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

Diff of /Sprout/ERDB.pm

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

revision 1.61, Mon Jul 10 09:05:17 2006 UTC revision 1.92, Mon Jun 11 18:51:23 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 190  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 209  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 242  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 286  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 320  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. "sort" is the key modifier for the sort command.  # and "indexMod", if non-zero, is the number of characters to use when the field is specified in an
343  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",  dataGen => "StringGen('A')" },  # index
344                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n", dataGen => "IntGen(0, 99999999)" },  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",
345                    counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n", dataGen => "IntGen(0, 99999999)" },                                 indexMod =>   0, notes => "single ASCII character"},
346                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, sort => "",  dataGen => "StringGen(IntGen(10,250))" },                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n",
347                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, sort => "",  dataGen => "StringGen(IntGen(80,1000))" },                                 indexMod =>   0, notes => "signed 32-bit integer"},
348                    date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, sort => "n", dataGen => "DateGen(-7, 7, IntGen(0,1400))" },                    counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n",
349                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, sort => "g", dataGen => "FloatGen(0.0, 100.0)" },                                 indexMod =>   0, notes => "unsigned 32-bit integer"},
350                    boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, sort => "n", dataGen => "IntGen(0, 1)" },                    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, sort => "",  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, sort => "",  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, sort => "",  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, sort => "",  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, sort => "",  dataGen => "StringGen(IntGen(10,160))" },                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",
374                                   indexMod =>   0, notes => "character string, 0 to 160 characters"},
375                     'long-string' =>
376                                 { sqlType => 'VARCHAR(500)',       maxLen => 500,          avglen => 255, sort => "",
377                                   indexMod =>   0, notes => "character string, 0 to 500 characters"},
378                  );                  );
379    
380  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 349  Line 383 
383                     'MM' => 'many-to-many'                     'MM' => 'many-to-many'
384                   );                   );
385    
386  # Table for interpreting string patterns.  # Options for XML input and output.
387    
388    my %XmlOptions = (GroupTags =>  { Relationships => 'Relationship',
389                                      Entities => 'Entity',
390                                      Fields => 'Field',
391                                      Indexes => 'Index',
392                                      IndexFields => 'IndexField'
393                                    },
394                      KeyAttr =>    { Relationship => 'name',
395                                      Entity => 'name',
396                                      Field => 'name'
397                                    },
398                      SuppressEmpty => 1,
399                     );
400    
401  my %PictureTable = ( 'A' => "abcdefghijklmnopqrstuvwxyz",  my %XmlInOpts  = (
402                       '9' => "0123456789",                    ForceArray => ['Field', 'Index', 'IndexField', 'Relationship', 'Entity'],
403                       'X' => "abcdefghijklmnopqrstuvwxyz0123456789",                    ForceContent => 1,
404                       'V' => "aeiou",                    NormalizeSpace => 2,
405                       'K' => "bcdfghjklmnoprstvwxyz"                   );
406    my %XmlOutOpts = (
407                      RootName => 'Database',
408                      XMLDecl => 1,
409                     );                     );
410    
411    
412  =head2 Public Methods  =head2 Public Methods
413    
414  =head3 new  =head3 new
# Line 498  Line 549 
549          my $entityData = $entityList->{$key};          my $entityData = $entityList->{$key};
550          # If there's descriptive text, display it.          # If there's descriptive text, display it.
551          if (my $notes = $entityData->{Notes}) {          if (my $notes = $entityData->{Notes}) {
552              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
553          }          }
554          # Now we want a list of the entity's relationships. First, we set up the relationship subsection.          # See if we need a list of the entity's relationships.
555            my $relCount = keys %{$relationshipList};
556            if ($relCount > 0) {
557                # First, we set up the relationship subsection.
558          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
559          # Loop through the relationships.          # Loop through the relationships.
560          for my $relationship (sort keys %{$relationshipList}) {          for my $relationship (sort keys %{$relationshipList}) {
# Line 516  Line 570 
570          }          }
571          # Close off the relationship list.          # Close off the relationship list.
572          $retVal .= "</ul>\n";          $retVal .= "</ul>\n";
573            }
574          # Get the entity's relations.          # Get the entity's relations.
575          my $relationList = $entityData->{Relations};          my $relationList = $entityData->{Relations};
576          # Create a header for the relation subsection.          # Create a header for the relation subsection.
# Line 555  Line 610 
610          $retVal .= "</p>\n";          $retVal .= "</p>\n";
611          # If there are notes on this relationship, display them.          # If there are notes on this relationship, display them.
612          if (my $notes = $relationshipStructure->{Notes}) {          if (my $notes = $relationshipStructure->{Notes}) {
613              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
614          }          }
615          # Generate the relationship's relation table.          # Generate the relationship's relation table.
616          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
# Line 602  Line 657 
657      return Data::Dumper::Dumper($self->{_metaData});      return Data::Dumper::Dumper($self->{_metaData});
658  }  }
659    
660    =head3 CreatePPO
661    
662    C<< ERDB::CreatePPO($erdbXMLFile, $ppoXMLFile); >>
663    
664    Create a PPO XML file from an ERDB data definition XML file. At the
665    current time, the PPO XML file can be used to create a database with
666    similar functionality. Eventually, the PPO will be able to use the
667    created XML to access the live ERDB database.
668    
669    =over 4
670    
671    =item erdbXMLFile
672    
673    Name of the XML data definition file for the ERDB database. This
674    file must exist.
675    
676    =item ppoXMLFile
677    
678    Output file for the PPO XML definition. If this file exists, it
679    will be overwritten.
680    
681    =back
682    
683    =cut
684    
685    sub CreatePPO {
686        # Get the parameters.
687        my ($erdbXMLFile, $ppoXMLFile) = @_;
688        # First, we want to slurp in the ERDB XML file in its raw form.
689        my $xml = ReadMetaXML($erdbXMLFile);
690        # Create a variable to hold all of the objects in the PPO project.
691        my @objects = ();
692        # Get the relationship hash.
693        my $relationships = $xml->{Relationships};
694        # Loop through the entities.
695        my $entities = $xml->{Entities};
696        for my $entityName (keys %{$entities}) {
697            # Get the entity's data structures.
698            my $entityObject = $entities->{$entityName};
699            # We put the object's fields in here, according to their type.
700            my (@object_refs, @scalars, @indexes, @arrays);
701            # Create the ID field for the entity. We get the key type from the
702            # entity object and compute the corresponding SQL type.
703            my $type = $TypeTable{$entityObject->{keyType}}->{sqlType};
704            push @scalars, { label => 'id', type => $type };
705            # Loop through the entity fields.
706            for my $fieldName ( keys %{$entityObject->{Fields}} ) {
707                # Get the field object.
708                my $fieldObject = $entityObject->{Fields}->{$fieldName};
709                # Convert it to a scalar tag.
710                my $scalar = _CreatePPOField($fieldName, $fieldObject);
711                # If we have a relation, this field is stored in an array.
712                # otherwise, it is a scalar. The array tag has scalars
713                # stored as an XML array. In ERDB, there is only ever one,
714                # but PPO can have more.
715                my $relation = $fieldObject->{relation};
716                if ($relation) {
717                    push @arrays, { scalar => [$scalar] };
718                } else {
719                    push @scalars, $scalar;
720                }
721            }
722            # Loop through the relationships. If this entity is the to-entity
723            # on a relationship of 1M arity, then it is implemented as a PPO
724            # object reference.
725            for my $relationshipName (keys %{$relationships}) {
726                # Get the relationship data.
727                my $relationshipData = $relationships->{$relationshipName};
728                # If we have a from for this entity and an arity of 1M, we
729                # have an object reference.
730                if ($relationshipData->{to} eq $entityName &&
731                    $relationshipData->{arity} eq '1M') {
732                    # Build the object reference tag.
733                    push @object_refs, { label => $relationshipName,
734                                         type => $relationshipData->{from} };
735                }
736            }
737            # Create the indexes.
738            my $indexList = $entityObject->{Indexes};
739            push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
740            # Build the object XML tree.
741            my $object = { label => $entityName,
742                           object_ref => \@object_refs,
743                           scalar => \@scalars,
744                           index => \@indexes,
745                           array => \@arrays
746                          };
747            # Push the object onto the objects list.
748            push @objects, $object;
749        }
750        # Loop through the relationships, searching for MMs. The 1Ms were
751        # already handled by the entity search above.
752        for my $relationshipName (keys %{$relationships}) {
753            # Get this relationship's object.
754            my $relationshipObject = $relationships->{$relationshipName};
755            # Only proceed if it's many-to-many.
756            if ($relationshipObject->{arity} eq 'MM') {
757                # Create the tag lists for the relationship object.
758                my (@object_refs, @scalars, @indexes);
759                # The relationship will be created as an object with object
760                # references for its links to the participating entities.
761                my %links = ( from_link => $relationshipObject->{from},
762                              to_link => $relationshipObject->{to} );
763                for my $link (keys %links) {
764                    # Create an object_ref tag for this piece of the
765                    # relationship (from or to).
766                    my $object_ref = { label => $link,
767                                       type => $links{$link} };
768                    push @object_refs, $object_ref;
769                }
770                # Loop through the intersection data fields, creating scalar tags.
771                # There are no fancy array tags in a relationship.
772                for my $fieldName (keys %{$relationshipObject->{Fields}}) {
773                    my $fieldObject = $relationshipObject->{Fields}->{$fieldName};
774                    push @scalars, _CreatePPOField($fieldName, $fieldObject);
775                }
776                # Finally, the indexes: currently we cannot support the to-index and
777                # from-index in PPO, so we just process the alternate indexes.
778                my $indexList = $relationshipObject->{Indexes};
779                push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
780                # Wrap up all the stuff about this relationship.
781                my $object = { label => $relationshipName,
782                               scalar => \@scalars,
783                               object_ref => \@object_refs,
784                               index => \@indexes
785                             };
786                # Push it into the object list.
787                push @objects, $object;
788            }
789        }
790        # Compute a title.
791        my $title;
792        if ($erdbXMLFile =~ /(\/|^)([^\/]+)DBD\.xml/) {
793            # Here we have a standard file name we can use for a title.
794            $title = $2;
795        } else {
796            # Here the file name is non-standard, so we carve up the
797            # database title.
798            $title = $xml->{Title}->{content};
799            $title =~ s/\s\.,//g;
800        }
801        # Wrap up the XML as a project.
802        my $ppoXML = { project => { label => $title,
803                                    object => \@objects }};
804        # Write out the results.
805        my $ppoString = XML::Simple::XMLout($ppoXML,
806                                            AttrIndent => 1,
807                                            KeepRoot => 1);
808        Tracer::PutFile($ppoXMLFile, [ $ppoString ]);
809    }
810    
811    =head3 FindIndexForEntity
812    
813    C<< my $indexFound = ERDB::FindIndexForEntity($xml, $entityName, $attributeName); >>
814    
815    This method locates the entry in an entity's index list that begins with the
816    specified attribute name. If the entity has no index list, one will be
817    created. This method works on raw XML, not a live ERDB object.
818    
819    =over 4
820    
821    =item xml
822    
823    The raw XML structure defining the database.
824    
825    =item entityName
826    
827    The name of the relevant entity.
828    
829    =item attributeName
830    
831    The name of the attribute relevant to the search.
832    
833    =item RETURN
834    
835    The numerical index in the index list of the index entry for the specified entity and
836    attribute, or C<undef> if no such index exists.
837    
838    =back
839    
840    =cut
841    
842    sub FindIndexForEntity {
843        # Get the parameters.
844        my ($xml, $entityName, $attributeName) = @_;
845        # Declare the return variable.
846        my $retVal;
847        # Get the named entity.
848        my $entityData = $xml->{Entities}->{$entityName};
849        if (! $entityData) {
850            Confess("Entity $entityName not found in DBD structure.");
851        } else {
852            # Insure it has an index list.
853            if (! exists $entityData->{Indexes}) {
854                $entityData->{Indexes} = [];
855            } else {
856                # Search for the desired index.
857                my $indexList = $entityData->{Indexes};
858                my $n = scalar @{$indexList};
859                Trace("Searching $n indexes in index list for $entityName.") if T(2);
860                # We use an indexed FOR here because we're returning an
861                # index number instead of an object. We do THAT so we can
862                # delete the index from the list if needed.
863                for (my $i = 0; $i < $n && !defined($retVal); $i++) {
864                    my $index = $indexList->[$i];
865                    my $fields = $index->{IndexFields};
866                    # Technically this IF should be safe (that is, we are guaranteed
867                    # the existence of a "$fields->[0]"), because when we load the XML
868                    # we have SuppressEmpty specified.
869                    if ($fields->[0]->{name} eq $attributeName) {
870                        $retVal = $i;
871                    }
872                }
873            }
874        }
875        Trace("Index for $attributeName of $entityName found at position $retVal.") if defined($retVal) && T(3);
876        Trace("Index for $attributeName not found in $entityName.") if !defined($retVal) && T(3);
877        # Return the result.
878        return $retVal;
879    }
880    
881  =head3 CreateTables  =head3 CreateTables
882    
883  C<< $erdb->CreateTables(); >>  C<< $erdb->CreateTables(); >>
# Line 621  Line 897 
897      # Loop through the relations.      # Loop through the relations.
898      for my $relationName (@relNames) {      for my $relationName (@relNames) {
899          # Create a table for this relation.          # Create a table for this relation.
900          $self->CreateTable($relationName);          $self->CreateTable($relationName, 1);
901          Trace("Relation $relationName created.") if T(2);          Trace("Relation $relationName created.") if T(2);
902      }      }
903  }  }
# Line 689  Line 965 
965      Trace("Creating table $relationName: $fieldThing") if T(2);      Trace("Creating table $relationName: $fieldThing") if T(2);
966      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);
967      Trace("Relation $relationName created in database.") if T(2);      Trace("Relation $relationName created in database.") if T(2);
968      # If we want to build the indexes, we do it here.      # If we want to build the indexes, we do it here. Note that the full-text search
969        # index will not be built until the table has been loaded.
970      if ($indexFlag) {      if ($indexFlag) {
