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

Diff of /Sprout/ERDB.pm

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

revision 1.42, Wed Apr 19 03:34:15 2006 UTC revision 1.76, Wed Nov 15 12:08:26 2006 UTC
# Line 11  Line 11 
11      use Time::HiRes qw(gettimeofday);      use Time::HiRes qw(gettimeofday);
12      use Digest::MD5 qw(md5_base64);      use Digest::MD5 qw(md5_base64);
13      use FIG;      use FIG;
14        use CGI;
15    
16  =head1 Entity-Relationship Database Package  =head1 Entity-Relationship Database Package
17    
# Line 59  Line 60 
60  B<start-position>, which indicates where in the contig that the sequence begins. This attribute  B<start-position>, which indicates where in the contig that the sequence begins. This attribute
61  is implemented as the C<start_position> field in the C<IsMadeUpOf> relation.  is implemented as the C<start_position> field in the C<IsMadeUpOf> relation.
62    
63  The database itself is described by an XML file using the F<ERDatabase.xsd> schema. In addition to  The database itself is described by an XML file. In addition to all the data required to define
64  all the data required to define the entities, relationships, and attributes, the schema provides  the entities, relationships, and attributes, the schema provides space for notes describing
65  space for notes describing the data and what it means. These notes are used by L</ShowMetaData>  the data and what it means. These notes are used by L</ShowMetaData> to generate documentation
66  to generate documentation for the database.  for the database.
67    
68    Special support is provided for text searching. An entity field can be marked as <em>searchable</em>,
69    in which case it will be used to generate a text search index in which the user searches for words
70    in the field instead of a particular field value.
71    
72  Finally, every entity and relationship object has a flag indicating if it is new or old. The object  Finally, every entity and relationship object has a flag indicating if it is new or old. The object
73  is considered I<old> if it was loaded by the L</LoadTables> method. It is considered I<new> if it  is considered I<old> if it was loaded by the L</LoadTables> method. It is considered I<new> if it
74  was inserted by the L</InsertObject> method.  was inserted by the L</InsertObject> method.
75    
 To facilitate testing, the ERDB module supports automatic generation of test data. This process  
 is described in the L</GenerateEntity> and L</GenerateConnection> methods, though it is not yet  
 fully implemented.  
   
76  =head2 XML Database Description  =head2 XML Database Description
77    
78  =head3 Data Types  =head3 Data Types
# Line 91  Line 92 
92    
93  32-bit signed integer  32-bit signed integer
94    
95    =item counter
96    
97    32-bit unsigned integer
98    
99  =item date  =item date
100    
101  64-bit unsigned integer, representing a PERL date/time value  64-bit unsigned integer, representing a PERL date/time value
# Line 110  Line 115 
115  compatability with certain database packages), but the only values supported are  compatability with certain database packages), but the only values supported are
116  0 and 1.  0 and 1.
117    
118    =item id-string
119    
120    variable-length string, maximum 25 characters
121    
122  =item key-string  =item key-string
123    
124  variable-length string, maximum 40 characters  variable-length string, maximum 40 characters
# Line 182  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 201  Line 212 
212  entity, the fields without a relation attribute are said to belong to the  entity, the fields without a relation attribute are said to belong to the
213  I<primary relation>. This relation has the same name as the entity itself.  I<primary relation>. This relation has the same name as the entity itself.
214    
215    =item searchable
216    
217    If specified, then the field is a candidate for full-text searching. A single full-text
218    index will be created for each relation with at least one searchable field in it.
219    For best results, this option should only be used for string or text fields.
220    
221    =item special
222    
223    This attribute allows the subclass to assign special meaning for certain fields.
224    The interpretation is up to the subclass itself. Currently, only entity fields
225    can have this attribute.
226    
227  =back  =back
228    
229  =head3 Indexes  =head3 Indexes
230    
231  An entity can have multiple alternate indexes associated with it. The fields must  An entity can have multiple alternate indexes associated with it. The fields must
232  be from the primary relation. The alternate indexes assist in ordering results  all be from the same relation. The alternate indexes assist in ordering results
233  from a query. A relationship can have up to two indexes-- a I<to-index> and a  from a query. A relationship can have up to two indexes-- a I<to-index> and a
234  I<from-index>. These order the results when crossing the relationship. For  I<from-index>. These order the results when crossing the relationship. For
235  example, in the relationship C<HasContig> from C<Genome> to C<Contig>, the  example, in the relationship C<HasContig> from C<Genome> to C<Contig>, the
# Line 312  Line 335 
335    
336  # Table of information about our datatypes. "sqlType" is the corresponding SQL datatype string.  # Table of information about our datatypes. "sqlType" is the corresponding SQL datatype string.
