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

Diff of /Sprout/ERDB.pm

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

revision 1.69, Fri Sep 29 15:06:17 2006 UTC revision 1.75, Thu Nov 9 21:21:49 2006 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 190  Line 191 
191    
192  Name of the field. The field name should contain only letters, digits, and hyphens (C<->),  Name of the field. The field name should contain only letters, digits, and hyphens (C<->),
193  and the first character should be a letter. Most underlying databases are case-insensitive  and the first character should be a letter. Most underlying databases are case-insensitive
194  with the respect to field names, so a best practice is to use lower-case letters only.  with the respect to field names, so a best practice is to use lower-case letters only. Finally,
195    the name C<search-relevance> has special meaning for full-text searches and should not be
196    used as a field name.
197    
198  =item type  =item type
199    
# Line 209  Line 212 
212  entity, the fields without a relation attribute are said to belong to the  entity, the fields without a relation attribute are said to belong to the
213  I<primary relation>. This relation has the same name as the entity itself.  I<primary relation>. This relation has the same name as the entity itself.
214    
215    =item searchable
216    
217    If specified, then the field is a candidate for full-text searching. A single full-text
218    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.
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 320  Line 335 
335    
336  # 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.
337  # "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
338  # 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
339  # 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,
340  # 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
341  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",  dataGen => "StringGen('A')" },  # index
342                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n", dataGen => "IntGen(0, 99999999)" },  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",
343                    counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n", dataGen => "IntGen(0, 99999999)" },                                 indexMod =>   0, notes => "single ASCII character"},
344                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, sort => "",  dataGen => "StringGen(IntGen(10,250))" },                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n",
345                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, sort => "",  dataGen => "StringGen(IntGen(80,1000))" },                                 indexMod =>   0, notes => "signed 32-bit integer"},
346                    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",
347                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, sort => "g", dataGen => "FloatGen(0.0, 100.0)" },                                 indexMod =>   0, notes => "unsigned 32-bit integer"},
348                    boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, sort => "n", dataGen => "IntGen(0, 1)" },                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, sort => "",
349                                   indexMod =>   0, notes => "character string, 0 to 255 characters"},
350                      text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, sort => "",
351                                   indexMod => 255, notes => "character string, nearly unlimited length, only first 255 characters are indexed"},
352                      date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, sort => "n",
353                                   indexMod =>   0, notes => "signed, 64-bit integer"},
354                      float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, sort => "g",
355                                   indexMod =>   0, notes => "64-bit double precision floating-point number"},
356                      boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, sort => "n",
357                                   indexMod =>   0, notes => "boolean value: 0 if false, 1 if true"},
358                   'hash-string' =>                   'hash-string' =>
359                               { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, sort => "",  dataGen => "SringGen(22)" },                               { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, sort => "",
360                                   indexMod =>   0, notes => "string stored in digested form, used for certain types of key fields"},
361                   'id-string' =>                   'id-string' =>
362                               { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, sort => "",  dataGen => "SringGen(22)" },                               { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, sort => "",
363                                   indexMod =>   0, notes => "character string, 0 to 25 characters"},
364                   'key-string' =>                   'key-string' =>
365                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, sort => "",  dataGen => "StringGen(IntGen(10,40))" },                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, sort => "",
366                                   indexMod =>   0, notes => "character string, 0 to 40 characters"},
367                   'name-string' =>                   'name-string' =>
368                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, sort => "",  dataGen => "StringGen(IntGen(10,80))" },                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, sort => "",
369                                   indexMod =>   0, notes => "character string, 0 to 80 characters"},
370                   'medium-string' =>                   'medium-string' =>
371                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",  dataGen => "StringGen(IntGen(10,160))" },                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",
372                                   indexMod =>   0, notes => "character string, 0 to 160 characters"},
373                  );                  );
374    
375  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 349  Line 378 
378                     'MM' => 'many-to-many'                     'MM' => 'many-to-many'
379                   );                   );
380    
381  # Table for interpreting string patterns.  # Options for XML input and output.
382    
383    my %XmlOptions = (GroupTags =>  { Relationships => 'Relationship',
384                                      Entities => 'Entity',
385                                      Fields => 'Field',
386                                      Indexes => 'Index',
387                                      IndexFields => 'IndexField'
388                                    },
389                      KeyAttr =>    { Relationship => 'name',
390                                      Entity => 'name',
391                                      Field => 'name'
392                                    },
393                      SuppressEmpty => 1,
394                     );
395    
396  my %PictureTable = ( 'A' => "abcdefghijklmnopqrstuvwxyz",  my %XmlInOpts  = (
397                       '9' => "0123456789",                    ForceArray => ['Field', 'Index', 'IndexField'],
398                       'X' => "abcdefghijklmnopqrstuvwxyz0123456789",                    ForceContent => 1,
399                       'V' => "aeiou",                    NormalizeSpace => 2,
                      'K' => "bcdfghjklmnoprstvwxyz"  
400                     );                     );
401    my %XmlOutOpts = (
402                      RootName => 'Database',
403                      XMLDecl => 1,
404                     );
405    
406    
407  =head2 Public Methods  =head2 Public Methods
408    
# Line 498  Line 544 
544          my $entityData = $entityList->{$key};          my $entityData = $entityList->{$key};
545          # If there's descriptive text, display it.          # If there's descriptive text, display it.
546          if (my $notes = $entityData->{Notes}) {          if (my $notes = $entityData->{Notes}) {
547              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
548          }          }
549          # Now we want a list of the entity's relationships. First, we set up the relationship subsection.          # Now we want a list of the entity's relationships. First, we set up the relationship subsection.
550          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
# Line 555  Line 601 
601          $retVal .= "</p>\n";          $retVal .= "</p>\n";
602          # If there are notes on this relationship, display them.          # If there are notes on this relationship, display them.
603          if (my $notes = $relationshipStructure->{Notes}) {          if (my $notes = $relationshipStructure->{Notes}) {
604              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
605          }          }
606          # Generate the relationship's relation table.          # Generate the relationship's relation table.
607          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
# Line 602  Line 648 
648      return Data::Dumper::Dumper($self->{_metaData});      return Data::Dumper::Dumper($self->{_metaData});
649  }  }
650    
651    =head3 FindIndexForEntity
652    
653    C<< my $indexFound = ERDB::FindIndexForEntity($xml, $entityName, $attributeName); >>
654    
655    This method locates the entry in an entity's index list that begins with the
656    specified attribute name. If the entity has no index list, one will be
657    created. This method works on raw XML, not a live ERDB object.
658    
659    =over 4
660    
661    =item xml
662    
663    The raw XML structure defining the database.
664    
665    =item entityName
666    
667    The name of the relevant entity.
668    
669    =item attributeName
670    
671    The name of the attribute relevant to the search.
672    
673    =item RETURN
674    
675    The numerical index in the index list of the index entry for the specified entity and
676    attribute, or C<undef> if no such index exists.
677    
678    =back
679    
680    =cut
681    
682    sub FindIndexForEntity {
683        # Get the parameters.
684        my ($xml, $entityName, $attributeName) = @_;
685        # Declare the return variable.
686        my $retVal;
687        # Get the named entity.
688        my $entityData = $xml->{Entities}->{$entityName};
689        if (! $entityData) {
690            Confess("Entity $entityName not found in DBD structure.");
691        } else {
692            # Insure it has an index list.
693            if (! exists $entityData->{Indexes}) {
694                $entityData->{Indexes} = [];
695            } else {
696                # Search for the desired index.
697                my $indexList = $entityData->{Indexes};
698                my $n = scalar @{$indexList};
699                Trace("Searching $n indexes in index list for $entityName.") if T(2);
700                # We use an indexed FOR here because we're returning an
701                # index number instead of an object. We do THAT so we can
702                # delete the index from the list if needed.
703                for (my $i = 0; $i < $n && !defined($retVal); $i++) {
704                    my $index = $indexList->[$i];
705                    my $fields = $index->{IndexFields};
706                    # Technically this IF should be safe (that is, we are guaranteed
707                    # the existence of a "$fields->[0]"), because when we load the XML
708                    # we have SuppressEmpty specified.
709                    if ($fields->[0]->{name} eq $attributeName) {
710                        $retVal = $i;
711                    }
712                }
713            }
714        }
715        Trace("Index for $attributeName of $entityName found at position $retVal.") if defined($retVal) && T(3);
716        Trace("Index for $attributeName not found in $entityName.") if !defined($retVal) && T(3);
717        # Return the result.
718        return $retVal;
719    }
720    
721  =head3 CreateTables  =head3 CreateTables
722    
723  C<< $erdb->CreateTables(); >>  C<< $erdb->CreateTables(); >>
# Line 689  Line 805 
805      Trace("Creating table $relationName: $fieldThing") if T(2);      Trace("Creating table $relationName: $fieldThing") if T(2);
806      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);
807      Trace("Relation $relationName created in database.") if T(2);      Trace("Relation $relationName created in database.") if T(2);
808      # If we want to build the indexes, we do it here.      # If we want to build the indexes, we do it here. Note that the full-text search
809        # index will not be built until the table has been loaded.
810      if ($indexFlag) {      if ($indexFlag) {
811          $self->CreateIndex($relationName);          $self->CreateIndex($relationName);
812      }      }
# Line 846  Line 963 
963      for my $indexName (keys %{$indexHash}) {      for my $indexName (keys %{$indexHash}) {
964          my $indexData = $indexHash->{$indexName};          my $indexData = $indexHash->{$indexName};
965          # Get the index's field list.          # Get the index's field list.
966          my @fieldList = _FixNames(@{$indexData->{IndexFields}});          my @rawFields = @{$indexData->{IndexFields}};
