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

Diff of /Sprout/ERDB.pm

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

revision 1.48, Wed Jun 21 03:12:20 2006 UTC revision 1.74, Fri Nov 3 16:49:44 2006 UTC
# Line 11  Line 11 
11      use Time::HiRes qw(gettimeofday);      use Time::HiRes qw(gettimeofday);
12      use Digest::MD5 qw(md5_base64);      use Digest::MD5 qw(md5_base64);
13      use FIG;      use FIG;
14        use CGI;
15    
16  =head1 Entity-Relationship Database Package  =head1 Entity-Relationship Database Package
17    
# Line 59  Line 60 
60  B<start-position>, which indicates where in the contig that the sequence begins. This attribute  B<start-position>, which indicates where in the contig that the sequence begins. This attribute
61  is implemented as the C<start_position> field in the C<IsMadeUpOf> relation.  is implemented as the C<start_position> field in the C<IsMadeUpOf> relation.
62    
63  The database itself is described by an XML file using the F<ERDatabase.xsd> schema. In addition to  The database itself is described by an XML file. In addition to all the data required to define
64  all the data required to define the entities, relationships, and attributes, the schema provides  the entities, relationships, and attributes, the schema provides space for notes describing
65  space for notes describing the data and what it means. These notes are used by L</ShowMetaData>  the data and what it means. These notes are used by L</ShowMetaData> to generate documentation
66  to generate documentation for the database.  for the database.
67    
68    Special support is provided for text searching. An entity field can be marked as <em>searchable</em>,
69    in which case it will be used to generate a text search index in which the user searches for words
70    in the field instead of a particular field value.
71    
72  Finally, every entity and relationship object has a flag indicating if it is new or old. The object  Finally, every entity and relationship object has a flag indicating if it is new or old. The object
73  is considered I<old> if it was loaded by the L</LoadTables> method. It is considered I<new> if it  is considered I<old> if it was loaded by the L</LoadTables> method. It is considered I<new> if it
74  was inserted by the L</InsertObject> method.  was inserted by the L</InsertObject> method.
75    
 To facilitate testing, the ERDB module supports automatic generation of test data. This process  
 is described in the L</GenerateEntity> and L</GenerateConnection> methods, though it is not yet  
 fully implemented.  
   
