->{$field}->{type};
1191            }
1192        }
1193        # Return the result.
1194        return %retVal;
1195    }
1196    
1197    =head3 GetFieldRelationName
1198    
1199    C<< my $name = $erdb->GetFieldRelationName($objectName, $fieldName); >>
1200    
1201    Return the name of the relation containing a specified field.
1202    
1203    =over 4
1204    
1205    =item objectName
1206    
1207    Name of the entity or relationship containing the field.
1208    
1209    =item fieldName
1210    
1211    Name of the relevant field in that entity or relationship.
1212    
1213    =item RETURN
1214    
1215    Returns the name of the database relation containing the field, or C<undef> if
1216    the field does not exist.
1217    
1218    =back
1219    
1220    =cut
1221    
1222    sub GetFieldRelationName {
1223        # Get the parameters.
1224        my ($self, $objectName, $fieldName) = @_;
1225        # Declare the return variable.
1226        my $retVal;
1227        # Get the object field table.
1228        my $table = $self->GetFieldTable($objectName);
1229        # Only proceed if the field exists.
1230        if (exists $table->{$fieldName}) {
1231            # Determine the name of the relation that contains this field.
1232            $retVal = $table->{$fieldName}->{relation};
1233        }
1234        # Return the result.
1235        return $retVal;
1236    }
1237    
1238    =head3 DeleteValue
1239    
1240    C<< my $numDeleted = $erdb->DeleteValue($entityName, $id, $fieldName, $fieldValue); >>
1241    
1242    Delete secondary field values from the database. This method can be used to delete all
1243    values of a specified field for a particular entity instance, or only a single value.
1244    
1245    Secondary fields are stored in two-column relations separate from an entity's primary
1246    table, and as a result a secondary field can legitimately have no value or multiple
1247    values. Therefore, it makes sense to talk about deleting secondary fields where it
1248    would not make sense for primary fields.
1249    
1250    =over 4
1251    
1252    =item entityName
1253    
1254    Name of the entity from which the fields are to be deleted.
1255    
1256    =item id
1257    
1258    ID of the entity instance to be processed. If the instance is not found, this
1259    method will have no effect. If C<undef> is specified, all values for all of
1260    the entity instances will be deleted.
1261    
1262    =item fieldName
1263    
1264    Name of the field whose values are to be deleted.
1265    
1266    =item fieldValue (optional)
1267    
1268    Value to be deleted. If not specified, then all values of the specified field
1269    will be deleted for the entity instance. If specified, then only the values which
1270    match this parameter will be deleted.
1271    
1272    =item RETURN
1273    
1274    Returns the number of rows deleted.
1275    
1276    =back
1277    
1278    =cut
1279    
1280    sub DeleteValue {
1281        # Get the parameters.
1282        my ($self, $entityName, $id, $fieldName, $fieldValue) = @_;
1283        # Declare the return value.
1284        my $retVal = 0;
1285        # We need to set up an SQL command to do the deletion. First, we
1286        # find the name of the field's relation.
1287        my $table = $self->GetFieldTable($entityName);
1288        my $field = $table->{$fieldName};
1289        my $relation = $field->{relation};
1290        # Make sure this is a secondary field.
1291        if ($relation eq $entityName) {
1292            Confess("Cannot delete values of $fieldName for $entityName.");
1293        } else {
1294            # Set up the SQL command to delete all values.
1295            my $sql = "DELETE FROM $relation";
1296            # Build the filter.
1297            my @filters = ();
1298            my @parms = ();
1299            # Check for a filter by ID.
1300            if (defined $id) {
1301                push @filters, "id = ?";
1302                push @parms, $id;
1303            }
1304            # Check for a filter by value.
1305            if (defined $fieldValue) {
1306                push @filters, "$fieldName = ?";
1307                push @parms, $fieldValue;
1308            }
1309            # Append the filters to the command.
1310            if (@filters) {
1311                $sql .= " WHERE " . join(" AND ", @filters);
1312            }
1313            # Execute the command.
1314            my $dbh = $self->{_dbh};
1315            $retVal = $dbh->SQL($sql, 0, @parms);
1316        }
1317        # Return the result.
1318        return $retVal;
1319    }
1320    
1321  =head3 LoadTables  =head3 LoadTables
1322    
1323  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>
# Line 950  Line 1412 
1412      return sort keys %{$entityList};      return sort keys %{$entityList};
1413  }  }
1414    
1415    =head3 GetDataTypes
1416    
1417    C<< my %types = ERDB::GetDataTypes(); >>
1418    
1419    Return a table of ERDB data types. The table returned is a hash of hashes.
1420    The keys of the big hash are the datatypes. Each smaller hash has several
1421    values used to manage the data. The most interesting is the SQL type (key
1422    C<sqlType>) and the descriptive node (key C<notes>).
1423    
1424    Note that changing the values in the smaller hashes will seriously break
1425    things, so this data should be treated as read-only.
1426    
1427    =cut
1428    
1429    sub GetDataTypes {
1430        return %TypeTable;
1431    }
1432    
1433    
1434  =head3 IsEntity  =head3 IsEntity
1435    
1436  C<< my $flag = $erdb->IsEntity($entityName); >>  C<< my $flag = $erdb->IsEntity($entityName); >>
# Line 1094  Line 1575 
1575      return $retVal;      return $retVal;
1576  }  }
1577    
1578    
1579    
1580    =head3 Search
1581    
1582    C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>
1583    
1584    Perform a full text search with filtering. The search will be against a specified object
1585    in the object name list. That object will get an extra field containing the search
1586    relevance. Note that except for the search expression, the parameters of this method are
1587    the same as those for L</Get> and follow the same rules.
1588    
1589    =over 4
1590    
1591    =item searchExpression
1592    
1593    Boolean search expression for the text fields of the target object. The default mode for
1594    a Boolean search expression is OR, but we want the default to be AND, so we will
1595    add a C<+> operator to each word with no other operator before it.
1596    
1597    =item idx
1598    
1599    Index in the I<$objectNames> list of the table to be searched in full-text mode.
1600    
1601    =item objectNames
1602    
1603    List containing the names of the entity and relationship objects to be retrieved.
1604    
1605    =item filterClause
1606    
1607    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1608    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
1609    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
1610    in the filter clause should be added to the parameter list as additional parameters. The
1611    fields in a filter clause can come from primary entity relations, relationship relations,
1612    or secondary entity relations; however, all of the entities and relationships involved must
1613    be included in the list of object names.
1614    
1615    =item params
1616    
1617    Reference to a list of parameter values to be substituted into the filter clause.
1618    
1619    =item RETURN
1620    
1621    Returns a query object for the specified search.
1622    
1623    =back
1624    
1625    =cut
1626    
1627    sub Search {
1628        # Get the parameters.
1629        my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1630        # Declare the return variable.
1631        my $retVal;
1632        # Create a safety copy of the parameter list. Note we have to be careful to insure
1633        # a parameter list exists before we copy it.
1634        my @myParams = ();
1635        if (defined $params) {
1636            @myParams = @{$params};
1637        }
1638        # Get the first object's structure so we have access to the searchable fields.
1639        my $object1Name = $objectNames->[$idx];
1640        my $object1Structure = $self->_GetStructure($object1Name);
1641        # Get the field list.
1642        if (! exists $object1Structure->{searchFields}) {
1643            Confess("No searchable index for $object1Name.");
1644        } else {
1645            # Get the field list.
1646            my @fields = @{$object1Structure->{searchFields}};
1647            # Clean the search expression.
1648            my $actualKeywords = $self->CleanKeywords($searchExpression);
1649            # Prefix a "+" to each uncontrolled word. This converts the default
1650            # search mode from OR to AND.
1651            $actualKeywords =~ s/(^|\s)(\w|")/$1\+$2/g;
1652            Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1653            # We need two match expressions, one for the filter clause and one in the
1654            # query itself. Both will use a parameter mark, so we need to push the
1655            # search expression onto the front of the parameter list twice.
1656            unshift @myParams, $actualKeywords, $actualKeywords;
1657            # Build the match expression.
1658            my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
1659            my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
1660            # Process the SQL stuff.
1661            my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1662                $self->_SetupSQL($objectNames, $filterClause, $matchClause);
1663            # Create the query. Note that the match clause is inserted at the front of
1664            # the select fields.
1665            my $command = "SELECT DISTINCT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .
1666                ".* $suffix";
1667            my $sth = $self->_GetStatementHandle($command, \@myParams);
1668            # Now we create the relation map, which enables DBQuery to determine the order, name
1669            # and mapped name for each object in the query.
1670            my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
1671            # Return the statement object.
1672            $retVal = DBQuery::_new($self, $sth, \@relationMap, $object1Name);
1673        }
1674        return $retVal;
1675    }
1676    
1677  =head3 GetFlat  =head3 GetFlat
1678    
1679  C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>  C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>
# Line 1147  Line 1727 
1727      return @retVal;      return @retVal;
1728  }  }
1729    
1730    =head3 SpecialFields
1731    
1732    C<< my %specials = $erdb->SpecialFields($entityName); >>
1733    
1734    Return a hash mapping special fields in the specified entity to the value of their
1735    C<special> attribute. This enables the subclass to get access to the special field
1736    attributes without needed to plumb the internal ERDB data structures.
1737    
1738    =over 4
1739    
1740    =item entityName
1741    
1742    Name of the entity whose special fields are desired.
1743    
1744    =item RETURN
1745    
1746    Returns a hash. The keys of the hash are the special field names, and the values
1747    are the values from each special field's C<special> attribute.
1748    
1749    =back
1750    
1751    =cut
1752    
1753    sub SpecialFields {
1754        # Get the parameters.
1755        my ($self, $entityName) = @_;
1756        # Declare the return variable.
1757        my %retVal = ();
1758        # Find the entity's data structure.
1759        my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1760        # Loop through its fields, adding each special field to the return hash.
1761        my $fieldHash = $entityData->{Fields};
1762        for my $fieldName (keys %{$fieldHash}) {
1763            my $fieldData = $fieldHash->{$fieldName};
1764            if (exists $fieldData->{special}) {
1765                $retVal{$fieldName} = $fieldData->{special};
1766            }
1767        }
1768        # Return the result.
1769        return %retVal;
1770    }
1771    
1772  =head3 Delete  =head3 Delete
1773    
1774  C<< my $stats = $erdb->Delete($entityName, $objectID); >>  C<< my $stats = $erdb->Delete($entityName, $objectID, %options); >>
1775    
1776  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
1777  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.
1778  always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many  
1779  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
1780    relationship connected to a dependent entity or if it is the "to" entity connected to a 1-to-many
1781  dependent relationship.  dependent relationship.
1782    
1783  =over 4  =over 4
# Line 1168  Line 1791 
1791  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<%>),
1792  then it is presumed to by a LIKE pattern.  then it is presumed to by a LIKE pattern.
