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

Diff of /Sprout/ERDB.pm

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

revision 1.47, Sun Jun 18 05:14:56 2006 UTC revision 1.88, Tue Apr 10 05:54:18 2007 UTC
# Line 6  Line 6 
6      use Data::Dumper;      use Data::Dumper;
7      use XML::Simple;      use XML::Simple;
8      use DBQuery;      use DBQuery;
9      use DBObject;      use ERDBObject;
10      use Stats;      use Stats;
11      use Time::HiRes qw(gettimeofday);      use Time::HiRes qw(gettimeofday);
12      use Digest::MD5 qw(md5_base64);      use Digest::MD5 qw(md5_base64);
13      use FIG;      use FIG;
14        use CGI;
15    
16  =head1 Entity-Relationship Database Package  =head1 Entity-Relationship Database Package
17    
# Line 59  Line 60 
60  B<start-position>, which indicates where in the contig that the sequence begins. This attribute  B<start-position>, which indicates where in the contig that the sequence begins. This attribute
61  is implemented as the C<start_position> field in the C<IsMadeUpOf> relation.  is implemented as the C<start_position> field in the C<IsMadeUpOf> relation.
62    
63  The database itself is described by an XML file using the F<ERDatabase.xsd> schema. In addition to  The database itself is described by an XML file. In addition to all the data required to define
64  all the data required to define the entities, relationships, and attributes, the schema provides  the entities, relationships, and attributes, the schema provides space for notes describing
65  space for notes describing the data and what it means. These notes are used by L</ShowMetaData>  the data and what it means. These notes are used by L</ShowMetaData> to generate documentation
66  to generate documentation for the database.  for the database.
67    
68    Special support is provided for text searching. An entity field can be marked as <em>searchable</em>,
69    in which case it will be used to generate a text search index in which the user searches for words
70    in the field instead of a particular field value.
71    
72  Finally, every entity and relationship object has a flag indicating if it is new or old. The object  Finally, every entity and relationship object has a flag indicating if it is new or old. The object
73  is considered I<old> if it was loaded by the L</LoadTables> method. It is considered I<new> if it  is considered I<old> if it was loaded by the L</LoadTables> method. It is considered I<new> if it
74  was inserted by the L</InsertObject> method.  was inserted by the L</InsertObject> method.
75    
 To facilitate testing, the ERDB module supports automatic generation of test data. This process  
 is described in the L</GenerateEntity> and L</GenerateConnection> methods, though it is not yet  
 fully implemented.  
   
76  =head2 XML Database Description  =head2 XML Database Description
77    
78  =head3 Data Types  =head3 Data Types
# Line 91  Line 92 
92    
93  32-bit signed integer  32-bit signed integer
94    
95    =item counter
96    
97    32-bit unsigned integer
98    
99  =item date  =item date
100    
101  64-bit unsigned integer, representing a PERL date/time value  64-bit unsigned integer, representing a PERL date/time value
# Line 186  Line 191 
191    
192  Name of the field. The field name should contain only letters, digits, and hyphens (C<->),  Name of the field. The field name should contain only letters, digits, and hyphens (C<->),
193  and the first character should be a letter. Most underlying databases are case-insensitive  and the first character should be a letter. Most underlying databases are case-insensitive
194  with the respect to field names, so a best practice is to use lower-case letters only.  with the respect to field names, so a best practice is to use lower-case letters only. Finally,
195    the name C<search-relevance> has special meaning for full-text searches and should not be
196    used as a field name.
197    
198  =item type  =item type
199    
# Line 205  Line 212 
212  entity, the fields without a relation attribute are said to belong to the  entity, the fields without a relation attribute are said to belong to the
213  I<primary relation>. This relation has the same name as the entity itself.  I<primary relation>. This relation has the same name as the entity itself.
214    
215    =item searchable
216    
217    If specified, then the field is a candidate for full-text searching. A single full-text
218    index will be created for each relation with at least one searchable field in it.
219    For best results, this option should only be used for string or text fields.
220    
221    =item special
222    
223    This attribute allows the subclass to assign special meaning for certain fields.
224    The interpretation is up to the subclass itself. Currently, only entity fields
225    can have this attribute.
226    
227  =back  =back
228    
229  =head3 Indexes  =head3 Indexes
230    
231  An entity can have multiple alternate indexes associated with it. The fields must  An entity can have multiple alternate indexes associated with it. The fields in an
232  be from the primary relation. The alternate indexes assist in ordering results  index must all be from the same relation. The alternate indexes assist in searching
233  from a query. A relationship can have up to two indexes-- a I<to-index> and a  on fields other than the entity ID. A relationship has at least two indexes-- a I<to-index> and a
234  I<from-index>. These order the results when crossing the relationship. For  I<from-index> that order the results when crossing the relationship. For
235  example, in the relationship C<HasContig> from C<Genome> to C<Contig>, the  example, in the relationship C<HasContig> from C<Genome> to C<Contig>, the
236  from-index would order the contigs of a ganome, and the to-index would order  from-index would order the contigs of a ganome, and the to-index would order
237  the genomes of a contig. A relationship's index must specify only fields in  the genomes of a contig. In addition, it can have zero or more alternate
238    indexes. A relationship's index must specify only fields in
239  the relationship.  the relationship.
240    
241  The indexes for an entity must be listed inside the B<Indexes> tag. The from-index  The alternate indexes for an entity or relationship must be listed inside the B<Indexes> tag.
242  of a relationship is specified using the B<FromIndex> tag; the to-index is specified  The from-index of a relationship is specified using the B<FromIndex> tag; the to-index is
243  using the B<ToIndex> tag.  specified using the B<ToIndex> tag.
244    
245  Each index can contain a B<Notes> tag. In addition, it will have an B<IndexFields>  Each index can contain a B<Notes> tag. In addition, it will have an B<IndexFields>
246  tag containing the B<IndexField> tags. These specify, in order, the fields used in  tag containing the B<IndexField> tags. These specify, in order, the fields used in
# Line 238  Line 258 
258    
259  =back  =back
260    
261  The B<Index>, B<FromIndex>, and B<ToIndex> tags themselves have no attributes.  The B<FromIndex>, and B<ToIndex> tags have no attributes. The B<Index> tag can
262    have a B<Unique> attribute. If specified, the index will be generated as a unique
263    index.
264    
265  =head3 Object and Field Names  =head3 Object and Field Names
266    
# Line 282  Line 304 
304    
305  A relationship is described by the C<Relationship> tag. Within a relationship,  A relationship is described by the C<Relationship> tag. Within a relationship,
306  there can be a C<Notes> tag, a C<Fields> tag containing the intersection data  there can be a C<Notes> tag, a C<Fields> tag containing the intersection data
307  fields, a C<FromIndex> tag containing the from-index, and a C<ToIndex> tag containing  fields, a C<FromIndex> tag containing the from-index, a C<ToIndex> tag containing
308  the to-index.  the to-index, and an C<Indexes> tag containing the alternate indexes.
309    
310  The C<Relationship> tag has the following attributes.  The C<Relationship> tag has the following attributes.
311    
# Line 316  Line 338 
338    
339  # 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.
340  # "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
341  # 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
342  # 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,
343  # record sizes.  # and "indexMod", if non-zero, is the number of characters to use when the field is specified in an
344  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, dataGen => "StringGen('A')" },  # index
345                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, dataGen => "IntGen(0, 99999999)" },  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",
346                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, dataGen => "StringGen(IntGen(10,250))" },                                 indexMod =>   0, notes => "single ASCII character"},
347                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, dataGen => "StringGen(IntGen(80,1000))" },                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n",
348                    date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, dataGen => "DateGen(-7, 7, IntGen(0,1400))" },                                 indexMod =>   0, notes => "signed 32-bit integer"},
349                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, dataGen => "FloatGen(0.0, 100.0)" },                    counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n",
350                    boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, dataGen => "IntGen(0, 1)" },                                 indexMod =>   0, notes => "unsigned 32-bit integer"},
351                      string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, sort => "",
352                                   indexMod =>   0, notes => "character string, 0 to 255 characters"},
353                      text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, sort => "",
354                                   indexMod => 255, notes => "character string, nearly unlimited length, only first 255 characters are indexed"},
355                      date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, sort => "n",
356                                   indexMod =>   0, notes => "signed, 64-bit integer"},
357                      float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, sort => "g",
358                                   indexMod =>   0, notes => "64-bit double precision floating-point number"},
359                      boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, sort => "n",
360                                   indexMod =>   0, notes => "boolean value: 0 if false, 1 if true"},
361                   'hash-string' =>                   'hash-string' =>
362                               { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, dataGen => "SringGen(22)" },                               { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, sort => "",
363                                   indexMod =>   0, notes => "string stored in digested form, used for certain types of key fields"},
364                   'id-string' =>                   'id-string' =>
365                               { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, dataGen => "SringGen(22)" },                               { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, sort => "",
366                                   indexMod =>   0, notes => "character string, 0 to 25 characters"},
367                   'key-string' =>                   'key-string' =>
368                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, dataGen => "StringGen(IntGen(10,40))" },                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, sort => "",
369                                   indexMod =>   0, notes => "character string, 0 to 40 characters"},
370                   'name-string' =>                   'name-string' =>
371                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, dataGen => "StringGen(IntGen(10,80))" },                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, sort => "",
372                                   indexMod =>   0, notes => "character string, 0 to 80 characters"},
373                   'medium-string' =>                   'medium-string' =>
374                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, dataGen => "StringGen(IntGen(10,160))" },                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",
375                                   indexMod =>   0, notes => "character string, 0 to 160 characters"},
376                  );                  );
377    
378  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 344  Line 381 
381                     'MM' => 'many-to-many'                     'MM' => 'many-to-many'
382                   );                   );
383    
384  # Table for interpreting string patterns.  # Options for XML input and output.
385    
386    my %XmlOptions = (GroupTags =>  { Relationships => 'Relationship',
387                                      Entities => 'Entity',
388                                      Fields => 'Field',
389                                      Indexes => 'Index',
390                                      IndexFields => 'IndexField'
391                                    },
392                      KeyAttr =>    { Relationship => 'name',
393                                      Entity => 'name',
394                                      Field => 'name'
395                                    },
396                      SuppressEmpty => 1,
397                     );
398    
399  my %PictureTable = ( 'A' => "abcdefghijklmnopqrstuvwxyz",  my %XmlInOpts  = (
400                       '9' => "0123456789",                    ForceArray => ['Field', 'Index', 'IndexField', 'Relationship', 'Entity'],
401                       'X' => "abcdefghijklmnopqrstuvwxyz0123456789",                    ForceContent => 1,
402                       'V' => "aeiou",                    NormalizeSpace => 2,
403                       'K' => "bcdfghjklmnoprstvwxyz"                   );
404    my %XmlOutOpts = (
405                      RootName => 'Database',
406                      XMLDecl => 1,
407                     );                     );
408    
409    
410  =head2 Public Methods  =head2 Public Methods
411    
412  =head3 new  =head3 new
# Line 493  Line 547 
547          my $entityData = $entityList->{$key};          my $entityData = $entityList->{$key};
548          # If there's descriptive text, display it.          # If there's descriptive text, display it.
549          if (my $notes = $entityData->{Notes}) {          if (my $notes = $entityData->{Notes}) {
550              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
551          }          }
552          # Now we want a list of the entity's relationships. First, we set up the relationship subsection.          # See if we need a list of the entity's relationships.
553            my $relCount = keys %{$relationshipList};
554            if ($relCount > 0) {
555                # First, we set up the relationship subsection.
556          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
557          # Loop through the relationships.          # Loop through the relationships.
558          for my $relationship (sort keys %{$relationshipList}) {          for my $relationship (sort keys %{$relationshipList}) {
# Line 511  Line 568 
568          }          }
569          # Close off the relationship list.          # Close off the relationship list.
570          $retVal .= "</ul>\n";          $retVal .= "</ul>\n";
571            }
572          # Get the entity's relations.          # Get the entity's relations.
573          my $relationList = $entityData->{Relations};          my $relationList = $entityData->{Relations};
574          # Create a header for the relation subsection.          # Create a header for the relation subsection.
# Line 550  Line 608 
608          $retVal .= "</p>\n";          $retVal .= "</p>\n";
609          # If there are notes on this relationship, display them.          # If there are notes on this relationship, display them.
610          if (my $notes = $relationshipStructure->{Notes}) {          if (my $notes = $relationshipStructure->{Notes}) {
611              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
612          }          }
613          # Generate the relationship's relation table.          # Generate the relationship's relation table.
614          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
# Line 597  Line 655 
655      return Data::Dumper::Dumper($self->{_metaData});      return Data::Dumper::Dumper($self->{_metaData});
656  }  }
657    
658    =head3 FindIndexForEntity
659    
660    C<< my $indexFound = ERDB::FindIndexForEntity($xml, $entityName, $attributeName); >>
661    
662    This method locates the entry in an entity's index list that begins with the
663    specified attribute name. If the entity has no index list, one will be
664    created. This method works on raw XML, not a live ERDB object.
665    
666    =over 4
667    
668    =item xml
669    
670    The raw XML structure defining the database.
671    
672    =item entityName
673    
674    The name of the relevant entity.
675    
676    =item attributeName
677    
678    The name of the attribute relevant to the search.
679    
680    =item RETURN
681    
682    The numerical index in the index list of the index entry for the specified entity and
683    attribute, or C<undef> if no such index exists.
684    
685    =back
686    
687    =cut
688    
689    sub FindIndexForEntity {
690        # Get the parameters.
691        my ($xml, $entityName, $attributeName) = @_;
692        # Declare the return variable.
693        my $retVal;
694        # Get the named entity.