76  =head2 XML Database Description  =head2 XML Database Description
77    
78  =head3 Data Types  =head3 Data Types
# Line 91  Line 92 
92    
93  32-bit signed integer  32-bit signed integer
94    
95    =item counter
96    
97    32-bit unsigned integer
98    
99  =item date  =item date
100    
101  64-bit unsigned integer, representing a PERL date/time value  64-bit unsigned integer, representing a PERL date/time value
# Line 186  Line 191 
191    
192  Name of the field. The field name should contain only letters, digits, and hyphens (C<->),  Name of the field. The field name should contain only letters, digits, and hyphens (C<->),
193  and the first character should be a letter. Most underlying databases are case-insensitive  and the first character should be a letter. Most underlying databases are case-insensitive
194  with the respect to field names, so a best practice is to use lower-case letters only.  with the respect to field names, so a best practice is to use lower-case letters only. Finally,
195    the name C<search-relevance> has special meaning for full-text searches and should not be
196    used as a field name.
197    
198  =item type  =item type
199    
# Line 205  Line 212 
212  entity, the fields without a relation attribute are said to belong to the  entity, the fields without a relation attribute are said to belong to the
213  I<primary relation>. This relation has the same name as the entity itself.  I<primary relation>. This relation has the same name as the entity itself.
214    
215    =item searchable
216    
217    If specified, then the field is a candidate for full-text searching. A single full-text
218    index will be created for each relation with at least one searchable field in it.
219    For best results, this option should only be used for string or text fields.
220    
221    =item special
222    
223    This attribute allows the subclass to assign special meaning for certain fields.
224    The interpretation is up to the subclass itself. Currently, only entity fields
225    can have this attribute.
226    
227  =back  =back
228    
229  =head3 Indexes  =head3 Indexes
230    
231  An entity can have multiple alternate indexes associated with it. The fields must  An entity can have multiple alternate indexes associated with it. The fields must
232  be from the primary relation. The alternate indexes assist in ordering results  all be from the same relation. The alternate indexes assist in ordering results
233  from a query. A relationship can have up to two indexes-- a I<to-index> and a  from a query. A relationship can have up to two indexes-- a I<to-index> and a
234  I<from-index>. These order the results when crossing the relationship. For  I<from-index>. These order the results when crossing the relationship. For
235  example, in the relationship C<HasContig> from C<Genome> to C<Contig>, the  example, in the relationship C<HasContig> from C<Genome> to C<Contig>, the
# Line 316  Line 335 
335    
336  # Table of information about our datatypes. "sqlType" is the corresponding SQL datatype string.  # Table of information about our datatypes. "sqlType" is the corresponding SQL datatype string.
337  # "maxLen" is the maximum permissible length of the incoming string data used to populate a field  # "maxLen" is the maximum permissible length of the incoming string data used to populate a field
338  # of the specified type. "dataGen" is PERL string that will be evaluated if no test data generation  # of the specified type. "avgLen" is the average byte length for estimating
339  # string is specified in the field definition. "avgLen" is the average byte length for estimating  # record sizes. "sort" is the key modifier for the sort command, "notes" is a type description.
340  # record sizes.  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",
341  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, dataGen => "StringGen('A')" },                                 notes => "single ASCII character"},
342                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, dataGen => "IntGen(0, 99999999)" },                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n",
343                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, dataGen => "StringGen(IntGen(10,250))" },                                 notes => "signed 32-bit integer"},
344                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, dataGen => "StringGen(IntGen(80,1000))" },                    counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n",
345                    date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, dataGen => "DateGen(-7, 7, IntGen(0,1400))" },                                 notes => "unsigned 32-bit integer"},
346                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, dataGen => "FloatGen(0.0, 100.0)" },                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, sort => "",
347                    boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, dataGen => "IntGen(0, 1)" },                                 notes => "character string, 0 to 255 characters"},
348                      text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, sort => "",
349                                   notes => "character string, nearly unlimited length, cannot be indexed"},
350                      date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, sort => "n",
351                                   notes => "signed, 64-bit integer"},
352                      float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, sort => "g",
353                                   notes => "64-bit double precision floating-point number"},
354                      boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, sort => "n",
355                                   notes => "boolean value: 0 if false, 1 if true"},
356                   'hash-string' =>                   'hash-string' =>
357                               { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, dataGen => "SringGen(22)" },                               { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, sort => "",
358                                   notes => "string stored in digested form, used for certain types of key fields"},
359                   'id-string' =>                   'id-string' =>
360                               { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, dataGen => "SringGen(22)" },                               { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, sort => "",
361                                   notes => "character string, 0 to 25 characters"},
362                   'key-string' =>                   'key-string' =>
363                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, dataGen => "StringGen(IntGen(10,40))" },                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, sort => "",
364                                   notes => "character string, 0 to 40 characters"},
365                   'name-string' =>                   'name-string' =>
366                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, dataGen => "StringGen(IntGen(10,80))" },                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, sort => "",
367                                   notes => "character string, 0 to 80 characters"},
368                   'medium-string' =>                   'medium-string' =>
369                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, dataGen => "StringGen(IntGen(10,160))" },                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",
370                                   notes => "character string, 0 to 160 characters"},
371                  );                  );
372    
373  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 344  Line 376 
376                     'MM' => 'many-to-many'                     'MM' => 'many-to-many'
377                   );                   );
378    
379  # Table for interpreting string patterns.  # Options for XML input and output.
380    
381    my %XmlOptions = (GroupTags =>  { Relationships => 'Relationship',
382                                      Entities => 'Entity',
383                                      Fields => 'Field',
384                                      Indexes => 'Index',
385                                      IndexFields => 'IndexField'
386                                    },
387                      KeyAttr =>    { Relationship => 'name',
388                                      Entity => 'name',
389                                      Field => 'name'
390                                    },
391                      SuppressEmpty => 1,
392                     );
393    
394  my %PictureTable = ( 'A' => "abcdefghijklmnopqrstuvwxyz",  my %XmlInOpts  = (
395                       '9' => "0123456789",                    ForceArray => ['Field', 'Index', 'IndexField'],
396                       'X' => "abcdefghijklmnopqrstuvwxyz0123456789",                    ForceContent => 1,
397                       'V' => "aeiou",                    NormalizeSpace => 2,
                      'K' => "bcdfghjklmnoprstvwxyz"  
398                     );                     );
399    my %XmlOutOpts = (
400                      RootName => 'Database',
401                      XMLDecl => 1,
402                     );
403    
404    
405  =head2 Public Methods  =head2 Public Methods
406    
# Line 493  Line 542 
542          my $entityData = $entityList->{$key};          my $entityData = $entityList->{$key};
543          # If there's descriptive text, display it.          # If there's descriptive text, display it.
544          if (my $notes = $entityData->{Notes}) {          if (my $notes = $entityData->{Notes}) {
545              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
546          }          }
547          # 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.
548          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
# Line 550  Line 599 
599          $retVal .= "</p>\n";          $retVal .= "</p>\n";
600          # If there are notes on this relationship, display them.          # If there are notes on this relationship, display them.
601          if (my $notes = $relationshipStructure->{Notes}) {          if (my $notes = $relationshipStructure->{Notes}) {
602              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
603          }          }
604          # Generate the relationship's relation table.          # Generate the relationship's relation table.
605          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
# Line 597  Line 646 
646      return Data::Dumper::Dumper($self->{_metaData});      return Data::Dumper::Dumper($self->{_metaData});
647  }  }
648    
649    =head3 FindIndexForEntity
650    
651    C<< my $indexFound = ERDB::FindIndexForEntity($xml, $entityName, $attributeName); >>
652    
653    This method locates the entry in an entity's index list that begins with the
654    specified attribute name. If the entity has no index list, one will be
655    created. This method works on raw XML, not a live ERDB object.
656    
657    =over 4
658    
659    =item xml
660    
661    The raw XML structure defining the database.
662    
663    =item entityName
664    
665    The name of the relevant entity.
666    
667    =item attributeName
