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

Diff of /Sprout/ERDB.pm

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

revision 1.70, Fri Oct 13 21:45:11 2006 UTC revision 1.83, Mon Jan 22 20:23:58 2007 UTC
# Line 11  Line 11 
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 FIG;
14        use CGI;
15    
16  =head1 Entity-Relationship Database Package  =head1 Entity-Relationship Database Package
17    
# Line 59  Line 60 
60  B<start-position>, which indicates where in the contig that the sequence begins. This attribute  B<start-position>, which indicates where in the contig that the sequence begins. This attribute
61  is implemented as the C<start_position> field in the C<IsMadeUpOf> relation.  is implemented as the C<start_position> field in the C<IsMadeUpOf> relation.
62    
63  The database itself is described by an XML file using the F<ERDatabase.xsd> schema. In addition to  The database itself is described by an XML file. In addition to all the data required to define
64  all the data required to define the entities, relationships, and attributes, the schema provides  the entities, relationships, and attributes, the schema provides space for notes describing
65  space for notes describing the data and what it means. These notes are used by L</ShowMetaData>  the data and what it means. These notes are used by L</ShowMetaData> to generate documentation
66  to generate documentation for the database.  for the database.
67    
68    Special support is provided for text searching. An entity field can be marked as <em>searchable</em>,
69    in which case it will be used to generate a text search index in which the user searches for words
70    in the field instead of a particular field value.
71    
72  Finally, every entity and relationship object has a flag indicating if it is new or old. The object  Finally, every entity and relationship object has a flag indicating if it is new or old. The object
73  is considered I<old> if it was loaded by the L</LoadTables> method. It is considered I<new> if it  is considered I<old> if it was loaded by the L</LoadTables> method. It is considered I<new> if it
74  was inserted by the L</InsertObject> method.  was inserted by the L</InsertObject> method.
75    
 To facilitate testing, the ERDB module supports automatic generation of test data. This process  
 is described in the L</GenerateEntity> and L</GenerateConnection> methods, though it is not yet  
 fully implemented.  
   
76  =head2 XML Database Description  =head2 XML Database Description
77    
78  =head3 Data Types  =head3 Data Types
# Line 217  Line 218 
218  index will be created for each relation with at least one searchable field in it.  index will be created for each relation with at least one searchable field in it.
219  For best results, this option should only be used for string or text fields.  For best results, this option should only be used for string or text fields.
220    
221    =item special
222    
223    This attribute allows the subclass to assign special meaning for certain fields.
224    The interpretation is up to the subclass itself. Currently, only entity fields
225    can have this attribute.
226    
227  =back  =back
228    
229  =head3 Indexes  =head3 Indexes
230    
231  An entity can have multiple alternate indexes associated with it. The fields must  An entity can have multiple alternate indexes associated with it. The fields must
232  be from the primary relation. The alternate indexes assist in ordering results  all be from the same relation. The alternate indexes assist in ordering results
233  from a query. A relationship can have up to two indexes-- a I<to-index> and a  from a query. A relationship can have up to two indexes-- a I<to-index> and a
234  I<from-index>. These order the results when crossing the relationship. For  I<from-index>. These order the results when crossing the relationship. For
235  example, in the relationship C<HasContig> from C<Genome> to C<Contig>, the  example, in the relationship C<HasContig> from C<Genome> to C<Contig>, the
# Line 250  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 328  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                  );                  );
376    
377  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 357  Line 380 
380                     'MM' => 'many-to-many'                     'MM' => 'many-to-many'
381                   );                   );
382    
383  # Table for interpreting string patterns.  # Options for XML input and output.
384    
385    my %XmlOptions = (GroupTags =>  { Relationships => 'Relationship',
386                                      Entities => 'Entity',
387                                      Fields => 'Field',
388                                      Indexes => 'Index',
389                                      IndexFields => 'IndexField'
390                                    },
391                      KeyAttr =>    { Relationship => 'name',
392                                      Entity => 'name',
393                                      Field => 'name'
394                                    },
395                      SuppressEmpty => 1,
396                     );
397    
398  my %PictureTable = ( 'A' => "abcdefghijklmnopqrstuvwxyz",  my %XmlInOpts  = (
399                       '9' => "0123456789",                    ForceArray => ['Field', 'Index', 'IndexField', 'Relationship', 'Entity'],
400                       'X' => "abcdefghijklmnopqrstuvwxyz0123456789",                    ForceContent => 1,
401                       'V' => "aeiou",                    NormalizeSpace => 2,
402                       'K' => "bcdfghjklmnoprstvwxyz"                   );
403    my %XmlOutOpts = (
404                      RootName => 'Database',
405                      XMLDecl => 1,
406                     );                     );
407    
408    
409  =head2 Public Methods  =head2 Public Methods
410    
411  =head3 new  =head3 new
# Line 506  Line 546 
546          my $entityData = $entityList->{$key};          my $entityData = $entityList->{$key};
547          # If there's descriptive text, display it.          # If there's descriptive text, display it.
548          if (my $notes = $entityData->{Notes}) {          if (my $notes = $entityData->{Notes}) {
549              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
550          }          }
551          # Now we want a list of the entity's relationships. First, we set up the relationship subsection.          # See if we need a list of the entity's relationships.
552            my $relCount = keys %{$relationshipList};
553            if ($relCount > 0) {
554                # First, we set up the relationship subsection.
555          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
556          # Loop through the relationships.          # Loop through the relationships.
557          for my $relationship (sort keys %{$relationshipList}) {          for my $relationship (sort keys %{$relationshipList}) {
# Line 524  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 563  Line 607 
607          $retVal .= "</p>\n";          $retVal .= "</p>\n";
608          # If there are notes on this relationship, display them.          # If there are notes on this relationship, display them.
609          if (my $notes = $relationshipStructure->{Notes}) {          if (my $notes = $relationshipStructure->{Notes}) {
610              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
611          }          }
612          # Generate the relationship's relation table.          # Generate the relationship's relation table.
613          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
# Line 610  Line 654 
654      return Data::Dumper::Dumper($self->{_metaData});      return Data::Dumper::Dumper($self->{_metaData});
655  }  }
656    
657    =head3 FindIndexForEntity
658    
659    C<< my $indexFound = ERDB::FindIndexForEntity($xml, $entityName, $attributeName); >>
660    
661    This method locates the entry in an entity's index list that begins with the
662    specified attribute name. If the entity has no index list, one will be
663    created. This method works on raw XML, not a live ERDB object.
664    
665    =over 4
666    
667    =item xml
668    
669    The raw XML structure defining the database.
670    
671    =item entityName
672    
673    The name of the relevant entity.
674    
675    =item attributeName
676    
677    The name of the attribute relevant to the search.
678    
679    =item RETURN
680    
681    The numerical index in the index list of the index entry for the specified entity and
682    attribute, or C<undef> if no such index exists.
683    
684    =back
685    
686    =cut
687    
688    sub FindIndexForEntity {
689        # Get the parameters.
690        my ($xml, $entityName, $attributeName) = @_;
691        # Declare the return variable.
692        my $retVal;
693        # Get the named entity.
694        my $entityData = $xml->{Entities}->{$entityName};
695        if (! $entityData) {
696            Confess("Entity $entityName not found in DBD structure.");
697        } else {
698            # Insure it has an index list.
699            if (! exists $entityData->{Indexes}) {
700                $entityData->{Indexes} = [];
701            } else {
702                # Search for the desired index.
703                my $indexList = $entityData->{Indexes};
704                my $n = scalar @{$indexList};
705                Trace("Searching $n indexes in index list for $entityName.") if T(2);
706                # We use an indexed FOR here because we're returning an
707                # index number instead of an object. We do THAT so we can
708                # delete the index from the list if needed.