971          $self->CreateIndex($relationName);          $self->CreateIndex($relationName);
972      }      }
# Line 740  Line 1017 
1017              my $oldString = $fieldList->[$i];              my $oldString = $fieldList->[$i];
1018              if (length($oldString) > $maxLen) {              if (length($oldString) > $maxLen) {
1019                  # Here it's too big, so we truncate it.                  # Here it's too big, so we truncate it.
1020                  Trace("Truncating field $i in relation $relName to $maxLen characters from \"$oldString\".") if T(1);                  Trace("Truncating field $i ($fieldTypes->[$i]->{name}) in relation $relName to $maxLen characters from \"$oldString\".") if T(1);
1021                  $fieldList->[$i] = substr $oldString, 0, $maxLen;                  $fieldList->[$i] = substr $oldString, 0, $maxLen;
1022                  $retVal++;                  $retVal++;
1023              }              }
# Line 846  Line 1123 
1123      for my $indexName (keys %{$indexHash}) {      for my $indexName (keys %{$indexHash}) {
1124          my $indexData = $indexHash->{$indexName};          my $indexData = $indexHash->{$indexName};
1125          # Get the index's field list.          # Get the index's field list.
1126          my @fieldList = _FixNames(@{$indexData->{IndexFields}});          my @rawFields = @{$indexData->{IndexFields}};
1127            # Get a hash of the relation's field types.
1128            my %types = map { $_->{name} => $_->{type} } @{$relationData->{Fields}};
1129            # We need to check for text fields so we can append a length limitation for them. To do
1130            # that, we need the relation's field list.
1131            my $relFields = $relationData->{Fields};
1132            for (my $i = 0; $i <= $#rawFields; $i++) {
1133                # Get the field type.
1134                my $field = $rawFields[$i];
1135                my $type = $types{$field};
1136                # Ask if it requires using prefix notation for the index.
1137                my $mod = $TypeTable{$type}->{indexMod};
1138                Trace("Field $field ($i) in $relationName has type $type and indexMod $mod.") if T(3);
1139                if ($mod) {
1140                    # Append the prefix length to the field name,
1141                    $rawFields[$i] .= "($mod)";
1142                }
1143            }
1144            my @fieldList = _FixNames(@rawFields);
1145          my $flds = join(', ', @fieldList);          my $flds = join(', ', @fieldList);
1146          # Get the index's uniqueness flag.          # Get the index's uniqueness flag.
1147          my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
1148          # Create the index.          # Create the index.
1149          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
1150                                      flds => $flds, unique => $unique);                                      flds => $flds, kind => $unique);
1151          if ($rv) {          if ($rv) {
1152              Trace("Index created: $indexName for $relationName ($flds)") if T(1);              Trace("Index created: $indexName for $relationName ($flds)") if T(1);
1153          } else {          } else {
# Line 861  Line 1156 
1156      }      }
1157  }  }
1158    
1159    =head3 GetSecondaryFields
1160    
1161    C<< my %fieldTuples = $erdb->GetSecondaryFields($entityName); >>
1162    
1163    This method will return a list of the name and type of each of the secondary
1164    fields for a specified entity. Secondary fields are stored in two-column tables
1165    in addition to the primary entity table. This enables the field to have no value
1166    or to have multiple values.
1167    
1168    =over 4
1169    
1170    =item entityName
1171    
1172    Name of the entity whose secondary fields are desired.
1173    
1174    =item RETURN
1175    
1176    Returns a hash mapping the field names to their field types.
1177    
1178    =back
1179    
1180    =cut
1181    
1182    sub GetSecondaryFields {
1183        # Get the parameters.
1184        my ($self, $entityName) = @_;
1185        # Declare the return variable.
1186        my %retVal = ();
1187        # Look for the entity.
1188        my $table = $self->GetFieldTable($entityName);
1189        # Loop through the fields, pulling out the secondaries.
1190        for my $field (sort keys %{$table}) {
1191            if ($table->{$field}->{relation} ne $entityName) {
1192                # Here we have a secondary field.
1193                $retVal{$field} = $table->{$field}->{type};
1194            }
1195        }
1196        # Return the result.
1197        return %retVal;
1198    }
1199    
1200    =head3 GetFieldRelationName
1201    
1202    C<< my $name = $erdb->GetFieldRelationName($objectName, $fieldName); >>
1203    
1204    Return the name of the relation containing a specified field.
1205    
1206    =over 4
1207    
1208    =item objectName
1209    
1210    Name of the entity or relationship containing the field.
1211    
1212    =item fieldName
1213    
1214    Name of the relevant field in that entity or relationship.
1215    
1216    =item RETURN
1217    
1218    Returns the name of the database relation containing the field, or C<undef> if
1219    the field does not exist.
1220    
1221    =back
1222    
1223    =cut
1224    
1225    sub GetFieldRelationName {
1226        # Get the parameters.
1227        my ($self, $objectName, $fieldName) = @_;
1228        # Declare the return variable.
1229        my $retVal;
1230        # Get the object field table.
1231        my $table = $self->GetFieldTable($objectName);
1232        # Only proceed if the field exists.
1233        if (exists $table->{$fieldName}) {
1234            # Determine the name of the relation that contains this field.
1235            $retVal = $table->{$fieldName}->{relation};
1236        }
1237        # Return the result.
1238        return $retVal;
1239    }
1240    
1241    =head3 DeleteValue
1242    
1243    C<< my $numDeleted = $erdb->DeleteValue($entityName, $id, $fieldName, $fieldValue); >>
1244    
1245    Delete secondary field values from the database. This method can be used to delete all
1246    values of a specified field for a particular entity instance, or only a single value.
1247    
1248    Secondary fields are stored in two-column relations separate from an entity's primary
1249    table, and as a result a secondary field can legitimately have no value or multiple
1250    values. Therefore, it makes sense to talk about deleting secondary fields where it
1251    would not make sense for primary fields.
1252    
1253    =over 4
1254    
1255    =item entityName
1256    
1257    Name of the entity from which the fields are to be deleted.
1258    
1259    =item id
1260    
1261    ID of the entity instance to be processed. If the instance is not found, this
1262    method will have no effect. If C<undef> is specified, all values for all of
1263    the entity instances will be deleted.
1264    
1265    =item fieldName
1266    
1267    Name of the field whose values are to be deleted.
1268    
1269    =item fieldValue (optional)
1270    
1271    Value to be deleted. If not specified, then all values of the specified field
1272    will be deleted for the entity instance. If specified, then only the values which
1273    match this parameter will be deleted.
1274    
1275    =item RETURN
1276    
1277    Returns the number of rows deleted.
1278    
1279    =back
1280    
1281    =cut
1282    
1283    sub DeleteValue {
1284        # Get the parameters.
1285        my ($self, $entityName, $id, $fieldName, $fieldValue) = @_;
1286        # Declare the return value.
1287        my $retVal = 0;
1288        # We need to set up an SQL command to do the deletion. First, we
1289        # find the name of the field's relation.
1290        my $table = $self->GetFieldTable($entityName);
1291        my $field = $table->{$fieldName};
1292        my $relation = $field->{relation};
1293        # Make sure this is a secondary field.
1294        if ($relation eq $entityName) {
1295            Confess("Cannot delete values of $fieldName for $entityName.");
1296        } else {
1297            # Set up the SQL command to delete all values.
1298            my $sql = "DELETE FROM $relation";
1299            # Build the filter.
1300            my @filters = ();
1301            my @parms = ();
1302            # Check for a filter by ID.
1303            if (defined $id) {
1304                push @filters, "id = ?";
1305                push @parms, $id;
1306            }
1307            # Check for a filter by value.
1308            if (defined $fieldValue) {
1309                push @filters, "$fieldName = ?";
1310                push @parms, $fieldValue;
1311            }
1312            # Append the filters to the command.
1313            if (@filters) {
1314                $sql .= " WHERE " . join(" AND ", @filters);
1315            }
1316            # Execute the command.
1317            my $dbh = $self->{_dbh};
1318            $retVal = $dbh->SQL($sql, 0, @parms);
1319        }
1320        # Return the result.
1321        return $retVal;
1322    }
1323    
1324  =head3 LoadTables  =head3 LoadTables
1325    
1326  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>
# Line 955  Line 1415 
1415      return sort keys %{$entityList};      return sort keys %{$entityList};
1416  }  }
1417    
1418    =head3 GetDataTypes
1419    
1420    C<< my %types = ERDB::GetDataTypes(); >>
1421    
1422    Return a table of ERDB data types. The table returned is a hash of hashes.
1423    The keys of the big hash are the datatypes. Each smaller hash has several
1424    values used to manage the data. The most interesting is the SQL type (key
1425    C<sqlType>) and the descriptive node (key C<notes>).
1426    
1427    Note that changing the values in the smaller hashes will seriously break
1428    things, so this data should be treated as read-only.
1429    
1430    =cut
1431    
1432    sub GetDataTypes {
1433        return %TypeTable;
1434    }
1435    
1436    
1437  =head3 IsEntity  =head3 IsEntity
1438    
1439  C<< my $flag = $erdb->IsEntity($entityName); >>  C<< my $flag = $erdb->IsEntity($entityName); >>
# Line 1099  Line 1578 
1578      return $retVal;      return $retVal;
1579  }  }
1580    
1581    
1582    
1583    =head3 Search
1584    
1585    C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>
1586    
1587    Perform a full text search with filtering. The search will be against a specified object
1588    in the object name list. That object will get an extra field containing the search
1589    relevance. Note that except for the search expression, the parameters of this method are
1590    the same as those for L</Get> and follow the same rules.
1591    
1592    =over 4
1593    
1594    =item searchExpression
1595    
1596    Boolean search expression for the text fields of the target object. The default mode for
1597    a Boolean search expression is OR, but we want the default to be AND, so we will
1598    add a C<+> operator to each word with no other operator before it.
1599    
1600    =item idx
1601    
1602    Index in the I<$objectNames> list of the table to be searched in full-text mode.
1603    
1604    =item objectNames
1605    
1606    List containing the names of the entity and relationship objects to be retrieved.
1607    
1608    =item filterClause
1609    
1610    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1611    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
1612    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
1613    in the filter clause should be added to the parameter list as additional parameters. The
1614    fields in a filter clause can come from primary entity relations, relationship relations,
1615    or secondary entity relations; however, all of the entities and relationships involved must
1616    be included in the list of object names.
1617    
1618    =item params
1619    
1620    Reference to a list of parameter values to be substituted into the filter clause.
1621    
1622    =item RETURN
1623    
1624    Returns a query object for the specified search.
1625    
1626    =back
1627    
1628    =cut
1629    
1630    sub Search {
1631        # Get the parameters.
1632        my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1633        # Declare the return variable.
1634        my $retVal;
1635        # Create a safety copy of the parameter list. Note we have to be careful to insure
1636        # a parameter list exists before we copy it.
1637        my @myParams = ();
1638        if (defined $params) {
1639            @myParams = @{$params};
1640        }
1641        # Get the first object's structure so we have access to the searchable fields.
1642        my $object1Name = $objectNames->[$idx];
1643        my $object1Structure = $self->_GetStructure($object1Name);
1644        # Get the field list.
1645        if (! exists $object1Structure->{searchFields}) {
1646            Confess("No searchable index for $object1Name.");
1647        } else {
1648            # Get the field list.
1649            my @fields = @{$object1Structure->{searchFields}};
1650            # Clean the search expression.
1651            my $actualKeywords = $self->CleanKeywords($searchExpression);
1652            # Prefix a "+" to each uncontrolled word. This converts the default
1653            # search mode from OR to AND.
1654            $actualKeywords =~ s/(^|\s)(\w|")/$1\+$2/g;
1655            Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1656            # We need two match expressions, one for the filter clause and one in the
1657            # query itself. Both will use a parameter mark, so we need to push the
1658            # search expression onto the front of the parameter list twice.
1659            unshift @myParams, $actualKeywords, $actualKeywords;
1660            # Build the match expression.
1661            my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
1662            my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
1663            # Process the SQL stuff.
1664            my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1665                $self->_SetupSQL($objectNames, $filterClause, $matchClause);
1666            # Create the query. Note that the match clause is inserted at the front of
1667            # the select fields.
1668            my $command = "SELECT DISTINCT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .
1669                ".* $suffix";
1670            my $sth = $self->_GetStatementHandle($command, \@myParams);
1671            # Now we create the relation map, which enables DBQuery to determine the order, name
1672            # and mapped name for each object in the query.
1673            my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
1674            # Return the statement object.
1675            $retVal = DBQuery::_new($self, $sth, \@relationMap, $object1Name);
1676        }
1677        return $retVal;
1678    }
1679    
1680  =head3 GetFlat  =head3 GetFlat
1681    
1682  C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>  C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>
# Line 1152  Line 1730 
1730      return @retVal;      return @retVal;
1731  }  }
1732    
1733    =head3 SpecialFields
1734    
1735    C<< my %specials = $erdb->SpecialFields($entityName); >>
1736    
1737    Return a hash mapping special fields in the specified entity to the value of their
1738    C<special> attribute. This enables the subclass to get access to the special field
1739    attributes without needed to plumb the internal ERDB data structures.
1740    
1741    =over 4
1742    
1743    =item entityName
1744    
1745    Name of the entity whose special fields are desired.
1746    
1747    =item RETURN
1748    
1749    Returns a hash. The keys of the hash are the special field names, and the values
1750    are the values from each special field's C<special> attribute.
1751    
1752    =back
1753    
1754    =cut
1755    
1756    sub SpecialFields {
1757        # Get the parameters.
1758        my ($self, $entityName) = @_;
1759        # Declare the return variable.
1760        my %retVal = ();
1761        # Find the entity's data structure.
1762        my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1763        # Loop through its fields, adding each special field to the return hash.
1764        my $fieldHash = $entityData->{Fields};
1765        for my $fieldName (keys %{$fieldHash}) {
1766            my $fieldData = $fieldHash->{$fieldName};
1767            if (exists $fieldData->{special}) {
1768                $retVal{$fieldName} = $fieldData->{special};
1769            }
1770        }
1771        # Return the result.
1772        return %retVal;
1773    }
1774    
1775  =head3 Delete  =head3 Delete
1776    
1777  C<< my $stats = $erdb->Delete($entityName, $objectID); >>  C<< my $stats = $erdb->Delete($entityName, $objectID, %options); >>
1778    
1779  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
1780  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.
1781  always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many  
1782  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
1783    relationship connected to a dependent entity or if it is the "to" entity connected to a 1-to-many
1784  dependent relationship.  dependent relationship.
1785    
1786  =over 4  =over 4
# Line 1173  Line 1794 
1794  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<%>),
1795  then it is presumed to by a LIKE pattern.  then it is presumed to by a LIKE pattern.
1796    
1797  =item testFlag  =item options
1798    
1799  If TRUE, the delete statements will be traced without being executed.  A hash detailing the options for this delete operation.
1800    
1801  =item RETURN  =item RETURN
1802    
# Line 1184  Line 1805 
1805    
1806  =back  =back
1807    
1808  =cut  The permissible options for this method are as follows.
1809  #: Return Type $%;  
1810    =over 4
1811    
1812    =item testMode
1813    
1814    If TRUE, then the delete statements will be traced, but no changes will be made to the database.
1815    
1816    =item keepRoot
1817    
1818    If TRUE, then the entity instances will not be deleted, only the dependent records.
1819    
1820    =back
1821    
1822    =cut
1823    #: Return Type $%;
1824  sub Delete {  sub Delete {
1825      # Get the parameters.      # Get the parameters.
1826      my ($self, $entityName, $objectID, $testFlag) = @_;      my ($self, $entityName, $objectID, %options) = @_;
1827      # Declare the return variable.      # Declare the return variable.
1828      my $retVal = Stats->new();      my $retVal = Stats->new();
1829      # Get the DBKernel object.      # Get the DBKernel object.
