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

Diff of /Sprout/ERDB.pm

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

revision 1.73, Fri Nov 3 00:33:26 2006 UTC revision 1.90, Fri Apr 27 22:19:49 2007 UTC
# Line 6  Line 6 
6      use Data::Dumper;      use Data::Dumper;
7      use XML::Simple;      use XML::Simple;
8      use DBQuery;      use DBQuery;
9      use DBObject;      use ERDBObject;
10      use Stats;      use Stats;
11      use Time::HiRes qw(gettimeofday);      use Time::HiRes qw(gettimeofday);
12      use Digest::MD5 qw(md5_base64);      use Digest::MD5 qw(md5_base64);
     use FIG;  
13      use CGI;      use CGI;
14    
15  =head1 Entity-Relationship Database Package  =head1 Entity-Relationship Database Package
# Line 228  Line 227 
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 257  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 301  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 336  Line 338 
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. "avgLen" is the average byte length for estimating  # of the specified type. "avgLen" is the average byte length for estimating
341  # record sizes. "sort" is the key modifier for the sort command, "notes" is a type description.  # record sizes. "sort" is the key modifier for the sort command, "notes" is a type description,
342    # and "indexMod", if non-zero, is the number of characters to use when the field is specified in an
343    # index
344  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",
345                                 notes => "single ASCII character"},                                 indexMod =>   0, notes => "single ASCII character"},
346                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n",                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n",
347                                 notes => "signed 32-bit integer"},                                 indexMod =>   0, notes => "signed 32-bit integer"},
348                    counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n",                    counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n",
349                                 notes => "unsigned 32-bit integer"},                                 indexMod =>   0, notes => "unsigned 32-bit integer"},
350                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, sort => "",                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, sort => "",
351                                 notes => "character string, 0 to 255 characters"},                                 indexMod =>   0, notes => "character string, 0 to 255 characters"},
352                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, sort => "",                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, sort => "",
353                                 notes => "character string, nearly unlimited length, cannot be indexed"},                                 indexMod => 255, notes => "character string, nearly unlimited length, only first 255 characters are indexed"},
354                    date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, sort => "n",                    date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, sort => "n",
355                                 notes => "signed, 64-bit integer"},                                 indexMod =>   0, notes => "signed, 64-bit integer"},
356                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, sort => "g",                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, sort => "g",
357                                 notes => "64-bit double precision floating-point number"},                                 indexMod =>   0, notes => "64-bit double precision floating-point number"},
358                    boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, sort => "n",                    boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, sort => "n",
359                                 notes => "boolean value: 0 if false, 1 if true"},                                 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 => "",                               { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, sort => "",
362                                 notes => "string stored in digested form, used for certain types of key fields"},                                 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 => "",                               { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, sort => "",
365                                 notes => "character string, 0 to 25 characters"},                                 indexMod =>   0, notes => "character string, 0 to 25 characters"},
366                   'key-string' =>                   'key-string' =>
367                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, sort => "",                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, sort => "",
368                                 notes => "character string, 0 to 40 characters"},                                 indexMod =>   0, notes => "character string, 0 to 40 characters"},
369                   'name-string' =>                   'name-string' =>
370                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, sort => "",                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, sort => "",
371                                 notes => "character string, 0 to 80 characters"},                                 indexMod =>   0, notes => "character string, 0 to 80 characters"},
372                   'medium-string' =>                   'medium-string' =>
373                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",
374                                 notes => "character string, 0 to 160 characters"},                                 indexMod =>   0, notes => "character string, 0 to 160 characters"},
375                  );                  );
376    
377  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 392  Line 396 
396                   );                   );
397    
398  my %XmlInOpts  = (  my %XmlInOpts  = (
399                    ForceArray => ['Field', 'Index', 'IndexField'],                    ForceArray => ['Field', 'Index', 'IndexField', 'Relationship', 'Entity'],
400                    ForceContent => 1,                    ForceContent => 1,
401                    NormalizeSpace => 2,                    NormalizeSpace => 2,
402                   );                   );
# Line 544  Line 548 
548          if (my $notes = $entityData->{Notes}) {          if (my $notes = $entityData->{Notes}) {
549              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
550          }          }
551          # Now we want a list of the entity's relationships. First, we set up the relationship subsection.          # See if we need a list of the entity's relationships.
552            my $relCount = keys %{$relationshipList};
553            if ($relCount > 0) {
554                # First, we set up the relationship subsection.
555          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
556          # Loop through the relationships.          # Loop through the relationships.
557          for my $relationship (sort keys %{$relationshipList}) {          for my $relationship (sort keys %{$relationshipList}) {
# Line 560  Line 567 
567          }          }
568          # Close off the relationship list.          # Close off the relationship list.
569          $retVal .= "</ul>\n";          $retVal .= "</ul>\n";
570            }
571          # Get the entity's relations.          # Get the entity's relations.
572          my $relationList = $entityData->{Relations};          my $relationList = $entityData->{Relations};
573          # Create a header for the relation subsection.          # Create a header for the relation subsection.
# Line 646  Line 654 
654      return Data::Dumper::Dumper($self->{_metaData});      return Data::Dumper::Dumper($self->{_metaData});
655  }  }
656    
657    =head3 CreatePPO
658    
659    C<< ERDB::CreatePPO($erdbXMLFile, $ppoXMLFile); >>
660    
661    Create a PPO XML file from an ERDB data definition XML file. At the
662    current time, the PPO XML file can be used to create a database with
663    similar functionality. Eventually, the PPO will be able to use the
664    created XML to access the live ERDB database.
665    
666    =over 4
667    
668    =item erdbXMLFile
669    
670    Name of the XML data definition file for the ERDB database. This
671    file must exist.
672    
673    =item ppoXMLFile
674    
675    Output file for the PPO XML definition. If this file exists, it
676    will be overwritten.
677    
678    =back
679    
680    =cut
681    
682    sub CreatePPO {
683        # Get the parameters.
684        my ($erdbXMLFile, $ppoXMLFile) = @_;
685        # First, we want to slurp in the ERDB XML file in its raw form.
686        my $xml = ReadMetaXML($erdbXMLFile);
687        # Create a variable to hold all of the objects in the PPO project.
688        my @objects = ();
689        # Get the relationship hash.
690        my $relationships = $xml->{Relationships};
691        # Loop through the entities.
692        my $entities = $xml->{Entities};
693        for my $entityName (keys %{$entities}) {
694            # Get the entity's data structures.
695            my $entityObject = $entities->{$entityName};
696            # We put the object's fields in here, according to their type.
697            my (@object_refs, @scalars, @indexes, @arrays);
698            # Create the ID field for the entity. We get the key type from the
699            # entity object and compute the corresponding SQL type.
700            my $type = $TypeTable{$entityObject->{keyType}}->{sqlType};
701            push @scalars, { label => 'id', type => $type };
702            # Loop through the entity fields.
703            for my $fieldName ( keys %{$entityObject->{Fields}} ) {
704                # Get the field object.
705                my $fieldObject = $entityObject->{Fields}->{$fieldName};
706                # Convert it to a scalar tag.
707                my $scalar = _CreatePPOField($fieldName, $fieldObject);
708                # If we have a relation, this field is stored in an array.
709                # otherwise, it is a scalar. The array tag has scalars
710                # stored as an XML array. In ERDB, there is only ever one,
711                # but PPO can have more.
712                my $relation = $fieldObject->{relation};
713                if ($relation) {
714                    push @arrays, { scalar => [$scalar] };
715                } else {
716                    push @scalars, $scalar;
717                }
718            }
719            # Loop through the relationships. If this entity is the to-entity
720            # on a relationship of 1M arity, then it is implemented as a PPO
721            # object reference.
722            for my $relationshipName (keys %{$relationships}) {
723                # Get the relationship data.
724                my $relationshipData = $relationships->{$relationshipName};
725                # If we have a from for this entity and an arity of 1M, we
726                # have an object reference.
727                if ($relationshipData->{to} eq $entityName &&
728                    $relationshipData->{arity} eq '1M') {
729                    # Build the object reference tag.
730                    push @object_refs, { label => $relationshipName,
731                                         type => $relationshipData->{from} };
732                }
733            }
734            # Create the indexes.
735            my $indexList = $entityObject->{Indexes};
736            push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
737            # Build the object XML tree.