709                for (my $i = 0; $i < $n && !defined($retVal); $i++) {
710                    my $index = $indexList->[$i];
711                    my $fields = $index->{IndexFields};
712                    # Technically this IF should be safe (that is, we are guaranteed
713                    # the existence of a "$fields->[0]"), because when we load the XML
714                    # we have SuppressEmpty specified.
715                    if ($fields->[0]->{name} eq $attributeName) {
716                        $retVal = $i;
717                    }
718                }
719            }
720        }
721        Trace("Index for $attributeName of $entityName found at position $retVal.") if defined($retVal) && T(3);
722        Trace("Index for $attributeName not found in $entityName.") if !defined($retVal) && T(3);
723        # Return the result.
724        return $retVal;
725    }
726    
727  =head3 CreateTables  =head3 CreateTables
728    
729  C<< $erdb->CreateTables(); >>  C<< $erdb->CreateTables(); >>
# Line 855  Line 969 
969      for my $indexName (keys %{$indexHash}) {      for my $indexName (keys %{$indexHash}) {
970          my $indexData = $indexHash->{$indexName};          my $indexData = $indexHash->{$indexName};
971          # Get the index's field list.          # Get the index's field list.
972          my @fieldList = _FixNames(@{$indexData->{IndexFields}});          my @rawFields = @{$indexData->{IndexFields}};
973            # Get a hash of the relation's field types.
974            my %types = map { $_->{name} => $_->{type} } @{$relationData->{Fields}};
975            # We need to check for text fields so we can append a length limitation for them. To do
976            # that, we need the relation's field list.
977            my $relFields = $relationData->{Fields};
978            for (my $i = 0; $i <= $#rawFields; $i++) {
979                # Get the field type.
980                my $field = $rawFields[$i];
981                my $type = $types{$field};
982                # Ask if it requires using prefix notation for the index.
983                my $mod = $TypeTable{$type}->{indexMod};
984                Trace("Field $field ($i) in $relationName has type $type and indexMod $mod.") if T(3);
985                if ($mod) {
986                    # Append the prefix length to the field name,
987                    $rawFields[$i] .= "($mod)";
988                }
989            }
990            my @fieldList = _FixNames(@rawFields);
991          my $flds = join(', ', @fieldList);          my $flds = join(', ', @fieldList);
992          # Get the index's uniqueness flag.          # Get the index's uniqueness flag.
993          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
# Line 870  Line 1002 
1002      }      }
1003  }  }
1004    
1005    =head3 GetSecondaryFields
1006    
1007    C<< my %fieldTuples = $erdb->GetSecondaryFields($entityName); >>
1008    
1009    This method will return a list of the name and type of each of the secondary
1010    fields for a specified entity. Secondary fields are stored in two-column tables
1011    in addition to the primary entity table. This enables the field to have no value
1012    or to have multiple values.
1013    
1014    =over 4
1015    
1016    =item entityName
1017    
1018    Name of the entity whose secondary fields are desired.
1019    
1020    =item RETURN
1021    
1022    Returns a hash mapping the field names to their field types.
1023    
1024    =back
1025    
1026    =cut
1027    
1028    sub GetSecondaryFields {
1029        # Get the parameters.
1030        my ($self, $entityName) = @_;
1031        # Declare the return variable.
1032        my %retVal = ();
1033        # Look for the entity.
1034        my $table = $self->GetFieldTable($entityName);
1035        # Loop through the fields, pulling out the secondaries.
1036        for my $field (sort keys %{$table}) {
1037            if ($table->{$field}->{relation} ne $entityName) {
1038                # Here we have a secondary field.
1039                $retVal{$field} = $table->{$field}->{type};
1040            }
1041        }
1042        # Return the result.
1043        return %retVal;
1044    }
1045    
1046    =head3 GetFieldRelationName
1047    
1048    C<< my $name = $erdb->GetFieldRelationName($objectName, $fieldName); >>
1049    
1050    Return the name of the relation containing a specified field.
1051    
1052    =over 4
1053    
1054    =item objectName
1055    
1056    Name of the entity or relationship containing the field.
1057    
1058    =item fieldName
1059    
1060    Name of the relevant field in that entity or relationship.
1061    
1062    =item RETURN
1063    
1064    Returns the name of the database relation containing the field, or C<undef> if
1065    the field does not exist.
1066    
1067    =back
1068    
1069    =cut
1070    
1071    sub GetFieldRelationName {
1072        # Get the parameters.
1073        my ($self, $objectName, $fieldName) = @_;
1074        # Declare the return variable.
1075        my $retVal;
1076        # Get the object field table.
1077        my $table = $self->GetFieldTable($objectName);
1078        # Only proceed if the field exists.
1079        if (exists $table->{$fieldName}) {
1080            # Determine the name of the relation that contains this field.
1081            $retVal = $table->{$fieldName}->{relation};
1082        }
1083        # Return the result.
1084        return $retVal;
1085    }
1086    
1087    =head3 DeleteValue
1088    
1089    C<< my $numDeleted = $erdb->DeleteValue($entityName, $id, $fieldName, $fieldValue); >>
1090    
1091    Delete secondary field values from the database. This method can be used to delete all
1092    values of a specified field for a particular entity instance, or only a single value.
1093    
1094    Secondary fields are stored in two-column relations separate from an entity's primary
1095    table, and as a result a secondary field can legitimately have no value or multiple
1096    values. Therefore, it makes sense to talk about deleting secondary fields where it
1097    would not make sense for primary fields.
1098    
1099    =over 4
1100    
1101    =item entityName
1102    
1103    Name of the entity from which the fields are to be deleted.
1104    
1105    =item id
1106    
1107    ID of the entity instance to be processed. If the instance is not found, this
1108    method will have no effect. If C<undef> is specified, all values for all of
1109    the entity instances will be deleted.
1110    
1111    =item fieldName
1112    
1113    Name of the field whose values are to be deleted.
1114    
1115    =item fieldValue (optional)
1116    
1117    Value to be deleted. If not specified, then all values of the specified field
1118    will be deleted for the entity instance. If specified, then only the values which
1119    match this parameter will be deleted.
1120    
1121    =item RETURN
1122    
1123    Returns the number of rows deleted.
1124    
1125    =back
1126    
1127    =cut
1128    
1129    sub DeleteValue {
1130        # Get the parameters.
1131        my ($self, $entityName, $id, $fieldName, $fieldValue) = @_;
1132        # Declare the return value.
1133        my $retVal = 0;
1134        # We need to set up an SQL command to do the deletion. First, we
1135        # find the name of the field's relation.
1136        my $table = $self->GetFieldTable($entityName);
1137        my $field = $table->{$fieldName};
1138        my $relation = $field->{relation};
1139        # Make sure this is a secondary field.
1140        if ($relation eq $entityName) {
1141            Confess("Cannot delete values of $fieldName for $entityName.");
1142        } else {
1143            # Set up the SQL command to delete all values.
1144            my $sql = "DELETE FROM $relation";
1145            # Build the filter.
1146            my @filters = ();
1147            my @parms = ();
1148            # Check for a filter by ID.
1149            if (defined $id) {
1150                push @filters, "id = ?";
1151                push @parms, $id;
1152            }
1153            # Check for a filter by value.
1154            if (defined $fieldValue) {
1155                push @filters, "$fieldName = ?";
1156                push @parms, $fieldValue;
1157            }
1158            # Append the filters to the command.
1159            if (@filters) {
1160                $sql .= " WHERE " . join(" AND ", @filters);
1161            }
1162            # Execute the command.
1163            my $dbh = $self->{_dbh};
1164            $retVal = $dbh->SQL($sql, 0, @parms);
1165        }
1166        # Return the result.