668    
669    The name of the attribute relevant to the search.
670    
671    =item RETURN
672    
673    The numerical index in the index list of the index entry for the specified entity and
674    attribute, or C<undef> if no such index exists.
675    
676    =back
677    
678    =cut
679    
680    sub FindIndexForEntity {
681        # Get the parameters.
682        my ($xml, $entityName, $attributeName) = @_;
683        # Declare the return variable.
684        my $retVal;
685        # Get the named entity.
686        my $entityData = $xml->{Entities}->{$entityName};
687        if (! $entityData) {
688            Confess("Entity $entityName not found in DBD structure.");
689        } else {
690            # Insure it has an index list.
691            if (! exists $entityData->{Indexes}) {
692                $entityData->{Indexes} = [];
693            } else {
694                # Search for the desired index.
695                my $indexList = $entityData->{Indexes};
696                my $n = scalar @{$indexList};
697                Trace("Searching $n indexes in index list for $entityName.") if T(2);
698                # We use an indexed FOR here because we're returning an
699                # index number instead of an object. We do THAT so we can
700                # delete the index from the list if needed.
701                for (my $i = 0; $i < $n && !defined($retVal); $i++) {
702                    my $index = $indexList->[$i];
703                    my $fields = $index->{IndexFields};
704                    # Technically this IF should be safe (that is, we are guaranteed
705                    # the existence of a "$fields->[0]"), because when we load the XML
706                    # we have SuppressEmpty specified.
707                    if ($fields->[0]->{name} eq $attributeName) {
708                        $retVal = $i;
709                    }
710                }
711            }
712        }
713        Trace("Index for $attributeName of $entityName found at position $retVal.") if defined($retVal) && T(3);
714        Trace("Index for $attributeName not found in $entityName.") if !defined($retVal) && T(3);
715        # Return the result.
716        return $retVal;
717    }
718    
719  =head3 CreateTables  =head3 CreateTables
720    
721  C<< $erdb->CreateTables(); >>  C<< $erdb->CreateTables(); >>
# Line 684  Line 803 
803      Trace("Creating table $relationName: $fieldThing") if T(2);      Trace("Creating table $relationName: $fieldThing") if T(2);
804      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);
805      Trace("Relation $relationName created in database.") if T(2);      Trace("Relation $relationName created in database.") if T(2);
806      # If we want to build the indexes, we do it here.      # If we want to build the indexes, we do it here. Note that the full-text search
807        # index will not be built until the table has been loaded.
808      if ($indexFlag) {      if ($indexFlag) {
809          $self->CreateIndex($relationName);          $self->CreateIndex($relationName);
810      }      }
# Line 844  Line 964 
964          my @fieldList = _FixNames(@{$indexData->{IndexFields}});          my @fieldList = _FixNames(@{$indexData->{IndexFields}});
965          my $flds = join(', ', @fieldList);          my $flds = join(', ', @fieldList);
966          # Get the index's uniqueness flag.          # Get the index's uniqueness flag.
967          my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
968          # Create the index.          # Create the index.
969          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
970                                      flds => $flds, unique => $unique);                                      flds => $flds, kind => $unique);
971          if ($rv) {          if ($rv) {
972              Trace("Index created: $indexName for $relationName ($flds)") if T(1);              Trace("Index created: $indexName for $relationName ($flds)") if T(1);
973          } else {          } else {
# Line 950  Line 1070 
1070      return sort keys %{$entityList};      return sort keys %{$entityList};
1071  }  }
1072    
1073    =head3 GetDataTypes
1074    
1075    C<< my %types = ERDB::GetDataTypes(); >>
1076    
1077    Return a table of ERDB data types. The table returned is a hash of hashes.
1078    The keys of the big hash are the datatypes. Each smaller hash has several
1079    values used to manage the data. The most interesting is the SQL type (key
1080    C<sqlType>) and the descriptive node (key C<notes>).
1081    
1082    Note that changing the values in the smaller hashes will seriously break
1083    things, so this data should be treated as read-only.
1084    
1085    =cut
1086    
1087    sub GetDataTypes {
1088        return %TypeTable;
1089    }
1090    
1091    
1092  =head3 IsEntity  =head3 IsEntity
1093    
1094  C<< my $flag = $erdb->IsEntity($entityName); >>  C<< my $flag = $erdb->IsEntity($entityName); >>
# Line 1094  Line 1233 
1233      return $retVal;      return $retVal;
1234  }  }
1235    
1236    =head3 Search
1237    
1238    C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>
1239    
1240    Perform a full text search with filtering. The search will be against a specified object
1241    in the object name list. That object will get an extra field containing the search
1242    relevance. Note that except for the search expression, the parameters of this method are
1243    the same as those for L</Get> and follow the same rules.
1244    
1245    =over 4
1246    
1247    =item searchExpression
1248    
1249    Boolean search expression for the text fields of the target object.
1250    
1251    =item idx
1252    
1253    Index in the I<$objectNames> list of the table to be searched in full-text mode.
1254    
1255    =item objectNames
1256    
1257    List containing the names of the entity and relationship objects to be retrieved.
1258    
1259    =item filterClause
1260    
1261    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1262    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
1263    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
1264    in the filter clause should be added to the parameter list as additional parameters. The
1265    fields in a filter clause can come from primary entity relations, relationship relations,
1266    or secondary entity relations; however, all of the entities and relationships involved must
1267    be included in the list of object names.
1268    
1269    =item params
1270    
1271    Reference to a list of parameter values to be substituted into the filter clause.
1272    
1273    =item RETURN
1274    
1275    Returns a query object for the specified search.
1276    
1277    =back
1278    
1279    =cut
1280    
1281    sub Search {
1282        # Get the parameters.
1283        my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1284        # Declare the return variable.
1285        my $retVal;
1286        # Create a safety copy of the parameter list. Note we have to be careful to insure
1287        # a parameter list exists before we copy it.
1288        my @myParams = ();
1289        if (defined $params) {
1290            @myParams = @{$params};
1291        }
1292        # Get the first object's structure so we have access to the searchable fields.
1293        my $object1Name = $objectNames->[$idx];
1294        my $object1Structure = $self->_GetStructure($object1Name);
1295        # Get the field list.
1296        if (! exists $object1Structure->{searchFields}) {
1297            Confess("No searchable index for $object1Name.");
1298        } else {
1299            # Get the field list.
1300            my @fields = @{$object1Structure->{searchFields}};
1301            # Clean the search expression.
1302            my $actualKeywords = $self->CleanKeywords($searchExpression);
1303            Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1304            # We need two match expressions, one for the filter clause and one in the
1305            # query itself. Both will use a parameter mark, so we need to push the
1306            # search expression onto the front of the parameter list twice.
1307            unshift @myParams, $actualKeywords, $actualKeywords;
1308            # Build the match expression.
1309            my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
1310            my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
1311            # Process the SQL stuff.
1312            my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1313                $self->_SetupSQL($objectNames, $filterClause, $matchClause);
1314            # Create the query. Note that the match clause is inserted at the front of
1315            # the select fields.
1316            my $command = "SELECT DISTINCT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .
1317                ".* $suffix";
1318            my $sth = $self->_GetStatementHandle($command, \@myParams);
1319            # Now we create the relation map, which enables DBQuery to determine the order, name
1320            # and mapped name for each object in the query.
1321            my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
1322            # Return the statement object.
1323            $retVal = DBQuery::_new($self, $sth, \@relationMap, $object1Name);
1324        }
1325        return $retVal;
1326    }
1327    
1328  =head3 GetFlat  =head3 GetFlat
1329    
1330  C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>  C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>
# Line 1147  Line 1378 
1378      return @retVal;      return @retVal;
1379  }  }
1380    
1381    =head3 SpecialFields
1382    
1383    C<< my %specials = $erdb->SpecialFields($entityName); >>
1384    
1385    Return a hash mapping special fields in the specified entity to the value of their
1386    C<special> attribute. This enables the subclass to get access to the special field
1387    attributes without needed to plumb the internal ERDB data structures.
1388    
1389    =over 4
1390    
1391    =item entityName
1392    
1393    Name of the entity whose special fields are desired.
1394    
1395    =item RETURN
1396    
1397    Returns a hash. The keys of the hash are the special field names, and the values
1398    are the values from each special field's C<special> attribute.
1399    
1400    =back
1401    
1402    =cut
1403    
1404    sub SpecialFields {
1405        # Get the parameters.
1406        my ($self, $entityName) = @_;
1407        # Declare the return variable.
1408        my %retVal = ();
1409        # Find the entity's data structure.
1410        my $entityData = $self->{Entities}->{$entityName};
1411        # Loop through its fields, adding each special field to the return hash.
1412        my $fieldHash = $entityData->{Fields};
1413        for my $fieldName (keys %{$fieldHash}) {
1414            my $fieldData = $fieldHash->{$fieldName};
1415            if (exists $fieldData->{special}) {
1416                $retVal{$fieldName} = $fieldData->{special};
1417            }
1418        }
1419        # Return the result.
1420        return %retVal;
1421    }
1422    
1423  =head3 Delete  =head3 Delete
1424    
1425  C<< my $stats = $erdb->Delete($entityName, $objectID); >>  C<< my $stats = $erdb->Delete($entityName, $objectID); >>
# Line 1315  Line 1588 
1588      return $retVal;      return $retVal;
1589  }  }
1590    
