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

Diff of /Sprout/ERDB.pm

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

revision 1.48, Wed Jun 21 03:12:20 2006 UTC revision 1.77, Mon Nov 20 05:53:02 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 91  Line 92 
92    
93  32-bit signed integer  32-bit signed integer
94    
95    =item counter
96    
97    32-bit unsigned integer
98    
99  =item date  =item date
100    
101  64-bit unsigned integer, representing a PERL date/time value  64-bit unsigned integer, representing a PERL date/time value
# Line 186  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 205  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 316  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.  # 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, dataGen => "StringGen('A')" },  # index
342                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, dataGen => "IntGen(0, 99999999)" },  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",
343                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, dataGen => "StringGen(IntGen(10,250))" },                                 indexMod =>   0, notes => "single ASCII character"},
344                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, dataGen => "StringGen(IntGen(80,1000))" },                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n",
345                    date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, dataGen => "DateGen(-7, 7, IntGen(0,1400))" },                                 indexMod =>   0, notes => "signed 32-bit integer"},
346                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, dataGen => "FloatGen(0.0, 100.0)" },                    counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n",
347                    boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, dataGen => "IntGen(0, 1)" },                                 indexMod =>   0, notes => "unsigned 32-bit integer"},
348                      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, 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, 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, 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, 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, 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 344  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 493  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 550  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 597  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 684  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 841  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 856  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, $fieldValue); >>
1084    
1085    Delete secondary field values from the database. This method can be used to delete all
1086    values of a specified field for a particular entity instance, or only a single value.
1087    
1088    Secondary fields are stored in two-column relations separate from an entity's primary
1089    table, and as a result a secondary field can legitimately have no value or multiple
1090    values. Therefore, it makes sense to talk about deleting secondary fields where it
1091    would not make sense for primary fields.
1092    
1093    =over 4
1094    
1095    =item entityName
1096    
1097    Name of the entity from which the fields are to be deleted.
1098    
1099    =item id
1100    
1101    ID of the entity instance to be processed. If the instance is not found, this
1102    method will have no effect. If C<undef> is specified, all values for all of
1103    the entity instances will be deleted.
1104    
1105    =item fieldName
1106    
1107    Name of the field whose values are to be deleted.
1108    
1109    =item fieldValue (optional)
1110    
1111    Value to be deleted. If not specified, then all values of the specified field
1112    will be deleted for the entity instance. If specified, then only the values which
1113    match this parameter will be deleted.
1114    
1115    =item RETURN
1116    
1117    Returns the number of rows deleted.
1118    
1119    =back
1120    
1121    =cut
1122    
1123    sub DeleteValue {
1124        # Get the parameters.
1125        my ($self, $entityName, $id, $fieldName, $fieldValue) = @_;
1126        # Declare the return value.
1127        my $retVal = 0;
1128        # We need to set up an SQL command to do the deletion. First, we
1129        # find the name of the field's relation.
1130        my $table = $self->GetFieldTable($entityName);
1131        my $field = $table->{$fieldName};
1132        my $relation = $field->{relation};
1133        # Make sure this is a secondary field.
1134        if ($relation eq $entityName) {
1135            Confess("Cannot delete values of $fieldName for $entityName.");
1136        } else {
1137            # Set up the SQL command to delete all values.
1138            my $sql = "DELETE FROM $relation";
1139            # Build the filter.
1140            my @filters = ();
1141            my @parms = ();
1142            # Check for a filter by ID.
1143            if (defined $id) {
1144                push @filters, "id = ?";
1145                push @parms, $id;
1146            }
1147            # Check for a filter by value.
1148            if (defined $fieldValue) {
1149                push @filters, "$fieldName = ?";
1150                push @parms, $fieldValue;
1151            }
1152            # Append the filters to the command.
1153            if (@filters) {
1154                $sql .= " WHERE " . join(" AND ", @filters);
1155            }
1156            # Execute the command.
1157            my $dbh = $self->{_dbh};
1158            $retVal = $dbh->SQL($sql, 0, @parms);
1159        }
1160        # Return the result.
1161        return $retVal;
1162    }
1163    
1164  =head3 LoadTables  =head3 LoadTables
1165    
1166  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>
# Line 950  Line 1255 
1255      return sort keys %{$entityList};      return sort keys %{$entityList};
1256  }  }
1257    
1258    =head3 GetDataTypes
1259    
1260    C<< my %types = ERDB::GetDataTypes(); >>
1261    
1262    Return a table of ERDB data types. The table returned is a hash of hashes.
1263    The keys of the big hash are the datatypes. Each smaller hash has several
1264    values used to manage the data. The most interesting is the SQL type (key
1265    C<sqlType>) and the descriptive node (key C<notes>).
1266    
1267    Note that changing the values in the smaller hashes will seriously break
1268    things, so this data should be treated as read-only.
1269    
1270    =cut
1271    
1272    sub GetDataTypes {
1273        return %TypeTable;
1274    }
1275    
1276    
1277  =head3 IsEntity  =head3 IsEntity
1278    
1279  C<< my $flag = $erdb->IsEntity($entityName); >>  C<< my $flag = $erdb->IsEntity($entityName); >>
# Line 1094  Line 1418 
1418      return $retVal;      return $retVal;
1419  }  }
1420    
1421    =head3 Search
1422    
1423    C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>
1424    
1425    Perform a full text search with filtering. The search will be against a specified object
1426    in the object name list. That object will get an extra field containing the search
1427    relevance. Note that except for the search expression, the parameters of this method are
1428    the same as those for L</Get> and follow the same rules.
1429    
1430    =over 4
1431    
1432    =item searchExpression
1433    
1434    Boolean search expression for the text fields of the target object. The default mode for
1435    a Boolean search expression is OR, but we want the default to be AND, so we will
1436    add a C<+> operator to each word with no other operator before it.
1437    
1438    =item idx
1439    
1440    Index in the I<$objectNames> list of the table to be searched in full-text mode.
1441    
1442    =item objectNames
1443    
1444    List containing the names of the entity and relationship objects to be retrieved.
1445    
1446    =item filterClause
1447    
1448    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1449    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
