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

Diff of /Sprout/ERDB.pm

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

revision 1.70, Fri Oct 13 21:45:11 2006 UTC revision 1.82, Tue Jan 9 01:49:57 2007 UTC
# Line 11  Line 11 
11      use Time::HiRes qw(gettimeofday);      use Time::HiRes qw(gettimeofday);
12      use Digest::MD5 qw(md5_base64);      use Digest::MD5 qw(md5_base64);
13      use FIG;      use FIG;
14        use CGI;
15    
16  =head1 Entity-Relationship Database Package  =head1 Entity-Relationship Database Package
17    
# Line 59  Line 60 
60  B<start-position>, which indicates where in the contig that the sequence begins. This attribute  B<start-position>, which indicates where in the contig that the sequence begins. This attribute
61  is implemented as the C<start_position> field in the C<IsMadeUpOf> relation.  is implemented as the C<start_position> field in the C<IsMadeUpOf> relation.
62    
63  The database itself is described by an XML file using the F<ERDatabase.xsd> schema. In addition to  The database itself is described by an XML file. In addition to all the data required to define
64  all the data required to define the entities, relationships, and attributes, the schema provides  the entities, relationships, and attributes, the schema provides space for notes describing
65  space for notes describing the data and what it means. These notes are used by L</ShowMetaData>  the data and what it means. These notes are used by L</ShowMetaData> to generate documentation
66  to generate documentation for the database.  for the database.
67    
68    Special support is provided for text searching. An entity field can be marked as <em>searchable</em>,
69    in which case it will be used to generate a text search index in which the user searches for words
70    in the field instead of a particular field value.
71    
72  Finally, every entity and relationship object has a flag indicating if it is new or old. The object  Finally, every entity and relationship object has a flag indicating if it is new or old. The object
73  is considered I<old> if it was loaded by the L</LoadTables> method. It is considered I<new> if it  is considered I<old> if it was loaded by the L</LoadTables> method. It is considered I<new> if it
74  was inserted by the L</InsertObject> method.  was inserted by the L</InsertObject> method.
75    
 To facilitate testing, the ERDB module supports automatic generation of test data. This process  
 is described in the L</GenerateEntity> and L</GenerateConnection> methods, though it is not yet  
 fully implemented.  
   
76  =head2 XML Database Description  =head2 XML Database Description
77    
78  =head3 Data Types  =head3 Data Types
# Line 217  Line 218 
218  index will be created for each relation with at least one searchable field in it.  index will be created for each relation with at least one searchable field in it.
219  For best results, this option should only be used for string or text fields.  For best results, this option should only be used for string or text fields.
220    
221    =item special
222    
223    This attribute allows the subclass to assign special meaning for certain fields.
224    The interpretation is up to the subclass itself. Currently, only entity fields
225    can have this attribute.
226    
227  =back  =back
228    
229  =head3 Indexes  =head3 Indexes
230    
231  An entity can have multiple alternate indexes associated with it. The fields must  An entity can have multiple alternate indexes associated with it. The fields must
232  be from the primary relation. The alternate indexes assist in ordering results  all be from the same relation. The alternate indexes assist in ordering results
233  from a query. A relationship can have up to two indexes-- a I<to-index> and a  from a query. A relationship can have up to two indexes-- a I<to-index> and a
234  I<from-index>. These order the results when crossing the relationship. For  I<from-index>. These order the results when crossing the relationship. For
235  example, in the relationship C<HasContig> from C<Genome> to C<Contig>, the  example, in the relationship C<HasContig> from C<Genome> to C<Contig>, the
# Line 250  Line 257 
257    
258  =back  =back
259    
260  The B<Index>, B<FromIndex>, and B<ToIndex> tags themselves have no attributes.  The B<FromIndex>, and B<ToIndex> tags have no attributes. The B<Index> tag can
261    have a B<Unique> attribute. If specified, the index will be generated as a unique
262    index.
263    
264  =head3 Object and Field Names  =head3 Object and Field Names
265    
# Line 328  Line 337 
337    
338  # Table of information about our datatypes. "sqlType" is the corresponding SQL datatype string.  # Table of information about our datatypes. "sqlType" is the corresponding SQL datatype string.
339  # "maxLen" is the maximum permissible length of the incoming string data used to populate a field  # "maxLen" is the maximum permissible length of the incoming string data used to populate a field
340  # of the specified type. "dataGen" is PERL string that will be evaluated if no test data generation  # of the specified type. "avgLen" is the average byte length for estimating
341  # string is specified in the field definition. "avgLen" is the average byte length for estimating  # record sizes. "sort" is the key modifier for the sort command, "notes" is a type description,
342  # record sizes. "sort" is the key modifier for the sort command.  # and "indexMod", if non-zero, is the number of characters to use when the field is specified in an
343  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",  dataGen => "StringGen('A')" },  # index
344                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n", dataGen => "IntGen(0, 99999999)" },  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",
345                    counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n", dataGen => "IntGen(0, 99999999)" },                                 indexMod =>   0, notes => "single ASCII character"},
346                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, sort => "",  dataGen => "StringGen(IntGen(10,250))" },                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n",
347                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, sort => "",  dataGen => "StringGen(IntGen(80,1000))" },                                 indexMod =>   0, notes => "signed 32-bit integer"},
348                    date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, sort => "n", dataGen => "DateGen(-7, 7, IntGen(0,1400))" },                    counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n",
349                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, sort => "g", dataGen => "FloatGen(0.0, 100.0)" },                                 indexMod =>   0, notes => "unsigned 32-bit integer"},
350                    boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, sort => "n", dataGen => "IntGen(0, 1)" },                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, sort => "",
351                                   indexMod =>   0, notes => "character string, 0 to 255 characters"},
352                      text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, sort => "",
353                                   indexMod => 255, notes => "character string, nearly unlimited length, only first 255 characters are indexed"},
354                      date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, sort => "n",
355                                   indexMod =>   0, notes => "signed, 64-bit integer"},
356                      float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, sort => "g",
357                                   indexMod =>   0, notes => "64-bit double precision floating-point number"},
358                      boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, sort => "n",
359                                   indexMod =>   0, notes => "boolean value: 0 if false, 1 if true"},
360                   'hash-string' =>                   'hash-string' =>
361                               { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, sort => "",  dataGen => "SringGen(22)" },                               { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, sort => "",
362                                   indexMod =>   0, notes => "string stored in digested form, used for certain types of key fields"},
363                   'id-string' =>                   'id-string' =>
364                               { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, sort => "",  dataGen => "SringGen(22)" },                               { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, sort => "",
365                                   indexMod =>   0, notes => "character string, 0 to 25 characters"},
366                   'key-string' =>                   'key-string' =>
367                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, sort => "",  dataGen => "StringGen(IntGen(10,40))" },                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, sort => "",
368                                   indexMod =>   0, notes => "character string, 0 to 40 characters"},
369                   'name-string' =>                   'name-string' =>
370                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, sort => "",  dataGen => "StringGen(IntGen(10,80))" },                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, sort => "",
371                                   indexMod =>   0, notes => "character string, 0 to 80 characters"},
372                   'medium-string' =>                   'medium-string' =>
373                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",  dataGen => "StringGen(IntGen(10,160))" },                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",
374                                   indexMod =>   0, notes => "character string, 0 to 160 characters"},
375                  );                  );
376    
377  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 357  Line 380 
380                     'MM' => 'many-to-many'                     'MM' => 'many-to-many'
381                   );                   );
382    
383  # Table for interpreting string patterns.  # Options for XML input and output.
384    
385    my %XmlOptions = (GroupTags =>  { Relationships => 'Relationship',
386                                      Entities => 'Entity',
387                                      Fields => 'Field',
388                                      Indexes => 'Index',
389                                      IndexFields => 'IndexField'
390                                    },
391                      KeyAttr =>    { Relationship => 'name',
392                                      Entity => 'name',
393                                      Field => 'name'
394                                    },
395                      SuppressEmpty => 1,
396                     );
397    
398  my %PictureTable = ( 'A' => "abcdefghijklmnopqrstuvwxyz",  my %XmlInOpts  = (
399                       '9' => "0123456789",                    ForceArray => ['Field', 'Index', 'IndexField', 'Relationship', 'Entity'],
400                       'X' => "abcdefghijklmnopqrstuvwxyz0123456789",                    ForceContent => 1,
401                       'V' => "aeiou",                    NormalizeSpace => 2,
402                       'K' => "bcdfghjklmnoprstvwxyz"                   );
403    my %XmlOutOpts = (
404                      RootName => 'Database',
405                      XMLDecl => 1,
406                     );                     );
407    
408    
409  =head2 Public Methods  =head2 Public Methods
410    
411  =head3 new  =head3 new
# Line 506  Line 546 
546          my $entityData = $entityList->{$key};          my $entityData = $entityList->{$key};
547          # If there's descriptive text, display it.          # If there's descriptive text, display it.