1793    
1794  =item testFlag  =item options
1795    
1796  If TRUE, the delete statements will be traced without being executed.  A hash detailing the options for this delete operation.
1797    
1798  =item RETURN  =item RETURN
1799    
# Line 1179  Line 1802 
1802    
1803  =back  =back
1804    
1805    The permissible options for this method are as follows.
1806    
1807    =over 4
1808    
1809    =item testMode
1810    
1811    If TRUE, then the delete statements will be traced, but no changes will be made to the database.
1812    
1813    =item keepRoot
1814    
1815    If TRUE, then the entity instances will not be deleted, only the dependent records.
1816    
1817    =back
1818    
1819  =cut  =cut
1820  #: Return Type $%;  #: Return Type $%;
1821  sub Delete {  sub Delete {
1822      # Get the parameters.      # Get the parameters.
1823      my ($self, $entityName, $objectID, $testFlag) = @_;      my ($self, $entityName, $objectID, %options) = @_;
1824      # Declare the return variable.      # Declare the return variable.
1825      my $retVal = Stats->new();      my $retVal = Stats->new();
1826      # Get the DBKernel object.      # Get the DBKernel object.
# Line 1200  Line 1837 
1837      # FROM-relationships and entities.      # FROM-relationships and entities.
1838      my @fromPathList = ();      my @fromPathList = ();
1839      my @toPathList = ();      my @toPathList = ();
1840      # This final hash is used to remember what work still needs to be done. We push paths      # This final list is used to remember what work still needs to be done. We push paths
1841      # onto the list, then pop them off to extend the paths. We prime it with the starting      # onto the list, then pop them off to extend the paths. We prime it with the starting
1842      # point. Note that we will work hard to insure that the last item on a path in the      # point. Note that we will work hard to insure that the last item on a path in the
1843      # TODO list is always an entity.      # to-do list is always an entity.
1844      my @todoList = ([$entityName]);      my @todoList = ([$entityName]);
1845      while (@todoList) {      while (@todoList) {
1846          # Get the current path.          # Get the current path.
# Line 1211  Line 1848 
1848          # Copy it into a list.          # Copy it into a list.
1849          my @stackedPath = @{$current};          my @stackedPath = @{$current};
1850          # 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.
1851          my $entityName = pop @stackedPath;          my $myEntityName = pop @stackedPath;
1852          # Add it to the alreadyFound list.          # Add it to the alreadyFound list.
1853          $alreadyFound{$entityName} = 1;          $alreadyFound{$myEntityName} = 1;
1854            # Figure out if we need to delete this entity.
1855            if ($myEntityName ne $entityName || ! $options{keepRoot}) {
1856          # Get the entity data.          # Get the entity data.
1857          my $entityData = $self->_GetStructure($entityName);              my $entityData = $self->_GetStructure($myEntityName);
1858          # 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.  
1859          my $relations = $entityData->{Relations};          my $relations = $entityData->{Relations};
1860          for my $relation (keys %{$relations}) {          for my $relation (keys %{$relations}) {
1861              my @augmentedList = (@stackedPath, $relation);              my @augmentedList = (@stackedPath, $relation);
1862              push @fromPathList, \@augmentedList;              push @fromPathList, \@augmentedList;
1863          }          }
1864            }
1865          # Now we need to look for relationships connected to this entity.          # Now we need to look for relationships connected to this entity.
1866          my $relationshipList = $self->{_metaData}->{Relationships};          my $relationshipList = $self->{_metaData}->{Relationships};
1867          for my $relationshipName (keys %{$relationshipList}) {          for my $relationshipName (keys %{$relationshipList}) {
1868              my $relationship = $relationshipList->{$relationshipName};              my $relationship = $relationshipList->{$relationshipName};
1869              # Check the FROM field. We're only interested if it's us.              # Check the FROM field. We're only interested if it's us.
1870              if ($relationship->{from} eq $entityName) {              if ($relationship->{from} eq $myEntityName) {
1871                  # Add the path to this relationship.                  # Add the path to this relationship.
1872                  my @augmentedList = (@stackedPath, $entityName, $relationshipName);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1873                  push @fromPathList, \@augmentedList;                  push @fromPathList, \@augmentedList;
1874                  # Check the arity. If it's MM we're done. If it's 1M                  # Check the arity. If it's MM we're done. If it's 1M
1875                  # and the target hasn't been seen yet, we want to                  # and the target hasn't been seen yet, we want to
# Line 1249  Line 1888 
1888              }              }
1889              # Now check the TO field. In this case only the relationship needs              # Now check the TO field. In this case only the relationship needs
1890              # deletion.              # deletion.
1891              if ($relationship->{to} eq $entityName) {              if ($relationship->{to} eq $myEntityName) {
1892                  my @augmentedList = (@stackedPath, $entityName, $relationshipName);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1893                  push @toPathList, \@augmentedList;                  push @toPathList, \@augmentedList;
1894              }              }
1895          }          }
1896      }      }
1897      # Create the first qualifier for the WHERE clause. This selects the      # Create the first qualifier for the WHERE clause. This selects the
1898      # 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
1899      # 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
1900      # to the table containing the dependent records to delete.      # to the table containing the dependent records to delete.
1901      my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");      my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
1902      # 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 1935 
1935                  }                  }
1936              }              }
1937              # Now we have our desired DELETE statement.              # Now we have our desired DELETE statement.
1938              if ($testFlag) {              if ($options{testMode}) {
1939                  # Here the user wants to trace without executing.                  # Here the user wants to trace without executing.
1940                  Trace($stmt) if T(0);                  Trace($stmt) if T(0);
1941              } else {              } else {
1942                  # 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
1943                  # if an error occurs, so we just go ahead and do it.                  # if an error occurs, so we just go ahead and do it.
1944                  Trace("Executing delete from $target using '$objectID'.") if T(3);                  Trace("Executing delete from $target using '$objectID'.") if T(3);
1945                  my $rv = $db->SQL($stmt, 0, $objectID);                  my $rv = $db->SQL($stmt, 0, $objectID);
# Line 1315  Line 1954 
1954      return $retVal;      return $retVal;
1955  }  }
1956    
1957    =head3 Disconnect
1958    
1959    C<< $erdb->Disconnect($relationshipName, $originEntityName, $originEntityID); >>
1960    
1961    Disconnect an entity instance from all the objects to which it is related. This
1962    will delete each relationship instance that connects to the specified entity.
1963    
1964    =over 4
1965    
1966    =item relationshipName
1967    
1968    Name of the relationship whose instances are to be deleted.
1969    
1970    =item originEntityName
1971    
1972    Name of the entity that is to be disconnected.
1973    
1974    =item originEntityID
1975    
1976    ID of the entity that is to be disconnected.
1977    
1978    =back
1979    
1980    =cut
1981    
1982    sub Disconnect {
1983        # Get the parameters.
1984        my ($self, $relationshipName, $originEntityName, $originEntityID) = @_;
1985        # Get the relationship descriptor.
1986        my $structure = $self->_GetStructure($relationshipName);
1987        # Insure we have a relationship.
1988        if (! exists $structure->{from}) {
1989            Confess("$relationshipName is not a relationship in the database.");
1990        } else {
1991            # Get the database handle.
1992            my $dbh = $self->{_dbh};
1993            # We'll set this value to 1 if we find our entity.
1994            my $found = 0;
1995            # Loop through the ends of the relationship.
1996            for my $dir ('from', 'to') {
1997                if ($structure->{$dir} eq $originEntityName) {
1998                    # Delete all relationship instances on this side of the entity instance.
1999                    Trace("Disconnecting in $dir direction with ID \"$originEntityID\".");
2000                    $dbh->SQL("DELETE FROM $relationshipName WHERE ${dir}_link = ?", 0, $originEntityID);
2001                    $found = 1;
2002                }
2003            }
2004            # Insure we found the entity on at least one end.
2005            if (! $found) {
2006                Confess("Entity \"$originEntityName\" does not use $relationshipName.");
2007            }
2008        }
2009    }
2010    
2011    =head3 DeleteRow
2012    
2013    C<< $erdb->DeleteRow($relationshipName, $fromLink, $toLink, \%values); >>
2014    
2015    Delete a row from a relationship. In most cases, only the from-link and to-link are
2016    needed; however, for relationships with intersection data values can be specified
2017    for the other fields using a hash.
2018    
2019    =over 4
2020    
2021    =item relationshipName
2022    
2023    Name of the relationship from which the row is to be deleted.
2024    
2025    =item fromLink
2026    
2027    ID of the entity instance in the From direction.
2028    
2029    =item toLink
2030    
2031    ID of the entity instance in the To direction.
2032    
2033    =item values
2034    
2035    Reference to a hash of other values to be used for filtering the delete.
2036    
2037    =back
2038    
2039    =cut
2040    
2041    sub DeleteRow {
2042        # Get the parameters.
2043        my ($self, $relationshipName, $fromLink, $toLink, $values) = @_;
2044        # Create a hash of all the filter information.
2045        my %filter = ('from-link' => $fromLink, 'to-link' => $toLink);
2046        if (defined $values) {
2047            for my $key (keys %{$values}) {
2048                $filter{$key} = $values->{$key};
2049            }
2050        }
2051        # Build an SQL statement out of the hash.
2052        my @filters = ();
2053        my @parms = ();
2054        for my $key (keys %filter) {
2055            push @filters, _FixName($key) . " = ?";
2056            push @parms, $filter{$key};
2057        }
2058        Trace("Parms for delete row are " . join(", ", map { "\"$_\"" } @parms) . ".") if T(SQL => 4);
2059        my $command = "DELETE FROM $relationshipName WHERE " .
2060                      join(" AND ", @filters);
2061        # Execute it.
2062        my $dbh = $self->{_dbh};
2063        $dbh->SQL($command, undef, @parms);
2064    }
2065    
2066    =head3 SortNeeded
2067    
2068    C<< my $parms = $erdb->SortNeeded($relationName); >>
2069    
2070    Return the pipe command for the sort that should be applied to the specified
2071    relation when creating the load file.
2072    
2073    For example, if the load file should be sorted ascending by the first
2074    field, this method would return
2075    
2076        sort -k1 -t"\t"
2077    
2078    If the first field is numeric, the method would return
2079    
2080        sort -k1n -t"\t"
2081    
2082    Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate
2083    keys using a sort.
2084    
2085    =over 4
2086    
2087    =item relationName
2088    
2089    Name of the relation to be examined.
2090    
2091    =item
2092    
2093    Returns the sort command to use for sorting the relation, suitable for piping.
2094    
2095    =back
2096    
2097    =cut
2098    #: Return Type $;
2099    sub SortNeeded {
2100        # Get the parameters.