1450    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
1451    in the filter clause should be added to the parameter list as additional parameters. The
1452    fields in a filter clause can come from primary entity relations, relationship relations,
1453    or secondary entity relations; however, all of the entities and relationships involved must
1454    be included in the list of object names.
1455    
1456    =item params
1457    
1458    Reference to a list of parameter values to be substituted into the filter clause.
1459    
1460    =item RETURN
1461    
1462    Returns a query object for the specified search.
1463    
1464    =back
1465    
1466    =cut
1467    
1468    sub Search {
1469        # Get the parameters.
1470        my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1471        # Declare the return variable.
1472        my $retVal;
1473        # Create a safety copy of the parameter list. Note we have to be careful to insure
1474        # a parameter list exists before we copy it.
1475        my @myParams = ();
1476        if (defined $params) {
1477            @myParams = @{$params};
1478        }
1479        # Get the first object's structure so we have access to the searchable fields.
1480        my $object1Name = $objectNames->[$idx];
1481        my $object1Structure = $self->_GetStructure($object1Name);
1482        # Get the field list.
1483        if (! exists $object1Structure->{searchFields}) {
1484            Confess("No searchable index for $object1Name.");
1485        } else {
1486            # Get the field list.
1487            my @fields = @{$object1Structure->{searchFields}};
1488            # Clean the search expression.
1489            my $actualKeywords = $self->CleanKeywords($searchExpression);
1490            # Prefix a "+" to each uncontrolled word. This converts the default
1491            # search mode from OR to AND.
1492            $actualKeywords =~ s/(^|\s)(\w)/$1\+$2/g;
1493            Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1494            # We need two match expressions, one for the filter clause and one in the
1495            # query itself. Both will use a parameter mark, so we need to push the
1496            # search expression onto the front of the parameter list twice.
1497            unshift @myParams, $actualKeywords, $actualKeywords;
1498            # Build the match expression.
1499            my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
1500            my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
1501            # Process the SQL stuff.
1502            my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1503                $self->_SetupSQL($objectNames, $filterClause, $matchClause);
1504            # Create the query. Note that the match clause is inserted at the front of
1505            # the select fields.
1506            my $command = "SELECT DISTINCT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .
1507                ".* $suffix";
1508            my $sth = $self->_GetStatementHandle($command, \@myParams);
1509            # Now we create the relation map, which enables DBQuery to determine the order, name
1510            # and mapped name for each object in the query.
1511            my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
1512            # Return the statement object.
1513            $retVal = DBQuery::_new($self, $sth, \@relationMap, $object1Name);
1514        }
1515        return $retVal;
1516    }
1517    
1518  =head3 GetFlat  =head3 GetFlat
1519    
1520  C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>  C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>
# Line 1147  Line 1568 
1568      return @retVal;      return @retVal;
1569  }  }
1570    
1571    =head3 SpecialFields
1572    
1573    C<< my %specials = $erdb->SpecialFields($entityName); >>
1574    
1575    Return a hash mapping special fields in the specified entity to the value of their
1576    C<special> attribute. This enables the subclass to get access to the special field
1577    attributes without needed to plumb the internal ERDB data structures.
1578    
1579    =over 4
1580    
1581    =item entityName
1582    
1583    Name of the entity whose special fields are desired.
1584    
1585    =item RETURN
1586    
1587    Returns a hash. The keys of the hash are the special field names, and the values
1588    are the values from each special field's C<special> attribute.
1589    
1590    =back
1591    
1592    =cut
1593    
1594    sub SpecialFields {
1595        # Get the parameters.
1596        my ($self, $entityName) = @_;
1597        # Declare the return variable.
1598        my %retVal = ();
1599        # Find the entity's data structure.
1600        my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1601        # Loop through its fields, adding each special field to the return hash.
1602        my $fieldHash = $entityData->{Fields};
1603        for my $fieldName (keys %{$fieldHash}) {
1604            my $fieldData = $fieldHash->{$fieldName};
1605            if (exists $fieldData->{special}) {
1606                $retVal{$fieldName} = $fieldData->{special};
1607            }
1608        }
1609        # Return the result.
1610        return %retVal;
1611    }
1612    
1613  =head3 Delete  =head3 Delete
1614    
1615  C<< my $stats = $erdb->Delete($entityName, $objectID); >>  C<< my $stats = $erdb->Delete($entityName, $objectID, $testFlag); >>
1616    
1617  Delete an entity instance from the database. The instance is deleted along with all entity and  Delete an entity instance from the database. The instance is deleted along with all entity and
1618  relationship instances dependent on it. The idea of dependence here is recursive. An object is  relationship instances dependent on it. The definition of I<dependence> is recursive.
1619  always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many  
1620  relationship connected to a dependent entity or the "to" entity connected to a 1-to-many  An object is always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many
1621    relationship connected to a dependent entity or if it is the "to" entity connected to a 1-to-many
1622  dependent relationship.  dependent relationship.
1623    
1624  =over 4  =over 4
# Line 1203  Line 1667 
1667      # This final hash is used to remember what work still needs to be done. We push paths      # This final hash is used to remember what work still needs to be done. We push paths
1668      # onto the list, then pop them off to extend the paths. We prime it with the starting      # onto the list, then pop them off to extend the paths. We prime it with the starting
1669      # point. Note that we will work hard to insure that the last item on a path in the      # point. Note that we will work hard to insure that the last item on a path in the
1670      # TODO list is always an entity.      # to-do list is always an entity.
1671      my @todoList = ([$entityName]);      my @todoList = ([$entityName]);
1672      while (@todoList) {      while (@todoList) {
1673          # Get the current path.          # Get the current path.
# Line 1300  Line 1764 
1764                  # Here the user wants to trace without executing.                  # Here the user wants to trace without executing.
1765                  Trace($stmt) if T(0);                  Trace($stmt) if T(0);
1766              } else {              } else {
1767                  # Here we can delete. Note that the SQL method dies with a confessing                  # Here we can delete. Note that the SQL method dies with a confession
1768                  # if an error occurs, so we just go ahead and do it.                  # if an error occurs, so we just go ahead and do it.
1769                  Trace("Executing delete from $target using '$objectID'.") if T(3);                  Trace("Executing delete from $target using '$objectID'.") if T(3);
1770                  my $rv = $db->SQL($stmt, 0, $objectID);                  my $rv = $db->SQL($stmt, 0, $objectID);
# Line 1315  Line 1779 
1779      return $retVal;      return $retVal;
1780  }  }
1781    
1782  =head3 GetList  =head3 SortNeeded
   