695        my $entityData = $xml->{Entities}->{$entityName};
696        if (! $entityData) {
697            Confess("Entity $entityName not found in DBD structure.");
698        } else {
699            # Insure it has an index list.
700            if (! exists $entityData->{Indexes}) {
701                $entityData->{Indexes} = [];
702            } else {
703                # Search for the desired index.
704                my $indexList = $entityData->{Indexes};
705                my $n = scalar @{$indexList};
706                Trace("Searching $n indexes in index list for $entityName.") if T(2);
707                # We use an indexed FOR here because we're returning an
708                # index number instead of an object. We do THAT so we can
709                # delete the index from the list if needed.
710                for (my $i = 0; $i < $n && !defined($retVal); $i++) {
711                    my $index = $indexList->[$i];
712                    my $fields = $index->{IndexFields};
713                    # Technically this IF should be safe (that is, we are guaranteed
714                    # the existence of a "$fields->[0]"), because when we load the XML
715                    # we have SuppressEmpty specified.
716                    if ($fields->[0]->{name} eq $attributeName) {
717                        $retVal = $i;
718                    }
719                }
720            }
721        }
722        Trace("Index for $attributeName of $entityName found at position $retVal.") if defined($retVal) && T(3);
723        Trace("Index for $attributeName not found in $entityName.") if !defined($retVal) && T(3);
724        # Return the result.
725        return $retVal;
726    }
727    
728  =head3 CreateTables  =head3 CreateTables
729    
730  C<< $erdb->CreateTables(); >>  C<< $erdb->CreateTables(); >>
# Line 616  Line 744 
744      # Loop through the relations.      # Loop through the relations.
745      for my $relationName (@relNames) {      for my $relationName (@relNames) {
746          # Create a table for this relation.          # Create a table for this relation.
747          $self->CreateTable($relationName);          $self->CreateTable($relationName, 1);
748          Trace("Relation $relationName created.") if T(2);          Trace("Relation $relationName created.") if T(2);
749      }      }
750  }  }
# Line 684  Line 812 
812      Trace("Creating table $relationName: $fieldThing") if T(2);      Trace("Creating table $relationName: $fieldThing") if T(2);
813      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);
814      Trace("Relation $relationName created in database.") if T(2);      Trace("Relation $relationName created in database.") if T(2);
815      # If we want to build the indexes, we do it here.      # If we want to build the indexes, we do it here. Note that the full-text search
816        # index will not be built until the table has been loaded.
817      if ($indexFlag) {      if ($indexFlag) {
818          $self->CreateIndex($relationName);          $self->CreateIndex($relationName);
819      }      }
# Line 841  Line 970 
970      for my $indexName (keys %{$indexHash}) {      for my $indexName (keys %{$indexHash}) {
971          my $indexData = $indexHash->{$indexName};          my $indexData = $indexHash->{$indexName};
972          # Get the index's field list.          # Get the index's field list.
973          my @fieldList = _FixNames(@{$indexData->{IndexFields}});          my @rawFields = @{$indexData->{IndexFields}};
974            # Get a hash of the relation's field types.
975            my %types = map { $_->{name} => $_->{type} } @{$relationData->{Fields}};
976            # We need to check for text fields so we can append a length limitation for them. To do
977            # that, we need the relation's field list.
978            my $relFields = $relationData->{Fields};
979            for (my $i = 0; $i <= $#rawFields; $i++) {
980                # Get the field type.
981                my $field = $rawFields[$i];
982                my $type = $types{$field};
983                # Ask if it requires using prefix notation for the index.
984                my $mod = $TypeTable{$type}->{indexMod};
985                Trace("Field $field ($i) in $relationName has type $type and indexMod $mod.") if T(3);
986                if ($mod) {
987                    # Append the prefix length to the field name,
988                    $rawFields[$i] .= "($mod)";
989                }
990            }
991            my @fieldList = _FixNames(@rawFields);
992          my $flds = join(', ', @fieldList);          my $flds = join(', ', @fieldList);
993          # Get the index's uniqueness flag.          # Get the index's uniqueness flag.
994          my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
995          # Create the index.          # Create the index.
996          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
997                                      flds => $flds, unique => $unique);                                      flds => $flds, kind => $unique);
998          if ($rv) {          if ($rv) {
999              Trace("Index created: $indexName for $relationName ($flds)") if T(1);              Trace("Index created: $indexName for $relationName ($flds)") if T(1);
1000          } else {          } else {
# Line 856  Line 1003 
1003      }      }
1004  }  }
1005    
1006    =head3 GetSecondaryFields
1007    
1008    C<< my %fieldTuples = $erdb->GetSecondaryFields($entityName); >>
1009    
1010    This method will return a list of the name and type of each of the secondary
1011    fields for a specified entity. Secondary fields are stored in two-column tables
1012    in addition to the primary entity table. This enables the field to have no value
1013    or to have multiple values.
1014    
1015    =over 4
1016    
1017    =item entityName
1018    
1019    Name of the entity whose secondary fields are desired.
1020    
1021    =item RETURN
1022    
1023    Returns a hash mapping the field names to their field types.
1024    
1025    =back
1026    
1027    =cut
1028    
1029    sub GetSecondaryFields {
1030        # Get the parameters.
1031        my ($self, $entityName) = @_;
1032        # Declare the return variable.
1033        my %retVal = ();
1034        # Look for the entity.
1035        my $table = $self->GetFieldTable($entityName);
1036        # Loop through the fields, pulling out the secondaries.
1037        for my $field (sort keys %{$table}) {
1038            if ($table->{$field}->{relation} ne $entityName) {
1039                # Here we have a secondary field.
1040                $retVal{$field} = $table->{$field}->{type};
1041            }
1042        }
1043        # Return the result.
1044        return %retVal;
1045    }
1046    
1047    =head3 GetFieldRelationName
1048    
1049    C<< my $name = $erdb->GetFieldRelationName($objectName, $fieldName); >>
1050    
1051    Return the name of the relation containing a specified field.
1052    
1053    =over 4
1054    
1055    =item objectName
1056    
1057    Name of the entity or relationship containing the field.
1058    
1059    =item fieldName
1060    
1061    Name of the relevant field in that entity or relationship.
1062    
1063    =item RETURN
1064    
1065    Returns the name of the database relation containing the field, or C<undef> if
1066    the field does not exist.
1067    
1068    =back
1069    
1070    =cut
1071    
1072    sub GetFieldRelationName {
1073        # Get the parameters.
1074        my ($self, $objectName, $fieldName) = @_;
1075        # Declare the return variable.
1076        my $retVal;
1077        # Get the object field table.
1078        my $table = $self->GetFieldTable($objectName);
1079        # Only proceed if the field exists.
1080        if (exists $table->{$fieldName}) {
1081            # Determine the name of the relation that contains this field.
1082            $retVal = $table->{$fieldName}->{relation};
1083        }
1084        # Return the result.
1085        return $retVal;
1086    }
1087    
1088    =head3 DeleteValue
1089    
1090    C<< my $numDeleted = $erdb->DeleteValue($entityName, $id, $fieldName, $fieldValue); >>
1091    
1092    Delete secondary field values from the database. This method can be used to delete all
1093    values of a specified field for a particular entity instance, or only a single value.
1094    
1095    Secondary fields are stored in two-column relations separate from an entity's primary
1096    table, and as a result a secondary field can legitimately have no value or multiple
1097    values. Therefore, it makes sense to talk about deleting secondary fields where it
1098    would not make sense for primary fields.
1099    
1100    =over 4
1101    
1102    =item entityName
1103    
1104    Name of the entity from which the fields are to be deleted.
1105    
1106    =item id
1107    
1108    ID of the entity instance to be processed. If the instance is not found, this
1109    method will have no effect. If C<undef> is specified, all values for all of
1110    the entity instances will be deleted.
1111    
1112    =item fieldName
1113    
1114    Name of the field whose values are to be deleted.
1115    
1116    =item fieldValue (optional)
1117    
1118    Value to be deleted. If not specified, then all values of the specified field
1119    will be deleted for the entity instance. If specified, then only the values which
1120    match this parameter will be deleted.
1121    
1122    =item RETURN
1123    
1124    Returns the number of rows deleted.
1125    
1126    =back
1127    
1128    =cut
1129    
1130    sub DeleteValue {
1131        # Get the parameters.
1132        my ($self, $entityName, $id, $fieldName, $fieldValue) = @_;
1133        # Declare the return value.
1134        my $retVal = 0;
1135        # We need to set up an SQL command to do the deletion. First, we
1136        # find the name of the field's relation.
1137        my $table = $self->GetFieldTable($entityName);
1138        my $field = $table->{$fieldName};
1139        my $relation = $field->{relation};
1140        # Make sure this is a secondary field.
1141        if ($relation eq $entityName) {
1142            Confess("Cannot delete values of $fieldName for $entityName.");
1143        } else {
1144            # Set up the SQL command to delete all values.
1145            my $sql = "DELETE FROM $relation";
1146            # Build the filter.
1147            my @filters = ();
1148            my @parms = ();
1149            # Check for a filter by ID.
1150            if (defined $id) {
1151                push @filters, "id = ?";
1152                push @parms, $id;
1153            }
1154            # Check for a filter by value.
1155            if (defined $fieldValue) {
1156                push @filters, "$fieldName = ?";
1157                push @parms, $fieldValue;
1158            }
1159            # Append the filters to the command.
1160            if (@filters) {
1161                $sql .= " WHERE " . join(" AND ", @filters);
1162            }
1163            # Execute the command.
1164            my $dbh = $self->{_dbh};
1165            $retVal = $dbh->SQL($sql, 0, @parms);
1166        }
1167        # Return the result.
1168        return $retVal;
1169    }
1170    
1171  =head3 LoadTables  =head3 LoadTables
1172    
1173  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>
# Line 950  Line 1262 
1262      return sort keys %{$entityList};      return sort keys %{$entityList};
1263  }  }
1264    
1265    =head3 GetDataTypes
1266    
1267    C<< my %types = ERDB::GetDataTypes(); >>
1268    
1269    Return a table of ERDB data types. The table returned is a hash of hashes.
1270    The keys of the big hash are the datatypes. Each smaller hash has several
1271    values used to manage the data. The most interesting is the SQL type (key
1272    C<sqlType>) and the descriptive node (key C<notes>).
1273    
1274    Note that changing the values in the smaller hashes will seriously break
1275    things, so this data should be treated as read-only.
1276    
1277    =cut
1278    
1279    sub GetDataTypes {
1280        return %TypeTable;
1281    }
1282    
1283    
1284  =head3 IsEntity  =head3 IsEntity
1285    
1286  C<< my $flag = $erdb->IsEntity($entityName); >>  C<< my $flag = $erdb->IsEntity($entityName); >>
# Line 1094  Line 1425 
1425      return $retVal;      return $retVal;
1426  }  }
1427    
1428    
1429    
1430    =head3 Search
1431    
1432    C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>
1433    
1434    Perform a full text search with filtering. The search will be against a specified object
1435    in the object name list. That object will get an extra field containing the search
1436    relevance. Note that except for the search expression, the parameters of this method are
1437    the same as those for L</Get> and follow the same rules.
1438    
1439    =over 4
1440    
1441    =item searchExpression
1442    
1443    Boolean search expression for the text fields of the target object. The default mode for
1444    a Boolean search expression is OR, but we want the default to be AND, so we will
1445    add a C<+> operator to each word with no other operator before it.
1446    
1447    =item idx
1448    
1449    Index in the I<$objectNames> list of the table to be searched in full-text mode.
1450    
1451    =item objectNames
1452    
1453    List containing the names of the entity and relationship objects to be retrieved.
1454    
1455    =item filterClause
1456    
1457    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1458    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
1459    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
1460    in the filter clause should be added to the parameter list as additional parameters. The
1461    fields in a filter clause can come from primary entity relations, relationship relations,
1462    or secondary entity relations; however, all of the entities and relationships involved must
1463    be included in the list of object names.
1464    
1465    =item params
1466    
1467    Reference to a list of parameter values to be substituted into the filter clause.
1468    
1469    =item RETURN
1470    
1471    Returns a query object for the specified search.
1472    
1473    =back
1474    
1475    =cut
1476    
1477    sub Search {
1478        # Get the parameters.
1479        my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1480        # Declare the return variable.
1481        my $retVal;
1482        # Create a safety copy of the parameter list. Note we have to be careful to insure
1483        # a parameter list exists before we copy it.
1484        my @myParams = ();
1485        if (defined $params) {
1486            @myParams = @{$params};
1487        }
1488        # Get the first object's structure so we have access to the searchable fields.
1489        my $object1Name = $objectNames->[$idx];
1490        my $object1Structure = $self->_GetStructure($object1Name);
1491        # Get the field list.
1492        if (! exists $object1Structure->{searchFields}) {
1493            Confess("No searchable index for $object1Name.");
1494        } else {
1495            # Get the field list.
1496            my @fields = @{$object1Structure->{searchFields}};
1497            # Clean the search expression.
1498            my $actualKeywords = $self->CleanKeywords($searchExpression);
1499            # Prefix a "+" to each uncontrolled word. This converts the default
1500            # search mode from OR to AND.
1501            $actualKeywords =~ s/(^|\s)(\w|")/$1\+$2/g;
1502            Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1503            # We need two match expressions, one for the filter clause and one in the
1504            # query itself. Both will use a parameter mark, so we need to push the
1505            # search expression onto the front of the parameter list twice.
1506            unshift @myParams, $actualKeywords, $actualKeywords;
1507            # Build the match expression.
1508            my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
1509            my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
1510            # Process the SQL stuff.