548          if (my $notes = $entityData->{Notes}) {          if (my $notes = $entityData->{Notes}) {
549              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
550          }          }
551          # Now we want a list of the entity's relationships. First, we set up the relationship subsection.          # Now we want a list of the entity's relationships. First, we set up the relationship subsection.
552          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
# Line 563  Line 603 
603          $retVal .= "</p>\n";          $retVal .= "</p>\n";
604          # If there are notes on this relationship, display them.          # If there are notes on this relationship, display them.
605          if (my $notes = $relationshipStructure->{Notes}) {          if (my $notes = $relationshipStructure->{Notes}) {
606              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
607          }          }
608          # Generate the relationship's relation table.          # Generate the relationship's relation table.
609          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
# Line 610  Line 650 
650      return Data::Dumper::Dumper($self->{_metaData});      return Data::Dumper::Dumper($self->{_metaData});
651  }  }
652    
653    =head3 FindIndexForEntity
654    
655    C<< my $indexFound = ERDB::FindIndexForEntity($xml, $entityName, $attributeName); >>
656    
657    This method locates the entry in an entity's index list that begins with the
658    specified attribute name. If the entity has no index list, one will be
659    created. This method works on raw XML, not a live ERDB object.
660    
661    =over 4
662    
663    =item xml
664    
665    The raw XML structure defining the database.
666    
667    =item entityName
668    
669    The name of the relevant entity.
670    
671    =item attributeName
672    
673    The name of the attribute relevant to the search.
674    
675    =item RETURN
676    
677    The numerical index in the index list of the index entry for the specified entity and
678    attribute, or C<undef> if no such index exists.
679    
680    =back
681    
682    =cut
683    
684    sub FindIndexForEntity {
685        # Get the parameters.
686        my ($xml, $entityName, $attributeName) = @_;
687        # Declare the return variable.
688        my $retVal;
689        # Get the named entity.
690        my $entityData = $xml->{Entities}->{$entityName};
691        if (! $entityData) {
692            Confess("Entity $entityName not found in DBD structure.");
693        } else {
694            # Insure it has an index list.
695            if (! exists $entityData->{Indexes}) {
696                $entityData->{Indexes} = [];
697            } else {
698                # Search for the desired index.
699                my $indexList = $entityData->{Indexes};
700                my $n = scalar @{$indexList};
701                Trace("Searching $n indexes in index list for $entityName.") if T(2);
702                # We use an indexed FOR here because we're returning an
703                # index number instead of an object. We do THAT so we can
704                # delete the index from the list if needed.
705                for (my $i = 0; $i < $n && !defined($retVal); $i++) {
706                    my $index = $indexList->[$i];
707                    my $fields = $index->{IndexFields};
708                    # Technically this IF should be safe (that is, we are guaranteed
709                    # the existence of a "$fields->[0]"), because when we load the XML
710                    # we have SuppressEmpty specified.
711                    if ($fields->[0]->{name} eq $attributeName) {
712                        $retVal = $i;
713                    }
714                }
715            }
716        }
717        Trace("Index for $attributeName of $entityName found at position $retVal.") if defined($retVal) && T(3);
718        Trace("Index for $attributeName not found in $entityName.") if !defined($retVal) && T(3);
719        # Return the result.
720        return $retVal;
721    }
722    
723  =head3 CreateTables  =head3 CreateTables
724    
725  C<< $erdb->CreateTables(); >>  C<< $erdb->CreateTables(); >>
# Line 855  Line 965 
965      for my $indexName (keys %{$indexHash}) {      for my $indexName (keys %{$indexHash}) {
966          my $indexData = $indexHash->{$indexName};          my $indexData = $indexHash->{$indexName};
967          # Get the index's field list.          # Get the index's field list.
968          my @fieldList = _FixNames(@{$indexData->{IndexFields}});          my @rawFields = @{$indexData->{IndexFields}};
969            # Get a hash of the relation's field types.
970            my %types = map { $_->{name} => $_->{type} } @{$relationData->{Fields}};
971            # We need to check for text fields so we can append a length limitation for them. To do
972            # that, we need the relation's field list.
973            my $relFields = $relationData->{Fields};
974            for (my $i = 0; $i <= $#rawFields; $i++) {
975                # Get the field type.
976                my $field = $rawFields[$i];
977                my $type = $types{$field};
978                # Ask if it requires using prefix notation for the index.
979                my $mod = $TypeTable{$type}->{indexMod};
980                Trace("Field $field ($i) in $relationName has type $type and indexMod $mod.") if T(3);
981                if ($mod) {
982                    # Append the prefix length to the field name,
983                    $rawFields[$i] .= "($mod)";
984                }
985            }
986            my @fieldList = _FixNames(@rawFields);
987          my $flds = join(', ', @fieldList);          my $flds = join(', ', @fieldList);
988          # Get the index's uniqueness flag.          # Get the index's uniqueness flag.
989          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
# Line 870  Line 998 
998      }      }
999  }  }
1000    
1001    =head3 GetSecondaryFields
1002    
1003    C<< my %fieldTuples = $erdb->GetSecondaryFields($entityName); >>
1004    
1005    This method will return a list of the name and type of each of the secondary
1006    fields for a specified entity. Secondary fields are stored in two-column tables
1007    in addition to the primary entity table. This enables the field to have no value
1008    or to have multiple values.
1009    
1010    =over 4
1011    
1012    =item entityName
1013    
1014    Name of the entity whose secondary fields are desired.
1015    
1016    =item RETURN
1017    
1018    Returns a hash mapping the field names to their field types.
1019    
1020    =back
1021    
1022    =cut
1023    
1024    sub GetSecondaryFields {
1025        # Get the parameters.
1026        my ($self, $entityName) = @_;
1027        # Declare the return variable.
1028        my %retVal = ();
1029        # Look for the entity.
1030        my $table = $self->GetFieldTable($entityName);
1031        # Loop through the fields, pulling out the secondaries.
1032        for my $field (sort keys %{$table}) {
1033            if ($table->{$field}->{relation} ne $entityName) {
1034                # Here we have a secondary field.
1035                $retVal{$field} = $table->{$field}->{type};
1036            }
1037        }
1038        # Return the result.
1039        return %retVal;
1040    }
1041    
1042    =head3 GetFieldRelationName
1043    
1044    C<< my $name = $erdb->GetFieldRelationName($objectName, $fieldName); >>
1045    
1046    Return the name of the relation containing a specified field.
1047    
1048    =over 4
1049    
1050    =item objectName
1051    
1052    Name of the entity or relationship containing the field.
1053    
1054    =item fieldName
1055    
1056    Name of the relevant field in that entity or relationship.
1057    
1058    =item RETURN
1059    
1060    Returns the name of the database relation containing the field, or C<undef> if
1061    the field does not exist.
1062    
1063    =back
1064    
1065    =cut
1066    
1067    sub GetFieldRelationName {
1068        # Get the parameters.
1069        my ($self, $objectName, $fieldName) = @_;
1070        # Declare the return variable.
1071        my $retVal;
1072        # Get the object field table.
1073        my $table = $self->GetFieldTable($objectName);
1074        # Only proceed if the field exists.
1075        if (exists $table->{$fieldName}) {
1076            # Determine the name of the relation that contains this field.
1077            $retVal = $table->{$fieldName}->{relation};
1078        }
1079        # Return the result.
1080        return $retVal;
1081    }
1082    
1083    =head3 DeleteValue
1084    
1085    C<< my $numDeleted = $erdb->DeleteValue($entityName, $id, $fieldName, $fieldValue); >>
1086    
1087    Delete secondary field values from the database. This method can be used to delete all
1088    values of a specified field for a particular entity instance, or only a single value.