 C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>  
   
 Return a list of object descriptors for the specified objects as determined by the  
 specified filter clause.  
   
 This method is essentially the same as L</Get> except it returns a list of objects rather  
 than a query object that can be used to get the results one record at a time.  
1783    
1784  =over 4  C<< my $parms = $erdb->SortNeeded($relationName); >>
1785    
1786  =item objectNames  Return the pipe command for the sort that should be applied to the specified
1787    relation when creating the load file.
1788    
1789  List containing the names of the entity and relationship objects to be retrieved.  For example, if the load file should be sorted ascending by the first
1790    field, this method would return
1791    
1792  =item filterClause      sort -k1 -t"\t"
1793    
1794  WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  If the first field is numeric, the method would return
 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.  
1795    
1796  The filter clause can also specify a sort order. To do this, simply follow the filter string      sort -k1n -t"\t"
 with an ORDER BY clause. For example, the following filter string gets all genomes for a  
 particular genus and sorts them by species name.  
1797    
1798  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>  Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate
1799    keys using a sort.
1800    
1801  The rules for field references in a sort order are the same as those for field references in the  =over 4
 filter clause in general; however, odd things may happen if a sort field is from a secondary  
 relation.  
1802    
1803  =item params  =item relationName
1804    
1805  Reference to a list of parameter values to be substituted into the filter clause.  Name of the relation to be examined.
1806    
1807  =item RETURN  =item
1808    
1809  Returns a list of B<DBObject>s that satisfy the query conditions.  Returns the sort command to use for sorting the relation, suitable for piping.
1810    
1811  =back  =back
1812    
1813  =cut  =cut
1814  #: Return Type @%  #: Return Type $;
1815  sub GetList {  sub SortNeeded {
1816      # Get the parameters.      # Get the parameters.
1817        my ($self, $relationName) = @_;
1818        # Declare a descriptor to hold the names of the key fields.
1819        my @keyNames = ();
1820        # Get the relation structure.
1821        my $relationData = $self->_FindRelation($relationName);
1822        # Find out if the relation is a primary entity relation,
1823        # a relationship relation, or a secondary entity relation.
1824        my $entityTable = $self->{_metaData}->{Entities};
1825        my $relationshipTable = $self->{_metaData}->{Relationships};
1826        if (exists $entityTable->{$relationName}) {
1827            # Here we have a primary entity relation.
1828            push @keyNames, "id";
1829        } elsif (exists $relationshipTable->{$relationName}) {
1830            # Here we have a relationship. We sort using the FROM index.
1831            my $relationshipData = $relationshipTable->{$relationName};
1832            my $index = $relationData->{Indexes}->{idxFrom};
1833            push @keyNames, @{$index->{IndexFields}};
1834        } else {
1835            # Here we have a secondary entity relation, so we have a sort on the ID field.
1836            push @keyNames, "id";
1837        }
1838        # Now we parse the key names into sort parameters. First, we prime the return
1839        # string.
1840        my $retVal = "sort -t\"\t\" ";
1841        # Get the relation's field list.
1842        my @fields = @{$relationData->{Fields}};
1843        # Loop through the keys.
1844        for my $keyData (@keyNames) {
1845            # Get the key and the ordering.
1846            my ($keyName, $ordering);
1847            if ($keyData =~ /^([^ ]+) DESC/) {
1848                ($keyName, $ordering) = ($1, "descending");
1849            } else {
1850                ($keyName, $ordering) = ($keyData, "ascending");
1851            }
1852            # Find the key's position and type.
1853            my $fieldSpec;
1854            for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {
1855                my $thisField = $fields[$i];
1856                if ($thisField->{name} eq $keyName) {
1857                    # Get the sort modifier for this field type. The modifier
1858                    # decides whether we're using a character, numeric, or
1859                    # floating-point sort.
1860                    my $modifier = $TypeTable{$thisField->{type}}->{sort};
1861                    # If the index is descending for this field, denote we want
1862                    # to reverse the sort order on this field.
1863                    if ($ordering eq 'descending') {
1864                        $modifier .= "r";
1865                    }
1866                    # Store the position and modifier into the field spec, which
1867                    # will stop the inner loop. Note that the field number is
1868                    # 1-based in the sort command, so we have to increment the
1869                    # index.
1870                    $fieldSpec = ($i + 1) . $modifier;
1871                }
1872            }
1873            # Add this field to the sort command.
1874            $retVal .= " -k$fieldSpec";
1875        }
1876        # Return the result.
1877        return $retVal;
1878    }
1879    
1880    =head3 GetList
1881    
1882    C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>
1883    
1884    Return a list of object descriptors for the specified objects as determined by the
1885    specified filter clause.
1886    
1887    This method is essentially the same as L</Get> except it returns a list of objects rather
1888    than a query object that can be used to get the results one record at a time.
1889    
1890    =over 4
1891    
1892    =item objectNames
1893    
1894    List containing the names of the entity and relationship objects to be retrieved.
1895    
1896    =item filterClause
1897    
1898    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1899    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
1900    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
1901    in the filter clause should be added to the parameter list as additional parameters. The
1902    fields in a filter clause can come from primary entity relations, relationship relations,
1903    or secondary entity relations; however, all of the entities and relationships involved must
1904    be included in the list of object names.
1905    
1906    The filter clause can also specify a sort order. To do this, simply follow the filter string
1907    with an ORDER BY clause. For example, the following filter string gets all genomes for a
1908    particular genus and sorts them by species name.
1909    
1910    C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
1911    
1912    The rules for field references in a sort order are the same as those for field references in the
1913    filter clause in general; however, odd things may happen if a sort field is from a secondary
1914    relation.
1915    
1916    =item params
1917    
1918    Reference to a list of parameter values to be substituted into the filter clause.
1919    
1920    =item RETURN
1921    
1922    Returns a list of B<DBObject>s that satisfy the query conditions.
1923    
1924    =back
1925    
1926    =cut
1927    #: Return Type @%
1928    sub GetList {
1929        # Get the parameters.
1930      my ($self, $objectNames, $filterClause, $params) = @_;      my ($self, $objectNames, $filterClause, $params) = @_;
1931      # Declare the return variable.      # Declare the return variable.
1932      my @retVal = ();      my @retVal = ();
# Line 1431  Line 1993 
1993  sub GetCount {  sub GetCount {
1994      # Get the parameters.      # Get the parameters.
1995      my ($self, $objectNames, $filter, $params) = @_;      my ($self, $objectNames, $filter, $params) = @_;
1996        # Insure the params argument is an array reference if the caller left it off.
1997        if (! defined($params)) {
1998            $params = [];
1999        }
2000      # Declare the return variable.      # Declare the return variable.
2001      my $retVal;      my $retVal;
2002      # Find out if we're counting an entity or a relationship.      # Find out if we're counting an entity or a relationship.
# Line 1544  Line 2110 
2110      }      }
2111  }  }
2112    
2113    =head3 InsertValue
2114    
2115    C<< $erdb->InsertValue($entityID, $fieldName, $value); >>
2116    
2117    This method will insert a new value into the database. The value must be one
2118    associated with a secondary relation, since primary values cannot be inserted:
2119    they occur exactly once. Secondary values, on the other hand, can be missing
2120    or multiply-occurring.
2121    
2122    =over 4
2123    
2124    =item entityID
2125    
2126    ID of the object that is to receive the new value.
2127    
2128    =item fieldName
2129    
2130    Field name for the new value-- this includes the entity name, since
2131    field names are of the format I<objectName>C<(>I<fieldName>C<)>.
2132    
2133    =item value
2134    
2135    New value to be put in the field.
2136    
2137    =back
2138    
2139    =cut
2140    
2141    sub InsertValue {
2142        # Get the parameters.
2143        my ($self, $entityID, $fieldName, $value) = @_;
2144        # Parse the entity name and the real field name.
2145        if ($fieldName =~ /^([^(]+)\(([^)]+)\)/) {
2146            my $entityName = $1;
2147            my $fieldTitle = $2;
2148            # Get its descriptor.
2149            if (!$self->IsEntity($entityName)) {
2150                Confess("$entityName is not a valid entity.");
2151            } else {
2152                my $entityData = $self->{_metaData}->{Entities}->{$entityName};
2153                # Find the relation containing this field.
2154                my $fieldHash = $entityData->{Fields};
2155                if (! exists $fieldHash->{$fieldTitle}) {
2156                    Confess("$fieldTitle not found in $entityName.");
2157                } else {
2158                    my $relation = $fieldHash->{$fieldTitle}->{relation};
2159                    if ($relation eq $entityName) {
2160                        Confess("Cannot do InsertValue on primary field $fieldTitle of $entityName.");
2161                    } else {
2162                        # Now we can create an INSERT statement.
2163                        my $dbh = $self->{_dbh};
2164                        my $fixedName = _FixName($fieldTitle);
2165                        my $statement = "INSERT INTO $relation (id, $fixedName) VALUES(?, ?)";
2166                        # Execute the command.
2167                        $dbh->SQL($statement, 0, $entityID, $value);
2168                    }
2169                }
2170            }
2171        } else {
2172            Confess("$fieldName is not a valid field name.");
2173        }
2174    }
2175    
2176  =head3 InsertObject  =head3 InsertObject
2177    
2178  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>
# Line 1560  Line 2189 
2189  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
2190  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
2191    
2192  C<< $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>  C<< $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>
2193    
2194  =over 4  =over 4
2195    
# Line 1752  Line 2381 
2381      };      };
2382      if (!defined $rv) {      if (!defined $rv) {
2383          $retVal->AddMessage($@) if ($@);          $retVal->AddMessage($@) if ($@);
2384          $retVal->AddMessage("Table load failed for $relationName using $fileName.");          $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2385          Trace("Table load failed for $relationName.") if T(1);          Trace("Table load failed for $relationName.") if T(1);
2386      } else {      } else {
2387          # Here we successfully loaded the table.          # Here we successfully loaded the table.
# Line 1760  Line 2389 
2389          my $size = -s $fileName;          my $size = -s $fileName;
2390          Trace("$size bytes loaded into $relationName.") if T(2);          Trace("$size bytes loaded into $relationName.") if T(2);
2391          # If we're rebuilding, we need to create the table indexes.          # If we're rebuilding, we need to create the table indexes.
2392          if ($truncateFlag && ! $dbh->{_preIndex}) {          if ($truncateFlag) {
2393                # Indexes are created here for PostGres. For PostGres, indexes are
2394                # best built at the end. For MySQL, the reverse is true.
2395                if (! $dbh->{_preIndex}) {
2396              eval {              eval {
2397                  $self->CreateIndex($relationName);                  $self->CreateIndex($relationName);
2398              };              };
# Line 1768  Line 2400 
2400                  $retVal->AddMessage($@);                  $retVal->AddMessage($@);
2401              }              }
2402          }          }
2403                # The full-text index (if any) is always built last, even for MySQL.
2404                # First we need to see if this table has a full-text index. Only
2405                # primary relations are allowed that privilege.
2406                if ($self->_IsPrimary($relationName)) {
2407                    # Get the relation's entity/relationship structure.
2408                    my $structure = $self->_GetStructure($relationName);
2409                    # Check for a searchable fields list.
2410                    if (exists $structure->{searchFields}) {
2411                        # Here we know that we need to create a full-text search index.
2412                        # Get an SQL-formatted field name list.
2413                        my $fields = join(", ", $self->_FixNames(@{$structure->{searchFields}}));
2414                        # Create the index.
2415                        $dbh->create_index(tbl => $relationName, idx => "search_idx",
2416                                           flds => $fields, kind => 'fulltext');
2417                    }
2418                }
2419            }
2420      }      }
2421      # Analyze the table to improve performance.      # Analyze the table to improve performance.
2422        Trace("Analyzing and compacting $relationName.") if T(3);
2423      $dbh->vacuum_it($relationName);      $dbh->vacuum_it($relationName);
2424        Trace("$relationName load completed.") if T(3);
2425      # Return the statistics.      # Return the statistics.
2426      return $retVal;      return $retVal;
2427  }  }
2428    
2429  =head3 GenerateEntity  =head3 DropRelation
2430    
2431  C<< my $fieldHash = $erdb->GenerateEntity($id, $type, \%values); >>  C<< $erdb->DropRelation($relationName); >>
2432    
2433  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.  
2434    
2435  =over 4  =over 4
2436    
2437  =item id  =item relationName
   