337  # "maxLen" is the maximum permissible length of the incoming string data used to populate a field  # "maxLen" is the maximum permissible length of the incoming string data used to populate a field
338  # of the specified type. "dataGen" is PERL string that will be evaluated if no test data generation  # of the specified type. "avgLen" is the average byte length for estimating
339  # string is specified in the field definition. "avgLen" is the average byte length for estimating  # record sizes. "sort" is the key modifier for the sort command, "notes" is a type description,
340  # record sizes.  # and "indexMod", if non-zero, is the number of characters to use when the field is specified in an
341  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, dataGen => "StringGen('A')" },  # index
342                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, dataGen => "IntGen(0, 99999999)" },  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",
343                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, dataGen => "StringGen(IntGen(10,250))" },                                 indexMod =>   0, notes => "single ASCII character"},
344                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, dataGen => "StringGen(IntGen(80,1000))" },                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n",
345                    date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, dataGen => "DateGen(-7, 7, IntGen(0,1400))" },                                 indexMod =>   0, notes => "signed 32-bit integer"},
346                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, dataGen => "FloatGen(0.0, 100.0)" },                    counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n",
347                    boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, dataGen => "IntGen(0, 1)" },                                 indexMod =>   0, notes => "unsigned 32-bit integer"},
348                      string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, sort => "",
349                                   indexMod =>   0, notes => "character string, 0 to 255 characters"},
350                      text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, sort => "",
351                                   indexMod => 255, notes => "character string, nearly unlimited length, only first 255 characters are indexed"},
352                      date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, sort => "n",
353                                   indexMod =>   0, notes => "signed, 64-bit integer"},
354                      float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, sort => "g",
355                                   indexMod =>   0, notes => "64-bit double precision floating-point number"},
356                      boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, sort => "n",
357                                   indexMod =>   0, notes => "boolean value: 0 if false, 1 if true"},
358                   'hash-string' =>                   'hash-string' =>
359                               { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, dataGen => "SringGen(22)" },                               { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, sort => "",
360                                   indexMod =>   0, notes => "string stored in digested form, used for certain types of key fields"},
361                     'id-string' =>
362                                 { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, sort => "",
363                                   indexMod =>   0, notes => "character string, 0 to 25 characters"},
364                   'key-string' =>                   'key-string' =>
365                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, dataGen => "StringGen(IntGen(10,40))" },                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, sort => "",
366                                   indexMod =>   0, notes => "character string, 0 to 40 characters"},
367                   'name-string' =>                   'name-string' =>
368                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, dataGen => "StringGen(IntGen(10,80))" },                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, sort => "",
369                                   indexMod =>   0, notes => "character string, 0 to 80 characters"},
370                   'medium-string' =>                   'medium-string' =>
371                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, dataGen => "StringGen(IntGen(10,160))" },                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",
372                                   indexMod =>   0, notes => "character string, 0 to 160 characters"},
373                  );                  );
374    
375  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 338  Line 378 
378                     'MM' => 'many-to-many'                     'MM' => 'many-to-many'
379                   );                   );
380    
381  # Table for interpreting string patterns.  # Options for XML input and output.
382    
383    my %XmlOptions = (GroupTags =>  { Relationships => 'Relationship',
384                                      Entities => 'Entity',
385                                      Fields => 'Field',
386                                      Indexes => 'Index',
387                                      IndexFields => 'IndexField'
388                                    },
389                      KeyAttr =>    { Relationship => 'name',
390                                      Entity => 'name',
391                                      Field => 'name'
392                                    },
393                      SuppressEmpty => 1,
394                     );
395    
396  my %PictureTable = ( 'A' => "abcdefghijklmnopqrstuvwxyz",  my %XmlInOpts  = (
397                       '9' => "0123456789",                    ForceArray => ['Field', 'Index', 'IndexField'],
398                       'X' => "abcdefghijklmnopqrstuvwxyz0123456789",                    ForceContent => 1,
399                       'V' => "aeiou",                    NormalizeSpace => 2,
                      'K' => "bcdfghjklmnoprstvwxyz"  
400                     );                     );
401    my %XmlOutOpts = (
402                      RootName => 'Database',
403                      XMLDecl => 1,
404                     );
405    
406    
407  =head2 Public Methods  =head2 Public Methods
408    
# Line 416  Line 473 
473      # Write the HTML heading stuff.      # Write the HTML heading stuff.