1511            my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1512                $self->_SetupSQL($objectNames, $filterClause, $matchClause);
1513            # Create the query. Note that the match clause is inserted at the front of
1514            # the select fields.
1515            my $command = "SELECT DISTINCT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .
1516                ".* $suffix";
1517            my $sth = $self->_GetStatementHandle($command, \@myParams);
1518            # Now we create the relation map, which enables DBQuery to determine the order, name
1519            # and mapped name for each object in the query.
1520            my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
1521            # Return the statement object.
1522            $retVal = DBQuery::_new($self, $sth, \@relationMap, $object1Name);
1523        }
1524        return $retVal;
1525    }
1526    
1527  =head3 GetFlat  =head3 GetFlat
1528    
1529  C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>  C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>
# Line 1147  Line 1577 
1577      return @retVal;      return @retVal;
1578  }  }
1579    
1580    =head3 SpecialFields
1581    
1582    C<< my %specials = $erdb->SpecialFields($entityName); >>
1583    
1584    Return a hash mapping special fields in the specified entity to the value of their
1585    C<special> attribute. This enables the subclass to get access to the special field
1586    attributes without needed to plumb the internal ERDB data structures.
1587    
1588    =over 4
1589    
1590    =item entityName
1591    
1592    Name of the entity whose special fields are desired.
1593    
1594    =item RETURN
1595    
1596    Returns a hash. The keys of the hash are the special field names, and the values
1597    are the values from each special field's C<special> attribute.
1598    
1599    =back
1600    
1601    =cut
1602    
1603    sub SpecialFields {
1604        # Get the parameters.
1605        my ($self, $entityName) = @_;
1606        # Declare the return variable.
1607        my %retVal = ();
1608        # Find the entity's data structure.
1609        my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1610        # Loop through its fields, adding each special field to the return hash.
1611        my $fieldHash = $entityData->{Fields};
1612        for my $fieldName (keys %{$fieldHash}) {
1613            my $fieldData = $fieldHash->{$fieldName};
1614            if (exists $fieldData->{special}) {
1615                $retVal{$fieldName} = $fieldData->{special};
1616            }
1617        }
1618        # Return the result.
1619        return %retVal;
1620    }
1621    
1622  =head3 Delete  =head3 Delete
1623    
1624  C<< my $stats = $erdb->Delete($entityName, $objectID); >>  C<< my $stats = $erdb->Delete($entityName, $objectID, %options); >>
1625    
1626  Delete an entity instance from the database. The instance is deleted along with all entity and  Delete an entity instance from the database. The instance is deleted along with all entity and
1627  relationship instances dependent on it. The idea of dependence here is recursive. An object is  relationship instances dependent on it. The definition of I<dependence> is recursive.
1628  always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many  
1629  relationship connected to a dependent entity or the "to" entity connected to a 1-to-many  An object is always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many
1630    relationship connected to a dependent entity or if it is the "to" entity connected to a 1-to-many
1631  dependent relationship.  dependent relationship.
1632    
1633  =over 4  =over 4
# Line 1168  Line 1641 
1641  ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),  ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),
1642  then it is presumed to by a LIKE pattern.  then it is presumed to by a LIKE pattern.
1643    
1644  =item testFlag  =item options
1645    
1646  If TRUE, the delete statements will be traced without being executed.  A hash detailing the options for this delete operation.
1647    
1648  =item RETURN  =item RETURN
1649    
# Line 1179  Line 1652 
1652    
1653  =back  =back
1654    
1655    The permissible options for this method are as follows.
1656    
1657    =over 4
1658    
1659    =item testMode
1660    
1661    If TRUE, then the delete statements will be traced, but no changes will be made to the database.
1662    
1663    =item keepRoot
1664    
1665    If TRUE, then the entity instances will not be deleted, only the dependent records.
1666    
1667    =back
1668    
1669  =cut  =cut
1670  #: Return Type $%;  #: Return Type $%;
1671  sub Delete {  sub Delete {
1672      # Get the parameters.      # Get the parameters.
1673      my ($self, $entityName, $objectID, $testFlag) = @_;      my ($self, $entityName, $objectID, %options) = @_;
1674      # Declare the return variable.      # Declare the return variable.
1675      my $retVal = Stats->new();      my $retVal = Stats->new();
1676      # Get the DBKernel object.      # Get the DBKernel object.
# Line 1200  Line 1687 
1687      # FROM-relationships and entities.      # FROM-relationships and entities.
1688      my @fromPathList = ();      my @fromPathList = ();
1689      my @toPathList = ();      my @toPathList = ();
1690      # This final hash is used to remember what work still needs to be done. We push paths      # This final list is used to remember what work still needs to be done. We push paths
1691      # onto the list, then pop them off to extend the paths. We prime it with the starting      # onto the list, then pop them off to extend the paths. We prime it with the starting
1692      # point. Note that we will work hard to insure that the last item on a path in the      # point. Note that we will work hard to insure that the last item on a path in the
1693      # TODO list is always an entity.      # to-do list is always an entity.
1694      my @todoList = ([$entityName]);      my @todoList = ([$entityName]);
1695      while (@todoList) {      while (@todoList) {
1696          # Get the current path.          # Get the current path.
# Line 1211  Line 1698 
1698          # Copy it into a list.          # Copy it into a list.
1699          my @stackedPath = @{$current};          my @stackedPath = @{$current};
1700          # Pull off the last item on the path. It will always be an entity.          # Pull off the last item on the path. It will always be an entity.
1701          my $entityName = pop @stackedPath;          my $myEntityName = pop @stackedPath;
1702          # Add it to the alreadyFound list.          # Add it to the alreadyFound list.
1703          $alreadyFound{$entityName} = 1;          $alreadyFound{$myEntityName} = 1;
1704            # Figure out if we need to delete this entity.
1705            if ($myEntityName ne $entityName || ! $options{keepRoot}) {
1706          # Get the entity data.          # Get the entity data.
1707          my $entityData = $self->_GetStructure($entityName);              my $entityData = $self->_GetStructure($myEntityName);
1708          # The first task is to loop through the entity's relation. A DELETE command will              # Loop through the entity's relations. A DELETE command will be needed for each of them.
         # be needed for each of them.  
1709          my $relations = $entityData->{Relations};          my $relations = $entityData->{Relations};
1710          for my $relation (keys %{$relations}) {          for my $relation (keys %{$relations}) {
1711              my @augmentedList = (@stackedPath, $relation);              my @augmentedList = (@stackedPath, $relation);
1712              push @fromPathList, \@augmentedList;              push @fromPathList, \@augmentedList;
1713          }          }
1714            }
1715          # Now we need to look for relationships connected to this entity.          # Now we need to look for relationships connected to this entity.
1716          my $relationshipList = $self->{_metaData}->{Relationships};          my $relationshipList = $self->{_metaData}->{Relationships};
1717          for my $relationshipName (keys %{$relationshipList}) {          for my $relationshipName (keys %{$relationshipList}) {
1718              my $relationship = $relationshipList->{$relationshipName};              my $relationship = $relationshipList->{$relationshipName};
1719              # Check the FROM field. We're only interested if it's us.              # Check the FROM field. We're only interested if it's us.
1720              if ($relationship->{from} eq $entityName) {              if ($relationship->{from} eq $myEntityName) {
1721                  # Add the path to this relationship.                  # Add the path to this relationship.
1722                  my @augmentedList = (@stackedPath, $entityName, $relationshipName);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1723                  push @fromPathList, \@augmentedList;                  push @fromPathList, \@augmentedList;
1724                  # Check the arity. If it's MM we're done. If it's 1M                  # Check the arity. If it's MM we're done. If it's 1M
1725                  # and the target hasn't been seen yet, we want to                  # and the target hasn't been seen yet, we want to
# Line 1249  Line 1738 
1738              }              }
1739              # Now check the TO field. In this case only the relationship needs              # Now check the TO field. In this case only the relationship needs
1740              # deletion.              # deletion.
1741              if ($relationship->{to} eq $entityName) {              if ($relationship->{to} eq $myEntityName) {
1742                  my @augmentedList = (@stackedPath, $entityName, $relationshipName);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1743                  push @toPathList, \@augmentedList;                  push @toPathList, \@augmentedList;
1744              }              }
1745          }          }
1746      }      }
1747      # Create the first qualifier for the WHERE clause. This selects the      # Create the first qualifier for the WHERE clause. This selects the
1748      # keys of the primary entity records to be deleted. When we're deleting      # keys of the primary entity records to be deleted. When we're deleting
1749      # from a dependent table, we construct a join page from the first qualifier      # from a dependent table, we construct a join path from the first qualifier
1750      # to the table containing the dependent records to delete.      # to the table containing the dependent records to delete.
1751      my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");      my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
1752      # We need to make two passes. The first is through the to-list, and      # We need to make two passes. The first is through the to-list, and
# Line 1296  Line 1785 
1785                  }                  }
1786              }              }
1787              # Now we have our desired DELETE statement.              # Now we have our desired DELETE statement.
1788              if ($testFlag) {              if ($options{testMode}) {
1789                  # Here the user wants to trace without executing.                  # Here the user wants to trace without executing.
1790                  Trace($stmt) if T(0);                  Trace($stmt) if T(0);
1791              } else {              } else {
1792                  # Here we can delete. Note that the SQL method dies with a confessing                  # Here we can delete. Note that the SQL method dies with a confession
1793                  # if an error occurs, so we just go ahead and do it.                  # if an error occurs, so we just go ahead and do it.
1794                  Trace("Executing delete from $target using '$objectID'.") if T(3);                  Trace("Executing delete from $target using '$objectID'.") if T(3);
1795                  my $rv = $db->SQL($stmt, 0, $objectID);                  my $rv = $db->SQL($stmt, 0, $objectID);
# Line 1315  Line 1804 
1804      return $retVal;      return $retVal;
1805  }  }
1806    
1807  =head3 GetList  =head3 Disconnect
   
 C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>  
1808    
1809  Return a list of object descriptors for the specified objects as determined by the  C<< $erdb->Disconnect($relationshipName, $originEntityName, $originEntityID); >>
 specified filter clause.  
1810    
1811  This method is essentially the same as L</Get> except it returns a list of objects rather  Disconnect an entity instance from all the objects to which it is related. This
1812  than a query object that can be used to get the results one record at a time.  will delete each relationship instance that connects to the specified entity.
1813    
1814  =over 4  =over 4
1815    
1816  =item objectNames  =item relationshipName
1817    
1818  List containing the names of the entity and relationship objects to be retrieved.  Name of the relationship whose instances are to be deleted.
1819    
1820  =item filterClause  =item originEntityName
1821    
1822  WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  Name of the entity that is to be disconnected.
 be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be  
 specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified  
 in the filter clause should be added to the parameter list as additional parameters. The  
 fields in a filter clause can come from primary entity relations, relationship relations,  
 or secondary entity relations; however, all of the entities and relationships involved must  
 be included in the list of object names.  
1823    
1824  The filter clause can also specify a sort order. To do this, simply follow the filter string  =item originEntityID
 with an ORDER BY clause. For example, the following filter string gets all genomes for a  
 particular genus and sorts them by species name.  
1825    
1826  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>  ID of the entity that is to be disconnected.
1827    
1828  The rules for field references in a sort order are the same as those for field references in the  =back
1829  filter clause in general; however, odd things may happen if a sort field is from a secondary  
1830  relation.  =cut
1831    
1832    sub Disconnect {
1833        # Get the parameters.
1834        my ($self, $relationshipName, $originEntityName, $originEntityID) = @_;
1835        # Get the relationship descriptor.
1836        my $structure = $self->_GetStructure($relationshipName);
1837        # Insure we have a relationship.
1838        if (! exists $structure->{from}) {
1839            Confess("$relationshipName is not a relationship in the database.");
1840        } else {
1841            # Get the database handle.
1842            my $dbh = $self->{_dbh};
1843            # We'll set this value to 1 if we find our entity.
1844            my $found = 0;
1845            # Loop through the ends of the relationship.
1846            for my $dir ('from', 'to') {
1847                if ($structure->{$dir} eq $originEntityName) {
1848                    # Delete all relationship instances on this side of the entity instance.
1849                    Trace("Disconnecting in $dir direction with ID \"$originEntityID\".");
1850                    $dbh->SQL("DELETE FROM $relationshipName WHERE ${dir}_link = ?", 0, $originEntityID);
1851                    $found = 1;
1852                }
1853            }
1854            # Insure we found the entity on at least one end.
1855            if (! $found) {
1856                Confess("Entity \"$originEntityName\" does not use $relationshipName.");
1857            }
1858        }
1859    }
1860    
1861    =head3 DeleteRow
1862    
1863    C<< $erdb->DeleteRow($relationshipName, $fromLink, $toLink, \%values); >>
1864    
1865    Delete a row from a relationship. In most cases, only the from-link and to-link are
1866    needed; however, for relationships with intersection data values can be specified
1867    for the other fields using a hash.
1868    
1869    =over 4
1870    
1871    =item relationshipName
1872    
1873    Name of the relationship from which the row is to be deleted.
1874    
1875    =item fromLink
1876    
1877    ID of the entity instance in the From direction.
1878    
1879    =item toLink
1880    
1881    ID of the entity instance in the To direction.
1882    
1883    =item values
1884    
1885    Reference to a hash of other values to be used for filtering the delete.
1886    
1887    =back
1888    
1889    =cut
1890    
1891    sub DeleteRow {
1892        # Get the parameters.
1893        my ($self, $relationshipName, $fromLink, $toLink, $values) = @_;
1894        # Create a hash of all the filter information.