738            my $object = { label => $entityName,
739                           object_ref => \@object_refs,
740                           scalar => \@scalars,
741                           index => \@indexes,
742                           array => \@arrays
743                          };
744            # Push the object onto the objects list.
745            push @objects, $object;
746        }
747        # Loop through the relationships, searching for MMs. The 1Ms were
748        # already handled by the entity search above.
749        for my $relationshipName (keys %{$relationships}) {
750            # Get this relationship's object.
751            my $relationshipObject = $relationships->{$relationshipName};
752            # Only proceed if it's many-to-many.
753            if ($relationshipObject->{arity} eq 'MM') {
754                # Create the tag lists for the relationship object.
755                my (@object_refs, @scalars, @indexes);
756                # The relationship will be created as an object with object
757                # references for its links to the participating entities.
758                my %links = ( from_link => $relationshipObject->{from},
759                              to_link => $relationshipObject->{to} );
760                for my $link (keys %links) {
761                    # Create an object_ref tag for this piece of the
762                    # relationship (from or to).
763                    my $object_ref = { label => $link,
764                                       type => $links{$link} };
765                    push @object_refs, $object_ref;
766                }
767                # Loop through the intersection data fields, creating scalar tags.
768                # There are no fancy array tags in a relationship.
769                for my $fieldName (keys %{$relationshipObject->{Fields}}) {
770                    my $fieldObject = $relationshipObject->{Fields}->{$fieldName};
771                    push @scalars, _CreatePPOField($fieldName, $fieldObject);
772                }
773                # Finally, the indexes: currently we cannot support the to-index and
774                # from-index in PPO, so we just process the alternate indexes.
775                my $indexList = $relationshipObject->{Indexes};
776                push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
777                # Wrap up all the stuff about this relationship.
778                my $object = { label => $relationshipName,
779                               scalar => \@scalars,
780                               object_ref => \@object_refs,
781                               index => \@indexes
782                             };
783                # Push it into the object list.
784                push @objects, $object;
785            }
786        }
787        # Compute a title.
788        my $title;
789        if ($erdbXMLFile =~ /(\/|^)([^\/]+)DBD\.xml/) {
790            # Here we have a standard file name we can use for a title.
791            $title = $2;
792        } else {
793            # Here the file name is non-standard, so we carve up the
794            # database title.
795            $title = $xml->{Title}->{content};
796            $title =~ s/\s\.,//g;
797        }
798        # Wrap up the XML as a project.
799        my $ppoXML = { project => { label => $title,
800                                    object => \@objects }};
801        # Write out the results.
802        my $ppoString = XML::Simple::XMLout($ppoXML,
803                                            AttrIndent => 1,
804                                            KeepRoot => 1);
805        Tracer::PutFile($ppoXMLFile, [ $ppoString ]);
806    }
807    
808    =head3 FindIndexForEntity
809    
810    C<< my $indexFound = ERDB::FindIndexForEntity($xml, $entityName, $attributeName); >>
811    
812    This method locates the entry in an entity's index list that begins with the
813    specified attribute name. If the entity has no index list, one will be
814    created. This method works on raw XML, not a live ERDB object.
815    
816    =over 4
817    
818    =item xml
819    
820    The raw XML structure defining the database.
821    
822    =item entityName
823    
824    The name of the relevant entity.
825    
826    =item attributeName
827    
828    The name of the attribute relevant to the search.
829    
830    =item RETURN
831    
832    The numerical index in the index list of the index entry for the specified entity and
833    attribute, or C<undef> if no such index exists.
834    
835    =back
836    
837    =cut
838    
839    sub FindIndexForEntity {
840        # Get the parameters.
841        my ($xml, $entityName, $attributeName) = @_;
842        # Declare the return variable.
843        my $retVal;
844        # Get the named entity.
845        my $entityData = $xml->{Entities}->{$entityName};
846        if (! $entityData) {
847            Confess("Entity $entityName not found in DBD structure.");
848        } else {
849            # Insure it has an index list.
850            if (! exists $entityData->{Indexes}) {
851                $entityData->{Indexes} = [];
852            } else {
853                # Search for the desired index.
854                my $indexList = $entityData->{Indexes};
855                my $n = scalar @{$indexList};
856                Trace("Searching $n indexes in index list for $entityName.") if T(2);
857                # We use an indexed FOR here because we're returning an
858                # index number instead of an object. We do THAT so we can
859                # delete the index from the list if needed.
860                for (my $i = 0; $i < $n && !defined($retVal); $i++) {
861                    my $index = $indexList->[$i];
862                    my $fields = $index->{IndexFields};
863                    # Technically this IF should be safe (that is, we are guaranteed
864                    # the existence of a "$fields->[0]"), because when we load the XML
865                    # we have SuppressEmpty specified.
866                    if ($fields->[0]->{name} eq $attributeName) {
867                        $retVal = $i;
868                    }
869                }
870            }
871        }
872        Trace("Index for $attributeName of $entityName found at position $retVal.") if defined($retVal) && T(3);
873        Trace("Index for $attributeName not found in $entityName.") if !defined($retVal) && T(3);
874        # Return the result.
875        return $retVal;
876    }
877    
878  =head3 CreateTables  =head3 CreateTables
879    
880  C<< $erdb->CreateTables(); >>  C<< $erdb->CreateTables(); >>
# Line 665  Line 894 
894      # Loop through the relations.      # Loop through the relations.
895      for my $relationName (@relNames) {      for my $relationName (@relNames) {
896          # Create a table for this relation.          # Create a table for this relation.
897          $self->CreateTable($relationName);          $self->CreateTable($relationName, 1);
898          Trace("Relation $relationName created.") if T(2);          Trace("Relation $relationName created.") if T(2);
899      }      }
900  }  }
# Line 891  Line 1120 
1120      for my $indexName (keys %{$indexHash}) {      for my $indexName (keys %{$indexHash}) {
1121          my $indexData = $indexHash->{$indexName};          my $indexData = $indexHash->{$indexName};
1122          # Get the index's field list.          # Get the index's field list.
1123          my @fieldList = _FixNames(@{$indexData->{IndexFields}});          my @rawFields = @{$indexData->{IndexFields}};
1124            # Get a hash of the relation's field types.
1125            my %types = map { $_->{name} => $_->{type} } @{$relationData->{Fields}};
1126            # We need to check for text fields so we can append a length limitation for them. To do
1127            # that, we need the relation's field list.
1128            my $relFields = $relationData->{Fields};
1129            for (my $i = 0; $i <= $#rawFields; $i++) {
1130                # Get the field type.
1131                my $field = $rawFields[$i];
1132                my $type = $types{$field};
1133                # Ask if it requires using prefix notation for the index.
1134                my $mod = $TypeTable{$type}->{indexMod};
1135                Trace("Field $field ($i) in $relationName has type $type and indexMod $mod.") if T(3);
1136                if ($mod) {
1137                    # Append the prefix length to the field name,
1138                    $rawFields[$i] .= "($mod)";
1139                }
1140            }
1141            my @fieldList = _FixNames(@rawFields);
1142          my $flds = join(', ', @fieldList);          my $flds = join(', ', @fieldList);
1143          # Get the index's uniqueness flag.          # Get the index's uniqueness flag.
1144          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
# Line 906  Line 1153 
1153      }      }
1154  }  }
1155    
1156    =head3 GetSecondaryFields
1157    
1158    C<< my %fieldTuples = $erdb->GetSecondaryFields($entityName); >>
1159    
1160    This method will return a list of the name and type of each of the secondary
1161    fields for a specified entity. Secondary fields are stored in two-column tables
1162    in addition to the primary entity table. This enables the field to have no value
1163    or to have multiple values.
1164    
1165    =over 4
1166    
1167    =item entityName
1168    
1169    Name of the entity whose secondary fields are desired.
1170    
1171    =item RETURN
1172    
1173    Returns a hash mapping the field names to their field types.
1174    
1175    =back
1176    
1177    =cut
1178    
1179    sub GetSecondaryFields {
1180        # Get the parameters.
1181        my ($self, $entityName) = @_;
1182        # Declare the return variable.
1183        my %retVal = ();
1184        # Look for the entity.
1185        my $table = $self->GetFieldTable($entityName);
1186        # Loop through the fields, pulling out the secondaries.