1089    
1090    Secondary fields are stored in two-column relations separate from an entity's primary
1091    table, and as a result a secondary field can legitimately have no value or multiple
1092    values. Therefore, it makes sense to talk about deleting secondary fields where it
1093    would not make sense for primary fields.
1094    
1095    =over 4
1096    
1097    =item entityName
1098    
1099    Name of the entity from which the fields are to be deleted.
1100    
1101    =item id
1102    
1103    ID of the entity instance to be processed. If the instance is not found, this
1104    method will have no effect. If C<undef> is specified, all values for all of
1105    the entity instances will be deleted.
1106    
1107    =item fieldName
1108    
1109    Name of the field whose values are to be deleted.
1110    
1111    =item fieldValue (optional)
1112    
1113    Value to be deleted. If not specified, then all values of the specified field
1114    will be deleted for the entity instance. If specified, then only the values which
1115    match this parameter will be deleted.
1116    
1117    =item RETURN
1118    
1119    Returns the number of rows deleted.
1120    
1121    =back
1122    
1123    =cut
1124    
1125    sub DeleteValue {
1126        # Get the parameters.
1127        my ($self, $entityName, $id, $fieldName, $fieldValue) = @_;
1128        # Declare the return value.
1129        my $retVal = 0;
1130        # We need to set up an SQL command to do the deletion. First, we
1131        # find the name of the field's relation.
1132        my $table = $self->GetFieldTable($entityName);
1133        my $field = $table->{$fieldName};
1134        my $relation = $field->{relation};
1135        # Make sure this is a secondary field.
1136        if ($relation eq $entityName) {
1137            Confess("Cannot delete values of $fieldName for $entityName.");
1138        } else {
1139            # Set up the SQL command to delete all values.
1140            my $sql = "DELETE FROM $relation";
1141            # Build the filter.
1142            my @filters = ();
1143            my @parms = ();
1144            # Check for a filter by ID.
1145            if (defined $id) {
1146                push @filters, "id = ?";
1147                push @parms, $id;
1148            }
1149            # Check for a filter by value.
1150            if (defined $fieldValue) {
1151                push @filters, "$fieldName = ?";
1152                push @parms, $fieldValue;
1153            }
1154            # Append the filters to the command.
1155            if (@filters) {
1156                $sql .= " WHERE " . join(" AND ", @filters);
1157            }
1158            # Execute the command.
1159            my $dbh = $self->{_dbh};
1160            $retVal = $dbh->SQL($sql, 0, @parms);
1161        }
1162        # Return the result.
1163        return $retVal;
1164    }
1165    
1166  =head3 LoadTables  =head3 LoadTables
1167    
1168  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>
# Line 964  Line 1257 
1257      return sort keys %{$entityList};      return sort keys %{$entityList};
1258  }  }
1259    
1260    =head3 GetDataTypes
1261    
1262    C<< my %types = ERDB::GetDataTypes(); >>
1263    
1264    Return a table of ERDB data types. The table returned is a hash of hashes.
1265    The keys of the big hash are the datatypes. Each smaller hash has several
1266    values used to manage the data. The most interesting is the SQL type (key
1267    C<sqlType>) and the descriptive node (key C<notes>).
1268    
1269    Note that changing the values in the smaller hashes will seriously break
1270    things, so this data should be treated as read-only.
1271    
1272    =cut
1273    
1274    sub GetDataTypes {
1275        return %TypeTable;
1276    }
1277    
1278    
1279  =head3 IsEntity  =head3 IsEntity
1280    
1281  C<< my $flag = $erdb->IsEntity($entityName); >>  C<< my $flag = $erdb->IsEntity($entityName); >>
# Line 1108  Line 1420 
1420      return $retVal;      return $retVal;
1421  }  }
1422    
1423    
1424    
1425  =head3 Search  =head3 Search
1426    
1427  C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>  C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>
# Line 1121  Line 1435 
1435    
1436  =item searchExpression  =item searchExpression
1437    
1438  Boolean search expression for the text fields of the target object.  Boolean search expression for the text fields of the target object. The default mode for
1439    a Boolean search expression is OR, but we want the default to be AND, so we will
1440    add a C<+> operator to each word with no other operator before it.
1441    
1442  =item idx  =item idx
1443    
# Line 1158  Line 1474 
1474      my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;      my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1475      # Declare the return variable.      # Declare the return variable.
1476      my $retVal;      my $retVal;
1477      # Create a safety copy of the parameter list.      # Create a safety copy of the parameter list. Note we have to be careful to insure
1478      my @myParams = @{$params};      # a parameter list exists before we copy it.
1479        my @myParams = ();
1480        if (defined $params) {
1481            @myParams = @{$params};
1482        }
1483      # Get the first object's structure so we have access to the searchable fields.      # Get the first object's structure so we have access to the searchable fields.
1484      my $object1Name = $objectNames->[$idx];      my $object1Name = $objectNames->[$idx];
1485      my $object1Structure = $self->_GetStructure($object1Name);      my $object1Structure = $self->_GetStructure($object1Name);
# Line 1169  Line 1489 
1489      } else {      } else {
1490          # Get the field list.          # Get the field list.
1491          my @fields = @{$object1Structure->{searchFields}};          my @fields = @{$object1Structure->{searchFields}};
1492            # Clean the search expression.
1493            my $actualKeywords = $self->CleanKeywords($searchExpression);
1494            # Prefix a "+" to each uncontrolled word. This converts the default
1495            # search mode from OR to AND.
1496            $actualKeywords =~ s/(^|\s)(\w|")/$1\+$2/g;
1497            Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1498          # We need two match expressions, one for the filter clause and one in the          # We need two match expressions, one for the filter clause and one in the
1499          # query itself. Both will use a parameter mark, so we need to push the          # query itself. Both will use a parameter mark, so we need to push the
1500          # search expression onto the front of the parameter list twice.          # search expression onto the front of the parameter list twice.
1501          unshift @myParams, $searchExpression, $searchExpression;          unshift @myParams, $actualKeywords, $actualKeywords;
1502          # Build the match expression.          # Build the match expression.
1503          my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;          my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
1504          my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";          my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
# Line 1246  Line 1572 
1572      return @retVal;      return @retVal;
1573  }  }
1574    
1575    =head3 SpecialFields
1576    
1577    C<< my %specials = $erdb->SpecialFields($entityName); >>
1578    
1579    Return a hash mapping special fields in the specified entity to the value of their
1580    C<special> attribute. This enables the subclass to get access to the special field
1581    attributes without needed to plumb the internal ERDB data structures.
1582    
1583    =over 4
1584    
1585    =item entityName
1586    
1587    Name of the entity whose special fields are desired.
1588    
1589    =item RETURN
1590    
1591    Returns a hash. The keys of the hash are the special field names, and the values
1592    are the values from each special field's C<special> attribute.
1593    
1594    =back
1595    
1596    =cut
1597    
1598    sub SpecialFields {
1599        # Get the parameters.
1600        my ($self, $entityName) = @_;
1601        # Declare the return variable.
1602        my %retVal = ();
1603        # Find the entity's data structure.
1604        my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1605        # Loop through its fields, adding each special field to the return hash.
1606        my $fieldHash = $entityData->{Fields};
1607        for my $fieldName (keys %{$fieldHash}) {
1608            my $fieldData = $fieldHash->{$fieldName};
1609            if (exists $fieldData->{special}) {
1610                $retVal{$fieldName} = $fieldData->{special};
1611            }
1612        }
1613        # Return the result.
1614        return %retVal;
1615    }
1616    
1617  =head3 Delete  =head3 Delete
1618    
1619  C<< my $stats = $erdb->Delete($entityName, $objectID); >>  C<< my $stats = $erdb->Delete($entityName, $objectID, %options); >>
1620    
1621  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
1622  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.
1623  always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many  
1624  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
1625    relationship connected to a dependent entity or if it is the "to" entity connected to a 1-to-many
1626  dependent relationship.  dependent relationship.
1627    
1628  =over 4  =over 4
# Line 1267  Line 1636 
1636  ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),  ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),
1637  then it is presumed to by a LIKE pattern.  then it is presumed to by a LIKE pattern.