1591    =head3 SortNeeded
1592    
1593    C<< my $parms = $erdb->SortNeeded($relationName); >>
1594    
1595    Return the pipe command for the sort that should be applied to the specified
1596    relation when creating the load file.
1597    
1598    For example, if the load file should be sorted ascending by the first
1599    field, this method would return
1600    
1601        sort -k1 -t"\t"
1602    
1603    If the first field is numeric, the method would return
1604    
1605        sort -k1n -t"\t"
1606    
1607    Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate
1608    keys using a sort.
1609    
1610    =over 4
1611    
1612    =item relationName
1613    
1614    Name of the relation to be examined.
1615    
1616    =item
1617    
1618    Returns the sort command to use for sorting the relation, suitable for piping.
1619    
1620    =back
1621    
1622    =cut
1623    #: Return Type $;
1624    sub SortNeeded {
1625        # Get the parameters.
1626        my ($self, $relationName) = @_;
1627        # Declare a descriptor to hold the names of the key fields.
1628        my @keyNames = ();
1629        # Get the relation structure.
1630        my $relationData = $self->_FindRelation($relationName);
1631        # Find out if the relation is a primary entity relation,
1632        # a relationship relation, or a secondary entity relation.
1633        my $entityTable = $self->{_metaData}->{Entities};
1634        my $relationshipTable = $self->{_metaData}->{Relationships};
1635        if (exists $entityTable->{$relationName}) {
1636            # Here we have a primary entity relation.
1637            push @keyNames, "id";
1638        } elsif (exists $relationshipTable->{$relationName}) {
1639            # Here we have a relationship. We sort using the FROM index.
1640            my $relationshipData = $relationshipTable->{$relationName};
1641            my $index = $relationData->{Indexes}->{"idx${relationName}From"};
1642            push @keyNames, @{$index->{IndexFields}};
1643        } else {
1644            # Here we have a secondary entity relation, so we have a sort on the ID field.
1645            push @keyNames, "id";
1646        }
1647        # Now we parse the key names into sort parameters. First, we prime the return
1648        # string.
1649        my $retVal = "sort -t\"\t\" ";
1650        # Get the relation's field list.
1651        my @fields = @{$relationData->{Fields}};
1652        # Loop through the keys.
1653        for my $keyData (@keyNames) {
1654            # Get the key and the ordering.
1655            my ($keyName, $ordering);
1656            if ($keyData =~ /^([^ ]+) DESC/) {
1657                ($keyName, $ordering) = ($1, "descending");
1658            } else {
1659                ($keyName, $ordering) = ($keyData, "ascending");
1660            }
1661            # Find the key's position and type.
1662            my $fieldSpec;
1663            for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {
1664                my $thisField = $fields[$i];
1665                if ($thisField->{name} eq $keyName) {
1666                    # Get the sort modifier for this field type. The modifier
1667                    # decides whether we're using a character, numeric, or
1668                    # floating-point sort.
1669                    my $modifier = $TypeTable{$thisField->{type}}->{sort};
1670                    # If the index is descending for this field, denote we want
1671                    # to reverse the sort order on this field.
1672                    if ($ordering eq 'descending') {
1673                        $modifier .= "r";
1674                    }
1675                    # Store the position and modifier into the field spec, which
1676                    # will stop the inner loop. Note that the field number is
1677                    # 1-based in the sort command, so we have to increment the
1678                    # index.
1679                    $fieldSpec = ($i + 1) . $modifier;
1680                }
1681            }
1682            # Add this field to the sort command.
1683            $retVal .= " -k$fieldSpec";
1684        }
1685        # Return the result.
1686        return $retVal;
1687    }
1688    
1689  =head3 GetList  =head3 GetList
1690    
1691  C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>  C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>
# Line 1431  Line 1802 
1802  sub GetCount {  sub GetCount {
1803      # Get the parameters.      # Get the parameters.
1804      my ($self, $objectNames, $filter, $params) = @_;      my ($self, $objectNames, $filter, $params) = @_;
1805        # Insure the params argument is an array reference if the caller left it off.
1806        if (! defined($params)) {
1807            $params = [];
1808        }
1809      # Declare the return variable.      # Declare the return variable.
1810      my $retVal;      my $retVal;
1811      # Find out if we're counting an entity or a relationship.      # Find out if we're counting an entity or a relationship.
# Line 1544  Line 1919 
1919      }      }
1920  }  }
1921    
1922    =head3 InsertValue
1923    
1924    C<< $erdb->InsertValue($entityID, $fieldName, $value); >>
1925    
1926    This method will insert a new value into the database. The value must be one
1927    associated with a secondary relation, since primary values cannot be inserted:
1928    they occur exactly once. Secondary values, on the other hand, can be missing
1929    or multiply-occurring.
1930    
1931    =over 4
1932    
1933    =item entityID
1934    
1935    ID of the object that is to receive the new value.
1936    
1937    =item fieldName
1938    
1939    Field name for the new value-- this includes the entity name, since
1940    field names are of the format I<objectName>C<(>I<fieldName>C<)>.
1941    
1942    =item value
1943    
1944    New value to be put in the field.
1945    
1946    =back
1947    
1948    =cut
1949    
1950    sub InsertValue {
1951        # Get the parameters.
1952        my ($self, $entityID, $fieldName, $value) = @_;
1953        # Parse the entity name and the real field name.
1954        if ($fieldName =~ /^([^(]+)\(([^)]+)\)/) {
1955            my $entityName = $1;
1956            my $fieldTitle = $2;
1957            # Get its descriptor.
1958            if (!$self->IsEntity($entityName)) {
1959                Confess("$entityName is not a valid entity.");
1960            } else {
1961                my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1962                # Find the relation containing this field.
1963                my $fieldHash = $entityData->{Fields};
1964                if (! exists $fieldHash->{$fieldTitle}) {
1965                    Confess("$fieldTitle not found in $entityName.");
1966                } else {
1967                    my $relation = $fieldHash->{$fieldTitle}->{relation};
1968                    if ($relation eq $entityName) {
1969                        Confess("Cannot do InsertValue on primary field $fieldTitle of $entityName.");
1970                    } else {
1971                        # Now we can create an INSERT statement.
1972                        my $dbh = $self->{_dbh};
1973                        my $fixedName = _FixName($fieldTitle);
1974                        my $statement = "INSERT INTO $relation (id, $fixedName) VALUES(?, ?)";
1975                        # Execute the command.
1976                        $dbh->SQL($statement, 0, $entityID, $value);
1977                    }
1978                }
1979            }
1980        } else {
1981            Confess("$fieldName is not a valid field name.");
1982        }
1983    }
1984    
1985  =head3 InsertObject  =head3 InsertObject
1986    
1987  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>
# Line 1560  Line 1998 
1998  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
1999  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
2000    
2001  C<< $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>  C<< $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>
2002    
2003  =over 4  =over 4
2004    
# Line 1752  Line 2190 
2190      };      };
2191      if (!defined $rv) {      if (!defined $rv) {
2192          $retVal->AddMessage($@) if ($@);          $retVal->AddMessage($@) if ($@);
2193          $retVal->AddMessage("Table load failed for $relationName using $fileName.");          $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2194          Trace("Table load failed for $relationName.") if T(1);          Trace("Table load failed for $relationName.") if T(1);
2195      } else {      } else {
2196          # Here we successfully loaded the table.          # Here we successfully loaded the table.
# Line 1760  Line 2198 
2198          my $size = -s $fileName;          my $size = -s $fileName;
2199          Trace("$size bytes loaded into $relationName.") if T(2);          Trace("$size bytes loaded into $relationName.") if T(2);
2200          # If we're rebuilding, we need to create the table indexes.          # If we're rebuilding, we need to create the table indexes.
2201          if ($truncateFlag && ! $dbh->{_preIndex}) {          if ($truncateFlag) {
2202                # Indexes are created here for PostGres. For PostGres, indexes are
2203                # best built at the end. For MySQL, the reverse is true.
2204                if (! $dbh->{_preIndex}) {
2205              eval {              eval {
2206                  $self->CreateIndex($relationName);                  $self->CreateIndex($relationName);
2207              };              };
# Line 1768  Line 2209 
2209                  $retVal->AddMessage($@);                  $retVal->AddMessage($@);
2210              }              }
2211          }          }
2212                # The full-text index (if any) is always built last, even for MySQL.
2213                # First we need to see if this table has a full-text index. Only
2214                # primary relations are allowed that privilege.
2215                if ($self->_IsPrimary($relationName)) {
2216                    # Get the relation's entity/relationship structure.
2217                    my $structure = $self->_GetStructure($relationName);
2218                    # Check for a searchable fields list.
2219                    if (exists $structure->{searchFields}) {
2220                        # Here we know that we need to create a full-text search index.
2221                        # Get an SQL-formatted field name list.
2222                        my $fields = join(", ", $self->_FixNames(@{$structure->{searchFields}}));
2223                        # Create the index.
2224                        $dbh->create_index(tbl => $relationName, idx => "search_idx_$relationName",
2225                                           flds => $fields, kind => 'fulltext');
2226                    }
2227                }
2228            }
2229      }      }
2230      # Analyze the table to improve performance.      # Analyze the table to improve performance.
2231        Trace("Analyzing and compacting $relationName.") if T(3);
2232      $dbh->vacuum_it($relationName);      $dbh->vacuum_it($relationName);
2233        Trace("$relationName load completed.") if T(3);
2234      # Return the statistics.      # Return the statistics.
2235      return $retVal;      return $retVal;
2236  }  }
2237    
2238  =head3 GenerateEntity  =head3 DropRelation
   