1187        for my $field (sort keys %{$table}) {
1188            if ($table->{$field}->{relation} ne $entityName) {
1189                # Here we have a secondary field.
1190                $retVal{$field} = $table->{$field}->{type};
1191            }
1192        }
1193        # Return the result.
1194        return %retVal;
1195    }
1196    
1197    =head3 GetFieldRelationName
1198    
1199    C<< my $name = $erdb->GetFieldRelationName($objectName, $fieldName); >>
1200    
1201    Return the name of the relation containing a specified field.
1202    
1203    =over 4
1204    
1205    =item objectName
1206    
1207    Name of the entity or relationship containing the field.
1208    
1209    =item fieldName
1210    
1211    Name of the relevant field in that entity or relationship.
1212    
1213    =item RETURN
1214    
1215    Returns the name of the database relation containing the field, or C<undef> if
1216    the field does not exist.
1217    
1218    =back
1219    
1220    =cut
1221    
1222    sub GetFieldRelationName {
1223        # Get the parameters.
1224        my ($self, $objectName, $fieldName) = @_;
1225        # Declare the return variable.
1226        my $retVal;
1227        # Get the object field table.
1228        my $table = $self->GetFieldTable($objectName);
1229        # Only proceed if the field exists.
1230        if (exists $table->{$fieldName}) {
1231            # Determine the name of the relation that contains this field.
1232            $retVal = $table->{$fieldName}->{relation};
1233        }
1234        # Return the result.
1235        return $retVal;
1236    }
1237    
1238    =head3 DeleteValue
1239    
1240    C<< my $numDeleted = $erdb->DeleteValue($entityName, $id, $fieldName, $fieldValue); >>
1241    
1242    Delete secondary field values from the database. This method can be used to delete all
1243    values of a specified field for a particular entity instance, or only a single value.
1244    
1245    Secondary fields are stored in two-column relations separate from an entity's primary
1246    table, and as a result a secondary field can legitimately have no value or multiple
1247    values. Therefore, it makes sense to talk about deleting secondary fields where it
1248    would not make sense for primary fields.
1249    
1250    =over 4
1251    
1252    =item entityName
1253    
1254    Name of the entity from which the fields are to be deleted.
1255    
1256    =item id
1257    
1258    ID of the entity instance to be processed. If the instance is not found, this
1259    method will have no effect. If C<undef> is specified, all values for all of
1260    the entity instances will be deleted.
1261    
1262    =item fieldName
1263    
1264    Name of the field whose values are to be deleted.
1265    
1266    =item fieldValue (optional)
1267    
1268    Value to be deleted. If not specified, then all values of the specified field
1269    will be deleted for the entity instance. If specified, then only the values which
1270    match this parameter will be deleted.
1271    
1272    =item RETURN
1273    
1274    Returns the number of rows deleted.
1275    
1276    =back
1277    
1278    =cut
1279    
1280    sub DeleteValue {
1281        # Get the parameters.
1282        my ($self, $entityName, $id, $fieldName, $fieldValue) = @_;
1283        # Declare the return value.
1284        my $retVal = 0;
1285        # We need to set up an SQL command to do the deletion. First, we
1286        # find the name of the field's relation.
1287        my $table = $self->GetFieldTable($entityName);
1288        my $field = $table->{$fieldName};
1289        my $relation = $field->{relation};
1290        # Make sure this is a secondary field.
1291        if ($relation eq $entityName) {
1292            Confess("Cannot delete values of $fieldName for $entityName.");
1293        } else {
1294            # Set up the SQL command to delete all values.
1295            my $sql = "DELETE FROM $relation";
1296            # Build the filter.
1297            my @filters = ();
1298            my @parms = ();
1299            # Check for a filter by ID.
1300            if (defined $id) {
1301                push @filters, "id = ?";
1302                push @parms, $id;
1303            }
1304            # Check for a filter by value.
1305            if (defined $fieldValue) {
1306                push @filters, "$fieldName = ?";
1307                push @parms, $fieldValue;
1308            }
1309            # Append the filters to the command.
1310            if (@filters) {
1311                $sql .= " WHERE " . join(" AND ", @filters);
1312            }
1313            # Execute the command.
1314            my $dbh = $self->{_dbh};
1315            $retVal = $dbh->SQL($sql, 0, @parms);
1316        }
1317        # Return the result.
1318        return $retVal;
1319    }
1320    
1321  =head3 LoadTables  =head3 LoadTables
1322    
1323  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>
# Line 1163  Line 1575 
1575      return $retVal;      return $retVal;
1576  }  }
1577    
1578    
1579    
1580  =head3 Search  =head3 Search
1581    
1582  C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>  C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>
# Line 1176  Line 1590 
1590    
1591  =item searchExpression  =item searchExpression
1592    
1593  Boolean search expression for the text fields of the target object.  Boolean search expression for the text fields of the target object. The default mode for
1594    a Boolean search expression is OR, but we want the default to be AND, so we will
1595    add a C<+> operator to each word with no other operator before it.
1596    
1597  =item idx  =item idx
1598    
# Line 1230  Line 1646 
1646          my @fields = @{$object1Structure->{searchFields}};          my @fields = @{$object1Structure->{searchFields}};
1647          # Clean the search expression.          # Clean the search expression.
1648          my $actualKeywords = $self->CleanKeywords($searchExpression);          my $actualKeywords = $self->CleanKeywords($searchExpression);
1649            # Prefix a "+" to each uncontrolled word. This converts the default
1650            # search mode from OR to AND.
1651            $actualKeywords =~ s/(^|\s)(\w|")/$1\+$2/g;
1652          Trace("Actual keywords for search are\n$actualKeywords") if T(3);          Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1653          # We need two match expressions, one for the filter clause and one in the          # We need two match expressions, one for the filter clause and one in the
1654          # query itself. Both will use a parameter mark, so we need to push the          # query itself. Both will use a parameter mark, so we need to push the
# Line 1337  Line 1756 
1756      # Declare the return variable.      # Declare the return variable.
1757      my %retVal = ();      my %retVal = ();
1758      # Find the entity's data structure.      # Find the entity's data structure.
1759      my $entityData = $self->{Entities}->{$entityName};      my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1760      # Loop through its fields, adding each special field to the return hash.      # Loop through its fields, adding each special field to the return hash.
1761      my $fieldHash = $entityData->{Fields};      my $fieldHash = $entityData->{Fields};
1762      for my $fieldName (keys %{$fieldHash}) {      for my $fieldName (keys %{$fieldHash}) {
# Line 1352  Line 1771 
1771    
1772  =head3 Delete  =head3 Delete
1773    
1774  C<< my $stats = $erdb->Delete($entityName, $objectID); >>  C<< my $stats = $erdb->Delete($entityName, $objectID, %options); >>
1775    
1776  Delete an entity instance from the database. The instance is deleted along with all entity and  Delete an entity instance from the database. The instance is deleted along with all entity and
1777  relationship instances dependent on it. The idea of dependence here is recursive. An object is  relationship instances dependent on it. The definition of I<dependence> is recursive.
1778  always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many  
1779  relationship connected to a dependent entity or the "to" entity connected to a 1-to-many  An object is always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many
1780    relationship connected to a dependent entity or if it is the "to" entity connected to a 1-to-many
1781  dependent relationship.  dependent relationship.
1782    
1783  =over 4  =over 4
# Line 1371  Line 1791 
1791  ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),  ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),
1792  then it is presumed to by a LIKE pattern.  then it is presumed to by a LIKE pattern.
1793    
1794  =item testFlag  =item options
1795    
1796  If TRUE, the delete statements will be traced without being executed.  A hash detailing the options for this delete operation.
1797    
1798  =item RETURN  =item RETURN
1799    
# Line 1382  Line 1802 
1802    
1803  =back  =back
1804    
1805    The permissible options for this method are as follows.
1806    
1807    =over 4
1808    
1809    =item testMode
1810    
1811    If TRUE, then the delete statements will be traced, but no changes will be made to the database.
1812    
1813    =item keepRoot
1814    
1815    If TRUE, then the entity instances will not be deleted, only the dependent records.
1816    
1817    =back
1818    
1819  =cut  =cut
1820  #: Return Type $%;  #: Return Type $%;
1821  sub Delete {  sub Delete {
1822      # Get the parameters.      # Get the parameters.
1823      my ($self, $entityName, $objectID, $testFlag) = @_;      my ($self, $entityName, $objectID, %options) = @_;
1824      # Declare the return variable.      # Declare the return variable.
