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

Diff of /Sprout/ERDB.pm

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

revision 1.55, Sat Jun 24 23:49:10 2006 UTC revision 1.73, Fri Nov 3 00:33:26 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
# 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 684  Line 733 
733      Trace("Creating table $relationName: $fieldThing") if T(2);      Trace("Creating table $relationName: $fieldThing") if T(2);
734      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);
735      Trace("Relation $relationName created in database.") if T(2);      Trace("Relation $relationName created in database.") if T(2);
736      # If we want to build the indexes, we do it here.      # If we want to build the indexes, we do it here. Note that the full-text search
737        # index will not be built until the table has been loaded.
738      if ($indexFlag) {      if ($indexFlag) {
739          $self->CreateIndex($relationName);          $self->CreateIndex($relationName);
740      }      }
# Line 844  Line 894 
894          my @fieldList = _FixNames(@{$indexData->{IndexFields}});          my @fieldList = _FixNames(@{$indexData->{IndexFields}});
895          my $flds = join(', ', @fieldList);          my $flds = join(', ', @fieldList);
896          # Get the index's uniqueness flag.          # Get the index's uniqueness flag.
897          my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
898          # Create the index.          # Create the index.
899          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
900                                      flds => $flds, unique => $unique);                                      flds => $flds, kind => $unique);
901          if ($rv) {          if ($rv) {
902              Trace("Index created: $indexName for $relationName ($flds)") if T(1);              Trace("Index created: $indexName for $relationName ($flds)") if T(1);
903          } else {          } else {
# Line 950  Line 1000 
1000      return sort keys %{$entityList};      return sort keys %{$entityList};
1001  }  }
1002    
1003    =head3 GetDataTypes
1004    
1005    C<< my %types = ERDB::GetDataTypes(); >>
1006    
1007    Return a table of ERDB data types. The table returned is a hash of hashes.
1008    The keys of the big hash are the datatypes. Each smaller hash has several
1009    values used to manage the data. The most interesting is the SQL type (key
1010    C<sqlType>) and the descriptive node (key C<notes>).
1011    
1012    Note that changing the values in the smaller hashes will seriously break
1013    things, so this data should be treated as read-only.
1014    
1015    =cut
1016    
1017    sub GetDataTypes {
1018        return %TypeTable;
1019    }
1020    
1021    
1022  =head3 IsEntity  =head3 IsEntity
1023    
1024  C<< my $flag = $erdb->IsEntity($entityName); >>  C<< my $flag = $erdb->IsEntity($entityName); >>
# Line 1094  Line 1163 
1163      return $retVal;      return $retVal;
1164  }  }
1165    
1166    =head3 Search
1167    
1168    C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>
1169    
1170    Perform a full text search with filtering. The search will be against a specified object
1171    in the object name list. That object will get an extra field containing the search
1172    relevance. Note that except for the search expression, the parameters of this method are
1173    the same as those for L</Get> and follow the same rules.
1174    
1175    =over 4
1176    
1177    =item searchExpression
1178    
1179    Boolean search expression for the text fields of the target object.
1180    
1181    =item idx
1182    
1183    Index in the I<$objectNames> list of the table to be searched in full-text mode.
1184    
1185    =item objectNames
1186    
1187    List containing the names of the entity and relationship objects to be retrieved.
1188    
1189    =item filterClause
1190    
1191    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1192    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
1193    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
1194    in the filter clause should be added to the parameter list as additional parameters. The
1195    fields in a filter clause can come from primary entity relations, relationship relations,
1196    or secondary entity relations; however, all of the entities and relationships involved must
1197    be included in the list of object names.
1198    
1199    =item params
1200    
1201    Reference to a list of parameter values to be substituted into the filter clause.
1202    
1203    =item RETURN
1204    
1205    Returns a query object for the specified search.
1206    
1207    =back
1208    
1209    =cut
1210    
1211    sub Search {
1212        # Get the parameters.
1213        my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1214        # Declare the return variable.
1215        my $retVal;
1216        # Create a safety copy of the parameter list. Note we have to be careful to insure
1217        # a parameter list exists before we copy it.
1218        my @myParams = ();
1219        if (defined $params) {
1220            @myParams = @{$params};
1221        }
1222        # Get the first object's structure so we have access to the searchable fields.
1223        my $object1Name = $objectNames->[$idx];
1224        my $object1Structure = $self->_GetStructure($object1Name);
1225        # Get the field list.
1226        if (! exists $object1Structure->{searchFields}) {
1227            Confess("No searchable index for $object1Name.");
1228        } else {
1229            # Get the field list.
1230            my @fields = @{$object1Structure->{searchFields}};
1231            # Clean the search expression.
1232            my $actualKeywords = $self->CleanKeywords($searchExpression);
1233            Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1234            # We need two match expressions, one for the filter clause and one in the
1235            # query itself. Both will use a parameter mark, so we need to push the
1236            # search expression onto the front of the parameter list twice.
1237            unshift @myParams, $actualKeywords, $actualKeywords;
1238            # Build the match expression.
1239            my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
1240            my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
1241            # Process the SQL stuff.
1242            my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1243                $self->_SetupSQL($objectNames, $filterClause, $matchClause);
1244            # Create the query. Note that the match clause is inserted at the front of
1245            # the select fields.
1246            my $command = "SELECT DISTINCT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .
1247                ".* $suffix";
1248            my $sth = $self->_GetStatementHandle($command, \@myParams);
1249            # Now we create the relation map, which enables DBQuery to determine the order, name
1250            # and mapped name for each object in the query.
1251            my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
1252            # Return the statement object.
1253            $retVal = DBQuery::_new($self, $sth, \@relationMap, $object1Name);
1254        }
1255        return $retVal;
1256    }
1257    
1258  =head3 GetFlat  =head3 GetFlat
1259    
1260  C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>  C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>
# Line 1147  Line 1308 
1308      return @retVal;      return @retVal;
1309  }  }
1310    
1311    =head3 SpecialFields
1312    
1313    C<< my %specials = $erdb->SpecialFields($entityName); >>
1314    
1315    Return a hash mapping special fields in the specified entity to the value of their
1316    C<special> attribute. This enables the subclass to get access to the special field
1317    attributes without needed to plumb the internal ERDB data structures.
1318    
1319    =over 4
1320    
1321    =item entityName
1322    
1323    Name of the entity whose special fields are desired.
1324    
1325    =item RETURN
1326    
1327    Returns a hash. The keys of the hash are the special field names, and the values
1328    are the values from each special field's C<special> attribute.
1329    
1330    =back
1331    
1332    =cut
1333    
1334    sub SpecialFields {
1335        # Get the parameters.
1336        my ($self, $entityName) = @_;
1337        # Declare the return variable.
1338        my %retVal = ();
1339        # Find the entity's data structure.
1340        my $entityData = $self->{Entities}->{$entityName};
1341        # Loop through its fields, adding each special field to the return hash.
1342        my $fieldHash = $entityData->{Fields};
1343        for my $fieldName (keys %{$fieldHash}) {
1344            my $fieldData = $fieldHash->{$fieldName};
1345            if (exists $fieldData->{special}) {
1346                $retVal{$fieldName} = $fieldData->{special};