1895        my %filter = ('from-link' => $fromLink, 'to-link' => $toLink);
1896        if (defined $values) {
1897            for my $key (keys %{$values}) {
1898                $filter{$key} = $values->{$key};
1899            }
1900        }
1901        # Build an SQL statement out of the hash.
1902        my @filters = ();
1903        my @parms = ();
1904        for my $key (keys %filter) {
1905            push @filters, _FixName($key) . " = ?";
1906            push @parms, $filter{$key};
1907        }
1908        Trace("Parms for delete row are " . join(", ", map { "\"$_\"" } @parms) . ".") if T(SQL => 4);
1909        my $command = "DELETE FROM $relationshipName WHERE " .
1910                      join(" AND ", @filters);
1911        # Execute it.
1912        my $dbh = $self->{_dbh};
1913        $dbh->SQL($command, undef, @parms);
1914    }
1915    
1916    =head3 SortNeeded
1917    
1918    C<< my $parms = $erdb->SortNeeded($relationName); >>
1919    
1920    Return the pipe command for the sort that should be applied to the specified
1921    relation when creating the load file.
1922    
1923    For example, if the load file should be sorted ascending by the first
1924    field, this method would return
1925    
1926        sort -k1 -t"\t"
1927    
1928    If the first field is numeric, the method would return
1929    
1930        sort -k1n -t"\t"
1931    
1932    Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate
1933    keys using a sort.
1934    
1935    =over 4
1936    
1937    =item relationName
1938    
1939    Name of the relation to be examined.
1940    
1941    =item
1942    
1943    Returns the sort command to use for sorting the relation, suitable for piping.
1944    
1945    =back
1946    
1947    =cut
1948    #: Return Type $;
1949    sub SortNeeded {
1950        # Get the parameters.
1951        my ($self, $relationName) = @_;
1952        # Declare a descriptor to hold the names of the key fields.
1953        my @keyNames = ();
1954        # Get the relation structure.
1955        my $relationData = $self->_FindRelation($relationName);
1956        # Find out if the relation is a primary entity relation,
1957        # a relationship relation, or a secondary entity relation.
1958        my $entityTable = $self->{_metaData}->{Entities};
1959        my $relationshipTable = $self->{_metaData}->{Relationships};
1960        if (exists $entityTable->{$relationName}) {
1961            # Here we have a primary entity relation.
1962            push @keyNames, "id";
1963        } elsif (exists $relationshipTable->{$relationName}) {
1964            # Here we have a relationship. We sort using the FROM index.
1965            my $relationshipData = $relationshipTable->{$relationName};
1966            my $index = $relationData->{Indexes}->{idxFrom};
1967            push @keyNames, @{$index->{IndexFields}};
1968        } else {
1969            # Here we have a secondary entity relation, so we have a sort on the ID field.
1970            push @keyNames, "id";
1971        }
1972        # Now we parse the key names into sort parameters. First, we prime the return
1973        # string.
1974        my $retVal = "sort -t\"\t\" ";
1975        # Get the relation's field list.
1976        my @fields = @{$relationData->{Fields}};
1977        # Loop through the keys.
1978        for my $keyData (@keyNames) {
1979            # Get the key and the ordering.
1980            my ($keyName, $ordering);
1981            if ($keyData =~ /^([^ ]+) DESC/) {
1982                ($keyName, $ordering) = ($1, "descending");
1983            } else {
1984                ($keyName, $ordering) = ($keyData, "ascending");
1985            }
1986            # Find the key's position and type.
1987            my $fieldSpec;
1988            for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {
1989                my $thisField = $fields[$i];
1990                if ($thisField->{name} eq $keyName) {
1991                    # Get the sort modifier for this field type. The modifier
1992                    # decides whether we're using a character, numeric, or
1993                    # floating-point sort.
1994                    my $modifier = $TypeTable{$thisField->{type}}->{sort};
1995                    # If the index is descending for this field, denote we want
1996                    # to reverse the sort order on this field.
1997                    if ($ordering eq 'descending') {
1998                        $modifier .= "r";
1999                    }
2000                    # Store the position and modifier into the field spec, which
2001                    # will stop the inner loop. Note that the field number is
2002                    # 1-based in the sort command, so we have to increment the
2003                    # index.
2004                    $fieldSpec = ($i + 1) . $modifier;
2005                }
2006            }
2007            # Add this field to the sort command.
2008            $retVal .= " -k$fieldSpec";
2009        }
2010        # Return the result.
2011        return $retVal;
2012    }
2013    
2014    =head3 GetList
2015    
2016    C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>
2017    
2018    Return a list of object descriptors for the specified objects as determined by the
2019    specified filter clause.
2020    
2021    This method is essentially the same as L</Get> except it returns a list of objects rather
2022    than a query object that can be used to get the results one record at a time.
2023    
2024    =over 4
2025    
2026    =item objectNames
2027    
2028    List containing the names of the entity and relationship objects to be retrieved.
2029    
2030    =item filterClause
2031    
2032    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
2033    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
2034    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
2035    in the filter clause should be added to the parameter list as additional parameters. The
2036    fields in a filter clause can come from primary entity relations, relationship relations,
2037    or secondary entity relations; however, all of the entities and relationships involved must
2038    be included in the list of object names.
2039    
2040    The filter clause can also specify a sort order. To do this, simply follow the filter string
2041    with an ORDER BY clause. For example, the following filter string gets all genomes for a
2042    particular genus and sorts them by species name.
2043    
2044    C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
2045    
2046    The rules for field references in a sort order are the same as those for field references in the
2047    filter clause in general; however, odd things may happen if a sort field is from a secondary
2048    relation.
2049    
2050  =item params  =item params
2051    
# Line 1357  Line 2053 
2053    
2054  =item RETURN  =item RETURN
2055    
2056  Returns a list of B<DBObject>s that satisfy the query conditions.  Returns a list of B<ERDBObject>s that satisfy the query conditions.
2057    
2058  =back  =back
2059    
# Line 1431  Line 2127 
2127  sub GetCount {  sub GetCount {
2128      # Get the parameters.      # Get the parameters.
2129      my ($self, $objectNames, $filter, $params) = @_;      my ($self, $objectNames, $filter, $params) = @_;
2130        # Insure the params argument is an array reference if the caller left it off.
2131        if (! defined($params)) {
2132            $params = [];
2133        }
2134      # Declare the return variable.      # Declare the return variable.
2135      my $retVal;      my $retVal;
2136      # Find out if we're counting an entity or a relationship.      # Find out if we're counting an entity or a relationship.
# Line 1544  Line 2244 
2244      }      }
2245  }  }
2246    
2247    =head3 InsertValue
2248    
2249    C<< $erdb->InsertValue($entityID, $fieldName, $value); >>
2250    
2251    This method will insert a new value into the database. The value must be one
2252    associated with a secondary relation, since primary values cannot be inserted:
2253    they occur exactly once. Secondary values, on the other hand, can be missing
2254    or multiply-occurring.
2255    
2256    =over 4
2257    
2258    =item entityID
2259    
2260    ID of the object that is to receive the new value.
2261    
2262    =item fieldName
2263    
2264    Field name for the new value-- this includes the entity name, since
2265    field names are of the format I<objectName>C<(>I<fieldName>C<)>.
2266    
2267    =item value
2268    
2269    New value to be put in the field.
2270    
2271    =back
2272    
2273    =cut
2274    
2275    sub InsertValue {
2276        # Get the parameters.
2277        my ($self, $entityID, $fieldName, $value) = @_;
2278        # Parse the entity name and the real field name.
2279        if ($fieldName =~ /^([^(]+)\(([^)]+)\)/) {
2280            my $entityName = $1;
2281            my $fieldTitle = $2;
2282            # Get its descriptor.
2283            if (!$self->IsEntity($entityName)) {
2284                Confess("$entityName is not a valid entity.");
2285            } else {
2286                my $entityData = $self->{_metaData}->{Entities}->{$entityName};
2287                # Find the relation containing this field.
2288                my $fieldHash = $entityData->{Fields};
2289                if (! exists $fieldHash->{$fieldTitle}) {
2290                    Confess("$fieldTitle not found in $entityName.");
2291                } else {
2292                    my $relation = $fieldHash->{$fieldTitle}->{relation};
2293                    if ($relation eq $entityName) {
2294                        Confess("Cannot do InsertValue on primary field $fieldTitle of $entityName.");
2295                    } else {
2296                        # Now we can create an INSERT statement.
2297                        my $dbh = $self->{_dbh};
2298                        my $fixedName = _FixName($fieldTitle);
2299                        my $statement = "INSERT INTO $relation (id, $fixedName) VALUES(?, ?)";
2300                        # Execute the command.
2301                        $dbh->SQL($statement, 0, $entityID, $value);
2302                    }
2303                }
2304            }
2305        } else {
2306            Confess("$fieldName is not a valid field name.");
2307        }
2308    }
2309    
2310  =head3 InsertObject  =head3 InsertObject
2311    
2312  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>  C<< $erdb->InsertObject($objectType, \%fieldHash); >>
2313    
2314  Insert an object into the database. The object is defined by a type name and then a hash  Insert an object into the database. The object is defined by a type name and then a hash
2315  of field names to values. Field values in the primary relation are represented by scalars.  of field names to values. Field values in the primary relation are represented by scalars.
# Line 1560  Line 2323 
2323  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
2324  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>.
2325    
2326  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'}); >>
2327    
2328  =over 4  =over 4
2329    
# Line 1572  Line 2335 
2335    
2336  Hash of field names to values.  Hash of field names to values.
2337    
 =item RETURN  
   
 Returns 1 if successful, 0 if an error occurred.  
   
2338  =back  =back
2339    
2340  =cut  =cut
# Line 1674  Line 2433 
2433                  $retVal = $sth->execute(@parameterList);                  $retVal = $sth->execute(@parameterList);
2434                  if (!$retVal) {                  if (!$retVal) {
2435                      my $errorString = $sth->errstr();                      my $errorString = $sth->errstr();
2436                      Trace("Insert error: $errorString.") if T(0);                      Confess("Error inserting into $relationName: $errorString");
2437                    } else {
2438                        Trace("Insert successful using $parameterList[0].") if T(3);
2439                  }                  }
2440              }              }
2441          }          }
2442      }      }
2443      # Return the success indicator.      # Return a 1 for backward compatability.
2444      return $retVal;      return 1;
2445    }
2446    
2447    =head3 UpdateEntity
2448    
2449    C<< $erdb->UpdateEntity($entityName, $id, \%fields); >>
2450    
2451    Update the values of an entity. This is an unprotected update, so it should only be
2452    done if the database resides on a database server.
2453    
2454    =over 4
2455    
2456    =item entityName
2457    
2458    Name of the entity to update. (This is the entity type.)
2459    
2460    =item id
2461    
2462    ID of the entity to update. If no entity exists with this ID, an error will be thrown.
2463    
2464    =item fields
2465    
2466    Reference to a hash mapping field names to their new values. All of the fields named
2467    must be in the entity's primary relation, and they cannot any of them be the ID field.
2468    
2469    =back
2470    
2471    =cut
2472    
2473    sub UpdateEntity {
2474        # Get the parameters.
2475        my ($self, $entityName, $id, $fields) = @_;
2476        # Get a list of the field names being updated.
2477        my @fieldList = keys %{$fields};
2478        # Verify that the fields exist.
2479        my $checker = $self->GetFieldTable($entityName);
2480        for my $field (@fieldList) {
2481            if ($field eq 'id') {
2482                Confess("Cannot update the ID field for entity $entityName.");
2483            } elsif ($checker->{$field}->{relation} ne $entityName) {
2484                Confess("Cannot find $field in primary relation of $entityName.");
2485            }
2486        }
2487        # Build the SQL statement.
2488        my @sets = ();
2489        my @valueList = ();
2490        for my $field (@fieldList) {
2491            push @sets, _FixName($field) . " = ?";
2492            push @valueList, $fields->{$field};
2493        }
2494        my $command = "UPDATE $entityName SET " . join(", ", @sets) . " WHERE id = ?";
2495        # Add the ID to the list of binding values.
2496        push @valueList, $id;
2497        # Call SQL to do the work.
2498        my $rows = $self->{_dbh}->SQL($command, 0, @valueList);
2499        # Check for errors.
2500        if ($rows == 0) {
2501            Confess("Entity $id of type $entityName not found.");
2502        }
2503  }  }
2504    
2505  =head3 LoadTable  =head3 LoadTable
2506    
2507  C<< my %results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>  C<< my $results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>
2508    
2509  Load data from a tab-delimited file into a specified table, optionally re-creating the table  Load data from a tab-delimited file into a specified table, optionally re-creating the table
2510  first.  first.
# Line 1752  Line 2571 
2571      };      };
2572      if (!defined $rv) {      if (!defined $rv) {
2573          $retVal->AddMessage($@) if ($@);          $retVal->AddMessage($@) if ($@);
2574          $retVal->AddMessage("Table load failed for $relationName using $fileName.");          $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2575          Trace("Table load failed for $relationName.") if T(1);          Trace("Table load failed for $relationName.") if T(1);
2576      } else {      } else {
2577          # Here we successfully loaded the table.          # Here we successfully loaded the table.
# Line 1760  Line 2579 
2579          my $size = -s $fileName;          my $size = -s $fileName;
2580          Trace("$size bytes loaded into $relationName.") if T(2);          Trace("$size bytes loaded into $relationName.") if T(2);
2581          # If we're rebuilding, we need to create the table indexes.          # If we're rebuilding, we need to create the table indexes.
2582          if ($truncateFlag && ! $dbh->{_preIndex}) {          if ($truncateFlag) {
2583                # Indexes are created here for PostGres. For PostGres, indexes are
2584                # best built at the end. For MySQL, the reverse is true.