1638    
1639  =item testFlag  =item options
1640    
1641  If TRUE, the delete statements will be traced without being executed.  A hash detailing the options for this delete operation.
1642    
1643  =item RETURN  =item RETURN
1644    
# Line 1278  Line 1647 
1647    
1648  =back  =back
1649    
1650    The permissible options for this method are as follows.
1651    
1652    =over 4
1653    
1654    =item testMode
1655    
1656    If TRUE, then the delete statements will be traced, but no changes will be made to the database.
1657    
1658    =item keepRoot
1659    
1660    If TRUE, then the entity instances will not be deleted, only the dependent records.
1661    
1662    =back
1663    
1664  =cut  =cut
1665  #: Return Type $%;  #: Return Type $%;
1666  sub Delete {  sub Delete {
1667      # Get the parameters.      # Get the parameters.
1668      my ($self, $entityName, $objectID, $testFlag) = @_;      my ($self, $entityName, $objectID, %options) = @_;
1669      # Declare the return variable.      # Declare the return variable.
1670      my $retVal = Stats->new();      my $retVal = Stats->new();
1671      # Get the DBKernel object.      # Get the DBKernel object.
# Line 1299  Line 1682 
1682      # FROM-relationships and entities.      # FROM-relationships and entities.
1683      my @fromPathList = ();      my @fromPathList = ();
1684      my @toPathList = ();      my @toPathList = ();
1685      # This final hash is used to remember what work still needs to be done. We push paths      # This final list is used to remember what work still needs to be done. We push paths
1686      # onto the list, then pop them off to extend the paths. We prime it with the starting      # onto the list, then pop them off to extend the paths. We prime it with the starting
1687      # point. Note that we will work hard to insure that the last item on a path in the      # point. Note that we will work hard to insure that the last item on a path in the
1688      # TODO list is always an entity.      # to-do list is always an entity.
1689      my @todoList = ([$entityName]);      my @todoList = ([$entityName]);
1690      while (@todoList) {      while (@todoList) {
1691          # Get the current path.          # Get the current path.
# Line 1310  Line 1693 
1693          # Copy it into a list.          # Copy it into a list.
1694          my @stackedPath = @{$current};          my @stackedPath = @{$current};
1695          # Pull off the last item on the path. It will always be an entity.          # Pull off the last item on the path. It will always be an entity.
1696          my $entityName = pop @stackedPath;          my $myEntityName = pop @stackedPath;
1697          # Add it to the alreadyFound list.          # Add it to the alreadyFound list.
1698          $alreadyFound{$entityName} = 1;          $alreadyFound{$myEntityName} = 1;
1699            # Figure out if we need to delete this entity.
1700            if ($myEntityName ne $entityName || ! $options{keepRoot}) {
1701          # Get the entity data.          # Get the entity data.
1702          my $entityData = $self->_GetStructure($entityName);              my $entityData = $self->_GetStructure($myEntityName);
1703          # The first task is to loop through the entity's relation. A DELETE command will              # Loop through the entity's relations. A DELETE command will be needed for each of them.
         # be needed for each of them.  
1704          my $relations = $entityData->{Relations};          my $relations = $entityData->{Relations};
1705          for my $relation (keys %{$relations}) {          for my $relation (keys %{$relations}) {
1706              my @augmentedList = (@stackedPath, $relation);              my @augmentedList = (@stackedPath, $relation);
1707              push @fromPathList, \@augmentedList;              push @fromPathList, \@augmentedList;
1708          }          }
1709            }
1710          # Now we need to look for relationships connected to this entity.          # Now we need to look for relationships connected to this entity.
1711          my $relationshipList = $self->{_metaData}->{Relationships};          my $relationshipList = $self->{_metaData}->{Relationships};
1712          for my $relationshipName (keys %{$relationshipList}) {          for my $relationshipName (keys %{$relationshipList}) {
1713              my $relationship = $relationshipList->{$relationshipName};              my $relationship = $relationshipList->{$relationshipName};
1714              # Check the FROM field. We're only interested if it's us.              # Check the FROM field. We're only interested if it's us.
1715              if ($relationship->{from} eq $entityName) {              if ($relationship->{from} eq $myEntityName) {
1716                  # Add the path to this relationship.                  # Add the path to this relationship.
1717                  my @augmentedList = (@stackedPath, $entityName, $relationshipName);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1718                  push @fromPathList, \@augmentedList;                  push @fromPathList, \@augmentedList;
1719                  # Check the arity. If it's MM we're done. If it's 1M                  # Check the arity. If it's MM we're done. If it's 1M
1720                  # and the target hasn't been seen yet, we want to                  # and the target hasn't been seen yet, we want to
# Line 1348  Line 1733 
1733              }              }
1734              # Now check the TO field. In this case only the relationship needs              # Now check the TO field. In this case only the relationship needs
1735              # deletion.              # deletion.
1736              if ($relationship->{to} eq $entityName) {              if ($relationship->{to} eq $myEntityName) {
1737                  my @augmentedList = (@stackedPath, $entityName, $relationshipName);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1738                  push @toPathList, \@augmentedList;                  push @toPathList, \@augmentedList;
1739              }              }
1740          }          }
1741      }      }
1742      # Create the first qualifier for the WHERE clause. This selects the      # Create the first qualifier for the WHERE clause. This selects the
1743      # keys of the primary entity records to be deleted. When we're deleting      # keys of the primary entity records to be deleted. When we're deleting
1744      # from a dependent table, we construct a join page from the first qualifier      # from a dependent table, we construct a join path from the first qualifier
1745      # to the table containing the dependent records to delete.      # to the table containing the dependent records to delete.
1746      my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");      my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
1747      # We need to make two passes. The first is through the to-list, and      # We need to make two passes. The first is through the to-list, and
# Line 1395  Line 1780 
1780                  }                  }
1781              }              }
1782              # Now we have our desired DELETE statement.              # Now we have our desired DELETE statement.
1783              if ($testFlag) {              if ($options{testMode}) {
1784                  # Here the user wants to trace without executing.                  # Here the user wants to trace without executing.
1785                  Trace($stmt) if T(0);                  Trace($stmt) if T(0);
1786              } else {              } else {
1787                  # 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
1788                  # if an error occurs, so we just go ahead and do it.                  # if an error occurs, so we just go ahead and do it.
1789                  Trace("Executing delete from $target using '$objectID'.") if T(3);                  Trace("Executing delete from $target using '$objectID'.") if T(3);
1790                  my $rv = $db->SQL($stmt, 0, $objectID);                  my $rv = $db->SQL($stmt, 0, $objectID);
# Line 1414  Line 1799 
1799      return $retVal;      return $retVal;
1800  }  }
1801    
1802    =head3 Disconnect
1803    
1804    C<< $erdb->Disconnect($relationshipName, $originEntityName, $originEntityID); >>
1805    
1806    Disconnect an entity instance from all the objects to which it is related. This
1807    will delete each relationship instance that connects to the specified entity.
1808    
1809    =over 4
1810    
1811    =item relationshipName
1812    
1813    Name of the relationship whose instances are to be deleted.
1814    
1815    =item originEntityName
1816    
1817    Name of the entity that is to be disconnected.
1818    
1819    =item originEntityID
1820    
1821    ID of the entity that is to be disconnected.
1822    
1823    =back
1824    
1825    =cut
1826    
1827    sub Disconnect {
1828        # Get the parameters.
1829        my ($self, $relationshipName, $originEntityName, $originEntityID) = @_;
1830        # Get the relationship descriptor.
1831        my $structure = $self->_GetStructure($relationshipName);
1832        # Insure we have a relationship.
1833        if (! exists $structure->{from}) {
1834            Confess("$relationshipName is not a relationship in the database.");
1835        } else {
1836            # Get the database handle.
1837            my $dbh = $self->{_dbh};
1838            # We'll set this value to 1 if we find our entity.
1839            my $found = 0;
1840            # Loop through the ends of the relationship.
1841            for my $dir ('from', 'to') {
1842                if ($structure->{$dir} eq $originEntityName) {
1843                    # Delete all relationship instances on this side of the entity instance.
1844                    $dbh->SQL("DELETE FROM $relationshipName WHERE ${dir}_link = ?", 0, $originEntityID);
1845                    $found = 1;
1846                }
1847            }
1848            # Insure we found the entity on at least one end.