1347            }
1348        }
1349        # Return the result.
1350        return %retVal;
1351    }
1352    
1353  =head3 Delete  =head3 Delete
1354    
1355  C<< my $stats = $erdb->Delete($entityName, $objectID); >>  C<< my $stats = $erdb->Delete($entityName, $objectID); >>
# Line 1315  Line 1518 
1518      return $retVal;      return $retVal;
1519  }  }
1520    
1521    =head3 SortNeeded
1522    
1523    C<< my $parms = $erdb->SortNeeded($relationName); >>
1524    
1525    Return the pipe command for the sort that should be applied to the specified
1526    relation when creating the load file.
1527    
1528    For example, if the load file should be sorted ascending by the first
1529    field, this method would return
1530    
1531        sort -k1 -t"\t"
1532    
1533    If the first field is numeric, the method would return
1534    
1535        sort -k1n -t"\t"
1536    
1537    Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate
1538    keys using a sort.
1539    
1540    =over 4
1541    
1542    =item relationName
1543    
1544    Name of the relation to be examined.
1545    
1546    =item
1547    
1548    Returns the sort command to use for sorting the relation, suitable for piping.
1549    
1550    =back
1551    
1552    =cut
1553    #: Return Type $;
1554    sub SortNeeded {
1555        # Get the parameters.
1556        my ($self, $relationName) = @_;
1557        # Declare a descriptor to hold the names of the key fields.
1558        my @keyNames = ();
1559        # Get the relation structure.
1560        my $relationData = $self->_FindRelation($relationName);
1561        # Find out if the relation is a primary entity relation,
1562        # a relationship relation, or a secondary entity relation.
1563        my $entityTable = $self->{_metaData}->{Entities};
1564        my $relationshipTable = $self->{_metaData}->{Relationships};
1565        if (exists $entityTable->{$relationName}) {
1566            # Here we have a primary entity relation.
1567            push @keyNames, "id";
1568        } elsif (exists $relationshipTable->{$relationName}) {
1569            # Here we have a relationship. We sort using the FROM index.
1570            my $relationshipData = $relationshipTable->{$relationName};
1571            my $index = $relationData->{Indexes}->{"idx${relationName}From"};
1572            push @keyNames, @{$index->{IndexFields}};
1573        } else {
1574            # Here we have a secondary entity relation, so we have a sort on the ID field.
1575            push @keyNames, "id";
1576        }
1577        # Now we parse the key names into sort parameters. First, we prime the return
1578        # string.
1579        my $retVal = "sort -t\"\t\" ";
1580        # Get the relation's field list.
1581        my @fields = @{$relationData->{Fields}};
1582        # Loop through the keys.
1583        for my $keyData (@keyNames) {
1584            # Get the key and the ordering.
1585            my ($keyName, $ordering);
1586            if ($keyData =~ /^([^ ]+) DESC/) {
1587                ($keyName, $ordering) = ($1, "descending");
1588            } else {
1589                ($keyName, $ordering) = ($keyData, "ascending");
1590            }
1591            # Find the key's position and type.
1592            my $fieldSpec;
1593            for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {
1594                my $thisField = $fields[$i];
1595                if ($thisField->{name} eq $keyName) {
1596                    # Get the sort modifier for this field type. The modifier
1597                    # decides whether we're using a character, numeric, or
1598                    # floating-point sort.
1599                    my $modifier = $TypeTable{$thisField->{type}}->{sort};
1600                    # If the index is descending for this field, denote we want
1601                    # to reverse the sort order on this field.
1602                    if ($ordering eq 'descending') {
1603                        $modifier .= "r";
1604                    }
1605                    # Store the position and modifier into the field spec, which
1606                    # will stop the inner loop. Note that the field number is
1607                    # 1-based in the sort command, so we have to increment the
1608                    # index.
1609                    $fieldSpec = ($i + 1) . $modifier;
1610                }
1611            }
1612            # Add this field to the sort command.
1613            $retVal .= " -k$fieldSpec";
1614        }
1615        # Return the result.
1616        return $retVal;
1617    }
1618    
1619  =head3 GetList  =head3 GetList
1620    
1621  C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>  C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>
# Line 1431  Line 1732 
1732  sub GetCount {  sub GetCount {
1733      # Get the parameters.      # Get the parameters.
1734      my ($self, $objectNames, $filter, $params) = @_;      my ($self, $objectNames, $filter, $params) = @_;
1735        # Insure the params argument is an array reference if the caller left it off.
1736        if (! defined($params)) {
1737            $params = [];
1738        }
1739      # Declare the return variable.      # Declare the return variable.
1740      my $retVal;      my $retVal;
1741      # Find out if we're counting an entity or a relationship.      # Find out if we're counting an entity or a relationship.
# Line 1623  Line 1928 
1928  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
1929  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>.
1930    
1931  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'}); >>
1932    
1933  =over 4  =over 4
1934    
# Line 1815  Line 2120 
2120      };      };
2121      if (!defined $rv) {      if (!defined $rv) {
2122          $retVal->AddMessage($@) if ($@);          $retVal->AddMessage($@) if ($@);
2123          $retVal->AddMessage("Table load failed for $relationName using $fileName.");          $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2124          Trace("Table load failed for $relationName.") if T(1);          Trace("Table load failed for $relationName.") if T(1);
2125      } else {      } else {
2126          # Here we successfully loaded the table.          # Here we successfully loaded the table.
# Line 1823  Line 2128 
2128          my $size = -s $fileName;          my $size = -s $fileName;
2129          Trace("$size bytes loaded into $relationName.") if T(2);          Trace("$size bytes loaded into $relationName.") if T(2);
2130          # If we're rebuilding, we need to create the table indexes.          # If we're rebuilding, we need to create the table indexes.
2131          if ($truncateFlag && ! $dbh->{_preIndex}) {          if ($truncateFlag) {
2132                # Indexes are created here for PostGres. For PostGres, indexes are
2133                # best built at the end. For MySQL, the reverse is true.
2134                if (! $dbh->{_preIndex}) {
2135              eval {              eval {
2136                  $self->CreateIndex($relationName);                  $self->CreateIndex($relationName);
2137              };              };
# Line 1831  Line 2139 
2139                  $retVal->AddMessage($@);                  $retVal->AddMessage($@);
2140              }              }
2141          }          }
2142                # The full-text index (if any) is always built last, even for MySQL.
2143                # First we need to see if this table has a full-text index. Only
2144                # primary relations are allowed that privilege.
2145                if ($self->_IsPrimary($relationName)) {
2146                    # Get the relation's entity/relationship structure.
2147                    my $structure = $self->_GetStructure($relationName);
2148                    # Check for a searchable fields list.
2149                    if (exists $structure->{searchFields}) {
2150                        # Here we know that we need to create a full-text search index.
2151                        # Get an SQL-formatted field name list.
2152                        my $fields = join(", ", $self->_FixNames(@{$structure->{searchFields}}));
2153                        # Create the index.
2154                        $dbh->create_index(tbl => $relationName, idx => "search_idx_$relationName",
2155                                           flds => $fields, kind => 'fulltext');
2156                    }
2157                }
2158            }
2159      }      }
2160      # Analyze the table to improve performance.      # Analyze the table to improve performance.
2161        Trace("Analyzing and compacting $relationName.") if T(3);
2162      $dbh->vacuum_it($relationName);      $dbh->vacuum_it($relationName);
2163        Trace("$relationName load completed.") if T(3);
2164      # Return the statistics.      # Return the statistics.
2165      return $retVal;      return $retVal;
2166  }  }
2167    
2168  =head3 GenerateEntity  =head3 DropRelation
   