2101        my ($self, $relationName) = @_;
2102        # Declare a descriptor to hold the names of the key fields.
2103        my @keyNames = ();
2104        # Get the relation structure.
2105        my $relationData = $self->_FindRelation($relationName);
2106        # Find out if the relation is a primary entity relation,
2107        # a relationship relation, or a secondary entity relation.
2108        my $entityTable = $self->{_metaData}->{Entities};
2109        my $relationshipTable = $self->{_metaData}->{Relationships};
2110        if (exists $entityTable->{$relationName}) {
2111            # Here we have a primary entity relation.
2112            push @keyNames, "id";
2113        } elsif (exists $relationshipTable->{$relationName}) {
2114            # Here we have a relationship. We sort using the FROM index.
2115            my $relationshipData = $relationshipTable->{$relationName};
2116            my $index = $relationData->{Indexes}->{idxFrom};
2117            push @keyNames, @{$index->{IndexFields}};
2118        } else {
2119            # Here we have a secondary entity relation, so we have a sort on the ID field.
2120            push @keyNames, "id";
2121        }
2122        # Now we parse the key names into sort parameters. First, we prime the return
2123        # string.
2124        my $retVal = "sort -t\"\t\" ";
2125        # Get the relation's field list.
2126        my @fields = @{$relationData->{Fields}};
2127        # Loop through the keys.
2128        for my $keyData (@keyNames) {
2129            # Get the key and the ordering.
2130            my ($keyName, $ordering);
2131            if ($keyData =~ /^([^ ]+) DESC/) {
2132                ($keyName, $ordering) = ($1, "descending");
2133            } else {
2134                ($keyName, $ordering) = ($keyData, "ascending");
2135            }
2136            # Find the key's position and type.
2137            my $fieldSpec;
2138            for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {
2139                my $thisField = $fields[$i];
2140                if ($thisField->{name} eq $keyName) {
2141                    # Get the sort modifier for this field type. The modifier
2142                    # decides whether we're using a character, numeric, or
2143                    # floating-point sort.
2144                    my $modifier = $TypeTable{$thisField->{type}}->{sort};
2145                    # If the index is descending for this field, denote we want
2146                    # to reverse the sort order on this field.
2147                    if ($ordering eq 'descending') {
2148                        $modifier .= "r";
2149                    }
2150                    # Store the position and modifier into the field spec, which
2151                    # will stop the inner loop. Note that the field number is
2152                    # 1-based in the sort command, so we have to increment the
2153                    # index.
2154                    $fieldSpec = ($i + 1) . $modifier;
2155                }
2156            }
2157            # Add this field to the sort command.
2158            $retVal .= " -k$fieldSpec";
2159        }
2160        # Return the result.
2161        return $retVal;
2162    }
2163    
2164  =head3 GetList  =head3 GetList
2165    
2166  C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>  C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>
# Line 1357  Line 2203 
2203    
2204  =item RETURN  =item RETURN
2205    
2206  Returns a list of B<DBObject>s that satisfy the query conditions.  Returns a list of B<ERDBObject>s that satisfy the query conditions.
2207    
2208  =back  =back
2209    
# Line 1431  Line 2277 
2277  sub GetCount {  sub GetCount {
2278      # Get the parameters.      # Get the parameters.
2279      my ($self, $objectNames, $filter, $params) = @_;      my ($self, $objectNames, $filter, $params) = @_;
2280        # Insure the params argument is an array reference if the caller left it off.
2281        if (! defined($params)) {
2282            $params = [];
2283        }
2284      # Declare the return variable.      # Declare the return variable.
2285      my $retVal;      my $retVal;
2286      # Find out if we're counting an entity or a relationship.      # Find out if we're counting an entity or a relationship.
# Line 1609  Line 2459 
2459    
2460  =head3 InsertObject  =head3 InsertObject
2461    
2462  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>  C<< $erdb->InsertObject($objectType, \%fieldHash); >>
2463    
2464  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
2465  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 1623  Line 2473 
2473  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
2474  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>.
2475    
2476  C<< $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>  C<< $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>
2477    
2478  =over 4  =over 4
2479    
# Line 1635  Line 2485 
2485    
2486  Hash of field names to values.  Hash of field names to values.
2487    
 =item RETURN  
   
 Returns 1 if successful, 0 if an error occurred.  
   
2488  =back  =back
2489    
2490  =cut  =cut
# Line 1737  Line 2583 
2583                  $retVal = $sth->execute(@parameterList);                  $retVal = $sth->execute(@parameterList);
2584                  if (!$retVal) {                  if (!$retVal) {
2585                      my $errorString = $sth->errstr();                      my $errorString = $sth->errstr();
2586                      Trace("Insert error: $errorString.") if T(0);                      Confess("Error inserting into $relationName: $errorString");
2587                    } else {
2588                        Trace("Insert successful using $parameterList[0].") if T(3);
2589                  }                  }
2590              }              }
2591          }          }
2592      }      }
2593      # Return the success indicator.      # Return a 1 for backward compatability.
2594      return $retVal;      return 1;
2595    }
2596    
2597    =head3 UpdateEntity
2598    
2599    C<< $erdb->UpdateEntity($entityName, $id, \%fields); >>
2600    
2601    Update the values of an entity. This is an unprotected update, so it should only be
2602    done if the database resides on a database server.
2603    
2604    =over 4
2605    
2606    =item entityName
2607    
2608    Name of the entity to update. (This is the entity type.)
2609    
2610    =item id
2611    
2612    ID of the entity to update. If no entity exists with this ID, an error will be thrown.
2613    
2614    =item fields
2615    
2616    Reference to a hash mapping field names to their new values. All of the fields named
2617    must be in the entity's primary relation, and they cannot any of them be the ID field.
2618    
2619    =back
2620    
2621    =cut
2622    
2623    sub UpdateEntity {
2624        # Get the parameters.
2625        my ($self, $entityName, $id, $fields) = @_;
2626        # Get a list of the field names being updated.
2627        my @fieldList = keys %{$fields};
2628        # Verify that the fields exist.
2629        my $checker = $self->GetFieldTable($entityName);
2630        for my $field (@fieldList) {
2631            if ($field eq 'id') {
2632                Confess("Cannot update the ID field for entity $entityName.");
2633            } elsif ($checker->{$field}->{relation} ne $entityName) {
2634                Confess("Cannot find $field in primary relation of $entityName.");
2635            }
2636        }
2637        # Build the SQL statement.
2638        my @sets = ();
2639        my @valueList = ();
2640        for my $field (@fieldList) {
2641            push @sets, _FixName($field) . " = ?";
2642            push @valueList, $fields->{$field};
2643        }
2644        my $command = "UPDATE $entityName SET " . join(", ", @sets) . " WHERE id = ?";
2645        # Add the ID to the list of binding values.
2646        push @valueList, $id;
2647        # Call SQL to do the work.
2648        my $rows = $self->{_dbh}->SQL($command, 0, @valueList);
2649        # Check for errors.
2650        if ($rows == 0) {
2651            Confess("Entity $id of type $entityName not found.");
2652        }
2653  }  }
2654    
2655  =head3 LoadTable  =head3 LoadTable
2656    
2657  C<< my %results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>  C<< my $results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>
2658    
2659  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
2660  first.  first.
# Line 1795  Line 2701 
2701          # leave extra room. We postulate a minimum row count of 1000 to          # leave extra room. We postulate a minimum row count of 1000 to
2702          # prevent problems with incoming empty load files.          # prevent problems with incoming empty load files.
2703          my $rowSize = $self->EstimateRowSize($relationName);          my $rowSize = $self->EstimateRowSize($relationName);
2704          my $estimate = FIG::max($fileSize * 1.5 / $rowSize, 1000);          my $estimate = $fileSize * 1.5 / $rowSize;
2705            if ($estimate < 1000) {
2706                $estimate = 1000;
2707            }
2708          # Re-create the table without its index.          # Re-create the table without its index.
2709          $self->CreateTable($relationName, 0, $estimate);          $self->CreateTable($relationName, 0, $estimate);
2710          # 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 2724 
2724      };      };
2725      if (!defined $rv) {      if (!defined $rv) {
2726          $retVal->AddMessage($@) if ($@);          $retVal->AddMessage($@) if ($@);
2727          $retVal->AddMessage("Table load failed for $relationName using $fileName.");          $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2728          Trace("Table load failed for $relationName.") if T(1);          Trace("Table load failed for $relationName.") if T(1);
2729      } else {      } else {
2730          # Here we successfully loaded the table.          # Here we successfully loaded the table.
# Line 1823  Line 2732 
2732          my $size = -s $fileName;          my $size = -s $fileName;
2733          Trace("$size bytes loaded into $relationName.") if T(2);          Trace("$size bytes loaded into $relationName.") if T(2);
2734          # If we're rebuilding, we need to create the table indexes.          # If we're rebuilding, we need to create the table indexes.
2735          if ($truncateFlag && ! $dbh->{_preIndex}) {          if ($truncateFlag) {
2736                # Indexes are created here for PostGres. For PostGres, indexes are
2737                # best built at the end. For MySQL, the reverse is true.
2738                if (! $dbh->{_preIndex}) {
2739              eval {              eval {
2740                  $self->CreateIndex($relationName);                  $self->CreateIndex($relationName);
2741              };              };
# Line 1831  Line 2743 
2743                  $retVal->AddMessage($@);                  $retVal->AddMessage($@);
2744              }              }
2745          }          }
2746                # The full-text index (if any) is always built last, even for MySQL.
2747                # First we need to see if this table has a full-text index. Only
2748                # primary relations are allowed that privilege.
2749                Trace("Checking for full-text index on $relationName.") if T(2);
2750                if ($self->_IsPrimary($relationName)) {
2751                    $self->CreateSearchIndex($relationName);
2752                }
2753            }
2754      }      }
2755      # Analyze the table to improve performance.      # Analyze the table to improve performance.
2756        Trace("Analyzing and compacting $relationName.") if T(3);
2757      $dbh->vacuum_it($relationName);      $dbh->vacuum_it($relationName);
2758        Trace("$relationName load completed.") if T(3);
2759      # Return the statistics.      # Return the statistics.
2760      return $retVal;      return $retVal;
2761  }  }
2762    
2763  =head3 GenerateEntity  =head3 CreateSearchIndex
2764    
2765  C<< my $fieldHash = $erdb->GenerateEntity($id, $type, \%values); >>  C<< $erdb->CreateSearchIndex($objectName); >>
2766    
2767  Generate the data for a new entity instance. This method creates a field hash suitable for  Check for a full-text search index on the specified entity or relationship object, and
2768  passing as a parameter to L</InsertObject>. The ID is specified by the callr, but the rest  if one is required, rebuild it.
 of the fields are generated using information in the database schema.  