1167        return $retVal;
1168    }
1169    
1170  =head3 LoadTables  =head3 LoadTables
1171    
1172  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>
# Line 964  Line 1261 
1261      return sort keys %{$entityList};      return sort keys %{$entityList};
1262  }  }
1263    
1264    =head3 GetDataTypes
1265    
1266    C<< my %types = ERDB::GetDataTypes(); >>
1267    
1268    Return a table of ERDB data types. The table returned is a hash of hashes.
1269    The keys of the big hash are the datatypes. Each smaller hash has several
1270    values used to manage the data. The most interesting is the SQL type (key
1271    C<sqlType>) and the descriptive node (key C<notes>).
1272    
1273    Note that changing the values in the smaller hashes will seriously break
1274    things, so this data should be treated as read-only.
1275    
1276    =cut
1277    
1278    sub GetDataTypes {
1279        return %TypeTable;
1280    }
1281    
1282    
1283  =head3 IsEntity  =head3 IsEntity
1284    
1285  C<< my $flag = $erdb->IsEntity($entityName); >>  C<< my $flag = $erdb->IsEntity($entityName); >>
# Line 1108  Line 1424 
1424      return $retVal;      return $retVal;
1425  }  }
1426    
1427    
1428    
1429  =head3 Search  =head3 Search
1430    
1431  C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>  C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>
# Line 1121  Line 1439 
1439    
1440  =item searchExpression  =item searchExpression
1441    
1442  Boolean search expression for the text fields of the target object.  Boolean search expression for the text fields of the target object. The default mode for
1443    a Boolean search expression is OR, but we want the default to be AND, so we will
1444    add a C<+> operator to each word with no other operator before it.
1445    
1446  =item idx  =item idx
1447    
# Line 1158  Line 1478 
1478      my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;      my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1479      # Declare the return variable.      # Declare the return variable.
1480      my $retVal;      my $retVal;
1481      # Create a safety copy of the parameter list.      # Create a safety copy of the parameter list. Note we have to be careful to insure
1482      my @myParams = @{$params};      # a parameter list exists before we copy it.
1483        my @myParams = ();
1484        if (defined $params) {
1485            @myParams = @{$params};
1486        }
1487      # Get the first object's structure so we have access to the searchable fields.      # Get the first object's structure so we have access to the searchable fields.
1488      my $object1Name = $objectNames->[$idx];      my $object1Name = $objectNames->[$idx];
1489      my $object1Structure = $self->_GetStructure($object1Name);      my $object1Structure = $self->_GetStructure($object1Name);
# Line 1169  Line 1493 
1493      } else {      } else {
1494          # Get the field list.          # Get the field list.
1495          my @fields = @{$object1Structure->{searchFields}};          my @fields = @{$object1Structure->{searchFields}};
1496            # Clean the search expression.
1497            my $actualKeywords = $self->CleanKeywords($searchExpression);
1498            # Prefix a "+" to each uncontrolled word. This converts the default
1499            # search mode from OR to AND.
1500            $actualKeywords =~ s/(^|\s)(\w|")/$1\+$2/g;
1501            Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1502          # 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
1503          # 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
1504          # search expression onto the front of the parameter list twice.          # search expression onto the front of the parameter list twice.
1505          unshift @myParams, $searchExpression, $searchExpression;          unshift @myParams, $actualKeywords, $actualKeywords;
1506          # Build the match expression.          # Build the match expression.
1507          my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;          my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
1508          my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";          my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
# Line 1246  Line 1576 
1576      return @retVal;      return @retVal;
1577  }  }
1578    
1579    =head3 SpecialFields
1580    
1581    C<< my %specials = $erdb->SpecialFields($entityName); >>
1582    
1583    Return a hash mapping special fields in the specified entity to the value of their
1584    C<special> attribute. This enables the subclass to get access to the special field
1585    attributes without needed to plumb the internal ERDB data structures.
1586    
1587    =over 4
1588    
1589    =item entityName
1590    
1591    Name of the entity whose special fields are desired.
1592    
1593    =item RETURN
1594    
1595    Returns a hash. The keys of the hash are the special field names, and the values
1596    are the values from each special field's C<special> attribute.
1597    
1598    =back
1599    
1600    =cut
1601    
1602    sub SpecialFields {
1603        # Get the parameters.
1604        my ($self, $entityName) = @_;
1605        # Declare the return variable.
1606        my %retVal = ();
1607        # Find the entity's data structure.
1608        my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1609        # Loop through its fields, adding each special field to the return hash.
1610        my $fieldHash = $entityData->{Fields};
1611        for my $fieldName (keys %{$fieldHash}) {
1612            my $fieldData = $fieldHash->{$fieldName};
1613            if (exists $fieldData->{special}) {
1614                $retVal{$fieldName} = $fieldData->{special};
1615            }
1616        }
1617        # Return the result.
1618        return %retVal;
1619    }
1620    
1621  =head3 Delete  =head3 Delete
1622    
1623  C<< my $stats = $erdb->Delete($entityName, $objectID); >>  C<< my $stats = $erdb->Delete($entityName, $objectID, %options); >>
1624    
1625  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
1626  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.
1627  always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many  
1628  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
1629    relationship connected to a dependent entity or if it is the "to" entity connected to a 1-to-many
1630  dependent relationship.  dependent relationship.
1631    
1632  =over 4  =over 4
# Line 1267  Line 1640 
1640  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<%>),
1641  then it is presumed to by a LIKE pattern.  then it is presumed to by a LIKE pattern.
1642    
1643  =item testFlag  =item options
1644    
1645  If TRUE, the delete statements will be traced without being executed.  A hash detailing the options for this delete operation.
1646    
1647  =item RETURN  =item RETURN
1648    
# Line 1278  Line 1651 
1651    
1652  =back  =back
1653    
1654    The permissible options for this method are as follows.
1655    
1656    =over 4
1657    
1658    =item testMode
1659    
1660    If TRUE, then the delete statements will be traced, but no changes will be made to the database.
1661    
1662    =item keepRoot
1663    
1664    If TRUE, then the entity instances will not be deleted, only the dependent records.
1665    
1666    =back
1667    
1668  =cut  =cut
1669  #: Return Type $%;  #: Return Type $%;
1670  sub Delete {  sub Delete {
1671      # Get the parameters.      # Get the parameters.
1672      my ($self, $entityName, $objectID, $testFlag) = @_;      my ($self, $entityName, $objectID, %options) = @_;
1673      # Declare the return variable.      # Declare the return variable.
1674      my $retVal = Stats->new();      my $retVal = Stats->new();
1675      # Get the DBKernel object.      # Get the DBKernel object.
# Line 1299  Line 1686 
1686      # FROM-relationships and entities.      # FROM-relationships and entities.
1687      my @fromPathList = ();      my @fromPathList = ();
1688      my @toPathList = ();      my @toPathList = ();
1689      # This final hash is used to remember what work still needs to be done. We push paths      # This final list is used to remember what work still needs to be done. We push paths
1690      # onto the list, then pop them off to extend the paths. We prime it with the starting      # onto the list, then pop them off to extend the paths. We prime it with the starting
1691      # point. Note that we will work hard to insure that the last item on a path in the      # point. Note that we will work hard to insure that the last item on a path in the
1692      # TODO list is always an entity.      # to-do list is always an entity.
1693      my @todoList = ([$entityName]);      my @todoList = ([$entityName]);
1694      while (@todoList) {      while (@todoList) {
1695          # Get the current path.          # Get the current path.
# Line 1310  Line 1697 
1697          # Copy it into a list.          # Copy it into a list.
1698          my @stackedPath = @{$current};          my @stackedPath = @{$current};
1699          # 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.