 C<< my $fieldHash = $erdb->GenerateEntity($id, $type, \%values); >>  
2239    
2240  Generate the data for a new entity instance. This method creates a field hash suitable for  C<< $erdb->DropRelation($relationName); >>
 passing as a parameter to L</InsertObject>. The ID is specified by the callr, but the rest  
 of the fields are generated using information in the database schema.  
2241    
2242  Each data type has a default algorithm for generating random test data. This can be overridden  Physically drop a relation from the database.
 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.  
2243    
2244  =over 4  =over 4
2245    
2246  =item id  =item relationName
   
 ID to assign to the new entity.  
   
 =item type  
   
 Type name for the new entity.  
   
 =item values  
2247    
2248  Hash containing additional values that might be needed by the data generation methods (optional).  Name of the relation to drop. If it does not exist, this method will have
2249    no effect.
2250    
2251  =back  =back
2252    
2253  =cut  =cut
2254    
2255  sub GenerateEntity {  sub DropRelation {
2256      # Get the parameters.      # Get the parameters.
2257      my ($self, $id, $type, $values) = @_;      my ($self, $relationName) = @_;
2258      # Create the return hash.      # Get the database handle.
2259      my $this = { id => $id };      my $dbh = $self->{_dbh};
2260      # Get the metadata structure.      # Drop the relation. The method used here has no effect if the relation
2261      my $metadata = $self->{_metaData};      # does not exist.
2262      # Get this entity's list of fields.      Trace("Invoking DB Kernel to drop $relationName.") if T(3);
2263      if (!exists $metadata->{Entities}->{$type}) {      $dbh->drop_table(tbl => $relationName);
         Confess("Unrecognized entity type $type in GenerateEntity.");  
     } else {  
         my $entity = $metadata->{Entities}->{$type};  
         my $fields = $entity->{Fields};  
         # Generate data from the fields.  
         _GenerateFields($this, $fields, $type, $values);  
     }  
     # Return the hash created.  
     return $this;  
2264  }  }
2265    
2266  =head3 GetEntity  =head3 GetEntity
# Line 1869  Line 2299 
2299      return $retVal;      return $retVal;
2300  }  }
2301    
2302    =head3 GetChoices
2303    
2304    C<< my @values = $erdb->GetChoices($entityName, $fieldName); >>
2305    
2306    Return a list of all the values for the specified field that are represented in the
2307    specified entity.
2308    
2309    Note that if the field is not indexed, then this will be a very slow operation.
2310    
2311    =over 4
2312    
2313    =item entityName
2314    
2315    Name of an entity in the database.
2316    
2317    =item fieldName
2318    
2319    Name of a field belonging to the entity. This is a raw field name without
2320    the standard parenthesized notation used in most calls.
2321    
2322    =item RETURN
2323    
2324    Returns a list of the distinct values for the specified field in the database.
2325    
2326    =back
2327    
2328    =cut
2329    
2330    sub GetChoices {
2331        # Get the parameters.
2332        my ($self, $entityName, $fieldName) = @_;
2333        # Declare the return variable.
2334        my @retVal;
2335        # Get the entity data structure.
2336        my $entityData = $self->_GetStructure($entityName);
2337        # Get the field.
2338        my $fieldHash = $entityData->{Fields};
2339        if (! exists $fieldHash->{$fieldName}) {
2340            Confess("$fieldName not found in $entityName.");
2341        } else {
2342            # Get the name of the relation containing the field.
2343            my $relation = $fieldHash->{$fieldName}->{relation};
2344            # Fix up the field name.
2345            my $realName = _FixName($fieldName);
2346            # Get the database handle.
2347            my $dbh = $self->{_dbh};
2348            # Query the database.
2349            my $results = $dbh->SQL("SELECT DISTINCT $realName FROM $relation");
2350            # Clean the results. They are stored as a list of lists, and we just want the one list.
2351            @retVal = sort map { $_->[0] } @{$results};
2352        }
2353        # Return the result.
2354        return @retVal;
2355    }
2356    
2357  =head3 GetEntityValues  =head3 GetEntityValues
2358    
2359  C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>  C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>
2360    
2361  Return a list of values from a specified entity instance.  Return a list of values from a specified entity instance. If the entity instance
2362    does not exist, an empty list is returned.
2363    
2364  =over 4  =over 4
2365    
# Line 2001  Line 2487 
2487          push @retVal, \@rowData;          push @retVal, \@rowData;
2488          $fetched++;          $fetched++;
2489      }      }
2490        Trace("$fetched rows returned in GetAll.") if T(SQL => 4);
2491      # Return the resulting list.      # Return the resulting list.
2492      return @retVal;      return @retVal;
2493  }  }
2494    
2495  =head3 EstimateRowSize  =head3 Exists
2496    
2497  C<< my $rowSize = $erdb->EstimateRowSize($relName); >>  C<< my $found = $sprout->Exists($entityName, $entityID); >>
2498    
2499  Estimate the row size of the specified relation. The estimated row size is computed by adding  Return TRUE if an entity exists, else FALSE.
 up the average length for each data type.  
2500    
2501  =over 4  =over 4
2502    
2503  =item relName  =item entityName
2504    
2505    Name of the entity type (e.g. C<Feature>) relevant to the existence check.
2506    
2507    =item entityID
2508    
2509    ID of the entity instance whose existence is to be checked.
2510    
2511    =item RETURN
2512    
2513    Returns TRUE if the entity instance exists, else FALSE.
2514    
2515    =back
2516    
2517    =cut
2518    #: Return Type $;
2519    sub Exists {
2520        # Get the parameters.
2521        my ($self, $entityName, $entityID) = @_;
2522        # Check for the entity instance.
2523        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
2524        my $testInstance = $self->GetEntity($entityName, $entityID);
2525        # Return an existence indicator.
2526        my $retVal = ($testInstance ? 1 : 0);
2527        return $retVal;
2528    }
2529    
2530    =head3 EstimateRowSize
2531    
2532    C<< my $rowSize = $erdb->EstimateRowSize($relName); >>
2533    
2534    Estimate the row size of the specified relation. The estimated row size is computed by adding
2535    up the average length for each data type.
2536    
2537    =over 4
2538    
2539    =item relName
2540    
2541  Name of the relation whose estimated row size is desired.  Name of the relation whose estimated row size is desired.
2542    
# Line 2072  Line 2594 
2594      return $objectData->{Fields};      return $objectData->{Fields};
2595  }  }
2596    
2597    =head3 SplitKeywords
2598    
2599    C<< my @keywords = ERDB::SplitKeywords($keywordString); >>
2600    
2601    This method returns a list of the positive keywords in the specified
2602    keyword string. All of the operators will have been stripped off,
2603    and if the keyword is preceded by a minus operator (C<->), it will
2604    not be in the list returned. The idea here is to get a list of the
2605    keywords the user wants to see. The list will be processed to remove
2606    duplicates.
2607    
2608    It is possible to create a string that confuses this method. For example
2609    
2610        frog toad -frog
2611    
2612    would return both C<frog> and C<toad>. If this is a problem we can deal
2613    with it later.
2614    
2615    =over 4
2616    
2617    =item keywordString
2618    
2619    The keyword string to be parsed.
2620    
2621    =item RETURN
2622    
2623    Returns a list of the words in the keyword string the user wants to
2624    see.
2625    
2626    =back
2627    
2628    =cut
2629    
2630    sub SplitKeywords {
2631        # Get the parameters.
2632        my ($keywordString) = @_;
2633        # Make a safety copy of the string. (This helps during debugging.)
2634        my $workString = $keywordString;
2635        # Convert operators we don't care about to spaces.
2636        $workString =~ tr/+"()<>/ /;
2637        # Split the rest of the string along space boundaries. Note that we
2638        # eliminate any words that are zero length or begin with a minus sign.
2639        my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
2640        # Use a hash to remove duplicates.
2641        my %words = map { $_ => 1 } @wordList;
2642        # Return the result.
2643        return sort keys %words;
2644    }
2645    
2646    =head3 ValidateFieldName
2647    
2648    C<< my $okFlag = ERDB::ValidateFieldName($fieldName); >>
2649    
2650    Return TRUE if the specified field name is valid, else FALSE. Valid field names must
2651    be hyphenated words subject to certain restrictions.
2652    
2653    =over 4
2654    
2655    =item fieldName
2656    
2657    Field name to be validated.
2658    
2659    =item RETURN
2660    
2661    Returns TRUE if the field name is valid, else FALSE.
2662    
2663    =back
2664    
2665    =cut
2666    
2667    sub ValidateFieldName {
2668        # Get the parameters.
2669        my ($fieldName) = @_;
2670        # Declare the return variable. The field name is valid until we hear
2671        # differently.
2672        my $retVal = 1;
2673        # Look for bad stuff in the name.
2674        if ($fieldName =~ /--/) {
2675            # Here we have a doubled minus sign.
2676            Trace("Field name $fieldName has a doubled hyphen.") if T(1);
2677            $retVal = 0;
2678        } elsif ($fieldName !~ /^[A-Za-z]/) {
2679            # Here the field name is missing the initial letter.
2680            Trace("Field name $fieldName does not begin with a letter.") if T(1);
2681            $retVal = 0;
2682        } else {
2683            # Strip out the minus signs. Everything remaining must be a letter
2684            # or digit.
2685            my $strippedName = $fieldName;
2686            $strippedName =~ s/-//g;
2687            if ($strippedName !~ /^[A-Za-z0-9]+$/) {
2688                Trace("Field name $fieldName contains illegal characters.") if T(1);
2689                $retVal = 0;
2690            }
2691        }
2692        # Return the result.
2693        return $retVal;
2694    }
2695    
2696    =head3 ReadMetaXML
2697    
2698    C<< my $rawMetaData = ERDB::ReadDBD($fileName); >>
2699    
2700    This method reads a raw database definition XML file and returns it.
2701    Normally, the metadata used by the ERDB system has been processed and
2702    modified to make it easier to load and retrieve the data; however,
2703    this method can be used to get the data in its raw form.
2704    
2705    =over 4
2706    
2707    =item fileName
2708    
2709    Name of the XML file to read.
2710    
2711    =item RETURN
2712    
2713    Returns a hash reference containing the raw XML data from the specified file.
2714    
2715    =back
2716    
2717    =cut
2718    
2719    sub ReadMetaXML {
2720        # Get the parameters.
2721        my ($fileName) = @_;
2722        # Read the XML.
2723        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
2724        Trace("XML metadata loaded from file $fileName.") if T(1);
2725        # Return the result.
2726        return $retVal;
2727    }
2728    
2729    =head3 GetEntityFieldHash
2730    
2731    C<< my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName); >>
2732    
2733    Get the field hash of the named entity in the specified raw XML structure.
2734    The field hash may not exist, in which case we need to create it.
2735    
2736    =over 4
2737    
2738    =item structure
2739    
2740    Raw XML structure defininng the database. This is not the run-time XML used by
2741    an ERDB object, since that has all sorts of optimizations built-in.
2742    
2743    =item entityName
2744    
2745    Name of the entity whose field structure is desired.
2746    
2747    =item RETURN
2748    
2749    Returns the field hash used to define the entity's fields.
2750    
2751    =back
2752    
2753    =cut
2754    
2755    sub GetEntityFieldHash {
2756        # Get the parameters.
2757        my ($structure, $entityName) = @_;
2758        # Get the entity structure.
2759        my $entityData = $structure->{Entities}->{$entityName};
2760        # Look for a field structure.
2761        my $retVal = $entityData->{Fields};
2762        # If it doesn't exist, create it.
2763        if (! defined($retVal)) {
2764            $entityData->{Fields} = {};
2765            $retVal = $entityData->{Fields};
2766        }
2767        # Return the result.
2768        return $retVal;
2769    }
2770    
2771    =head3 WriteMetaXML
2772    
2773    C<< ERDB::WriteMetaXML($structure, $fileName); >>
2774    
2775    Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
2776    used to update the database definition. It must be used with care, however, since it
2777    will only work on a raw structure, not on the processed structure created by an ERDB
2778    constructor.
2779    
2780    =over 4
2781    
2782    =item structure
2783    
2784    XML structure to be written to the file.
2785    
2786    =item fileName
2787    
2788    Name of the output file to which the updated XML should be stored.
2789    
2790    =back
2791    
2792    =cut
2793    
2794    sub WriteMetaXML {
2795        # Get the parameters.
2796        my ($structure, $fileName) = @_;
2797        # Compute the output.
2798        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
2799        # Write it to the file.
2800        my $xmlOut = Open(undef, ">$fileName");
2801        print $xmlOut $fileString;
2802    }
2803    
2804    
2805    =head3 HTMLNote
2806    
2807    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
2808    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
2809    Except for C<[p]>, all the codes are closed by slash-codes. So, for
2810    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
2811    
2812    C<< my $realHtml = ERDB::HTMLNote($dataString); >>
2813    
2814    =over 4
2815    
2816    =item dataString
2817    
2818    String to convert to HTML.
2819    
2820    =item RETURN
2821    
2822    An HTML string derived from the input string.
2823    
2824    =back
2825    
2826    =cut
2827    
2828    sub HTMLNote {
2829        # Get the parameter.
2830        my ($dataString) = @_;