   
 Each data type has a default algorithm for generating random test data. This can be overridden  
 by including a B<DataGen> element in the field. If this happens, the content of the element is  
 executed as a PERL program in the context of this module. The element may make use of a C<$this>  
 variable which contains the field hash as it has been built up to the current point. If any  
 fields are dependent on other fields, the C<pass> attribute can be used to control the order  
 in which the fields are generated. A field with a high data pass number will be generated after  
 a field with a lower one. If any external values are needed, they should be passed in via the  
 optional third parameter, which will be available to the data generation script under the name  
 C<$value>. Several useful utility methods are provided for generating random values, including  
 L</IntGen>, L</StringGen>, L</FloatGen>, and L</DateGen>. Note that dates are stored and generated  
 in the form of a timestamp number rather than a string.  
2769    
2770  =over 4  =over 4
2771    
2772  =item id  =item objectName
2773    
2774  ID to assign to the new entity.  Name of the entity or relationship to be indexed.
2775    
2776  =item type  =back
2777    
2778  Type name for the new entity.  =cut
2779    
2780  =item values  sub CreateSearchIndex {
2781        # Get the parameters.
2782        my ($self, $objectName) = @_;
2783        # Get the relation's entity/relationship structure.
2784        my $structure = $self->_GetStructure($objectName);
2785        # Get the database handle.
2786        my $dbh = $self->{_dbh};
2787        Trace("Checking for search fields in $objectName.") if T(3);
2788        # Check for a searchable fields list.
2789        if (exists $structure->{searchFields}) {
2790            # Here we know that we need to create a full-text search index.
2791            # Get an SQL-formatted field name list.
2792            my $fields = join(", ", _FixNames(@{$structure->{searchFields}}));
2793            # Create the index. If it already exists, it will be dropped.
2794            $dbh->create_index(tbl => $objectName, idx => "search_idx",
2795                               flds => $fields, kind => 'fulltext');
2796            Trace("Index created for $fields in $objectName.") if T(2);
2797        }
2798    }
2799    
2800  Hash containing additional values that might be needed by the data generation methods (optional).  =head3 DropRelation
2801    
2802    C<< $erdb->DropRelation($relationName); >>
2803    
2804    Physically drop a relation from the database.
2805    
2806    =over 4
2807    
2808    =item relationName
2809    
2810    Name of the relation to drop. If it does not exist, this method will have
2811    no effect.
2812    
2813  =back  =back
2814    
2815  =cut  =cut
2816    
2817  sub GenerateEntity {  sub DropRelation {
2818      # Get the parameters.      # Get the parameters.
2819      my ($self, $id, $type, $values) = @_;      my ($self, $relationName) = @_;
2820      # Create the return hash.      # Get the database handle.
2821      my $this = { id => $id };      my $dbh = $self->{_dbh};
2822      # Get the metadata structure.      # Drop the relation. The method used here has no effect if the relation
2823      my $metadata = $self->{_metaData};      # does not exist.
2824      # Get this entity's list of fields.      Trace("Invoking DB Kernel to drop $relationName.") if T(3);
2825      if (!exists $metadata->{Entities}->{$type}) {      $dbh->drop_table(tbl => $relationName);
2826          Confess("Unrecognized entity type $type in GenerateEntity.");  }
2827    
2828    =head3 MatchSqlPattern
2829    
2830    C<< my $matched = ERDB::MatchSqlPattern($value, $pattern); >>
2831    
2832    Determine whether or not a specified value matches an SQL pattern. An SQL
2833    pattern has two wild card characters: C<%> that matches multiple characters,
2834    and C<_> that matches a single character. These can be escaped using a
2835    backslash (C<\>). We pull this off by converting the SQL pattern to a
2836    PERL regular expression. As per SQL rules, the match is case-insensitive.
2837    
2838    =over 4
2839    
2840    =item value
2841    
2842    Value to be matched against the pattern. Note that an undefined or empty
2843    value will not match anything.
2844    
2845    =item pattern
2846    
2847    SQL pattern against which to match the value. An undefined or empty pattern will
2848    match everything.
2849    
2850    =item RETURN
2851    
2852    Returns TRUE if the value and pattern match, else FALSE.
2853    
2854    =back
2855    
2856    =cut
2857    
2858    sub MatchSqlPattern {
2859        # Get the parameters.
2860        my ($value, $pattern) = @_;
2861        # Declare the return variable.
2862        my $retVal;
2863        # Insure we have a pattern.
2864        if (! defined($pattern) || $pattern eq "") {
2865            $retVal = 1;
2866        } else {
2867            # Break the pattern into pieces around the wildcard characters. Because we
2868            # use parentheses in the split function's delimiter expression, we'll get
2869            # list elements for the delimiters as well as the rest of the string.
2870            my @pieces = split /([_%]|\\[_%])/, $pattern;
2871            # Check some fast special cases.
2872            if ($pattern eq '%') {
2873                # A null pattern matches everything.
2874                $retVal = 1;
2875            } elsif (@pieces == 1) {
2876                # No wildcards, so we have a literal comparison. Note we're case-insensitive.
2877                $retVal = (lc($value) eq lc($pattern));
2878            } elsif (@pieces == 2 && $pieces[1] eq '%') {
2879                # A wildcard at the end, so we have a substring match. This is also case-insensitive.
2880                $retVal = (lc(substr($value, 0, length($pieces[0]))) eq lc($pieces[0]));
2881            } else {
2882                # Okay, we have to do it the hard way. Convert each piece to a PERL pattern.
2883                my $realPattern = "";
2884                for my $piece (@pieces) {
2885                    # Determine the type of piece.
2886                    if ($piece eq "") {
2887                        # Empty pieces are ignored.
2888                    } elsif ($piece eq "%") {
2889                        # Here we have a multi-character wildcard. Note that it can match
2890                        # zero or more characters.
2891                        $realPattern .= ".*"
2892                    } elsif ($piece eq "_") {
2893                        # Here we have a single-character wildcard.
2894                        $realPattern .= ".";
2895                    } elsif ($piece eq "\\%" || $piece eq "\\_") {
2896                        # This is an escape sequence (which is a rare thing, actually).
2897                        $realPattern .= substr($piece, 1, 1);
2898      } else {      } else {
2899          my $entity = $metadata->{Entities}->{$type};                      # Here we have raw text.
2900          my $fields = $entity->{Fields};                      $realPattern .= quotemeta($piece);
         # Generate data from the fields.  
         _GenerateFields($this, $fields, $type, $values);  
2901      }      }
2902      # Return the hash created.              }
2903      return $this;              # Do the match.
2904                $retVal = ($value =~ /^$realPattern$/i ? 1 : 0);
2905            }
2906        }
2907        # Return the result.
2908        return $retVal;
2909  }  }
2910    
2911  =head3 GetEntity  =head3 GetEntity
# Line 1914  Line 2926 
2926    
2927  =item RETURN  =item RETURN
2928    
2929  Returns a B<DBObject> representing the desired entity instance, or an undefined value if no  Returns a B<ERDBObject> representing the desired entity instance, or an undefined value if no
2930  instance is found with the specified key.  instance is found with the specified key.
2931    
2932  =back  =back
# Line 1932  Line 2944 
2944      return $retVal;      return $retVal;
2945  }  }
2946    
2947    =head3 GetChoices
2948    
2949    C<< my @values = $erdb->GetChoices($entityName, $fieldName); >>
2950    
2951    Return a list of all the values for the specified field that are represented in the
2952    specified entity.
2953    
2954    Note that if the field is not indexed, then this will be a very slow operation.
2955    
2956    =over 4
2957    
2958    =item entityName
2959    
2960    Name of an entity in the database.
2961    
2962    =item fieldName
2963    
2964    Name of a field belonging to the entity. This is a raw field name without
2965    the standard parenthesized notation used in most calls.
2966    
2967    =item RETURN
2968    
2969    Returns a list of the distinct values for the specified field in the database.
2970    
2971    =back
2972    
2973    =cut
2974    
2975    sub GetChoices {
2976        # Get the parameters.
2977        my ($self, $entityName, $fieldName) = @_;
2978        # Declare the return variable.
2979        my @retVal;
2980        # Get the entity data structure.
2981        my $entityData = $self->_GetStructure($entityName);
2982        # Get the field.
2983        my $fieldHash = $entityData->{Fields};
2984        if (! exists $fieldHash->{$fieldName}) {
2985            Confess("$fieldName not found in $entityName.");
2986        } else {
2987            # Get the name of the relation containing the field.
2988            my $relation = $fieldHash->{$fieldName}->{relation};
2989            # Fix up the field name.
2990            my $realName = _FixName($fieldName);
2991            # Get the database handle.
2992            my $dbh = $self->{_dbh};
2993            # Query the database.
2994            my $results = $dbh->SQL("SELECT DISTINCT $realName FROM $relation");
2995            # Clean the results. They are stored as a list of lists, and we just want the one list.
2996            @retVal = sort map { $_->[0] } @{$results};
2997        }
2998        # Return the result.
2999        return @retVal;
3000    }
3001    
3002  =head3 GetEntityValues  =head3 GetEntityValues
3003    
3004  C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>  C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>
3005    
3006  Return a list of values from a specified entity instance.  Return a list of values from a specified entity instance. If the entity instance
3007    does not exist, an empty list is returned.
3008    
3009  =over 4  =over 4
3010    
# Line 1993  Line 3061 
3061  spreadsheet cell, and each feature will be represented by a list containing the  spreadsheet cell, and each feature will be represented by a list containing the
3062  feature ID followed by all of its aliases.  feature ID followed by all of its aliases.
3063    
3064  C<< $query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>  C<< @query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>
3065    
3066  =over 4  =over 4
3067    
# Line 2171  Line 3239 
3239      return $objectData->{Fields};      return $objectData->{Fields};
3240  }  }
3241    
3242  =head2 Data Mining Methods  =head3 SplitKeywords
3243    
3244  =head3 GetUsefulCrossValues  C<< my @keywords = ERDB::SplitKeywords($keywordString); >>
3245    
3246  C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>  This method returns a list of the positive keywords in the specified
3247    keyword string. All of the operators will have been stripped off,
3248    and if the keyword is preceded by a minus operator (C<->), it will
3249    not be in the list returned. The idea here is to get a list of the
3250    keywords the user wants to see. The list will be processed to remove
3251    duplicates.
3252    
3253  Return a list of the useful attributes that would be returned by a B<Cross> call  It is possible to create a string that confuses this method. For example
 from an entity of the source entity type through the specified relationship. This  
 means it will return the fields of the target entity type and the intersection data  
 fields in the relationship. Only primary table fields are returned. In other words,  
 the field names returned will be for fields where there is always one and only one  
 value.  
3254    
3255  =over 4      frog toad -frog
3256    
3257  =item sourceEntity  would return both C<frog> and C<toad>. If this is a problem we can deal
3258    with it later.