1700          my $entityName = pop @stackedPath;          my $myEntityName = pop @stackedPath;
1701          # Add it to the alreadyFound list.          # Add it to the alreadyFound list.
1702          $alreadyFound{$entityName} = 1;          $alreadyFound{$myEntityName} = 1;
1703            # Figure out if we need to delete this entity.
1704            if ($myEntityName ne $entityName || ! $options{keepRoot}) {
1705          # Get the entity data.          # Get the entity data.
1706          my $entityData = $self->_GetStructure($entityName);              my $entityData = $self->_GetStructure($myEntityName);
1707          # 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.  
1708          my $relations = $entityData->{Relations};          my $relations = $entityData->{Relations};
1709          for my $relation (keys %{$relations}) {          for my $relation (keys %{$relations}) {
1710              my @augmentedList = (@stackedPath, $relation);              my @augmentedList = (@stackedPath, $relation);
1711              push @fromPathList, \@augmentedList;              push @fromPathList, \@augmentedList;
1712          }          }
1713            }
1714          # Now we need to look for relationships connected to this entity.          # Now we need to look for relationships connected to this entity.
1715          my $relationshipList = $self->{_metaData}->{Relationships};          my $relationshipList = $self->{_metaData}->{Relationships};
1716          for my $relationshipName (keys %{$relationshipList}) {          for my $relationshipName (keys %{$relationshipList}) {
1717              my $relationship = $relationshipList->{$relationshipName};              my $relationship = $relationshipList->{$relationshipName};
1718              # Check the FROM field. We're only interested if it's us.              # Check the FROM field. We're only interested if it's us.
1719              if ($relationship->{from} eq $entityName) {              if ($relationship->{from} eq $myEntityName) {
1720                  # Add the path to this relationship.                  # Add the path to this relationship.
1721                  my @augmentedList = (@stackedPath, $entityName, $relationshipName);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1722                  push @fromPathList, \@augmentedList;                  push @fromPathList, \@augmentedList;
1723                  # Check the arity. If it's MM we're done. If it's 1M                  # Check the arity. If it's MM we're done. If it's 1M
1724                  # and the target hasn't been seen yet, we want to                  # and the target hasn't been seen yet, we want to
# Line 1348  Line 1737 
1737              }              }
1738              # Now check the TO field. In this case only the relationship needs              # Now check the TO field. In this case only the relationship needs
1739              # deletion.              # deletion.
1740              if ($relationship->{to} eq $entityName) {              if ($relationship->{to} eq $myEntityName) {
1741                  my @augmentedList = (@stackedPath, $entityName, $relationshipName);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1742                  push @toPathList, \@augmentedList;                  push @toPathList, \@augmentedList;
1743              }              }
1744          }          }
1745      }      }
1746      # Create the first qualifier for the WHERE clause. This selects the      # Create the first qualifier for the WHERE clause. This selects the
1747      # 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
1748      # 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
1749      # to the table containing the dependent records to delete.      # to the table containing the dependent records to delete.
1750      my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");      my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
1751      # 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 1395  Line 1784 
1784                  }                  }
1785              }              }
1786              # Now we have our desired DELETE statement.              # Now we have our desired DELETE statement.
1787              if ($testFlag) {              if ($options{testMode}) {
1788                  # Here the user wants to trace without executing.                  # Here the user wants to trace without executing.
1789                  Trace($stmt) if T(0);                  Trace($stmt) if T(0);
1790              } else {              } else {
1791                  # 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
1792                  # if an error occurs, so we just go ahead and do it.                  # if an error occurs, so we just go ahead and do it.
1793                  Trace("Executing delete from $target using '$objectID'.") if T(3);                  Trace("Executing delete from $target using '$objectID'.") if T(3);
1794                  my $rv = $db->SQL($stmt, 0, $objectID);                  my $rv = $db->SQL($stmt, 0, $objectID);
# Line 1414  Line 1803 
1803      return $retVal;      return $retVal;
1804  }  }
1805    
1806    =head3 Disconnect
1807    
1808    C<< $erdb->Disconnect($relationshipName, $originEntityName, $originEntityID); >>
1809    
1810    Disconnect an entity instance from all the objects to which it is related. This
1811    will delete each relationship instance that connects to the specified entity.
1812    
1813    =over 4
1814    
1815    =item relationshipName
1816    
1817    Name of the relationship whose instances are to be deleted.
1818    
1819    =item originEntityName
1820    
1821    Name of the entity that is to be disconnected.
1822    
1823    =item originEntityID
1824    
1825    ID of the entity that is to be disconnected.
1826    
1827    =back
1828    
1829    =cut
1830    
1831    sub Disconnect {
1832        # Get the parameters.
1833        my ($self, $relationshipName, $originEntityName, $originEntityID) = @_;
1834        # Get the relationship descriptor.
1835        my $structure = $self->_GetStructure($relationshipName);
1836        # Insure we have a relationship.
1837        if (! exists $structure->{from}) {
1838            Confess("$relationshipName is not a relationship in the database.");
1839        } else {
1840            # Get the database handle.
1841            my $dbh = $self->{_dbh};
1842            # We'll set this value to 1 if we find our entity.
1843            my $found = 0;
1844            # Loop through the ends of the relationship.
1845            for my $dir ('from', 'to') {
1846                if ($structure->{$dir} eq $originEntityName) {
1847                    # Delete all relationship instances on this side of the entity instance.
1848                    $dbh->SQL("DELETE FROM $relationshipName WHERE ${dir}_link = ?", 0, $originEntityID);
1849                    $found = 1;
1850                }
1851            }
1852            # Insure we found the entity on at least one end.
1853            if (! $found) {
1854                Confess("Entity \"$originEntityName\" does not use $relationshipName.");
1855            }
1856        }
1857    }
1858    
1859    =head3 DeleteRow
1860    
1861    C<< $erdb->DeleteRow($relationshipName, $fromLink, $toLink, \%values); >>
1862    
1863    Delete a row from a relationship. In most cases, only the from-link and to-link are
1864    needed; however, for relationships with intersection data values can be specified
1865    for the other fields using a hash.
1866    
1867    =over 4
1868    
1869    =item relationshipName
1870    
1871    Name of the relationship from which the row is to be deleted.
1872    
1873    =item fromLink
1874    
1875    ID of the entity instance in the From direction.
1876    
1877    =item toLink
1878    
1879    ID of the entity instance in the To direction.
1880    
1881    =item values
1882    
1883    Reference to a hash of other values to be used for filtering the delete.
1884    
1885    =back
1886    
1887    =cut
1888    
1889    sub DeleteRow {
1890        # Get the parameters.
1891        my ($self, $relationshipName, $fromLink, $toLink, $values) = @_;
1892        # Create a hash of all the filter information.
1893        my %filter = ('from-link' => $fromLink, 'to-link' => $toLink);
1894        if (defined $values) {
1895            for my $key (keys %{$values}) {
1896                $filter{$key} = $values->{$key};
1897            }
1898        }
1899        # Build an SQL statement out of the hash.
1900        my @filters = ();
1901        my @parms = ();
1902        for my $key (keys %filter) {
1903            push @filters, _FixName($key) . " = ?";
1904            push @parms, $filter{$key};
1905        }
1906        Trace("Parms for delete row are " . join(", ", map { "\"$_\"" } @parms) . ".") if T(SQL => 4);
1907        my $command = "DELETE FROM $relationshipName WHERE " .
1908                      join(" AND ", @filters);
1909        # Execute it.