# Line 1205  Line 1840 
1840      # FROM-relationships and entities.      # FROM-relationships and entities.
1841      my @fromPathList = ();      my @fromPathList = ();
1842      my @toPathList = ();      my @toPathList = ();
1843      # This final hash is used to remember what work still needs to be done. We push paths      # This final list is used to remember what work still needs to be done. We push paths
1844      # onto the list, then pop them off to extend the paths. We prime it with the starting      # onto the list, then pop them off to extend the paths. We prime it with the starting
1845      # point. Note that we will work hard to insure that the last item on a path in the      # point. Note that we will work hard to insure that the last item on a path in the
1846      # TODO list is always an entity.      # to-do list is always an entity.
1847      my @todoList = ([$entityName]);      my @todoList = ([$entityName]);
1848      while (@todoList) {      while (@todoList) {
1849          # Get the current path.          # Get the current path.
# Line 1216  Line 1851 
1851          # Copy it into a list.          # Copy it into a list.
1852          my @stackedPath = @{$current};          my @stackedPath = @{$current};
1853          # 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.
1854          my $entityName = pop @stackedPath;          my $myEntityName = pop @stackedPath;
1855          # Add it to the alreadyFound list.          # Add it to the alreadyFound list.
1856          $alreadyFound{$entityName} = 1;          $alreadyFound{$myEntityName} = 1;
1857            # Figure out if we need to delete this entity.
1858            if ($myEntityName ne $entityName || ! $options{keepRoot}) {
1859          # Get the entity data.          # Get the entity data.
1860          my $entityData = $self->_GetStructure($entityName);              my $entityData = $self->_GetStructure($myEntityName);
1861          # 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.  
1862          my $relations = $entityData->{Relations};          my $relations = $entityData->{Relations};
1863          for my $relation (keys %{$relations}) {          for my $relation (keys %{$relations}) {
1864              my @augmentedList = (@stackedPath, $relation);              my @augmentedList = (@stackedPath, $relation);
1865              push @fromPathList, \@augmentedList;              push @fromPathList, \@augmentedList;
1866          }          }
1867            }
1868          # Now we need to look for relationships connected to this entity.          # Now we need to look for relationships connected to this entity.
1869          my $relationshipList = $self->{_metaData}->{Relationships};          my $relationshipList = $self->{_metaData}->{Relationships};
1870          for my $relationshipName (keys %{$relationshipList}) {          for my $relationshipName (keys %{$relationshipList}) {
1871              my $relationship = $relationshipList->{$relationshipName};              my $relationship = $relationshipList->{$relationshipName};
1872              # Check the FROM field. We're only interested if it's us.              # Check the FROM field. We're only interested if it's us.
1873              if ($relationship->{from} eq $entityName) {              if ($relationship->{from} eq $myEntityName) {
1874                  # Add the path to this relationship.                  # Add the path to this relationship.
1875                  my @augmentedList = (@stackedPath, $entityName, $relationshipName);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1876                  push @fromPathList, \@augmentedList;                  push @fromPathList, \@augmentedList;
1877                  # Check the arity. If it's MM we're done. If it's 1M                  # Check the arity. If it's MM we're done. If it's 1M
1878                  # and the target hasn't been seen yet, we want to                  # and the target hasn't been seen yet, we want to
# Line 1254  Line 1891 
1891              }              }
1892              # Now check the TO field. In this case only the relationship needs              # Now check the TO field. In this case only the relationship needs
1893              # deletion.              # deletion.
1894              if ($relationship->{to} eq $entityName) {              if ($relationship->{to} eq $myEntityName) {
1895                  my @augmentedList = (@stackedPath, $entityName, $relationshipName);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1896                  push @toPathList, \@augmentedList;                  push @toPathList, \@augmentedList;
1897              }              }
1898          }          }
1899      }      }
1900      # Create the first qualifier for the WHERE clause. This selects the      # Create the first qualifier for the WHERE clause. This selects the
1901      # 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
1902      # 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
1903      # to the table containing the dependent records to delete.      # to the table containing the dependent records to delete.
1904      my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");      my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
1905      # We need to make two passes. The first is through the to-list, and      # We need to make two passes. The first is through the to-list, and
# Line 1301  Line 1938 
1938                  }                  }
1939              }              }
1940              # Now we have our desired DELETE statement.              # Now we have our desired DELETE statement.
1941              if ($testFlag) {              if ($options{testMode}) {
1942                  # Here the user wants to trace without executing.                  # Here the user wants to trace without executing.
1943                  Trace($stmt) if T(0);                  Trace($stmt) if T(0);
1944              } else {              } else {
1945                  # 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
1946                  # if an error occurs, so we just go ahead and do it.                  # if an error occurs, so we just go ahead and do it.
1947                  Trace("Executing delete from $target using '$objectID'.") if T(3);                  Trace("Executing delete from $target using '$objectID'.") if T(3);
1948                  my $rv = $db->SQL($stmt, 0, $objectID);                  my $rv = $db->SQL($stmt, 0, $objectID);
# Line 1320  Line 1957 
1957      return $retVal;      return $retVal;
1958  }  }
1959    
1960    =head3 Disconnect
1961    
1962    C<< $erdb->Disconnect($relationshipName, $originEntityName, $originEntityID); >>
1963    
1964    Disconnect an entity instance from all the objects to which it is related. This
1965    will delete each relationship instance that connects to the specified entity.
1966    
1967    =over 4
1968    
1969    =item relationshipName
1970    
1971    Name of the relationship whose instances are to be deleted.
1972    
1973    =item originEntityName
1974    
1975    Name of the entity that is to be disconnected.
1976    
1977    =item originEntityID
1978    
1979    ID of the entity that is to be disconnected.
1980    
1981    =back
1982    
1983    =cut
1984    
1985    sub Disconnect {
1986        # Get the parameters.
1987        my ($self, $relationshipName, $originEntityName, $originEntityID) = @_;
1988        # Get the relationship descriptor.
1989        my $structure = $self->_GetStructure($relationshipName);
1990        # Insure we have a relationship.
1991        if (! exists $structure->{from}) {
1992            Confess("$relationshipName is not a relationship in the database.");
1993        } else {
1994            # Get the database handle.
1995            my $dbh = $self->{_dbh};
1996            # We'll set this value to 1 if we find our entity.
1997            my $found = 0;
1998            # Loop through the ends of the relationship.
1999            for my $dir ('from', 'to') {
2000                if ($structure->{$dir} eq $originEntityName) {
2001                    # Delete all relationship instances on this side of the entity instance.
2002                    Trace("Disconnecting in $dir direction with ID \"$originEntityID\".");
2003                    $dbh->SQL("DELETE FROM $relationshipName WHERE ${dir}_link = ?", 0, $originEntityID);
2004                    $found = 1;
2005                }
2006            }
2007            # Insure we found the entity on at least one end.
2008            if (! $found) {
2009                Confess("Entity \"$originEntityName\" does not use $relationshipName.");
2010            }
2011        }
2012    }
2013    
2014    =head3 DeleteRow
2015    
2016    C<< $erdb->DeleteRow($relationshipName, $fromLink, $toLink, \%values); >>
2017    
2018    Delete a row from a relationship. In most cases, only the from-link and to-link are
2019    needed; however, for relationships with intersection data values can be specified
2020    for the other fields using a hash.
2021    
2022    =over 4
2023    
2024    =item relationshipName
2025    
2026    Name of the relationship from which the row is to be deleted.
2027    
2028    =item fromLink
2029    
2030    ID of the entity instance in the From direction.
2031    
2032    =item toLink
2033    
2034    ID of the entity instance in the To direction.
2035    
2036    =item values
2037    
2038    Reference to a hash of other values to be used for filtering the delete.
2039    
2040    =back
2041    
2042    =cut
2043    
2044    sub DeleteRow {
2045        # Get the parameters.
2046        my ($self, $relationshipName, $fromLink, $toLink, $values) = @_;
2047        # Create a hash of all the filter information.
2048        my %filter = ('from-link' => $fromLink, 'to-link' => $toLink);
2049        if (defined $values) {
2050            for my $key (keys %{$values}) {
2051                $filter{$key} = $values->{$key};
2052            }
2053        }
2054        # Build an SQL statement out of the hash.
2055        my @filters = ();
2056        my @parms = ();
2057        for my $key (keys %filter) {
2058            push @filters, _FixName($key) . " = ?";
2059            push @parms, $filter{$key};
2060        }
2061        Trace("Parms for delete row are " . join(", ", map { "\"$_\"" } @parms) . ".") if T(SQL => 4);
2062        my $command = "DELETE FROM $relationshipName WHERE " .
2063                      join(" AND ", @filters);
2064        # Execute it.
2065        my $dbh = $self->{_dbh};
2066        $dbh->SQL($command, undef, @parms);
2067    }
2068    
2069    =head3 DeleteLike
2070    
2071    C<< my $deleteCount = $erdb->DeleteLike($relName, $filter, \@parms); >>
2072    
2073    Delete all the relationship rows that satisfy a particular filter condition. Unlike a normal
2074    filter, only fields from the relationship itself can be used.
2075    
2076    =over 4
2077    
2078    =item relName
2079    
2080    Name of the relationship whose records are to be deleted.
2081    
2082    =item filter
2083    
2084    A filter clause (L</Get>-style) for the delete query.
2085    
2086    =item parms
2087    
2088    Reference to a list of parameters for the filter clause.
2089    
2090    =item RETURN
2091    
2092    Returns a count of the number of rows deleted.
2093    
2094    =back
2095    
2096    =cut
2097    
2098    sub DeleteLike {
2099        # Get the parameters.
2100        my ($self, $objectName, $filter, $parms) = @_;
2101        # Declare the return variable.
2102        my $retVal;
2103        # Insure the parms argument is an array reference if the caller left it off.
2104        if (! defined($parms)) {
2105            $parms = [];
2106        }
2107        # Insure we have a relationship. The main reason for this is if we delete an entity
2108        # instance we have to yank out a bunch of other stuff with it.
2109        if ($self->IsEntity($objectName)) {
2110            Confess("Cannot use DeleteLike on $objectName, because it is not a relationship.");
2111        } else {
2112            # Create the SQL command suffix to get the desierd records.
2113            my ($suffix) = $self->_SetupSQL([$objectName], $filter);
2114            # Convert it to a DELETE command.
2115            my $command = "DELETE $suffix";
2116            # Execute the command.
2117            my $dbh = $self->{_dbh};
2118            my $result = $dbh->SQL($command, 0, @{$parms});
2119            # Check the results. Note we convert the "0D0" result to a real zero.
2120            # A failure causes an abnormal termination, so the caller isn't going to
2121            # worry about it.
2122            if (! defined $result) {
2123                Confess("Error deleting from $objectName: " . $dbh->errstr());
2124            } elsif ($result == 0) {
2125                $retVal = 0;
2126            } else {
2127                $retVal = $result;
2128            }
2129        }
2130        # Return the result count.
2131        return $retVal;
2132    }
2133    
2134    =head3 SortNeeded
2135    
2136    C<< my $parms = $erdb->SortNeeded($relationName); >>
2137    
2138    Return the pipe command for the sort that should be applied to the specified
2139    relation when creating the load file.
2140    
2141    For example, if the load file should be sorted ascending by the first
2142    field, this method would return
2143    
2144        sort -k1 -t"\t"
2145    
2146    If the first field is numeric, the method would return
2147    
2148        sort -k1n -t"\t"
2149    
2150    Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate
2151    keys using a sort.
2152    
2153    =over 4
2154    
2155    =item relationName
2156    
2157    Name of the relation to be examined.
2158    
2159    =item
2160    
2161    Returns the sort command to use for sorting the relation, suitable for piping.
2162    
2163    =back
2164    
2165    =cut
2166    #: Return Type $;
2167    sub SortNeeded {
2168        # Get the parameters.
2169        my ($self, $relationName) = @_;
2170        # Declare a descriptor to hold the names of the key fields.
2171        my @keyNames = ();
2172        # Get the relation structure.
2173        my $relationData = $self->_FindRelation($relationName);
2174        # Find out if the relation is a primary entity relation,
2175        # a relationship relation, or a secondary entity relation.
2176        my $entityTable = $self->{_metaData}->{Entities};
2177        my $relationshipTable = $self->{_metaData}->{Relationships};
2178        if (exists $entityTable->{$relationName}) {
2179            # Here we have a primary entity relation.
2180            push @keyNames, "id";
2181        } elsif (exists $relationshipTable->{$relationName}) {
2182            # Here we have a relationship. We sort using the FROM index.
2183            my $relationshipData = $relationshipTable->{$relationName};
2184            my $index = $relationData->{Indexes}->{idxFrom};
2185            push @keyNames, @{$index->{IndexFields}};
2186        } else {
2187            # Here we have a secondary entity relation, so we have a sort on the ID field.
2188            push @keyNames, "id";
2189        }
2190        # Now we parse the key names into sort parameters. First, we prime the return
2191        # string.
2192        my $retVal = "sort -t\"\t\" ";
2193        # Get the relation's field list.
2194        my @fields = @{$relationData->{Fields}};
2195        # Loop through the keys.
2196        for my $keyData (@keyNames) {
2197            # Get the key and the ordering.
2198            my ($keyName, $ordering);
2199            if ($keyData =~ /^([^ ]+) DESC/) {
2200                ($keyName, $ordering) = ($1, "descending");
2201            } else {
2202                ($keyName, $ordering) = ($keyData, "ascending");
2203            }
2204            # Find the key's position and type.
2205            my $fieldSpec;
2206            for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {
2207                my $thisField = $fields[$i];
2208                if ($thisField->{name} eq $keyName) {
2209                    # Get the sort modifier for this field type. The modifier
2210                    # decides whether we're using a character, numeric, or
2211                    # floating-point sort.
2212                    my $modifier = $TypeTable{$thisField->{type}}->{sort};
2213                    # If the index is descending for this field, denote we want
2214                    # to reverse the sort order on this field.
2215                    if ($ordering eq 'descending') {
2216                        $modifier .= "r";
2217                    }
2218                    # Store the position and modifier into the field spec, which
2219                    # will stop the inner loop. Note that the field number is
2220                    # 1-based in the sort command, so we have to increment the
2221                    # index.
2222                    $fieldSpec = ($i + 1) . $modifier;
2223                }
2224            }
2225            # Add this field to the sort command.
2226            $retVal .= " -k$fieldSpec";
2227        }
2228        # Return the result.
2229        return $retVal;
2230    }
2231    
2232  =head3 GetList  =head3 GetList
2233    
2234  C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>  C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>
# Line 1362  Line 2271 
2271    
2272  =item RETURN  =item RETURN
2273    
2274  Returns a list of B<DBObject>s that satisfy the query conditions.  Returns a list of B<ERDBObject>s that satisfy the query conditions.
2275    
2276  =back  =back
2277    
# Line 1436  Line 2345 
2345  sub GetCount {  sub GetCount {
2346      # Get the parameters.      # Get the parameters.
2347      my ($self, $objectNames, $filter, $params) = @_;      my ($self, $objectNames, $filter, $params) = @_;
2348        # Insure the params argument is an array reference if the caller left it off.
2349        if (! defined($params)) {
2350            $params = [];
2351        }
2352      # Declare the return variable.      # Declare the return variable.
2353      my $retVal;      my $retVal;
2354      # Find out if we're counting an entity or a relationship.      # Find out if we're counting an entity or a relationship.
# Line 1614  Line 2527 
2527    
2528  =head3 InsertObject  =head3 InsertObject
2529    
2530  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>  C<< $erdb->InsertObject($objectType, \%fieldHash); >>
2531    
2532  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
2533  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 1640  Line 2553 
2553    
2554  Hash of field names to values.  Hash of field names to values.
2555    
 =item RETURN  
   