1825      my $retVal = Stats->new();      my $retVal = Stats->new();
1826      # Get the DBKernel object.      # Get the DBKernel object.
# Line 1403  Line 1837 
1837      # FROM-relationships and entities.      # FROM-relationships and entities.
1838      my @fromPathList = ();      my @fromPathList = ();
1839      my @toPathList = ();      my @toPathList = ();
1840      # This final hash is used to remember what work still needs to be done. We push paths      # This final list is used to remember what work still needs to be done. We push paths
1841      # onto the list, then pop them off to extend the paths. We prime it with the starting      # onto the list, then pop them off to extend the paths. We prime it with the starting
1842      # point. Note that we will work hard to insure that the last item on a path in the      # point. Note that we will work hard to insure that the last item on a path in the
1843      # TODO list is always an entity.      # to-do list is always an entity.
1844      my @todoList = ([$entityName]);      my @todoList = ([$entityName]);
1845      while (@todoList) {      while (@todoList) {
1846          # Get the current path.          # Get the current path.
# Line 1414  Line 1848 
1848          # Copy it into a list.          # Copy it into a list.
1849          my @stackedPath = @{$current};          my @stackedPath = @{$current};
1850          # Pull off the last item on the path. It will always be an entity.          # Pull off the last item on the path. It will always be an entity.
1851          my $entityName = pop @stackedPath;          my $myEntityName = pop @stackedPath;
1852          # Add it to the alreadyFound list.          # Add it to the alreadyFound list.
1853          $alreadyFound{$entityName} = 1;          $alreadyFound{$myEntityName} = 1;
1854            # Figure out if we need to delete this entity.
1855            if ($myEntityName ne $entityName || ! $options{keepRoot}) {
1856          # Get the entity data.          # Get the entity data.
1857          my $entityData = $self->_GetStructure($entityName);              my $entityData = $self->_GetStructure($myEntityName);
1858          # The first task is to loop through the entity's relation. A DELETE command will              # Loop through the entity's relations. A DELETE command will be needed for each of them.
         # be needed for each of them.  
1859          my $relations = $entityData->{Relations};          my $relations = $entityData->{Relations};
1860          for my $relation (keys %{$relations}) {          for my $relation (keys %{$relations}) {
1861              my @augmentedList = (@stackedPath, $relation);              my @augmentedList = (@stackedPath, $relation);
1862              push @fromPathList, \@augmentedList;              push @fromPathList, \@augmentedList;
1863          }          }
1864            }
1865          # Now we need to look for relationships connected to this entity.          # Now we need to look for relationships connected to this entity.
1866          my $relationshipList = $self->{_metaData}->{Relationships};          my $relationshipList = $self->{_metaData}->{Relationships};
1867          for my $relationshipName (keys %{$relationshipList}) {          for my $relationshipName (keys %{$relationshipList}) {
1868              my $relationship = $relationshipList->{$relationshipName};              my $relationship = $relationshipList->{$relationshipName};
1869              # Check the FROM field. We're only interested if it's us.              # Check the FROM field. We're only interested if it's us.
1870              if ($relationship->{from} eq $entityName) {              if ($relationship->{from} eq $myEntityName) {
1871                  # Add the path to this relationship.                  # Add the path to this relationship.
1872                  my @augmentedList = (@stackedPath, $entityName, $relationshipName);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1873                  push @fromPathList, \@augmentedList;                  push @fromPathList, \@augmentedList;
1874                  # Check the arity. If it's MM we're done. If it's 1M                  # Check the arity. If it's MM we're done. If it's 1M
1875                  # and the target hasn't been seen yet, we want to                  # and the target hasn't been seen yet, we want to
# Line 1452  Line 1888 
1888              }              }
1889              # Now check the TO field. In this case only the relationship needs              # Now check the TO field. In this case only the relationship needs
1890              # deletion.              # deletion.
1891              if ($relationship->{to} eq $entityName) {              if ($relationship->{to} eq $myEntityName) {
1892                  my @augmentedList = (@stackedPath, $entityName, $relationshipName);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1893                  push @toPathList, \@augmentedList;                  push @toPathList, \@augmentedList;
1894              }              }
1895          }          }
1896      }      }
1897      # Create the first qualifier for the WHERE clause. This selects the      # Create the first qualifier for the WHERE clause. This selects the
1898      # keys of the primary entity records to be deleted. When we're deleting      # keys of the primary entity records to be deleted. When we're deleting
1899      # from a dependent table, we construct a join page from the first qualifier      # from a dependent table, we construct a join path from the first qualifier
1900      # to the table containing the dependent records to delete.      # to the table containing the dependent records to delete.
1901      my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");      my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
1902      # We need to make two passes. The first is through the to-list, and      # We need to make two passes. The first is through the to-list, and
# Line 1499  Line 1935 
1935                  }                  }
1936              }              }
1937              # Now we have our desired DELETE statement.              # Now we have our desired DELETE statement.
1938              if ($testFlag) {              if ($options{testMode}) {
1939                  # Here the user wants to trace without executing.                  # Here the user wants to trace without executing.
1940                  Trace($stmt) if T(0);                  Trace($stmt) if T(0);
1941              } else {              } else {
1942                  # Here we can delete. Note that the SQL method dies with a confessing                  # Here we can delete. Note that the SQL method dies with a confession
1943                  # if an error occurs, so we just go ahead and do it.                  # if an error occurs, so we just go ahead and do it.
1944                  Trace("Executing delete from $target using '$objectID'.") if T(3);                  Trace("Executing delete from $target using '$objectID'.") if T(3);
1945                  my $rv = $db->SQL($stmt, 0, $objectID);                  my $rv = $db->SQL($stmt, 0, $objectID);
# Line 1518  Line 1954 
1954      return $retVal;      return $retVal;
1955  }  }
1956    
1957    =head3 Disconnect
1958    
1959    C<< $erdb->Disconnect($relationshipName, $originEntityName, $originEntityID); >>
1960    
1961    Disconnect an entity instance from all the objects to which it is related. This
1962    will delete each relationship instance that connects to the specified entity.
1963    
1964    =over 4
1965    
1966    =item relationshipName
1967    
1968    Name of the relationship whose instances are to be deleted.
1969    
1970    =item originEntityName
1971    
1972    Name of the entity that is to be disconnected.
1973    
1974    =item originEntityID
1975    
1976    ID of the entity that is to be disconnected.
1977    
1978    =back
1979    
1980    =cut
1981    
1982    sub Disconnect {
1983        # Get the parameters.
1984        my ($self, $relationshipName, $originEntityName, $originEntityID) = @_;
1985        # Get the relationship descriptor.
1986        my $structure = $self->_GetStructure($relationshipName);
1987        # Insure we have a relationship.
1988        if (! exists $structure->{from}) {
1989            Confess("$relationshipName is not a relationship in the database.");
1990        } else {
1991            # Get the database handle.
1992            my $dbh = $self->{_dbh};
1993            # We'll set this value to 1 if we find our entity.
1994            my $found = 0;
1995            # Loop through the ends of the relationship.
1996            for my $dir ('from', 'to') {
1997                if ($structure->{$dir} eq $originEntityName) {
1998                    # Delete all relationship instances on this side of the entity instance.
1999                    Trace("Disconnecting in $dir direction with ID \"$originEntityID\".");
2000                    $dbh->SQL("DELETE FROM $relationshipName WHERE ${dir}_link = ?", 0, $originEntityID);
2001                    $found = 1;
2002                }
2003            }
2004            # Insure we found the entity on at least one end.
2005            if (! $found) {
2006                Confess("Entity \"$originEntityName\" does not use $relationshipName.");
2007            }
2008        }
2009    }
2010    
2011    =head3 DeleteRow
2012    
2013    C<< $erdb->DeleteRow($relationshipName, $fromLink, $toLink, \%values); >>
2014    
2015    Delete a row from a relationship. In most cases, only the from-link and to-link are
2016    needed; however, for relationships with intersection data values can be specified
2017    for the other fields using a hash.