1849            if (! $found) {
1850                Confess("Entity \"$originEntityName\" does not use $relationshipName.");
1851            }
1852        }
1853    }
1854    
1855    =head3 DeleteRow
1856    
1857    C<< $erdb->DeleteRow($relationshipName, $fromLink, $toLink, \%values); >>
1858    
1859    Delete a row from a relationship. In most cases, only the from-link and to-link are
1860    needed; however, for relationships with intersection data values can be specified
1861    for the other fields using a hash.
1862    
1863    =over 4
1864    
1865    =item relationshipName
1866    
1867    Name of the relationship from which the row is to be deleted.
1868    
1869    =item fromLink
1870    
1871    ID of the entity instance in the From direction.
1872    
1873    =item toLink
1874    
1875    ID of the entity instance in the To direction.
1876    
1877    =item values
1878    
1879    Reference to a hash of other values to be used for filtering the delete.
1880    
1881    =back
1882    
1883    =cut
1884    
1885    sub DeleteRow {
1886        # Get the parameters.
1887        my ($self, $relationshipName, $fromLink, $toLink, $values) = @_;
1888        # Create a hash of all the filter information.
1889        my %filter = ('from-link' => $fromLink, 'to-link' => $toLink);
1890        if (defined $values) {
1891            for my $key (keys %{$values}) {
1892                $filter{$key} = $values->{$key};
1893            }
1894        }
1895        # Build an SQL statement out of the hash.
1896        my @filters = ();
1897        my @parms = ();
1898        for my $key (keys %filter) {
1899            push @filters, _FixName($key) . " = ?";
1900            push @parms, $filter{$key};
1901        }
1902        Trace("Parms for delete row are " . join(", ", map { "\"$_\"" } @parms) . ".") if T(SQL => 4);
1903        my $command = "DELETE FROM $relationshipName WHERE " .
1904                      join(" AND ", @filters);
1905        # Execute it.
1906        my $dbh = $self->{_dbh};
1907        $dbh->SQL($command, undef, @parms);
1908    }
1909    
1910  =head3 SortNeeded  =head3 SortNeeded
1911    
1912  C<< my $parms = $erdb->SortNeeded($relationName); >>  C<< my $parms = $erdb->SortNeeded($relationName); >>
# Line 1464  Line 1957 
1957      } elsif (exists $relationshipTable->{$relationName}) {      } elsif (exists $relationshipTable->{$relationName}) {
1958          # Here we have a relationship. We sort using the FROM index.          # Here we have a relationship. We sort using the FROM index.
1959          my $relationshipData = $relationshipTable->{$relationName};          my $relationshipData = $relationshipTable->{$relationName};
1960          my $index = $relationData->{Indexes}->{"idx${relationName}From"};          my $index = $relationData->{Indexes}->{idxFrom};
1961          push @keyNames, @{$index->{IndexFields}};          push @keyNames, @{$index->{IndexFields}};
1962      } else {      } else {
1963          # Here we have a secondary entity relation, so we have a sort on the ID field.          # Here we have a secondary entity relation, so we have a sort on the ID field.
# Line 1810  Line 2303 
2303    
2304  =head3 InsertObject  =head3 InsertObject
2305    
2306  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>  C<< $erdb->InsertObject($objectType, \%fieldHash); >>
2307    
2308  Insert an object into the database. The object is defined by a type name and then a hash  Insert an object into the database. The object is defined by a type name and then a hash
2309  of field names to values. Field values in the primary relation are represented by scalars.  of field names to values. Field values in the primary relation are represented by scalars.
# Line 1836  Line 2329 
2329    
2330  Hash of field names to values.  Hash of field names to values.
2331    
 =item RETURN  
   
 Returns 1 if successful, 0 if an error occurred.  
   
2332  =back  =back
2333    
2334  =cut  =cut
# Line 1938  Line 2427 
2427                  $retVal = $sth->execute(@parameterList);                  $retVal = $sth->execute(@parameterList);
2428                  if (!$retVal) {                  if (!$retVal) {
2429                      my $errorString = $sth->errstr();                      my $errorString = $sth->errstr();
2430                      Trace("Insert error: $errorString.") if T(0);                      Confess("Error inserting into $relationName: $errorString");
2431                  }                  }
2432              }              }
2433          }          }
2434      }      }
2435      # Return the success indicator.      # Return a 1 for backward compatability.
2436      return $retVal;      return 1;
2437  }  }
2438    
2439  =head3 LoadTable  =head3 UpdateEntity
2440    
2441  C<< my %results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>  C<< $erdb->UpdateEntity($entityName, $id, \%fields); >>
2442    
2443  Load data from a tab-delimited file into a specified table, optionally re-creating the table  Update the values of an entity. This is an unprotected update, so it should only be
2444  first.  done if the database resides on a database server.
2445    
2446  =over 4  =over 4
2447    
2448  =item fileName  =item entityName
2449    
2450  Name of the file from which the table data should be loaded.  Name of the entity to update. (This is the entity type.)
2451    
2452  =item relationName  =item id
2453    
2454  Name of the relation to be loaded. This is the same as the table name.  ID of the entity to update. If no entity exists with this ID, an error will be thrown.
2455    
2456  =item truncateFlag  =item fields
2457    
2458  TRUE if the table should be dropped and re-created, else FALSE  Reference to a hash mapping field names to their new values. All of the fields named
2459    must be in the entity's primary relation, and they cannot any of them be the ID field.
2460    
2461  =item RETURN  =back
2462    
2463  Returns a statistical object containing a list of the error messages.  =cut
2464    
2465    sub UpdateEntity {
2466        # Get the parameters.
2467        my ($self, $entityName, $id, $fields) = @_;
2468        # Get a list of the field names being updated.
2469        my @fieldList = keys %{$fields};
2470        # Verify that the fields exist.
2471        my $checker = $self->GetFieldTable($entityName);
2472        for my $field (@fieldList) {
2473            if ($field eq 'id') {
2474                Confess("Cannot update the ID field for entity $entityName.");
2475            } elsif ($checker->{$field}->{relation} ne $entityName) {
2476                Confess("Cannot find $field in primary relation of $entityName.");
2477            }
2478        }
2479        # Build the SQL statement.
2480        my @sets = ();
2481        my @valueList = ();
2482        for my $field (@fieldList) {
2483            push @sets, _FixName($field) . " = ?";
2484            push @valueList, $fields->{$field};
2485        }
2486        my $command = "UPDATE $entityName SET " . join(", ", @sets) . " WHERE id = ?";
2487        # Add the ID to the list of binding values.
2488        push @valueList, $id;
2489        # Call SQL to do the work.
2490        my $rows = $self->{_dbh}->SQL($command, 0, @valueList);
2491        # Check for errors.
2492        if ($rows == 0) {
2493            Confess("Entity $id of type $entityName not found.");
2494        }
2495    }
2496    
2497    =head3 LoadTable
2498    
2499    C<< my $results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>
2500    
2501    Load data from a tab-delimited file into a specified table, optionally re-creating the table
2502    first.
2503    
2504    =over 4
2505    
2506    =item fileName
2507    
2508    Name of the file from which the table data should be loaded.
2509    
2510    =item relationName
2511    
2512    Name of the relation to be loaded. This is the same as the table name.
2513    
2514    =item truncateFlag
2515    
2516    TRUE if the table should be dropped and re-created, else FALSE
2517    
2518    =item RETURN
2519    
2520    Returns a statistical object containing a list of the error messages.
2521    
2522  =back  =back
2523    
# Line 2016  Line 2563 
2563      };      };
2564      if (!defined $rv) {      if (!defined $rv) {
2565          $retVal->AddMessage($@) if ($@);          $retVal->AddMessage($@) if ($@);
2566          $retVal->AddMessage("Table load failed for $relationName using $fileName.");          $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2567          Trace("Table load failed for $relationName.") if T(1);          Trace("Table load failed for $relationName.") if T(1);
2568      } else {      } else {
2569          # Here we successfully loaded the table.          # Here we successfully loaded the table.
# Line 2038  Line 2585 
2585              # The full-text index (if any) is always built last, even for MySQL.              # The full-text index (if any) is always built last, even for MySQL.
2586              # First we need to see if this table has a full-text index. Only              # First we need to see if this table has a full-text index. Only
2587              # primary relations are allowed that privilege.              # primary relations are allowed that privilege.