 Returns 1 if successful, 0 if an error occurred.  
   
2556  =back  =back
2557    
2558  =cut  =cut
# Line 1742  Line 2651 
2651                  $retVal = $sth->execute(@parameterList);                  $retVal = $sth->execute(@parameterList);
2652                  if (!$retVal) {                  if (!$retVal) {
2653                      my $errorString = $sth->errstr();                      my $errorString = $sth->errstr();
2654                      Trace("Insert error: $errorString.") if T(0);                      Confess("Error inserting into $relationName: $errorString");
2655                    } else {
2656                        Trace("Insert successful using $parameterList[0].") if T(3);
2657                  }                  }
2658              }              }
2659          }          }
2660      }      }
2661      # Return the success indicator.      # Return a 1 for backward compatability.
2662      return $retVal;      return 1;
2663    }
2664    
2665    =head3 UpdateEntity
2666    
2667    C<< $erdb->UpdateEntity($entityName, $id, \%fields); >>
2668    
2669    Update the values of an entity. This is an unprotected update, so it should only be
2670    done if the database resides on a database server.
2671    
2672    =over 4
2673    
2674    =item entityName
2675    
2676    Name of the entity to update. (This is the entity type.)
2677    
2678    =item id
2679    
2680    ID of the entity to update. If no entity exists with this ID, an error will be thrown.
2681    
2682    =item fields
2683    
2684    Reference to a hash mapping field names to their new values. All of the fields named
2685    must be in the entity's primary relation, and they cannot any of them be the ID field.
2686    
2687    =back
2688    
2689    =cut
2690    
2691    sub UpdateEntity {
2692        # Get the parameters.
2693        my ($self, $entityName, $id, $fields) = @_;
2694        # Get a list of the field names being updated.
2695        my @fieldList = keys %{$fields};
2696        # Verify that the fields exist.
2697        my $checker = $self->GetFieldTable($entityName);
2698        for my $field (@fieldList) {
2699            if ($field eq 'id') {
2700                Confess("Cannot update the ID field for entity $entityName.");
2701            } elsif ($checker->{$field}->{relation} ne $entityName) {
2702                Confess("Cannot find $field in primary relation of $entityName.");
2703            }
2704        }
2705        # Build the SQL statement.
2706        my @sets = ();
2707        my @valueList = ();
2708        for my $field (@fieldList) {
2709            push @sets, _FixName($field) . " = ?";
2710            push @valueList, $fields->{$field};
2711        }
2712        my $command = "UPDATE $entityName SET " . join(", ", @sets) . " WHERE id = ?";
2713        # Add the ID to the list of binding values.
2714        push @valueList, $id;
2715        # Call SQL to do the work.
2716        my $rows = $self->{_dbh}->SQL($command, 0, @valueList);
2717        # Check for errors.
2718        if ($rows == 0) {
2719            Confess("Entity $id of type $entityName not found.");
2720        }
2721  }  }
2722    
2723  =head3 LoadTable  =head3 LoadTable
2724    
2725  C<< my %results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>  C<< my $results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>
2726    
2727  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
2728  first.  first.
# Line 1800  Line 2769 
2769          # leave extra room. We postulate a minimum row count of 1000 to          # leave extra room. We postulate a minimum row count of 1000 to
2770          # prevent problems with incoming empty load files.          # prevent problems with incoming empty load files.
2771          my $rowSize = $self->EstimateRowSize($relationName);          my $rowSize = $self->EstimateRowSize($relationName);
2772          my $estimate = FIG::max($fileSize * 1.5 / $rowSize, 1000);          my $estimate = $fileSize * 1.5 / $rowSize;
2773            if ($estimate < 1000) {
2774                $estimate = 1000;
2775            }
2776          # Re-create the table without its index.          # Re-create the table without its index.
2777          $self->CreateTable($relationName, 0, $estimate);          $self->CreateTable($relationName, 0, $estimate);
2778          # If this is a pre-index DBMS, create the index here.          # If this is a pre-index DBMS, create the index here.
# Line 1820  Line 2792 
2792      };      };
2793      if (!defined $rv) {      if (!defined $rv) {
2794          $retVal->AddMessage($@) if ($@);          $retVal->AddMessage($@) if ($@);
2795          $retVal->AddMessage("Table load failed for $relationName using $fileName.");          $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2796          Trace("Table load failed for $relationName.") if T(1);          Trace("Table load failed for $relationName.") if T(1);
2797      } else {      } else {
2798          # Here we successfully loaded the table.          # Here we successfully loaded the table.
# Line 1828  Line 2800 
2800          my $size = -s $fileName;          my $size = -s $fileName;
2801          Trace("$size bytes loaded into $relationName.") if T(2);          Trace("$size bytes loaded into $relationName.") if T(2);
2802          # If we're rebuilding, we need to create the table indexes.          # If we're rebuilding, we need to create the table indexes.
2803          if ($truncateFlag && ! $dbh->{_preIndex}) {          if ($truncateFlag) {
2804                # Indexes are created here for PostGres. For PostGres, indexes are
2805                # best built at the end. For MySQL, the reverse is true.
2806                if (! $dbh->{_preIndex}) {
2807              eval {              eval {
2808                  $self->CreateIndex($relationName);                  $self->CreateIndex($relationName);
2809              };              };
# Line 1836  Line 2811 
2811                  $retVal->AddMessage($@);                  $retVal->AddMessage($@);
2812              }              }
2813          }          }
2814                # The full-text index (if any) is always built last, even for MySQL.
2815                # First we need to see if this table has a full-text index. Only
2816                # primary relations are allowed that privilege.
2817                Trace("Checking for full-text index on $relationName.") if T(2);
2818                if ($self->_IsPrimary($relationName)) {
2819                    $self->CreateSearchIndex($relationName);
2820                }
2821            }
2822      }      }
2823      # Analyze the table to improve performance.      # Analyze the table to improve performance.
2824      Trace("Analyzing and compacting $relationName.") if T(3);      Trace("Analyzing and compacting $relationName.") if T(3);
2825      $dbh->vacuum_it($relationName);      $dbh->vacuum_it($relationName);
     # Flush the database cache.  
     $dbh->flush_tables();  
2826      Trace("$relationName load completed.") if T(3);      Trace("$relationName load completed.") if T(3);
2827      # Return the statistics.      # Return the statistics.
2828      return $retVal;      return $retVal;
2829  }  }
2830    
2831  =head3 GenerateEntity  =head3 CreateSearchIndex
2832    
2833  C<< my $fieldHash = $erdb->GenerateEntity($id, $type, \%values); >>  C<< $erdb->CreateSearchIndex($objectName); >>
2834    
2835  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
2836  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.  
2837    
2838  =over 4  =over 4
2839    
2840  =item id  =item objectName
2841    
2842  ID to assign to the new entity.  Name of the entity or relationship to be indexed.
2843    
2844  =item type  =back
2845    
2846  Type name for the new entity.  =cut
2847    
2848  =item values  sub CreateSearchIndex {
2849        # Get the parameters.
2850        my ($self, $objectName) = @_;
2851        # Get the relation's entity/relationship structure.
2852        my $structure = $self->_GetStructure($objectName);
2853        # Get the database handle.
2854        my $dbh = $self->{_dbh};
2855        Trace("Checking for search fields in $objectName.") if T(3);
2856        # Check for a searchable fields list.
2857        if (exists $structure->{searchFields}) {
2858            # Here we know that we need to create a full-text search index.
2859            # Get an SQL-formatted field name list.
2860            my $fields = join(", ", _FixNames(@{$structure->{searchFields}}));
2861            # Create the index. If it already exists, it will be dropped.
2862            $dbh->create_index(tbl => $objectName, idx => "search_idx",
2863                               flds => $fields, kind => 'fulltext');
2864            Trace("Index created for $fields in $objectName.") if T(2);
2865        }
2866    }
2867    
2868  Hash containing additional values that might be needed by the data generation methods (optional).  =head3 DropRelation
2869    
2870    C<< $erdb->DropRelation($relationName); >>
2871    
2872    Physically drop a relation from the database.
2873    
2874    =over 4
2875    
2876    =item relationName
2877    
2878    Name of the relation to drop. If it does not exist, this method will have
2879    no effect.
2880    
2881  =back  =back
2882    
2883  =cut  =cut
2884    
2885  sub GenerateEntity {  sub DropRelation {
2886      # Get the parameters.      # Get the parameters.
2887      my ($self, $id, $type, $values) = @_;      my ($self, $relationName) = @_;
2888      # Create the return hash.      # Get the database handle.
2889      my $this = { id => $id };      my $dbh = $self->{_dbh};
2890      # Get the metadata structure.      # Drop the relation. The method used here has no effect if the relation
2891      my $metadata = $self->{_metaData};      # does not exist.
2892      # Get this entity's list of fields.      Trace("Invoking DB Kernel to drop $relationName.") if T(3);
2893      if (!exists $metadata->{Entities}->{$type}) {      $dbh->drop_table(tbl => $relationName);
         Confess("Unrecognized entity type $type in GenerateEntity.");  
     } else {  
         my $entity = $metadata->{Entities}->{$type};  
         my $fields = $entity->{Fields};  
         # Generate data from the fields.  
         _GenerateFields($this, $fields, $type, $values);  
     }  
     # Return the hash created.  
     return $this;  
2894  }  }
2895    
2896  =head3 GetEntity  =head3 MatchSqlPattern
2897    
2898  C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>  C<< my $matched = ERDB::MatchSqlPattern($value, $pattern); >>
2899    
2900  Return an object describing the entity instance with a specified ID.  Determine whether or not a specified value matches an SQL pattern. An SQL
2901    pattern has two wild card characters: C<%> that matches multiple characters,
2902    and C<_> that matches a single character. These can be escaped using a
2903    backslash (C<\>). We pull this off by converting the SQL pattern to a
2904    PERL regular expression. As per SQL rules, the match is case-insensitive.
2905    
2906  =over 4  =over 4
2907    
2908  =item entityType  =item value
2909    
2910  Entity type name.  Value to be matched against the pattern. Note that an undefined or empty
2911    value will not match anything.
2912    
2913  =item ID  =item pattern
2914    
2915  ID of the desired entity.  SQL pattern against which to match the value. An undefined or empty pattern will
2916    match everything.
2917    
2918  =item RETURN  =item RETURN
2919    
2920  Returns a B<DBObject> representing the desired entity instance, or an undefined value if no  Returns TRUE if the value and pattern match, else FALSE.
2921  instance is found with the specified key.  
2922    =back
2923    
2924    =cut
2925    
2926    sub MatchSqlPattern {
2927        # Get the parameters.
2928        my ($value, $pattern) = @_;
2929        # Declare the return variable.
2930        my $retVal;
2931        # Insure we have a pattern.
2932        if (! defined($pattern) || $pattern eq "") {
2933            $retVal = 1;
2934        } else {
2935            # Break the pattern into pieces around the wildcard characters. Because we
2936            # use parentheses in the split function's delimiter expression, we'll get
2937            # list elements for the delimiters as well as the rest of the string.
2938            my @pieces = split /([_%]|\\[_%])/, $pattern;
2939            # Check some fast special cases.
2940            if ($pattern eq '%') {
2941                # A null pattern matches everything.
2942                $retVal = 1;
2943            } elsif (@pieces == 1) {
2944                # No wildcards, so we have a literal comparison. Note we're case-insensitive.
2945                $retVal = (lc($value) eq lc($pattern));
2946            } elsif (@pieces == 2 && $pieces[1] eq '%') {
2947                # A wildcard at the end, so we have a substring match. This is also case-insensitive.
2948                $retVal = (lc(substr($value, 0, length($pieces[0]))) eq lc($pieces[0]));
2949            } else {
2950                # Okay, we have to do it the hard way. Convert each piece to a PERL pattern.
2951                my $realPattern = "";
2952                for my $piece (@pieces) {
2953                    # Determine the type of piece.
2954                    if ($piece eq "") {
2955                        # Empty pieces are ignored.
2956                    } elsif ($piece eq "%") {
2957                        # Here we have a multi-character wildcard. Note that it can match
2958                        # zero or more characters.
2959                        $realPattern .= ".*"
2960                    } elsif ($piece eq "_") {
2961                        # Here we have a single-character wildcard.
2962                        $realPattern .= ".";
2963                    } elsif ($piece eq "\\%" || $piece eq "\\_") {
2964                        # This is an escape sequence (which is a rare thing, actually).
2965                        $realPattern .= substr($piece, 1, 1);
2966                    } else {
2967                        # Here we have raw text.
2968                        $realPattern .= quotemeta($piece);
2969                    }
2970                }
2971                # Do the match.
2972                $retVal = ($value =~ /^$realPattern$/i ? 1 : 0);
2973            }
2974        }
2975        # Return the result.
2976        return $retVal;
2977    }
2978    
2979    =head3 GetEntity
2980    
2981    C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>
2982    
2983    Return an object describing the entity instance with a specified ID.
2984    
2985    =over 4
2986    
2987    =item entityType
2988    
2989    Entity type name.
2990    
2991    =item ID
2992    
2993    ID of the desired entity.
2994    
2995    =item RETURN
2996    
2997    Returns a B<ERDBObject> representing the desired entity instance, or an undefined value if no
2998    instance is found with the specified key.
2999    
3000  =back  =back
3001    
# Line 1941  Line 3012 
3012      return $retVal;      return $retVal;
3013  }  }
3014    
3015    =head3 GetChoices
3016    
3017    C<< my @values = $erdb->GetChoices($entityName, $fieldName); >>
3018    
3019    Return a list of all the values for the specified field that are represented in the
3020    specified entity.
3021    
3022    Note that if the field is not indexed, then this will be a very slow operation.
3023    
3024    =over 4
3025    
3026    =item entityName
3027    
3028    Name of an entity in the database.
3029    
3030    =item fieldName
3031    
3032    Name of a field belonging to the entity. This is a raw field name without
3033    the standard parenthesized notation used in most calls.
3034    
3035    =item RETURN
3036    
3037    Returns a list of the distinct values for the specified field in the database.
3038    
3039    =back
3040    
3041    =cut
3042    
3043    sub GetChoices {
3044        # Get the parameters.
3045        my ($self, $entityName, $fieldName) = @_;
3046        # Declare the return variable.
3047        my @retVal;
3048        # Get the entity data structure.
3049        my $entityData = $self->_GetStructure($entityName);
3050        # Get the field.
3051        my $fieldHash = $entityData->{Fields};
3052        if (! exists $fieldHash->{$fieldName}) {
3053            Confess("$fieldName not found in $entityName.");
3054        } else {
3055            # Get the name of the relation containing the field.
3056            my $relation = $fieldHash->{$fieldName}->{relation};
3057            # Fix up the field name.
3058            my $realName = _FixName($fieldName);
3059            # Get the database handle.
3060            my $dbh = $self->{_dbh};
3061            # Query the database.
3062            my $results = $dbh->SQL("SELECT DISTINCT $realName FROM $relation");
3063            # Clean the results. They are stored as a list of lists, and we just want the one list.
3064            @retVal = sort map { $_->[0] } @{$results};
3065        }
3066        # Return the result.
3067        return @retVal;
3068    }
3069    
3070  =head3 GetEntityValues  =head3 GetEntityValues
3071    
3072  C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>  C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>
3073    
3074  Return a list of values from a specified entity instance.  Return a list of values from a specified entity instance. If the entity instance
3075    does not exist, an empty list is returned.
3076    
3077  =over 4  =over 4
3078    
# Line 2000  Line 3127 
3127  fields specified returns multiple values, they are flattened in with the rest. For  fields specified returns multiple values, they are flattened in with the rest. For
3128  example, the following call will return a list of the features in a particular  example, the following call will return a list of the features in a particular
3129  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
3130  feature ID followed by all of its aliases.  feature ID followed by all of its essentiality determinations.
3131    
3132  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(essential)']); >>
3133    
3134  =over 4  =over 4
3135    