474      print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";      print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";
475      print HTMLOUT "</head>\n<body>\n";      print HTMLOUT "</head>\n<body>\n";
476        # Write the documentation.
477        print HTMLOUT $self->DisplayMetaData();
478        # Close the document.
479        print HTMLOUT "</body>\n</html>\n";
480        # Close the file.
481        close HTMLOUT;
482    }
483    
484    =head3 DisplayMetaData
485    
486    C<< my $html = $erdb->DisplayMetaData(); >>
487    
488    Return an HTML description of the database. This description can be used to help users create
489    the data to be loaded into the relations and form queries. The output is raw includable HTML
490    without any HEAD or BODY tags.
491    
492    =over 4
493    
494    =item filename
495    
496    The name of the output file.
497    
498    =back
499    
500    =cut
501    
502    sub DisplayMetaData {
503        # Get the parameters.
504        my ($self) = @_;
505        # Get the metadata and the title string.
506        my $metadata = $self->{_metaData};
507        # Get the title string.
508        my $title = $metadata->{Title};
509        # Get the entity and relationship lists.
510        my $entityList = $metadata->{Entities};
511        my $relationshipList = $metadata->{Relationships};
512        # Declare the return variable.
513        my $retVal = "";
514        # Open the output file.
515        Trace("Building MetaData table of contents.") if T(4);
516      # Here we do the table of contents. It starts as an unordered list of section names. Each      # Here we do the table of contents. It starts as an unordered list of section names. Each
517      # section contains an ordered list of entity or relationship subsections.      # section contains an ordered list of entity or relationship subsections.
518      print HTMLOUT "<ul>\n<li><a href=\"#EntitiesSection\">Entities</a>\n<ol>\n";      $retVal .= "<ul>\n<li><a href=\"#EntitiesSection\">Entities</a>\n<ol>\n";
519      # Loop through the Entities, displaying a list item for each.      # Loop through the Entities, displaying a list item for each.
520      foreach my $key (sort keys %{$entityList}) {      foreach my $key (sort keys %{$entityList}) {
521          # Display this item.          # Display this item.
522          print HTMLOUT "<li><a href=\"#$key\">$key</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$key</a></li>\n";
523      }      }
524      # Close off the entity section and start the relationship section.      # Close off the entity section and start the relationship section.
525      print HTMLOUT "</ol></li>\n<li><a href=\"#RelationshipsSection\">Relationships</a>\n<ol>\n";      $retVal .= "</ol></li>\n<li><a href=\"#RelationshipsSection\">Relationships</a>\n<ol>\n";
526      # Loop through the Relationships.      # Loop through the Relationships.
527      foreach my $key (sort keys %{$relationshipList}) {      foreach my $key (sort keys %{$relationshipList}) {
528          # Display this item.          # Display this item.
529          my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});          my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});
530          print HTMLOUT "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";
531      }      }
532      # Close off the relationship section and list the join table section.      # Close off the relationship section and list the join table section.
533      print HTMLOUT "</ol></li>\n<li><a href=\"#JoinTable\">Join Table</a></li>\n";      $retVal .= "</ol></li>\n<li><a href=\"#JoinTable\">Join Table</a></li>\n";
534      # Close off the table of contents itself.      # Close off the table of contents itself.
535      print HTMLOUT "</ul>\n";      $retVal .=  "</ul>\n";
536      # Now we start with the actual data. Denote we're starting the entity section.      # Now we start with the actual data. Denote we're starting the entity section.
537      print HTMLOUT "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";      $retVal .= "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";
538      # Loop through the entities.      # Loop through the entities.
539      for my $key (sort keys %{$entityList}) {      for my $key (sort keys %{$entityList}) {
540          Trace("Building MetaData entry for $key entity.") if T(4);          Trace("Building MetaData entry for $key entity.") if T(4);
541          # Create the entity header. It contains a bookmark and the entity name.          # Create the entity header. It contains a bookmark and the entity name.
542          print HTMLOUT "<a name=\"$key\"></a><h3>$key</h3>\n";          $retVal .= "<a name=\"$key\"></a><h3>$key</h3>\n";
543          # Get the entity data.          # Get the entity data.
544          my $entityData = $entityList->{$key};          my $entityData = $entityList->{$key};
545          # If there's descriptive text, display it.          # If there's descriptive text, display it.