2588                Trace("Checking for full-text index on $relationName.") if T(2);
2589              if ($self->_IsPrimary($relationName)) {              if ($self->_IsPrimary($relationName)) {
2590                  # Get the relation's entity/relationship structure.                  $self->CreateSearchIndex($relationName);
                 my $structure = $self->_GetStructure($relationName);  
                 # Check for a searchable fields list.  
                 if (exists $structure->{searchFields}) {  
                     # Here we know that we need to create a full-text search index.  
                     # Get an SQL-formatted field name list.  
                     my $fields = join(", ", $self->_FixNames(@{$structure->{searchFields}}));  
                     # Create the index.  
                     $dbh->create_index(tbl => $relationName, idx => "search_idx_$relationName",  
                                        flds => $fields, kind => 'fulltext');  
                 }  
2591              }              }
2592          }          }
2593      }      }
# Line 2061  Line 2599 
2599      return $retVal;      return $retVal;
2600  }  }
2601    
2602  =head3 GenerateEntity  =head3 CreateSearchIndex
2603    
2604  C<< my $fieldHash = $erdb->GenerateEntity($id, $type, \%values); >>  C<< $erdb->CreateSearchIndex($objectName); >>
2605    
2606  Generate the data for a new entity instance. This method creates a field hash suitable for  Check for a full-text search index on the specified entity or relationship object, and
2607  passing as a parameter to L</InsertObject>. The ID is specified by the callr, but the rest  if one is required, rebuild it.
 of the fields are generated using information in the database schema.  
   
 Each data type has a default algorithm for generating random test data. This can be overridden  
 by including a B<DataGen> element in the field. If this happens, the content of the element is  
 executed as a PERL program in the context of this module. The element may make use of a C<$this>  
 variable which contains the field hash as it has been built up to the current point. If any  
 fields are dependent on other fields, the C<pass> attribute can be used to control the order  
 in which the fields are generated. A field with a high data pass number will be generated after  
 a field with a lower one. If any external values are needed, they should be passed in via the  
 optional third parameter, which will be available to the data generation script under the name  
 C<$value>. Several useful utility methods are provided for generating random values, including  
 L</IntGen>, L</StringGen>, L</FloatGen>, and L</DateGen>. Note that dates are stored and generated  
 in the form of a timestamp number rather than a string.  
2608    
2609  =over 4  =over 4
2610    
2611  =item id  =item objectName
2612    
2613  ID to assign to the new entity.  Name of the entity or relationship to be indexed.
2614    
2615  =item type  =back
2616    
2617  Type name for the new entity.  =cut
2618    
2619  =item values  sub CreateSearchIndex {
2620        # Get the parameters.
2621        my ($self, $objectName) = @_;
2622        # Get the relation's entity/relationship structure.
2623        my $structure = $self->_GetStructure($objectName);
2624        # Get the database handle.
2625        my $dbh = $self->{_dbh};
2626        Trace("Checking for search fields in $objectName.") if T(3);
2627        # Check for a searchable fields list.
2628        if (exists $structure->{searchFields}) {
2629            # Here we know that we need to create a full-text search index.
2630            # Get an SQL-formatted field name list.
2631            my $fields = join(", ", _FixNames(@{$structure->{searchFields}}));
2632            # Create the index. If it already exists, it will be dropped.
2633            $dbh->create_index(tbl => $objectName, idx => "search_idx",
2634                               flds => $fields, kind => 'fulltext');
2635            Trace("Index created for $fields in $objectName.") if T(2);
2636        }
2637    }
2638    
2639    =head3 DropRelation
2640    
2641    C<< $erdb->DropRelation($relationName); >>
2642    
2643  Hash containing additional values that might be needed by the data generation methods (optional).  Physically drop a relation from the database.
2644    
2645    =over 4
2646    
2647    =item relationName
2648    
2649    Name of the relation to drop. If it does not exist, this method will have
2650    no effect.
2651    
2652  =back  =back
2653    
2654  =cut  =cut
2655    
2656  sub GenerateEntity {  sub DropRelation {
2657      # Get the parameters.      # Get the parameters.
2658      my ($self, $id, $type, $values) = @_;      my ($self, $relationName) = @_;
2659      # Create the return hash.      # Get the database handle.
2660      my $this = { id => $id };      my $dbh = $self->{_dbh};
2661      # Get the metadata structure.      # Drop the relation. The method used here has no effect if the relation
2662      my $metadata = $self->{_metaData};      # does not exist.
2663      # Get this entity's list of fields.      Trace("Invoking DB Kernel to drop $relationName.") if T(3);
2664      if (!exists $metadata->{Entities}->{$type}) {      $dbh->drop_table(tbl => $relationName);
2665          Confess("Unrecognized entity type $type in GenerateEntity.");  }
2666    
2667    =head3 MatchSqlPattern
2668    
2669    C<< my $matched = ERDB::MatchSqlPattern($value, $pattern); >>
2670    
2671    Determine whether or not a specified value matches an SQL pattern. An SQL
2672    pattern has two wild card characters: C<%> that matches multiple characters,
2673    and C<_> that matches a single character. These can be escaped using a
2674    backslash (C<\>). We pull this off by converting the SQL pattern to a
2675    PERL regular expression. As per SQL rules, the match is case-insensitive.
2676    
2677    =over 4
2678    
2679    =item value
2680    
2681    Value to be matched against the pattern. Note that an undefined or empty
2682    value will not match anything.
2683    
2684    =item pattern
2685    
2686    SQL pattern against which to match the value. An undefined or empty pattern will
2687    match everything.
2688    
2689    =item RETURN
2690    
2691    Returns TRUE if the value and pattern match, else FALSE.
2692    
2693    =back
2694    
2695    =cut
2696    
2697    sub MatchSqlPattern {
2698        # Get the parameters.
2699        my ($value, $pattern) = @_;
2700        # Declare the return variable.
2701        my $retVal;
2702        # Insure we have a pattern.
2703        if (! defined($pattern) || $pattern eq "") {
2704            $retVal = 1;
2705      } else {      } else {
2706          my $entity = $metadata->{Entities}->{$type};          # Break the pattern into pieces around the wildcard characters. Because we
2707          my $fields = $entity->{Fields};          # use parentheses in the split function's delimiter expression, we'll get
2708          # Generate data from the fields.          # list elements for the delimiters as well as the rest of the string.
2709          _GenerateFields($this, $fields, $type, $values);          my @pieces = split /([_%]|\\[_%])/, $pattern;
2710            # Check some fast special cases.
2711            if ($pattern eq '%') {
2712                # A null pattern matches everything.
2713                $retVal = 1;
2714            } elsif (@pieces == 1) {
2715                # No wildcards, so we have a literal comparison. Note we're case-insensitive.
2716                $retVal = (lc($value) eq lc($pattern));
2717            } elsif (@pieces == 2 && $pieces[1] eq '%') {
2718                # A wildcard at the end, so we have a substring match. This is also case-insensitive.
2719                $retVal = (lc(substr($value, 0, length($pieces[0]))) eq lc($pieces[0]));
2720            } else {
2721                # Okay, we have to do it the hard way. Convert each piece to a PERL pattern.
2722                my $realPattern = "";
2723                for my $piece (@pieces) {
2724                    # Determine the type of piece.
2725                    if ($piece eq "") {
2726                        # Empty pieces are ignored.
2727                    } elsif ($piece eq "%") {
2728                        # Here we have a multi-character wildcard. Note that it can match
2729                        # zero or more characters.
2730                        $realPattern .= ".*"
2731                    } elsif ($piece eq "_") {
2732                        # Here we have a single-character wildcard.
2733                        $realPattern .= ".";
2734                    } elsif ($piece eq "\\%" || $piece eq "\\_") {
2735                        # This is an escape sequence (which is a rare thing, actually).
2736                        $realPattern .= substr($piece, 1, 1);
2737                    } else {
2738                        # Here we have raw text.
2739                        $realPattern .= quotemeta($piece);
2740                    }
2741                }
2742                # Do the match.
2743                $retVal = ($value =~ /^$realPattern$/i ? 1 : 0);
2744      }      }
2745      # Return the hash created.      }
2746      return $this;      # Return the result.