2831        # HTML-escape the text.
2832        my $retVal = CGI::escapeHTML($dataString);
2833        # Substitute the bulletin board codes.
2834        $retVal =~ s!\[(/?[bi])\]!<$1>!g;
2835        $retVal =~ s!\[p\]!</p><p>!g;
2836        # Return the result.
2837        return $retVal;
2838    }
2839    
2840    
2841  =head2 Data Mining Methods  =head2 Data Mining Methods
2842    
2843  =head3 GetUsefulCrossValues  =head3 GetUsefulCrossValues
# Line 2195  Line 2961 
2961    
2962  =head3 ParseColumns  =head3 ParseColumns
2963    
2964  C<< my @columns = ERDB->ParseColumns($line); >>  C<< my @columns = ERDB::ParseColumns($line); >>
2965    
2966  Convert the specified data line to a list of columns.  Convert the specified data line to a list of columns.
2967    
# Line 2216  Line 2982 
2982    
2983  sub ParseColumns {  sub ParseColumns {
2984      # Get the parameters.      # Get the parameters.
2985      my ($self, $line) = @_;      my ($line) = @_;
2986      # Chop off the line-end.      # Chop off the line-end.
2987      chomp $line;      chomp $line;
2988      # Split it into a list.      # Split it into a list.
# Line 2225  Line 2991 
2991      return @retVal;      return @retVal;
2992  }  }
2993    
2994    =head2 Virtual Methods
2995    
2996    =head3 CleanKeywords
2997    
2998    C<< my $cleanedString = $erdb->CleanKeywords($searchExpression); >>
2999    
3000    Clean up a search expression or keyword list. This is a virtual method that may
3001    be overridden by the subclass. The base-class method removes extra spaces
3002    and converts everything to lower case.
3003    
3004    =over 4
3005    
3006    =item searchExpression
3007    
3008    Search expression or keyword list to clean. Note that a search expression may
3009    contain boolean operators which need to be preserved. This includes leading
3010    minus signs.
3011    
3012    =item RETURN
3013    
3014    Cleaned expression or keyword list.
3015    
3016    =back
3017    
3018    =cut
3019    
3020    sub CleanKeywords {
3021        # Get the parameters.
3022        my ($self, $searchExpression) = @_;
3023        # Lower-case the expression and copy it into the return variable. Note that we insure we
3024        # don't accidentally end up with an undefined value.
3025        my $retVal = lc($searchExpression || "");
3026        # Remove extra spaces.
3027        $retVal =~ s/\s+/ /g;
3028        $retVal =~ s/(^\s+)|(\s+$)//g;
3029        # Return the result.
3030        return $retVal;
3031    }
3032    
3033    =head3 GetSourceObject
3034    
3035    C<< my $source = $erdb->GetSourceObject($entityName); >>
3036    
3037    Return the object to be used in loading special attributes of the specified entity. The
3038    algorithm for loading special attributes is stored in the C<DataGen> elements of the
3039    XML
3040    
3041  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3042    
3043  =head3 SetupSQL  =head3 _RelationMap
3044    
3045    C<< my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef); >>
3046    
3047    Create the relation map for an SQL query. The relation map is used by B<DBObject>
3048    to determine how to interpret the results of the query.
3049    
3050    =over 4
3051    
3052    =item mappedNameHashRef
3053    
3054    Reference to a hash that maps modified object names to real object names.
3055    
3056    =item mappedNameListRef
3057    
3058    Reference to a list of modified object names in the order they appear in the
3059    SELECT list.
3060    
3061    =item RETURN
3062    
3063    Returns a list of 2-tuples. Each tuple consists of an object name as used in the
3064    query followed by the actual name of that object. This enables the B<DBObject> to
3065    determine the order of the tables in the query and which object name belongs to each
3066    mapped object name. Most of the time these two values are the same; however, if a
3067    relation occurs twice in the query, the relation name in the field list and WHERE
3068    clause will use a mapped name (generally the actual relation name with a numeric
3069    suffix) that does not match the actual relation name.
3070    
3071    =back
3072    
3073    =cut
3074    
3075    sub _RelationMap {
3076        # Get the parameters.
3077        my ($mappedNameHashRef, $mappedNameListRef) = @_;
3078        # Declare the return variable.
3079        my @retVal = ();
3080        # Build the map.
3081        for my $mappedName (@{$mappedNameListRef}) {
3082            push @retVal, [$mappedName, $mappedNameHashRef->{$mappedName}];
3083        }
3084        # Return it.
3085        return @retVal;
3086    }
3087    
3088    
3089    =head3 _SetupSQL
3090    
3091  Process a list of object names and a filter clause so that they can be used to  Process a list of object names and a filter clause so that they can be used to
3092  build an SQL statement. This method takes in a reference to a list of object names  build an SQL statement. This method takes in a reference to a list of object names
# Line 2247  Line 3106 
3106  A string containing the WHERE clause for the query (without the C<WHERE>) and also  A string containing the WHERE clause for the query (without the C<WHERE>) and also
3107  optionally the C<ORDER BY> and C<LIMIT> clauses.  optionally the C<ORDER BY> and C<LIMIT> clauses.
3108    
3109    =item matchClause
3110    
3111    An optional full-text search clause. If specified, it will be inserted at the
3112    front of the WHERE clause. It should already be SQL-formatted; that is, the
3113    field names should be in the form I<table>C<.>I<fieldName>.
3114    
3115  =item RETURN  =item RETURN
3116    
3117  Returns a three-element list. The first element is the SQL statement suffix, beginning  Returns a three-element list. The first element is the SQL statement suffix, beginning
# Line 2259  Line 3124 
3124  =cut  =cut
3125    
3126  sub _SetupSQL {  sub _SetupSQL {
3127      my ($self, $objectNames, $filterClause) = @_;      my ($self, $objectNames, $filterClause, $matchClause) = @_;
3128      # Adjust the list of object names to account for multiple occurrences of the      # Adjust the list of object names to account for multiple occurrences of the
3129      # same object. We start with a hash table keyed on object name that will      # same object. We start with a hash table keyed on object name that will
3130      # return the object suffix. The first time an object is encountered it will      # return the object suffix. The first time an object is encountered it will
# Line 2308  Line 3173 
3173      # FROM name1, name2, ... nameN      # FROM name1, name2, ... nameN
3174      #      #
3175      my $suffix = "FROM " . join(', ', @fromList);      my $suffix = "FROM " . join(', ', @fromList);
3176        # Now for the WHERE. First, we need a place for the filter string.
3177        my $filterString = "";
3178        # We will also keep a list of conditions to add to the WHERE clause in order to link
3179        # entities and relationships as well as primary relations to secondary ones.
3180        my @joinWhere = ();
3181      # Check for a filter clause.      # Check for a filter clause.
3182      if ($filterClause) {      if ($filterClause) {
3183          # Here we have one, so we convert its field names and add it to the query. First,          # Here we have one, so we convert its field names and add it to the query. First,
3184          # We create a copy of the filter string we can work with.          # We create a copy of the filter string we can work with.
3185          my $filterString = $filterClause;          $filterString = $filterClause;
3186          # Next, we sort the object names by length. This helps protect us from finding          # Next, we sort the object names by length. This helps protect us from finding
3187          # object names inside other object names when we're doing our search and replace.          # object names inside other object names when we're doing our search and replace.
3188          my @sortedNames = sort { length($b) - length($a) } @mappedNameList;          my @sortedNames = sort { length($b) - length($a) } @mappedNameList;
         # We will also keep a list of conditions to add to the WHERE clause in order to link  
         # entities and relationships as well as primary relations to secondary ones.  
         my @joinWhere = ();  
3189          # The final preparatory step is to create a hash table of relation names. The          # The final preparatory step is to create a hash table of relation names. The
3190          # table begins with the relation names already in the SELECT command. We may          # table begins with the relation names already in the SELECT command. We may
3191          # need to add relations later if there is filtering on a field in a secondary          # need to add relations later if there is filtering on a field in a secondary
# Line 2386  Line 3253 
3253                  }                  }
3254              }              }
3255          }          }
3256        }
3257          # The next step is to join the objects together. We only need to do this if there          # The next step is to join the objects together. We only need to do this if there
3258          # is more than one object in the object list. We start with the first object and          # is more than one object in the object list. We start with the first object and
3259          # run through the objects after it. Note also that we make a safety copy of the          # run through the objects after it. Note also that we make a safety copy of the
3260          # list before running through it.      # list before running through it, because we shift off the first object before
3261        # processing the rest.
3262          my @mappedObjectList = @mappedNameList;          my @mappedObjectList = @mappedNameList;
3263          my $lastMappedObject = shift @mappedObjectList;          my $lastMappedObject = shift @mappedObjectList;
3264          # Get the join table.          # Get the join table.
# Line 2418  Line 3287 
3287          # here is we want the filter clause to be empty if there's no WHERE filter.          # here is we want the filter clause to be empty if there's no WHERE filter.
3288          # We'll put the ORDER BY / LIMIT clauses in the following variable.          # We'll put the ORDER BY / LIMIT clauses in the following variable.
3289          my $orderClause = "";          my $orderClause = "";
3290        # This is only necessary if we have a filter string in which the ORDER BY
3291        # and LIMIT clauses can live.
3292        if ($filterString) {
3293          # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy          # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy
3294          # operator so that we find the first occurrence of either verb.          # operator so that we find the first occurrence of either verb.
3295          if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {          if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {
# Line 2426  Line 3298 
3298              $orderClause = $2 . substr($filterString, $pos);              $orderClause = $2 . substr($filterString, $pos);
3299              $filterString = $1;              $filterString = $1;
3300          }          }
3301          # Add the filter and the join clauses (if any) to the SELECT command.      }
3302        # All the things that are supposed to be in the WHERE clause of the
3303        # SELECT command need to be put into @joinWhere so we can string them
3304        # together. We begin with the match clause. This is important,
3305        # because the match clause's parameter mark must precede any parameter
3306        # marks in the filter string.
3307        if ($matchClause) {
3308            push @joinWhere, $matchClause;
3309        }
3310        # Add the filter string. We put it in parentheses to avoid operator
3311        # precedence problems with the match clause or the joins.
3312          if ($filterString) {          if ($filterString) {
3313              Trace("Filter string is \"$filterString\".") if T(4);              Trace("Filter string is \"$filterString\".") if T(4);
3314              push @joinWhere, "($filterString)";              push @joinWhere, "($filterString)";
3315          }          }
3316        # String it all together into a big filter clause.
3317          if (@joinWhere) {          if (@joinWhere) {
3318              $suffix .= " WHERE " . join(' AND ', @joinWhere);              $suffix .= " WHERE " . join(' AND ', @joinWhere);
3319          }          }
3320          # Add the sort or limit clause (if any) to the SELECT command.      # Add the sort or limit clause (if any).
3321          if ($orderClause) {          if ($orderClause) {
3322              $suffix .= " $orderClause";              $suffix .= " $orderClause";
3323          }          }
     }  
3324      # Return the suffix, the mapped name list, and the mapped name hash.      # Return the suffix, the mapped name list, and the mapped name hash.
3325      return ($suffix, \@mappedNameList, \%mappedNameHash);      return ($suffix, \@mappedNameList, \%mappedNameHash);
3326  }  }
3327    
3328  =head3 GetStatementHandle  =head3 _GetStatementHandle
3329    
3330  This method will prepare and execute an SQL query, returning the statement handle.  This method will prepare and execute an SQL query, returning the statement handle.
3331  The main reason for doing this here is so that everybody who does SQL queries gets  The main reason for doing this here is so that everybody who does SQL queries gets
# Line 2486  Line 3368 
3368      return $sth;      return $sth;
3369  }  }
3370    
3371  =head3 GetLoadStats  =head3 _GetLoadStats
3372    
3373  Return a blank statistics object for use by the load methods.  Return a blank statistics object for use by the load methods.
3374    
# Line 2498  Line 3380 
3380      return Stats->new();      return Stats->new();
3381  }  }
3382    
3383  =head3 GenerateFields  =head3 _DumpRelation
3384    
3385  Generate field values from a field structure and store in a specified table. The field names  Dump the specified relation to the specified output file in tab-delimited format.
 are first sorted by pass count, certain pre-defined fields are removed from the list, and  
 then we rip through them evaluation the data generation string. Fields in the primary relation  
 are stored as scalars; fields in secondary relations are stored as value lists.  
   