 ID to assign to the new entity.  
   
 =item type  
   
 Type name for the new entity.  
   
 =item values  
2438    
2439  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
2440    no effect.
2441    
2442  =back  =back
2443    
2444  =cut  =cut
2445    
2446  sub GenerateEntity {  sub DropRelation {
2447      # Get the parameters.      # Get the parameters.
2448      my ($self, $id, $type, $values) = @_;      my ($self, $relationName) = @_;
2449      # Create the return hash.      # Get the database handle.
2450      my $this = { id => $id };      my $dbh = $self->{_dbh};
2451      # Get the metadata structure.      # Drop the relation. The method used here has no effect if the relation
2452      my $metadata = $self->{_metaData};      # does not exist.
2453      # Get this entity's list of fields.      Trace("Invoking DB Kernel to drop $relationName.") if T(3);
2454      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;  
2455  }  }
2456    
2457  =head3 GetEntity  =head3 GetEntity
# Line 1869  Line 2490 
2490      return $retVal;      return $retVal;
2491  }  }
2492    
2493    =head3 GetChoices
2494    
2495    C<< my @values = $erdb->GetChoices($entityName, $fieldName); >>
2496    
2497    Return a list of all the values for the specified field that are represented in the
2498    specified entity.
2499    
2500    Note that if the field is not indexed, then this will be a very slow operation.
2501    
2502    =over 4
2503    
2504    =item entityName
2505    
2506    Name of an entity in the database.
2507    
2508    =item fieldName
2509    
2510    Name of a field belonging to the entity. This is a raw field name without
2511    the standard parenthesized notation used in most calls.
2512    
2513    =item RETURN
2514    
2515    Returns a list of the distinct values for the specified field in the database.
2516    
2517    =back
2518    
2519    =cut
2520    
2521    sub GetChoices {
2522        # Get the parameters.
2523        my ($self, $entityName, $fieldName) = @_;
2524        # Declare the return variable.
2525        my @retVal;
2526        # Get the entity data structure.
2527        my $entityData = $self->_GetStructure($entityName);
2528        # Get the field.
2529        my $fieldHash = $entityData->{Fields};
2530        if (! exists $fieldHash->{$fieldName}) {
2531            Confess("$fieldName not found in $entityName.");
2532        } else {
2533            # Get the name of the relation containing the field.
2534            my $relation = $fieldHash->{$fieldName}->{relation};
2535            # Fix up the field name.
2536            my $realName = _FixName($fieldName);
2537            # Get the database handle.
2538            my $dbh = $self->{_dbh};
2539            # Query the database.
2540            my $results = $dbh->SQL("SELECT DISTINCT $realName FROM $relation");
2541            # Clean the results. They are stored as a list of lists, and we just want the one list.
2542            @retVal = sort map { $_->[0] } @{$results};
2543        }
2544        # Return the result.
2545        return @retVal;
2546    }
2547    
2548  =head3 GetEntityValues  =head3 GetEntityValues
2549    
2550  C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>  C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>
2551    
2552  Return a list of values from a specified entity instance.  Return a list of values from a specified entity instance. If the entity instance
2553    does not exist, an empty list is returned.
2554    
2555  =over 4  =over 4
2556    
# Line 2001  Line 2678 
2678          push @retVal, \@rowData;          push @retVal, \@rowData;
2679          $fetched++;          $fetched++;
2680      }      }
2681        Trace("$fetched rows returned in GetAll.") if T(SQL => 4);
2682      # Return the resulting list.      # Return the resulting list.
2683      return @retVal;      return @retVal;
2684  }  }
2685    
2686    =head3 Exists
2687    
2688    C<< my $found = $sprout->Exists($entityName, $entityID); >>
2689    
2690    Return TRUE if an entity exists, else FALSE.
2691    
2692    =over 4
2693    
2694    =item entityName
2695    
2696    Name of the entity type (e.g. C<Feature>) relevant to the existence check.
2697    
2698    =item entityID
2699    
2700    ID of the entity instance whose existence is to be checked.
2701    
2702    =item RETURN
2703    
2704    Returns TRUE if the entity instance exists, else FALSE.
2705    
2706    =back
2707    
2708    =cut
2709    #: Return Type $;
2710    sub Exists {
2711        # Get the parameters.
2712        my ($self, $entityName, $entityID) = @_;
2713        # Check for the entity instance.
2714        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
2715        my $testInstance = $self->GetEntity($entityName, $entityID);
2716        # Return an existence indicator.
2717        my $retVal = ($testInstance ? 1 : 0);
2718        return $retVal;
2719    }
2720    
2721  =head3 EstimateRowSize  =head3 EstimateRowSize
2722    
2723  C<< my $rowSize = $erdb->EstimateRowSize($relName); >>  C<< my $rowSize = $erdb->EstimateRowSize($relName); >>
# Line 2072  Line 2785 
2785      return $objectData->{Fields};      return $objectData->{Fields};
2786  }  }
2787    
2788    =head3 SplitKeywords
2789    
2790    C<< my @keywords = ERDB::SplitKeywords($keywordString); >>
2791    
2792    This method returns a list of the positive keywords in the specified
2793    keyword string. All of the operators will have been stripped off,
2794    and if the keyword is preceded by a minus operator (C<->), it will
2795    not be in the list returned. The idea here is to get a list of the
2796    keywords the user wants to see. The list will be processed to remove
2797    duplicates.
2798    
2799    It is possible to create a string that confuses this method. For example
2800    
2801        frog toad -frog
2802    
2803    would return both C<frog> and C<toad>. If this is a problem we can deal
2804    with it later.
2805    
2806    =over 4
2807    
2808    =item keywordString
2809    
2810    The keyword string to be parsed.
2811    
2812    =item RETURN
2813    
2814    Returns a list of the words in the keyword string the user wants to
2815    see.
2816    
2817    =back
2818    
2819    =cut
2820    
2821    sub SplitKeywords {
2822        # Get the parameters.
2823        my ($keywordString) = @_;
2824        # Make a safety copy of the string. (This helps during debugging.)
2825        my $workString = $keywordString;
2826        # Convert operators we don't care about to spaces.
2827        $workString =~ tr/+"()<>/ /;
2828        # Split the rest of the string along space boundaries. Note that we
2829        # eliminate any words that are zero length or begin with a minus sign.
2830        my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
2831        # Use a hash to remove duplicates.
2832        my %words = map { $_ => 1 } @wordList;
2833        # Return the result.
2834        return sort keys %words;
2835    }
2836    
2837    =head3 ValidateFieldName
2838    
2839    C<< my $okFlag = ERDB::ValidateFieldName($fieldName); >>
2840    
2841    Return TRUE if the specified field name is valid, else FALSE. Valid field names must
2842    be hyphenated words subject to certain restrictions.
2843    
2844    =over 4
2845    
2846    =item fieldName
2847    
2848    Field name to be validated.
2849    
2850    =item RETURN
2851    
2852    Returns TRUE if the field name is valid, else FALSE.
2853    
2854    =back
2855    
2856    =cut
2857    
2858    sub ValidateFieldName {
2859        # Get the parameters.
2860        my ($fieldName) = @_;
2861        # Declare the return variable. The field name is valid until we hear
2862        # differently.
2863        my $retVal = 1;
2864        # Look for bad stuff in the name.
2865        if ($fieldName =~ /--/) {
2866            # Here we have a doubled minus sign.
2867            Trace("Field name $fieldName has a doubled hyphen.") if T(1);
2868            $retVal = 0;
2869        } elsif ($fieldName !~ /^[A-Za-z]/) {
2870            # Here the field name is missing the initial letter.
2871            Trace("Field name $fieldName does not begin with a letter.") if T(1);
2872            $retVal = 0;
2873        } else {
2874            # Strip out the minus signs. Everything remaining must be a letter,
2875            # underscore, or digit.
2876            my $strippedName = $fieldName;
2877            $strippedName =~ s/-//g;
2878            if ($strippedName !~ /^(\w|\d)+$/) {
2879                Trace("Field name $fieldName contains illegal characters.") if T(1);