2747        return $retVal;
2748  }  }
2749    
2750  =head3 GetEntity  =head3 GetEntity
# Line 2272  Line 2900 
2900  spreadsheet cell, and each feature will be represented by a list containing the  spreadsheet cell, and each feature will be represented by a list containing the
2901  feature ID followed by all of its aliases.  feature ID followed by all of its aliases.
2902    
2903  C<< $query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>  C<< @query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>
2904    
2905  =over 4  =over 4
2906    
# Line 2450  Line 3078 
3078      return $objectData->{Fields};      return $objectData->{Fields};
3079  }  }
3080    
3081    =head3 SplitKeywords
3082    
3083    C<< my @keywords = ERDB::SplitKeywords($keywordString); >>
3084    
3085    This method returns a list of the positive keywords in the specified
3086    keyword string. All of the operators will have been stripped off,
3087    and if the keyword is preceded by a minus operator (C<->), it will
3088    not be in the list returned. The idea here is to get a list of the
3089    keywords the user wants to see. The list will be processed to remove
3090    duplicates.
3091    
3092    It is possible to create a string that confuses this method. For example
3093    
3094        frog toad -frog
3095    
3096    would return both C<frog> and C<toad>. If this is a problem we can deal
3097    with it later.
3098    
3099    =over 4
3100    
3101    =item keywordString
3102    
3103    The keyword string to be parsed.
3104    
3105    =item RETURN
3106    
3107    Returns a list of the words in the keyword string the user wants to
3108    see.
3109    
3110    =back
3111    
3112    =cut
3113    
3114    sub SplitKeywords {
3115        # Get the parameters.
3116        my ($keywordString) = @_;
3117        # Make a safety copy of the string. (This helps during debugging.)
3118        my $workString = $keywordString;
3119        # Convert operators we don't care about to spaces.
3120        $workString =~ tr/+"()<>/ /;
3121        # Split the rest of the string along space boundaries. Note that we
3122        # eliminate any words that are zero length or begin with a minus sign.
3123        my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
3124        # Use a hash to remove duplicates.
3125        my %words = map { $_ => 1 } @wordList;
3126        # Return the result.
3127        return sort keys %words;
3128    }
3129    
3130    =head3 ValidateFieldName
3131    
3132    C<< my $okFlag = ERDB::ValidateFieldName($fieldName); >>
3133    
3134    Return TRUE if the specified field name is valid, else FALSE. Valid field names must
3135    be hyphenated words subject to certain restrictions.
3136    
3137    =over 4
3138    
3139    =item fieldName
3140    
3141    Field name to be validated.
3142    
3143    =item RETURN
3144    
3145    Returns TRUE if the field name is valid, else FALSE.
3146    
3147    =back
3148    
3149    =cut
3150    
3151    sub ValidateFieldName {
3152        # Get the parameters.
3153        my ($fieldName) = @_;
3154        # Declare the return variable. The field name is valid until we hear
3155        # differently.
3156        my $retVal = 1;
3157        # Compute the maximum name length.
3158        my $maxLen = $TypeTable{'name-string'}->{maxLen};
3159        # Look for bad stuff in the name.
3160        if ($fieldName =~ /--/) {
3161            # Here we have a doubled minus sign.
3162            Trace("Field name $fieldName has a doubled hyphen.") if T(1);
3163            $retVal = 0;
3164        } elsif ($fieldName !~ /^[A-Za-z]/) {
3165            # Here the field name is missing the initial letter.
3166            Trace("Field name $fieldName does not begin with a letter.") if T(1);
3167            $retVal = 0;
3168        } elsif (length($fieldName) > $maxLen) {
3169            # Here the field name is too long.
3170            Trace("Maximum field name length is $maxLen. Field name must be truncated to " . substr($fieldName,0, $maxLen) . ".");
3171        } else {
3172            # Strip out the minus signs. Everything remaining must be a letter,
3173            # underscore, or digit.
3174            my $strippedName = $fieldName;
3175            $strippedName =~ s/-//g;
3176            if ($strippedName !~ /^(\w|\d)+$/) {
3177                Trace("Field name $fieldName contains illegal characters.") if T(1);
3178                $retVal = 0;
3179            }
3180        }
3181        # Return the result.
3182        return $retVal;
3183    }
3184    
3185    =head3 ReadMetaXML
3186    
3187    C<< my $rawMetaData = ERDB::ReadDBD($fileName); >>
3188    
3189    This method reads a raw database definition XML file and returns it.
3190    Normally, the metadata used by the ERDB system has been processed and
3191    modified to make it easier to load and retrieve the data; however,
3192    this method can be used to get the data in its raw form.
3193    
3194    =over 4
3195    
3196    =item fileName
3197    
3198    Name of the XML file to read.
3199    
3200    =item RETURN
3201    
3202    Returns a hash reference containing the raw XML data from the specified file.
3203    
3204    =back
3205    
3206    =cut
3207    
3208    sub ReadMetaXML {
3209        # Get the parameters.
3210        my ($fileName) = @_;
3211        # Read the XML.
3212        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
3213        Trace("XML metadata loaded from file $fileName.") if T(1);
3214        # Return the result.
3215        return $retVal;
3216    }
3217    
3218    =head3 GetEntityFieldHash
3219    
3220    C<< my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName); >>
3221    
3222    Get the field hash of the named entity in the specified raw XML structure.
3223    The field hash may not exist, in which case we need to create it.
3224    
3225    =over 4
3226    
3227    =item structure
3228    
3229    Raw XML structure defininng the database. This is not the run-time XML used by
3230    an ERDB object, since that has all sorts of optimizations built-in.
3231    
3232    =item entityName
3233    
3234    Name of the entity whose field structure is desired.
3235    
3236    =item RETURN
3237    
3238    Returns the field hash used to define the entity's fields.
3239    
3240    =back
3241    
3242    =cut
3243    
3244    sub GetEntityFieldHash {
3245        # Get the parameters.
3246        my ($structure, $entityName) = @_;
3247        # Get the entity structure.
3248        my $entityData = $structure->{Entities}->{$entityName};
3249        # Look for a field structure.
3250        my $retVal = $entityData->{Fields};
3251        # If it doesn't exist, create it.
3252        if (! defined($retVal)) {
3253            $entityData->{Fields} = {};
3254            $retVal = $entityData->{Fields};
3255        }
3256        # Return the result.
3257        return $retVal;
3258    }
3259    
3260    =head3 WriteMetaXML
3261    
3262    C<< ERDB::WriteMetaXML($structure, $fileName); >>
3263    
3264    Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
3265    used to update the database definition. It must be used with care, however, since it
3266    will only work on a raw structure, not on the processed structure created by an ERDB
3267    constructor.
3268    
3269    =over 4
3270    
3271    =item structure
3272    
3273    XML structure to be written to the file.
3274    
3275    =item fileName
3276    
3277    Name of the output file to which the updated XML should be stored.
3278    
3279    =back
3280    
3281    =cut
3282    
3283    sub WriteMetaXML {
3284        # Get the parameters.
3285        my ($structure, $fileName) = @_;
3286        # Compute the output.
3287        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
3288        # Write it to the file.
3289        my $xmlOut = Open(undef, ">$fileName");
3290        print $xmlOut $fileString;
3291    }
3292    
3293    
3294    =head3 HTMLNote
3295    
3296    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
3297    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
3298    Except for C<[p]>, all the codes are closed by slash-codes. So, for
3299    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
3300    
3301    C<< my $realHtml = ERDB::HTMLNote($dataString); >>
3302    
3303    =over 4
3304    
3305    =item dataString
3306    
3307    String to convert to HTML.
3308    
3309    =item RETURN
3310    
3311    An HTML string derived from the input string.
3312    
3313    =back
3314    
3315    =cut
3316    
3317    sub HTMLNote {
3318        # Get the parameter.
3319        my ($dataString) = @_;
3320        # HTML-escape the text.
3321        my $retVal = CGI::escapeHTML($dataString);
3322        # Substitute the bulletin board codes.
3323        $retVal =~ s!\[(/?[bi])\]!<$1>!g;
3324        $retVal =~ s!\[p\]!</p><p>!g;
3325        # Return the result.