 This is a static method.  
   
 =over 4  
   
 =item this  
   
 Hash table into which the field values should be placed.  
   
 =item fields  
   
 Field structure from which the field descriptors should be taken.  
   
 =item type  
   
 Type name of the object whose fields are being generated.  
   
 =item values (optional)  
   
 Reference to a value structure from which additional values can be taken.  
   
 =item from (optiona)  
   
 Reference to the source entity instance if relationship data is being generated.  
   
 =item to (optional)  
   
 Reference to the target entity instance if relationship data is being generated.  
   
 =back  
   
 =cut  
   
 sub _GenerateFields {  
     # Get the parameters.  
     my ($this, $fields, $type, $values, $from, $to) = @_;  
     # Sort the field names by pass number.  
     my @fieldNames = sort { $fields->{$a}->{DataGen}->{pass} <=> $fields->{$b}->{DataGen}->{pass} } keys %{$fields};  
     # Loop through the field names, generating data.  
     for my $name (@fieldNames) {  
         # Only proceed if this field needs to be generated.  
         if (!exists $this->{$name}) {  
             # Get this field's data generation descriptor.  
             my $fieldDescriptor = $fields->{$name};  
             my $data = $fieldDescriptor->{DataGen};  
             # Get the code to generate the field value.  
             my $codeString = $data->{content};  
             # Determine whether or not this field is in the primary relation.  
             if ($fieldDescriptor->{relation} eq $type) {  
                 # Here we have a primary relation field. Store the field value as  
                 # a scalar.  
                 $this->{$name} = eval($codeString);  
             } else {  
                 # Here we have a secondary relation field. Create a null list  
                 # and push the desired number of field values onto it.  
                 my @fieldValues = ();  
                 my $count = IntGen(0,$data->{testCount});  
                 for (my $i = 0; $i < $count; $i++) {  
                     my $newValue = eval($codeString);  
                     push @fieldValues, $newValue;  
                 }  
                 # Store the value list in the main hash.  
                 $this->{$name} = \@fieldValues;  
             }  
         }  
     }  
 }  
   
 =head3 DumpRelation  
   
 Dump the specified relation's to the specified output file in tab-delimited format.  
3386    
3387  This is an instance method.  This is an instance method.
3388    
# Line 2622  Line 3430 
3430      close DTXOUT;      close DTXOUT;
3431  }  }
3432    
3433  =head3 GetStructure  =head3 _GetStructure
3434    
3435  Get the data structure for a specified entity or relationship.  Get the data structure for a specified entity or relationship.
3436    
# Line 2661  Line 3469 
3469      return $retVal;      return $retVal;
3470  }  }
3471    
3472  =head3 GetRelationTable  
3473    
3474    =head3 _GetRelationTable
3475    
3476  Get the list of relations for a specified entity or relationship.  Get the list of relations for a specified entity or relationship.
3477    
# Line 2690  Line 3500 
3500      return $objectData->{Relations};      return $objectData->{Relations};
3501  }  }
3502    
3503  =head3 ValidateFieldNames  =head3 _ValidateFieldNames
3504    
3505  Determine whether or not the field names are valid. A description of the problems with the names  Determine whether or not the field names are valid. A description of the problems with the names
3506  will be written to the standard error output. If there is an error, this method will abort. This is  will be written to the standard error output. If there is an error, this method will abort. This is
# Line 2717  Line 3527 
3527          for my $object (values %{$metadata->{$section}}) {          for my $object (values %{$metadata->{$section}}) {
3528              # Loop through the object's fields.              # Loop through the object's fields.
3529              for my $fieldName (keys %{$object->{Fields}}) {              for my $fieldName (keys %{$object->{Fields}}) {
3530                  # Now we make some initial validations.                  # If this field name is invalid, set the return value to zero
3531                  if ($fieldName =~ /--/) {                  # so we know we encountered an error.
3532                      # Here we have a doubled minus sign.                  if (! ValidateFieldName($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";  
3533                          $retVal = 0;                          $retVal = 0;
3534                      }                      }
3535                  }                  }
3536              }              }
3537          }          }
     }  
3538      # If an error was found, fail.      # If an error was found, fail.
3539      if ($retVal  == 0) {      if ($retVal  == 0) {
3540          Confess("Errors found in field names.");          Confess("Errors found in field names.");
3541      }      }
3542  }  }
3543    
3544  =head3 LoadRelation  =head3 _LoadRelation
3545    
3546  Load a relation from the data in a tab-delimited disk file. The load will only take place if a disk  Load a relation from the data in a tab-delimited disk file. The load will only take place if a disk
3547  file with the same name as the relation exists in the specified directory.  file with the same name as the relation exists in the specified directory.
# Line 2805  Line 3601 
3601      return $retVal;      return $retVal;
3602  }  }
3603    
3604  =head3 LoadMetaData  
3605    =head3 _LoadMetaData
3606    
3607  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.
3608  The resulting structure is a set of nested hash tables containing all the information needed to  The resulting structure is a set of nested hash tables containing all the information needed to
# Line 2833  Line 3630 
3630      Trace("Reading Sprout DBD from $filename.") if T(2);      Trace("Reading Sprout DBD from $filename.") if T(2);
3631      # 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
3632      # get the exact structure we want.      # get the exact structure we want.
3633      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 $filename.") if T(1);  
3634      # Before we go any farther, we need to validate the field and object names. If an error is found,      # Before we go any farther, we need to validate the field and object names. If an error is found,
3635      # the method below will fail.      # the method below will fail.
3636      _ValidateFieldNames($metadata);      _ValidateFieldNames($metadata);
# Line 3132  Line 3916 
3916      return $metadata;      return $metadata;
3917  }  }
3918    
3919  =head3 SortNeeded  =head3 _CreateRelationshipIndex
   
 C<< my $flag = $erdb->SortNeeded($relationName); >>  
   
 Return TRUE if the specified relation should be sorted during loading to remove duplicate keys,  
 else FALSE.  
   
 =over 4  
   
 =item relationName  
   
 Name of the relation to be examined.  
   
 =item RETURN  
   
 Returns TRUE if the relation needs a sort, else FALSE.  
   