2880                $retVal = 0;
2881            }
2882        }
2883        # Return the result.
2884        return $retVal;
2885    }
2886    
2887    =head3 ReadMetaXML
2888    
2889    C<< my $rawMetaData = ERDB::ReadDBD($fileName); >>
2890    
2891    This method reads a raw database definition XML file and returns it.
2892    Normally, the metadata used by the ERDB system has been processed and
2893    modified to make it easier to load and retrieve the data; however,
2894    this method can be used to get the data in its raw form.
2895    
2896    =over 4
2897    
2898    =item fileName
2899    
2900    Name of the XML file to read.
2901    
2902    =item RETURN
2903    
2904    Returns a hash reference containing the raw XML data from the specified file.
2905    
2906    =back
2907    
2908    =cut
2909    
2910    sub ReadMetaXML {
2911        # Get the parameters.
2912        my ($fileName) = @_;
2913        # Read the XML.
2914        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
2915        Trace("XML metadata loaded from file $fileName.") if T(1);
2916        # Return the result.
2917        return $retVal;
2918    }
2919    
2920    =head3 GetEntityFieldHash
2921    
2922    C<< my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName); >>
2923    
2924    Get the field hash of the named entity in the specified raw XML structure.
2925    The field hash may not exist, in which case we need to create it.
2926    
2927    =over 4
2928    
2929    =item structure
2930    
2931    Raw XML structure defininng the database. This is not the run-time XML used by
2932    an ERDB object, since that has all sorts of optimizations built-in.
2933    
2934    =item entityName
2935    
2936    Name of the entity whose field structure is desired.
2937    
2938    =item RETURN
2939    
2940    Returns the field hash used to define the entity's fields.
2941    
2942    =back
2943    
2944    =cut
2945    
2946    sub GetEntityFieldHash {
2947        # Get the parameters.
2948        my ($structure, $entityName) = @_;
2949        # Get the entity structure.
2950        my $entityData = $structure->{Entities}->{$entityName};
2951        # Look for a field structure.
2952        my $retVal = $entityData->{Fields};
2953        # If it doesn't exist, create it.
2954        if (! defined($retVal)) {
2955            $entityData->{Fields} = {};
2956            $retVal = $entityData->{Fields};
2957        }
2958        # Return the result.
2959        return $retVal;
2960    }
2961    
2962    =head3 WriteMetaXML
2963    
2964    C<< ERDB::WriteMetaXML($structure, $fileName); >>
2965    
2966    Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
2967    used to update the database definition. It must be used with care, however, since it
2968    will only work on a raw structure, not on the processed structure created by an ERDB
2969    constructor.
2970    
2971    =over 4
2972    
2973    =item structure
2974    
2975    XML structure to be written to the file.
2976    
2977    =item fileName
2978    
2979    Name of the output file to which the updated XML should be stored.
2980    
2981    =back
2982    
2983    =cut
2984    
2985    sub WriteMetaXML {
2986        # Get the parameters.
2987        my ($structure, $fileName) = @_;
2988        # Compute the output.
2989        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
2990        # Write it to the file.
2991        my $xmlOut = Open(undef, ">$fileName");
2992        print $xmlOut $fileString;
2993    }
2994    
2995    
2996    =head3 HTMLNote
2997    
2998    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
2999    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
3000    Except for C<[p]>, all the codes are closed by slash-codes. So, for
3001    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
3002    
3003    C<< my $realHtml = ERDB::HTMLNote($dataString); >>
3004    
3005    =over 4
3006    
3007    =item dataString
3008    
3009    String to convert to HTML.
3010    
3011    =item RETURN
3012    
3013    An HTML string derived from the input string.
3014    
3015    =back
3016    
3017    =cut
3018    
3019    sub HTMLNote {
3020        # Get the parameter.
3021        my ($dataString) = @_;
3022        # HTML-escape the text.
3023        my $retVal = CGI::escapeHTML($dataString);
3024        # Substitute the bulletin board codes.
3025        $retVal =~ s!\[(/?[bi])\]!<$1>!g;
3026        $retVal =~ s!\[p\]!</p><p>!g;
3027        # Return the result.
3028        return $retVal;
3029    }
3030    
3031    
3032  =head2 Data Mining Methods  =head2 Data Mining Methods
3033    
3034  =head3 GetUsefulCrossValues  =head3 GetUsefulCrossValues
# Line 2195  Line 3152 
3152    
3153  =head3 ParseColumns  =head3 ParseColumns
3154    
3155  C<< my @columns = ERDB->ParseColumns($line); >>  C<< my @columns = ERDB::ParseColumns($line); >>
3156    
3157  Convert the specified data line to a list of columns.  Convert the specified data line to a list of columns.
3158    
# Line 2216  Line 3173 
3173    
3174  sub ParseColumns {  sub ParseColumns {
3175      # Get the parameters.      # Get the parameters.
3176      my ($self, $line) = @_;      my ($line) = @_;
3177      # Chop off the line-end.      # Chop off the line-end.
3178      chomp $line;      chomp $line;
3179      # Split it into a list.      # Split it into a list.
# Line 2225  Line 3182 
3182      return @retVal;      return @retVal;
3183  }  }
3184    
3185    =head2 Virtual Methods
3186    
3187    =head3 CleanKeywords
3188    
3189    C<< my $cleanedString = $erdb->CleanKeywords($searchExpression); >>
3190    
3191    Clean up a search expression or keyword list. This is a virtual method that may
3192    be overridden by the subclass. The base-class method removes extra spaces
3193    and converts everything to lower case.
3194    
3195    =over 4
3196    
3197    =item searchExpression
3198    
3199    Search expression or keyword list to clean. Note that a search expression may
3200    contain boolean operators which need to be preserved. This includes leading
3201    minus signs.
3202    
3203    =item RETURN
3204    
3205    Cleaned expression or keyword list.
3206    
3207    =back
3208    
3209    =cut
3210    
3211    sub CleanKeywords {
3212        # Get the parameters.
3213        my ($self, $searchExpression) = @_;
3214        # Lower-case the expression and copy it into the return variable. Note that we insure we
3215        # don't accidentally end up with an undefined value.
3216        my $retVal = lc($searchExpression || "");
3217        # Remove extra spaces.
3218        $retVal =~ s/\s+/ /g;
3219        $retVal =~ s/(^\s+)|(\s+$)//g;
3220        # Return the result.
3221        return $retVal;
3222    }
3223    
3224    =head3 GetSourceObject
3225    
3226    C<< my $source = $erdb->GetSourceObject($entityName); >>
3227    
3228    Return the object to be used in loading special attributes of the specified entity. The
3229    algorithm for loading special attributes is stored in the C<DataGen> elements of the
3230    XML
3231    
3232  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3233    
3234  =head3 SetupSQL  =head3 _RelationMap
3235    
3236    C<< my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef); >>
3237    
3238    Create the relation map for an SQL query. The relation map is used by B<DBObject>
3239    to determine how to interpret the results of the query.
3240    
3241    =over 4
3242    
3243    =item mappedNameHashRef
3244    
3245    Reference to a hash that maps modified object names to real object names.
3246    
3247    =item mappedNameListRef
3248    
3249    Reference to a list of modified object names in the order they appear in the
3250    SELECT list.
3251    
3252    =item RETURN
3253    
3254    Returns a list of 2-tuples. Each tuple consists of an object name as used in the
3255    query followed by the actual name of that object. This enables the B<DBObject> to
3256    determine the order of the tables in the query and which object name belongs to each
3257    mapped object name. Most of the time these two values are the same; however, if a
3258    relation occurs twice in the query, the relation name in the field list and WHERE
3259    clause will use a mapped name (generally the actual relation name with a numeric
3260    suffix) that does not match the actual relation name.
3261    
3262    =back
3263    
3264    =cut
3265    
3266    sub _RelationMap {
3267        # Get the parameters.
3268        my ($mappedNameHashRef, $mappedNameListRef) = @_;
3269        # Declare the return variable.
3270        my @retVal = ();