# Line 2180  Line 3307 
3307      return $objectData->{Fields};      return $objectData->{Fields};
3308  }  }
3309    
3310    =head3 SplitKeywords
3311    
3312    C<< my @keywords = ERDB::SplitKeywords($keywordString); >>
3313    
3314    This method returns a list of the positive keywords in the specified
3315    keyword string. All of the operators will have been stripped off,
3316    and if the keyword is preceded by a minus operator (C<->), it will
3317    not be in the list returned. The idea here is to get a list of the
3318    keywords the user wants to see. The list will be processed to remove
3319    duplicates.
3320    
3321    It is possible to create a string that confuses this method. For example
3322    
3323        frog toad -frog
3324    
3325    would return both C<frog> and C<toad>. If this is a problem we can deal
3326    with it later.
3327    
3328    =over 4
3329    
3330    =item keywordString
3331    
3332    The keyword string to be parsed.
3333    
3334    =item RETURN
3335    
3336    Returns a list of the words in the keyword string the user wants to
3337    see.
3338    
3339    =back
3340    
3341    =cut
3342    
3343    sub SplitKeywords {
3344        # Get the parameters.
3345        my ($keywordString) = @_;
3346        # Make a safety copy of the string. (This helps during debugging.)
3347        my $workString = $keywordString;
3348        # Convert operators we don't care about to spaces.
3349        $workString =~ tr/+"()<>/ /;
3350        # Split the rest of the string along space boundaries. Note that we
3351        # eliminate any words that are zero length or begin with a minus sign.
3352        my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
3353        # Use a hash to remove duplicates.
3354        my %words = map { $_ => 1 } @wordList;
3355        # Return the result.
3356        return sort keys %words;
3357    }
3358    
3359    =head3 ValidateFieldName
3360    
3361    C<< my $okFlag = ERDB::ValidateFieldName($fieldName); >>
3362    
3363    Return TRUE if the specified field name is valid, else FALSE. Valid field names must
3364    be hyphenated words subject to certain restrictions.
3365    
3366    =over 4
3367    
3368    =item fieldName
3369    
3370    Field name to be validated.
3371    
3372    =item RETURN
3373    
3374    Returns TRUE if the field name is valid, else FALSE.
3375    
3376    =back
3377    
3378    =cut
3379    
3380    sub ValidateFieldName {
3381        # Get the parameters.
3382        my ($fieldName) = @_;
3383        # Declare the return variable. The field name is valid until we hear
3384        # differently.
3385        my $retVal = 1;
3386        # Compute the maximum name length.
3387        my $maxLen = $TypeTable{'name-string'}->{maxLen};
3388        # Look for bad stuff in the name.
3389        if ($fieldName =~ /--/) {
3390            # Here we have a doubled minus sign.
3391            Trace("Field name $fieldName has a doubled hyphen.") if T(1);
3392            $retVal = 0;
3393        } elsif ($fieldName !~ /^[A-Za-z]/) {
3394            # Here the field name is missing the initial letter.
3395            Trace("Field name $fieldName does not begin with a letter.") if T(1);
3396            $retVal = 0;
3397        } elsif (length($fieldName) > $maxLen) {
3398            # Here the field name is too long.
3399            Trace("Maximum field name length is $maxLen. Field name must be truncated to " . substr($fieldName,0, $maxLen) . ".");
3400        } else {
3401            # Strip out the minus signs. Everything remaining must be a letter,
3402            # underscore, or digit.
3403            my $strippedName = $fieldName;
3404            $strippedName =~ s/-//g;
3405            if ($strippedName !~ /^(\w|\d)+$/) {
3406                Trace("Field name $fieldName contains illegal characters.") if T(1);
3407                $retVal = 0;
3408            }
3409        }
3410        # Return the result.
3411        return $retVal;
3412    }
3413    
3414    =head3 ReadMetaXML
3415    
3416    C<< my $rawMetaData = ERDB::ReadDBD($fileName); >>
3417    
3418    This method reads a raw database definition XML file and returns it.
3419    Normally, the metadata used by the ERDB system has been processed and
3420    modified to make it easier to load and retrieve the data; however,
3421    this method can be used to get the data in its raw form.
3422    
3423    =over 4
3424    
3425    =item fileName
3426    
3427    Name of the XML file to read.
3428    
3429    =item RETURN
3430    
3431    Returns a hash reference containing the raw XML data from the specified file.
3432    
3433    =back
3434    
3435    =cut
3436    
3437    sub ReadMetaXML {
3438        # Get the parameters.
3439        my ($fileName) = @_;
3440        # Read the XML.
3441        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
3442        Trace("XML metadata loaded from file $fileName.") if T(1);
3443        # Return the result.
3444        return $retVal;
3445    }
3446    
3447    =head3 GetEntityFieldHash
3448    
3449    C<< my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName); >>
3450    
3451    Get the field hash of the named entity in the specified raw XML structure.
3452    The field hash may not exist, in which case we need to create it.
3453    
3454    =over 4
3455    
3456    =item structure
3457    
3458    Raw XML structure defininng the database. This is not the run-time XML used by
3459    an ERDB object, since that has all sorts of optimizations built-in.
3460    
3461    =item entityName
3462    
3463    Name of the entity whose field structure is desired.
3464    
3465    =item RETURN
3466    
3467    Returns the field hash used to define the entity's fields.
3468    
3469    =back
3470    
3471    =cut
3472    
3473    sub GetEntityFieldHash {
3474        # Get the parameters.
3475        my ($structure, $entityName) = @_;
3476        # Get the entity structure.
3477        my $entityData = $structure->{Entities}->{$entityName};
3478        # Look for a field structure.
3479        my $retVal = $entityData->{Fields};
3480        # If it doesn't exist, create it.
3481        if (! defined($retVal)) {
3482            $entityData->{Fields} = {};
3483            $retVal = $entityData->{Fields};
3484        }
3485        # Return the result.
3486        return $retVal;
3487    }
3488    
3489    =head3 WriteMetaXML
3490    
3491    C<< ERDB::WriteMetaXML($structure, $fileName); >>
3492    
3493    Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
3494    used to update the database definition. It must be used with care, however, since it
3495    will only work on a raw structure, not on the processed structure created by an ERDB
3496    constructor.
3497    
3498    =over 4
3499    
3500    =item structure
3501    
3502    XML structure to be written to the file.
3503    
3504    =item fileName
3505    
3506    Name of the output file to which the updated XML should be stored.
3507    
3508    =back
3509    
3510    =cut
3511    
3512    sub WriteMetaXML {
3513        # Get the parameters.
3514        my ($structure, $fileName) = @_;
3515        # Compute the output.
3516        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
3517        # Write it to the file.
3518        my $xmlOut = Open(undef, ">$fileName");
3519        print $xmlOut $fileString;
3520    }
3521    
3522    
3523    =head3 HTMLNote
3524    
3525    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
3526    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
3527    Except for C<[p]>, all the codes are closed by slash-codes. So, for
3528    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
3529    
3530    C<< my $realHtml = ERDB::HTMLNote($dataString); >>
3531    
3532    =over 4
3533    
3534    =item dataString
3535    
3536    String to convert to HTML.
3537    
3538    =item RETURN
3539    
3540    An HTML string derived from the input string.
3541    
3542    =back
3543    
3544    =cut
3545    
3546    sub HTMLNote {
3547        # Get the parameter.
3548        my ($dataString) = @_;
3549        # HTML-escape the text.
3550        my $retVal = CGI::escapeHTML($dataString);
3551        # Substitute the bulletin board codes.
3552        $retVal =~ s!\[(/?[bi])\]!<$1>!g;
3553        $retVal =~ s!\[p\]!</p><p>!g;
3554        $retVal =~ s!\[link\s+([^\]]+)\]!<a href="$1">!g;
3555        $retVal =~ s!\[/link\]!</a>!g;
3556        # Return the result.
3557        return $retVal;
3558    }
3559    
3560    =head3 BeginTran
3561    
3562    C<< $erdb->BeginTran(); >>
3563    
3564    Start a database transaction.
3565    
3566    =cut
3567    
3568    sub BeginTran {
3569        my ($self) = @_;
3570        $self->{_dbh}->begin_tran();
3571    
3572    }
3573    
3574    =head3 CommitTran
3575    
3576    C<< $erdb->CommitTran(); >>
3577    
3578    Commit an active database transaction.
3579    
3580    =cut
3581    
3582    sub CommitTran {
3583        my ($self) = @_;
3584        $self->{_dbh}->commit_tran();
3585    }
3586    
3587    =head3 RollbackTran
3588    
3589    C<< $erdb->RollbackTran(); >>
3590    
3591    Roll back an active database transaction.
3592    
3593    =cut
3594    
3595    sub RollbackTran {
3596        my ($self) = @_;
3597        $self->{_dbh}->roll_tran();
3598    }
3599    
3600    =head3 UpdateField
3601    
3602    C<< my $count = $erdb->UpdateField($objectNames, $fieldName, $oldValue, $newValue, $filter, $parms); >>
3603    
3604    Update all occurrences of a specific field value to a new value. The number of rows changed will be
3605    returned.
3606    
3607    =over 4
3608    
3609    =item fieldName
3610    
3611    Name of the field in standard I<objectName>C<(>I<fieldName>C<)> format.
3612    
3613    =item oldValue
3614    
3615    Value to be modified. All occurrences of this value in the named field will be replaced by the
3616    new value.
3617    
3618    =item newValue
3619    
3620    New value to be substituted for the old value when it's found.
3621    
3622    =item filter
3623    
3624    A standard ERDB filter clause (see L</Get>). The filter will be applied before any substitutions take place.
3625    
3626    =item parms
3627    
3628    Reference to a list of parameter values in the filter.
3629    
3630    =item RETURN
3631    
3632    Returns the number of rows modified.
3633    
3634    =back
3635    
3636    =cut
3637    
3638    sub UpdateField {
3639        # Get the parameters.
3640        my ($self, $fieldName, $oldValue, $newValue, $filter, $parms) = @_;
3641        # Get the object and field names from the field name parameter.
3642        $fieldName =~ /^([^(]+)\(([^)]+)\)/;
3643        my $objectName = $1;
3644        my $realFieldName = _FixName($2);
3645        # Add the old value to the filter. Note we allow the possibility that no
3646        # filter was specified.
3647        my $realFilter = "$fieldName = ?";
3648        if ($filter) {
3649            $realFilter .= " AND $filter";
3650        }
3651        # Format the query filter.
3652        my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
3653            $self->_SetupSQL([$objectName], $realFilter);
3654        # Create the query. Since there is only one object name, the mapped-name data is not
3655        # necessary. Neither is the FROM clause.
3656        $suffix =~ s/^FROM.+WHERE\s+//;
3657        # Create the update statement.
3658        my $command = "UPDATE $objectName SET $realFieldName = ? WHERE $suffix";
3659        # Get the database handle.
3660        my $dbh = $self->{_dbh};
3661        # Add the old and new values to the parameter list. Note we allow the possibility that
3662        # there are no user-supplied parameters.
3663        my @params = ($newValue, $oldValue);
3664        if (defined $parms) {
3665            push @params, @{$parms};
3666        }
3667        # Execute the update.
3668        my $retVal = $dbh->SQL($command, 0, @params);
3669        # Make the funky zero a real zero.
3670        if ($retVal == 0) {
3671            $retVal = 0;
3672        }
3673        # Return the result.
3674        return $retVal;
3675    }
3676    
3677    
3678  =head2 Data Mining Methods  =head2 Data Mining Methods
3679    
3680  =head3 GetUsefulCrossValues  =head3 GetUsefulCrossValues
# Line 2240  Line 3735 
3735      # Push these onto the return list.      # Push these onto the return list.
3736      push @retVal, sort @fieldList2;      push @retVal, sort @fieldList2;
3737      # Return the result.      # Return the result.
3738      return @retVal;      return @retVal;
3739    }
3740    
3741    =head3 FindColumn
3742    
3743    C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>
3744    
3745    Return the location a desired column in a data mining header line. The data
3746    mining header line is a tab-separated list of column names. The column
3747    identifier is either the numerical index of a column or the actual column
3748    name.
3749    
3750    =over 4
3751    
3752    =item headerLine
3753    
3754    The header line from a data mining command, which consists of a tab-separated
3755    list of column names.
3756    
3757    =item columnIdentifier
3758    
3759    Either the ordinal number of the desired column (1-based), or the name of the
3760    desired column.
3761    
3762    =item RETURN
3763    
3764    Returns the array index (0-based) of the desired column.
3765    
3766    =back
3767    
3768    =cut
3769    
3770    sub FindColumn {
3771        # Get the parameters.
3772        my ($headerLine, $columnIdentifier) = @_;
3773        # Declare the return variable.
3774        my $retVal;
3775        # Split the header line into column names.
3776        my @headers = ParseColumns($headerLine);
3777        # Determine whether we have a number or a name.
3778        if ($columnIdentifier =~ /^\d+$/) {
3779            # Here we have a number. Subtract 1 and validate the result.
3780            $retVal = $columnIdentifier - 1;
3781            if ($retVal < 0 || $retVal > $#headers) {
3782                Confess("Invalid column identifer \"$columnIdentifier\": value out of range.");
3783            }
3784        } else {
3785            # Here we have a name. We need to find it in the list.
3786            for (my $i = 0; $i <= $#headers && ! defined($retVal); $i++) {
3787                if ($headers[$i] eq $columnIdentifier) {
3788                    $retVal = $i;
3789                }
3790            }
3791            if (! defined($retVal)) {
3792                Confess("Invalid column identifier \"$columnIdentifier\": value not found.");
3793            }
3794        }
3795        # Return the result.
3796        return $retVal;
3797    }
3798    
3799    =head3 ParseColumns
3800    
3801    C<< my @columns = ERDB::ParseColumns($line); >>
3802    
3803    Convert the specified data line to a list of columns.
3804    
3805    =over 4
3806    
3807    =item line
3808    
3809    A data mining input, consisting of a tab-separated list of columns terminated by a
3810    new-line.
3811    
3812    =item RETURN
3813    
3814    Returns a list consisting of the column values.
3815    
3816    =back
3817    
3818    =cut
3819    
3820    sub ParseColumns {
3821        # Get the parameters.
3822        my ($line) = @_;
3823        # Chop off the line-end.
3824        chomp $line;
3825        # Split it into a list.
3826        my @retVal = split(/\t/, $line);
3827        # Return the result.
3828        return @retVal;
3829    }
3830    
3831    =head2 Virtual Methods
3832    
3833    =head3 _CreatePPOIndex
3834    
3835    C<< my $index = ERDB::_CreatePPOIndex($indexObject); >>
3836    
3837    Convert the XML for an ERDB index to the XML structure for a PPO
3838    index.
3839    
3840    =over 4
3841    
3842    ERDB XML structure for an index.
3843    
3844    =item RETURN
3845    
3846    PPO XML structure for the same index.
3847    
3848    =back
3849    
3850    =cut
3851    
3852    sub _CreatePPOIndex {
3853        # Get the parameters.
3854        my ($indexObject) = @_;
3855        # The incoming index contains a list of the index fields in the IndexFields
3856        # member. We loop through it to create the index tags.
3857        my @fields = map { { label => _FixName($_->{name}) } } @{$indexObject->{IndexFields}};
3858        # Wrap the fields in attribute tags.
3859        my $retVal = { attribute => \@fields };
3860        # Return the result.
3861        return $retVal;
3862    }
3863    
3864    =head3 _CreatePPOField
3865    
3866    C<< my $fieldXML = ERDB::_CreatePPOField($fieldName, $fieldObject); >>
3867    
3868    Convert the ERDB XML structure for a field to a PPO scalar XML structure.
3869    
3870    =over 4
3871    
3872    =item fieldName
3873    
3874    Name of the scalar field.
3875    
3876    =item fieldObject
3877    
3878    ERDB XML structure describing the field.
3879    
3880    =item RETURN
3881    
3882    Returns a PPO XML structure for the same field.
3883    
3884    =back
3885    
3886    =cut
3887    
3888    sub _CreatePPOField {
3889        # Get the parameters.
3890        my ($fieldName, $fieldObject) = @_;
3891        # Get the field type.
3892        my $type = $TypeTable{$fieldObject->{type}}->{sqlType};
3893        # Fix up the field name.
3894        $fieldName = _FixName($fieldName);
3895        # Build the scalar tag.
3896        my $retVal = { label => $fieldName, type => $type };
3897        # Return the result.
3898        return $retVal;
3899  }  }
3900    
3901  =head3 FindColumn  =head3 CleanKeywords
3902    
3903  C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>  C<< my $cleanedString = $erdb->CleanKeywords($searchExpression); >>
3904    
3905  Return the location a desired column in a data mining header line. The data  Clean up a search expression or keyword list. This is a virtual method that may
3906  mining header line is a tab-separated list of column names. The column  be overridden by the subclass. The base-class method removes extra spaces
3907  identifier is either the numerical index of a column or the actual column  and converts everything to lower case.
 name.  
3908    
3909  =over 4  =over 4
3910    
3911  =item headerLine  =item searchExpression
   