2585                if (! $dbh->{_preIndex}) {
2586              eval {              eval {
2587                  $self->CreateIndex($relationName);                  $self->CreateIndex($relationName);
2588              };              };
# Line 1768  Line 2590 
2590                  $retVal->AddMessage($@);                  $retVal->AddMessage($@);
2591              }              }
2592          }          }
2593                # The full-text index (if any) is always built last, even for MySQL.
2594                # First we need to see if this table has a full-text index. Only
2595                # primary relations are allowed that privilege.
2596                Trace("Checking for full-text index on $relationName.") if T(2);
2597                if ($self->_IsPrimary($relationName)) {
2598                    $self->CreateSearchIndex($relationName);
2599                }
2600            }
2601      }      }
2602      # Analyze the table to improve performance.      # Analyze the table to improve performance.
2603        Trace("Analyzing and compacting $relationName.") if T(3);
2604      $dbh->vacuum_it($relationName);      $dbh->vacuum_it($relationName);
2605        Trace("$relationName load completed.") if T(3);
2606      # Return the statistics.      # Return the statistics.
2607      return $retVal;      return $retVal;
2608  }  }
2609    
2610  =head3 GenerateEntity  =head3 CreateSearchIndex
2611    
2612  C<< my $fieldHash = $erdb->GenerateEntity($id, $type, \%values); >>  C<< $erdb->CreateSearchIndex($objectName); >>
2613    
2614  Generate the data for a new entity instance. This method creates a field hash suitable for  Check for a full-text search index on the specified entity or relationship object, and
2615  passing as a parameter to L</InsertObject>. The ID is specified by the callr, but the rest  if one is required, rebuild it.
 of the fields are generated using information in the database schema.  
   
 Each data type has a default algorithm for generating random test data. This can be overridden  
 by including a B<DataGen> element in the field. If this happens, the content of the element is  
 executed as a PERL program in the context of this module. The element may make use of a C<$this>  
 variable which contains the field hash as it has been built up to the current point. If any  
 fields are dependent on other fields, the C<pass> attribute can be used to control the order  
 in which the fields are generated. A field with a high data pass number will be generated after  
 a field with a lower one. If any external values are needed, they should be passed in via the  
 optional third parameter, which will be available to the data generation script under the name  
 C<$value>. Several useful utility methods are provided for generating random values, including  
 L</IntGen>, L</StringGen>, L</FloatGen>, and L</DateGen>. Note that dates are stored and generated  
 in the form of a timestamp number rather than a string.  
2616    
2617  =over 4  =over 4
2618    
2619  =item id  =item objectName
2620    
2621  ID to assign to the new entity.  Name of the entity or relationship to be indexed.
2622    
2623  =item type  =back
2624    
2625  Type name for the new entity.  =cut
2626    
2627  =item values  sub CreateSearchIndex {
2628        # Get the parameters.
2629        my ($self, $objectName) = @_;
2630        # Get the relation's entity/relationship structure.
2631        my $structure = $self->_GetStructure($objectName);
2632        # Get the database handle.
2633        my $dbh = $self->{_dbh};
2634        Trace("Checking for search fields in $objectName.") if T(3);
2635        # Check for a searchable fields list.
2636        if (exists $structure->{searchFields}) {
2637            # Here we know that we need to create a full-text search index.
2638            # Get an SQL-formatted field name list.
2639            my $fields = join(", ", _FixNames(@{$structure->{searchFields}}));
2640            # Create the index. If it already exists, it will be dropped.
2641            $dbh->create_index(tbl => $objectName, idx => "search_idx",
2642                               flds => $fields, kind => 'fulltext');
2643            Trace("Index created for $fields in $objectName.") if T(2);
2644        }
2645    }
2646    
2647    =head3 DropRelation
2648    
2649    C<< $erdb->DropRelation($relationName); >>
2650    
2651    Physically drop a relation from the database.
2652    
2653    =over 4
2654    
2655    =item relationName
2656    
2657  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
2658    no effect.
2659    
2660  =back  =back
2661    
2662  =cut  =cut
2663    
2664  sub GenerateEntity {  sub DropRelation {
2665      # Get the parameters.      # Get the parameters.
2666      my ($self, $id, $type, $values) = @_;      my ($self, $relationName) = @_;
2667      # Create the return hash.      # Get the database handle.
2668      my $this = { id => $id };      my $dbh = $self->{_dbh};
2669      # Get the metadata structure.      # Drop the relation. The method used here has no effect if the relation
2670      my $metadata = $self->{_metaData};      # does not exist.
2671      # Get this entity's list of fields.      Trace("Invoking DB Kernel to drop $relationName.") if T(3);
2672      if (!exists $metadata->{Entities}->{$type}) {      $dbh->drop_table(tbl => $relationName);
2673          Confess("Unrecognized entity type $type in GenerateEntity.");  }
2674      } else {  
2675          my $entity = $metadata->{Entities}->{$type};  =head3 MatchSqlPattern
2676          my $fields = $entity->{Fields};  
2677          # Generate data from the fields.  C<< my $matched = ERDB::MatchSqlPattern($value, $pattern); >>
2678          _GenerateFields($this, $fields, $type, $values);  
2679    Determine whether or not a specified value matches an SQL pattern. An SQL
2680    pattern has two wild card characters: C<%> that matches multiple characters,
2681    and C<_> that matches a single character. These can be escaped using a
2682    backslash (C<\>). We pull this off by converting the SQL pattern to a
2683    PERL regular expression. As per SQL rules, the match is case-insensitive.
2684    
2685    =over 4
2686    
2687    =item value
2688    
2689    Value to be matched against the pattern. Note that an undefined or empty
2690    value will not match anything.
2691    
2692    =item pattern
2693    
2694    SQL pattern against which to match the value. An undefined or empty pattern will
2695    match everything.
2696    
2697    =item RETURN
2698    
2699    Returns TRUE if the value and pattern match, else FALSE.
2700    
2701    =back
2702    
2703    =cut
2704    
2705    sub MatchSqlPattern {
2706        # Get the parameters.
2707        my ($value, $pattern) = @_;
2708        # Declare the return variable.
2709        my $retVal;
2710        # Insure we have a pattern.
2711        if (! defined($pattern) || $pattern eq "") {
2712            $retVal = 1;
2713        } else {
2714            # Break the pattern into pieces around the wildcard characters. Because we
2715            # use parentheses in the split function's delimiter expression, we'll get
2716            # list elements for the delimiters as well as the rest of the string.
2717            my @pieces = split /([_%]|\\[_%])/, $pattern;
2718            # Check some fast special cases.
2719            if ($pattern eq '%') {
2720                # A null pattern matches everything.
2721                $retVal = 1;
2722            } elsif (@pieces == 1) {
2723                # No wildcards, so we have a literal comparison. Note we're case-insensitive.
2724                $retVal = (lc($value) eq lc($pattern));
2725            } elsif (@pieces == 2 && $pieces[1] eq '%') {
2726                # A wildcard at the end, so we have a substring match. This is also case-insensitive.
2727                $retVal = (lc(substr($value, 0, length($pieces[0]))) eq lc($pieces[0]));
2728            } else {
2729                # Okay, we have to do it the hard way. Convert each piece to a PERL pattern.
2730                my $realPattern = "";
2731                for my $piece (@pieces) {
2732                    # Determine the type of piece.
2733                    if ($piece eq "") {
2734                        # Empty pieces are ignored.
2735                    } elsif ($piece eq "%") {
2736                        # Here we have a multi-character wildcard. Note that it can match
2737                        # zero or more characters.
2738                        $realPattern .= ".*"
2739                    } elsif ($piece eq "_") {
2740                        # Here we have a single-character wildcard.
2741                        $realPattern .= ".";
2742                    } elsif ($piece eq "\\%" || $piece eq "\\_") {
2743                        # This is an escape sequence (which is a rare thing, actually).
2744                        $realPattern .= substr($piece, 1, 1);
2745                    } else {
2746                        # Here we have raw text.
2747                        $realPattern .= quotemeta($piece);
2748                    }
2749                }
2750                # Do the match.
2751                $retVal = ($value =~ /^$realPattern$/i ? 1 : 0);
2752      }      }
2753      # Return the hash created.      }
2754      return $this;      # Return the result.
2755        return $retVal;
2756  }  }
2757    
2758  =head3 GetEntity  =head3 GetEntity
# Line 1851  Line 2773 
2773    
2774  =item RETURN  =item RETURN
2775    
2776  Returns a B<DBObject> representing the desired entity instance, or an undefined value if no  Returns a B<ERDBObject> representing the desired entity instance, or an undefined value if no
2777  instance is found with the specified key.  instance is found with the specified key.
2778    
2779  =back  =back
# Line 1869  Line 2791 
2791      return $retVal;      return $retVal;
2792  }  }
2793    
2794    =head3 GetChoices
2795    
2796    C<< my @values = $erdb->GetChoices($entityName, $fieldName); >>
2797    
2798    Return a list of all the values for the specified field that are represented in the
2799    specified entity.
2800    
2801    Note that if the field is not indexed, then this will be a very slow operation.
2802    
2803    =over 4
2804    
2805    =item entityName
2806    
2807    Name of an entity in the database.
2808    
2809    =item fieldName
2810    
2811    Name of a field belonging to the entity. This is a raw field name without
2812    the standard parenthesized notation used in most calls.
2813    
2814    =item RETURN
2815    
2816    Returns a list of the distinct values for the specified field in the database.
2817    
2818    =back
2819    
2820    =cut
2821    
2822    sub GetChoices {
2823        # Get the parameters.
2824        my ($self, $entityName, $fieldName) = @_;
2825        # Declare the return variable.
2826        my @retVal;
2827        # Get the entity data structure.
2828        my $entityData = $self->_GetStructure($entityName);
2829        # Get the field.
2830        my $fieldHash = $entityData->{Fields};
2831        if (! exists $fieldHash->{$fieldName}) {
2832            Confess("$fieldName not found in $entityName.");
2833        } else {
2834            # Get the name of the relation containing the field.
2835            my $relation = $fieldHash->{$fieldName}->{relation};
2836            # Fix up the field name.
2837            my $realName = _FixName($fieldName);
2838            # Get the database handle.
2839            my $dbh = $self->{_dbh};
2840            # Query the database.
2841            my $results = $dbh->SQL("SELECT DISTINCT $realName FROM $relation");
2842            # Clean the results. They are stored as a list of lists, and we just want the one list.
2843            @retVal = sort map { $_->[0] } @{$results};
2844        }
2845        # Return the result.
2846        return @retVal;
2847    }
2848    
2849  =head3 GetEntityValues  =head3 GetEntityValues
2850    
2851  C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>  C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>
2852    
2853  Return a list of values from a specified entity instance.  Return a list of values from a specified entity instance. If the entity instance
2854    does not exist, an empty list is returned.
2855    
2856  =over 4  =over 4
2857    
# Line 1930  Line 2908 
2908  spreadsheet cell, and each feature will be represented by a list containing the  spreadsheet cell, and each feature will be represented by a list containing the
2909  feature ID followed by all of its aliases.  feature ID followed by all of its aliases.
2910    
2911  C<< $query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>  C<< @query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>
2912    
2913  =over 4  =over 4
2914    
# Line 2001  Line 2979 
2979          push @retVal, \@rowData;          push @retVal, \@rowData;
2980          $fetched++;          $fetched++;
2981      }      }
2982        Trace("$fetched rows returned in GetAll.") if T(SQL => 4);
2983      # Return the resulting list.      # Return the resulting list.
2984      return @retVal;      return @retVal;
2985  }  }
2986    
2987    =head3 Exists
2988    
2989    C<< my $found = $sprout->Exists($entityName, $entityID); >>
2990    
2991    Return TRUE if an entity exists, else FALSE.
2992    
2993    =over 4
2994    
2995    =item entityName
2996    
2997    Name of the entity type (e.g. C<Feature>) relevant to the existence check.
2998    
2999    =item entityID
3000    
3001    ID of the entity instance whose existence is to be checked.
3002    
3003    =item RETURN
3004    
3005    Returns TRUE if the entity instance exists, else FALSE.
3006    
3007    =back
3008    
3009    =cut
3010    #: Return Type $;
3011    sub Exists {
3012        # Get the parameters.
3013        my ($self, $entityName, $entityID) = @_;
3014        # Check for the entity instance.
3015        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
3016        my $testInstance = $self->GetEntity($entityName, $entityID);
3017        # Return an existence indicator.
3018        my $retVal = ($testInstance ? 1 : 0);
3019        return $retVal;
3020    }
3021    
3022  =head3 EstimateRowSize  =head3 EstimateRowSize
3023    
3024  C<< my $rowSize = $erdb->EstimateRowSize($relName); >>  C<< my $rowSize = $erdb->EstimateRowSize($relName); >>
# Line 2043  Line 3057 
3057      return $retVal;      return $retVal;
3058  }  }
3059    
3060  =head3 GetFieldTable  =head3 GetFieldTable
3061    
3062    C<< my $fieldHash = $self->GetFieldTable($objectnName); >>
3063    
3064    Get the field structure for a specified entity or relationship.
3065    
3066    =over 4
3067    
3068    =item objectName
3069    
3070    Name of the desired entity or relationship.
3071    
3072    =item RETURN
3073    
3074    The table containing the field descriptors for the specified object.
3075    
3076    =back
3077    
3078    =cut
3079    
3080    sub GetFieldTable {
3081        # Get the parameters.
3082        my ($self, $objectName) = @_;
3083        # Get the descriptor from the metadata.
3084        my $objectData = $self->_GetStructure($objectName);
3085        # Return the object's field table.