3271        # Build the map.
3272        for my $mappedName (@{$mappedNameListRef}) {
3273            push @retVal, [$mappedName, $mappedNameHashRef->{$mappedName}];
3274        }
3275        # Return it.
3276        return @retVal;
3277    }
3278    
3279    
3280    =head3 _SetupSQL
3281    
3282  Process a list of object names and a filter clause so that they can be used to  Process a list of object names and a filter clause so that they can be used to
3283  build an SQL statement. This method takes in a reference to a list of object names  build an SQL statement. This method takes in a reference to a list of object names
# Line 2247  Line 3297 
3297  A string containing the WHERE clause for the query (without the C<WHERE>) and also  A string containing the WHERE clause for the query (without the C<WHERE>) and also
3298  optionally the C<ORDER BY> and C<LIMIT> clauses.  optionally the C<ORDER BY> and C<LIMIT> clauses.
3299    
3300    =item matchClause
3301    
3302    An optional full-text search clause. If specified, it will be inserted at the
3303    front of the WHERE clause. It should already be SQL-formatted; that is, the
3304    field names should be in the form I<table>C<.>I<fieldName>.
3305    
3306  =item RETURN  =item RETURN
3307    
3308  Returns a three-element list. The first element is the SQL statement suffix, beginning  Returns a three-element list. The first element is the SQL statement suffix, beginning
# Line 2259  Line 3315 
3315  =cut  =cut
3316    
3317  sub _SetupSQL {  sub _SetupSQL {
3318      my ($self, $objectNames, $filterClause) = @_;      my ($self, $objectNames, $filterClause, $matchClause) = @_;
3319      # Adjust the list of object names to account for multiple occurrences of the      # Adjust the list of object names to account for multiple occurrences of the
3320      # 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
3321      # return the object suffix. The first time an object is encountered it will      # return the object suffix. The first time an object is encountered it will
# Line 2308  Line 3364 
3364      # FROM name1, name2, ... nameN      # FROM name1, name2, ... nameN
3365      #      #
3366      my $suffix = "FROM " . join(', ', @fromList);      my $suffix = "FROM " . join(', ', @fromList);
3367        # Now for the WHERE. First, we need a place for the filter string.
3368        my $filterString = "";
3369        # We will also keep a list of conditions to add to the WHERE clause in order to link
3370        # entities and relationships as well as primary relations to secondary ones.
3371        my @joinWhere = ();
3372      # Check for a filter clause.      # Check for a filter clause.
3373      if ($filterClause) {      if ($filterClause) {
3374          # 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,
3375          # We create a copy of the filter string we can work with.          # We create a copy of the filter string we can work with.
3376          my $filterString = $filterClause;          $filterString = $filterClause;
3377          # Next, we sort the object names by length. This helps protect us from finding          # Next, we sort the object names by length. This helps protect us from finding
3378          # object names inside other object names when we're doing our search and replace.          # object names inside other object names when we're doing our search and replace.
3379          my @sortedNames = sort { length($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 = ();  
3380          # 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
3381          # 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
3382          # 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 2386  Line 3444 
3444                  }                  }
3445              }              }
3446          }          }
3447        }
3448          # 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
3449          # 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
3450          # 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
3451          # list before running through it.      # list before running through it, because we shift off the first object before
3452        # processing the rest.
3453          my @mappedObjectList = @mappedNameList;          my @mappedObjectList = @mappedNameList;
3454          my $lastMappedObject = shift @mappedObjectList;          my $lastMappedObject = shift @mappedObjectList;
3455          # Get the join table.          # Get the join table.
# Line 2418  Line 3478 
3478          # 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.
3479          # We'll put the ORDER BY / LIMIT clauses in the following variable.          # We'll put the ORDER BY / LIMIT clauses in the following variable.
3480          my $orderClause = "";          my $orderClause = "";
3481        # This is only necessary if we have a filter string in which the ORDER BY
3482        # and LIMIT clauses can live.
3483        if ($filterString) {
3484          # 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
3485          # operator so that we find the first occurrence of either verb.          # operator so that we find the first occurrence of either verb.
3486          if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {          if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {
# Line 2426  Line 3489 
3489              $orderClause = $2 . substr($filterString, $pos);              $orderClause = $2 . substr($filterString, $pos);
3490              $filterString = $1;              $filterString = $1;
3491          }          }
3492          # Add the filter and the join clauses (if any) to the SELECT command.      }
3493        # All the things that are supposed to be in the WHERE clause of the
3494        # SELECT command need to be put into @joinWhere so we can string them
3495        # together. We begin with the match clause. This is important,
3496        # because the match clause's parameter mark must precede any parameter
3497        # marks in the filter string.
3498        if ($matchClause) {
3499            push @joinWhere, $matchClause;
3500        }
3501        # Add the filter string. We put it in parentheses to avoid operator
3502        # precedence problems with the match clause or the joins.
3503          if ($filterString) {          if ($filterString) {
3504              Trace("Filter string is \"$filterString\".") if T(4);              Trace("Filter string is \"$filterString\".") if T(4);
3505              push @joinWhere, "($filterString)";              push @joinWhere, "($filterString)";
3506          }          }
3507        # String it all together into a big filter clause.
3508          if (@joinWhere) {          if (@joinWhere) {
3509              $suffix .= " WHERE " . join(' AND ', @joinWhere);              $suffix .= " WHERE " . join(' AND ', @joinWhere);
3510          }          }
3511          # Add the sort or limit clause (if any) to the SELECT command.      # Add the sort or limit clause (if any).
3512          if ($orderClause) {          if ($orderClause) {
3513              $suffix .= " $orderClause";              $suffix .= " $orderClause";
3514          }          }
     }  
3515      # Return the suffix, the mapped name list, and the mapped name hash.      # Return the suffix, the mapped name list, and the mapped name hash.
3516      return ($suffix, \@mappedNameList, \%mappedNameHash);      return ($suffix, \@mappedNameList, \%mappedNameHash);
3517  }  }
3518    
3519  =head3 GetStatementHandle  =head3 _GetStatementHandle
3520    
3521  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.
3522  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 2481  Line 3554 
3554      # Prepare the command.      # Prepare the command.
3555      my $sth = $dbh->prepare_command($command);      my $sth = $dbh->prepare_command($command);
3556      # Execute it with the parameters bound in.      # Execute it with the parameters bound in.
3557      $sth->execute(@{$params}) || Confess("SELECT error" . $sth->errstr());      $sth->execute(@{$params}) || Confess("SELECT error:  " . $sth->errstr());
3558      # Return the statement handle.      # Return the statement handle.
3559      return $sth;      return $sth;
3560  }  }
3561    
3562  =head3 GetLoadStats  =head3 _GetLoadStats
3563    
3564  Return a blank statistics object for use by the load methods.  Return a blank statistics object for use by the load methods.
3565    
# Line 2495  Line 3568 
3568  =cut  =cut
3569    
3570  sub _GetLoadStats{  sub _GetLoadStats{
3571      return Stats->new();      return Stats->new();
 }  
   