 C<< my $fieldHash = $erdb->GenerateEntity($id, $type, \%values); >>  
2169    
2170  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.  
2171    
2172  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.  
2173    
2174  =over 4  =over 4
2175    
2176  =item id  =item relationName
   
 ID to assign to the new entity.  
   
 =item type  
   
 Type name for the new entity.  
   
 =item values  
2177    
2178  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
2179    no effect.
2180    
2181  =back  =back
2182    
2183  =cut  =cut
2184    
2185  sub GenerateEntity {  sub DropRelation {
2186      # Get the parameters.      # Get the parameters.
2187      my ($self, $id, $type, $values) = @_;      my ($self, $relationName) = @_;
2188      # Create the return hash.      # Get the database handle.
2189      my $this = { id => $id };      my $dbh = $self->{_dbh};
2190      # Get the metadata structure.      # Drop the relation. The method used here has no effect if the relation
2191      my $metadata = $self->{_metaData};      # does not exist.
2192      # Get this entity's list of fields.      $dbh->drop_table($relationName);
     if (!exists $metadata->{Entities}->{$type}) {  
         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;  
2193  }  }
2194    
2195  =head3 GetEntity  =head3 GetEntity
# Line 1932  Line 2228 
2228      return $retVal;      return $retVal;
2229  }  }
2230    
2231    =head3 GetChoices
2232    
2233    C<< my @values = $erdb->GetChoices($entityName, $fieldName); >>
2234    
2235    Return a list of all the values for the specified field that are represented in the
2236    specified entity.
2237    
2238    Note that if the field is not indexed, then this will be a very slow operation.
2239    
2240    =over 4
2241    
2242    =item entityName
2243    
2244    Name of an entity in the database.
2245    
2246    =item fieldName
2247    
2248    Name of a field belonging to the entity. This is a raw field name without
2249    the standard parenthesized notation used in most calls.
2250    
2251    =item RETURN
2252    
2253    Returns a list of the distinct values for the specified field in the database.
2254    
2255    =back
2256    
2257    =cut
2258    
2259    sub GetChoices {
2260        # Get the parameters.
2261        my ($self, $entityName, $fieldName) = @_;
2262        # Declare the return variable.
2263        my @retVal;
2264        # Get the entity data structure.
2265        my $entityData = $self->_GetStructure($entityName);
2266        # Get the field.
2267        my $fieldHash = $entityData->{Fields};
2268        if (! exists $fieldHash->{$fieldName}) {
2269            Confess("$fieldName not found in $entityName.");
2270        } else {
2271            # Get the name of the relation containing the field.
2272            my $relation = $fieldHash->{$fieldName}->{relation};
2273            # Fix up the field name.
2274            my $realName = _FixName($fieldName);
2275            # Get the database handle.
2276            my $dbh = $self->{_dbh};
2277            # Query the database.
2278            my $results = $dbh->SQL("SELECT DISTINCT $realName FROM $relation");
2279            # Clean the results. They are stored as a list of lists, and we just want the one list.
2280            @retVal = sort map { $_->[0] } @{$results};
2281        }
2282        # Return the result.
2283        return @retVal;
2284    }
2285    
2286  =head3 GetEntityValues  =head3 GetEntityValues
2287    
2288  C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>  C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>
2289    
2290  Return a list of values from a specified entity instance.  Return a list of values from a specified entity instance. If the entity instance
2291    does not exist, an empty list is returned.
2292    
2293  =over 4  =over 4
2294    
# Line 2171  Line 2523 
2523      return $objectData->{Fields};      return $objectData->{Fields};
2524  }  }
2525    
2526  =head2 Data Mining Methods  =head3 SplitKeywords
2527    
2528  =head3 GetUsefulCrossValues  C<< my @keywords = ERDB::SplitKeywords($keywordString); >>
2529    
2530  C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>  This method returns a list of the positive keywords in the specified
2531    keyword string. All of the operators will have been stripped off,
2532    and if the keyword is preceded by a minus operator (C<->), it will
2533    not be in the list returned. The idea here is to get a list of the
2534    keywords the user wants to see. The list will be processed to remove
2535    duplicates.
2536    
2537  Return a list of the useful attributes that would be returned by a B<Cross> call  It is possible to create a string that confuses this method. For example
 from an entity of the source entity type through the specified relationship. This  
 means it will return the fields of the target entity type and the intersection data  
 fields in the relationship. Only primary table fields are returned. In other words,  
 the field names returned will be for fields where there is always one and only one  
 value.  
2538    
2539  =over 4      frog toad -frog
2540    
2541  =item sourceEntity  would return both C<frog> and C<toad>. If this is a problem we can deal
2542    with it later.
2543    
2544  Name of the entity from which the relationship crossing will start.  =over 4
2545    
2546  =item relationship  =item keywordString
2547    
2548  Name of the relationship being crossed.  The keyword string to be parsed.
2549    
2550  =item RETURN  =item RETURN
2551    
2552  Returns a list of field names in Sprout field format (I<objectName>C<(>I<fieldName>C<)>.  Returns a list of the words in the keyword string the user wants to
2553    see.
2554    
2555  =back  =back
2556    
2557  =cut  =cut
2558  #: Return Type @;  
2559  sub GetUsefulCrossValues {  sub SplitKeywords {
2560      # Get the parameters.      # Get the parameters.
2561      my ($self, $sourceEntity, $relationship) = @_;      my ($keywordString) = @_;
2562      # Declare the return variable.      # Make a safety copy of the string. (This helps during debugging.)
2563      my @retVal = ();      my $workString = $keywordString;
2564      # Determine the target entity for the relationship. This is whichever entity is not      # Convert operators we don't care about to spaces.
2565      # the source entity. So, if the source entity is the FROM, we'll get the name of      $workString =~ tr/+"()<>/ /;
2566      # the TO, and vice versa.      # Split the rest of the string along space boundaries. Note that we
2567      my $relStructure = $self->_GetStructure($relationship);      # eliminate any words that are zero length or begin with a minus sign.
2568      my $targetEntityType = ($relStructure->{from} eq $sourceEntity ? "to" : "from");      my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
2569      my $targetEntity = $relStructure->{$targetEntityType};      # Use a hash to remove duplicates.
2570      # Get the field table for the entity.      my %words = map { $_ => 1 } @wordList;
     my $entityFields = $self->GetFieldTable($targetEntity);  
     # The field table is a hash. The hash key is the field name. The hash value is a structure.  
     # For the entity fields, the key aspect of the target structure is that the {relation} value  
     # must match the entity name.  
     my @fieldList = map { "$targetEntity($_)" } grep { $entityFields->{$_}->{relation} eq $targetEntity }  
                         keys %{$entityFields};  
     # Push the fields found onto the return variable.  
     push @retVal, sort @fieldList;  
     # Get the field table for the relationship.  
     my $relationshipFields = $self->GetFieldTable($relationship);  
     # Here we have a different rule. We want all the fields other than "from-link" and "to-link".  
     # This may end up being an empty set.  
     my @fieldList2 = map { "$relationship($_)" } grep { $_ ne "from-link" && $_ ne "to-link" }  
                         keys %{$relationshipFields};  
     # Push these onto the return list.  
     push @retVal, sort @fieldList2;  
2571      # Return the result.      # Return the result.
2572      return @retVal;      return sort keys %words;
2573  }  }
2574    
2575  =head3 FindColumn  =head3 ValidateFieldName
2576    
2577  C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>  C<< my $okFlag = ERDB::ValidateFieldName($fieldName); >>
2578    
2579  Return the location a desired column in a data mining header line. The data  Return TRUE if the specified field name is valid, else FALSE. Valid field names must
2580  mining header line is a tab-separated list of column names. The column  be hyphenated words subject to certain restrictions.
 identifier is either the numerical index of a column or the actual column  
 name.  
2581    
2582  =over 4  =over 4
2583    
2584  =item headerLine  =item fieldName
   