1910        my $dbh = $self->{_dbh};
1911        $dbh->SQL($command, undef, @parms);
1912    }
1913    
1914  =head3 SortNeeded  =head3 SortNeeded
1915    
1916  C<< my $parms = $erdb->SortNeeded($relationName); >>  C<< my $parms = $erdb->SortNeeded($relationName); >>
# Line 1464  Line 1961 
1961      } elsif (exists $relationshipTable->{$relationName}) {      } elsif (exists $relationshipTable->{$relationName}) {
1962          # Here we have a relationship. We sort using the FROM index.          # Here we have a relationship. We sort using the FROM index.
1963          my $relationshipData = $relationshipTable->{$relationName};          my $relationshipData = $relationshipTable->{$relationName};
1964          my $index = $relationData->{Indexes}->{"idx${relationName}From"};          my $index = $relationData->{Indexes}->{idxFrom};
1965          push @keyNames, @{$index->{IndexFields}};          push @keyNames, @{$index->{IndexFields}};
1966      } else {      } else {
1967          # 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 1810  Line 2307 
2307    
2308  =head3 InsertObject  =head3 InsertObject
2309    
2310  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>  C<< $erdb->InsertObject($objectType, \%fieldHash); >>
2311    
2312  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
2313  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 1836  Line 2333 
2333    
2334  Hash of field names to values.  Hash of field names to values.
2335    
 =item RETURN  
   
 Returns 1 if successful, 0 if an error occurred.  
   
2336  =back  =back
2337    
2338  =cut  =cut
# Line 1938  Line 2431 
2431                  $retVal = $sth->execute(@parameterList);                  $retVal = $sth->execute(@parameterList);
2432                  if (!$retVal) {                  if (!$retVal) {
2433                      my $errorString = $sth->errstr();                      my $errorString = $sth->errstr();
2434                      Trace("Insert error: $errorString.") if T(0);                      Confess("Error inserting into $relationName: $errorString");
2435                  }                  }
2436              }              }
2437          }          }
2438      }      }
2439      # Return the success indicator.      # Return a 1 for backward compatability.
2440      return $retVal;      return 1;
2441  }  }
2442    
2443  =head3 LoadTable  =head3 UpdateEntity
2444    
2445  C<< my %results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>  C<< $erdb->UpdateEntity($entityName, $id, \%fields); >>
2446    
2447  Load data from a tab-delimited file into a specified table, optionally re-creating the table  Update the values of an entity. This is an unprotected update, so it should only be
2448  first.  done if the database resides on a database server.
2449    
2450  =over 4  =over 4
2451    
2452  =item fileName  =item entityName
2453    
2454  Name of the file from which the table data should be loaded.  Name of the entity to update. (This is the entity type.)
2455    
2456  =item relationName  =item id
2457    
2458  Name of the relation to be loaded. This is the same as the table name.  ID of the entity to update. If no entity exists with this ID, an error will be thrown.
2459    
2460  =item truncateFlag  =item fields
2461    
2462  TRUE if the table should be dropped and re-created, else FALSE  Reference to a hash mapping field names to their new values. All of the fields named
2463    must be in the entity's primary relation, and they cannot any of them be the ID field.
2464    
2465  =item RETURN  =back
2466    
2467    =cut
2468    
2469    sub UpdateEntity {
2470        # Get the parameters.
2471        my ($self, $entityName, $id, $fields) = @_;
2472        # Get a list of the field names being updated.
2473        my @fieldList = keys %{$fields};
2474        # Verify that the fields exist.
2475        my $checker = $self->GetFieldTable($entityName);
2476        for my $field (@fieldList) {
2477            if ($field eq 'id') {
2478                Confess("Cannot update the ID field for entity $entityName.");
2479            } elsif ($checker->{$field}->{relation} ne $entityName) {
2480                Confess("Cannot find $field in primary relation of $entityName.");
2481            }
2482        }
2483        # Build the SQL statement.
2484        my @sets = ();
2485        my @valueList = ();
2486        for my $field (@fieldList) {
2487            push @sets, _FixName($field) . " = ?";
2488            push @valueList, $fields->{$field};
2489        }
2490        my $command = "UPDATE $entityName SET " . join(", ", @sets) . " WHERE id = ?";
2491        # Add the ID to the list of binding values.
2492        push @valueList, $id;
2493        # Call SQL to do the work.
2494        my $rows = $self->{_dbh}->SQL($command, 0, @valueList);
2495        # Check for errors.
2496        if ($rows == 0) {
2497            Confess("Entity $id of type $entityName not found.");
2498        }
2499    }
2500    
2501    =head3 LoadTable
2502    
2503    C<< my $results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>
2504    
2505    Load data from a tab-delimited file into a specified table, optionally re-creating the table
2506    first.
2507    
2508    =over 4
2509    
2510    =item fileName
2511    
2512    Name of the file from which the table data should be loaded.
2513    
2514    =item relationName
2515    
2516    Name of the relation to be loaded. This is the same as the table name.
2517    
2518    =item truncateFlag
2519    
2520    TRUE if the table should be dropped and re-created, else FALSE
2521    
2522    =item RETURN
2523    
2524  Returns a statistical object containing a list of the error messages.  Returns a statistical object containing a list of the error messages.
2525    
# Line 2016  Line 2567 
2567      };      };
2568      if (!defined $rv) {      if (!defined $rv) {
2569          $retVal->AddMessage($@) if ($@);          $retVal->AddMessage($@) if ($@);
2570          $retVal->AddMessage("Table load failed for $relationName using $fileName.");          $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2571          Trace("Table load failed for $relationName.") if T(1);          Trace("Table load failed for $relationName.") if T(1);
2572      } else {      } else {
2573          # Here we successfully loaded the table.          # Here we successfully loaded the table.
# Line 2038  Line 2589 
2589              # 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.
2590              # 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
2591              # primary relations are allowed that privilege.              # primary relations are allowed that privilege.
2592                Trace("Checking for full-text index on $relationName.") if T(2);
2593              if ($self->_IsPrimary($relationName)) {              if ($self->_IsPrimary($relationName)) {
2594                  # 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');  
                 }  
2595              }              }
2596          }          }
2597      }      }
# Line 2061  Line 2603 
2603      return $retVal;      return $retVal;
2604  }  }
2605    
2606  =head3 GenerateEntity  =head3 CreateSearchIndex
2607    
2608  C<< my $fieldHash = $erdb->GenerateEntity($id, $type, \%values); >>  C<< $erdb->CreateSearchIndex($objectName); >>
2609    
2610  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
2611  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.  
2612    
2613  =over 4  =over 4
2614    
2615  =item id  =item objectName
2616    
2617  ID to assign to the new entity.  Name of the entity or relationship to be indexed.
2618    
2619  =item type  =back
2620    
2621  Type name for the new entity.  =cut
2622    
2623  =item values  sub CreateSearchIndex {
2624        # Get the parameters.
2625        my ($self, $objectName) = @_;
2626        # Get the relation's entity/relationship structure.
2627        my $structure = $self->_GetStructure($objectName);
2628        # Get the database handle.
2629        my $dbh = $self->{_dbh};
2630        Trace("Checking for search fields in $objectName.") if T(3);
2631        # Check for a searchable fields list.
2632        if (exists $structure->{searchFields}) {
2633            # Here we know that we need to create a full-text search index.
2634            # Get an SQL-formatted field name list.
2635            my $fields = join(", ", _FixNames(@{$structure->{searchFields}}));
2636            # Create the index. If it already exists, it will be dropped.
2637            $dbh->create_index(tbl => $objectName, idx => "search_idx",
2638                               flds => $fields, kind => 'fulltext');
2639            Trace("Index created for $fields in $objectName.") if T(2);
2640        }
2641    }
2642    
2643    =head3 DropRelation
2644    
2645    C<< $erdb->DropRelation($relationName); >>
2646    
2647  Hash containing additional values that might be needed by the data generation methods (optional).  Physically drop a relation from the database.