 =head3 GenerateFields  
   
 Generate field values from a field structure and store in a specified table. The field names  
 are first sorted by pass count, certain pre-defined fields are removed from the list, and  
 then we rip through them evaluation the data generation string. Fields in the primary relation  
 are stored as scalars; fields in secondary relations are stored as value lists.  
   
 This is a static method.  
   
 =over 4  
   
 =item this  
   
 Hash table into which the field values should be placed.  
   
 =item fields  
   
 Field structure from which the field descriptors should be taken.  
   
 =item type  
   
 Type name of the object whose fields are being generated.  
   
 =item values (optional)  
   
 Reference to a value structure from which additional values can be taken.  
   
 =item from (optiona)  
   
 Reference to the source entity instance if relationship data is being generated.  
   
 =item to (optional)  
   
 Reference to the target entity instance if relationship data is being generated.  
   
 =back  
   
 =cut  
   
 sub _GenerateFields {  
     # Get the parameters.  
     my ($this, $fields, $type, $values, $from, $to) = @_;  
     # Sort the field names by pass number.  
     my @fieldNames = sort { $fields->{$a}->{DataGen}->{pass} <=> $fields->{$b}->{DataGen}->{pass} } keys %{$fields};  
     # Loop through the field names, generating data.  
     for my $name (@fieldNames) {  
         # Only proceed if this field needs to be generated.  
         if (!exists $this->{$name}) {  
             # Get this field's data generation descriptor.  
             my $fieldDescriptor = $fields->{$name};  
             my $data = $fieldDescriptor->{DataGen};  
             # Get the code to generate the field value.  
             my $codeString = $data->{content};  
             # Determine whether or not this field is in the primary relation.  
             if ($fieldDescriptor->{relation} eq $type) {  
                 # Here we have a primary relation field. Store the field value as  
                 # a scalar.  
                 $this->{$name} = eval($codeString);  
             } else {  
                 # Here we have a secondary relation field. Create a null list  
                 # and push the desired number of field values onto it.  
                 my @fieldValues = ();  
                 my $count = IntGen(0,$data->{testCount});  
                 for (my $i = 0; $i < $count; $i++) {  
                     my $newValue = eval($codeString);  
                     push @fieldValues, $newValue;  
                 }  
                 # Store the value list in the main hash.  
                 $this->{$name} = \@fieldValues;  
             }  
         }  
     }  
3572  }  }
3573    
3574  =head3 DumpRelation  =head3 _DumpRelation
3575    
3576  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.
3577    
3578  This is an instance method.  This is an instance method.
3579    
# Line 2622  Line 3621 
3621      close DTXOUT;      close DTXOUT;
3622  }  }
3623    
3624  =head3 GetStructure  =head3 _GetStructure
3625    
3626  Get the data structure for a specified entity or relationship.  Get the data structure for a specified entity or relationship.
3627    
# Line 2661  Line 3660 
3660      return $retVal;      return $retVal;
3661  }  }
3662    
3663  =head3 GetRelationTable  
3664    
3665    =head3 _GetRelationTable
3666    
3667  Get the list of relations for a specified entity or relationship.  Get the list of relations for a specified entity or relationship.
3668    
# Line 2690  Line 3691 
3691      return $objectData->{Relations};      return $objectData->{Relations};
3692  }  }
3693    
3694  =head3 ValidateFieldNames  =head3 _ValidateFieldNames
3695    
3696  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
3697  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 2717  Line 3718 
3718          for my $object (values %{$metadata->{$section}}) {          for my $object (values %{$metadata->{$section}}) {
3719              # Loop through the object's fields.              # Loop through the object's fields.
3720              for my $fieldName (keys %{$object->{Fields}}) {              for my $fieldName (keys %{$object->{Fields}}) {
3721                  # Now we make some initial validations.                  # If this field name is invalid, set the return value to zero
3722                  if ($fieldName =~ /--/) {                  # so we know we encountered an error.
3723                      # Here we have a doubled minus sign.                  if (! ValidateFieldName($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";  
3724                          $retVal = 0;                          $retVal = 0;
3725                      }                      }
3726                  }                  }
3727              }              }
3728          }          }
     }  
3729      # If an error was found, fail.      # If an error was found, fail.
3730      if ($retVal  == 0) {      if ($retVal  == 0) {
3731          Confess("Errors found in field names.");          Confess("Errors found in field names.");
3732      }      }
3733  }  }
3734    
3735  =head3 LoadRelation  =head3 _LoadRelation
3736    
3737  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
3738  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 2805  Line 3792 
3792      return $retVal;      return $retVal;
3793  }  }
3794    
3795  =head3 LoadMetaData  
3796    =head3 _LoadMetaData
3797    
3798  This method loads the data describing this database from an XML file into a metadata structure.  This method loads the data describing this database from an XML file into a metadata structure.
3799  The resulting structure is a set of nested hash tables containing all the information needed to  The resulting structure is a set of nested hash tables containing all the information needed to
# Line 2830  Line 3818 
3818  sub _LoadMetaData {  sub _LoadMetaData {
3819      # Get the parameters.      # Get the parameters.
3820      my ($filename) = @_;      my ($filename) = @_;
3821      Trace("Reading Sprout DBD from $filename.") if T(2);      Trace("Reading DBD from $filename.") if T(2);
3822      # 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
3823      # get the exact structure we want.      # get the exact structure we want.
3824      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 $filename.") if T(1);  
3825      # Before we go any farther, we need to validate the field and object names. If an error is found,      # Before we go any farther, we need to validate the field and object names. If an error is found,
3826      # the method below will fail.      # the method below will fail.
3827      _ValidateFieldNames($metadata);      _ValidateFieldNames($metadata);
# Line 2976  Line 3951 
3951              my $count = 0;              my $count = 0;
3952              for my $index (@{$indexList}) {              for my $index (@{$indexList}) {
3953                  # Add this index to the index table.                  # Add this index to the index table.
3954                  _AddIndex("idx$relationName$count", $relation, $index);                  _AddIndex("idx$count", $relation, $index);
3955                  # Increment the counter so that the next index has a different name.                  # Increment the counter so that the next index has a different name.
3956                  $count++;                  $count++;
3957              }              }
# Line 3132  Line 4107 
4107      return $metadata;      return $metadata;
4108  }  }
4109    
4110  =head3 SortNeeded  =head3 _CreateRelationshipIndex
   
 C<< my $flag = $erdb->SortNeeded($relationName); >>  
   
 Return TRUE if the specified relation should be sorted during loading to remove duplicate keys,  
 else FALSE.  
   
 =over 4  
   
 =item relationName  
   
 Name of the relation to be examined.  
   
 =item RETURN  
   
 Returns TRUE if the relation needs a sort, else FALSE.  
   