 The header line from a data mining command, which consists of a tab-separated  
 list of column names.  
   
 =item columnIdentifier  
2585    
2586  Either the ordinal number of the desired column (1-based), or the name of the  Field name to be validated.
 desired column.  
2587    
2588  =item RETURN  =item RETURN
2589    
2590  Returns the array index (0-based) of the desired column.  Returns TRUE if the field name is valid, else FALSE.
2591    
2592  =back  =back
2593    
2594  =cut  =cut
2595    
2596  sub FindColumn {  sub ValidateFieldName {
2597      # Get the parameters.      # Get the parameters.
2598      my ($headerLine, $columnIdentifier) = @_;      my ($fieldName) = @_;
2599      # Declare the return variable.      # Declare the return variable. The field name is valid until we hear
2600      my $retVal;      # differently.
2601        my $retVal = 1;
2602        # Look for bad stuff in the name.
2603        if ($fieldName =~ /--/) {
2604            # Here we have a doubled minus sign.
2605            Trace("Field name $fieldName has a doubled hyphen.") if T(1);
2606            $retVal = 0;
2607        } elsif ($fieldName !~ /^[A-Za-z]/) {
2608            # Here the field name is missing the initial letter.
2609            Trace("Field name $fieldName does not begin with a letter.") if T(1);
2610            $retVal = 0;
2611        } else {
2612            # Strip out the minus signs. Everything remaining must be a letter
2613            # or digit.
2614            my $strippedName = $fieldName;
2615            $strippedName =~ s/-//g;
2616            if ($strippedName !~ /^[A-Za-z0-9]+$/) {
2617                Trace("Field name $fieldName contains illegal characters.") if T(1);
2618                $retVal = 0;
2619            }
2620        }
2621        # Return the result.
2622        return $retVal;
2623    }
2624    
2625    =head3 ReadMetaXML
2626    
2627    C<< my $rawMetaData = ERDB::ReadDBD($fileName); >>
2628    
2629    This method reads a raw database definition XML file and returns it.
2630    Normally, the metadata used by the ERDB system has been processed and
2631    modified to make it easier to load and retrieve the data; however,
2632    this method can be used to get the data in its raw form.
2633    
2634    =over 4
2635    
2636    =item fileName
2637    
2638    Name of the XML file to read.
2639    
2640    =item RETURN
2641    
2642    Returns a hash reference containing the raw XML data from the specified file.
2643    
2644    =back
2645    
2646    =cut
2647    
2648    sub ReadMetaXML {
2649        # Get the parameters.
2650        my ($fileName) = @_;
2651        # Read the XML.
2652        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
2653        Trace("XML metadata loaded from file $fileName.") if T(1);
2654        # Return the result.
2655        return $retVal;
2656    }
2657    
2658    =head3 GetEntityFieldHash
2659    
2660    C<< my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName); >>
2661    
2662    Get the field hash of the named entity in the specified raw XML structure.
2663    The field hash may not exist, in which case we need to create it.
2664    
2665    =over 4
2666    
2667    =item structure
2668    
2669    Raw XML structure defininng the database. This is not the run-time XML used by
2670    an ERDB object, since that has all sorts of optimizations built-in.
2671    
2672    =item entityName
2673    
2674    Name of the entity whose field structure is desired.
2675    
2676    =item RETURN
2677    
2678    Returns the field hash used to define the entity's fields.
2679    
2680    =back
2681    
2682    =cut
2683    
2684    sub GetEntityFieldHash {
2685        # Get the parameters.
2686        my ($structure, $entityName) = @_;
2687        # Get the entity structure.
2688        my $entityData = $structure->{Entities}->{$entityName};
2689        # Look for a field structure.
2690        my $retVal = $entityData->{Fields};
2691        # If it doesn't exist, create it.
2692        if (! defined($retVal)) {
2693            $entityData->{Fields} = {};
2694            $retVal = $entityData->{Fields};
2695        }
2696        # Return the result.
2697        return $retVal;
2698    }
2699    
2700    =head3 WriteMetaXML
2701    
2702    C<< ERDB::WriteMetaXML($structure, $fileName); >>
2703    
2704    Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
2705    used to update the database definition. It must be used with care, however, since it
2706    will only work on a raw structure, not on the processed structure created by an ERDB
2707    constructor.
2708    
2709    =over 4
2710    
2711    =item structure
2712    
2713    XML structure to be written to the file.
2714    
2715    =item fileName
2716    
2717    Name of the output file to which the updated XML should be stored.
2718    
2719    =back
2720    
2721    =cut
2722    
2723    sub WriteMetaXML {
2724        # Get the parameters.
2725        my ($structure, $fileName) = @_;
2726        # Compute the output.
2727        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
2728        # Write it to the file.
2729        my $xmlOut = Open(undef, ">$fileName");
2730        print $xmlOut $fileString;
2731    }
2732    
2733    
2734    =head3 HTMLNote
2735    
2736    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
2737    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
2738    Except for C<[p]>, all the codes are closed by slash-codes. So, for
2739    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
2740    
2741    C<< my $realHtml = ERDB::HTMLNote($dataString); >>
2742    
2743    =over 4
2744    
2745    =item dataString
2746    
2747    String to convert to HTML.
2748    
2749    =item RETURN
2750    
2751    An HTML string derived from the input string.
2752    
2753    =back
2754    
2755    =cut
2756    
2757    sub HTMLNote {
2758        # Get the parameter.
2759        my ($dataString) = @_;
2760        # HTML-escape the text.
2761        my $retVal = CGI::escapeHTML($dataString);
2762        # Substitute the bulletin board codes.
2763        $retVal =~ s!\[(/?[bi])\]!<$1>!g;
2764        $retVal =~ s!\[p\]!</p><p>!g;
2765        # Return the result.
2766        return $retVal;
2767    }
2768    
2769    
2770    =head2 Data Mining Methods
2771    
2772    =head3 GetUsefulCrossValues
2773    
2774    C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>
2775    
2776    Return a list of the useful attributes that would be returned by a B<Cross> call
2777    from an entity of the source entity type through the specified relationship. This
2778    means it will return the fields of the target entity type and the intersection data
2779    fields in the relationship. Only primary table fields are returned. In other words,
2780    the field names returned will be for fields where there is always one and only one
2781    value.
2782    
2783    =over 4
2784    
2785    =item sourceEntity
2786    
2787    Name of the entity from which the relationship crossing will start.
2788    
2789    =item relationship
2790    
2791    Name of the relationship being crossed.