967            # Get a hash of the relation's field types.
968            my %types = map { $_->{name} => $_->{type} } @{$relationData->{Fields}};
969            # We need to check for text fields. We need a append a length limitation for them. To do
970            # that, we need the relation's field list.
971            my $relFields = $relationData->{Fields};
972            for (my $i = 0; $i <= $#rawFields; $i++) {
973                # Get the field type.
974                my $field = $rawFields[$i];
975                my $type = $types{$field};
976                # Ask if it requires using prefix notation for the index.
977                my $mod = $TypeTable{$type}->{indexMod};
978                Trace("Field $field ($i) in $relationName has type $type and indexMod $mod.") if T(3);
979                if ($mod) {
980                    # Append the prefix length to the field name,
981                    $rawFields[$i] .= "($mod)";
982                }
983            }
984            my @fieldList = _FixNames(@rawFields);
985          my $flds = join(', ', @fieldList);          my $flds = join(', ', @fieldList);
986          # Get the index's uniqueness flag.          # Get the index's uniqueness flag.
987          my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
988          # Create the index.          # Create the index.
989          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
990                                      flds => $flds, unique => $unique);                                      flds => $flds, kind => $unique);
991          if ($rv) {          if ($rv) {
992              Trace("Index created: $indexName for $relationName ($flds)") if T(1);              Trace("Index created: $indexName for $relationName ($flds)") if T(1);
993          } else {          } else {
# Line 861  Line 996 
996      }      }
997  }  }
998    
999    =head3 GetSecondaryFields
1000    
1001    C<< my %fieldTuples = $erdb->GetSecondaryFields($entityName); >>
1002    
1003    This method will return a list of the name and type of each of the secondary
1004    fields for a specified entity. Secondary fields are stored in two-column tables
1005    in addition to the primary entity table. This enables the field to have no value
1006    or to have multiple values.
1007    
1008    =over 4
1009    
1010    =item entityName
1011    
1012    Name of the entity whose secondary fields are desired.
1013    
1014    =item RETURN
1015    
1016    Returns a hash mapping the field names to their field types.
1017    
1018    =back
1019    
1020    =cut
1021    
1022    sub GetSecondaryFields {
1023        # Get the parameters.
1024        my ($self, $entityName) = @_;
1025        # Declare the return variable.
1026        my %retVal = ();
1027        # Look for the entity.
1028        my $table = $self->GetFieldTable($entityName);
1029        # Loop through the fields, pulling out the secondaries.
1030        for my $field (sort keys %{$table}) {
1031            if ($table->{$field}->{relation} ne $entityName) {
1032                # Here we have a secondary field.
1033                $retVal{$field} = $table->{$field}->{type};
1034            }
1035        }
1036        # Return the result.
1037        return %retVal;
1038    }
1039    
1040    =head3 GetFieldRelationName
1041    
1042    C<< my $name = $erdb->GetFieldRelationName($objectName, $fieldName); >>
1043    
1044    Return the name of the relation containing a specified field.
1045    
1046    =over 4
1047    
1048    =item objectName
1049    
1050    Name of the entity or relationship containing the field.
1051    
1052    =item fieldName
1053    
1054    Name of the relevant field in that entity or relationship.
1055    
1056    =item RETURN
1057    
1058    Returns the name of the database relation containing the field, or C<undef> if
1059    the field does not exist.
1060    
1061    =back
1062    
1063    =cut
1064    
1065    sub GetFieldRelationName {
1066        # Get the parameters.
1067        my ($self, $objectName, $fieldName) = @_;
1068        # Declare the return variable.
1069        my $retVal;
1070        # Get the object field table.
1071        my $table = $self->GetFieldTable($objectName);
1072        # Only proceed if the field exists.
1073        if (exists $table->{$fieldName}) {
1074            # Determine the name of the relation that contains this field.
1075            $retVal = $table->{$fieldName}->{relation};
1076        }
1077        # Return the result.
1078        return $retVal;
1079    }
1080    
1081    =head3 DeleteValue
1082    
1083    C<< my $numDeleted = $erdb->DeleteValue($entityName, $id, $fieldName, $fieldValue); >>
1084    
1085    Delete secondary field values from the database. This method can be used to delete all
1086    values of a specified field for a particular entity instance, or only a single value.
1087    
1088    Secondary fields are stored in two-column relations separate from an entity's primary
1089    table, and as a result a secondary field can legitimately have no value or multiple
1090    values. Therefore, it makes sense to talk about deleting secondary fields where it
1091    would not make sense for primary fields.
1092    
1093    =over 4
1094    
1095    =item entityName
1096    
1097    Name of the entity from which the fields are to be deleted.
1098    
1099    =item id
1100    
1101    ID of the entity instance to be processed. If the instance is not found, this
1102    method will have no effect.
1103    
1104    =item fieldName
1105    
1106    Name of the field whose values are to be deleted.
1107    
1108    =item fieldValue (optional)
1109    
1110    Value to be deleted. If not specified, then all values of the specified field
1111    will be deleted for the entity instance. If specified, then only the values which
1112    match this parameter will be deleted.
1113    
1114    =item RETURN
1115    
1116    Returns the number of rows deleted.
1117    
1118    =back
1119    
1120    =cut
1121    
1122    sub DeleteValue {
1123        # Get the parameters.
1124        my ($self, $entityName, $id, $fieldName, $fieldValue) = @_;
1125        # Declare the return value.
1126        my $retVal = 0;
1127        # We need to set up an SQL command to do the deletion. First, we
1128        # find the name of the field's relation.
1129        my $table = $self->GetFieldTable($entityName);
1130        my $field = $table->{$fieldName};
1131        my $relation = $field->{relation};
1132        # Make sure this is a secondary field.
1133        if ($relation eq $entityName) {
1134            Confess("Cannot delete values of $fieldName for $entityName.");
1135        } else {
1136            # Set up the SQL command to delete all values.
1137            my $sql = "DELETE FROM $relation WHERE id = ?";
1138            my @parms = $id;
1139            # If a value has been specified, append it to the statement.
1140            if (defined $fieldValue) {
1141                $sql .= " AND $fieldName = ?";
1142                push @parms, $fieldValue;
1143            }
1144            # Execute the command.
1145            my $dbh = $self->{_dbh};
1146            $retVal = $dbh->SQL($sql, 0, @parms);
1147        }
1148        # Return the result.
1149        return $retVal;
1150    }
1151    
1152  =head3 LoadTables  =head3 LoadTables
1153    
1154  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>
# Line 955  Line 1243 
1243      return sort keys %{$entityList};      return sort keys %{$entityList};
1244  }  }
1245    
1246    =head3 GetDataTypes
1247    
1248    C<< my %types = ERDB::GetDataTypes(); >>
1249    
1250    Return a table of ERDB data types. The table returned is a hash of hashes.
1251    The keys of the big hash are the datatypes. Each smaller hash has several
1252    values used to manage the data. The most interesting is the SQL type (key
1253    C<sqlType>) and the descriptive node (key C<notes>).
1254    
1255    Note that changing the values in the smaller hashes will seriously break
1256    things, so this data should be treated as read-only.
1257    
1258    =cut
1259    
1260    sub GetDataTypes {
1261        return %TypeTable;
1262    }
1263    
1264    
1265  =head3 IsEntity  =head3 IsEntity
1266    
1267  C<< my $flag = $erdb->IsEntity($entityName); >>  C<< my $flag = $erdb->IsEntity($entityName); >>
# Line 1099  Line 1406 
1406      return $retVal;      return $retVal;
1407  }  }
1408    
1409    =head3 Search
1410    
1411    C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>
1412    
1413    Perform a full text search with filtering. The search will be against a specified object
1414    in the object name list. That object will get an extra field containing the search
1415    relevance. Note that except for the search expression, the parameters of this method are
1416    the same as those for L</Get> and follow the same rules.
1417    
1418    =over 4
1419    
1420    =item searchExpression
1421    
1422    Boolean search expression for the text fields of the target object. The default mode for
1423    a Boolean search expression is OR, but we want the default to be AND, so we will
1424    add a C<+> operator to each word with no other operator before it.
1425    
1426    =item idx
1427    
1428    Index in the I<$objectNames> list of the table to be searched in full-text mode.
1429    
1430    =item objectNames
1431    
1432    List containing the names of the entity and relationship objects to be retrieved.
1433    
1434    =item filterClause
1435    
1436    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1437    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
1438    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
1439    in the filter clause should be added to the parameter list as additional parameters. The
1440    fields in a filter clause can come from primary entity relations, relationship relations,
1441    or secondary entity relations; however, all of the entities and relationships involved must
1442    be included in the list of object names.
1443    
1444    =item params
1445    
1446    Reference to a list of parameter values to be substituted into the filter clause.
1447    
1448    =item RETURN
1449    
1450    Returns a query object for the specified search.
1451    
1452    =back
1453    
1454    =cut
1455    
1456    sub Search {
1457        # Get the parameters.
1458        my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1459        # Declare the return variable.
1460        my $retVal;
1461        # Create a safety copy of the parameter list. Note we have to be careful to insure
1462        # a parameter list exists before we copy it.
1463        my @myParams = ();
1464        if (defined $params) {
1465            @myParams = @{$params};
1466        }
1467        # Get the first object's structure so we have access to the searchable fields.
1468        my $object1Name = $objectNames->[$idx];
1469        my $object1Structure = $self->_GetStructure($object1Name);
1470        # Get the field list.
1471        if (! exists $object1Structure->{searchFields}) {
1472            Confess("No searchable index for $object1Name.");
1473        } else {
1474            # Get the field list.
1475            my @fields = @{$object1Structure->{searchFields}};
1476            # Clean the search expression.
1477            my $actualKeywords = $self->CleanKeywords($searchExpression);
1478            # Prefix a "+" to each uncontrolled word. This converts the default
1479            # search mode from OR to AND.
1480            $actualKeywords =~ s/(^|\s)(\w)/$1\+$2/g;
1481            Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1482            # We need two match expressions, one for the filter clause and one in the
1483            # query itself. Both will use a parameter mark, so we need to push the
1484            # search expression onto the front of the parameter list twice.
1485            unshift @myParams, $actualKeywords, $actualKeywords;
1486            # Build the match expression.
1487            my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
1488            my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
1489            # Process the SQL stuff.
1490            my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1491                $self->_SetupSQL($objectNames, $filterClause, $matchClause);
1492            # Create the query. Note that the match clause is inserted at the front of
1493            # the select fields.
1494            my $command = "SELECT DISTINCT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .
1495                ".* $suffix";
1496            my $sth = $self->_GetStatementHandle($command, \@myParams);
1497            # Now we create the relation map, which enables DBQuery to determine the order, name
1498            # and mapped name for each object in the query.
1499            my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
1500            # Return the statement object.
1501            $retVal = DBQuery::_new($self, $sth, \@relationMap, $object1Name);
1502        }
1503        return $retVal;
1504    }
1505    
1506  =head3 GetFlat  =head3 GetFlat
1507    
1508  C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>  C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>
# Line 1152  Line 1556 
1556      return @retVal;      return @retVal;
1557  }  }
1558    
1559    =head3 SpecialFields
1560    
1561    C<< my %specials = $erdb->SpecialFields($entityName); >>
1562    
1563    Return a hash mapping special fields in the specified entity to the value of their