 =back  
   
 =cut  
 #: Return Type $;  
 sub SortNeeded {  
     # Get the parameters.  
     my ($self, $relationName) = @_;  
     # Declare the return variable.  
     my $retVal = 0;  
     # Find out if the relation is a primary entity relation.  
     my $entityTable = $self->{_metaData}->{Entities};  
     if (exists $entityTable->{$relationName}) {  
         my $keyType = $entityTable->{$relationName}->{keyType};  
         Trace("Relation $relationName found in entity table with key type $keyType.") if T(3);  
         # If the key is not a hash string, we must do the sort.  
         if ($keyType ne 'hash-string') {  
             $retVal = 1;  
         }  
     }  
     # Return the result.  
     return $retVal;  
 }  
   
 =head3 CreateRelationshipIndex  
4111    
4112  Create an index for a relationship's relation.  Create an index for a relationship's relation.
4113    
# Line 3214  Line 4149 
4149          $newIndex->{Unique} = 'true';          $newIndex->{Unique} = 'true';
4150      }      }
4151      # Add the index to the relation.      # Add the index to the relation.
4152      _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);      _AddIndex("idx$indexKey", $relationStructure, $newIndex);
4153  }  }
4154    
4155  =head3 AddIndex  =head3 _AddIndex
4156    
4157  Add an index to a relation structure.  Add an index to a relation structure.
4158    
# Line 3263  Line 4198 
4198      $relationStructure->{Indexes}->{$indexName} = $newIndex;      $relationStructure->{Indexes}->{$indexName} = $newIndex;
4199  }  }
4200    
4201  =head3 FixupFields  =head3 _FixupFields
4202    
4203  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
4204  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 3301  Line 4236 
4236          # Here it doesn't, so we create a new one.          # Here it doesn't, so we create a new one.
4237          $structure->{Fields} = { };          $structure->{Fields} = { };
4238      } else {      } else {
4239          # 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
4240            # create a list for stashing them.
4241            my @textFields = ();
4242            # Loop through the fields.
4243          my $fieldStructures = $structure->{Fields};          my $fieldStructures = $structure->{Fields};
4244          for my $fieldName (keys %{$fieldStructures}) {          for my $fieldName (keys %{$fieldStructures}) {
4245              Trace("Processing field $fieldName of $defaultRelationName.") if T(4);              Trace("Processing field $fieldName of $defaultRelationName.") if T(4);
# Line 3310  Line 4248 
4248              my $type = $fieldData->{type};              my $type = $fieldData->{type};
4249              # Plug in a relation name if it is needed.              # Plug in a relation name if it is needed.
4250              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });
4251              # Plug in a data generator if we need one.              # Check for searchability.
4252              if (!exists $fieldData->{DataGen}) {              if ($fieldData->{searchable}) {
4253                  # The data generator will use the default for the field's type.                  # Only allow this for a primary relation.
4254                  $fieldData->{DataGen} = { content => $TypeTable{$type}->{dataGen} };                  if ($fieldData->{relation} ne $defaultRelationName) {
4255                        Confess("Field $fieldName of $defaultRelationName is in secondary relations and cannot be searchable.");
4256                    } else {
4257                        push @textFields, $fieldName;
4258                    }
4259              }              }
             # Plug in the defaults for the optional data generation parameters.  
             Tracer::MergeOptions($fieldData->{DataGen}, { testCount => 1, pass => 0 });  
4260              # Add the PrettySortValue.              # Add the PrettySortValue.
4261              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);
4262          }          }
4263            # If there are searchable fields, remember the fact.
4264            if (@textFields) {
4265                $structure->{searchFields} = \@textFields;
4266            }
4267      }      }
4268  }  }
4269    
4270  =head3 FixName  =head3 _FixName
4271    
4272  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.
4273    
# Line 3352  Line 4296 
4296      return $fieldName;      return $fieldName;
4297  }  }
4298    
4299  =head3 FixNames  =head3 _FixNames
4300    
4301  Fix all the field names in a list.  Fix all the field names in a list.
4302    
# Line 3383  Line 4327 
4327      return @result;      return @result;
4328  }  }
4329    
4330  =head3 AddField  =head3 _AddField
4331    
4332  Add a field to a field list.  Add a field to a field list.
4333    
# Line 3418  Line 4362 
4362      $fieldList->{$fieldName} = $fieldStructure;      $fieldList->{$fieldName} = $fieldStructure;
4363  }  }
4364    
4365  =head3 ReOrderRelationTable  =head3 _ReOrderRelationTable
4366    
4367  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
4368  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 3479  Line 4423 
4423    
4424  }  }
4425    
4426  =head3 IsPrimary  =head3 _IsPrimary
4427    
4428  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
4429  if it has the same name as an entity or relationship.  if it has the same name as an entity or relationship.
# Line 3515  Line 4459 
4459      return $retVal;      return $retVal;
4460  }  }
4461    
4462  =head3 FindRelation  =head3 _FindRelation
4463    
4464  Return the descriptor for the specified relation.  Return the descriptor for the specified relation.
4465    
# Line 3546  Line 4490 
4490    
4491  =head2 HTML Documentation Utility Methods  =head2 HTML Documentation Utility Methods
4492    
4493  =head3 ComputeRelationshipSentence  =head3 _ComputeRelationshipSentence
4494    
4495  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
4496  two related entities and an arity indicator.  two related entities and an arity indicator.
# Line 3584  Line 4528 
4528      return $result;      return $result;
4529  }  }
4530    
4531  =head3 ComputeRelationshipHeading  =head3 _ComputeRelationshipHeading
4532    
4533  The relationship heading is the L<relationship sentence|/ComputeRelationshipSentence> with the entity  The relationship heading is the L<relationship sentence|/ComputeRelationshipSentence> with the entity
4534  names hyperlinked to the appropriate entity sections of the document.  names hyperlinked to the appropriate entity sections of the document.
# Line 3621  Line 4565 
4565      return $result;      return $result;
4566  }  }
4567    
4568  =head3 ShowRelationTable  =head3 _ShowRelationTable
4569    
4570  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
4571  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 3671  Line 4615 
4615          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";
4616          # Add any note text.          # Add any note text.
4617          if (my $note = $indexData->{Notes}) {          if (my $note = $indexData->{Notes}) {
4618              $htmlString .= "<li>" . _HTMLNote($note->{content}) . "</li>\n";              $htmlString .= "<li>" . HTMLNote($note->{content}) . "</li>\n";
4619          }          }
4620          # Add the fiield list.          # Add the fiield list.
4621          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";
# Line 3682  Line 4626 
4626      $htmlString .= "</ul>\n";      $htmlString .= "</ul>\n";
4627  }  }
4628    
4629  =head3 OpenFieldTable  =head3 _OpenFieldTable
4630    
4631  This method creates the header string for the field table generated by L</ShowMetaData>.  This method creates the header string for the field table generated by L</ShowMetaData>.
4632    
# Line 3707  Line 4651 
4651      return _OpenTable($tablename, 'Field', 'Type', 'Description');      return _OpenTable($tablename, 'Field', 'Type', 'Description');
4652  }  }
4653    
4654  =head3 OpenTable  =head3 _OpenTable
4655    
4656  This method creates the header string for an HTML table.  This method creates the header string for an HTML table.
4657    
# Line 3747  Line 4691 
4691      return $htmlString;      return $htmlString;
4692  }  }
4693    
4694  =head3 CloseTable  =head3 _CloseTable
4695    
4696  This method returns the HTML for closing a table.  This method returns the HTML for closing a table.
4697    
# Line 3759  Line 4703 
4703      return "</table></p>\n";      return "</table></p>\n";
4704  }  }
4705    
4706  =head3 ShowField  =head3 _ShowField
4707    
4708  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.
4709    
# Line 3786  Line 4730 
4730      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>";
4731      # If we have content, add it as a third column.      # If we have content, add it as a third column.
4732      if (exists $fieldData->{Notes}) {      if (exists $fieldData->{Notes}) {
4733          $htmlString .= "<td>" . _HTMLNote($fieldData->{Notes}->{content}) . "</td>";          $htmlString .= "<td>" . HTMLNote($fieldData->{Notes}->{content}) . "</td>";
4734      }      }
4735      # Close off the row.      # Close off the row.
4736      $htmlString .= "</tr>\n";      $htmlString .= "</tr>\n";
# Line 3794  Line 4738 
4738      return $htmlString;      return $htmlString;
4739  }  }
4740    
 =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;  
 }  
   
4741  1;  1;

Legend:
Removed from v.1.48  
changed lines
  Added in v.1.77

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3