3086        return $objectData->{Fields};
3087    }
3088    
3089    =head3 SplitKeywords
3090    
3091    C<< my @keywords = ERDB::SplitKeywords($keywordString); >>
3092    
3093    This method returns a list of the positive keywords in the specified
3094    keyword string. All of the operators will have been stripped off,
3095    and if the keyword is preceded by a minus operator (C<->), it will
3096    not be in the list returned. The idea here is to get a list of the
3097    keywords the user wants to see. The list will be processed to remove
3098    duplicates.
3099    
3100    It is possible to create a string that confuses this method. For example
3101    
3102        frog toad -frog
3103    
3104    would return both C<frog> and C<toad>. If this is a problem we can deal
3105    with it later.
3106    
3107    =over 4
3108    
3109    =item keywordString
3110    
3111    The keyword string to be parsed.
3112    
3113    =item RETURN
3114    
3115    Returns a list of the words in the keyword string the user wants to
3116    see.
3117    
3118    =back
3119    
3120    =cut
3121    
3122    sub SplitKeywords {
3123        # Get the parameters.
3124        my ($keywordString) = @_;
3125        # Make a safety copy of the string. (This helps during debugging.)
3126        my $workString = $keywordString;
3127        # Convert operators we don't care about to spaces.
3128        $workString =~ tr/+"()<>/ /;
3129        # Split the rest of the string along space boundaries. Note that we
3130        # eliminate any words that are zero length or begin with a minus sign.
3131        my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
3132        # Use a hash to remove duplicates.
3133        my %words = map { $_ => 1 } @wordList;
3134        # Return the result.
3135        return sort keys %words;
3136    }
3137    
3138    =head3 ValidateFieldName
3139    
3140    C<< my $okFlag = ERDB::ValidateFieldName($fieldName); >>
3141    
3142    Return TRUE if the specified field name is valid, else FALSE. Valid field names must
3143    be hyphenated words subject to certain restrictions.
3144    
3145    =over 4
3146    
3147    =item fieldName
3148    
3149    Field name to be validated.
3150    
3151    =item RETURN
3152    
3153    Returns TRUE if the field name is valid, else FALSE.
3154    
3155    =back
3156    
3157    =cut
3158    
3159    sub ValidateFieldName {
3160        # Get the parameters.
3161        my ($fieldName) = @_;
3162        # Declare the return variable. The field name is valid until we hear
3163        # differently.
3164        my $retVal = 1;
3165        # Compute the maximum name length.
3166        my $maxLen = $TypeTable{'name-string'}->{maxLen};
3167        # Look for bad stuff in the name.
3168        if ($fieldName =~ /--/) {
3169            # Here we have a doubled minus sign.
3170            Trace("Field name $fieldName has a doubled hyphen.") if T(1);
3171            $retVal = 0;
3172        } elsif ($fieldName !~ /^[A-Za-z]/) {
3173            # Here the field name is missing the initial letter.
3174            Trace("Field name $fieldName does not begin with a letter.") if T(1);
3175            $retVal = 0;
3176        } elsif (length($fieldName) > $maxLen) {
3177            # Here the field name is too long.
3178            Trace("Maximum field name length is $maxLen. Field name must be truncated to " . substr($fieldName,0, $maxLen) . ".");
3179        } else {
3180            # Strip out the minus signs. Everything remaining must be a letter,
3181            # underscore, or digit.
3182            my $strippedName = $fieldName;
3183            $strippedName =~ s/-//g;
3184            if ($strippedName !~ /^(\w|\d)+$/) {
3185                Trace("Field name $fieldName contains illegal characters.") if T(1);
3186                $retVal = 0;
3187            }
3188        }
3189        # Return the result.
3190        return $retVal;
3191    }
3192    
3193    =head3 ReadMetaXML
3194    
3195    C<< my $rawMetaData = ERDB::ReadDBD($fileName); >>
3196    
3197    This method reads a raw database definition XML file and returns it.
3198    Normally, the metadata used by the ERDB system has been processed and
3199    modified to make it easier to load and retrieve the data; however,
3200    this method can be used to get the data in its raw form.
3201    
3202    =over 4
3203    
3204    =item fileName
3205    
3206    Name of the XML file to read.
3207    
3208    =item RETURN
3209    
3210    Returns a hash reference containing the raw XML data from the specified file.
3211    
3212    =back
3213    
3214    =cut
3215    
3216    sub ReadMetaXML {
3217        # Get the parameters.
3218        my ($fileName) = @_;
3219        # Read the XML.
3220        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
3221        Trace("XML metadata loaded from file $fileName.") if T(1);
3222        # Return the result.
3223        return $retVal;
3224    }
3225    
3226    =head3 GetEntityFieldHash
3227    
3228    C<< my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName); >>
3229    
3230    Get the field hash of the named entity in the specified raw XML structure.
3231    The field hash may not exist, in which case we need to create it.
3232    
3233    =over 4
3234    
3235    =item structure
3236    
3237    Raw XML structure defininng the database. This is not the run-time XML used by
3238    an ERDB object, since that has all sorts of optimizations built-in.
3239    
3240    =item entityName
3241    
3242    Name of the entity whose field structure is desired.
3243    
3244    =item RETURN
3245    
3246    Returns the field hash used to define the entity's fields.
3247    
3248    =back
3249    
3250    =cut
3251    
3252    sub GetEntityFieldHash {
3253        # Get the parameters.
3254        my ($structure, $entityName) = @_;
3255        # Get the entity structure.
3256        my $entityData = $structure->{Entities}->{$entityName};
3257        # Look for a field structure.
3258        my $retVal = $entityData->{Fields};
3259        # If it doesn't exist, create it.
3260        if (! defined($retVal)) {
3261            $entityData->{Fields} = {};
3262            $retVal = $entityData->{Fields};
3263        }
3264        # Return the result.
3265        return $retVal;
3266    }
3267    
3268    =head3 WriteMetaXML
3269    
3270    C<< ERDB::WriteMetaXML($structure, $fileName); >>
3271    
3272    Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
3273    used to update the database definition. It must be used with care, however, since it
3274    will only work on a raw structure, not on the processed structure created by an ERDB
3275    constructor.
3276    
3277    =over 4
3278    
3279    =item structure
3280    
3281    XML structure to be written to the file.
3282    
3283    =item fileName
3284    
3285    Name of the output file to which the updated XML should be stored.
3286    
3287    =back
3288    
3289    =cut
3290    
3291    sub WriteMetaXML {
3292        # Get the parameters.
3293        my ($structure, $fileName) = @_;
3294        # Compute the output.
3295        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
3296        # Write it to the file.
3297        my $xmlOut = Open(undef, ">$fileName");
3298        print $xmlOut $fileString;
3299    }
3300    
3301    
3302    =head3 HTMLNote
3303    
3304    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
3305    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
3306    Except for C<[p]>, all the codes are closed by slash-codes. So, for
3307    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
3308    
3309    C<< my $realHtml = ERDB::HTMLNote($dataString); >>
3310    
3311    =over 4
3312    
3313    =item dataString
3314    
3315    String to convert to HTML.
3316    
3317    =item RETURN
3318    
3319    An HTML string derived from the input string.
3320    
3321    =back
3322    
3323    =cut
3324    
3325    sub HTMLNote {
3326        # Get the parameter.
3327        my ($dataString) = @_;
3328        # HTML-escape the text.
3329        my $retVal = CGI::escapeHTML($dataString);
3330        # Substitute the bulletin board codes.
3331        $retVal =~ s!\[(/?[bi])\]!<$1>!g;
3332        $retVal =~ s!\[p\]!</p><p>!g;
3333        $retVal =~ s!\[link\s+([^\]]+)\]!<a href="$1">!g;
3334        $retVal =~ s!\[/link\]!</a>!g;
3335        # Return the result.
3336        return $retVal;
3337    }
3338    
3339    =head3 BeginTran
3340    
3341    C<< $erdb->BeginTran(); >>
3342    
3343    Start a database transaction.
3344    
3345  C<< my $fieldHash = $self->GetFieldTable($objectnName); >>  =cut
3346    
3347  Get the field structure for a specified entity or relationship.  sub BeginTran {
3348        my ($self) = @_;
3349        $self->{_dbh}->begin_tran();
3350    
3351  =over 4  }
3352    
3353  =item objectName  =head3 CommitTran
3354    
3355  Name of the desired entity or relationship.  C<< $erdb->CommitTran(); >>
3356    
3357  =item RETURN  Commit an active database transaction.
3358    
3359  The table containing the field descriptors for the specified object.  =cut
3360    
3361  =back  sub CommitTran {
3362        my ($self) = @_;
3363        $self->{_dbh}->commit_tran();
3364    }
3365    
3366    =head3 RollbackTran
3367    
3368    C<< $erdb->RollbackTran(); >>
3369    
3370    Roll back an active database transaction.
3371    
3372  =cut  =cut
3373    
3374  sub GetFieldTable {  sub RollbackTran {
3375      # Get the parameters.      my ($self) = @_;
3376      my ($self, $objectName) = @_;      $self->{_dbh}->roll_tran();
     # Get the descriptor from the metadata.  
     my $objectData = $self->_GetStructure($objectName);  
     # Return the object's field table.  
     return $objectData->{Fields};  
3377  }  }
3378    
3379    
3380    =head2 Data Mining Methods
3381    
3382  =head3 GetUsefulCrossValues  =head3 GetUsefulCrossValues
3383    
3384  C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>  C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>
# Line 2133  Line 3440 
3440      return @retVal;      return @retVal;
3441  }  }
3442    
3443    =head3 FindColumn
3444    
3445    C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>
3446    
3447    Return the location a desired column in a data mining header line. The data
3448    mining header line is a tab-separated list of column names. The column
3449    identifier is either the numerical index of a column or the actual column
3450    name.
3451    
3452    =over 4
3453    
3454    =item headerLine
3455    
3456    The header line from a data mining command, which consists of a tab-separated
3457    list of column names.
3458    
3459    =item columnIdentifier
3460    
3461    Either the ordinal number of the desired column (1-based), or the name of the
3462    desired column.
3463    
3464    =item RETURN
3465    
3466    Returns the array index (0-based) of the desired column.
3467    
3468    =back
3469    
3470    =cut
3471    
3472    sub FindColumn {
3473        # Get the parameters.
3474        my ($headerLine, $columnIdentifier) = @_;
3475        # Declare the return variable.
3476        my $retVal;
3477        # Split the header line into column names.
3478        my @headers = ParseColumns($headerLine);
3479        # Determine whether we have a number or a name.
3480        if ($columnIdentifier =~ /^\d+$/) {
3481            # Here we have a number. Subtract 1 and validate the result.
3482            $retVal = $columnIdentifier - 1;
3483            if ($retVal < 0 || $retVal > $#headers) {
3484                Confess("Invalid column identifer \"$columnIdentifier\": value out of range.");
3485            }
3486        } else {
3487            # Here we have a name. We need to find it in the list.
3488            for (my $i = 0; $i <= $#headers && ! defined($retVal); $i++) {
3489                if ($headers[$i] eq $columnIdentifier) {
3490                    $retVal = $i;
3491                }
3492            }
3493            if (! defined($retVal)) {
3494                Confess("Invalid column identifier \"$columnIdentifier\": value not found.");
3495            }
3496        }
3497        # Return the result.
3498        return $retVal;
3499    }
3500    
3501    =head3 ParseColumns
3502    
3503    C<< my @columns = ERDB::ParseColumns($line); >>
3504    
3505    Convert the specified data line to a list of columns.
3506    
3507    =over 4
3508    
3509    =item line
3510    
3511    A data mining input, consisting of a tab-separated list of columns terminated by a
3512    new-line.
3513    
3514    =item RETURN
3515    
3516    Returns a list consisting of the column values.
3517    
3518    =back
3519    
3520    =cut
3521    
3522    sub ParseColumns {
3523        # Get the parameters.
3524        my ($line) = @_;
3525        # Chop off the line-end.
3526        chomp $line;
3527        # Split it into a list.
3528        my @retVal = split(/\t/, $line);
3529        # Return the result.
3530        return @retVal;
3531    }
3532    
3533    =head2 Virtual Methods
3534    
3535    =head3 CleanKeywords
3536    
3537    C<< my $cleanedString = $erdb->CleanKeywords($searchExpression); >>
3538    
3539    Clean up a search expression or keyword list. This is a virtual method that may
3540    be overridden by the subclass. The base-class method removes extra spaces
3541    and converts everything to lower case.
3542    
3543    =over 4
3544    
3545    =item searchExpression
3546    
3547    Search expression or keyword list to clean. Note that a search expression may
3548    contain boolean operators which need to be preserved. This includes leading
3549    minus signs.
3550    
3551    =item RETURN
3552    
3553    Cleaned expression or keyword list.
3554    
3555    =back
3556    
3557    =cut
3558    
3559    sub CleanKeywords {
3560        # Get the parameters.
3561        my ($self, $searchExpression) = @_;
3562        # Lower-case the expression and copy it into the return variable. Note that we insure we
3563        # don't accidentally end up with an undefined value.
3564        my $retVal = lc($searchExpression || "");
3565        # Remove extra spaces.
3566        $retVal =~ s/\s+/ /g;
3567        $retVal =~ s/(^\s+)|(\s+$)//g;
3568        # Return the result.
3569        return $retVal;
3570    }
3571    
3572    =head3 GetSourceObject
3573    
3574    C<< my $source = $erdb->GetSourceObject($entityName); >>
3575    
3576    Return the object to be used in loading special attributes of the specified entity. The
3577    algorithm for loading special attributes is stored in the C<DataGen> elements of the
3578    XML
3579    
3580  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3581    
3582  =head3 SetupSQL  =head3 _RelationMap
3583    
3584    C<< my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef); >>
3585    
3586    Create the relation map for an SQL query. The relation map is used by B<ERDBObject>
3587    to determine how to interpret the results of the query.