1564    C<special> attribute. This enables the subclass to get access to the special field
1565    attributes without needed to plumb the internal ERDB data structures.
1566    
1567    =over 4
1568    
1569    =item entityName
1570    
1571    Name of the entity whose special fields are desired.
1572    
1573    =item RETURN
1574    
1575    Returns a hash. The keys of the hash are the special field names, and the values
1576    are the values from each special field's C<special> attribute.
1577    
1578    =back
1579    
1580    =cut
1581    
1582    sub SpecialFields {
1583        # Get the parameters.
1584        my ($self, $entityName) = @_;
1585        # Declare the return variable.
1586        my %retVal = ();
1587        # Find the entity's data structure.
1588        my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1589        # Loop through its fields, adding each special field to the return hash.
1590        my $fieldHash = $entityData->{Fields};
1591        for my $fieldName (keys %{$fieldHash}) {
1592            my $fieldData = $fieldHash->{$fieldName};
1593            if (exists $fieldData->{special}) {
1594                $retVal{$fieldName} = $fieldData->{special};
1595            }
1596        }
1597        # Return the result.
1598        return %retVal;
1599    }
1600    
1601  =head3 Delete  =head3 Delete
1602    
1603  C<< my $stats = $erdb->Delete($entityName, $objectID); >>  C<< my $stats = $erdb->Delete($entityName, $objectID); >>
# Line 1208  Line 1654 
1654      # This final hash is used to remember what work still needs to be done. We push paths      # This final hash is used to remember what work still needs to be done. We push paths
1655      # onto the list, then pop them off to extend the paths. We prime it with the starting      # onto the list, then pop them off to extend the paths. We prime it with the starting
1656      # point. Note that we will work hard to insure that the last item on a path in the      # point. Note that we will work hard to insure that the last item on a path in the
1657      # TODO list is always an entity.      # to-do list is always an entity.
1658      my @todoList = ([$entityName]);      my @todoList = ([$entityName]);
1659      while (@todoList) {      while (@todoList) {
1660          # Get the current path.          # Get the current path.
# Line 1320  Line 1766 
1766      return $retVal;      return $retVal;
1767  }  }
1768    
1769  =head3 GetList  =head3 SortNeeded
1770    
1771  C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>  C<< my $parms = $erdb->SortNeeded($relationName); >>
1772    
1773  Return a list of object descriptors for the specified objects as determined by the  Return the pipe command for the sort that should be applied to the specified
1774  specified filter clause.  relation when creating the load file.
1775    
1776  This method is essentially the same as L</Get> except it returns a list of objects rather  For example, if the load file should be sorted ascending by the first
1777  than a query object that can be used to get the results one record at a time.  field, this method would return
1778    
1779  =over 4      sort -k1 -t"\t"
1780    
1781  =item objectNames  If the first field is numeric, the method would return
1782    
1783  List containing the names of the entity and relationship objects to be retrieved.      sort -k1n -t"\t"
1784    
1785  =item filterClause  Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate
1786    keys using a sort.
1787    
1788  WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  =over 4
 be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be  
 specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified  
 in the filter clause should be added to the parameter list as additional parameters. The  
 fields in a filter clause can come from primary entity relations, relationship relations,  
 or secondary entity relations; however, all of the entities and relationships involved must  
 be included in the list of object names.  
1789    
1790  The filter clause can also specify a sort order. To do this, simply follow the filter string  =item relationName
 with an ORDER BY clause. For example, the following filter string gets all genomes for a  
 particular genus and sorts them by species name.  
1791    
1792  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>  Name of the relation to be examined.
1793    
1794  The rules for field references in a sort order are the same as those for field references in the  =item
1795  filter clause in general; however, odd things may happen if a sort field is from a secondary  
1796    Returns the sort command to use for sorting the relation, suitable for piping.
1797    
1798    =back
1799    
1800    =cut
1801    #: Return Type $;
1802    sub SortNeeded {
1803        # Get the parameters.
1804        my ($self, $relationName) = @_;
1805        # Declare a descriptor to hold the names of the key fields.
1806        my @keyNames = ();
1807        # Get the relation structure.
1808        my $relationData = $self->_FindRelation($relationName);
1809        # Find out if the relation is a primary entity relation,
1810        # a relationship relation, or a secondary entity relation.
1811        my $entityTable = $self->{_metaData}->{Entities};
1812        my $relationshipTable = $self->{_metaData}->{Relationships};
1813        if (exists $entityTable->{$relationName}) {
1814            # Here we have a primary entity relation.
1815            push @keyNames, "id";
1816        } elsif (exists $relationshipTable->{$relationName}) {
1817            # Here we have a relationship. We sort using the FROM index.
1818            my $relationshipData = $relationshipTable->{$relationName};
1819            my $index = $relationData->{Indexes}->{idxFrom};
1820            push @keyNames, @{$index->{IndexFields}};
1821        } else {
1822            # Here we have a secondary entity relation, so we have a sort on the ID field.
1823            push @keyNames, "id";
1824        }
1825        # Now we parse the key names into sort parameters. First, we prime the return
1826        # string.
1827        my $retVal = "sort -t\"\t\" ";
1828        # Get the relation's field list.
1829        my @fields = @{$relationData->{Fields}};
1830        # Loop through the keys.
1831        for my $keyData (@keyNames) {
1832            # Get the key and the ordering.
1833            my ($keyName, $ordering);
1834            if ($keyData =~ /^([^ ]+) DESC/) {
1835                ($keyName, $ordering) = ($1, "descending");
1836            } else {
1837                ($keyName, $ordering) = ($keyData, "ascending");
1838            }
1839            # Find the key's position and type.
1840            my $fieldSpec;
1841            for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {
1842                my $thisField = $fields[$i];
1843                if ($thisField->{name} eq $keyName) {
1844                    # Get the sort modifier for this field type. The modifier
1845                    # decides whether we're using a character, numeric, or
1846                    # floating-point sort.
1847                    my $modifier = $TypeTable{$thisField->{type}}->{sort};
1848                    # If the index is descending for this field, denote we want
1849                    # to reverse the sort order on this field.
1850                    if ($ordering eq 'descending') {
1851                        $modifier .= "r";
1852                    }
1853                    # Store the position and modifier into the field spec, which
1854                    # will stop the inner loop. Note that the field number is
1855                    # 1-based in the sort command, so we have to increment the
1856                    # index.
1857                    $fieldSpec = ($i + 1) . $modifier;
1858                }
1859            }
1860            # Add this field to the sort command.
1861            $retVal .= " -k$fieldSpec";
1862        }
1863        # Return the result.
1864        return $retVal;
1865    }
1866    
1867    =head3 GetList
1868    
1869    C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>
1870    
1871    Return a list of object descriptors for the specified objects as determined by the
1872    specified filter clause.
1873    
1874    This method is essentially the same as L</Get> except it returns a list of objects rather
1875    than a query object that can be used to get the results one record at a time.
1876    
1877    =over 4
1878    
1879    =item objectNames
1880    
1881    List containing the names of the entity and relationship objects to be retrieved.
1882    
1883    =item filterClause
1884    
1885    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1886    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
1887    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
1888    in the filter clause should be added to the parameter list as additional parameters. The
1889    fields in a filter clause can come from primary entity relations, relationship relations,
1890    or secondary entity relations; however, all of the entities and relationships involved must
1891    be included in the list of object names.
1892    
1893    The filter clause can also specify a sort order. To do this, simply follow the filter string
1894    with an ORDER BY clause. For example, the following filter string gets all genomes for a
1895    particular genus and sorts them by species name.
1896    
1897    C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
1898    
1899    The rules for field references in a sort order are the same as those for field references in the
1900    filter clause in general; however, odd things may happen if a sort field is from a secondary
1901  relation.  relation.
1902    
1903  =item params  =item params
# Line 1824  Line 2368 
2368      };      };
2369      if (!defined $rv) {      if (!defined $rv) {
2370          $retVal->AddMessage($@) if ($@);          $retVal->AddMessage($@) if ($@);
2371          $retVal->AddMessage("Table load failed for $relationName using $fileName.");          $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2372          Trace("Table load failed for $relationName.") if T(1);          Trace("Table load failed for $relationName.") if T(1);
2373      } else {      } else {
2374          # Here we successfully loaded the table.          # Here we successfully loaded the table.
# Line 1832  Line 2376 
2376          my $size = -s $fileName;          my $size = -s $fileName;
2377          Trace("$size bytes loaded into $relationName.") if T(2);          Trace("$size bytes loaded into $relationName.") if T(2);
2378          # If we're rebuilding, we need to create the table indexes.          # If we're rebuilding, we need to create the table indexes.
2379          if ($truncateFlag && ! $dbh->{_preIndex}) {          if ($truncateFlag) {
2380                # Indexes are created here for PostGres. For PostGres, indexes are
2381                # best built at the end. For MySQL, the reverse is true.
2382                if (! $dbh->{_preIndex}) {
2383              eval {              eval {
2384                  $self->CreateIndex($relationName);                  $self->CreateIndex($relationName);
2385              };              };
# Line 1840  Line 2387 
2387                  $retVal->AddMessage($@);                  $retVal->AddMessage($@);
2388              }              }
2389          }          }
2390                # The full-text index (if any) is always built last, even for MySQL.
2391                # First we need to see if this table has a full-text index. Only
2392                # primary relations are allowed that privilege.
2393                if ($self->_IsPrimary($relationName)) {
2394                    # Get the relation's entity/relationship structure.
2395                    my $structure = $self->_GetStructure($relationName);
2396                    # Check for a searchable fields list.
2397                    if (exists $structure->{searchFields}) {
2398                        # Here we know that we need to create a full-text search index.
2399                        # Get an SQL-formatted field name list.
2400                        my $fields = join(", ", $self->_FixNames(@{$structure->{searchFields}}));
2401                        # Create the index.
2402                        $dbh->create_index(tbl => $relationName, idx => "search_idx",
2403                                           flds => $fields, kind => 'fulltext');
2404                    }
2405                }
2406            }
2407      }      }
2408      # Analyze the table to improve performance.      # Analyze the table to improve performance.
2409      Trace("Analyzing and compacting $relationName.") if T(3);      Trace("Analyzing and compacting $relationName.") if T(3);
# Line 1849  Line 2413 
2413      return $retVal;      return $retVal;
2414  }  }
2415    
2416  =head3 GenerateEntity  =head3 DropRelation
2417    
2418  C<< my $fieldHash = $erdb->GenerateEntity($id, $type, \%values); >>  C<< $erdb->DropRelation($relationName); >>
2419    
2420  Generate the data for a new entity instance. This method creates a field hash suitable for  Physically drop a relation from the database.
 passing as a parameter to L</InsertObject>. The ID is specified by the callr, but the rest  
 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.  
2421    
2422  =over 4  =over 4
2423    
2424  =item id  =item relationName
   