 The header line from a data mining command, which consists of a tab-separated  
 list of column names.  
   
 =item columnIdentifier  
3912    
3913  Either the ordinal number of the desired column (1-based), or the name of the  Search expression or keyword list to clean. Note that a search expression may
3914  desired column.  contain boolean operators which need to be preserved. This includes leading
3915    minus signs.
3916    
3917  =item RETURN  =item RETURN
3918    
3919  Returns the array index (0-based) of the desired column.  Cleaned expression or keyword list.
3920    
3921  =back  =back
3922    
3923  =cut  =cut
3924    
3925  sub FindColumn {  sub CleanKeywords {
3926      # Get the parameters.      # Get the parameters.
3927      my ($headerLine, $columnIdentifier) = @_;      my ($self, $searchExpression) = @_;
3928      # Declare the return variable.      # Lower-case the expression and copy it into the return variable. Note that we insure we
3929      my $retVal;      # don't accidentally end up with an undefined value.
3930      # Split the header line into column names.      my $retVal = lc($searchExpression || "");
3931      my @headers = ParseColumns($headerLine);      # Remove extra spaces.
3932      # Determine whether we have a number or a name.      $retVal =~ s/\s+/ /g;
3933      if ($columnIdentifier =~ /^\d+$/) {      $retVal =~ s/(^\s+)|(\s+$)//g;
         # Here we have a number. Subtract 1 and validate the result.  
         $retVal = $columnIdentifier - 1;  
         if ($retVal < 0 || $retVal > $#headers) {  
             Confess("Invalid column identifer \"$columnIdentifier\": value out of range.");  
         }  
     } else {  
         # Here we have a name. We need to find it in the list.  
         for (my $i = 0; $i <= $#headers && ! defined($retVal); $i++) {  
             if ($headers[$i] eq $columnIdentifier) {  
                 $retVal = $i;  
             }  
         }  
         if (! defined($retVal)) {  
             Confess("Invalid column identifier \"$columnIdentifier\": value not found.");  
         }  
     }  
3934      # Return the result.      # Return the result.
3935      return $retVal;      return $retVal;
3936  }  }
3937    
3938  =head3 ParseColumns  =head3 GetSourceObject
3939    
3940  C<< my @columns = ERDB::ParseColumns($line); >>  C<< my $source = $erdb->GetSourceObject($entityName); >>
3941    
3942  Convert the specified data line to a list of columns.  Return the object to be used in loading special attributes of the specified entity. The
3943    algorithm for loading special attributes is stored in the C<DataGen> elements of the
3944    XML
3945    
3946    =head2 Internal Utility Methods
3947    
3948    =head3 _RelationMap
3949    
3950    C<< my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef); >>
3951    
3952    Create the relation map for an SQL query. The relation map is used by B<ERDBObject>
3953    to determine how to interpret the results of the query.
3954    
3955  =over 4  =over 4
3956    
3957  =item line  =item mappedNameHashRef
3958    
3959  A data mining input, consisting of a tab-separated list of columns terminated by a  Reference to a hash that maps modified object names to real object names.
3960  new-line.  
3961    =item mappedNameListRef
3962    
3963    Reference to a list of modified object names in the order they appear in the
3964    SELECT list.
3965    
3966  =item RETURN  =item RETURN
3967    
3968  Returns a list consisting of the column values.  Returns a list of 2-tuples. Each tuple consists of an object name as used in the
3969    query followed by the actual name of that object. This enables the B<ERDBObject> to
3970    determine the order of the tables in the query and which object name belongs to each
3971    mapped object name. Most of the time these two values are the same; however, if a
3972    relation occurs twice in the query, the relation name in the field list and WHERE
3973    clause will use a mapped name (generally the actual relation name with a numeric
3974    suffix) that does not match the actual relation name.
3975    
3976  =back  =back
3977    
3978  =cut  =cut
3979    
3980  sub ParseColumns {  sub _RelationMap {
3981      # Get the parameters.      # Get the parameters.
3982      my ($line) = @_;      my ($mappedNameHashRef, $mappedNameListRef) = @_;
3983      # Chop off the line-end.      # Declare the return variable.
3984      chomp $line;      my @retVal = ();
3985      # Split it into a list.      # Build the map.
3986      my @retVal = split(/\t/, $line);      for my $mappedName (@{$mappedNameListRef}) {
3987      # Return the result.          push @retVal, [$mappedName, $mappedNameHashRef->{$mappedName}];
3988        }
3989        # Return it.
3990      return @retVal;      return @retVal;
3991  }  }
3992    
 =head2 Internal Utility Methods  
3993    
3994  =head3 SetupSQL  =head3 _SetupSQL
3995    
3996  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
3997  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 2355  Line 4011 
4011  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
4012  optionally the C<ORDER BY> and C<LIMIT> clauses.  optionally the C<ORDER BY> and C<LIMIT> clauses.
4013    
4014    =item matchClause
4015    
4016    An optional full-text search clause. If specified, it will be inserted at the
4017    front of the WHERE clause. It should already be SQL-formatted; that is, the
4018    field names should be in the form I<table>C<.>I<fieldName>.
4019    
4020  =item RETURN  =item RETURN
4021    
4022  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 2367  Line 4029 
4029  =cut  =cut
4030    
4031  sub _SetupSQL {  sub _SetupSQL {
4032      my ($self, $objectNames, $filterClause) = @_;      my ($self, $objectNames, $filterClause, $matchClause) = @_;
4033      # 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
4034      # 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
4035      # 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 2416  Line 4078 
4078      # FROM name1, name2, ... nameN      # FROM name1, name2, ... nameN
4079      #      #
4080      my $suffix = "FROM " . join(', ', @fromList);      my $suffix = "FROM " . join(', ', @fromList);
4081        # Now for the WHERE. First, we need a place for the filter string.
4082        my $filterString = "";
4083        # We will also keep a list of conditions to add to the WHERE clause in order to link
4084        # entities and relationships as well as primary relations to secondary ones.
4085        my @joinWhere = ();
4086      # Check for a filter clause.      # Check for a filter clause.
4087      if ($filterClause) {      if ($filterClause) {
4088          # 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,
4089          # We create a copy of the filter string we can work with.          # We create a copy of the filter string we can work with.
4090          my $filterString = $filterClause;          $filterString = $filterClause;
4091          # Next, we sort the object names by length. This helps protect us from finding          # Next, we sort the object names by length. This helps protect us from finding
4092          # object names inside other object names when we're doing our search and replace.          # object names inside other object names when we're doing our search and replace.
4093          my @sortedNames = sort { length($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 = ();  
4094          # 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
4095          # 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
4096          # 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 2494  Line 4158 
4158                  }                  }
4159              }              }
4160          }          }
4161        }
4162          # 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
4163          # 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
4164          # 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
4165          # list before running through it.      # list before running through it, because we shift off the first object before
4166        # processing the rest.
4167          my @mappedObjectList = @mappedNameList;          my @mappedObjectList = @mappedNameList;
4168          my $lastMappedObject = shift @mappedObjectList;          my $lastMappedObject = shift @mappedObjectList;
4169          # Get the join table.          # Get the join table.
# Line 2526  Line 4192 
4192          # 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.
4193          # We'll put the ORDER BY / LIMIT clauses in the following variable.          # We'll put the ORDER BY / LIMIT clauses in the following variable.
4194          my $orderClause = "";          my $orderClause = "";
4195        # This is only necessary if we have a filter string in which the ORDER BY
4196        # and LIMIT clauses can live.
4197        if ($filterString) {
4198          # 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
4199          # operator so that we find the first occurrence of either verb.          # operator so that we find the first occurrence of either verb.
4200          if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {          if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {
# Line 2534  Line 4203 
4203              $orderClause = $2 . substr($filterString, $pos);              $orderClause = $2 . substr($filterString, $pos);
4204              $filterString = $1;              $filterString = $1;
4205          }          }
4206          # Add the filter and the join clauses (if any) to the SELECT command.      }
4207        # All the things that are supposed to be in the WHERE clause of the
4208        # SELECT command need to be put into @joinWhere so we can string them
4209        # together. We begin with the match clause. This is important,
4210        # because the match clause's parameter mark must precede any parameter
4211        # marks in the filter string.
4212        if ($matchClause) {
4213            push @joinWhere, $matchClause;
4214        }
4215        # Add the filter string. We put it in parentheses to avoid operator
4216        # precedence problems with the match clause or the joins.
4217          if ($filterString) {          if ($filterString) {
4218              Trace("Filter string is \"$filterString\".") if T(4);              Trace("Filter string is \"$filterString\".") if T(4);
4219              push @joinWhere, "($filterString)";              push @joinWhere, "($filterString)";
4220          }          }
4221        # String it all together into a big filter clause.
4222          if (@joinWhere) {          if (@joinWhere) {
4223              $suffix .= " WHERE " . join(' AND ', @joinWhere);              $suffix .= " WHERE " . join(' AND ', @joinWhere);
4224          }          }
4225          # Add the sort or limit clause (if any) to the SELECT command.      # Add the sort or limit clause (if any).
4226          if ($orderClause) {          if ($orderClause) {
4227              $suffix .= " $orderClause";              $suffix .= " $orderClause";
4228          }          }
     }  
4229      # Return the suffix, the mapped name list, and the mapped name hash.      # Return the suffix, the mapped name list, and the mapped name hash.
4230      return ($suffix, \@mappedNameList, \%mappedNameHash);      return ($suffix, \@mappedNameList, \%mappedNameHash);
4231  }  }
4232    
4233  =head3 GetStatementHandle  =head3 _GetStatementHandle
4234    
4235  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.
4236  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 2589  Line 4268 
4268      # Prepare the command.      # Prepare the command.
4269      my $sth = $dbh->prepare_command($command);      my $sth = $dbh->prepare_command($command);
4270      # Execute it with the parameters bound in.      # Execute it with the parameters bound in.
4271      $sth->execute(@{$params}) || Confess("SELECT error" . $sth->errstr());      $sth->execute(@{$params}) || Confess("SELECT error:  " . $sth->errstr());
4272      # Return the statement handle.      # Return the statement handle.
4273      return $sth;      return $sth;
4274  }  }
4275    
4276  =head3 GetLoadStats  =head3 _GetLoadStats
4277    
4278  Return a blank statistics object for use by the load methods.  Return a blank statistics object for use by the load methods.
4279    
# Line 2606  Line 4285 
4285      return Stats->new();      return Stats->new();
4286  }  }
4287    
4288  =head3 GenerateFields  =head3 _DumpRelation
   