2792    
2793    =item RETURN
2794    
2795    Returns a list of field names in Sprout field format (I<objectName>C<(>I<fieldName>C<)>.
2796    
2797    =back
2798    
2799    =cut
2800    #: Return Type @;
2801    sub GetUsefulCrossValues {
2802        # Get the parameters.
2803        my ($self, $sourceEntity, $relationship) = @_;
2804        # Declare the return variable.
2805        my @retVal = ();
2806        # Determine the target entity for the relationship. This is whichever entity is not
2807        # the source entity. So, if the source entity is the FROM, we'll get the name of
2808        # the TO, and vice versa.
2809        my $relStructure = $self->_GetStructure($relationship);
2810        my $targetEntityType = ($relStructure->{from} eq $sourceEntity ? "to" : "from");
2811        my $targetEntity = $relStructure->{$targetEntityType};
2812        # Get the field table for the entity.
2813        my $entityFields = $self->GetFieldTable($targetEntity);
2814        # The field table is a hash. The hash key is the field name. The hash value is a structure.
2815        # For the entity fields, the key aspect of the target structure is that the {relation} value
2816        # must match the entity name.
2817        my @fieldList = map { "$targetEntity($_)" } grep { $entityFields->{$_}->{relation} eq $targetEntity }
2818                            keys %{$entityFields};
2819        # Push the fields found onto the return variable.
2820        push @retVal, sort @fieldList;
2821        # Get the field table for the relationship.
2822        my $relationshipFields = $self->GetFieldTable($relationship);
2823        # Here we have a different rule. We want all the fields other than "from-link" and "to-link".
2824        # This may end up being an empty set.
2825        my @fieldList2 = map { "$relationship($_)" } grep { $_ ne "from-link" && $_ ne "to-link" }
2826                            keys %{$relationshipFields};
2827        # Push these onto the return list.
2828        push @retVal, sort @fieldList2;
2829        # Return the result.
2830        return @retVal;
2831    }
2832    
2833    =head3 FindColumn
2834    
2835    C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>
2836    
2837    Return the location a desired column in a data mining header line. The data
2838    mining header line is a tab-separated list of column names. The column
2839    identifier is either the numerical index of a column or the actual column
2840    name.
2841    
2842    =over 4
2843    
2844    =item headerLine
2845    
2846    The header line from a data mining command, which consists of a tab-separated
2847    list of column names.
2848    
2849    =item columnIdentifier
2850    
2851    Either the ordinal number of the desired column (1-based), or the name of the
2852    desired column.
2853    
2854    =item RETURN
2855    
2856    Returns the array index (0-based) of the desired column.
2857    
2858    =back
2859    
2860    =cut
2861    
2862    sub FindColumn {
2863        # Get the parameters.
2864        my ($headerLine, $columnIdentifier) = @_;
2865        # Declare the return variable.
2866        my $retVal;
2867      # Split the header line into column names.      # Split the header line into column names.
2868      my @headers = ParseColumns($headerLine);      my @headers = ParseColumns($headerLine);
2869      # Determine whether we have a number or a name.      # Determine whether we have a number or a name.
# Line 2324  Line 2920 
2920      return @retVal;      return @retVal;
2921  }  }
2922    
2923    =head2 Virtual Methods
2924    
2925    =head3 CleanKeywords
2926    
2927    C<< my $cleanedString = $erdb->CleanKeywords($searchExpression); >>
2928    
2929    Clean up a search expression or keyword list. This is a virtual method that may
2930    be overridden by the subclass. The base-class method removes extra spaces
2931    and converts everything to lower case.
2932    
2933    =over 4
2934    
2935    =item searchExpression
2936    
2937    Search expression or keyword list to clean. Note that a search expression may
2938    contain boolean operators which need to be preserved. This includes leading
2939    minus signs.
2940    
2941    =item RETURN
2942    
2943    Cleaned expression or keyword list.
2944    
2945    =back
2946    
2947    =cut
2948    
2949    sub CleanKeywords {
2950        # Get the parameters.
2951        my ($self, $searchExpression) = @_;
2952        # Lower-case the expression and copy it into the return variable. Note that we insure we
2953        # don't accidentally end up with an undefined value.
2954        my $retVal = lc($searchExpression || "");
2955        # Remove extra spaces.
2956        $retVal =~ s/\s+/ /g;
2957        $retVal =~ s/(^\s+)|(\s+$)//g;
2958        # Return the result.
2959        return $retVal;
2960    }
2961    
2962    =head3 GetSourceObject
2963    
2964    C<< my $source = $erdb->GetSourceObject($entityName); >>
2965    
2966    Return the object to be used in loading special attributes of the specified entity. The
2967    algorithm for loading special attributes is stored in the C<DataGen> elements of the
2968    XML
2969    
2970  =head2 Internal Utility Methods  =head2 Internal Utility Methods
2971    
2972  =head3 SetupSQL  =head3 _RelationMap
2973    
2974    C<< my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef); >>
2975    
2976    Create the relation map for an SQL query. The relation map is used by B<DBObject>
2977    to determine how to interpret the results of the query.
2978    
2979    =over 4
2980    
2981    =item mappedNameHashRef
2982    
2983    Reference to a hash that maps modified object names to real object names.
2984    
2985    =item mappedNameListRef
2986    
2987    Reference to a list of modified object names in the order they appear in the
2988    SELECT list.
2989    
2990    =item RETURN
2991    
2992    Returns a list of 2-tuples. Each tuple consists of an object name as used in the
2993    query followed by the actual name of that object. This enables the B<DBObject> to
2994    determine the order of the tables in the query and which object name belongs to each
2995    mapped object name. Most of the time these two values are the same; however, if a
2996    relation occurs twice in the query, the relation name in the field list and WHERE
2997    clause will use a mapped name (generally the actual relation name with a numeric
2998    suffix) that does not match the actual relation name.
2999    
3000    =back
3001    
3002    =cut
3003    
3004    sub _RelationMap {
3005        # Get the parameters.
3006        my ($mappedNameHashRef, $mappedNameListRef) = @_;
3007        # Declare the return variable.
3008        my @retVal = ();
3009        # Build the map.
3010        for my $mappedName (@{$mappedNameListRef}) {
3011            push @retVal, [$mappedName, $mappedNameHashRef->{$mappedName}];
3012        }
3013        # Return it.
3014        return @retVal;
3015    }
3016    
3017    
3018    =head3 _SetupSQL
3019    
3020  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