 ID to assign to the new entity.  
   
 =item type  
   
 Type name for the new entity.  
   
 =item values  
2425    
2426  Hash containing additional values that might be needed by the data generation methods (optional).  Name of the relation to drop. If it does not exist, this method will have
2427    no effect.
2428    
2429  =back  =back
2430    
2431  =cut  =cut
2432    
2433  sub GenerateEntity {  sub DropRelation {
2434      # Get the parameters.      # Get the parameters.
2435      my ($self, $id, $type, $values) = @_;      my ($self, $relationName) = @_;
2436      # Create the return hash.      # Get the database handle.
2437      my $this = { id => $id };      my $dbh = $self->{_dbh};
2438      # Get the metadata structure.      # Drop the relation. The method used here has no effect if the relation
2439      my $metadata = $self->{_metaData};      # does not exist.
2440      # Get this entity's list of fields.      Trace("Invoking DB Kernel to drop $relationName.") if T(3);
2441      if (!exists $metadata->{Entities}->{$type}) {      $dbh->drop_table(tbl => $relationName);
         Confess("Unrecognized entity type $type in GenerateEntity.");  
     } else {  
         my $entity = $metadata->{Entities}->{$type};  
         my $fields = $entity->{Fields};  
         # Generate data from the fields.  
         _GenerateFields($this, $fields, $type, $values);  
     }  
     # Return the hash created.  
     return $this;  
2442  }  }
2443    
2444  =head3 GetEntity  =head3 GetEntity
# Line 2238  Line 2772 
2772      return $objectData->{Fields};      return $objectData->{Fields};
2773  }  }
2774    
2775  =head2 Data Mining Methods  =head3 SplitKeywords
2776    
2777  =head3 GetUsefulCrossValues  C<< my @keywords = ERDB::SplitKeywords($keywordString); >>
2778    
2779  C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>  This method returns a list of the positive keywords in the specified
2780    keyword string. All of the operators will have been stripped off,
2781    and if the keyword is preceded by a minus operator (C<->), it will
2782    not be in the list returned. The idea here is to get a list of the
2783    keywords the user wants to see. The list will be processed to remove
2784    duplicates.
2785    
2786  Return a list of the useful attributes that would be returned by a B<Cross> call  It is possible to create a string that confuses this method. For example
 from an entity of the source entity type through the specified relationship. This  
 means it will return the fields of the target entity type and the intersection data  
 fields in the relationship. Only primary table fields are returned. In other words,  
 the field names returned will be for fields where there is always one and only one  
 value.  
2787    
2788  =over 4      frog toad -frog
2789    
2790  =item sourceEntity  would return both C<frog> and C<toad>. If this is a problem we can deal
2791    with it later.
2792    
2793  Name of the entity from which the relationship crossing will start.  =over 4
2794    
2795  =item relationship  =item keywordString
2796    
2797  Name of the relationship being crossed.  The keyword string to be parsed.
2798    
2799  =item RETURN  =item RETURN
2800    
2801  Returns a list of field names in Sprout field format (I<objectName>C<(>I<fieldName>C<)>.  Returns a list of the words in the keyword string the user wants to
2802    see.
2803    
2804  =back  =back
2805    
2806  =cut  =cut
2807  #: Return Type @;  
2808  sub GetUsefulCrossValues {  sub SplitKeywords {
2809      # Get the parameters.      # Get the parameters.
2810      my ($self, $sourceEntity, $relationship) = @_;      my ($keywordString) = @_;
2811      # Declare the return variable.      # Make a safety copy of the string. (This helps during debugging.)
2812      my @retVal = ();      my $workString = $keywordString;
2813      # Determine the target entity for the relationship. This is whichever entity is not      # Convert operators we don't care about to spaces.
2814      # the source entity. So, if the source entity is the FROM, we'll get the name of      $workString =~ tr/+"()<>/ /;
2815      # the TO, and vice versa.      # Split the rest of the string along space boundaries. Note that we
2816      my $relStructure = $self->_GetStructure($relationship);      # eliminate any words that are zero length or begin with a minus sign.
2817      my $targetEntityType = ($relStructure->{from} eq $sourceEntity ? "to" : "from");      my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
2818      my $targetEntity = $relStructure->{$targetEntityType};      # Use a hash to remove duplicates.
2819      # Get the field table for the entity.      my %words = map { $_ => 1 } @wordList;
     my $entityFields = $self->GetFieldTable($targetEntity);  
     # The field table is a hash. The hash key is the field name. The hash value is a structure.  
     # For the entity fields, the key aspect of the target structure is that the {relation} value  
     # must match the entity name.  
     my @fieldList = map { "$targetEntity($_)" } grep { $entityFields->{$_}->{relation} eq $targetEntity }  
                         keys %{$entityFields};  
     # Push the fields found onto the return variable.  
     push @retVal, sort @fieldList;  
     # Get the field table for the relationship.  
     my $relationshipFields = $self->GetFieldTable($relationship);  
     # Here we have a different rule. We want all the fields other than "from-link" and "to-link".  
     # This may end up being an empty set.  
     my @fieldList2 = map { "$relationship($_)" } grep { $_ ne "from-link" && $_ ne "to-link" }  
                         keys %{$relationshipFields};  
     # Push these onto the return list.  
     push @retVal, sort @fieldList2;  
2820      # Return the result.      # Return the result.
2821      return @retVal;      return sort keys %words;
2822  }  }
2823    
2824  =head3 FindColumn  =head3 ValidateFieldName
2825    
2826  C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>  C<< my $okFlag = ERDB::ValidateFieldName($fieldName); >>
2827    
2828  Return the location a desired column in a data mining header line. The data  Return TRUE if the specified field name is valid, else FALSE. Valid field names must
2829  mining header line is a tab-separated list of column names. The column  be hyphenated words subject to certain restrictions.
 identifier is either the numerical index of a column or the actual column  
 name.  
2830    
2831  =over 4  =over 4
2832    
2833  =item headerLine  =item fieldName
   
 The header line from a data mining command, which consists of a tab-separated  
 list of column names.  
   
 =item columnIdentifier  
2834    
2835  Either the ordinal number of the desired column (1-based), or the name of the  Field name to be validated.
 desired column.  
2836    
2837  =item RETURN  =item RETURN
2838    
2839  Returns the array index (0-based) of the desired column.  Returns TRUE if the field name is valid, else FALSE.
2840    
2841  =back  =back
2842    
2843  =cut  =cut
2844    
2845  sub FindColumn {  sub ValidateFieldName {
2846      # Get the parameters.      # Get the parameters.
2847      my ($headerLine, $columnIdentifier) = @_;      my ($fieldName) = @_;
2848      # Declare the return variable.      # Declare the return variable. The field name is valid until we hear
2849      my $retVal;      # differently.
2850      # Split the header line into column names.      my $retVal = 1;
2851      my @headers = ParseColumns($headerLine);      # Look for bad stuff in the name.
2852      # Determine whether we have a number or a name.      if ($fieldName =~ /--/) {
2853      if ($columnIdentifier =~ /^\d+$/) {          # Here we have a doubled minus sign.
2854          # Here we have a number. Subtract 1 and validate the result.          Trace("Field name $fieldName has a doubled hyphen.") if T(1);
2855          $retVal = $columnIdentifier - 1;          $retVal = 0;
2856          if ($retVal < 0 || $retVal > $#headers) {      } elsif ($fieldName !~ /^[A-Za-z]/) {
2857              Confess("Invalid column identifer \"$columnIdentifier\": value out of range.");          # Here the field name is missing the initial letter.
2858          }          Trace("Field name $fieldName does not begin with a letter.") if T(1);
2859            $retVal = 0;
2860      } else {      } else {
2861          # Here we have a name. We need to find it in the list.          # Strip out the minus signs. Everything remaining must be a letter,
2862          for (my $i = 0; $i <= $#headers && ! defined($retVal); $i++) {          # underscore, or digit.
2863              if ($headers[$i] eq $columnIdentifier) {          my $strippedName = $fieldName;
2864                  $retVal = $i;          $strippedName =~ s/-//g;
2865              }          if ($strippedName !~ /^(\w|\d)+$/) {
2866          }              Trace("Field name $fieldName contains illegal characters.") if T(1);
2867          if (! defined($retVal)) {              $retVal = 0;
             Confess("Invalid column identifier \"$columnIdentifier\": value not found.");  
2868          }          }
2869      }      }
2870      # Return the result.      # Return the result.
2871      return $retVal;      return $retVal;
2872  }  }
2873    
2874  =head3 ParseColumns  =head3 ReadMetaXML
2875    
2876  C<< my @columns = ERDB::ParseColumns($line); >>  C<< my $rawMetaData = ERDB::ReadDBD($fileName); >>
2877    
2878  Convert the specified data line to a list of columns.  This method reads a raw database definition XML file and returns it.
2879    Normally, the metadata used by the ERDB system has been processed and
2880    modified to make it easier to load and retrieve the data; however,
2881    this method can be used to get the data in its raw form.
2882    
2883  =over 4  =over 4
2884    
2885  =item line  =item fileName
2886    
2887  A data mining input, consisting of a tab-separated list of columns terminated by a  Name of the XML file to read.
 new-line.  
2888    
2889  =item RETURN  =item RETURN
2890    
2891  Returns a list consisting of the column values.  Returns a hash reference containing the raw XML data from the specified file.
2892    
2893  =back  =back
2894    
2895  =cut  =cut
2896    
2897  sub ParseColumns {  sub ReadMetaXML {
2898      # Get the parameters.      # Get the parameters.
2899      my ($line) = @_;      my ($fileName) = @_;
2900      # Chop off the line-end.      # Read the XML.
2901      chomp $line;      my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
2902      # Split it into a list.      Trace("XML metadata loaded from file $fileName.") if T(1);
     my @retVal = split(/\t/, $line);  
2903      # Return the result.      # Return the result.
2904      return @retVal;      return $retVal;
2905  }  }
2906    
2907  =head2 Internal Utility Methods  =head3 GetEntityFieldHash
   