3588    
3589    =over 4
3590    
3591    =item mappedNameHashRef
3592    
3593    Reference to a hash that maps modified object names to real object names.
3594    
3595    =item mappedNameListRef
3596    
3597    Reference to a list of modified object names in the order they appear in the
3598    SELECT list.
3599    
3600    =item RETURN
3601    
3602    Returns a list of 2-tuples. Each tuple consists of an object name as used in the
3603    query followed by the actual name of that object. This enables the B<ERDBObject> to
3604    determine the order of the tables in the query and which object name belongs to each
3605    mapped object name. Most of the time these two values are the same; however, if a
3606    relation occurs twice in the query, the relation name in the field list and WHERE
3607    clause will use a mapped name (generally the actual relation name with a numeric
3608    suffix) that does not match the actual relation name.
3609    
3610    =back
3611    
3612    =cut
3613    
3614    sub _RelationMap {
3615        # Get the parameters.
3616        my ($mappedNameHashRef, $mappedNameListRef) = @_;
3617        # Declare the return variable.
3618        my @retVal = ();
3619        # Build the map.
3620        for my $mappedName (@{$mappedNameListRef}) {
3621            push @retVal, [$mappedName, $mappedNameHashRef->{$mappedName}];
3622        }
3623        # Return it.
3624        return @retVal;
3625    }
3626    
3627    
3628    =head3 _SetupSQL
3629    
3630  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
3631  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 2155  Line 3645 
3645  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
3646  optionally the C<ORDER BY> and C<LIMIT> clauses.  optionally the C<ORDER BY> and C<LIMIT> clauses.
3647    
3648    =item matchClause
3649    
3650    An optional full-text search clause. If specified, it will be inserted at the
3651    front of the WHERE clause. It should already be SQL-formatted; that is, the
3652    field names should be in the form I<table>C<.>I<fieldName>.
3653    
3654  =item RETURN  =item RETURN
3655    
3656  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 2167  Line 3663 
3663  =cut  =cut
3664    
3665  sub _SetupSQL {  sub _SetupSQL {
3666      my ($self, $objectNames, $filterClause) = @_;      my ($self, $objectNames, $filterClause, $matchClause) = @_;
3667      # 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
3668      # 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
3669      # 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 2216  Line 3712 
3712      # FROM name1, name2, ... nameN      # FROM name1, name2, ... nameN
3713      #      #
3714      my $suffix = "FROM " . join(', ', @fromList);      my $suffix = "FROM " . join(', ', @fromList);
3715        # Now for the WHERE. First, we need a place for the filter string.
3716        my $filterString = "";
3717        # We will also keep a list of conditions to add to the WHERE clause in order to link
3718        # entities and relationships as well as primary relations to secondary ones.
3719        my @joinWhere = ();
3720      # Check for a filter clause.      # Check for a filter clause.
3721      if ($filterClause) {      if ($filterClause) {
3722          # 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,
3723          # We create a copy of the filter string we can work with.          # We create a copy of the filter string we can work with.
3724          my $filterString = $filterClause;          $filterString = $filterClause;
3725          # Next, we sort the object names by length. This helps protect us from finding          # Next, we sort the object names by length. This helps protect us from finding
3726          # object names inside other object names when we're doing our search and replace.          # object names inside other object names when we're doing our search and replace.
3727          my @sortedNames = sort { length($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 = ();  
3728          # 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
3729          # 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
3730          # 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 2294  Line 3792 
3792                  }                  }
3793              }              }
3794          }          }
3795        }
3796          # 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
3797          # 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
3798          # 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
3799          # list before running through it.      # list before running through it, because we shift off the first object before
3800        # processing the rest.
3801          my @mappedObjectList = @mappedNameList;          my @mappedObjectList = @mappedNameList;
3802          my $lastMappedObject = shift @mappedObjectList;          my $lastMappedObject = shift @mappedObjectList;
3803          # Get the join table.          # Get the join table.
# Line 2326  Line 3826 
3826          # 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.
3827          # We'll put the ORDER BY / LIMIT clauses in the following variable.          # We'll put the ORDER BY / LIMIT clauses in the following variable.
3828          my $orderClause = "";          my $orderClause = "";
3829        # This is only necessary if we have a filter string in which the ORDER BY
3830        # and LIMIT clauses can live.
3831        if ($filterString) {
3832          # 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
3833          # operator so that we find the first occurrence of either verb.          # operator so that we find the first occurrence of either verb.
3834          if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {          if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {
# Line 2334  Line 3837 
3837              $orderClause = $2 . substr($filterString, $pos);              $orderClause = $2 . substr($filterString, $pos);
3838              $filterString = $1;              $filterString = $1;
3839          }          }
3840          # Add the filter and the join clauses (if any) to the SELECT command.      }
3841        # All the things that are supposed to be in the WHERE clause of the
3842        # SELECT command need to be put into @joinWhere so we can string them
3843        # together. We begin with the match clause. This is important,
3844        # because the match clause's parameter mark must precede any parameter
3845        # marks in the filter string.
3846        if ($matchClause) {
3847            push @joinWhere, $matchClause;
3848        }
3849        # Add the filter string. We put it in parentheses to avoid operator
3850        # precedence problems with the match clause or the joins.
3851          if ($filterString) {          if ($filterString) {
3852              Trace("Filter string is \"$filterString\".") if T(4);              Trace("Filter string is \"$filterString\".") if T(4);
3853              push @joinWhere, "($filterString)";              push @joinWhere, "($filterString)";
3854          }          }
3855        # String it all together into a big filter clause.
3856          if (@joinWhere) {          if (@joinWhere) {
3857              $suffix .= " WHERE " . join(' AND ', @joinWhere);              $suffix .= " WHERE " . join(' AND ', @joinWhere);
3858          }          }
3859          # Add the sort or limit clause (if any) to the SELECT command.      # Add the sort or limit clause (if any).
3860          if ($orderClause) {          if ($orderClause) {
3861              $suffix .= " $orderClause";              $suffix .= " $orderClause";
3862          }          }
     }  
3863      # Return the suffix, the mapped name list, and the mapped name hash.      # Return the suffix, the mapped name list, and the mapped name hash.
3864      return ($suffix, \@mappedNameList, \%mappedNameHash);      return ($suffix, \@mappedNameList, \%mappedNameHash);
3865  }  }
3866    
3867  =head3 GetStatementHandle  =head3 _GetStatementHandle
3868    
3869  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.
3870  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 2389  Line 3902 
3902      # Prepare the command.      # Prepare the command.
3903      my $sth = $dbh->prepare_command($command);      my $sth = $dbh->prepare_command($command);
3904      # Execute it with the parameters bound in.      # Execute it with the parameters bound in.
3905      $sth->execute(@{$params}) || Confess("SELECT error" . $sth->errstr());      $sth->execute(@{$params}) || Confess("SELECT error:  " . $sth->errstr());
3906      # Return the statement handle.      # Return the statement handle.
3907      return $sth;      return $sth;
3908  }  }
3909    
3910  =head3 GetLoadStats  =head3 _GetLoadStats
3911    
3912  Return a blank statistics object for use by the load methods.  Return a blank statistics object for use by the load methods.
3913    
# Line 2406  Line 3919 
3919      return Stats->new();      return Stats->new();
3920  }  }
3921    
3922  =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  
3923    
3924  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.
3925    
3926  This is an instance method.  This is an instance method.
3927    
# Line 2530  Line 3969 
3969      close DTXOUT;      close DTXOUT;
3970  }  }
3971    
3972  =head3 GetStructure  =head3 _GetStructure
3973    
3974  Get the data structure for a specified entity or relationship.  Get the data structure for a specified entity or relationship.
3975    
# Line 2569  Line 4008 
4008      return $retVal;      return $retVal;
4009  }  }
4010    
4011  =head3 GetRelationTable  
4012    
4013    =head3 _GetRelationTable
4014    
4015  Get the list of relations for a specified entity or relationship.  Get the list of relations for a specified entity or relationship.
4016    
# Line 2598  Line 4039 
4039      return $objectData->{Relations};      return $objectData->{Relations};
4040  }  }
4041    
4042  =head3 ValidateFieldNames  =head3 _ValidateFieldNames
4043    
4044  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
4045  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 2625  Line 4066 
4066          for my $object (values %{$metadata->{$section}}) {          for my $object (values %{$metadata->{$section}}) {
4067              # Loop through the object's fields.              # Loop through the object's fields.
4068              for my $fieldName (keys %{$object->{Fields}}) {              for my $fieldName (keys %{$object->{Fields}}) {
4069                  # Now we make some initial validations.                  # If this field name is invalid, set the return value to zero
4070                  if ($fieldName =~ /--/) {                  # so we know we encountered an error.
4071                      # Here we have a doubled minus sign.                  if (! ValidateFieldName($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";  
4072                          $retVal = 0;                          $retVal = 0;
4073                      }                      }
4074                  }                  }
4075              }              }
4076          }          }
     }  
4077      # If an error was found, fail.      # If an error was found, fail.
4078      if ($retVal  == 0) {      if ($retVal  == 0) {
4079          Confess("Errors found in field names.");          Confess("Errors found in field names.");
4080      }      }
4081  }  }
4082    
4083  =head3 LoadRelation  =head3 _LoadRelation
4084    
4085  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
4086  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 2713  Line 4140 
4140      return $retVal;      return $retVal;
4141  }  }
4142    
4143  =head3 LoadMetaData  
4144    =head3 _LoadMetaData
4145    
4146    C<< my $metadata = ERDB::_LoadMetaData($filename); >>
4147    
4148  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.
4149  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 2738  Line 4168 
4168  sub _LoadMetaData {  sub _LoadMetaData {
4169      # Get the parameters.      # Get the parameters.
4170      my ($filename) = @_;      my ($filename) = @_;
4171      Trace("Reading Sprout DBD from $filename.") if T(2);      Trace("Reading DBD from $filename.") if T(2);
4172      # 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
4173      # get the exact structure we want.      # get the exact structure we want.
4174      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 $filename.") if T(1);  
4175      # Before we go any farther, we need to validate the field and object names. If an error is found,      # Before we go any farther, we need to validate the field and object names. If an error is found,
4176      # the method below will fail.      # the method below will fail.
4177      _ValidateFieldNames($metadata);      _ValidateFieldNames($metadata);
# Line 2877  Line 4294 
4294              if ($found == 0) {              if ($found == 0) {
4295                  push @{$indexList}, { IndexFields => [ {name => 'id', order => 'ascending'} ] };                  push @{$indexList}, { IndexFields => [ {name => 'id', order => 'ascending'} ] };
4296              }              }
4297              # Now we need to convert the relation's index list to an index table. We begin by creating              # Attach all the indexes to the relation.
4298              # an empty table in the relation structure.              _ProcessIndexes($indexList, $relation);
             $relation->{Indexes} = { };  
             # Loop through the indexes.  
             my $count = 0;  
             for my $index (@{$indexList}) {  
                 # Add this index to the index table.  
                 _AddIndex("idx$relationName$count", $relation, $index);  
                 # Increment the counter so that the next index has a different name.  
                 $count++;  
             }  
4299          }          }
4300          # Finally, we add the relation structure to the entity.          # Finally, we add the relation structure to the entity.
4301          $entityStructure->{Relations} = $relationTable;          $entityStructure->{Relations} = $relationTable;
# Line 2901  Line 4309 
4309          _FixupFields($relationshipStructure, $relationshipName, 2, 3);          _FixupFields($relationshipStructure, $relationshipName, 2, 3);
4310          # Format a description for the FROM field.          # Format a description for the FROM field.
4311          my $fromEntity = $relationshipStructure->{from};          my $fromEntity = $relationshipStructure->{from};
4312          my $fromComment = "<b>id</b> of the source <b><a href=\"#$fromEntity\">$fromEntity</a></b>.";          my $fromComment = "[b]id[/b] of the source [b][link #$fromEntity]$fromEntity\[/link][/b].";
4313          # Get the FROM entity's key type.          # Get the FROM entity's key type.
4314          my $fromType = $entityList->{$fromEntity}->{keyType};          my $fromType = $entityList->{$fromEntity}->{keyType};
4315          # Add the FROM field.          # Add the FROM field.
# Line 2911  Line 4319 
4319                                                      PrettySort => 1});                                                      PrettySort => 1});
4320          # Format a description for the TO field.          # Format a description for the TO field.
4321          my $toEntity = $relationshipStructure->{to};          my $toEntity = $relationshipStructure->{to};
4322          my $toComment = "<b>id</b> of the target <b><a href=\"#$toEntity\">$toEntity</a></b>.";          my $toComment = "[b]id[/b] of the target [b][link #$toEntity]$toEntity\[/link][/b].";
4323          # Get the TO entity's key type.          # Get the TO entity's key type.
4324          my $toType = $entityList->{$toEntity}->{keyType};          my $toType = $entityList->{$toEntity}->{keyType};
4325          # Add the TO field.          # Add the TO field.
# Line 2923  Line 4331 
4331          my $thisRelation = { Fields => _ReOrderRelationTable($relationshipStructure->{Fields}),          my $thisRelation = { Fields => _ReOrderRelationTable($relationshipStructure->{Fields}),
4332                               Indexes => { } };                               Indexes => { } };
4333          $relationshipStructure->{Relations} = { $relationshipName => $thisRelation };          $relationshipStructure->{Relations} = { $relationshipName => $thisRelation };
4334    
4335            # Add the alternate indexes (if any). This MUST be done before the FROM and
4336            # TO indexes, because it erases the relation's index list.