 =back  
   
 =cut  
 #: Return Type $;  
 sub SortNeeded {  
     # Get the parameters.  
     my ($self, $relationName) = @_;  
     # Declare the return variable.  
     my $retVal = 0;  
     # Find out if the relation is a primary entity relation.  
     my $entityTable = $self->{_metaData}->{Entities};  
     if (exists $entityTable->{$relationName}) {  
         my $keyType = $entityTable->{$relationName}->{keyType};  
         Trace("Relation $relationName found in entity table with key type $keyType.") if T(3);  
         # If the key is not a hash string, we must do the sort.  
         if ($keyType ne 'hash-string') {  
             $retVal = 1;  
         }  
     }  
     # Return the result.  
     return $retVal;  
 }  
   
 =head3 CreateRelationshipIndex  
3920    
3921  Create an index for a relationship's relation.  Create an index for a relationship's relation.
3922    
# Line 3217  Line 3961 
3961      _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);      _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);
3962  }  }
3963    
3964  =head3 AddIndex  =head3 _AddIndex
3965    
3966  Add an index to a relation structure.  Add an index to a relation structure.
3967    
# Line 3263  Line 4007 
4007      $relationStructure->{Indexes}->{$indexName} = $newIndex;      $relationStructure->{Indexes}->{$indexName} = $newIndex;
4008  }  }
4009    
4010  =head3 FixupFields  =head3 _FixupFields
4011    
4012  This method fixes the field list for an entity or relationship. It will add the caller-specified  This method fixes the field list for an entity or relationship. It will add the caller-specified
4013  relation name to fields that do not have a name and set the C<PrettySort> value as specified.  relation name to fields that do not have a name and set the C<PrettySort> value as specified.
# Line 3301  Line 4045 
4045          # Here it doesn't, so we create a new one.          # Here it doesn't, so we create a new one.
4046          $structure->{Fields} = { };          $structure->{Fields} = { };
4047      } else {      } else {
4048          # Here we have a field list. Loop through its fields.          # Here we have a field list. We need to track the searchable fields, so we
4049            # create a list for stashing them.
4050            my @textFields = ();
4051            # Loop through the fields.
4052          my $fieldStructures = $structure->{Fields};          my $fieldStructures = $structure->{Fields};
4053          for my $fieldName (keys %{$fieldStructures}) {          for my $fieldName (keys %{$fieldStructures}) {
4054              Trace("Processing field $fieldName of $defaultRelationName.") if T(4);              Trace("Processing field $fieldName of $defaultRelationName.") if T(4);
# Line 3310  Line 4057 
4057              my $type = $fieldData->{type};              my $type = $fieldData->{type};
4058              # Plug in a relation name if it is needed.              # Plug in a relation name if it is needed.
4059              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });
4060              # Plug in a data generator if we need one.              # Check for searchability.
4061              if (!exists $fieldData->{DataGen}) {              if ($fieldData->{searchable}) {
4062                  # The data generator will use the default for the field's type.                  # Only allow this for a primary relation.
4063                  $fieldData->{DataGen} = { content => $TypeTable{$type}->{dataGen} };                  if ($fieldData->{relation} ne $defaultRelationName) {
4064                        Confess("Field $fieldName of $defaultRelationName is in secondary relations and cannot be searchable.");
4065                    } else {
4066                        push @textFields, $fieldName;
4067                    }
4068              }              }
             # Plug in the defaults for the optional data generation parameters.  
             Tracer::MergeOptions($fieldData->{DataGen}, { testCount => 1, pass => 0 });  
4069              # Add the PrettySortValue.              # Add the PrettySortValue.
4070              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);
4071          }          }
4072            # If there are searchable fields, remember the fact.
4073            if (@textFields) {
4074                $structure->{searchFields} = \@textFields;
4075            }
4076      }      }
4077  }  }
4078    
4079  =head3 FixName  =head3 _FixName
4080    
4081  Fix the incoming field name so that it is a legal SQL column name.  Fix the incoming field name so that it is a legal SQL column name.
4082    
# Line 3352  Line 4105 
4105      return $fieldName;      return $fieldName;
4106  }  }
4107    
4108  =head3 FixNames  =head3 _FixNames
4109    
4110  Fix all the field names in a list.  Fix all the field names in a list.
4111    
# Line 3383  Line 4136 
4136      return @result;      return @result;
4137  }  }
4138    
4139  =head3 AddField  =head3 _AddField
4140    
4141  Add a field to a field list.  Add a field to a field list.
4142    
# Line 3418  Line 4171 
4171      $fieldList->{$fieldName} = $fieldStructure;      $fieldList->{$fieldName} = $fieldStructure;
4172  }  }
4173    
4174  =head3 ReOrderRelationTable  =head3 _ReOrderRelationTable
4175    
4176  This method will take a relation table and re-sort it according to the implicit ordering of the  This method will take a relation table and re-sort it according to the implicit ordering of the
4177  C<PrettySort> property. Instead of a hash based on field names, it will return a list of fields.  C<PrettySort> property. Instead of a hash based on field names, it will return a list of fields.
# Line 3479  Line 4232 
4232    
4233  }  }
4234    
4235  =head3 IsPrimary  =head3 _IsPrimary
4236    
4237  Return TRUE if a specified relation is a primary relation, else FALSE. A relation is primary  Return TRUE if a specified relation is a primary relation, else FALSE. A relation is primary
4238  if it has the same name as an entity or relationship.  if it has the same name as an entity or relationship.
# Line 3515  Line 4268 
4268      return $retVal;      return $retVal;
4269  }  }
4270    
4271  =head3 FindRelation  =head3 _FindRelation
4272    
4273  Return the descriptor for the specified relation.  Return the descriptor for the specified relation.
4274    
# Line 3546  Line 4299 
4299    
4300  =head2 HTML Documentation Utility Methods  =head2 HTML Documentation Utility Methods
4301    
4302  =head3 ComputeRelationshipSentence  =head3 _ComputeRelationshipSentence
4303    
4304  The relationship sentence consists of the relationship name between the names of the  The relationship sentence consists of the relationship name between the names of the
4305  two related entities and an arity indicator.  two related entities and an arity indicator.
# Line 3584  Line 4337 
4337      return $result;      return $result;
4338  }  }
4339    
4340  =head3 ComputeRelationshipHeading  =head3 _ComputeRelationshipHeading
4341    
4342  The relationship heading is the L<relationship sentence|/ComputeRelationshipSentence> with the entity  The relationship heading is the L<relationship sentence|/ComputeRelationshipSentence> with the entity
4343  names hyperlinked to the appropriate entity sections of the document.  names hyperlinked to the appropriate entity sections of the document.
# Line 3621  Line 4374 
4374      return $result;      return $result;
4375  }  }
4376    
4377  =head3 ShowRelationTable  =head3 _ShowRelationTable
4378    
4379  Generate the HTML string for a particular relation. The relation's data will be formatted as an HTML  Generate the HTML string for a particular relation. The relation's data will be formatted as an HTML
4380  table with three columns-- the field name, the field type, and the field description.  table with three columns-- the field name, the field type, and the field description.
# Line 3671  Line 4424 
4424          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";
4425          # Add any note text.          # Add any note text.
4426          if (my $note = $indexData->{Notes}) {          if (my $note = $indexData->{Notes}) {
4427              $htmlString .= "<li>" . _HTMLNote($note->{content}) . "</li>\n";              $htmlString .= "<li>" . HTMLNote($note->{content}) . "</li>\n";
4428          }          }
4429          # Add the fiield list.          # Add the fiield list.
4430          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";
# Line 3682  Line 4435 
4435      $htmlString .= "</ul>\n";      $htmlString .= "</ul>\n";
4436  }  }
4437    
4438  =head3 OpenFieldTable  =head3 _OpenFieldTable
4439    
4440  This method creates the header string for the field table generated by L</ShowMetaData>.  This method creates the header string for the field table generated by L</ShowMetaData>.
4441    
# Line 3707  Line 4460 
4460      return _OpenTable($tablename, 'Field', 'Type', 'Description');      return _OpenTable($tablename, 'Field', 'Type', 'Description');
4461  }  }
4462    
4463  =head3 OpenTable  =head3 _OpenTable
4464    
4465  This method creates the header string for an HTML table.  This method creates the header string for an HTML table.
4466    
# Line 3747  Line 4500 
4500      return $htmlString;      return $htmlString;
4501  }  }
4502    
4503  =head3 CloseTable  =head3 _CloseTable
4504    
4505  This method returns the HTML for closing a table.  This method returns the HTML for closing a table.
4506    
# Line 3759  Line 4512 
4512      return "</table></p>\n";      return "</table></p>\n";
4513  }  }
4514    
4515  =head3 ShowField  =head3 _ShowField
4516    
4517  This method returns the HTML for displaying a row of field information in a field table.  This method returns the HTML for displaying a row of field information in a field table.
4518    
# Line 3786  Line 4539 
4539      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>";
4540      # If we have content, add it as a third column.      # If we have content, add it as a third column.
4541      if (exists $fieldData->{Notes}) {      if (exists $fieldData->{Notes}) {
4542          $htmlString .= "<td>" . _HTMLNote($fieldData->{Notes}->{content}) . "</td>";          $htmlString .= "<td>" . HTMLNote($fieldData->{Notes}->{content}) . "</td>";
4543      }      }
4544      # Close off the row.      # Close off the row.
4545      $htmlString .= "</tr>\n";      $htmlString .= "</tr>\n";
# Line 3794  Line 4547 
4547      return $htmlString;      return $htmlString;
4548  }  }
4549    
 =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;  
 }  
   
4550  1;  1;

Legend:
Removed from v.1.48  
changed lines
  Added in v.1.74

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3