3021  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 2346  Line 3035 
3035  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
3036  optionally the C<ORDER BY> and C<LIMIT> clauses.  optionally the C<ORDER BY> and C<LIMIT> clauses.
3037    
3038    =item matchClause
3039    
3040    An optional full-text search clause. If specified, it will be inserted at the
3041    front of the WHERE clause. It should already be SQL-formatted; that is, the
3042    field names should be in the form I<table>C<.>I<fieldName>.
3043    
3044  =item RETURN  =item RETURN
3045    
3046  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 2358  Line 3053 
3053  =cut  =cut
3054    
3055  sub _SetupSQL {  sub _SetupSQL {
3056      my ($self, $objectNames, $filterClause) = @_;      my ($self, $objectNames, $filterClause, $matchClause) = @_;
3057      # 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
3058      # 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
3059      # 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 2407  Line 3102 
3102      # FROM name1, name2, ... nameN      # FROM name1, name2, ... nameN
3103      #      #
3104      my $suffix = "FROM " . join(', ', @fromList);      my $suffix = "FROM " . join(', ', @fromList);
3105        # Now for the WHERE. First, we need a place for the filter string.
3106        my $filterString = "";
3107        # We will also keep a list of conditions to add to the WHERE clause in order to link
3108        # entities and relationships as well as primary relations to secondary ones.
3109        my @joinWhere = ();
3110      # Check for a filter clause.      # Check for a filter clause.
3111      if ($filterClause) {      if ($filterClause) {
3112          # 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,
3113          # We create a copy of the filter string we can work with.          # We create a copy of the filter string we can work with.
3114          my $filterString = $filterClause;          $filterString = $filterClause;
3115          # Next, we sort the object names by length. This helps protect us from finding          # Next, we sort the object names by length. This helps protect us from finding
3116          # object names inside other object names when we're doing our search and replace.          # object names inside other object names when we're doing our search and replace.
3117          my @sortedNames = sort { length($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 = ();  
3118          # 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
3119          # 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
3120          # 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 2485  Line 3182 
3182                  }                  }
3183              }              }
3184          }          }
3185        }
3186          # 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
3187          # 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
3188          # 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
3189          # list before running through it.      # list before running through it, because we shift off the first object before
3190        # processing the rest.
3191          my @mappedObjectList = @mappedNameList;          my @mappedObjectList = @mappedNameList;
3192          my $lastMappedObject = shift @mappedObjectList;          my $lastMappedObject = shift @mappedObjectList;
3193          # Get the join table.          # Get the join table.
# Line 2517  Line 3216 
3216          # 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.
3217          # We'll put the ORDER BY / LIMIT clauses in the following variable.          # We'll put the ORDER BY / LIMIT clauses in the following variable.
3218          my $orderClause = "";          my $orderClause = "";
3219        # This is only necessary if we have a filter string in which the ORDER BY
3220        # and LIMIT clauses can live.
3221        if ($filterString) {
3222          # 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
3223          # operator so that we find the first occurrence of either verb.          # operator so that we find the first occurrence of either verb.
3224          if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {          if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {
# Line 2525  Line 3227 
3227              $orderClause = $2 . substr($filterString, $pos);              $orderClause = $2 . substr($filterString, $pos);
3228              $filterString = $1;              $filterString = $1;
3229          }          }
3230          # Add the filter and the join clauses (if any) to the SELECT command.      }
3231        # All the things that are supposed to be in the WHERE clause of the
3232        # SELECT command need to be put into @joinWhere so we can string them
3233        # together. We begin with the match clause. This is important,
3234        # because the match clause's parameter mark must precede any parameter
3235        # marks in the filter string.
3236        if ($matchClause) {
3237            push @joinWhere, $matchClause;
3238        }
3239        # Add the filter string. We put it in parentheses to avoid operator
3240        # precedence problems with the match clause or the joins.
3241          if ($filterString) {          if ($filterString) {
3242              Trace("Filter string is \"$filterString\".") if T(4);              Trace("Filter string is \"$filterString\".") if T(4);
3243              push @joinWhere, "($filterString)";              push @joinWhere, "($filterString)";
3244          }          }
3245        # String it all together into a big filter clause.
3246          if (@joinWhere) {          if (@joinWhere) {
3247              $suffix .= " WHERE " . join(' AND ', @joinWhere);              $suffix .= " WHERE " . join(' AND ', @joinWhere);
3248          }          }
3249          # Add the sort or limit clause (if any) to the SELECT command.      # Add the sort or limit clause (if any).
3250          if ($orderClause) {          if ($orderClause) {
3251              $suffix .= " $orderClause";              $suffix .= " $orderClause";
3252          }          }
     }  
3253      # Return the suffix, the mapped name list, and the mapped name hash.      # Return the suffix, the mapped name list, and the mapped name hash.
3254      return ($suffix, \@mappedNameList, \%mappedNameHash);      return ($suffix, \@mappedNameList, \%mappedNameHash);
3255  }  }
3256    
3257  =head3 GetStatementHandle  =head3 _GetStatementHandle
3258    
3259  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.
3260  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 2585  Line 3297 
3297      return $sth;      return $sth;
3298  }  }
3299    
3300  =head3 GetLoadStats  =head3 _GetLoadStats
3301    
3302  Return a blank statistics object for use by the load methods.  Return a blank statistics object for use by the load methods.
3303    
# Line 2597  Line 3309 
3309      return Stats->new();      return Stats->new();
3310  }  }
3311    
3312  =head3 GenerateFields  =head3 _DumpRelation
   