 Generate field values from a field structure and store in a specified table. The field names  
 are first sorted by pass count, certain pre-defined fields are removed from the list, and  
 then we rip through them evaluation the data generation string. Fields in the primary relation  
 are stored as scalars; fields in secondary relations are stored as value lists.  
   
 This is a static method.  
   
 =over 4  
   
 =item this  
   
 Hash table into which the field values should be placed.  
   
 =item fields  
   
 Field structure from which the field descriptors should be taken.  
   
 =item type  
   
 Type name of the object whose fields are being generated.  
   
 =item values (optional)  
   
 Reference to a value structure from which additional values can be taken.  
   
 =item from (optiona)  
   
 Reference to the source entity instance if relationship data is being generated.  
   
 =item to (optional)  
   
 Reference to the target entity instance if relationship data is being generated.  
   
 =back  
   
 =cut  
   
 sub _GenerateFields {  
     # Get the parameters.  
     my ($this, $fields, $type, $values, $from, $to) = @_;  
     # Sort the field names by pass number.  
     my @fieldNames = sort { $fields->{$a}->{DataGen}->{pass} <=> $fields->{$b}->{DataGen}->{pass} } keys %{$fields};  
     # Loop through the field names, generating data.  
     for my $name (@fieldNames) {  
         # Only proceed if this field needs to be generated.  
         if (!exists $this->{$name}) {  
             # Get this field's data generation descriptor.  
             my $fieldDescriptor = $fields->{$name};  
             my $data = $fieldDescriptor->{DataGen};  
             # Get the code to generate the field value.  
             my $codeString = $data->{content};  
             # Determine whether or not this field is in the primary relation.  
             if ($fieldDescriptor->{relation} eq $type) {  
                 # Here we have a primary relation field. Store the field value as  
                 # a scalar.  
                 $this->{$name} = eval($codeString);  
             } else {  
                 # Here we have a secondary relation field. Create a null list  
                 # and push the desired number of field values onto it.  
                 my @fieldValues = ();  
                 my $count = IntGen(0,$data->{testCount});  
                 for (my $i = 0; $i < $count; $i++) {  
                     my $newValue = eval($codeString);  
                     push @fieldValues, $newValue;  
                 }  
                 # Store the value list in the main hash.  
                 $this->{$name} = \@fieldValues;  
             }  
         }  
     }  
 }  
   
 =head3 DumpRelation  
4289    
4290  Dump the specified relation's to the specified output file in tab-delimited format.  Dump the specified relation to the specified output file in tab-delimited format.
4291    
4292  This is an instance method.  This is an instance method.
4293    
# Line 2730  Line 4335 
4335      close DTXOUT;      close DTXOUT;
4336  }  }
4337    
4338  =head3 GetStructure  =head3 _GetStructure
4339    
4340  Get the data structure for a specified entity or relationship.  Get the data structure for a specified entity or relationship.
4341    
# Line 2769  Line 4374 
4374      return $retVal;      return $retVal;
4375  }  }
4376    
4377  =head3 GetRelationTable  
4378    
4379    =head3 _GetRelationTable
4380    
4381  Get the list of relations for a specified entity or relationship.  Get the list of relations for a specified entity or relationship.
4382    
# Line 2798  Line 4405 
4405      return $objectData->{Relations};      return $objectData->{Relations};
4406  }  }
4407    
4408  =head3 ValidateFieldNames  =head3 _ValidateFieldNames
4409    
4410  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
4411  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 2825  Line 4432 
4432          for my $object (values %{$metadata->{$section}}) {          for my $object (values %{$metadata->{$section}}) {
4433              # Loop through the object's fields.              # Loop through the object's fields.
4434              for my $fieldName (keys %{$object->{Fields}}) {              for my $fieldName (keys %{$object->{Fields}}) {
4435                  # Now we make some initial validations.                  # If this field name is invalid, set the return value to zero
4436                  if ($fieldName =~ /--/) {                  # so we know we encountered an error.
4437                      # Here we have a doubled minus sign.                  if (! ValidateFieldName($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";  
4438                          $retVal = 0;                          $retVal = 0;
4439                      }                      }
4440                  }                  }
4441              }              }
4442          }          }
     }  
4443      # If an error was found, fail.      # If an error was found, fail.
4444      if ($retVal  == 0) {      if ($retVal  == 0) {
4445          Confess("Errors found in field names.");          Confess("Errors found in field names.");
4446      }      }
4447  }  }
4448    
4449  =head3 LoadRelation  =head3 _LoadRelation
4450    
4451  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
4452  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 2913  Line 4506 
4506      return $retVal;      return $retVal;
4507  }  }
4508    
4509  =head3 LoadMetaData  
4510    =head3 _LoadMetaData
4511    
4512    C<< my $metadata = ERDB::_LoadMetaData($filename); >>
4513    
4514  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.
4515  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 2938  Line 4534 
4534  sub _LoadMetaData {  sub _LoadMetaData {
4535      # Get the parameters.      # Get the parameters.
4536      my ($filename) = @_;      my ($filename) = @_;
4537      Trace("Reading Sprout DBD from $filename.") if T(2);      Trace("Reading DBD from $filename.") if T(2);
4538      # 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
4539      # get the exact structure we want.      # get the exact structure we want.
4540      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 $filename.") if T(1);  
4541      # Before we go any farther, we need to validate the field and object names. If an error is found,      # Before we go any farther, we need to validate the field and object names. If an error is found,
4542      # the method below will fail.      # the method below will fail.
4543      _ValidateFieldNames($metadata);      _ValidateFieldNames($metadata);
# Line 3077  Line 4660 
4660              if ($found == 0) {              if ($found == 0) {
4661                  push @{$indexList}, { IndexFields => [ {name => 'id', order => 'ascending'} ] };                  push @{$indexList}, { IndexFields => [ {name => 'id', order => 'ascending'} ] };
4662              }              }
4663              # Now we need to convert the relation's index list to an index table. We begin by creating              # Attach all the indexes to the relation.
4664              # an empty table in the relation structure.              _ProcessIndexes($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++;  
             }  
4665          }          }
4666          # Finally, we add the relation structure to the entity.          # Finally, we add the relation structure to the entity.
4667          $entityStructure->{Relations} = $relationTable;          $entityStructure->{Relations} = $relationTable;
# Line 3101  Line 4675 
4675          _FixupFields($relationshipStructure, $relationshipName, 2, 3);          _FixupFields($relationshipStructure, $relationshipName, 2, 3);
4676          # Format a description for the FROM field.          # Format a description for the FROM field.
4677          my $fromEntity = $relationshipStructure->{from};          my $fromEntity = $relationshipStructure->{from};
4678          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].";
4679          # Get the FROM entity's key type.          # Get the FROM entity's key type.
4680          my $fromType = $entityList->{$fromEntity}->{keyType};          my $fromType = $entityList->{$fromEntity}->{keyType};
4681          # Add the FROM field.          # Add the FROM field.
# Line 3111  Line 4685 
4685                                                      PrettySort => 1});                                                      PrettySort => 1});
4686          # Format a description for the TO field.          # Format a description for the TO field.
4687          my $toEntity = $relationshipStructure->{to};          my $toEntity = $relationshipStructure->{to};
4688          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].";
4689          # Get the TO entity's key type.          # Get the TO entity's key type.
4690          my $toType = $entityList->{$toEntity}->{keyType};          my $toType = $entityList->{$toEntity}->{keyType};
4691          # Add the TO field.          # Add the TO field.
# Line 3123  Line 4697 
4697          my $thisRelation = { Fields => _ReOrderRelationTable($relationshipStructure->{Fields}),          my $thisRelation = { Fields => _ReOrderRelationTable($relationshipStructure->{Fields}),
4698                               Indexes => { } };                               Indexes => { } };
4699          $relationshipStructure->{Relations} = { $relationshipName => $thisRelation };          $relationshipStructure->{Relations} = { $relationshipName => $thisRelation };
4700    
4701            # Add the alternate indexes (if any). This MUST be done before the FROM and
4702            # TO indexes, because it erases the relation's index list.
4703            if (exists $relationshipStructure->{Indexes}) {
4704                _ProcessIndexes($relationshipStructure->{Indexes}, $thisRelation);
4705            }
4706            # Add the relation to the master table.
4707          # Create the FROM and TO indexes.          # Create the FROM and TO indexes.
4708          _CreateRelationshipIndex("From", $relationshipName, $relationshipStructure);          _CreateRelationshipIndex("From", $relationshipName, $relationshipStructure);
4709          _CreateRelationshipIndex("To", $relationshipName, $relationshipStructure);          _CreateRelationshipIndex("To", $relationshipName, $relationshipStructure);
         # Add the relation to the master table.  
4710          $masterRelationTable{$relationshipName} = $thisRelation;          $masterRelationTable{$relationshipName} = $thisRelation;
4711      }      }
4712      # Now store the master relation table in the metadata structure.      # Now store the master relation table in the metadata structure.
# Line 3214  Line 4794 
4794                      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);
4795                      # Join from the left.                      # Join from the left.
4796                      $joinTable{"$relationshipName/$otherName"} =                      $joinTable{"$relationshipName/$otherName"} =
4797                          "$linkField = $otherName.from_link";                          "$linkField = $otherName.from_link";
4798                      # Join from the right.                      # Join from the right.
4799                      $joinTable{"$otherName/$relationshipName"} =                      $joinTable{"$otherName/$relationshipName"} =
4800                          "$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 $parms = $erdb->SortNeeded($relationName); >>  
   
 Return the pipe command for the sort that should be applied to the specified  
 relation when creating the load file.  
   