2648    
2649    =over 4
2650    
2651    =item relationName
2652    
2653    Name of the relation to drop. If it does not exist, this method will have
2654    no effect.
2655    
2656  =back  =back
2657    
2658  =cut  =cut
2659    
2660  sub GenerateEntity {  sub DropRelation {
2661      # Get the parameters.      # Get the parameters.
2662      my ($self, $id, $type, $values) = @_;      my ($self, $relationName) = @_;
2663      # Create the return hash.      # Get the database handle.
2664      my $this = { id => $id };      my $dbh = $self->{_dbh};
2665      # Get the metadata structure.      # Drop the relation. The method used here has no effect if the relation
2666      my $metadata = $self->{_metaData};      # does not exist.
2667      # Get this entity's list of fields.      Trace("Invoking DB Kernel to drop $relationName.") if T(3);
2668      if (!exists $metadata->{Entities}->{$type}) {      $dbh->drop_table(tbl => $relationName);
2669          Confess("Unrecognized entity type $type in GenerateEntity.");  }
2670    
2671    =head3 MatchSqlPattern
2672    
2673    C<< my $matched = ERDB::MatchSqlPattern($value, $pattern); >>
2674    
2675    Determine whether or not a specified value matches an SQL pattern. An SQL
2676    pattern has two wild card characters: C<%> that matches multiple characters,
2677    and C<_> that matches a single character. These can be escaped using a
2678    backslash (C<\>). We pull this off by converting the SQL pattern to a
2679    PERL regular expression. As per SQL rules, the match is case-insensitive.
2680    
2681    =over 4
2682    
2683    =item value
2684    
2685    Value to be matched against the pattern. Note that an undefined or empty
2686    value will not match anything.
2687    
2688    =item pattern
2689    
2690    SQL pattern against which to match the value. An undefined or empty pattern will
2691    match everything.
2692    
2693    =item RETURN
2694    
2695    Returns TRUE if the value and pattern match, else FALSE.
2696    
2697    =back
2698    
2699    =cut
2700    
2701    sub MatchSqlPattern {
2702        # Get the parameters.
2703        my ($value, $pattern) = @_;
2704        # Declare the return variable.
2705        my $retVal;
2706        # Insure we have a pattern.
2707        if (! defined($pattern) || $pattern eq "") {
2708            $retVal = 1;
2709      } else {      } else {
2710          my $entity = $metadata->{Entities}->{$type};          # Break the pattern into pieces around the wildcard characters. Because we
2711          my $fields = $entity->{Fields};          # use parentheses in the split function's delimiter expression, we'll get
2712          # Generate data from the fields.          # list elements for the delimiters as well as the rest of the string.
2713          _GenerateFields($this, $fields, $type, $values);          my @pieces = split /([_%]|\\[_%])/, $pattern;
2714            # Check some fast special cases.
2715            if ($pattern eq '%') {
2716                # A null pattern matches everything.
2717                $retVal = 1;
2718            } elsif (@pieces == 1) {
2719                # No wildcards, so we have a literal comparison. Note we're case-insensitive.
2720                $retVal = (lc($value) eq lc($pattern));
2721            } elsif (@pieces == 2 && $pieces[1] eq '%') {
2722                # A wildcard at the end, so we have a substring match. This is also case-insensitive.
2723                $retVal = (lc(substr($value, 0, length($pieces[0]))) eq lc($pieces[0]));
2724            } else {
2725                # Okay, we have to do it the hard way. Convert each piece to a PERL pattern.
2726                my $realPattern = "";
2727                for my $piece (@pieces) {
2728                    # Determine the type of piece.
2729                    if ($piece eq "") {
2730                        # Empty pieces are ignored.
2731                    } elsif ($piece eq "%") {
2732                        # Here we have a multi-character wildcard. Note that it can match
2733                        # zero or more characters.
2734                        $realPattern .= ".*"
2735                    } elsif ($piece eq "_") {
2736                        # Here we have a single-character wildcard.
2737                        $realPattern .= ".";
2738                    } elsif ($piece eq "\\%" || $piece eq "\\_") {
2739                        # This is an escape sequence (which is a rare thing, actually).
2740                        $realPattern .= substr($piece, 1, 1);
2741                    } else {
2742                        # Here we have raw text.
2743                        $realPattern .= quotemeta($piece);
2744                    }
2745                }
2746                # Do the match.
2747                $retVal = ($value =~ /^$realPattern$/i ? 1 : 0);
2748      }      }
2749      # Return the hash created.      }
2750      return $this;      # Return the result.
2751        return $retVal;
2752  }  }
2753    
2754  =head3 GetEntity  =head3 GetEntity
# Line 2272  Line 2904 
2904  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
2905  feature ID followed by all of its aliases.  feature ID followed by all of its aliases.
2906    
2907  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)']); >>
2908    
2909  =over 4  =over 4
2910    
# Line 2450  Line 3082 
3082      return $objectData->{Fields};      return $objectData->{Fields};
3083  }  }
3084    
3085    =head3 SplitKeywords
3086    
3087    C<< my @keywords = ERDB::SplitKeywords($keywordString); >>
3088    
3089    This method returns a list of the positive keywords in the specified
3090    keyword string. All of the operators will have been stripped off,
3091    and if the keyword is preceded by a minus operator (C<->), it will
3092    not be in the list returned. The idea here is to get a list of the
3093    keywords the user wants to see. The list will be processed to remove
3094    duplicates.
3095    
3096    It is possible to create a string that confuses this method. For example
3097    
3098        frog toad -frog
3099    
3100    would return both C<frog> and C<toad>. If this is a problem we can deal
3101    with it later.
3102    
3103    =over 4
3104    
3105    =item keywordString
3106    
3107    The keyword string to be parsed.
3108    
3109    =item RETURN
3110    
3111    Returns a list of the words in the keyword string the user wants to
3112    see.
3113    
3114    =back
3115    
3116    =cut
3117    
3118    sub SplitKeywords {
3119        # Get the parameters.
3120        my ($keywordString) = @_;
3121        # Make a safety copy of the string. (This helps during debugging.)
3122        my $workString = $keywordString;
3123        # Convert operators we don't care about to spaces.
3124        $workString =~ tr/+"()<>/ /;
3125        # Split the rest of the string along space boundaries. Note that we
3126        # eliminate any words that are zero length or begin with a minus sign.
3127        my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
3128        # Use a hash to remove duplicates.
3129        my %words = map { $_ => 1 } @wordList;
3130        # Return the result.
3131        return sort keys %words;
3132    }
3133    
3134    =head3 ValidateFieldName
3135    
3136    C<< my $okFlag = ERDB::ValidateFieldName($fieldName); >>
3137    
3138    Return TRUE if the specified field name is valid, else FALSE. Valid field names must
3139    be hyphenated words subject to certain restrictions.
3140    
3141    =over 4
3142    
3143    =item fieldName
3144    
3145    Field name to be validated.
3146    
3147    =item RETURN
3148    
3149    Returns TRUE if the field name is valid, else FALSE.
3150    
3151    =back
3152    
3153    =cut
3154    
3155    sub ValidateFieldName {
3156        # Get the parameters.
3157        my ($fieldName) = @_;
3158        # Declare the return variable. The field name is valid until we hear
3159        # differently.
3160        my $retVal = 1;
3161        # Compute the maximum name length.
3162        my $maxLen = $TypeTable{'name-string'}->{maxLen};
3163        # Look for bad stuff in the name.
3164        if ($fieldName =~ /--/) {
3165            # Here we have a doubled minus sign.
3166            Trace("Field name $fieldName has a doubled hyphen.") if T(1);
3167            $retVal = 0;
3168        } elsif ($fieldName !~ /^[A-Za-z]/) {
3169            # Here the field name is missing the initial letter.