 Generate field values from a field structure and store in a specified table. The field names  
 are first sorted by pass count, certain pre-defined fields are removed from the list, and  
 then we rip through them evaluation the data generation string. Fields in the primary relation  
 are stored as scalars; fields in secondary relations are stored as value lists.  
   
 This is a static method.  
   
 =over 4  
   
 =item this  
   
 Hash table into which the field values should be placed.  
   
 =item fields  
   
 Field structure from which the field descriptors should be taken.  
   
 =item type  
   
 Type name of the object whose fields are being generated.  
   
 =item values (optional)  
   
 Reference to a value structure from which additional values can be taken.  
   
 =item from (optiona)  
   
 Reference to the source entity instance if relationship data is being generated.  
   
 =item to (optional)  
   
 Reference to the target entity instance if relationship data is being generated.  
   
 =back  
   
 =cut  
   
 sub _GenerateFields {  
     # Get the parameters.  
     my ($this, $fields, $type, $values, $from, $to) = @_;  
     # Sort the field names by pass number.  
     my @fieldNames = sort { $fields->{$a}->{DataGen}->{pass} <=> $fields->{$b}->{DataGen}->{pass} } keys %{$fields};  
     # Loop through the field names, generating data.  
     for my $name (@fieldNames) {  
         # Only proceed if this field needs to be generated.  
         if (!exists $this->{$name}) {  
             # Get this field's data generation descriptor.  
             my $fieldDescriptor = $fields->{$name};  
             my $data = $fieldDescriptor->{DataGen};  
             # Get the code to generate the field value.  
             my $codeString = $data->{content};  
             # Determine whether or not this field is in the primary relation.  
             if ($fieldDescriptor->{relation} eq $type) {  
                 # Here we have a primary relation field. Store the field value as  
                 # a scalar.  
                 $this->{$name} = eval($codeString);  
             } else {  
                 # Here we have a secondary relation field. Create a null list  
                 # and push the desired number of field values onto it.  
                 my @fieldValues = ();  
                 my $count = IntGen(0,$data->{testCount});  
                 for (my $i = 0; $i < $count; $i++) {  
                     my $newValue = eval($codeString);  
                     push @fieldValues, $newValue;  
                 }  
                 # Store the value list in the main hash.  
                 $this->{$name} = \@fieldValues;  
             }  
         }  
     }  
 }  
   