546          if (my $notes = $entityData->{Notes}) {          if (my $notes = $entityData->{Notes}) {
547              print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
548          }          }
549          # Now we want a list of the entity's relationships. First, we set up the relationship subsection.          # Now we want a list of the entity's relationships. First, we set up the relationship subsection.
550          print HTMLOUT "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
551          # Loop through the relationships.          # Loop through the relationships.
552          for my $relationship (sort keys %{$relationshipList}) {          for my $relationship (sort keys %{$relationshipList}) {
553              # Get the relationship data.              # Get the relationship data.
# Line 460  Line 557 
557                  # Get the relationship sentence and append the arity.                  # Get the relationship sentence and append the arity.
558                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);
559                  # Display the relationship data.                  # Display the relationship data.
560                  print HTMLOUT "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";                  $retVal .= "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";
561              }              }
562          }          }
563          # Close off the relationship list.          # Close off the relationship list.
564          print HTMLOUT "</ul>\n";          $retVal .= "</ul>\n";
565          # Get the entity's relations.          # Get the entity's relations.
566          my $relationList = $entityData->{Relations};          my $relationList = $entityData->{Relations};
567          # Create a header for the relation subsection.          # Create a header for the relation subsection.
568          print HTMLOUT "<h4>Relations for <b>$key</b></h4>\n";          $retVal .= "<h4>Relations for <b>$key</b></h4>\n";
569          # Loop through the relations, displaying them.          # Loop through the relations, displaying them.
570          for my $relation (sort keys %{$relationList}) {          for my $relation (sort keys %{$relationList}) {
571              my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});              my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});
572              print HTMLOUT $htmlString;              $retVal .= $htmlString;
573          }          }
574      }      }
575      # Denote we're starting the relationship section.      # Denote we're starting the relationship section.
576      print HTMLOUT "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";      $retVal .= "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";
577      # Loop through the relationships.      # Loop through the relationships.
578      for my $key (sort keys %{$relationshipList}) {      for my $key (sort keys %{$relationshipList}) {
579          Trace("Building MetaData entry for $key relationship.") if T(4);          Trace("Building MetaData entry for $key relationship.") if T(4);
# Line 484  Line 581 
581          my $relationshipStructure = $relationshipList->{$key};          my $relationshipStructure = $relationshipList->{$key};
582          # Create the relationship header.          # Create the relationship header.
583          my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);          my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);
584          print HTMLOUT "<h3><a name=\"$key\"></a>$headerText</h3>\n";          $retVal .= "<h3><a name=\"$key\"></a>$headerText</h3>\n";
585          # Get the entity names.          # Get the entity names.
586          my $fromEntity = $relationshipStructure->{from};          my $fromEntity = $relationshipStructure->{from};
587          my $toEntity = $relationshipStructure->{to};          my $toEntity = $relationshipStructure->{to};
# Line 494  Line 591 
591          # since both sentences will say the same thing.          # since both sentences will say the same thing.
592          my $arity = $relationshipStructure->{arity};          my $arity = $relationshipStructure->{arity};
593          if ($arity eq "11") {          if ($arity eq "11") {
594              print HTMLOUT "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";
595          } else {          } else {
596              print HTMLOUT "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";
597              if ($arity eq "MM" && $fromEntity ne $toEntity) {              if ($arity eq "MM" && $fromEntity ne $toEntity) {
598                  print HTMLOUT "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";                  $retVal .= "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";
599              }              }
600          }          }
601          print HTMLOUT "</p>\n";          $retVal .= "</p>\n";
602          # If there are notes on this relationship, display them.          # If there are notes on this relationship, display them.
603          if (my $notes = $relationshipStructure->{Notes}) {          if (my $notes = $relationshipStructure->{Notes}) {
604              print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
605          }          }
606          # Generate the relationship's relation table.          # Generate the relationship's relation table.
607          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
608          print HTMLOUT $htmlString;          $retVal .= $htmlString;
609      }      }
610      Trace("Building MetaData join table.") if T(4);      Trace("Building MetaData join table.") if T(4);
611      # Denote we're starting the join table.      # Denote we're starting the join table.
612      print HTMLOUT "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";      $retVal .= "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";
613      # Create a table header.      # Create a table header.
614      print HTMLOUT _OpenTable("Join Table", "Source", "Target", "Join Condition");      $retVal .= _OpenTable("Join Table", "Source", "Target", "Join Condition");
615      # Loop through the joins.      # Loop through the joins.