3170            Trace("Field name $fieldName does not begin with a letter.") if T(1);
3171            $retVal = 0;
3172        } elsif (length($fieldName) > $maxLen) {
3173            # Here the field name is too long.
3174            Trace("Maximum field name length is $maxLen. Field name must be truncated to " . substr($fieldName,0, $maxLen) . ".");
3175        } else {
3176            # Strip out the minus signs. Everything remaining must be a letter,
3177            # underscore, or digit.
3178            my $strippedName = $fieldName;
3179            $strippedName =~ s/-//g;
3180            if ($strippedName !~ /^(\w|\d)+$/) {
3181                Trace("Field name $fieldName contains illegal characters.") if T(1);
3182                $retVal = 0;
3183            }
3184        }
3185        # Return the result.
3186        return $retVal;
3187    }
3188    
3189    =head3 ReadMetaXML
3190    
3191    C<< my $rawMetaData = ERDB::ReadDBD($fileName); >>
3192    
3193    This method reads a raw database definition XML file and returns it.
3194    Normally, the metadata used by the ERDB system has been processed and
3195    modified to make it easier to load and retrieve the data; however,
3196    this method can be used to get the data in its raw form.
3197    
3198    =over 4
3199    
3200    =item fileName
3201    
3202    Name of the XML file to read.
3203    
3204    =item RETURN
3205    
3206    Returns a hash reference containing the raw XML data from the specified file.
3207    
3208    =back
3209    
3210    =cut
3211    
3212    sub ReadMetaXML {
3213        # Get the parameters.
3214        my ($fileName) = @_;
3215        # Read the XML.
3216        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
3217        Trace("XML metadata loaded from file $fileName.") if T(1);
3218        # Return the result.
3219        return $retVal;
3220    }
3221    
3222    =head3 GetEntityFieldHash
3223    
3224    C<< my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName); >>
3225    
3226    Get the field hash of the named entity in the specified raw XML structure.
3227    The field hash may not exist, in which case we need to create it.
3228    
3229    =over 4
3230    
3231    =item structure
3232    
3233    Raw XML structure defininng the database. This is not the run-time XML used by
3234    an ERDB object, since that has all sorts of optimizations built-in.
3235    
3236    =item entityName
3237    
3238    Name of the entity whose field structure is desired.
3239    
3240    =item RETURN
3241    
3242    Returns the field hash used to define the entity's fields.
3243    
3244    =back
3245    
3246    =cut
3247    
3248    sub GetEntityFieldHash {
3249        # Get the parameters.
3250        my ($structure, $entityName) = @_;
3251        # Get the entity structure.
3252        my $entityData = $structure->{Entities}->{$entityName};
3253        # Look for a field structure.
3254        my $retVal = $entityData->{Fields};
3255        # If it doesn't exist, create it.
3256        if (! defined($retVal)) {
3257            $entityData->{Fields} = {};
3258            $retVal = $entityData->{Fields};
3259        }
3260        # Return the result.
3261        return $retVal;
3262    }
3263    
3264    =head3 WriteMetaXML
3265    
3266    C<< ERDB::WriteMetaXML($structure, $fileName); >>
3267    
3268    Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
3269    used to update the database definition. It must be used with care, however, since it
3270    will only work on a raw structure, not on the processed structure created by an ERDB
3271    constructor.
3272    
3273    =over 4
3274    
3275    =item structure
3276    
3277    XML structure to be written to the file.
3278    
3279    =item fileName
3280    
3281    Name of the output file to which the updated XML should be stored.
3282    
3283    =back
3284    
3285    =cut
3286    
3287    sub WriteMetaXML {
3288        # Get the parameters.
3289        my ($structure, $fileName) = @_;
3290        # Compute the output.
3291        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
3292        # Write it to the file.
3293        my $xmlOut = Open(undef, ">$fileName");
3294        print $xmlOut $fileString;
3295    }
3296    
3297    
3298    =head3 HTMLNote
3299    
3300    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
3301    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
3302    Except for C<[p]>, all the codes are closed by slash-codes. So, for
3303    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
3304    
3305    C<< my $realHtml = ERDB::HTMLNote($dataString); >>
3306    
3307    =over 4
3308    
3309    =item dataString
3310    
3311    String to convert to HTML.
3312    
3313    =item RETURN
3314    
3315    An HTML string derived from the input string.
3316    
3317    =back
3318    
3319    =cut
3320    
3321    sub HTMLNote {
3322        # Get the parameter.
3323        my ($dataString) = @_;
3324        # HTML-escape the text.
3325        my $retVal = CGI::escapeHTML($dataString);
3326        # Substitute the bulletin board codes.
3327        $retVal =~ s!\[(/?[bi])\]!<$1>!g;
3328        $retVal =~ s!\[p\]!</p><p>!g;
3329        $retVal =~ s!\[link\s+([^\]]+)\]!<a href="$1">!g;
3330        $retVal =~ s!\[/link\]!</a>!g;
3331        # Return the result.
3332        return $retVal;
3333    }
3334    
3335    
3336  =head2 Data Mining Methods  =head2 Data Mining Methods
3337    
3338  =head3 GetUsefulCrossValues  =head3 GetUsefulCrossValues
# Line 2600  Line 3483 
3483      # Split it into a list.      # Split it into a list.
3484      my @retVal = split(/\t/, $line);      my @retVal = split(/\t/, $line);
3485      # Return the result.      # Return the result.
3486      return @retVal;      return @retVal;
3487    }
3488    
3489    =head2 Virtual Methods
3490    
3491    =head3 CleanKeywords
3492    
3493    C<< my $cleanedString = $erdb->CleanKeywords($searchExpression); >>
3494    
3495    Clean up a search expression or keyword list. This is a virtual method that may
3496    be overridden by the subclass. The base-class method removes extra spaces
3497    and converts everything to lower case.
3498    
3499    =over 4
3500    
3501    =item searchExpression
3502    
3503    Search expression or keyword list to clean. Note that a search expression may
3504    contain boolean operators which need to be preserved. This includes leading
3505    minus signs.
3506    
3507    =item RETURN
3508    
3509    Cleaned expression or keyword list.
3510    
3511    =back
3512    
3513    =cut
3514    
3515    sub CleanKeywords {
3516        # Get the parameters.
3517        my ($self, $searchExpression) = @_;
3518        # Lower-case the expression and copy it into the return variable. Note that we insure we
3519        # don't accidentally end up with an undefined value.
3520        my $retVal = lc($searchExpression || "");
3521        # Remove extra spaces.
3522        $retVal =~ s/\s+/ /g;
3523        $retVal =~ s/(^\s+)|(\s+$)//g;
3524        # Return the result.
3525        return $retVal;
3526  }  }
3527    
3528    =head3 GetSourceObject
3529    
3530    C<< my $source = $erdb->GetSourceObject($entityName); >>
3531    
3532    Return the object to be used in loading special attributes of the specified entity. The
3533    algorithm for loading special attributes is stored in the C<DataGen> elements of the
3534    XML
3535    
3536  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3537    
3538  =head3 _RelationMap  =head3 _RelationMap
# Line 2928  Line 3858 
3858      # Prepare the command.      # Prepare the command.
3859      my $sth = $dbh->prepare_command($command);      my $sth = $dbh->prepare_command($command);
3860      # Execute it with the parameters bound in.      # Execute it with the parameters bound in.
3861      $sth->execute(@{$params}) || Confess("SELECT error" . $sth->errstr());      $sth->execute(@{$params}) || Confess("SELECT error:  " . $sth->errstr());
3862      # Return the statement handle.      # Return the statement handle.