 =head3 DumpRelation  
3313    
3314  Dump the specified relation's to the specified output file in tab-delimited format.  Dump the specified relation to the specified output file in tab-delimited format.
3315    
3316  This is an instance method.  This is an instance method.
3317    
# Line 2721  Line 3359 
3359      close DTXOUT;      close DTXOUT;
3360  }  }
3361    
3362  =head3 GetStructure  =head3 _GetStructure
3363    
3364  Get the data structure for a specified entity or relationship.  Get the data structure for a specified entity or relationship.
3365    
# Line 2760  Line 3398 
3398      return $retVal;      return $retVal;
3399  }  }
3400    
3401  =head3 GetRelationTable  
3402    
3403    =head3 _GetRelationTable
3404    
3405  Get the list of relations for a specified entity or relationship.  Get the list of relations for a specified entity or relationship.
3406    
# Line 2789  Line 3429 
3429      return $objectData->{Relations};      return $objectData->{Relations};
3430  }  }
3431    
3432  =head3 ValidateFieldNames  =head3 _ValidateFieldNames
3433    
3434  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
3435  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 2816  Line 3456 
3456          for my $object (values %{$metadata->{$section}}) {          for my $object (values %{$metadata->{$section}}) {
3457              # Loop through the object's fields.              # Loop through the object's fields.
3458              for my $fieldName (keys %{$object->{Fields}}) {              for my $fieldName (keys %{$object->{Fields}}) {
3459                  # Now we make some initial validations.                  # If this field name is invalid, set the return value to zero
3460                  if ($fieldName =~ /--/) {                  # so we know we encountered an error.
3461                      # Here we have a doubled minus sign.                  if (! ValidateFieldName($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";  
3462                          $retVal = 0;                          $retVal = 0;
3463                      }                      }
3464                  }                  }
3465              }              }
3466          }          }
     }  
3467      # If an error was found, fail.      # If an error was found, fail.
3468      if ($retVal  == 0) {      if ($retVal  == 0) {
3469          Confess("Errors found in field names.");          Confess("Errors found in field names.");
3470      }      }
3471  }  }
3472    
3473  =head3 LoadRelation  =head3 _LoadRelation
3474    
3475  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
3476  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 2904  Line 3530 
3530      return $retVal;      return $retVal;
3531  }  }
3532    
3533  =head3 LoadMetaData  
3534    =head3 _LoadMetaData
3535    
3536  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.
3537  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 2932  Line 3559 
3559      Trace("Reading Sprout DBD from $filename.") if T(2);      Trace("Reading Sprout DBD from $filename.") if T(2);
3560      # 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
3561      # get the exact structure we want.      # get the exact structure we want.
3562      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 $filename.") if T(1);  
3563      # Before we go any farther, we need to validate the field and object names. If an error is found,      # Before we go any farther, we need to validate the field and object names. If an error is found,
3564      # the method below will fail.      # the method below will fail.
3565      _ValidateFieldNames($metadata);      _ValidateFieldNames($metadata);
# Line 3231  Line 3845 
3845      return $metadata;      return $metadata;
3846  }  }
3847    
3848  =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  
3849    
3850  Create an index for a relationship's relation.  Create an index for a relationship's relation.
3851    
# Line 3316  Line 3890 
3890      _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);      _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);
3891  }  }
3892    
3893  =head3 AddIndex  =head3 _AddIndex
3894    
3895  Add an index to a relation structure.  Add an index to a relation structure.
3896    
# Line 3362  Line 3936 
3936      $relationStructure->{Indexes}->{$indexName} = $newIndex;      $relationStructure->{Indexes}->{$indexName} = $newIndex;
3937  }  }
3938    
3939  =head3 FixupFields  =head3 _FixupFields
3940    
3941  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
3942  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 3400  Line 3974 
3974          # Here it doesn't, so we create a new one.          # Here it doesn't, so we create a new one.
3975          $structure->{Fields} = { };          $structure->{Fields} = { };
3976      } else {      } else {
3977          # 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
3978            # create a list for stashing them.
3979            my @textFields = ();
3980            # Loop through the fields.
3981          my $fieldStructures = $structure->{Fields};          my $fieldStructures = $structure->{Fields};
3982          for my $fieldName (keys %{$fieldStructures}) {          for my $fieldName (keys %{$fieldStructures}) {
3983              Trace("Processing field $fieldName of $defaultRelationName.") if T(4);              Trace("Processing field $fieldName of $defaultRelationName.") if T(4);
# Line 3409  Line 3986 
3986              my $type = $fieldData->{type};              my $type = $fieldData->{type};
3987              # Plug in a relation name if it is needed.              # Plug in a relation name if it is needed.
3988              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });
3989              # Plug in a data generator if we need one.              # Check for searchability.
3990              if (!exists $fieldData->{DataGen}) {              if ($fieldData->{searchable}) {
3991                  # The data generator will use the default for the field's type.                  # Only allow this for a primary relation.
3992                  $fieldData->{DataGen} = { content => $TypeTable{$type}->{dataGen} };                  if ($fieldData->{relation} ne $defaultRelationName) {
3993                        Confess("Field $fieldName of $defaultRelationName is in secondary relations and cannot be searchable.");
3994                    } else {
3995                        push @textFields, $fieldName;
3996                    }
3997              }              }
             # Plug in the defaults for the optional data generation parameters.  
             Tracer::MergeOptions($fieldData->{DataGen}, { testCount => 1, pass => 0 });  
3998              # Add the PrettySortValue.              # Add the PrettySortValue.
3999              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);
4000          }          }
4001            # If there are searchable fields, remember the fact.
4002            if (@textFields) {
4003                $structure->{searchFields} = \@textFields;
4004            }
4005      }      }
4006  }  }
4007    
4008  =head3 FixName  =head3 _FixName
4009    
4010  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.
4011    
# Line 3451  Line 4034 
4034      return $fieldName;      return $fieldName;
4035  }  }
4036    
4037  =head3 FixNames  =head3 _FixNames
4038    
4039  Fix all the field names in a list.  Fix all the field names in a list.
4040    
# Line 3482  Line 4065 
4065      return @result;      return @result;
4066  }  }
4067    
4068  =head3 AddField  =head3 _AddField
4069    
4070  Add a field to a field list.  Add a field to a field list.
4071    
# Line 3517  Line 4100 
4100      $fieldList->{$fieldName} = $fieldStructure;      $fieldList->{$fieldName} = $fieldStructure;
4101  }  }
4102    
4103  =head3 ReOrderRelationTable  =head3 _ReOrderRelationTable
4104    
4105  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
4106  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 3578  Line 4161 
4161    
4162  }  }
4163    
4164  =head3 IsPrimary  =head3 _IsPrimary
4165    
4166  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
4167  if it has the same name as an entity or relationship.  if it has the same name as an entity or relationship.
# Line 3614  Line 4197 
4197      return $retVal;      return $retVal;
4198  }  }
4199    
4200  =head3 FindRelation  =head3 _FindRelation
4201    
4202  Return the descriptor for the specified relation.  Return the descriptor for the specified relation.
4203    
# Line 3645  Line 4228 
4228    
4229  =head2 HTML Documentation Utility Methods  =head2 HTML Documentation Utility Methods
4230    
4231  =head3 ComputeRelationshipSentence  =head3 _ComputeRelationshipSentence
4232    
4233  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
4234  two related entities and an arity indicator.  two related entities and an arity indicator.
# Line 3683  Line 4266 
4266      return $result;      return $result;
4267  }  }
4268    
4269  =head3 ComputeRelationshipHeading  =head3 _ComputeRelationshipHeading
4270    
4271  The relationship heading is the L<relationship sentence|/ComputeRelationshipSentence> with the entity  The relationship heading is the L<relationship sentence|/ComputeRelationshipSentence> with the entity
4272  names hyperlinked to the appropriate entity sections of the document.  names hyperlinked to the appropriate entity sections of the document.
# Line 3720  Line 4303 
4303      return $result;      return $result;
4304  }  }
4305    
4306  =head3 ShowRelationTable  =head3 _ShowRelationTable
4307    
4308  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
4309  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 3770  Line 4353 
4353          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";
4354          # Add any note text.          # Add any note text.
4355          if (my $note = $indexData->{Notes}) {          if (my $note = $indexData->{Notes}) {
4356              $htmlString .= "<li>" . _HTMLNote($note->{content}) . "</li>\n";              $htmlString .= "<li>" . HTMLNote($note->{content}) . "</li>\n";
4357          }          }
4358          # Add the fiield list.          # Add the fiield list.
4359          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";
# Line 3781  Line 4364 
4364      $htmlString .= "</ul>\n";      $htmlString .= "</ul>\n";
4365  }  }
4366    
4367  =head3 OpenFieldTable  =head3 _OpenFieldTable
4368    
4369  This method creates the header string for the field table generated by L</ShowMetaData>.  This method creates the header string for the field table generated by L</ShowMetaData>.
4370    
# Line 3806  Line 4389 
4389      return _OpenTable($tablename, 'Field', 'Type', 'Description');      return _OpenTable($tablename, 'Field', 'Type', 'Description');
4390  }  }
4391    
4392  =head3 OpenTable  =head3 _OpenTable
4393    
4394  This method creates the header string for an HTML table.  This method creates the header string for an HTML table.
4395    
# Line 3846  Line 4429 
4429      return $htmlString;      return $htmlString;
4430  }  }
4431    
4432  =head3 CloseTable  =head3 _CloseTable
4433    
4434  This method returns the HTML for closing a table.  This method returns the HTML for closing a table.
4435    
# Line 3858  Line 4441 
4441      return "</table></p>\n";      return "</table></p>\n";
4442  }  }
4443    
4444  =head3 ShowField  =head3 _ShowField
4445    
4446  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.
4447    
# Line 3885  Line 4468 
4468      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>";
4469      # If we have content, add it as a third column.      # If we have content, add it as a third column.
4470      if (exists $fieldData->{Notes}) {      if (exists $fieldData->{Notes}) {
4471          $htmlString .= "<td>" . _HTMLNote($fieldData->{Notes}->{content}) . "</td>";          $htmlString .= "<td>" . HTMLNote($fieldData->{Notes}->{content}) . "</td>";
4472      }      }
4473      # Close off the row.      # Close off the row.
4474      $htmlString .= "</tr>\n";      $htmlString .= "</tr>\n";
# Line 3893  Line 4476 
4476      return $htmlString;      return $htmlString;
4477  }  }
4478    
 =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;  
 }  
   
4479  1;  1;

Legend:
Removed from v.1.55  
changed lines
  Added in v.1.73

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3