 =head3 SetupSQL  
2908    
2909  Process a list of object names and a filter clause so that they can be used to  C<< my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName); >>
 build an SQL statement. This method takes in a reference to a list of object names  
 and a filter clause. It will return a corrected filter clause, a list of mapped  
 names and the mapped name hash.  
2910    
2911  This is an instance method.  Get the field hash of the named entity in the specified raw XML structure.
2912    The field hash may not exist, in which case we need to create it.
2913    
2914  =over 4  =over 4
2915    
2916  =item objectNames  =item structure
2917    
2918  Reference to a list of the object names to be included in the query.  Raw XML structure defininng the database. This is not the run-time XML used by
2919    an ERDB object, since that has all sorts of optimizations built-in.
2920    
2921  =item filterClause  =item entityName
2922    
2923  A string containing the WHERE clause for the query (without the C<WHERE>) and also  Name of the entity whose field structure is desired.
 optionally the C<ORDER BY> and C<LIMIT> clauses.  
2924    
2925  =item RETURN  =item RETURN
2926    
2927  Returns a three-element list. The first element is the SQL statement suffix, beginning  Returns the field hash used to define the entity's fields.
 with the FROM clause. The second element is a reference to a list of the names to be  
 used in retrieving the fields. The third element is a hash mapping the names to the  
 objects they represent.  
2928    
2929  =back  =back
2930    
2931  =cut  =cut
2932    
2933  sub _SetupSQL {  sub GetEntityFieldHash {
2934      my ($self, $objectNames, $filterClause) = @_;      # Get the parameters.
2935      # Adjust the list of object names to account for multiple occurrences of the      my ($structure, $entityName) = @_;
2936        # Get the entity structure.
2937        my $entityData = $structure->{Entities}->{$entityName};
2938        # Look for a field structure.
2939        my $retVal = $entityData->{Fields};
2940        # If it doesn't exist, create it.
2941        if (! defined($retVal)) {
2942            $entityData->{Fields} = {};
2943            $retVal = $entityData->{Fields};
2944        }
2945        # Return the result.
2946        return $retVal;
2947    }
2948    
2949    =head3 WriteMetaXML
2950    
2951    C<< ERDB::WriteMetaXML($structure, $fileName); >>
2952    
2953    Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
2954    used to update the database definition. It must be used with care, however, since it
2955    will only work on a raw structure, not on the processed structure created by an ERDB
2956    constructor.
2957    
2958    =over 4
2959    
2960    =item structure
2961    
2962    XML structure to be written to the file.
2963    
2964    =item fileName
2965    
2966    Name of the output file to which the updated XML should be stored.
2967    
2968    =back
2969    
2970    =cut
2971    
2972    sub WriteMetaXML {
2973        # Get the parameters.
2974        my ($structure, $fileName) = @_;
2975        # Compute the output.
2976        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
2977        # Write it to the file.
2978        my $xmlOut = Open(undef, ">$fileName");
2979        print $xmlOut $fileString;
2980    }
2981    
2982    
2983    =head3 HTMLNote
2984    
2985    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
2986    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
2987    Except for C<[p]>, all the codes are closed by slash-codes. So, for
2988    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
2989    
2990    C<< my $realHtml = ERDB::HTMLNote($dataString); >>
2991    
2992    =over 4
2993    
2994    =item dataString
2995    
2996    String to convert to HTML.
2997    
2998    =item RETURN
2999    
3000    An HTML string derived from the input string.
3001    
3002    =back
3003    
3004    =cut
3005    
3006    sub HTMLNote {
3007        # Get the parameter.
3008        my ($dataString) = @_;
3009        # HTML-escape the text.
3010        my $retVal = CGI::escapeHTML($dataString);
3011        # Substitute the bulletin board codes.
3012        $retVal =~ s!\[(/?[bi])\]!<$1>!g;
3013        $retVal =~ s!\[p\]!</p><p>!g;
3014        # Return the result.
3015        return $retVal;
3016    }
3017    
3018    
3019    =head2 Data Mining Methods
3020    
3021    =head3 GetUsefulCrossValues
3022    
3023    C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>
3024    
3025    Return a list of the useful attributes that would be returned by a B<Cross> call
3026    from an entity of the source entity type through the specified relationship. This
3027    means it will return the fields of the target entity type and the intersection data
3028    fields in the relationship. Only primary table fields are returned. In other words,
3029    the field names returned will be for fields where there is always one and only one
3030    value.
3031    
3032    =over 4
3033    
3034    =item sourceEntity
3035    
3036    Name of the entity from which the relationship crossing will start.
3037    
3038    =item relationship
3039    
3040    Name of the relationship being crossed.
3041    
3042    =item RETURN
3043    
3044    Returns a list of field names in Sprout field format (I<objectName>C<(>I<fieldName>C<)>.
3045    
3046    =back
3047    
3048    =cut
3049    #: Return Type @;
3050    sub GetUsefulCrossValues {
3051        # Get the parameters.
3052        my ($self, $sourceEntity, $relationship) = @_;
3053        # Declare the return variable.
3054        my @retVal = ();
3055        # Determine the target entity for the relationship. This is whichever entity is not
3056        # the source entity. So, if the source entity is the FROM, we'll get the name of
3057        # the TO, and vice versa.
3058        my $relStructure = $self->_GetStructure($relationship);
3059        my $targetEntityType = ($relStructure->{from} eq $sourceEntity ? "to" : "from");
3060        my $targetEntity = $relStructure->{$targetEntityType};
3061        # Get the field table for the entity.
3062        my $entityFields = $self->GetFieldTable($targetEntity);
3063        # The field table is a hash. The hash key is the field name. The hash value is a structure.
3064        # For the entity fields, the key aspect of the target structure is that the {relation} value
3065        # must match the entity name.
3066        my @fieldList = map { "$targetEntity($_)" } grep { $entityFields->{$_}->{relation} eq $targetEntity }
3067                            keys %{$entityFields};
3068        # Push the fields found onto the return variable.
3069        push @retVal, sort @fieldList;
3070        # Get the field table for the relationship.
3071        my $relationshipFields = $self->GetFieldTable($relationship);
3072        # Here we have a different rule. We want all the fields other than "from-link" and "to-link".
3073        # This may end up being an empty set.
3074        my @fieldList2 = map { "$relationship($_)" } grep { $_ ne "from-link" && $_ ne "to-link" }
3075                            keys %{$relationshipFields};
3076        # Push these onto the return list.
3077        push @retVal, sort @fieldList2;
3078        # Return the result.
3079        return @retVal;
3080    }
3081    
3082    =head3 FindColumn
3083    
3084    C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>
3085    
3086    Return the location a desired column in a data mining header line. The data
3087    mining header line is a tab-separated list of column names. The column
3088    identifier is either the numerical index of a column or the actual column
3089    name.
3090    
3091    =over 4
3092    
3093    =item headerLine
3094    
3095    The header line from a data mining command, which consists of a tab-separated
3096    list of column names.
3097    
3098    =item columnIdentifier
3099    
3100    Either the ordinal number of the desired column (1-based), or the name of the
3101    desired column.
3102    
3103    =item RETURN
3104    
3105    Returns the array index (0-based) of the desired column.
3106    
3107    =back
3108    
3109    =cut
3110    
3111    sub FindColumn {
3112        # Get the parameters.
3113        my ($headerLine, $columnIdentifier) = @_;
3114        # Declare the return variable.
3115        my $retVal;
3116        # Split the header line into column names.
3117        my @headers = ParseColumns($headerLine);
3118        # Determine whether we have a number or a name.
3119        if ($columnIdentifier =~ /^\d+$/) {
3120            # Here we have a number. Subtract 1 and validate the result.
3121            $retVal = $columnIdentifier - 1;
3122            if ($retVal < 0 || $retVal > $#headers) {
3123                Confess("Invalid column identifer \"$columnIdentifier\": value out of range.");
3124            }
3125        } else {
3126            # Here we have a name. We need to find it in the list.
3127            for (my $i = 0; $i <= $#headers && ! defined($retVal); $i++) {
3128                if ($headers[$i] eq $columnIdentifier) {
3129                    $retVal = $i;
3130                }
3131            }
3132            if (! defined($retVal)) {
3133                Confess("Invalid column identifier \"$columnIdentifier\": value not found.");
3134            }
3135        }
3136        # Return the result.
3137        return $retVal;
3138    }
3139    
3140    =head3 ParseColumns
3141    
3142    C<< my @columns = ERDB::ParseColumns($line); >>
3143    
3144    Convert the specified data line to a list of columns.
3145    
3146    =over 4
3147    
3148    =item line
3149    
3150    A data mining input, consisting of a tab-separated list of columns terminated by a
3151    new-line.
3152    
3153    =item RETURN
3154    
3155    Returns a list consisting of the column values.
3156    
3157    =back
3158    
3159    =cut
3160    
3161    sub ParseColumns {
3162        # Get the parameters.
3163        my ($line) = @_;
3164        # Chop off the line-end.
3165        chomp $line;
3166        # Split it into a list.
3167        my @retVal = split(/\t/, $line);
3168        # Return the result.
3169        return @retVal;
3170    }
3171    
3172    =head2 Virtual Methods
3173    
3174    =head3 CleanKeywords
3175    
3176    C<< my $cleanedString = $erdb->CleanKeywords($searchExpression); >>
3177    
3178    Clean up a search expression or keyword list. This is a virtual method that may
3179    be overridden by the subclass. The base-class method removes extra spaces
3180    and converts everything to lower case.
3181    
3182    =over 4
3183    
3184    =item searchExpression
3185    
3186    Search expression or keyword list to clean. Note that a search expression may
3187    contain boolean operators which need to be preserved. This includes leading
3188    minus signs.
3189    
3190    =item RETURN
3191    
3192    Cleaned expression or keyword list.
3193    
3194    =back
3195    
3196    =cut
3197    
3198    sub CleanKeywords {
3199        # Get the parameters.
3200        my ($self, $searchExpression) = @_;
3201        # Lower-case the expression and copy it into the return variable. Note that we insure we
3202        # don't accidentally end up with an undefined value.
3203        my $retVal = lc($searchExpression || "");
3204        # Remove extra spaces.
3205        $retVal =~ s/\s+/ /g;
3206        $retVal =~ s/(^\s+)|(\s+$)//g;
3207        # Return the result.
3208        return $retVal;
3209    }
3210    
3211    =head3 GetSourceObject
3212    
3213    C<< my $source = $erdb->GetSourceObject($entityName); >>
3214    
3215    Return the object to be used in loading special attributes of the specified entity. The
3216    algorithm for loading special attributes is stored in the C<DataGen> elements of the
3217    XML
3218    