3863      return $sth;      return $sth;
3864  }  }
# Line 2945  Line 3875 
3875      return Stats->new();      return Stats->new();
3876  }  }
3877    
 =head3 _GenerateFields  
   
 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;  
             }  
         }  
     }  
 }  
   
3878  =head3 _DumpRelation  =head3 _DumpRelation
3879    
3880  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.
3881    
3882  This is an instance method.  This is an instance method.
3883    
# Line 3166  Line 4022 
4022          for my $object (values %{$metadata->{$section}}) {          for my $object (values %{$metadata->{$section}}) {
4023              # Loop through the object's fields.              # Loop through the object's fields.
4024              for my $fieldName (keys %{$object->{Fields}}) {              for my $fieldName (keys %{$object->{Fields}}) {
4025                  # Now we make some initial validations.                  # If this field name is invalid, set the return value to zero
4026                  if ($fieldName =~ /--/) {                  # so we know we encountered an error.
4027                      # Here we have a doubled minus sign.                  if (! ValidateFieldName($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";  
4028                          $retVal = 0;                          $retVal = 0;
4029                      }                      }
4030                  }                  }
4031              }              }
4032          }          }
     }  
4033      # If an error was found, fail.      # If an error was found, fail.
4034      if ($retVal  == 0) {      if ($retVal  == 0) {
4035          Confess("Errors found in field names.");          Confess("Errors found in field names.");
# Line 3254  Line 4096 
4096      return $retVal;      return $retVal;
4097  }  }
4098    
4099    
4100  =head3 _LoadMetaData  =head3 _LoadMetaData
4101    
4102  This method loads the data describing this database from an XML file into a metadata structure.  This method loads the data describing this database from an XML file into a metadata structure.
# Line 3279  Line 4122 
4122  sub _LoadMetaData {  sub _LoadMetaData {
4123      # Get the parameters.      # Get the parameters.
4124      my ($filename) = @_;      my ($filename) = @_;
4125      Trace("Reading Sprout DBD from $filename.") if T(2);      Trace("Reading DBD from $filename.") if T(2);
4126      # 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
4127      # get the exact structure we want.      # get the exact structure we want.
4128      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 $filename.") if T(1);  
4129      # Before we go any farther, we need to validate the field and object names. If an error is found,      # Before we go any farther, we need to validate the field and object names. If an error is found,
4130      # the method below will fail.      # the method below will fail.
4131      _ValidateFieldNames($metadata);      _ValidateFieldNames($metadata);
# Line 3425  Line 4255 
4255              my $count = 0;              my $count = 0;
4256              for my $index (@{$indexList}) {              for my $index (@{$indexList}) {
4257                  # Add this index to the index table.                  # Add this index to the index table.
4258                  _AddIndex("idx$relationName$count", $relation, $index);                  _AddIndex("idx$count", $relation, $index);
4259                  # Increment the counter so that the next index has a different name.                  # Increment the counter so that the next index has a different name.
4260                  $count++;                  $count++;
4261              }              }
# Line 3442  Line 4272 
4272          _FixupFields($relationshipStructure, $relationshipName, 2, 3);          _FixupFields($relationshipStructure, $relationshipName, 2, 3);
4273          # Format a description for the FROM field.          # Format a description for the FROM field.
4274          my $fromEntity = $relationshipStructure->{from};          my $fromEntity = $relationshipStructure->{from};
4275          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].";
4276          # Get the FROM entity's key type.          # Get the FROM entity's key type.
4277          my $fromType = $entityList->{$fromEntity}->{keyType};          my $fromType = $entityList->{$fromEntity}->{keyType};
4278          # Add the FROM field.          # Add the FROM field.
# Line 3452  Line 4282 
4282                                                      PrettySort => 1});                                                      PrettySort => 1});
4283          # Format a description for the TO field.          # Format a description for the TO field.
4284          my $toEntity = $relationshipStructure->{to};          my $toEntity = $relationshipStructure->{to};
4285          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].";
4286          # Get the TO entity's key type.          # Get the TO entity's key type.
4287          my $toType = $entityList->{$toEntity}->{keyType};          my $toType = $entityList->{$toEntity}->{keyType};
4288          # Add the TO field.          # Add the TO field.
# Line 3623  Line 4453 
4453          $newIndex->{Unique} = 'true';          $newIndex->{Unique} = 'true';
4454      }      }
4455      # Add the index to the relation.      # Add the index to the relation.
4456      _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);      _AddIndex("idx$indexKey", $relationStructure, $newIndex);
4457  }  }
4458    
4459  =head3 _AddIndex  =head3 _AddIndex
# Line 3722  Line 4552 
4552              my $type = $fieldData->{type};              my $type = $fieldData->{type};
4553              # Plug in a relation name if it is needed.              # Plug in a relation name if it is needed.
4554              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });
             # Plug in a data generator if we need one.  
             if (!exists $fieldData->{DataGen}) {  
                 # The data generator will use the default for the field's type.  
                 $fieldData->{DataGen} = { content => $TypeTable{$type}->{dataGen} };  
             }  
4555              # Check for searchability.              # Check for searchability.
4556              if ($fieldData->{searchable}) {              if ($fieldData->{searchable}) {
4557                  # Only allow this for a primary relation.                  # Only allow this for a primary relation.
# Line 3736  Line 4561 
4561                      push @textFields, $fieldName;                      push @textFields, $fieldName;
4562                  }                  }
4563              }              }
             # Plug in the defaults for the optional data generation parameters.  
             Tracer::MergeOptions($fieldData->{DataGen}, { testCount => 1, pass => 0 });  
4564              # Add the PrettySortValue.              # Add the PrettySortValue.
4565              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);
4566          }          }
# Line 4096  Line 4919 
4919          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";
4920          # Add any note text.          # Add any note text.
4921          if (my $note = $indexData->{Notes}) {          if (my $note = $indexData->{Notes}) {
4922              $htmlString .= "<li>" . _HTMLNote($note->{content}) . "</li>\n";              $htmlString .= "<li>" . HTMLNote($note->{content}) . "</li>\n";
4923          }          }
4924          # Add the fiield list.          # Add the fiield list.
4925          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";
# Line 4162  Line 4985 
4985      # Compute the number of columns.      # Compute the number of columns.
4986      my $colCount = @colNames;      my $colCount = @colNames;
4987      # Generate the title row.      # Generate the title row.
4988      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";
4989      # Loop through the columns, adding the column header rows.      # Loop through the columns, adding the column header rows.
4990      $htmlString .= "<tr>";      $htmlString .= "<tr>";
4991      for my $colName (@colNames) {      for my $colName (@colNames) {
# Line 4181  Line 5004 
5004  =cut  =cut
5005    
5006  sub _CloseTable {  sub _CloseTable {
5007      return "</table></p>\n";      return "</table>\n";
5008  }  }
5009    
5010  =head3 _ShowField  =head3 _ShowField
# Line 4211  Line 5034 
5034      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>";
5035      # If we have content, add it as a third column.      # If we have content, add it as a third column.
5036      if (exists $fieldData->{Notes}) {      if (exists $fieldData->{Notes}) {
5037          $htmlString .= "<td>" . _HTMLNote($fieldData->{Notes}->{content}) . "</td>";          $htmlString .= "<td>" . HTMLNote($fieldData->{Notes}->{content}) . "</td>";
5038      }      }
5039      # Close off the row.      # Close off the row.
5040      $htmlString .= "</tr>\n";      $htmlString .= "</tr>\n";
# Line 4219  Line 5042 
5042      return $htmlString;      return $htmlString;
5043  }  }
5044    
 =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;  
 }  
   
5045  1;  1;

Legend:
Removed from v.1.70  
changed lines
  Added in v.1.83

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3