 For example, if the load file should be sorted ascending by the first  
 field with duplicates removed, this method would return  
   
     sort -k 1 -u -t "\t"  
   
 If the first field is numeric and duplicates are okay, the method would  
 return  
   
     sort -k 1n -t "\t"  
   
 =over 4  
   
 =item relationName  
   
 Name of the relation to be examined.  
   
 =item  
   
 Returns the sort command to use for sorting the relation, suitable for piping.  
   
 =back  
   
 =cut  
 #: Return Type $;  
 sub SortNeeded {  
     # Get the parameters.  
     my ($self, $relationName) = @_;  
     # Declare a descriptor to hold the names of the key fields.  
     my @keyNames = ();  
     # Declare a flag for indicating uniqueness.  
     my $unique;  
     # Get the relation structure.  
     my $relationData = $self->_FindRelation($relationName);  
     # Find out if the relation is a primary entity relation,  
     # a relationship relation, or a secondary entity relation.  
     my $entityTable = $self->{_metaData}->{Entities};  
     my $relationshipTable = $self->{_metaData}->{Relationships};  
     if (exists $entityTable->{$relationName}) {  
         # Here we have a primary entity relation, so we have a unique sort on the  
         # ID field.  
         $unique = "-u ";  
         push @keyNames, "id";  
     } elsif (exists $relationshipTable->{$relationName}) {  
         # Here we have a relationship. We sort using the FROM index.  
         $unique = "";  
         my $relationshipData = $relationshipTable->{$relationName};  
         my $index = $relationData->{Indexes}->{"idx${relationName}From"};  
         push @keyNames, @{$index->{IndexFields}};  
     } else {  
         # Here we have a secondary entity relation, so we have a non-unique sort on  
         # the ID field.  
         $unique = "";  
         push @keyNames, "id";  
     }  
     # Now we parse the key names into sort parameters. First, we prime the return  
     # string.  
     my $retVal = "sort -t \"\t\" $unique";  
     # Get the relation's field list.  
     my @fields = @{$relationData->{Fields}};  
     # Loop through the keys.  
     for my $keyData (@keyNames) {  
         # Get the key and the ordering.  
         my ($keyName, $ordering);  
         if ($keyData =~ /^([^ ]+) DESC/) {  
             ($keyName, $ordering) = ($1, "descending");  
         } else {  
             ($keyName, $ordering) = ($keyData, "ascending");  
         }  
         # Find the key's position and type.  
         my $fieldSpec;  
         for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {  
             my $thisField = $fields[$i];  
             if ($thisField->{name} eq $keyName) {  
                 # Get the sort modifier for this field type. The modifier  
                 # decides whether we're using a character, numeric, or  
                 # floating-point sort.  
                 my $modifier = $TypeTable{$thisField->{type}}->{sort};  
                 # If the index is descending for this field, denote we want  
                 # to reverse the sort order on this field.  
                 if ($ordering eq 'descending') {  
                     $modifier .= "r";  
4801                  }                  }
                 # Store the position and modifier into the field spec, which  
                 # will stop the inner loop.  
                 $fieldSpec = "$i$modifier";  
4802              }              }
4803          }          }
4804          # Add this field to the sort command.          # Create entity joins for the recursive relationships. Unlike the non-recursive
4805          $retVal .= " -k $fieldSpec";          # joins, the direction makes a difference with the recursive joins. This can give
4806            # rise to situations where we can't create the path we want; however, it is always
4807            # possible to get the same effect using multiple queries.
4808            for my $relationshipName (@bothList) {
4809                Trace("Setting up entity joins to recursive relationship $relationshipName with $entityName.") if T(metadata => 4);
4810                # Join to the entity from each direction.
4811                $joinTable{"$entityName/$relationshipName"} =
4812                    "$entityName.id = $relationshipName.from_link";
4813                $joinTable{"$relationshipName/$entityName"} =
4814                    "$relationshipName.to_link = $entityName.id";
4815      }      }
4816      # Return the result.      }
4817      return $retVal;      # Add the join table to the structure.
4818        $metadata->{Joins} = \%joinTable;
4819        # Return the slurped and fixed-up structure.
4820        return $metadata;
4821  }  }
4822    
4823  =head3 CreateRelationshipIndex  =head3 _CreateRelationshipIndex
4824    
4825  Create an index for a relationship's relation.  Create an index for a relationship's relation.
4826    
# Line 3383  Line 4862 
4862          $newIndex->{Unique} = 'true';          $newIndex->{Unique} = 'true';
4863      }      }
4864      # Add the index to the relation.      # Add the index to the relation.
4865      _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);      _AddIndex("idx$indexKey", $relationStructure, $newIndex);
4866    }
4867    
4868    =head3 _ProcessIndexes
4869    
4870    C<< ERDB::_ProcessIndexes($indexList, $relation); >>
4871    
4872    Build the data structures for the specified indexes in the specified relation.
4873    
4874    =over 4
4875    
4876    =item indexList
4877    
4878    Reference to a list of indexes. Each index is a hash reference containing an optional
4879    C<Notes> value that describes the index and an C<IndexFields> value that is a reference
4880    to a list of index field structures. An index field structure, in turn, is a reference
4881    to a hash that contains a C<name> attribute for the field name and an C<order>
4882    attribute that specifies either C<ascending> or C<descending>. In this sense the
4883    index list encapsulates the XML C<Indexes> structure in the database definition.
4884    
4885    =item relation
4886    
4887    The structure that describes the current relation. The new index descriptors will
4888    be stored in the structure's C<Indexes> member. Any previous data in the structure
4889    will be lost.
4890    
4891    =back
4892    
4893    =cut
4894    
4895    sub _ProcessIndexes {
4896        # Get the parameters.
4897        my ($indexList, $relation) = @_;
4898        # Now we need to convert the relation's index list to an index table. We begin by creating
4899        # an empty table in the relation structure.
4900        $relation->{Indexes} = { };
4901        # Loop through the indexes.
4902        my $count = 0;
4903        for my $index (@{$indexList}) {
4904            # Add this index to the index table.
4905            _AddIndex("idx$count", $relation, $index);
4906            # Increment the counter so that the next index has a different name.
4907            $count++;
4908        }
4909  }  }
4910    
4911  =head3 AddIndex  =head3 _AddIndex
4912    
4913  Add an index to a relation structure.  Add an index to a relation structure.
4914    
# Line 3432  Line 4954 
4954      $relationStructure->{Indexes}->{$indexName} = $newIndex;      $relationStructure->{Indexes}->{$indexName} = $newIndex;
4955  }  }
4956    
4957  =head3 FixupFields  =head3 _FixupFields
4958    
4959  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
4960  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 3470  Line 4992 
4992          # Here it doesn't, so we create a new one.          # Here it doesn't, so we create a new one.
4993          $structure->{Fields} = { };          $structure->{Fields} = { };
4994      } else {      } else {
4995          # 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
4996            # create a list for stashing them.
4997            my @textFields = ();
4998            # Loop through the fields.
4999          my $fieldStructures = $structure->{Fields};          my $fieldStructures = $structure->{Fields};
5000          for my $fieldName (keys %{$fieldStructures}) {          for my $fieldName (keys %{$fieldStructures}) {
5001              Trace("Processing field $fieldName of $defaultRelationName.") if T(4);              Trace("Processing field $fieldName of $defaultRelationName.") if T(4);
# Line 3479  Line 5004 
5004              my $type = $fieldData->{type};              my $type = $fieldData->{type};
5005              # Plug in a relation name if it is needed.              # Plug in a relation name if it is needed.
5006              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });
5007              # Plug in a data generator if we need one.              # Check for searchability.
5008              if (!exists $fieldData->{DataGen}) {              if ($fieldData->{searchable}) {
5009                  # The data generator will use the default for the field's type.                  # Only allow this for a primary relation.
5010                  $fieldData->{DataGen} = { content => $TypeTable{$type}->{dataGen} };                  if ($fieldData->{relation} ne $defaultRelationName) {
5011                        Confess("Field $fieldName of $defaultRelationName is in secondary relations and cannot be searchable.");
5012                    } else {
5013                        push @textFields, $fieldName;
5014                    }
5015              }              }
             # Plug in the defaults for the optional data generation parameters.  
             Tracer::MergeOptions($fieldData->{DataGen}, { testCount => 1, pass => 0 });  
5016              # Add the PrettySortValue.              # Add the PrettySortValue.
5017              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);
5018          }          }
5019            # If there are searchable fields, remember the fact.
5020            if (@textFields) {
5021                $structure->{searchFields} = \@textFields;
5022            }
5023      }      }
5024  }  }
5025    
5026  =head3 FixName  =head3 _FixName
5027    
5028  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.
5029    
# Line 3521  Line 5052 
5052      return $fieldName;      return $fieldName;
5053  }  }
5054    
5055  =head3 FixNames  =head3 _FixNames
5056    
5057  Fix all the field names in a list.  Fix all the field names in a list.
5058    
# Line 3552  Line 5083 
5083      return @result;      return @result;
5084  }  }
5085    
5086  =head3 AddField  =head3 _AddField
5087    
5088  Add a field to a field list.  Add a field to a field list.
5089    
# Line 3587  Line 5118 
5118      $fieldList->{$fieldName} = $fieldStructure;      $fieldList->{$fieldName} = $fieldStructure;
5119  }  }
5120    
5121  =head3 ReOrderRelationTable  =head3 _ReOrderRelationTable
5122    
5123  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
5124  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 3648  Line 5179 
5179    
5180  }  }
5181    
5182  =head3 IsPrimary  =head3 _IsPrimary
5183    
5184  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
5185  if it has the same name as an entity or relationship.  if it has the same name as an entity or relationship.
# Line 3684  Line 5215 
5215      return $retVal;      return $retVal;
5216  }  }
5217    
5218  =head3 FindRelation  =head3 _FindRelation
5219    
5220  Return the descriptor for the specified relation.  Return the descriptor for the specified relation.
5221    
# Line 3715  Line 5246 
5246    
5247  =head2 HTML Documentation Utility Methods  =head2 HTML Documentation Utility Methods
5248    
5249  =head3 ComputeRelationshipSentence  =head3 _ComputeRelationshipSentence
5250    
5251  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
5252  two related entities and an arity indicator.  two related entities and an arity indicator.
# Line 3753  Line 5284 
5284      return $result;      return $result;
5285  }  }
5286    
5287  =head3 ComputeRelationshipHeading  =head3 _ComputeRelationshipHeading
5288    
5289  The relationship heading is the L<relationship sentence|/ComputeRelationshipSentence> with the entity  The relationship heading is the L<relationship sentence|/ComputeRelationshipSentence> with the entity
5290  names hyperlinked to the appropriate entity sections of the document.  names hyperlinked to the appropriate entity sections of the document.
# Line 3790  Line 5321 
5321      return $result;      return $result;
5322  }  }
5323    
5324  =head3 ShowRelationTable  =head3 _ShowRelationTable
5325    
5326  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
5327  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 3840  Line 5371 
5371          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";
5372          # Add any note text.          # Add any note text.
5373          if (my $note = $indexData->{Notes}) {          if (my $note = $indexData->{Notes}) {
5374              $htmlString .= "<li>" . _HTMLNote($note->{content}) . "</li>\n";              $htmlString .= "<li>" . HTMLNote($note->{content}) . "</li>\n";
5375          }          }
5376          # Add the fiield list.          # Add the fiield list.
5377          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";
# Line 3851  Line 5382 
5382      $htmlString .= "</ul>\n";      $htmlString .= "</ul>\n";
5383  }  }
5384    
5385  =head3 OpenFieldTable  =head3 _OpenFieldTable
5386    
5387  This method creates the header string for the field table generated by L</ShowMetaData>.  This method creates the header string for the field table generated by L</ShowMetaData>.
5388    
# Line 3876  Line 5407 
5407      return _OpenTable($tablename, 'Field', 'Type', 'Description');      return _OpenTable($tablename, 'Field', 'Type', 'Description');
5408  }  }
5409    
5410  =head3 OpenTable  =head3 _OpenTable
5411    
5412  This method creates the header string for an HTML table.  This method creates the header string for an HTML table.
5413    
# Line 3906  Line 5437 
5437      # Compute the number of columns.      # Compute the number of columns.
5438      my $colCount = @colNames;      my $colCount = @colNames;
5439      # Generate the title row.      # Generate the title row.
5440      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";
5441      # Loop through the columns, adding the column header rows.      # Loop through the columns, adding the column header rows.
5442      $htmlString .= "<tr>";      $htmlString .= "<tr>";
5443      for my $colName (@colNames) {      for my $colName (@colNames) {
# Line 3916  Line 5447 
5447      return $htmlString;      return $htmlString;
5448  }  }
5449    
5450  =head3 CloseTable  =head3 _CloseTable
5451    
5452  This method returns the HTML for closing a table.  This method returns the HTML for closing a table.
5453    
# Line 3925  Line 5456 
5456  =cut  =cut
5457    
5458  sub _CloseTable {  sub _CloseTable {
5459      return "</table></p>\n";      return "</table>\n";
5460  }  }
5461    
5462  =head3 ShowField  =head3 _ShowField
5463    
5464  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.
5465    
# Line 3955  Line 5486 
5486      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>";
5487      # If we have content, add it as a third column.      # If we have content, add it as a third column.
5488      if (exists $fieldData->{Notes}) {      if (exists $fieldData->{Notes}) {
5489          $htmlString .= "<td>" . _HTMLNote($fieldData->{Notes}->{content}) . "</td>";          $htmlString .= "<td>" . HTMLNote($fieldData->{Notes}->{content}) . "</td>";
5490      }      }
5491      # Close off the row.      # Close off the row.
5492      $htmlString .= "</tr>\n";      $htmlString .= "</tr>\n";
# Line 3963  Line 5494 
5494      return $htmlString;      return $htmlString;
5495  }  }
5496    
 =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;  
 }  
   
5497  1;  1;

Legend:
Removed from v.1.61  
changed lines
  Added in v.1.92

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3