3259    
3260  Name of the entity from which the relationship crossing will start.  =over 4
3261    
3262  =item relationship  =item keywordString
3263    
3264  Name of the relationship being crossed.  The keyword string to be parsed.
3265    
3266  =item RETURN  =item RETURN
3267    
3268  Returns a list of field names in Sprout field format (I<objectName>C<(>I<fieldName>C<)>.  Returns a list of the words in the keyword string the user wants to
3269    see.
3270    
3271  =back  =back
3272    
3273  =cut  =cut
3274  #: Return Type @;  
3275  sub GetUsefulCrossValues {  sub SplitKeywords {
3276      # Get the parameters.      # Get the parameters.
3277      my ($self, $sourceEntity, $relationship) = @_;      my ($keywordString) = @_;
3278      # Declare the return variable.      # Make a safety copy of the string. (This helps during debugging.)
3279      my @retVal = ();      my $workString = $keywordString;
3280      # Determine the target entity for the relationship. This is whichever entity is not      # Convert operators we don't care about to spaces.
3281      # the source entity. So, if the source entity is the FROM, we'll get the name of      $workString =~ tr/+"()<>/ /;
3282      # the TO, and vice versa.      # Split the rest of the string along space boundaries. Note that we
3283      my $relStructure = $self->_GetStructure($relationship);      # eliminate any words that are zero length or begin with a minus sign.
3284      my $targetEntityType = ($relStructure->{from} eq $sourceEntity ? "to" : "from");      my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
3285      my $targetEntity = $relStructure->{$targetEntityType};      # Use a hash to remove duplicates.
3286        my %words = map { $_ => 1 } @wordList;
3287        # Return the result.
3288        return sort keys %words;
3289    }
3290    
3291    =head3 ValidateFieldName
3292    
3293    C<< my $okFlag = ERDB::ValidateFieldName($fieldName); >>
3294    
3295    Return TRUE if the specified field name is valid, else FALSE. Valid field names must
3296    be hyphenated words subject to certain restrictions.
3297    
3298    =over 4
3299    
3300    =item fieldName
3301    
3302    Field name to be validated.
3303    
3304    =item RETURN
3305    
3306    Returns TRUE if the field name is valid, else FALSE.
3307    
3308    =back
3309    
3310    =cut
3311    
3312    sub ValidateFieldName {
3313        # Get the parameters.
3314        my ($fieldName) = @_;
3315        # Declare the return variable. The field name is valid until we hear
3316        # differently.
3317        my $retVal = 1;
3318        # Compute the maximum name length.
3319        my $maxLen = $TypeTable{'name-string'}->{maxLen};
3320        # Look for bad stuff in the name.
3321        if ($fieldName =~ /--/) {
3322            # Here we have a doubled minus sign.
3323            Trace("Field name $fieldName has a doubled hyphen.") if T(1);
3324            $retVal = 0;
3325        } elsif ($fieldName !~ /^[A-Za-z]/) {
3326            # Here the field name is missing the initial letter.
3327            Trace("Field name $fieldName does not begin with a letter.") if T(1);
3328            $retVal = 0;
3329        } elsif (length($fieldName) > $maxLen) {
3330            # Here the field name is too long.
3331            Trace("Maximum field name length is $maxLen. Field name must be truncated to " . substr($fieldName,0, $maxLen) . ".");
3332        } else {
3333            # Strip out the minus signs. Everything remaining must be a letter,
3334            # underscore, or digit.
3335            my $strippedName = $fieldName;
3336            $strippedName =~ s/-//g;
3337            if ($strippedName !~ /^(\w|\d)+$/) {
3338                Trace("Field name $fieldName contains illegal characters.") if T(1);
3339                $retVal = 0;
3340            }
3341        }
3342        # Return the result.
3343        return $retVal;
3344    }
3345    
3346    =head3 ReadMetaXML
3347    
3348    C<< my $rawMetaData = ERDB::ReadDBD($fileName); >>
3349    
3350    This method reads a raw database definition XML file and returns it.
3351    Normally, the metadata used by the ERDB system has been processed and
3352    modified to make it easier to load and retrieve the data; however,
3353    this method can be used to get the data in its raw form.
3354    
3355    =over 4
3356    
3357    =item fileName
3358    
3359    Name of the XML file to read.
3360    
3361    =item RETURN
3362    
3363    Returns a hash reference containing the raw XML data from the specified file.
3364    
3365    =back
3366    
3367    =cut
3368    
3369    sub ReadMetaXML {
3370        # Get the parameters.
3371        my ($fileName) = @_;
3372        # Read the XML.
3373        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
3374        Trace("XML metadata loaded from file $fileName.") if T(1);
3375        # Return the result.
3376        return $retVal;
3377    }
3378    
3379    =head3 GetEntityFieldHash
3380    
3381    C<< my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName); >>
3382    
3383    Get the field hash of the named entity in the specified raw XML structure.
3384    The field hash may not exist, in which case we need to create it.
3385    
3386    =over 4
3387    
3388    =item structure
3389    
3390    Raw XML structure defininng the database. This is not the run-time XML used by
3391    an ERDB object, since that has all sorts of optimizations built-in.
3392    
3393    =item entityName
3394    
3395    Name of the entity whose field structure is desired.
3396    
3397    =item RETURN
3398    
3399    Returns the field hash used to define the entity's fields.
3400    
3401    =back
3402    
3403    =cut
3404    
3405    sub GetEntityFieldHash {
3406        # Get the parameters.
3407        my ($structure, $entityName) = @_;
3408        # Get the entity structure.
3409        my $entityData = $structure->{Entities}->{$entityName};
3410        # Look for a field structure.
3411        my $retVal = $entityData->{Fields};
3412        # If it doesn't exist, create it.
3413        if (! defined($retVal)) {
3414            $entityData->{Fields} = {};
3415            $retVal = $entityData->{Fields};
3416        }
3417        # Return the result.
3418        return $retVal;
3419    }
3420    
3421    =head3 WriteMetaXML
3422    
3423    C<< ERDB::WriteMetaXML($structure, $fileName); >>
3424    
3425    Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
3426    used to update the database definition. It must be used with care, however, since it
3427    will only work on a raw structure, not on the processed structure created by an ERDB
3428    constructor.
3429    
3430    =over 4
3431    
3432    =item structure
3433    
3434    XML structure to be written to the file.
3435    
3436    =item fileName
3437    
3438    Name of the output file to which the updated XML should be stored.
3439    
3440    =back
3441    
3442    =cut
3443    
3444    sub WriteMetaXML {
3445        # Get the parameters.
3446        my ($structure, $fileName) = @_;
3447        # Compute the output.
3448        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
3449        # Write it to the file.
3450        my $xmlOut = Open(undef, ">$fileName");
3451        print $xmlOut $fileString;
3452    }
3453    
3454    
3455    =head3 HTMLNote
3456    
3457    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
3458    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
3459    Except for C<[p]>, all the codes are closed by slash-codes. So, for
3460    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
3461    
3462    C<< my $realHtml = ERDB::HTMLNote($dataString); >>
3463    
3464    =over 4
3465    
3466    =item dataString
3467    
3468    String to convert to HTML.
3469    
3470    =item RETURN
3471    
3472    An HTML string derived from the input string.
3473    
3474    =back
3475    
3476    =cut
3477    
3478    sub HTMLNote {
3479        # Get the parameter.
3480        my ($dataString) = @_;
3481        # HTML-escape the text.
3482        my $retVal = CGI::escapeHTML($dataString);
3483        # Substitute the bulletin board codes.
3484        $retVal =~ s!\[(/?[bi])\]!<$1>!g;
3485        $retVal =~ s!\[p\]!</p><p>!g;
3486        $retVal =~ s!\[link\s+([^\]]+)\]!<a href="$1">!g;
3487        $retVal =~ s!\[/link\]!</a>!g;
3488        # Return the result.
3489        return $retVal;
3490    }
3491    
3492    =head3 BeginTran
3493    
3494    C<< $erdb->BeginTran(); >>
3495    
3496    Start a database transaction.
3497    
3498    =cut
3499    
3500    sub BeginTran {
3501        my ($self) = @_;
3502        $self->{_dbh}->begin_tran();
3503    
3504    }
3505    
3506    =head3 CommitTran
3507    
3508    C<< $erdb->CommitTran(); >>
3509    
3510    Commit an active database transaction.
3511    
3512    =cut
3513    
3514    sub CommitTran {
3515        my ($self) = @_;
3516        $self->{_dbh}->commit_tran();
3517    }
3518    
3519    =head3 RollbackTran
3520    
3521    C<< $erdb->RollbackTran(); >>
3522    
3523    Roll back an active database transaction.
3524    
3525    =cut
3526    
3527    sub RollbackTran {
3528        my ($self) = @_;
3529        $self->{_dbh}->roll_tran();
3530    }
3531    
3532    =head3 UpdateField
3533    
3534    C<< my $count = $erdb->UpdateField($objectNames, $fieldName, $oldValue, $newValue, $filter, $parms); >>
3535    
3536    Update all occurrences of a specific field value to a new value. The number of rows changed will be
3537    returned.
3538    
3539    =over 4
3540    
3541    =item fieldName
3542    
3543    Name of the field in standard I<objectName>C<(>I<fieldName>C<)> format.
3544    
3545    =item oldValue
3546    
3547    Value to be modified. All occurrences of this value in the named field will be replaced by the
3548    new value.
3549    
3550    =item newValue
3551    
3552    New value to be substituted for the old value when it's found.
3553    
3554    =item filter
3555    
3556    A standard ERDB filter clause (see L</Get>). The filter will be applied before any substitutions take place.
3557    
3558    =item parms
3559    
3560    Reference to a list of parameter values in the filter.
3561    
3562    =item RETURN
3563    
3564    Returns the number of rows modified.
3565    
3566    =back
3567    
3568    =cut
3569    
3570    sub UpdateField {
3571        # Get the parameters.
3572        my ($self, $fieldName, $oldValue, $newValue, $filter, $parms) = @_;
3573        # Get the object and field names from the field name parameter.
3574        $fieldName =~ /^([^(]+)\(([^)]+)\)/;
3575        my $objectName = $1;
3576        my $realFieldName = _FixName($2);
3577        # Add the old value to the filter. Note we allow the possibility that no
3578        # filter was specified.
3579        my $realFilter = "$fieldName = ?";
3580        if ($filter) {
3581            $realFilter .= " AND $filter";
3582        }
3583        # Format the query filter.
3584        my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
3585            $self->_SetupSQL([$objectName], $realFilter);
3586        # Create the query. Since there is only one object name, the mapped-name data is not
3587        # necessary. Neither is the FROM clause.