2018    
2019    =over 4
2020    
2021    =item relationshipName
2022    
2023    Name of the relationship from which the row is to be deleted.
2024    
2025    =item fromLink
2026    
2027    ID of the entity instance in the From direction.
2028    
2029    =item toLink
2030    
2031    ID of the entity instance in the To direction.
2032    
2033    =item values
2034    
2035    Reference to a hash of other values to be used for filtering the delete.
2036    
2037    =back
2038    
2039    =cut
2040    
2041    sub DeleteRow {
2042        # Get the parameters.
2043        my ($self, $relationshipName, $fromLink, $toLink, $values) = @_;
2044        # Create a hash of all the filter information.
2045        my %filter = ('from-link' => $fromLink, 'to-link' => $toLink);
2046        if (defined $values) {
2047            for my $key (keys %{$values}) {
2048                $filter{$key} = $values->{$key};
2049            }
2050        }
2051        # Build an SQL statement out of the hash.
2052        my @filters = ();
2053        my @parms = ();
2054        for my $key (keys %filter) {
2055            push @filters, _FixName($key) . " = ?";
2056            push @parms, $filter{$key};
2057        }
2058        Trace("Parms for delete row are " . join(", ", map { "\"$_\"" } @parms) . ".") if T(SQL => 4);
2059        my $command = "DELETE FROM $relationshipName WHERE " .
2060                      join(" AND ", @filters);
2061        # Execute it.
2062        my $dbh = $self->{_dbh};
2063        $dbh->SQL($command, undef, @parms);
2064    }
2065    
2066  =head3 SortNeeded  =head3 SortNeeded
2067    
2068  C<< my $parms = $erdb->SortNeeded($relationName); >>  C<< my $parms = $erdb->SortNeeded($relationName); >>
# Line 1568  Line 2113 
2113      } elsif (exists $relationshipTable->{$relationName}) {      } elsif (exists $relationshipTable->{$relationName}) {
2114          # Here we have a relationship. We sort using the FROM index.          # Here we have a relationship. We sort using the FROM index.
2115          my $relationshipData = $relationshipTable->{$relationName};          my $relationshipData = $relationshipTable->{$relationName};
2116          my $index = $relationData->{Indexes}->{"idx${relationName}From"};          my $index = $relationData->{Indexes}->{idxFrom};
2117          push @keyNames, @{$index->{IndexFields}};          push @keyNames, @{$index->{IndexFields}};
2118      } else {      } else {
2119          # Here we have a secondary entity relation, so we have a sort on the ID field.          # Here we have a secondary entity relation, so we have a sort on the ID field.
# Line 1658  Line 2203 
2203    
2204  =item RETURN  =item RETURN
2205    
2206  Returns a list of B<DBObject>s that satisfy the query conditions.  Returns a list of B<ERDBObject>s that satisfy the query conditions.
2207    
2208  =back  =back
2209    
# Line 1914  Line 2459 
2459    
2460  =head3 InsertObject  =head3 InsertObject
2461    
2462  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>  C<< $erdb->InsertObject($objectType, \%fieldHash); >>
2463    
2464  Insert an object into the database. The object is defined by a type name and then a hash  Insert an object into the database. The object is defined by a type name and then a hash
2465  of field names to values. Field values in the primary relation are represented by scalars.  of field names to values. Field values in the primary relation are represented by scalars.
# Line 1940  Line 2485 
2485    
2486  Hash of field names to values.  Hash of field names to values.
2487    
 =item RETURN  
   
 Returns 1 if successful, 0 if an error occurred.  
   
2488  =back  =back
2489    
2490  =cut  =cut
# Line 2042  Line 2583 
2583                  $retVal = $sth->execute(@parameterList);                  $retVal = $sth->execute(@parameterList);
2584                  if (!$retVal) {                  if (!$retVal) {
2585                      my $errorString = $sth->errstr();                      my $errorString = $sth->errstr();
2586                      Trace("Insert error: $errorString.") if T(0);                      Confess("Error inserting into $relationName: $errorString");
2587                    } else {
2588                        Trace("Insert successful using $parameterList[0].") if T(3);
2589                  }                  }
2590              }              }
2591          }          }
2592      }      }
2593      # Return the success indicator.      # Return a 1 for backward compatability.
2594      return $retVal;      return 1;
2595    }
2596    
2597    =head3 UpdateEntity
2598    
2599    C<< $erdb->UpdateEntity($entityName, $id, \%fields); >>
2600    
2601    Update the values of an entity. This is an unprotected update, so it should only be
2602    done if the database resides on a database server.
2603    
2604    =over 4
2605    
2606    =item entityName
2607    
2608    Name of the entity to update. (This is the entity type.)
2609    
2610    =item id
2611    
2612    ID of the entity to update. If no entity exists with this ID, an error will be thrown.
2613    
2614    =item fields
2615    
2616    Reference to a hash mapping field names to their new values. All of the fields named
2617    must be in the entity's primary relation, and they cannot any of them be the ID field.
2618    
2619    =back
2620    
2621    =cut
2622    
2623    sub UpdateEntity {
2624        # Get the parameters.
2625        my ($self, $entityName, $id, $fields) = @_;
2626        # Get a list of the field names being updated.
2627        my @fieldList = keys %{$fields};
2628        # Verify that the fields exist.
2629        my $checker = $self->GetFieldTable($entityName);
2630        for my $field (@fieldList) {
2631            if ($field eq 'id') {
2632                Confess("Cannot update the ID field for entity $entityName.");
2633            } elsif ($checker->{$field}->{relation} ne $entityName) {
2634                Confess("Cannot find $field in primary relation of $entityName.");
2635            }
2636        }
2637        # Build the SQL statement.
2638        my @sets = ();
2639        my @valueList = ();
2640        for my $field (@fieldList) {
2641            push @sets, _FixName($field) . " = ?";
2642            push @valueList, $fields->{$field};
2643        }
2644        my $command = "UPDATE $entityName SET " . join(", ", @sets) . " WHERE id = ?";
2645        # Add the ID to the list of binding values.
2646        push @valueList, $id;
2647        # Call SQL to do the work.
2648        my $rows = $self->{_dbh}->SQL($command, 0, @valueList);
2649        # Check for errors.
2650        if ($rows == 0) {
2651            Confess("Entity $id of type $entityName not found.");
2652        }
2653  }  }
2654    
2655  =head3 LoadTable  =head3 LoadTable
2656    
2657  C<< my %results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>  C<< my $results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>
2658    
2659  Load data from a tab-delimited file into a specified table, optionally re-creating the table  Load data from a tab-delimited file into a specified table, optionally re-creating the table
2660  first.  first.
# Line 2100  Line 2701 
2701          # leave extra room. We postulate a minimum row count of 1000 to          # leave extra room. We postulate a minimum row count of 1000 to
2702          # prevent problems with incoming empty load files.          # prevent problems with incoming empty load files.
2703          my $rowSize = $self->EstimateRowSize($relationName);          my $rowSize = $self->EstimateRowSize($relationName);
2704          my $estimate = FIG::max($fileSize * 1.5 / $rowSize, 1000);          my $estimate = $fileSize * 1.5 / $rowSize;
2705            if ($estimate < 1000) {
2706                $estimate = 1000;
2707            }
2708          # Re-create the table without its index.          # Re-create the table without its index.
2709          $self->CreateTable($relationName, 0, $estimate);          $self->CreateTable($relationName, 0, $estimate);
2710          # If this is a pre-index DBMS, create the index here.          # If this is a pre-index DBMS, create the index here.
# Line 2142  Line 2746 
2746              # The full-text index (if any) is always built last, even for MySQL.              # The full-text index (if any) is always built last, even for MySQL.
2747              # First we need to see if this table has a full-text index. Only              # First we need to see if this table has a full-text index. Only
2748              # primary relations are allowed that privilege.              # primary relations are allowed that privilege.
2749                Trace("Checking for full-text index on $relationName.") if T(2);
2750              if ($self->_IsPrimary($relationName)) {              if ($self->_IsPrimary($relationName)) {
2751                  # Get the relation's entity/relationship structure.                  $self->CreateSearchIndex($relationName);
                 my $structure = $self->_GetStructure($relationName);  
                 # Check for a searchable fields list.  
                 if (exists $structure->{searchFields}) {  
                     # Here we know that we need to create a full-text search index.  
                     # Get an SQL-formatted field name list.  
                     my $fields = join(", ", $self->_FixNames(@{$structure->{searchFields}}));  
                     # Create the index.  
                     $dbh->create_index(tbl => $relationName, idx => "search_idx_$relationName",  
                                        flds => $fields, kind => 'fulltext');  
                 }  
2752              }              }
2753          }          }
2754      }      }
# Line 2165  Line 2760 
2760      return $retVal;      return $retVal;
2761  }  }
2762    
2763    =head3 CreateSearchIndex
2764    
2765    C<< $erdb->CreateSearchIndex($objectName); >>
2766    
2767    Check for a full-text search index on the specified entity or relationship object, and
2768    if one is required, rebuild it.