4337            if (exists $relationshipStructure->{Indexes}) {
4338                _ProcessIndexes($relationshipStructure->{Indexes}, $thisRelation);
4339            }
4340            # Add the relation to the master table.
4341          # Create the FROM and TO indexes.          # Create the FROM and TO indexes.
4342          _CreateRelationshipIndex("From", $relationshipName, $relationshipStructure);          _CreateRelationshipIndex("From", $relationshipName, $relationshipStructure);
4343          _CreateRelationshipIndex("To", $relationshipName, $relationshipStructure);          _CreateRelationshipIndex("To", $relationshipName, $relationshipStructure);
         # Add the relation to the master table.  
4344          $masterRelationTable{$relationshipName} = $thisRelation;          $masterRelationTable{$relationshipName} = $thisRelation;
4345      }      }
4346      # Now store the master relation table in the metadata structure.      # Now store the master relation table in the metadata structure.
# Line 3015  Line 4429 
4429                      # Join from the left.                      # Join from the left.
4430                      $joinTable{"$relationshipName/$otherName"} =                      $joinTable{"$relationshipName/$otherName"} =
4431                          "$linkField = $otherName.from_link";                          "$linkField = $otherName.from_link";
4432                      # Join from the right.                      # Join from the right.
4433                      $joinTable{"$otherName/$relationshipName"} =                      $joinTable{"$otherName/$relationshipName"} =
4434                          "$otherName.to_link = $linkField";                          "$otherName.to_link = $linkField";
                 }  
             }  
         }  
         # Create entity joins for the recursive relationships. Unlike the non-recursive  
         # joins, the direction makes a difference with the recursive joins. This can give  
         # rise to situations where we can't create the path we want; however, it is always  
         # possible to get the same effect using multiple queries.  
         for my $relationshipName (@bothList) {  
             Trace("Setting up entity joins to recursive relationship $relationshipName with $entityName.") if T(metadata => 4);  
             # Join to the entity from each direction.  
             $joinTable{"$entityName/$relationshipName"} =  
                 "$entityName.id = $relationshipName.from_link";  
             $joinTable{"$relationshipName/$entityName"} =  
                 "$relationshipName.to_link = $entityName.id";  
         }  
     }  
     # Add the join table to the structure.  
     $metadata->{Joins} = \%joinTable;  
     # Return the slurped and fixed-up structure.  
     return $metadata;  
 }  
   
 =head3 SortNeeded  
   
 C<< my $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;  
4435          }          }
4436      }      }
4437      # Return the result.          }
4438      return $retVal;          # Create entity joins for the recursive relationships. Unlike the non-recursive
4439            # joins, the direction makes a difference with the recursive joins. This can give
4440            # rise to situations where we can't create the path we want; however, it is always
4441            # possible to get the same effect using multiple queries.
4442            for my $relationshipName (@bothList) {
4443                Trace("Setting up entity joins to recursive relationship $relationshipName with $entityName.") if T(metadata => 4);
4444                # Join to the entity from each direction.
4445                $joinTable{"$entityName/$relationshipName"} =
4446                    "$entityName.id = $relationshipName.from_link";
4447                $joinTable{"$relationshipName/$entityName"} =
4448                    "$relationshipName.to_link = $entityName.id";
4449            }
4450        }
4451        # Add the join table to the structure.
4452        $metadata->{Joins} = \%joinTable;
4453        # Return the slurped and fixed-up structure.
4454        return $metadata;
4455  }  }
4456    
4457  =head3 CreateRelationshipIndex  =head3 _CreateRelationshipIndex
4458    
4459  Create an index for a relationship's relation.  Create an index for a relationship's relation.
4460    
# Line 3122  Line 4496 
4496          $newIndex->{Unique} = 'true';          $newIndex->{Unique} = 'true';
4497      }      }
4498      # Add the index to the relation.      # Add the index to the relation.
4499      _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);      _AddIndex("idx$indexKey", $relationStructure, $newIndex);
4500    }
4501    
4502    =head3 _ProcessIndexes
4503    
4504    C<< ERDB::_ProcessIndexes($indexList, $relation); >>
4505    
4506    Build the data structures for the specified indexes in the specified relation.
4507    
4508    =over 4
4509    
4510    =item indexList
4511    
4512    Reference to a list of indexes. Each index is a hash reference containing an optional
4513    C<Notes> value that describes the index and an C<IndexFields> value that is a reference
4514    to a list of index field structures. An index field structure, in turn, is a reference
4515    to a hash that contains a C<name> attribute for the field name and an C<order>
4516    attribute that specifies either C<ascending> or C<descending>. In this sense the
4517    index list encapsulates the XML C<Indexes> structure in the database definition.
4518    
4519    =item relation
4520    
4521    The structure that describes the current relation. The new index descriptors will
4522    be stored in the structure's C<Indexes> member. Any previous data in the structure
4523    will be lost.
4524    
4525    =back
4526    
4527    =cut
4528    
4529    sub _ProcessIndexes {
4530        # Get the parameters.
4531        my ($indexList, $relation) = @_;
4532        # Now we need to convert the relation's index list to an index table. We begin by creating
4533        # an empty table in the relation structure.
4534        $relation->{Indexes} = { };
4535        # Loop through the indexes.
4536        my $count = 0;
4537        for my $index (@{$indexList}) {
4538            # Add this index to the index table.
4539            _AddIndex("idx$count", $relation, $index);
4540            # Increment the counter so that the next index has a different name.
4541            $count++;
4542        }
4543  }  }
4544    
4545  =head3 AddIndex  =head3 _AddIndex
4546    
4547  Add an index to a relation structure.  Add an index to a relation structure.
4548    
# Line 3171  Line 4588 
4588      $relationStructure->{Indexes}->{$indexName} = $newIndex;      $relationStructure->{Indexes}->{$indexName} = $newIndex;
4589  }  }
4590    
4591  =head3 FixupFields  =head3 _FixupFields
4592    
4593  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
4594  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 3209  Line 4626 
4626          # Here it doesn't, so we create a new one.          # Here it doesn't, so we create a new one.
4627          $structure->{Fields} = { };          $structure->{Fields} = { };
4628      } else {      } else {
4629          # 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
4630            # create a list for stashing them.
4631            my @textFields = ();
4632            # Loop through the fields.
4633          my $fieldStructures = $structure->{Fields};          my $fieldStructures = $structure->{Fields};
4634          for my $fieldName (keys %{$fieldStructures}) {          for my $fieldName (keys %{$fieldStructures}) {
4635              Trace("Processing field $fieldName of $defaultRelationName.") if T(4);              Trace("Processing field $fieldName of $defaultRelationName.") if T(4);
# Line 3218  Line 4638 
4638              my $type = $fieldData->{type};              my $type = $fieldData->{type};
4639              # Plug in a relation name if it is needed.              # Plug in a relation name if it is needed.
4640              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });
4641              # Plug in a data generator if we need one.              # Check for searchability.
4642              if (!exists $fieldData->{DataGen}) {              if ($fieldData->{searchable}) {
4643                  # The data generator will use the default for the field's type.                  # Only allow this for a primary relation.
4644                  $fieldData->{DataGen} = { content => $TypeTable{$type}->{dataGen} };                  if ($fieldData->{relation} ne $defaultRelationName) {
4645                        Confess("Field $fieldName of $defaultRelationName is in secondary relations and cannot be searchable.");
4646                    } else {
4647                        push @textFields, $fieldName;
4648                    }
4649              }              }
             # Plug in the defaults for the optional data generation parameters.  
             Tracer::MergeOptions($fieldData->{DataGen}, { testCount => 1, pass => 0 });  
4650              # Add the PrettySortValue.              # Add the PrettySortValue.
4651              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);
4652          }          }
4653            # If there are searchable fields, remember the fact.
4654            if (@textFields) {
4655                $structure->{searchFields} = \@textFields;
4656            }
4657      }      }
4658  }  }
4659    
4660  =head3 FixName  =head3 _FixName
4661    
4662  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.
4663    
# Line 3260  Line 4686 
4686      return $fieldName;      return $fieldName;
4687  }  }
4688    
4689  =head3 FixNames  =head3 _FixNames
4690    
4691  Fix all the field names in a list.  Fix all the field names in a list.
4692    
# Line 3291  Line 4717 
4717      return @result;      return @result;
4718  }  }
4719    
4720  =head3 AddField  =head3 _AddField
4721    
4722  Add a field to a field list.  Add a field to a field list.
4723    
# Line 3326  Line 4752 
4752      $fieldList->{$fieldName} = $fieldStructure;      $fieldList->{$fieldName} = $fieldStructure;
4753  }  }
4754    
4755  =head3 ReOrderRelationTable  =head3 _ReOrderRelationTable
4756    
4757  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
4758  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 3387  Line 4813 
4813    
4814  }  }
4815    
4816  =head3 IsPrimary  =head3 _IsPrimary
4817    
4818  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
4819  if it has the same name as an entity or relationship.  if it has the same name as an entity or relationship.
# Line 3423  Line 4849 
4849      return $retVal;      return $retVal;
4850  }  }
4851    
4852  =head3 FindRelation  =head3 _FindRelation
4853    
4854  Return the descriptor for the specified relation.  Return the descriptor for the specified relation.
4855    
# Line 3454  Line 4880 
4880    
4881  =head2 HTML Documentation Utility Methods  =head2 HTML Documentation Utility Methods
4882    
4883  =head3 ComputeRelationshipSentence  =head3 _ComputeRelationshipSentence
4884    
4885  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
4886  two related entities and an arity indicator.  two related entities and an arity indicator.
# Line 3492  Line 4918 
4918      return $result;      return $result;
4919  }  }
4920    
4921  =head3 ComputeRelationshipHeading  =head3 _ComputeRelationshipHeading
4922    
4923  The relationship heading is the L<relationship sentence|/ComputeRelationshipSentence> with the entity  The relationship heading is the L<relationship sentence|/ComputeRelationshipSentence> with the entity
4924  names hyperlinked to the appropriate entity sections of the document.  names hyperlinked to the appropriate entity sections of the document.
# Line 3529  Line 4955 
4955      return $result;      return $result;
4956  }  }
4957    
4958  =head3 ShowRelationTable  =head3 _ShowRelationTable
4959    
4960  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
4961  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 3579  Line 5005 
5005          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";
5006          # Add any note text.          # Add any note text.
5007          if (my $note = $indexData->{Notes}) {          if (my $note = $indexData->{Notes}) {
5008              $htmlString .= "<li>" . _HTMLNote($note->{content}) . "</li>\n";              $htmlString .= "<li>" . HTMLNote($note->{content}) . "</li>\n";
5009          }          }
5010          # Add the fiield list.          # Add the fiield list.
5011          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";
# Line 3590  Line 5016 
5016      $htmlString .= "</ul>\n";      $htmlString .= "</ul>\n";
5017  }  }
5018    
5019  =head3 OpenFieldTable  =head3 _OpenFieldTable
5020    
5021  This method creates the header string for the field table generated by L</ShowMetaData>.  This method creates the header string for the field table generated by L</ShowMetaData>.
5022    
# Line 3615  Line 5041 
5041      return _OpenTable($tablename, 'Field', 'Type', 'Description');      return _OpenTable($tablename, 'Field', 'Type', 'Description');
5042  }  }
5043    
5044  =head3 OpenTable  =head3 _OpenTable
5045    
5046  This method creates the header string for an HTML table.  This method creates the header string for an HTML table.
5047    
# Line 3645  Line 5071 
5071      # Compute the number of columns.      # Compute the number of columns.
5072      my $colCount = @colNames;      my $colCount = @colNames;
5073      # Generate the title row.      # Generate the title row.
5074      my $htmlString = "<p><table border=\"2\"><tr><td colspan=\"$colCount\" align=\"center\">$tablename</td></tr>\n";      my $htmlString = "<table border=\"2\"><tr><td colspan=\"$colCount\" align=\"center\">$tablename</td></tr>\n";
5075      # Loop through the columns, adding the column header rows.      # Loop through the columns, adding the column header rows.
5076      $htmlString .= "<tr>";      $htmlString .= "<tr>";
5077      for my $colName (@colNames) {      for my $colName (@colNames) {
# Line 3655  Line 5081 
5081      return $htmlString;      return $htmlString;
5082  }  }
5083    
5084  =head3 CloseTable  =head3 _CloseTable
5085    
5086  This method returns the HTML for closing a table.  This method returns the HTML for closing a table.
5087    
# Line 3664  Line 5090 
5090  =cut  =cut
5091    
5092  sub _CloseTable {  sub _CloseTable {
5093      return "</table></p>\n";      return "</table>\n";
5094  }  }
5095    
5096  =head3 ShowField  =head3 _ShowField
5097    
5098  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.
5099    
# Line 3694  Line 5120 
5120      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>";
5121      # If we have content, add it as a third column.      # If we have content, add it as a third column.
5122      if (exists $fieldData->{Notes}) {      if (exists $fieldData->{Notes}) {
5123          $htmlString .= "<td>" . _HTMLNote($fieldData->{Notes}->{content}) . "</td>";          $htmlString .= "<td>" . HTMLNote($fieldData->{Notes}->{content}) . "</td>";
5124      }      }
5125      # Close off the row.      # Close off the row.
5126      $htmlString .= "</tr>\n";      $htmlString .= "</tr>\n";
# Line 3702  Line 5128 
5128      return $htmlString;      return $htmlString;
5129  }  }
5130    
 =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;  
 }  
   
5131  1;  1;

Legend:
Removed from v.1.47  
changed lines
  Added in v.1.88

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3