3588        $suffix =~ s/^FROM.+WHERE\s+//;
3589        # Create the update statement.
3590        my $command = "UPDATE $objectName SET $realFieldName = ? WHERE $suffix";
3591        # Get the database handle.
3592        my $dbh = $self->{_dbh};
3593        # Add the old and new values to the parameter list. Note we allow the possibility that
3594        # there are no user-supplied parameters.
3595        my @params = ($newValue, $oldValue);
3596        if (defined $parms) {
3597            push @params, @{$parms};
3598        }
3599        # Execute the update.
3600        my $retVal = $dbh->SQL($command, 0, @params);
3601        # Make the funky zero a real zero.
3602        if ($retVal == 0) {
3603            $retVal = 0;
3604        }
3605        # Return the result.
3606        return $retVal;
3607    }
3608    
3609    
3610    =head2 Data Mining Methods
3611    
3612    =head3 GetUsefulCrossValues
3613    
3614    C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>
3615    
3616    Return a list of the useful attributes that would be returned by a B<Cross> call
3617    from an entity of the source entity type through the specified relationship. This
3618    means it will return the fields of the target entity type and the intersection data
3619    fields in the relationship. Only primary table fields are returned. In other words,
3620    the field names returned will be for fields where there is always one and only one
3621    value.
3622    
3623    =over 4
3624    
3625    =item sourceEntity
3626    
3627    Name of the entity from which the relationship crossing will start.
3628    
3629    =item relationship
3630    
3631    Name of the relationship being crossed.
3632    
3633    =item RETURN
3634    
3635    Returns a list of field names in Sprout field format (I<objectName>C<(>I<fieldName>C<)>.
3636    
3637    =back
3638    
3639    =cut
3640    #: Return Type @;
3641    sub GetUsefulCrossValues {
3642        # Get the parameters.
3643        my ($self, $sourceEntity, $relationship) = @_;
3644        # Declare the return variable.
3645        my @retVal = ();
3646        # Determine the target entity for the relationship. This is whichever entity is not
3647        # the source entity. So, if the source entity is the FROM, we'll get the name of
3648        # the TO, and vice versa.
3649        my $relStructure = $self->_GetStructure($relationship);
3650        my $targetEntityType = ($relStructure->{from} eq $sourceEntity ? "to" : "from");
3651        my $targetEntity = $relStructure->{$targetEntityType};
3652      # Get the field table for the entity.      # Get the field table for the entity.
3653      my $entityFields = $self->GetFieldTable($targetEntity);      my $entityFields = $self->GetFieldTable($targetEntity);
3654      # The field table is a hash. The hash key is the field name. The hash value is a structure.      # The field table is a hash. The hash key is the field name. The hash value is a structure.
# Line 2324  Line 3760 
3760      return @retVal;      return @retVal;
3761  }  }
3762    
3763    =head2 Virtual Methods
3764    
3765    =head3 _CreatePPOIndex
3766    
3767    C<< my $index = ERDB::_CreatePPOIndex($indexObject); >>
3768    
3769    Convert the XML for an ERDB index to the XML structure for a PPO
3770    index.
3771    
3772    =over 4
3773    
3774    ERDB XML structure for an index.
3775    
3776    =item RETURN
3777    
3778    PPO XML structure for the same index.
3779    
3780    =back
3781    
3782    =cut
3783    
3784    sub _CreatePPOIndex {
3785        # Get the parameters.
3786        my ($indexObject) = @_;
3787        # The incoming index contains a list of the index fields in the IndexFields
3788        # member. We loop through it to create the index tags.
3789        my @fields = map { { label => _FixName($_->{name}) } } @{$indexObject->{IndexFields}};
3790        # Wrap the fields in attribute tags.
3791        my $retVal = { attribute => \@fields };
3792        # Return the result.
3793        return $retVal;
3794    }
3795    
3796    =head3 _CreatePPOField
3797    
3798    C<< my $fieldXML = ERDB::_CreatePPOField($fieldName, $fieldObject); >>
3799    
3800    Convert the ERDB XML structure for a field to a PPO scalar XML structure.
3801    
3802    =over 4
3803    
3804    =item fieldName
3805    
3806    Name of the scalar field.
3807    
3808    =item fieldObject
3809    
3810    ERDB XML structure describing the field.
3811    
3812    =item RETURN
3813    
3814    Returns a PPO XML structure for the same field.
3815    
3816    =back
3817    
3818    =cut
3819    
3820    sub _CreatePPOField {
3821        # Get the parameters.
3822        my ($fieldName, $fieldObject) = @_;
3823        # Get the field type.
3824        my $type = $TypeTable{$fieldObject->{type}}->{sqlType};
3825        # Fix up the field name.
3826        $fieldName = _FixName($fieldName);
3827        # Build the scalar tag.
3828        my $retVal = { label => $fieldName, type => $type };
3829        # Return the result.
3830        return $retVal;
3831    }
3832    
3833    =head3 CleanKeywords
3834    
3835    C<< my $cleanedString = $erdb->CleanKeywords($searchExpression); >>
3836    
3837    Clean up a search expression or keyword list. This is a virtual method that may
3838    be overridden by the subclass. The base-class method removes extra spaces
3839    and converts everything to lower case.
3840    
3841    =over 4
3842    
3843    =item searchExpression
3844    
3845    Search expression or keyword list to clean. Note that a search expression may
3846    contain boolean operators which need to be preserved. This includes leading
3847    minus signs.
3848    
3849    =item RETURN
3850    
3851    Cleaned expression or keyword list.
3852    
3853    =back
3854    
3855    =cut
3856    
3857    sub CleanKeywords {
3858        # Get the parameters.
3859        my ($self, $searchExpression) = @_;
3860        # Lower-case the expression and copy it into the return variable. Note that we insure we
3861        # don't accidentally end up with an undefined value.
3862        my $retVal = lc($searchExpression || "");
3863        # Remove extra spaces.
3864        $retVal =~ s/\s+/ /g;
3865        $retVal =~ s/(^\s+)|(\s+$)//g;
3866        # Return the result.
3867        return $retVal;
3868    }
3869    
3870    =head3 GetSourceObject
3871    
3872    C<< my $source = $erdb->GetSourceObject($entityName); >>
3873    
3874    Return the object to be used in loading special attributes of the specified entity. The
3875    algorithm for loading special attributes is stored in the C<DataGen> elements of the
3876    XML
3877    
3878  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3879    
3880  =head3 SetupSQL  =head3 _RelationMap
3881    
3882    C<< my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef); >>
3883    
3884    Create the relation map for an SQL query. The relation map is used by B<ERDBObject>
3885    to determine how to interpret the results of the query.
3886    
3887    =over 4
3888    
3889    =item mappedNameHashRef
3890    
3891    Reference to a hash that maps modified object names to real object names.
3892    
3893    =item mappedNameListRef
3894    
3895    Reference to a list of modified object names in the order they appear in the
3896    SELECT list.
3897    
3898    =item RETURN
3899    
3900    Returns a list of 2-tuples. Each tuple consists of an object name as used in the
3901    query followed by the actual name of that object. This enables the B<ERDBObject> to
3902    determine the order of the tables in the query and which object name belongs to each
3903    mapped object name. Most of the time these two values are the same; however, if a
3904    relation occurs twice in the query, the relation name in the field list and WHERE
3905    clause will use a mapped name (generally the actual relation name with a numeric
3906    suffix) that does not match the actual relation name.
3907    
3908    =back
3909    
3910    =cut
3911    
3912    sub _RelationMap {
3913        # Get the parameters.
3914        my ($mappedNameHashRef, $mappedNameListRef) = @_;
3915        # Declare the return variable.
3916        my @retVal = ();
3917        # Build the map.
3918        for my $mappedName (@{$mappedNameListRef}) {
3919            push @retVal, [$mappedName, $mappedNameHashRef->{$mappedName}];
3920        }
3921        # Return it.
3922        return @retVal;
3923    }
3924    
3925    
3926    =head3 _SetupSQL
3927    
3928  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
3929  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 3943 
3943  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
3944  optionally the C<ORDER BY> and C<LIMIT> clauses.  optionally the C<ORDER BY> and C<LIMIT> clauses.
3945    
3946    =item matchClause
3947    
3948    An optional full-text search clause. If specified, it will be inserted at the
3949    front of the WHERE clause. It should already be SQL-formatted; that is, the
3950    field names should be in the form I<table>C<.>I<fieldName>.
3951    
3952  =item RETURN  =item RETURN
3953    
3954  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 3961 
3961  =cut  =cut
3962    
3963  sub _SetupSQL {  sub _SetupSQL {
3964      my ($self, $objectNames, $filterClause) = @_;      my ($self, $objectNames, $filterClause, $matchClause) = @_;
3965      # 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
3966      # 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
3967      # 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 4010 
4010      # FROM name1, name2, ... nameN      # FROM name1, name2, ... nameN
4011      #      #
4012      my $suffix = "FROM " . join(', ', @fromList);      my $suffix = "FROM " . join(', ', @fromList);
4013        # Now for the WHERE. First, we need a place for the filter string.
4014        my $filterString = "";
4015        # We will also keep a list of conditions to add to the WHERE clause in order to link
4016        # entities and relationships as well as primary relations to secondary ones.
4017        my @joinWhere = ();
4018      # Check for a filter clause.      # Check for a filter clause.
4019      if ($filterClause) {      if ($filterClause) {
4020          # 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,
4021          # We create a copy of the filter string we can work with.          # We create a copy of the filter string we can work with.
4022          my $filterString = $filterClause;          $filterString = $filterClause;
4023          # Next, we sort the object names by length. This helps protect us from finding          # Next, we sort the object names by length. This helps protect us from finding
4024          # object names inside other object names when we're doing our search and replace.          # object names inside other object names when we're doing our search and replace.
4025          my @sortedNames = sort { length($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 = ();  
4026          # 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
4027          # 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
4028          # 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 4090 
4090                  }                  }
4091              }              }
4092          }          }
4093        }
4094          # 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
4095          # 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
4096          # 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
4097          # list before running through it.      # list before running through it, because we shift off the first object before
4098        # processing the rest.
4099          my @mappedObjectList = @mappedNameList;          my @mappedObjectList = @mappedNameList;
4100          my $lastMappedObject = shift @mappedObjectList;          my $lastMappedObject = shift @mappedObjectList;
4101          # Get the join table.          # Get the join table.
# Line 2517  Line 4124 
4124          # 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.
4125          # We'll put the ORDER BY / LIMIT clauses in the following variable.          # We'll put the ORDER BY / LIMIT clauses in the following variable.
4126          my $orderClause = "";          my $orderClause = "";
4127        # This is only necessary if we have a filter string in which the ORDER BY
4128        # and LIMIT clauses can live.