2769    
2770    =over 4
2771    
2772    =item objectName
2773    
2774    Name of the entity or relationship to be indexed.
2775    
2776    =back
2777    
2778    =cut
2779    
2780    sub CreateSearchIndex {
2781        # Get the parameters.
2782        my ($self, $objectName) = @_;
2783        # Get the relation's entity/relationship structure.
2784        my $structure = $self->_GetStructure($objectName);
2785        # Get the database handle.
2786        my $dbh = $self->{_dbh};
2787        Trace("Checking for search fields in $objectName.") if T(3);
2788        # Check for a searchable fields list.
2789        if (exists $structure->{searchFields}) {
2790            # Here we know that we need to create a full-text search index.
2791            # Get an SQL-formatted field name list.
2792            my $fields = join(", ", _FixNames(@{$structure->{searchFields}}));
2793            # Create the index. If it already exists, it will be dropped.
2794            $dbh->create_index(tbl => $objectName, idx => "search_idx",
2795                               flds => $fields, kind => 'fulltext');
2796            Trace("Index created for $fields in $objectName.") if T(2);
2797        }
2798    }
2799    
2800  =head3 DropRelation  =head3 DropRelation
2801    
2802  C<< $erdb->DropRelation($relationName); >>  C<< $erdb->DropRelation($relationName); >>
# Line 2189  Line 2821 
2821      my $dbh = $self->{_dbh};      my $dbh = $self->{_dbh};
2822      # Drop the relation. The method used here has no effect if the relation      # Drop the relation. The method used here has no effect if the relation
2823      # does not exist.      # does not exist.
2824      $dbh->drop_table($relationName);      Trace("Invoking DB Kernel to drop $relationName.") if T(3);
2825        $dbh->drop_table(tbl => $relationName);
2826    }
2827    
2828    =head3 MatchSqlPattern
2829    
2830    C<< my $matched = ERDB::MatchSqlPattern($value, $pattern); >>
2831    
2832    Determine whether or not a specified value matches an SQL pattern. An SQL
2833    pattern has two wild card characters: C<%> that matches multiple characters,
2834    and C<_> that matches a single character. These can be escaped using a
2835    backslash (C<\>). We pull this off by converting the SQL pattern to a
2836    PERL regular expression. As per SQL rules, the match is case-insensitive.
2837    
2838    =over 4
2839    
2840    =item value
2841    
2842    Value to be matched against the pattern. Note that an undefined or empty
2843    value will not match anything.
2844    
2845    =item pattern
2846    
2847    SQL pattern against which to match the value. An undefined or empty pattern will
2848    match everything.
2849    
2850    =item RETURN
2851    
2852    Returns TRUE if the value and pattern match, else FALSE.
2853    
2854    =back
2855    
2856    =cut
2857    
2858    sub MatchSqlPattern {
2859        # Get the parameters.
2860        my ($value, $pattern) = @_;
2861        # Declare the return variable.
2862        my $retVal;
2863        # Insure we have a pattern.
2864        if (! defined($pattern) || $pattern eq "") {
2865            $retVal = 1;
2866        } else {
2867            # Break the pattern into pieces around the wildcard characters. Because we
2868            # use parentheses in the split function's delimiter expression, we'll get
2869            # list elements for the delimiters as well as the rest of the string.
2870            my @pieces = split /([_%]|\\[_%])/, $pattern;
2871            # Check some fast special cases.
2872            if ($pattern eq '%') {
2873                # A null pattern matches everything.
2874                $retVal = 1;
2875            } elsif (@pieces == 1) {
2876                # No wildcards, so we have a literal comparison. Note we're case-insensitive.
2877                $retVal = (lc($value) eq lc($pattern));
2878            } elsif (@pieces == 2 && $pieces[1] eq '%') {
2879                # A wildcard at the end, so we have a substring match. This is also case-insensitive.
2880                $retVal = (lc(substr($value, 0, length($pieces[0]))) eq lc($pieces[0]));
2881            } else {
2882                # Okay, we have to do it the hard way. Convert each piece to a PERL pattern.
2883                my $realPattern = "";
2884                for my $piece (@pieces) {
2885                    # Determine the type of piece.
2886                    if ($piece eq "") {
2887                        # Empty pieces are ignored.
2888                    } elsif ($piece eq "%") {
2889                        # Here we have a multi-character wildcard. Note that it can match
2890                        # zero or more characters.
2891                        $realPattern .= ".*"
2892                    } elsif ($piece eq "_") {
2893                        # Here we have a single-character wildcard.
2894                        $realPattern .= ".";
2895                    } elsif ($piece eq "\\%" || $piece eq "\\_") {
2896                        # This is an escape sequence (which is a rare thing, actually).
2897                        $realPattern .= substr($piece, 1, 1);
2898                    } else {
2899                        # Here we have raw text.
2900                        $realPattern .= quotemeta($piece);
2901                    }
2902                }
2903                # Do the match.
2904                $retVal = ($value =~ /^$realPattern$/i ? 1 : 0);
2905            }
2906        }
2907        # Return the result.
2908        return $retVal;
2909  }  }
2910    
2911  =head3 GetEntity  =head3 GetEntity
# Line 2210  Line 2926 
2926    
2927  =item RETURN  =item RETURN
2928    
2929  Returns a B<DBObject> representing the desired entity instance, or an undefined value if no  Returns a B<ERDBObject> representing the desired entity instance, or an undefined value if no
2930  instance is found with the specified key.  instance is found with the specified key.
2931    
2932  =back  =back
# Line 2345  Line 3061 
3061  spreadsheet cell, and each feature will be represented by a list containing the  spreadsheet cell, and each feature will be represented by a list containing the
3062  feature ID followed by all of its aliases.  feature ID followed by all of its aliases.
3063    
3064  C<< $query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>  C<< @query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>
3065    
3066  =over 4  =over 4
3067    
# Line 2599  Line 3315 
3315      # Declare the return variable. The field name is valid until we hear      # Declare the return variable. The field name is valid until we hear
3316      # differently.      # differently.
3317      my $retVal = 1;      my $retVal = 1;
3318        # Compute the maximum name length.
3319        my $maxLen = $TypeTable{'name-string'}->{maxLen};
3320      # Look for bad stuff in the name.      # Look for bad stuff in the name.
3321      if ($fieldName =~ /--/) {      if ($fieldName =~ /--/) {
3322          # Here we have a doubled minus sign.          # Here we have a doubled minus sign.
# Line 2608  Line 3326 
3326          # Here the field name is missing the initial letter.          # Here the field name is missing the initial letter.
3327          Trace("Field name $fieldName does not begin with a letter.") if T(1);          Trace("Field name $fieldName does not begin with a letter.") if T(1);
3328          $retVal = 0;          $retVal = 0;
3329        } elsif (length($fieldName) > $maxLen) {
3330            # Here the field name is too long.
3331            Trace("Maximum field name length is $maxLen. Field name must be truncated to " . substr($fieldName,0, $maxLen) . ".");
3332      } else {      } else {
3333          # Strip out the minus signs. Everything remaining must be a letter          # Strip out the minus signs. Everything remaining must be a letter,
3334          # or digit.          # underscore, or digit.
3335          my $strippedName = $fieldName;          my $strippedName = $fieldName;
3336          $strippedName =~ s/-//g;          $strippedName =~ s/-//g;
3337          if ($strippedName !~ /^[A-Za-z0-9]+$/) {          if ($strippedName !~ /^(\w|\d)+$/) {
3338              Trace("Field name $fieldName contains illegal characters.") if T(1);              Trace("Field name $fieldName contains illegal characters.") if T(1);
3339              $retVal = 0;              $retVal = 0;
3340          }          }
# Line 2762  Line 3483 
3483      # Substitute the bulletin board codes.      # Substitute the bulletin board codes.