3326        return $retVal;
3327    }
3328    
3329    
3330  =head2 Data Mining Methods  =head2 Data Mining Methods
3331    
3332  =head3 GetUsefulCrossValues  =head3 GetUsefulCrossValues
# Line 2600  Line 3477 
3477      # Split it into a list.      # Split it into a list.
3478      my @retVal = split(/\t/, $line);      my @retVal = split(/\t/, $line);
3479      # Return the result.      # Return the result.
3480      return @retVal;      return @retVal;
3481    }
3482    
3483    =head2 Virtual Methods
3484    
3485    =head3 CleanKeywords
3486    
3487    C<< my $cleanedString = $erdb->CleanKeywords($searchExpression); >>
3488    
3489    Clean up a search expression or keyword list. This is a virtual method that may
3490    be overridden by the subclass. The base-class method removes extra spaces
3491    and converts everything to lower case.
3492    
3493    =over 4
3494    
3495    =item searchExpression
3496    
3497    Search expression or keyword list to clean. Note that a search expression may
3498    contain boolean operators which need to be preserved. This includes leading
3499    minus signs.
3500    
3501    =item RETURN
3502    
3503    Cleaned expression or keyword list.
3504    
3505    =back
3506    
3507    =cut
3508    
3509    sub CleanKeywords {
3510        # Get the parameters.
3511        my ($self, $searchExpression) = @_;
3512        # Lower-case the expression and copy it into the return variable. Note that we insure we
3513        # don't accidentally end up with an undefined value.
3514        my $retVal = lc($searchExpression || "");
3515        # Remove extra spaces.
3516        $retVal =~ s/\s+/ /g;
3517        $retVal =~ s/(^\s+)|(\s+$)//g;
3518        # Return the result.
3519        return $retVal;
3520  }  }
3521    
3522    =head3 GetSourceObject
3523    
3524    C<< my $source = $erdb->GetSourceObject($entityName); >>
3525    
3526    Return the object to be used in loading special attributes of the specified entity. The
3527    algorithm for loading special attributes is stored in the C<DataGen> elements of the
3528    XML
3529    
3530  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3531    
3532  =head3 _RelationMap  =head3 _RelationMap
# Line 2928  Line 3852 
3852      # Prepare the command.      # Prepare the command.
3853      my $sth = $dbh->prepare_command($command);      my $sth = $dbh->prepare_command($command);
3854      # Execute it with the parameters bound in.      # Execute it with the parameters bound in.
3855      $sth->execute(@{$params}) || Confess("SELECT error" . $sth->errstr());      $sth->execute(@{$params}) || Confess("SELECT error:  " . $sth->errstr());
3856      # Return the statement handle.      # Return the statement handle.
3857      return $sth;      return $sth;
3858  }  }
# Line 2945  Line 3869 
3869      return Stats->new();      return Stats->new();
3870  }  }
3871    
 =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;  
             }  
         }  
     }  
 }  
   
3872  =head3 _DumpRelation  =head3 _DumpRelation
3873    
3874  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.
3875    
3876  This is an instance method.  This is an instance method.
3877    
# Line 3166  Line 4016 
4016          for my $object (values %{$metadata->{$section}}) {          for my $object (values %{$metadata->{$section}}) {
4017              # Loop through the object's fields.              # Loop through the object's fields.
4018              for my $fieldName (keys %{$object->{Fields}}) {              for my $fieldName (keys %{$object->{Fields}}) {
4019                  # Now we make some initial validations.                  # If this field name is invalid, set the return value to zero
4020                  if ($fieldName =~ /--/) {                  # so we know we encountered an error.
4021                      # Here we have a doubled minus sign.                  if (! ValidateFieldName($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";  
4022                          $retVal = 0;                          $retVal = 0;
4023                      }                      }
4024                  }                  }
4025              }              }
4026          }          }
     }  
4027      # If an error was found, fail.      # If an error was found, fail.
4028      if ($retVal  == 0) {      if ($retVal  == 0) {
4029          Confess("Errors found in field names.");          Confess("Errors found in field names.");
# Line 3254  Line 4090 
4090      return $retVal;      return $retVal;
4091  }  }
4092    
4093    
4094  =head3 _LoadMetaData  =head3 _LoadMetaData
4095    
4096  This method loads the data describing this database from an XML file into a metadata structure.  This method loads the data describing this database from an XML file into a metadata structure.
# Line 3279  Line 4116 
4116  sub _LoadMetaData {  sub _LoadMetaData {
4117      # Get the parameters.      # Get the parameters.
4118      my ($filename) = @_;      my ($filename) = @_;
4119      Trace("Reading Sprout DBD from $filename.") if T(2);      Trace("Reading DBD from $filename.") if T(2);
4120      # 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
4121      # get the exact structure we want.      # get the exact structure we want.
4122      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 $filename.") if T(1);  
4123      # Before we go any farther, we need to validate the field and object names. If an error is found,      # Before we go any farther, we need to validate the field and object names. If an error is found,
4124      # the method below will fail.      # the method below will fail.
4125      _ValidateFieldNames($metadata);      _ValidateFieldNames($metadata);
# Line 3425  Line 4249 
4249              my $count = 0;              my $count = 0;
4250              for my $index (@{$indexList}) {              for my $index (@{$indexList}) {
4251                  # Add this index to the index table.                  # Add this index to the index table.
4252                  _AddIndex("idx$relationName$count", $relation, $index);                  _AddIndex("idx$count", $relation, $index);
4253                  # Increment the counter so that the next index has a different name.                  # Increment the counter so that the next index has a different name.
4254                  $count++;                  $count++;
4255              }              }
# Line 3623  Line 4447 
4447          $newIndex->{Unique} = 'true';          $newIndex->{Unique} = 'true';
4448      }      }
4449      # Add the index to the relation.      # Add the index to the relation.
4450      _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);      _AddIndex("idx$indexKey", $relationStructure, $newIndex);
4451  }  }
4452    
4453  =head3 _AddIndex  =head3 _AddIndex
# Line 3722  Line 4546 
4546              my $type = $fieldData->{type};              my $type = $fieldData->{type};
4547              # Plug in a relation name if it is needed.              # Plug in a relation name if it is needed.
4548              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });
             # Plug in a data generator if we need one.  
             if (!exists $fieldData->{DataGen}) {  
                 # The data generator will use the default for the field's type.  
                 $fieldData->{DataGen} = { content => $TypeTable{$type}->{dataGen} };  
             }  
4549              # Check for searchability.              # Check for searchability.
4550              if ($fieldData->{searchable}) {              if ($fieldData->{searchable}) {
4551                  # Only allow this for a primary relation.                  # Only allow this for a primary relation.
# Line 3736  Line 4555 
4555                      push @textFields, $fieldName;                      push @textFields, $fieldName;
4556                  }                  }
4557              }              }
             # Plug in the defaults for the optional data generation parameters.  
             Tracer::MergeOptions($fieldData->{DataGen}, { testCount => 1, pass => 0 });  
4558              # Add the PrettySortValue.              # Add the PrettySortValue.
4559              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);
4560          }          }
# Line 4096  Line 4913 
4913          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";
4914          # Add any note text.          # Add any note text.
4915          if (my $note = $indexData->{Notes}) {          if (my $note = $indexData->{Notes}) {
4916              $htmlString .= "<li>" . _HTMLNote($note->{content}) . "</li>\n";              $htmlString .= "<li>" . HTMLNote($note->{content}) . "</li>\n";
4917          }          }
4918          # Add the fiield list.          # Add the fiield list.
4919          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";
# Line 4211  Line 5028 
5028      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>";
5029      # If we have content, add it as a third column.      # If we have content, add it as a third column.
5030      if (exists $fieldData->{Notes}) {      if (exists $fieldData->{Notes}) {
5031          $htmlString .= "<td>" . _HTMLNote($fieldData->{Notes}->{content}) . "</td>";          $htmlString .= "<td>" . HTMLNote($fieldData->{Notes}->{content}) . "</td>";
5032      }      }
5033      # Close off the row.      # Close off the row.
5034      $htmlString .= "</tr>\n";      $htmlString .= "</tr>\n";
# Line 4219  Line 5036 
5036      return $htmlString;      return $htmlString;
5037  }  }
5038    
 =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;  
 }  
   
5039  1;  1;

Legend:
Removed from v.1.70  
changed lines
  Added in v.1.82

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3