4129        if ($filterString) {
4130          # 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
4131          # operator so that we find the first occurrence of either verb.          # operator so that we find the first occurrence of either verb.
4132          if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {          if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {
# Line 2525  Line 4135 
4135              $orderClause = $2 . substr($filterString, $pos);              $orderClause = $2 . substr($filterString, $pos);
4136              $filterString = $1;              $filterString = $1;
4137          }          }
4138          # Add the filter and the join clauses (if any) to the SELECT command.      }
4139        # All the things that are supposed to be in the WHERE clause of the
4140        # SELECT command need to be put into @joinWhere so we can string them
4141        # together. We begin with the match clause. This is important,
4142        # because the match clause's parameter mark must precede any parameter
4143        # marks in the filter string.
4144        if ($matchClause) {
4145            push @joinWhere, $matchClause;
4146        }
4147        # Add the filter string. We put it in parentheses to avoid operator
4148        # precedence problems with the match clause or the joins.
4149          if ($filterString) {          if ($filterString) {
4150              Trace("Filter string is \"$filterString\".") if T(4);              Trace("Filter string is \"$filterString\".") if T(4);
4151              push @joinWhere, "($filterString)";              push @joinWhere, "($filterString)";
4152          }          }
4153        # String it all together into a big filter clause.
4154          if (@joinWhere) {          if (@joinWhere) {
4155              $suffix .= " WHERE " . join(' AND ', @joinWhere);              $suffix .= " WHERE " . join(' AND ', @joinWhere);
4156          }          }
4157          # Add the sort or limit clause (if any) to the SELECT command.      # Add the sort or limit clause (if any).
4158          if ($orderClause) {          if ($orderClause) {
4159              $suffix .= " $orderClause";              $suffix .= " $orderClause";
4160          }          }
     }  
4161      # Return the suffix, the mapped name list, and the mapped name hash.      # Return the suffix, the mapped name list, and the mapped name hash.
4162      return ($suffix, \@mappedNameList, \%mappedNameHash);      return ($suffix, \@mappedNameList, \%mappedNameHash);
4163  }  }
4164    
4165  =head3 GetStatementHandle  =head3 _GetStatementHandle
4166    
4167  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.
4168  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 2580  Line 4200 
4200      # Prepare the command.      # Prepare the command.
4201      my $sth = $dbh->prepare_command($command);      my $sth = $dbh->prepare_command($command);
4202      # Execute it with the parameters bound in.      # Execute it with the parameters bound in.
4203      $sth->execute(@{$params}) || Confess("SELECT error" . $sth->errstr());      $sth->execute(@{$params}) || Confess("SELECT error:  " . $sth->errstr());
4204      # Return the statement handle.      # Return the statement handle.
4205      return $sth;      return $sth;
4206  }  }
4207    
4208  =head3 GetLoadStats  =head3 _GetLoadStats
4209    
4210  Return a blank statistics object for use by the load methods.  Return a blank statistics object for use by the load methods.
4211    
# Line 2597  Line 4217 
4217      return Stats->new();      return Stats->new();
4218  }  }
4219    
4220  =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  
4221    
4222  =item this  Dump the specified relation to the specified output file in tab-delimited format.
   
 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  
   
 Dump the specified relation's to the specified output file in tab-delimited format.  
4223    
4224  This is an instance method.  This is an instance method.
4225    
# Line 2721  Line 4267 
4267      close DTXOUT;      close DTXOUT;
4268  }  }
4269    
4270  =head3 GetStructure  =head3 _GetStructure
4271    
4272  Get the data structure for a specified entity or relationship.  Get the data structure for a specified entity or relationship.
4273    
# Line 2760  Line 4306 
4306      return $retVal;      return $retVal;
4307  }  }
4308    
4309  =head3 GetRelationTable  
4310    
4311    =head3 _GetRelationTable
4312    
4313  Get the list of relations for a specified entity or relationship.  Get the list of relations for a specified entity or relationship.
4314    
# Line 2789  Line 4337 
4337      return $objectData->{Relations};      return $objectData->{Relations};
4338  }  }
4339    
4340  =head3 ValidateFieldNames  =head3 _ValidateFieldNames
4341    
4342  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
4343  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 4364 
4364          for my $object (values %{$metadata->{$section}}) {          for my $object (values %{$metadata->{$section}}) {
4365              # Loop through the object's fields.              # Loop through the object's fields.
4366              for my $fieldName (keys %{$object->{Fields}}) {              for my $fieldName (keys %{$object->{Fields}}) {
4367                  # Now we make some initial validations.                  # If this field name is invalid, set the return value to zero
4368                  if ($fieldName =~ /--/) {                  # so we know we encountered an error.
4369                      # Here we have a doubled minus sign.                  if (! ValidateFieldName($fieldName)) {
                     print STDERR "Field name $fieldName has a doubled hyphen.\n";  
                     $retVal = 0;  
                 } elsif ($fieldName !~ /^[A-Za-z]/) {  
                     # Here the field name is missing the initial letter.  
                     print STDERR "Field name $fieldName does not begin with a letter.\n";  
                     $retVal = 0;  
                 } else {  
                     # Strip out the minus signs. Everything remaining must be a letter  
                     # or digit.  
                     my $strippedName = $fieldName;  
                     $strippedName =~ s/-//g;  
                     if ($strippedName !~ /^[A-Za-z0-9]+$/) {  
                         print STDERR "Field name $fieldName contains illegal characters.\n";  
4370                          $retVal = 0;                          $retVal = 0;
4371                      }                      }
4372                  }                  }
4373              }              }
4374          }          }
     }  
4375      # If an error was found, fail.      # If an error was found, fail.
4376      if ($retVal  == 0) {      if ($retVal  == 0) {
4377          Confess("Errors found in field names.");          Confess("Errors found in field names.");
4378      }      }
4379  }  }
4380    
4381  =head3 LoadRelation  =head3 _LoadRelation
4382    
4383  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
4384  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 4438 
4438      return $retVal;      return $retVal;
4439  }  }
4440    
4441  =head3 LoadMetaData  
4442    =head3 _LoadMetaData
4443    
4444    C<< my $metadata = ERDB::_LoadMetaData($filename); >>
4445    
4446  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.
4447  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 4466 
4466  sub _LoadMetaData {  sub _LoadMetaData {
4467      # Get the parameters.      # Get the parameters.
4468      my ($filename) = @_;      my ($filename) = @_;
4469      Trace("Reading Sprout DBD from $filename.") if T(2);      Trace("Reading DBD from $filename.") if T(2);
4470      # 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
4471      # get the exact structure we want.      # get the exact structure we want.
4472      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 $filename.") if T(1);  
4473      # Before we go any farther, we need to validate the field and object names. If an error is found,      # Before we go any farther, we need to validate the field and object names. If an error is found,
4474      # the method below will fail.      # the method below will fail.
4475      _ValidateFieldNames($metadata);      _ValidateFieldNames($metadata);
# Line 3068  Line 4592 
4592              if ($found == 0) {              if ($found == 0) {
4593                  push @{$indexList}, { IndexFields => [ {name => 'id', order => 'ascending'} ] };                  push @{$indexList}, { IndexFields => [ {name => 'id', order => 'ascending'} ] };
4594              }              }
4595              # Now we need to convert the relation's index list to an index table. We begin by creating              # Attach all the indexes to the relation.
4596              # an empty table in the relation structure.              _ProcessIndexes($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++;  
             }  
4597          }          }
4598          # Finally, we add the relation structure to the entity.          # Finally, we add the relation structure to the entity.
4599          $entityStructure->{Relations} = $relationTable;          $entityStructure->{Relations} = $relationTable;
# Line 3092  Line 4607 
4607          _FixupFields($relationshipStructure, $relationshipName, 2, 3);          _FixupFields($relationshipStructure, $relationshipName, 2, 3);
4608          # Format a description for the FROM field.          # Format a description for the FROM field.
4609          my $fromEntity = $relationshipStructure->{from};          my $fromEntity = $relationshipStructure->{from};
4610          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].";
4611          # Get the FROM entity's key type.          # Get the FROM entity's key type.
4612          my $fromType = $entityList->{$fromEntity}->{keyType};          my $fromType = $entityList->{$fromEntity}->{keyType};
4613          # Add the FROM field.          # Add the FROM field.
# Line 3102  Line 4617 
4617                                                      PrettySort => 1});                                                      PrettySort => 1});
4618          # Format a description for the TO field.          # Format a description for the TO field.
4619          my $toEntity = $relationshipStructure->{to};          my $toEntity = $relationshipStructure->{to};
4620          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].";
4621          # Get the TO entity's key type.          # Get the TO entity's key type.
4622          my $toType = $entityList->{$toEntity}->{keyType};          my $toType = $entityList->{$toEntity}->{keyType};
4623          # Add the TO field.          # Add the TO field.
# Line 3114  Line 4629 
4629          my $thisRelation = { Fields => _ReOrderRelationTable($relationshipStructure->{Fields}),          my $thisRelation = { Fields => _ReOrderRelationTable($relationshipStructure->{Fields}),
4630                               Indexes => { } };                               Indexes => { } };
4631          $relationshipStructure->{Relations} = { $relationshipName => $thisRelation };          $relationshipStructure->{Relations} = { $relationshipName => $thisRelation };
4632    
4633            # Add the alternate indexes (if any). This MUST be done before the FROM and
4634            # TO indexes, because it erases the relation's index list.
4635            if (exists $relationshipStructure->{Indexes}) {
4636                _ProcessIndexes($relationshipStructure->{Indexes}, $thisRelation);
4637            }
4638            # Add the relation to the master table.
4639          # Create the FROM and TO indexes.          # Create the FROM and TO indexes.
4640          _CreateRelationshipIndex("From", $relationshipName, $relationshipStructure);          _CreateRelationshipIndex("From", $relationshipName, $relationshipStructure);
4641          _CreateRelationshipIndex("To", $relationshipName, $relationshipStructure);          _CreateRelationshipIndex("To", $relationshipName, $relationshipStructure);
         # Add the relation to the master table.  
4642          $masterRelationTable{$relationshipName} = $thisRelation;          $masterRelationTable{$relationshipName} = $thisRelation;
4643      }      }
4644      # Now store the master relation table in the metadata structure.      # Now store the master relation table in the metadata structure.
# Line 3205  Line 4726 
4726                      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);
4727                      # Join from the left.                      # Join from the left.
4728                      $joinTable{"$relationshipName/$otherName"} =                      $joinTable{"$relationshipName/$otherName"} =
4729                          "$linkField = $otherName.from_link";                          "$linkField = $otherName.from_link";
4730                      # Join from the right.                      # Join from the right.