3484      $retVal =~ s!\[(/?[bi])\]!<$1>!g;      $retVal =~ s!\[(/?[bi])\]!<$1>!g;
3485      $retVal =~ s!\[p\]!</p><p>!g;      $retVal =~ s!\[p\]!</p><p>!g;
3486        $retVal =~ s!\[link\s+([^\]]+)\]!<a href="$1">!g;
3487        $retVal =~ s!\[/link\]!</a>!g;
3488        # Return the result.
3489        return $retVal;
3490    }
3491    
3492    =head3 BeginTran
3493    
3494    C<< $erdb->BeginTran(); >>
3495    
3496    Start a database transaction.
3497    
3498    =cut
3499    
3500    sub BeginTran {
3501        my ($self) = @_;
3502        $self->{_dbh}->begin_tran();
3503    
3504    }
3505    
3506    =head3 CommitTran
3507    
3508    C<< $erdb->CommitTran(); >>
3509    
3510    Commit an active database transaction.
3511    
3512    =cut
3513    
3514    sub CommitTran {
3515        my ($self) = @_;
3516        $self->{_dbh}->commit_tran();
3517    }
3518    
3519    =head3 RollbackTran
3520    
3521    C<< $erdb->RollbackTran(); >>
3522    
3523    Roll back an active database transaction.
3524    
3525    =cut
3526    
3527    sub RollbackTran {
3528        my ($self) = @_;
3529        $self->{_dbh}->roll_tran();
3530    }
3531    
3532    =head3 UpdateField
3533    
3534    C<< my $count = $erdb->UpdateField($objectNames, $fieldName, $oldValue, $newValue, $filter, $parms); >>
3535    
3536    Update all occurrences of a specific field value to a new value. The number of rows changed will be
3537    returned.
3538    
3539    =over 4
3540    
3541    =item fieldName
3542    
3543    Name of the field in standard I<objectName>C<(>I<fieldName>C<)> format.
3544    
3545    =item oldValue
3546    
3547    Value to be modified. All occurrences of this value in the named field will be replaced by the
3548    new value.
3549    
3550    =item newValue
3551    
3552    New value to be substituted for the old value when it's found.
3553    
3554    =item filter
3555    
3556    A standard ERDB filter clause (see L</Get>). The filter will be applied before any substitutions take place.
3557    
3558    =item parms
3559    
3560    Reference to a list of parameter values in the filter.
3561    
3562    =item RETURN
3563    
3564    Returns the number of rows modified.
3565    
3566    =back
3567    
3568    =cut
3569    
3570    sub UpdateField {
3571        # Get the parameters.
3572        my ($self, $fieldName, $oldValue, $newValue, $filter, $parms) = @_;
3573        # Get the object and field names from the field name parameter.
3574        $fieldName =~ /^([^(]+)\(([^)]+)\)/;
3575        my $objectName = $1;
3576        my $realFieldName = _FixName($2);
3577        # Add the old value to the filter. Note we allow the possibility that no
3578        # filter was specified.
3579        my $realFilter = "$fieldName = ?";
3580        if ($filter) {
3581            $realFilter .= " AND $filter";
3582        }
3583        # Format the query filter.
3584        my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
3585            $self->_SetupSQL([$objectName], $realFilter);
3586        # Create the query. Since there is only one object name, the mapped-name data is not
3587        # necessary. Neither is the FROM clause.
3588        $suffix =~ s/^FROM.+WHERE\s+//;
3589        # Create the update statement.
3590        my $command = "UPDATE $objectName SET $realFieldName = ? WHERE $suffix";
3591        # Get the database handle.
3592        my $dbh = $self->{_dbh};
3593        # Add the old and new values to the parameter list. Note we allow the possibility that
3594        # there are no user-supplied parameters.
3595        my @params = ($newValue, $oldValue);
3596        if (defined $parms) {
3597            push @params, @{$parms};
3598        }
3599        # Execute the update.
3600        my $retVal = $dbh->SQL($command, 0, @params);
3601        # Make the funky zero a real zero.
3602        if ($retVal == 0) {
3603            $retVal = 0;
3604        }
3605      # Return the result.      # Return the result.
3606      return $retVal;      return $retVal;
3607  }  }
# Line 2922  Line 3762 
3762    
3763  =head2 Virtual Methods  =head2 Virtual Methods
3764    
3765    =head3 _CreatePPOIndex
3766    
3767    C<< my $index = ERDB::_CreatePPOIndex($indexObject); >>
3768    
3769    Convert the XML for an ERDB index to the XML structure for a PPO
3770    index.
3771    
3772    =over 4
3773    
3774    ERDB XML structure for an index.
3775    
3776    =item RETURN
3777    
3778    PPO XML structure for the same index.
3779    
3780    =back
3781    
3782    =cut
3783    
3784    sub _CreatePPOIndex {
3785        # Get the parameters.
3786        my ($indexObject) = @_;
3787        # The incoming index contains a list of the index fields in the IndexFields
3788        # member. We loop through it to create the index tags.
3789        my @fields = map { { label => _FixName($_->{name}) } } @{$indexObject->{IndexFields}};
3790        # Wrap the fields in attribute tags.
3791        my $retVal = { attribute => \@fields };
3792        # Return the result.
3793        return $retVal;
3794    }
3795    
3796    =head3 _CreatePPOField
3797    
3798    C<< my $fieldXML = ERDB::_CreatePPOField($fieldName, $fieldObject); >>
3799    
3800    Convert the ERDB XML structure for a field to a PPO scalar XML structure.
3801    
3802    =over 4
3803    
3804    =item fieldName
3805    
3806    Name of the scalar field.
3807    
3808    =item fieldObject
3809    
3810    ERDB XML structure describing the field.
3811    
3812    =item RETURN
3813    
3814    Returns a PPO XML structure for the same field.
3815    
3816    =back
3817    
3818    =cut
3819    
3820    sub _CreatePPOField {
3821        # Get the parameters.
3822        my ($fieldName, $fieldObject) = @_;
3823        # Get the field type.
3824        my $type = $TypeTable{$fieldObject->{type}}->{sqlType};
3825        # Fix up the field name.
3826        $fieldName = _FixName($fieldName);
3827        # Build the scalar tag.
3828        my $retVal = { label => $fieldName, type => $type };
3829        # Return the result.
3830        return $retVal;
3831    }
3832    
3833  =head3 CleanKeywords  =head3 CleanKeywords
3834    
3835  C<< my $cleanedString = $erdb->CleanKeywords($searchExpression); >>  C<< my $cleanedString = $erdb->CleanKeywords($searchExpression); >>
# Line 2973  Line 3881 
3881    
3882  C<< my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef); >>  C<< my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef); >>
3883    
3884  Create the relation map for an SQL query. The relation map is used by B<DBObject>  Create the relation map for an SQL query. The relation map is used by B<ERDBObject>
3885  to determine how to interpret the results of the query.  to determine how to interpret the results of the query.
3886    
3887  =over 4  =over 4
# Line 2990  Line 3898 
3898  =item RETURN  =item RETURN
3899    
3900  Returns a list of 2-tuples. Each tuple consists of an object name as used in the  Returns a list of 2-tuples. Each tuple consists of an object name as used in the
3901  query followed by the actual name of that object. This enables the B<DBObject> to  query followed by the actual name of that object. This enables the B<ERDBObject> to
3902  determine the order of the tables in the query and which object name belongs to each  determine the order of the tables in the query and which object name belongs to each
3903  mapped object name. Most of the time these two values are the same; however, if a  mapped object name. Most of the time these two values are the same; however, if a
3904  relation occurs twice in the query, the relation name in the field list and WHERE  relation occurs twice in the query, the relation name in the field list and WHERE
# Line 3292  Line 4200 
4200      # Prepare the command.      # Prepare the command.
4201      my $sth = $dbh->prepare_command($command);      my $sth = $dbh->prepare_command($command);
4202      # Execute it with the parameters bound in.      # Execute it with the parameters bound in.
4203      $sth->execute(@{$params}) || Confess("SELECT error" . $sth->errstr());      $sth->execute(@{$params}) || Confess("SELECT error:  " . $sth->errstr());
4204      # Return the statement handle.      # Return the statement handle.
4205      return $sth;      return $sth;
4206  }  }
# Line 3533  Line 4441 
4441    
4442  =head3 _LoadMetaData  =head3 _LoadMetaData
4443    
4444    C<< my $metadata = ERDB::_LoadMetaData($filename); >>
4445    
4446  This method loads the data describing this database from an XML file into a metadata structure.  This method loads the data describing this database from an XML file into a metadata structure.