3219    =head2 Internal Utility Methods
3220    
3221    =head3 _RelationMap
3222    
3223    C<< my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef); >>
3224    
3225    Create the relation map for an SQL query. The relation map is used by B<DBObject>
3226    to determine how to interpret the results of the query.
3227    
3228    =over 4
3229    
3230    =item mappedNameHashRef
3231    
3232    Reference to a hash that maps modified object names to real object names.
3233    
3234    =item mappedNameListRef
3235    
3236    Reference to a list of modified object names in the order they appear in the
3237    SELECT list.
3238    
3239    =item RETURN
3240    
3241    Returns a list of 2-tuples. Each tuple consists of an object name as used in the
3242    query followed by the actual name of that object. This enables the B<DBObject> to
3243    determine the order of the tables in the query and which object name belongs to each
3244    mapped object name. Most of the time these two values are the same; however, if a
3245    relation occurs twice in the query, the relation name in the field list and WHERE
3246    clause will use a mapped name (generally the actual relation name with a numeric
3247    suffix) that does not match the actual relation name.
3248    
3249    =back
3250    
3251    =cut
3252    
3253    sub _RelationMap {
3254        # Get the parameters.
3255        my ($mappedNameHashRef, $mappedNameListRef) = @_;
3256        # Declare the return variable.
3257        my @retVal = ();
3258        # Build the map.
3259        for my $mappedName (@{$mappedNameListRef}) {
3260            push @retVal, [$mappedName, $mappedNameHashRef->{$mappedName}];
3261        }
3262        # Return it.
3263        return @retVal;
3264    }
3265    
3266    
3267    =head3 _SetupSQL
3268    
3269    Process a list of object names and a filter clause so that they can be used to
3270    build an SQL statement. This method takes in a reference to a list of object names
3271    and a filter clause. It will return a corrected filter clause, a list of mapped
3272    names and the mapped name hash.
3273    
3274    This is an instance method.
3275    
3276    =over 4
3277    
3278    =item objectNames
3279    
3280    Reference to a list of the object names to be included in the query.
3281    
3282    =item filterClause
3283    
3284    A string containing the WHERE clause for the query (without the C<WHERE>) and also
3285    optionally the C<ORDER BY> and C<LIMIT> clauses.
3286    
3287    =item matchClause
3288    
3289    An optional full-text search clause. If specified, it will be inserted at the
3290    front of the WHERE clause. It should already be SQL-formatted; that is, the
3291    field names should be in the form I<table>C<.>I<fieldName>.
3292    
3293    =item RETURN
3294    
3295    Returns a three-element list. The first element is the SQL statement suffix, beginning
3296    with the FROM clause. The second element is a reference to a list of the names to be
3297    used in retrieving the fields. The third element is a hash mapping the names to the
3298    objects they represent.
3299    
3300    =back
3301    
3302    =cut
3303    
3304    sub _SetupSQL {
3305        my ($self, $objectNames, $filterClause, $matchClause) = @_;
3306        # Adjust the list of object names to account for multiple occurrences of the
3307      # same object. We start with a hash table keyed on object name that will      # same object. We start with a hash table keyed on object name that will
3308      # return the object suffix. The first time an object is encountered it will      # return the object suffix. The first time an object is encountered it will
3309      # not be found in the hash. The next time the hash will map the object name      # not be found in the hash. The next time the hash will map the object name
# Line 2474  Line 3351 
3351      # FROM name1, name2, ... nameN      # FROM name1, name2, ... nameN
3352      #      #
3353      my $suffix = "FROM " . join(', ', @fromList);      my $suffix = "FROM " . join(', ', @fromList);
3354        # Now for the WHERE. First, we need a place for the filter string.
3355        my $filterString = "";
3356        # We will also keep a list of conditions to add to the WHERE clause in order to link
3357        # entities and relationships as well as primary relations to secondary ones.
3358        my @joinWhere = ();
3359      # Check for a filter clause.      # Check for a filter clause.
3360      if ($filterClause) {      if ($filterClause) {
3361          # Here we have one, so we convert its field names and add it to the query. First,          # Here we have one, so we convert its field names and add it to the query. First,
3362          # We create a copy of the filter string we can work with.          # We create a copy of the filter string we can work with.
3363          my $filterString = $filterClause;          $filterString = $filterClause;
3364          # Next, we sort the object names by length. This helps protect us from finding          # Next, we sort the object names by length. This helps protect us from finding
3365          # object names inside other object names when we're doing our search and replace.          # object names inside other object names when we're doing our search and replace.
3366          my @sortedNames = sort { length($b) - length($a) } @mappedNameList;          my @sortedNames = sort { length($b) - length($a) } @mappedNameList;
         # We will also keep a list of conditions to add to the WHERE clause in order to link  
         # entities and relationships as well as primary relations to secondary ones.  
         my @joinWhere = ();  
3367          # The final preparatory step is to create a hash table of relation names. The          # The final preparatory step is to create a hash table of relation names. The
3368          # table begins with the relation names already in the SELECT command. We may          # table begins with the relation names already in the SELECT command. We may
3369          # need to add relations later if there is filtering on a field in a secondary          # need to add relations later if there is filtering on a field in a secondary
# Line 2552  Line 3431 
3431                  }                  }
3432              }              }
3433          }          }
3434        }
3435          # The next step is to join the objects together. We only need to do this if there          # The next step is to join the objects together. We only need to do this if there
3436          # is more than one object in the object list. We start with the first object and          # is more than one object in the object list. We start with the first object and
3437          # run through the objects after it. Note also that we make a safety copy of the          # run through the objects after it. Note also that we make a safety copy of the
3438          # list before running through it.      # list before running through it, because we shift off the first object before
3439        # processing the rest.
3440          my @mappedObjectList = @mappedNameList;          my @mappedObjectList = @mappedNameList;
3441          my $lastMappedObject = shift @mappedObjectList;          my $lastMappedObject = shift @mappedObjectList;
3442          # Get the join table.          # Get the join table.
# Line 2584  Line 3465 
3465          # here is we want the filter clause to be empty if there's no WHERE filter.          # here is we want the filter clause to be empty if there's no WHERE filter.
3466          # We'll put the ORDER BY / LIMIT clauses in the following variable.          # We'll put the ORDER BY / LIMIT clauses in the following variable.
3467          my $orderClause = "";          my $orderClause = "";
3468        # This is only necessary if we have a filter string in which the ORDER BY
3469        # and LIMIT clauses can live.
3470        if ($filterString) {
3471          # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy          # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy
3472          # operator so that we find the first occurrence of either verb.          # operator so that we find the first occurrence of either verb.
3473          if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {          if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {
# Line 2592  Line 3476 
3476              $orderClause = $2 . substr($filterString, $pos);              $orderClause = $2 . substr($filterString, $pos);
3477              $filterString = $1;              $filterString = $1;
3478          }          }
3479          # Add the filter and the join clauses (if any) to the SELECT command.      }
3480        # All the things that are supposed to be in the WHERE clause of the
3481        # SELECT command need to be put into @joinWhere so we can string them
3482        # together. We begin with the match clause. This is important,
3483        # because the match clause's parameter mark must precede any parameter
3484        # marks in the filter string.
3485        if ($matchClause) {
3486            push @joinWhere, $matchClause;
3487        }
3488        # Add the filter string. We put it in parentheses to avoid operator
3489        # precedence problems with the match clause or the joins.
3490          if ($filterString) {          if ($filterString) {
3491              Trace("Filter string is \"$filterString\".") if T(4);              Trace("Filter string is \"$filterString\".") if T(4);
3492              push @joinWhere, "($filterString)";              push @joinWhere, "($filterString)";
3493          }          }
3494        # String it all together into a big filter clause.
3495          if (@joinWhere) {          if (@joinWhere) {
3496              $suffix .= " WHERE " . join(' AND ', @joinWhere);              $suffix .= " WHERE " . join(' AND ', @joinWhere);
3497          }          }
3498          # Add the sort or limit clause (if any) to the SELECT command.      # Add the sort or limit clause (if any).
3499          if ($orderClause) {          if ($orderClause) {
3500              $suffix .= " $orderClause";              $suffix .= " $orderClause";
3501          }          }
     }  
3502      # Return the suffix, the mapped name list, and the mapped name hash.      # Return the suffix, the mapped name list, and the mapped name hash.
3503      return ($suffix, \@mappedNameList, \%mappedNameHash);      return ($suffix, \@mappedNameList, \%mappedNameHash);
3504  }  }
3505    
3506  =head3 GetStatementHandle  =head3 _GetStatementHandle
3507    
3508  This method will prepare and execute an SQL query, returning the statement handle.  This method will prepare and execute an SQL query, returning the statement handle.
3509  The main reason for doing this here is so that everybody who does SQL queries gets  The main reason for doing this here is so that everybody who does SQL queries gets
# Line 2647  Line 3541 
3541      # Prepare the command.      # Prepare the command.
3542      my $sth = $dbh->prepare_command($command);      my $sth = $dbh->prepare_command($command);
3543      # Execute it with the parameters bound in.      # Execute it with the parameters bound in.
3544      $sth->execute(@{$params}) || Confess("SELECT error" . $sth->errstr());      $sth->execute(@{$params}) || Confess("SELECT error:  " . $sth->errstr());
3545      # Return the statement handle.      # Return the statement handle.
3546      return $sth;      return $sth;
3547  }  }
3548    
3549  =head3 GetLoadStats  =head3 _GetLoadStats
3550    
3551  Return a blank statistics object for use by the load methods.  Return a blank statistics object for use by the load methods.
3552    
# Line 2664  Line 3558 
3558      return Stats->new();      return Stats->new();
3559  }  }
3560    
3561  =head3 GenerateFields  =head3 _DumpRelation
   