4731                      $joinTable{"$otherName/$relationshipName"} =                      $joinTable{"$otherName/$relationshipName"} =
4732                          "$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;  
4733          }          }
4734      }      }
4735      # Return the result.          }
4736      return $retVal;          # Create entity joins for the recursive relationships. Unlike the non-recursive
4737            # joins, the direction makes a difference with the recursive joins. This can give
4738            # rise to situations where we can't create the path we want; however, it is always
4739            # possible to get the same effect using multiple queries.
4740            for my $relationshipName (@bothList) {
4741                Trace("Setting up entity joins to recursive relationship $relationshipName with $entityName.") if T(metadata => 4);
4742                # Join to the entity from each direction.
4743                $joinTable{"$entityName/$relationshipName"} =
4744                    "$entityName.id = $relationshipName.from_link";
4745                $joinTable{"$relationshipName/$entityName"} =
4746                    "$relationshipName.to_link = $entityName.id";
4747            }
4748        }
4749        # Add the join table to the structure.
4750        $metadata->{Joins} = \%joinTable;
4751        # Return the slurped and fixed-up structure.
4752        return $metadata;
4753  }  }
4754    
4755  =head3 CreateRelationshipIndex  =head3 _CreateRelationshipIndex
4756    
4757  Create an index for a relationship's relation.  Create an index for a relationship's relation.
4758    
# Line 3313  Line 4794 
4794          $newIndex->{Unique} = 'true';          $newIndex->{Unique} = 'true';
4795      }      }
4796      # Add the index to the relation.      # Add the index to the relation.
4797      _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);      _AddIndex("idx$indexKey", $relationStructure, $newIndex);
4798    }
4799    
4800    =head3 _ProcessIndexes
4801    
4802    C<< ERDB::_ProcessIndexes($indexList, $relation); >>
4803    
4804    Build the data structures for the specified indexes in the specified relation.
4805    
4806    =over 4
4807    
4808    =item indexList
4809    
4810    Reference to a list of indexes. Each index is a hash reference containing an optional
4811    C<Notes> value that describes the index and an C<IndexFields> value that is a reference
4812    to a list of index field structures. An index field structure, in turn, is a reference
4813    to a hash that contains a C<name> attribute for the field name and an C<order>
4814    attribute that specifies either C<ascending> or C<descending>. In this sense the
4815    index list encapsulates the XML C<Indexes> structure in the database definition.
4816    
4817    =item relation
4818    
4819    The structure that describes the current relation. The new index descriptors will
4820    be stored in the structure's C<Indexes> member. Any previous data in the structure
4821    will be lost.
4822    
4823    =back
4824    
4825    =cut
4826    
4827    sub _ProcessIndexes {
4828        # Get the parameters.
4829        my ($indexList, $relation) = @_;
4830        # Now we need to convert the relation's index list to an index table. We begin by creating
4831        # an empty table in the relation structure.
4832        $relation->{Indexes} = { };
4833        # Loop through the indexes.
4834        my $count = 0;
4835        for my $index (@{$indexList}) {
4836            # Add this index to the index table.
4837            _AddIndex("idx$count", $relation, $index);
4838            # Increment the counter so that the next index has a different name.
4839            $count++;
4840        }
4841  }  }
4842    
4843  =head3 AddIndex  =head3 _AddIndex
4844    
4845  Add an index to a relation structure.  Add an index to a relation structure.
4846    
# Line 3362  Line 4886 
4886      $relationStructure->{Indexes}->{$indexName} = $newIndex;      $relationStructure->{Indexes}->{$indexName} = $newIndex;
4887  }  }
4888    
4889  =head3 FixupFields  =head3 _FixupFields
4890    
4891  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
4892  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 4924 
4924          # Here it doesn't, so we create a new one.          # Here it doesn't, so we create a new one.
4925          $structure->{Fields} = { };          $structure->{Fields} = { };
4926      } else {      } else {
4927          # 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
4928            # create a list for stashing them.
4929            my @textFields = ();
4930            # Loop through the fields.
4931          my $fieldStructures = $structure->{Fields};          my $fieldStructures = $structure->{Fields};
4932          for my $fieldName (keys %{$fieldStructures}) {          for my $fieldName (keys %{$fieldStructures}) {
4933              Trace("Processing field $fieldName of $defaultRelationName.") if T(4);              Trace("Processing field $fieldName of $defaultRelationName.") if T(4);
# Line 3409  Line 4936 
4936              my $type = $fieldData->{type};              my $type = $fieldData->{type};
4937              # Plug in a relation name if it is needed.              # Plug in a relation name if it is needed.
4938              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });
4939              # Plug in a data generator if we need one.              # Check for searchability.
4940              if (!exists $fieldData->{DataGen}) {              if ($fieldData->{searchable}) {
4941                  # The data generator will use the default for the field's type.                  # Only allow this for a primary relation.
4942                  $fieldData->{DataGen} = { content => $TypeTable{$type}->{dataGen} };                  if ($fieldData->{relation} ne $defaultRelationName) {
4943                        Confess("Field $fieldName of $defaultRelationName is in secondary relations and cannot be searchable.");
4944                    } else {
4945                        push @textFields, $fieldName;
4946                    }
4947              }              }
             # Plug in the defaults for the optional data generation parameters.  
             Tracer::MergeOptions($fieldData->{DataGen}, { testCount => 1, pass => 0 });  
4948              # Add the PrettySortValue.              # Add the PrettySortValue.
4949              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);
4950          }          }
4951            # If there are searchable fields, remember the fact.
4952            if (@textFields) {
4953                $structure->{searchFields} = \@textFields;
4954            }
4955      }      }
4956  }  }
4957    
4958  =head3 FixName  =head3 _FixName
4959    
4960  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.
4961    
# Line 3451  Line 4984 
4984      return $fieldName;      return $fieldName;
4985  }  }
4986    
4987  =head3 FixNames  =head3 _FixNames
4988    
4989  Fix all the field names in a list.  Fix all the field names in a list.
4990    
# Line 3482  Line 5015 
5015      return @result;      return @result;
5016  }  }
5017    
5018  =head3 AddField  =head3 _AddField
5019    
5020  Add a field to a field list.  Add a field to a field list.
5021    
# Line 3517  Line 5050 
5050      $fieldList->{$fieldName} = $fieldStructure;      $fieldList->{$fieldName} = $fieldStructure;
5051  }  }
5052    
5053  =head3 ReOrderRelationTable  =head3 _ReOrderRelationTable
5054    
5055  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
5056  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 5111 
5111    
5112  }  }
5113    
5114  =head3 IsPrimary  =head3 _IsPrimary
5115    
5116  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
5117  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 5147 
5147      return $retVal;      return $retVal;
5148  }  }
5149    
5150  =head3 FindRelation  =head3 _FindRelation
5151    
5152  Return the descriptor for the specified relation.  Return the descriptor for the specified relation.
5153    
# Line 3645  Line 5178 
5178    
5179  =head2 HTML Documentation Utility Methods  =head2 HTML Documentation Utility Methods
5180    
5181  =head3 ComputeRelationshipSentence  =head3 _ComputeRelationshipSentence
5182    
5183  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
5184  two related entities and an arity indicator.  two related entities and an arity indicator.
# Line 3683  Line 5216 
5216      return $result;      return $result;
5217  }  }
5218    
5219  =head3 ComputeRelationshipHeading  =head3 _ComputeRelationshipHeading
5220    
5221  The relationship heading is the L<relationship sentence|/ComputeRelationshipSentence> with the entity  The relationship heading is the L<relationship sentence|/ComputeRelationshipSentence> with the entity
5222  names hyperlinked to the appropriate entity sections of the document.  names hyperlinked to the appropriate entity sections of the document.
# Line 3720  Line 5253 
5253      return $result;      return $result;
5254  }  }
5255    
5256  =head3 ShowRelationTable  =head3 _ShowRelationTable
5257    
5258  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
5259  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 5303 
5303          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";
5304          # Add any note text.          # Add any note text.
5305          if (my $note = $indexData->{Notes}) {          if (my $note = $indexData->{Notes}) {
5306              $htmlString .= "<li>" . _HTMLNote($note->{content}) . "</li>\n";              $htmlString .= "<li>" . HTMLNote($note->{content}) . "</li>\n";
5307          }          }
5308          # Add the fiield list.          # Add the fiield list.
5309          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";
# Line 3781  Line 5314 
5314      $htmlString .= "</ul>\n";      $htmlString .= "</ul>\n";
5315  }  }
5316    
5317  =head3 OpenFieldTable  =head3 _OpenFieldTable
5318    
5319  This method creates the header string for the field table generated by L</ShowMetaData>.  This method creates the header string for the field table generated by L</ShowMetaData>.
5320    
# Line 3806  Line 5339 
5339      return _OpenTable($tablename, 'Field', 'Type', 'Description');      return _OpenTable($tablename, 'Field', 'Type', 'Description');
5340  }  }
5341    
5342  =head3 OpenTable  =head3 _OpenTable
5343    
5344  This method creates the header string for an HTML table.  This method creates the header string for an HTML table.
5345    
# Line 3836  Line 5369 
5369      # Compute the number of columns.      # Compute the number of columns.
5370      my $colCount = @colNames;      my $colCount = @colNames;
5371      # Generate the title row.      # Generate the title row.
5372      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";
5373      # Loop through the columns, adding the column header rows.      # Loop through the columns, adding the column header rows.
5374      $htmlString .= "<tr>";      $htmlString .= "<tr>";
5375      for my $colName (@colNames) {      for my $colName (@colNames) {
# Line 3846  Line 5379 
5379      return $htmlString;      return $htmlString;
5380  }  }
5381    
5382  =head3 CloseTable  =head3 _CloseTable
5383    
5384  This method returns the HTML for closing a table.  This method returns the HTML for closing a table.
5385    
# Line 3855  Line 5388 
5388  =cut  =cut
5389    
5390  sub _CloseTable {  sub _CloseTable {
5391      return "</table></p>\n";      return "</table>\n";
5392  }  }
5393    
5394  =head3 ShowField  =head3 _ShowField
5395    
5396  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.
5397    
# Line 3885  Line 5418 
5418      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>";
5419      # If we have content, add it as a third column.      # If we have content, add it as a third column.
5420      if (exists $fieldData->{Notes}) {      if (exists $fieldData->{Notes}) {
5421          $htmlString .= "<td>" . _HTMLNote($fieldData->{Notes}->{content}) . "</td>";          $htmlString .= "<td>" . HTMLNote($fieldData->{Notes}->{content}) . "</td>";
5422      }      }
5423      # Close off the row.      # Close off the row.
5424      $htmlString .= "</tr>\n";      $htmlString .= "</tr>\n";
# Line 3893  Line 5426 
5426      return $htmlString;      return $htmlString;
5427  }  }
5428    
 =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;  
 }  
   
5429  1;  1;

Legend:
Removed from v.1.55  
changed lines
  Added in v.1.90

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3