4447  The resulting structure is a set of nested hash tables containing all the information needed to  The resulting structure is a set of nested hash tables containing all the information needed to
4448  load or use the database. The schema for the XML file is F<ERDatabase.xml>.  load or use the database. The schema for the XML file is F<ERDatabase.xml>.
# Line 3556  Line 4466 
4466  sub _LoadMetaData {  sub _LoadMetaData {
4467      # Get the parameters.      # Get the parameters.
4468      my ($filename) = @_;      my ($filename) = @_;
4469      Trace("Reading Sprout DBD from $filename.") if T(2);      Trace("Reading DBD from $filename.") if T(2);
4470      # Slurp the XML file into a variable. Extensive use of options is used to insure we      # Slurp the XML file into a variable. Extensive use of options is used to insure we
4471      # get the exact structure we want.      # get the exact structure we want.
4472      my $metadata = ReadMetaXML($filename);      my $metadata = ReadMetaXML($filename);
# Line 3682  Line 4592 
4592              if ($found == 0) {              if ($found == 0) {
4593                  push @{$indexList}, { IndexFields => [ {name => 'id', order => 'ascending'} ] };                  push @{$indexList}, { IndexFields => [ {name => 'id', order => 'ascending'} ] };
4594              }              }
4595              # Now we need to convert the relation's index list to an index table. We begin by creating              # Attach all the indexes to the relation.
4596              # an empty table in the relation structure.              _ProcessIndexes($indexList, $relation);
             $relation->{Indexes} = { };  
             # Loop through the indexes.  
             my $count = 0;  
             for my $index (@{$indexList}) {  
                 # Add this index to the index table.  
                 _AddIndex("idx$relationName$count", $relation, $index);  
                 # Increment the counter so that the next index has a different name.  
                 $count++;  
             }  
4597          }          }
4598          # Finally, we add the relation structure to the entity.          # Finally, we add the relation structure to the entity.
4599          $entityStructure->{Relations} = $relationTable;          $entityStructure->{Relations} = $relationTable;
# Line 3706  Line 4607 
4607          _FixupFields($relationshipStructure, $relationshipName, 2, 3);          _FixupFields($relationshipStructure, $relationshipName, 2, 3);
4608          # Format a description for the FROM field.          # Format a description for the FROM field.
4609          my $fromEntity = $relationshipStructure->{from};          my $fromEntity = $relationshipStructure->{from};
4610          my $fromComment = "<b>id</b> of the source <b><a href=\"#$fromEntity\">$fromEntity</a></b>.";          my $fromComment = "[b]id[/b] of the source [b][link #$fromEntity]$fromEntity\[/link][/b].";
4611          # Get the FROM entity's key type.          # Get the FROM entity's key type.
4612          my $fromType = $entityList->{$fromEntity}->{keyType};          my $fromType = $entityList->{$fromEntity}->{keyType};
4613          # Add the FROM field.          # Add the FROM field.
# Line 3716  Line 4617 
4617                                                      PrettySort => 1});                                                      PrettySort => 1});
4618          # Format a description for the TO field.          # Format a description for the TO field.
4619          my $toEntity = $relationshipStructure->{to};          my $toEntity = $relationshipStructure->{to};
4620          my $toComment = "<b>id</b> of the target <b><a href=\"#$toEntity\">$toEntity</a></b>.";          my $toComment = "[b]id[/b] of the target [b][link #$toEntity]$toEntity\[/link][/b].";
4621          # Get the TO entity's key type.          # Get the TO entity's key type.
4622          my $toType = $entityList->{$toEntity}->{keyType};          my $toType = $entityList->{$toEntity}->{keyType};
4623          # Add the TO field.          # Add the TO field.
# Line 3728  Line 4629 
4629          my $thisRelation = { Fields => _ReOrderRelationTable($relationshipStructure->{Fields}),          my $thisRelation = { Fields => _ReOrderRelationTable($relationshipStructure->{Fields}),
4630                               Indexes => { } };                               Indexes => { } };
4631          $relationshipStructure->{Relations} = { $relationshipName => $thisRelation };          $relationshipStructure->{Relations} = { $relationshipName => $thisRelation };
4632    
4633            # Add the alternate indexes (if any). This MUST be done before the FROM and
4634            # TO indexes, because it erases the relation's index list.
4635            if (exists $relationshipStructure->{Indexes}) {
4636                _ProcessIndexes($relationshipStructure->{Indexes}, $thisRelation);
4637            }
4638            # Add the relation to the master table.
4639          # Create the FROM and TO indexes.          # Create the FROM and TO indexes.
4640          _CreateRelationshipIndex("From", $relationshipName, $relationshipStructure);          _CreateRelationshipIndex("From", $relationshipName, $relationshipStructure);
4641          _CreateRelationshipIndex("To", $relationshipName, $relationshipStructure);          _CreateRelationshipIndex("To", $relationshipName, $relationshipStructure);
         # Add the relation to the master table.  
4642          $masterRelationTable{$relationshipName} = $thisRelation;          $masterRelationTable{$relationshipName} = $thisRelation;
4643      }      }
4644      # Now store the master relation table in the metadata structure.      # Now store the master relation table in the metadata structure.
# Line 3887  Line 4794 
4794          $newIndex->{Unique} = 'true';          $newIndex->{Unique} = 'true';
4795      }      }
4796      # Add the index to the relation.      # Add the index to the relation.
4797      _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);      _AddIndex("idx$indexKey", $relationStructure, $newIndex);
4798    }
4799    
4800    =head3 _ProcessIndexes
4801    
4802    C<< ERDB::_ProcessIndexes($indexList, $relation); >>
4803    
4804    Build the data structures for the specified indexes in the specified relation.
4805    
4806    =over 4
4807    
4808    =item indexList
4809    
4810    Reference to a list of indexes. Each index is a hash reference containing an optional
4811    C<Notes> value that describes the index and an C<IndexFields> value that is a reference
4812    to a list of index field structures. An index field structure, in turn, is a reference
4813    to a hash that contains a C<name> attribute for the field name and an C<order>
4814    attribute that specifies either C<ascending> or C<descending>. In this sense the
4815    index list encapsulates the XML C<Indexes> structure in the database definition.
4816    
4817    =item relation
4818    
4819    The structure that describes the current relation. The new index descriptors will
4820    be stored in the structure's C<Indexes> member. Any previous data in the structure
4821    will be lost.
4822    
4823    =back
4824    
4825    =cut
4826    
4827    sub _ProcessIndexes {
4828        # Get the parameters.
4829        my ($indexList, $relation) = @_;
4830        # Now we need to convert the relation's index list to an index table. We begin by creating
4831        # an empty table in the relation structure.
4832        $relation->{Indexes} = { };
4833        # Loop through the indexes.
4834        my $count = 0;
4835        for my $index (@{$indexList}) {
4836            # Add this index to the index table.
4837            _AddIndex("idx$count", $relation, $index);
4838            # Increment the counter so that the next index has a different name.
4839            $count++;
4840        }
4841  }  }
4842    
4843  =head3 _AddIndex  =head3 _AddIndex
# Line 4419  Line 5369 
5369      # Compute the number of columns.      # Compute the number of columns.
5370      my $colCount = @colNames;      my $colCount = @colNames;
5371      # Generate the title row.      # Generate the title row.
5372      my $htmlString = "<p><table border=\"2\"><tr><td colspan=\"$colCount\" align=\"center\">$tablename</td></tr>\n";      my $htmlString = "<table border=\"2\"><tr><td colspan=\"$colCount\" align=\"center\">$tablename</td></tr>\n";
5373      # Loop through the columns, adding the column header rows.      # Loop through the columns, adding the column header rows.
5374      $htmlString .= "<tr>";      $htmlString .= "<tr>";
5375      for my $colName (@colNames) {      for my $colName (@colNames) {
# Line 4438  Line 5388 
5388  =cut  =cut
5389    
5390  sub _CloseTable {  sub _CloseTable {
5391      return "</table></p>\n";      return "</table>\n";
5392  }  }
5393    
5394  =head3 _ShowField  =head3 _ShowField

Legend:
Removed from v.1.73  
changed lines
  Added in v.1.90

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3