 Generate field values from a field structure and store in a specified table. The field names  
 are first sorted by pass count, certain pre-defined fields are removed from the list, and  
 then we rip through them evaluation the data generation string. Fields in the primary relation  
 are stored as scalars; fields in secondary relations are stored as value lists.  
   
 This is a static method.  
   
 =over 4  
   
 =item this  
   
 Hash table into which the field values should be placed.  
   
 =item fields  
   
 Field structure from which the field descriptors should be taken.  
   
 =item type  
   
 Type name of the object whose fields are being generated.  
   
 =item values (optional)  
   
 Reference to a value structure from which additional values can be taken.  
   
 =item from (optiona)  
   
 Reference to the source entity instance if relationship data is being generated.  
   
 =item to (optional)  
   
 Reference to the target entity instance if relationship data is being generated.  
   
 =back  
   
 =cut  
   
 sub _GenerateFields {  
     # Get the parameters.  
     my ($this, $fields, $type, $values, $from, $to) = @_;  
     # Sort the field names by pass number.  
     my @fieldNames = sort { $fields->{$a}->{DataGen}->{pass} <=> $fields->{$b}->{DataGen}->{pass} } keys %{$fields};  
     # Loop through the field names, generating data.  
     for my $name (@fieldNames) {  
         # Only proceed if this field needs to be generated.  
         if (!exists $this->{$name}) {  
             # Get this field's data generation descriptor.  
             my $fieldDescriptor = $fields->{$name};  
             my $data = $fieldDescriptor->{DataGen};  
             # Get the code to generate the field value.  
             my $codeString = $data->{content};  
             # Determine whether or not this field is in the primary relation.  
             if ($fieldDescriptor->{relation} eq $type) {  
                 # Here we have a primary relation field. Store the field value as  
                 # a scalar.  
                 $this->{$name} = eval($codeString);  
             } else {  
                 # Here we have a secondary relation field. Create a null list  
                 # and push the desired number of field values onto it.  
                 my @fieldValues = ();  
                 my $count = IntGen(0,$data->{testCount});  
                 for (my $i = 0; $i < $count; $i++) {  
                     my $newValue = eval($codeString);  
                     push @fieldValues, $newValue;  
                 }  
                 # Store the value list in the main hash.  
                 $this->{$name} = \@fieldValues;  
             }  
         }  
     }  
 }  
   
 =head3 DumpRelation  
3562    
3563  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.
3564    
3565  This is an instance method.  This is an instance method.
3566    
# Line 2788  Line 3608 
3608      close DTXOUT;      close DTXOUT;
3609  }  }
3610    
3611  =head3 GetStructure  =head3 _GetStructure
3612    
3613  Get the data structure for a specified entity or relationship.  Get the data structure for a specified entity or relationship.
3614    
# Line 2827  Line 3647 
3647      return $retVal;      return $retVal;
3648  }  }
3649    
3650  =head3 GetRelationTable  
3651    
3652    =head3 _GetRelationTable
3653    
3654  Get the list of relations for a specified entity or relationship.  Get the list of relations for a specified entity or relationship.
3655    
# Line 2856  Line 3678 
3678      return $objectData->{Relations};      return $objectData->{Relations};
3679  }  }
3680    
3681  =head3 ValidateFieldNames  =head3 _ValidateFieldNames
3682    
3683  Determine whether or not the field names are valid. A description of the problems with the names  Determine whether or not the field names are valid. A description of the problems with the names
3684  will be written to the standard error output. If there is an error, this method will abort. This is  will be written to the standard error output. If there is an error, this method will abort. This is
# Line 2883  Line 3705 
3705          for my $object (values %{$metadata->{$section}}) {          for my $object (values %{$metadata->{$section}}) {
3706              # Loop through the object's fields.              # Loop through the object's fields.
3707              for my $fieldName (keys %{$object->{Fields}}) {              for my $fieldName (keys %{$object->{Fields}}) {
3708                  # Now we make some initial validations.                  # If this field name is invalid, set the return value to zero
3709                  if ($fieldName =~ /--/) {                  # so we know we encountered an error.
3710                      # Here we have a doubled minus sign.                  if (! ValidateFieldName($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";  
3711                          $retVal = 0;                          $retVal = 0;
3712                      }                      }
3713                  }                  }
3714              }              }
3715          }          }
     }  
3716      # If an error was found, fail.      # If an error was found, fail.
3717      if ($retVal  == 0) {      if ($retVal  == 0) {
3718          Confess("Errors found in field names.");          Confess("Errors found in field names.");
3719      }      }
3720  }  }
3721    
3722  =head3 LoadRelation  =head3 _LoadRelation
3723    
3724  Load a relation from the data in a tab-delimited disk file. The load will only take place if a disk  Load a relation from the data in a tab-delimited disk file. The load will only take place if a disk
3725  file with the same name as the relation exists in the specified directory.  file with the same name as the relation exists in the specified directory.
# Line 2971  Line 3779 
3779      return $retVal;      return $retVal;
3780  }  }
3781    
3782  =head3 LoadMetaData  
3783    =head3 _LoadMetaData
3784    
3785  This method loads the data describing this database from an XML file into a metadata structure.  This method loads the data describing this database from an XML file into a metadata structure.
3786  The resulting structure is a set of nested hash tables containing all the information needed to  The resulting structure is a set of nested hash tables containing all the information needed to
# Line 2996  Line 3805 
3805  sub _LoadMetaData {  sub _LoadMetaData {
3806      # Get the parameters.      # Get the parameters.
3807      my ($filename) = @_;      my ($filename) = @_;
3808      Trace("Reading Sprout DBD from $filename.") if T(2);      Trace("Reading DBD from $filename.") if T(2);
3809      # 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
3810      # get the exact structure we want.      # get the exact structure we want.
3811      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 $filename.") if T(1);  
3812      # Before we go any farther, we need to validate the field and object names. If an error is found,      # Before we go any farther, we need to validate the field and object names. If an error is found,
3813      # the method below will fail.      # the method below will fail.
3814      _ValidateFieldNames($metadata);      _ValidateFieldNames($metadata);
# Line 3142  Line 3938 
3938              my $count = 0;              my $count = 0;
3939              for my $index (@{$indexList}) {              for my $index (@{$indexList}) {
3940                  # Add this index to the index table.                  # Add this index to the index table.
3941                  _AddIndex("idx$relationName$count", $relation, $index);                  _AddIndex("idx$count", $relation, $index);
3942                  # Increment the counter so that the next index has a different name.                  # Increment the counter so that the next index has a different name.
3943                  $count++;                  $count++;
3944              }              }
# Line 3264  Line 4060 
4060                          }                          }
4061                      }                      }
4062                  }                  }
4063                  # Create joins between this relationship and the recursive relationships.                  # Create joins between this relationship and the recursive relationships.
4064                  # We don't need to check for ambiguous joins here, because a recursive                  # We don't need to check for ambiguous joins here, because a recursive
4065                  # relationship can only be ambiguous with another recursive relationship,                  # relationship can only be ambiguous with another recursive relationship,
4066                  # and the incoming relationship from the outer loop is never recursive.                  # and the incoming relationship from the outer loop is never recursive.
4067                  for my $otherName (@bothList) {                  for my $otherName (@bothList) {
4068                      Trace("Setting up relationship joins to recursive relationship $otherName with $relationshipName.") if T(metadata => 4);                      Trace("Setting up relationship joins to recursive relationship $otherName with $relationshipName.") if T(metadata => 4);
4069                      # Join from the left.                      # Join from the left.
4070                      $joinTable{"$relationshipName/$otherName"} =                      $joinTable{"$relationshipName/$otherName"} =
4071                          "$linkField = $otherName.from_link";                          "$linkField = $otherName.from_link";
4072                      # Join from the right.                      # Join from the right.
4073                      $joinTable{"$otherName/$relationshipName"} =                      $joinTable{"$otherName/$relationshipName"} =
4074                          "$otherName.to_link = $linkField";                          "$otherName.to_link = $linkField";
                 }  
             }  
         }  
         # Create entity joins for the recursive relationships. Unlike the non-recursive  
         # joins, the direction makes a difference with the recursive joins. This can give  
         # rise to situations where we can't create the path we want; however, it is always  
         # possible to get the same effect using multiple queries.  
         for my $relationshipName (@bothList) {  
             Trace("Setting up entity joins to recursive relationship $relationshipName with $entityName.") if T(metadata => 4);  
             # Join to the entity from each direction.  
             $joinTable{"$entityName/$relationshipName"} =  
                 "$entityName.id = $relationshipName.from_link";  
             $joinTable{"$relationshipName/$entityName"} =  
                 "$relationshipName.to_link = $entityName.id";  
         }  
     }  
     # Add the join table to the structure.  
     $metadata->{Joins} = \%joinTable;  
     # Return the slurped and fixed-up structure.  
     return $metadata;  
 }  
   
 =head3 SortNeeded  
   
 C<< my $parms = $erdb->SortNeeded($relationName); >>  
   
 Return the pipe command for the sort that should be applied to the specified  
 relation when creating the load file.  
   
 For example, if the load file should be sorted ascending by the first  
 field, this method would return  
   
     sort -k1 -t"\t"  
   
 If the first field is numeric, the method would return  
   
     sort -k1n -t"\t"  
   
 Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate  
 keys using a sort.  
   
 =over 4  
   
 =item relationName  
   
 Name of the relation to be examined.  
   
 =item  
   
 Returns the sort command to use for sorting the relation, suitable for piping.  
   
 =back  
   
 =cut  
 #: Return Type $;  
 sub SortNeeded {  
     # Get the parameters.  
     my ($self, $relationName) = @_;  
     # Declare a descriptor to hold the names of the key fields.  
     my @keyNames = ();  
     # Get the relation structure.  
     my $relationData = $self->_FindRelation($relationName);  
     # Find out if the relation is a primary entity relation,  
     # a relationship relation, or a secondary entity relation.  
     my $entityTable = $self->{_metaData}->{Entities};  
     my $relationshipTable = $self->{_metaData}->{Relationships};  
     if (exists $entityTable->{$relationName}) {  
         # Here we have a primary entity relation.  
         push @keyNames, "id";  
     } elsif (exists $relationshipTable->{$relationName}) {  
         # Here we have a relationship. We sort using the FROM index.  
         my $relationshipData = $relationshipTable->{$relationName};  
         my $index = $relationData->{Indexes}->{"idx${relationName}From"};  
         push @keyNames, @{$index->{IndexFields}};  
     } else {  
         # Here we have a secondary entity relation, so we have a sort on the ID field.  
         push @keyNames, "id";  
     }  
     # Now we parse the key names into sort parameters. First, we prime the return  
     # string.  
     my $retVal = "sort -t\"\t\" ";  
     # Get the relation's field list.  
     my @fields = @{$relationData->{Fields}};  
     # Loop through the keys.  
     for my $keyData (@keyNames) {  
         # Get the key and the ordering.  
         my ($keyName, $ordering);  
         if ($keyData =~ /^([^ ]+) DESC/) {  
             ($keyName, $ordering) = ($1, "descending");  
         } else {  
             ($keyName, $ordering) = ($keyData, "ascending");  
         }  
         # Find the key's position and type.  
         my $fieldSpec;  
         for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {  
             my $thisField = $fields[$i];  
             if ($thisField->{name} eq $keyName) {  
                 # Get the sort modifier for this field type. The modifier  
                 # decides whether we're using a character, numeric, or  
                 # floating-point sort.  
                 my $modifier = $TypeTable{$thisField->{type}}->{sort};  
                 # If the index is descending for this field, denote we want  
                 # to reverse the sort order on this field.  
                 if ($ordering eq 'descending') {  
                     $modifier .= "r";  
                 }  
                 # Store the position and modifier into the field spec, which  
                 # will stop the inner loop. Note that the field number is  
                 # 1-based in the sort command, so we have to increment the  
                 # index.  
                 $fieldSpec = ($i + 1) . $modifier;  
             }  
4075          }          }
         # Add this field to the sort command.  
         $retVal .= " -k$fieldSpec";  
4076      }      }
4077      # Return the result.          }
4078      return $retVal;          # Create entity joins for the recursive relationships. Unlike the non-recursive
4079            # joins, the direction makes a difference with the recursive joins. This can give
4080            # rise to situations where we can't create the path we want; however, it is always
4081            # possible to get the same effect using multiple queries.
4082            for my $relationshipName (@bothList) {
4083                Trace("Setting up entity joins to recursive relationship $relationshipName with $entityName.") if T(metadata => 4);
4084                # Join to the entity from each direction.
4085                $joinTable{"$entityName/$relationshipName"} =
4086                    "$entityName.id = $relationshipName.from_link";
4087                $joinTable{"$relationshipName/$entityName"} =
4088                    "$relationshipName.to_link = $entityName.id";
4089            }
4090        }
4091        # Add the join table to the structure.
4092        $metadata->{Joins} = \%joinTable;
4093        # Return the slurped and fixed-up structure.
4094        return $metadata;
4095  }  }
4096    
4097  =head3 CreateRelationshipIndex  =head3 _CreateRelationshipIndex
4098    
4099  Create an index for a relationship's relation.  Create an index for a relationship's relation.
4100    
# Line 3438  Line 4136 
4136          $newIndex->{Unique} = 'true';          $newIndex->{Unique} = 'true';
4137      }      }
4138      # Add the index to the relation.      # Add the index to the relation.
4139      _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);      _AddIndex("idx$indexKey", $relationStructure, $newIndex);
4140  }  }
4141    
4142  =head3 AddIndex  =head3 _AddIndex
4143    
4144  Add an index to a relation structure.  Add an index to a relation structure.
4145    
# Line 3487  Line 4185 
4185      $relationStructure->{Indexes}->{$indexName} = $newIndex;      $relationStructure->{Indexes}->{$indexName} = $newIndex;
4186  }  }
4187    
4188  =head3 FixupFields  =head3 _FixupFields
4189    
4190  This method fixes the field list for an entity or relationship. It will add the caller-specified  This method fixes the field list for an entity or relationship. It will add the caller-specified
4191  relation name to fields that do not have a name and set the C<PrettySort> value as specified.  relation name to fields that do not have a name and set the C<PrettySort> value as specified.
# Line 3525  Line 4223 
4223          # Here it doesn't, so we create a new one.          # Here it doesn't, so we create a new one.
4224          $structure->{Fields} = { };          $structure->{Fields} = { };
4225      } else {      } else {
4226          # Here we have a field list. Loop through its fields.          # Here we have a field list. We need to track the searchable fields, so we
4227            # create a list for stashing them.
4228            my @textFields = ();
4229            # Loop through the fields.
4230          my $fieldStructures = $structure->{Fields};          my $fieldStructures = $structure->{Fields};
4231          for my $fieldName (keys %{$fieldStructures}) {          for my $fieldName (keys %{$fieldStructures}) {
4232              Trace("Processing field $fieldName of $defaultRelationName.") if T(4);              Trace("Processing field $fieldName of $defaultRelationName.") if T(4);
# Line 3534  Line 4235 
4235              my $type = $fieldData->{type};              my $type = $fieldData->{type};
4236              # Plug in a relation name if it is needed.              # Plug in a relation name if it is needed.
4237              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });
4238              # Plug in a data generator if we need one.              # Check for searchability.
4239              if (!exists $fieldData->{DataGen}) {              if ($fieldData->{searchable}) {
4240                  # The data generator will use the default for the field's type.                  # Only allow this for a primary relation.
4241                  $fieldData->{DataGen} = { content => $TypeTable{$type}->{dataGen} };                  if ($fieldData->{relation} ne $defaultRelationName) {
4242                        Confess("Field $fieldName of $defaultRelationName is in secondary relations and cannot be searchable.");
4243                    } else {
4244                        push @textFields, $fieldName;
4245                    }
4246              }              }
             # Plug in the defaults for the optional data generation parameters.  
             Tracer::MergeOptions($fieldData->{DataGen}, { testCount => 1, pass => 0 });  
4247              # Add the PrettySortValue.              # Add the PrettySortValue.
4248              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);
4249          }          }
4250            # If there are searchable fields, remember the fact.
4251            if (@textFields) {
4252                $structure->{searchFields} = \@textFields;
4253            }
4254      }      }
4255  }  }
4256    
4257  =head3 FixName  =head3 _FixName
4258    
4259  Fix the incoming field name so that it is a legal SQL column name.  Fix the incoming field name so that it is a legal SQL column name.
4260    
# Line 3576  Line 4283 
4283      return $fieldName;      return $fieldName;
4284  }  }
4285    
4286  =head3 FixNames  =head3 _FixNames
4287    
4288  Fix all the field names in a list.  Fix all the field names in a list.
4289    
# Line 3607  Line 4314 
4314      return @result;      return @result;
4315  }  }
4316    
4317  =head3 AddField  =head3 _AddField
4318    
4319  Add a field to a field list.  Add a field to a field list.
4320    
# Line 3642  Line 4349 
4349      $fieldList->{$fieldName} = $fieldStructure;      $fieldList->{$fieldName} = $fieldStructure;
4350  }  }
4351    
4352  =head3 ReOrderRelationTable  =head3 _ReOrderRelationTable
4353    
4354  This method will take a relation table and re-sort it according to the implicit ordering of the  This method will take a relation table and re-sort it according to the implicit ordering of the
4355  C<PrettySort> property. Instead of a hash based on field names, it will return a list of fields.  C<PrettySort> property. Instead of a hash based on field names, it will return a list of fields.
# Line 3703  Line 4410 
4410    
4411  }  }
4412    
4413  =head3 IsPrimary  =head3 _IsPrimary
4414    
4415  Return TRUE if a specified relation is a primary relation, else FALSE. A relation is primary  Return TRUE if a specified relation is a primary relation, else FALSE. A relation is primary
4416  if it has the same name as an entity or relationship.  if it has the same name as an entity or relationship.
# Line 3739  Line 4446 
4446      return $retVal;      return $retVal;
4447  }  }
4448    
4449  =head3 FindRelation  =head3 _FindRelation
4450    
4451  Return the descriptor for the specified relation.  Return the descriptor for the specified relation.
4452    
# Line 3770  Line 4477 
4477    
4478  =head2 HTML Documentation Utility Methods  =head2 HTML Documentation Utility Methods
4479    
4480  =head3 ComputeRelationshipSentence  =head3 _ComputeRelationshipSentence
4481    
4482  The relationship sentence consists of the relationship name between the names of the  The relationship sentence consists of the relationship name between the names of the
4483  two related entities and an arity indicator.  two related entities and an arity indicator.
# Line 3808  Line 4515 
4515      return $result;      return $result;
4516  }  }
4517    
4518  =head3 ComputeRelationshipHeading  =head3 _ComputeRelationshipHeading
4519    
4520  The relationship heading is the L<relationship sentence|/ComputeRelationshipSentence> with the entity  The relationship heading is the L<relationship sentence|/ComputeRelationshipSentence> with the entity
4521  names hyperlinked to the appropriate entity sections of the document.  names hyperlinked to the appropriate entity sections of the document.
# Line 3845  Line 4552 
4552      return $result;      return $result;
4553  }  }
4554    
4555  =head3 ShowRelationTable  =head3 _ShowRelationTable
4556    
4557  Generate the HTML string for a particular relation. The relation's data will be formatted as an HTML  Generate the HTML string for a particular relation. The relation's data will be formatted as an HTML
4558  table with three columns-- the field name, the field type, and the field description.  table with three columns-- the field name, the field type, and the field description.
# Line 3895  Line 4602 
4602          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";
4603          # Add any note text.          # Add any note text.
4604          if (my $note = $indexData->{Notes}) {          if (my $note = $indexData->{Notes}) {
4605              $htmlString .= "<li>" . _HTMLNote($note->{content}) . "</li>\n";              $htmlString .= "<li>" . HTMLNote($note->{content}) . "</li>\n";
4606          }          }
4607          # Add the fiield list.          # Add the fiield list.
4608          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";
# Line 3906  Line 4613 
4613      $htmlString .= "</ul>\n";      $htmlString .= "</ul>\n";
4614  }  }
4615    
4616  =head3 OpenFieldTable  =head3 _OpenFieldTable
4617    
4618  This method creates the header string for the field table generated by L</ShowMetaData>.  This method creates the header string for the field table generated by L</ShowMetaData>.
4619    
# Line 3931  Line 4638 
4638      return _OpenTable($tablename, 'Field', 'Type', 'Description');      return _OpenTable($tablename, 'Field', 'Type', 'Description');
4639  }  }
4640    
4641  =head3 OpenTable  =head3 _OpenTable
4642    
4643  This method creates the header string for an HTML table.  This method creates the header string for an HTML table.
4644    
# Line 3971  Line 4678 
4678      return $htmlString;      return $htmlString;
4679  }  }
4680    
4681  =head3 CloseTable  =head3 _CloseTable
4682    
4683  This method returns the HTML for closing a table.  This method returns the HTML for closing a table.
4684    
# Line 3983  Line 4690 
4690      return "</table></p>\n";      return "</table></p>\n";
4691  }  }
4692    
4693  =head3 ShowField  =head3 _ShowField
4694    
4695  This method returns the HTML for displaying a row of field information in a field table.  This method returns the HTML for displaying a row of field information in a field table.
4696    
# Line 4010  Line 4717 
4717      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>";
4718      # If we have content, add it as a third column.      # If we have content, add it as a third column.
4719      if (exists $fieldData->{Notes}) {      if (exists $fieldData->{Notes}) {
4720          $htmlString .= "<td>" . _HTMLNote($fieldData->{Notes}->{content}) . "</td>";          $htmlString .= "<td>" . HTMLNote($fieldData->{Notes}->{content}) . "</td>";
4721      }      }
4722      # Close off the row.      # Close off the row.
4723      $htmlString .= "</tr>\n";      $htmlString .= "</tr>\n";
# Line 4018  Line 4725 
4725      return $htmlString;      return $htmlString;
4726  }  }
4727    
 =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;  
 }  
   
4728  1;  1;

Legend:
Removed from v.1.69  
changed lines
  Added in v.1.75

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3