616      my $joinTable = $metadata->{Joins};      my $joinTable = $metadata->{Joins};
617      my @joinKeys = keys %{$joinTable};      my @joinKeys = keys %{$joinTable};
# Line 527  Line 624 
624          my $target = $self->ComputeObjectSentence($targetRelation);          my $target = $self->ComputeObjectSentence($targetRelation);
625          my $clause = $joinTable->{$joinKey};          my $clause = $joinTable->{$joinKey};
626          # Display them in a table row.          # Display them in a table row.
627          print HTMLOUT "<tr><td>$source</td><td>$target</td><td>$clause</td></tr>\n";          $retVal .= "<tr><td>$source</td><td>$target</td><td>$clause</td></tr>\n";
628      }      }
629      # Close the table.      # Close the table.
630      print HTMLOUT _CloseTable();      $retVal .= _CloseTable();
631      # Close the document.      Trace("Built MetaData HTML.") if T(3);
632      print HTMLOUT "</body>\n</html>\n";      # Return the HTML.
633      # Close the file.      return $retVal;
     close HTMLOUT;  
     Trace("Built MetaData web page.") if T(3);  
634  }  }
635    
636  =head3 DumpMetaData  =head3 DumpMetaData
# Line 553  Line 648 
648      return Data::Dumper::Dumper($self->{_metaData});      return Data::Dumper::Dumper($self->{_metaData});
649  }  }
650    
651    =head3 FindIndexForEntity
652    
653    C<< my $indexFound = ERDB::FindIndexForEntity($xml, $entityName, $attributeName); >>
654    
655    This method locates the entry in an entity's index list that begins with the
656    specified attribute name. If the entity has no index list, one will be
657    created. This method works on raw XML, not a live ERDB object.
658    
659    =over 4
660    
661    =item xml
662    
663    The raw XML structure defining the database.
664    
665    =item entityName
666    
667    The name of the relevant entity.
668    
669    =item attributeName
670    
671    The name of the attribute relevant to the search.
672    
673    =item RETURN
674    
675    The numerical index in the index list of the index entry for the specified entity and
676    attribute, or C<undef> if no such index exists.
677    
678    =back
679    
680    =cut
681    
682    sub FindIndexForEntity {
683        # Get the parameters.
684        my ($xml, $entityName, $attributeName) = @_;
685        # Declare the return variable.
686        my $retVal;
687        # Get the named entity.
688        my $entityData = $xml->{Entities}->{$entityName};
689        if (! $entityData) {
690            Confess("Entity $entityName not found in DBD structure.");
691        } else {
692            # Insure it has an index list.
693            if (! exists $entityData->{Indexes}) {
694                $entityData->{Indexes} = [];
695            } else {
696                # Search for the desired index.
697                my $indexList = $entityData->{Indexes};
698                my $n = scalar @{$indexList};
699                Trace("Searching $n indexes in index list for $entityName.") if T(2);
700                # We use an indexed FOR here because we're returning an
701                # index number instead of an object. We do THAT so we can
702                # delete the index from the list if needed.
703                for (my $i = 0; $i < $n && !defined($retVal); $i++) {
704                    my $index = $indexList->[$i];
705                    my $fields = $index->{IndexFields};
706                    # Technically this IF should be safe (that is, we are guaranteed
707                    # the existence of a "$fields->[0]"), because when we load the XML
708                    # we have SuppressEmpty specified.
709                    if ($fields->[0]->{name} eq $attributeName) {
710                        $retVal = $i;
711                    }
712                }
713            }
714        }
715        Trace("Index for $attributeName of $entityName found at position $retVal.") if defined($retVal) && T(3);
716        Trace("Index for $attributeName not found in $entityName.") if !defined($retVal) && T(3);
717        # Return the result.
718        return $retVal;
719    }
720    
721  =head3 CreateTables  =head3 CreateTables
722    
723  C<< $erdb->CreateTables(); >>  C<< $erdb->CreateTables(); >>
# Line 640  Line 805 
805      Trace("Creating table $relationName: $fieldThing") if T(2);      Trace("Creating table $relationName: $fieldThing") if T(2);
806      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);
807      Trace("Relation $relationName created in database.") if T(2);      Trace("Relation $relationName created in database.") if T(2);
808      # If we want to build the indexes, we do it here.      # If we want to build the indexes, we do it here. Note that the full-text search
809        # index will not be built until the table has been loaded.
810      if ($indexFlag) {      if ($indexFlag) {
811          $self->CreateIndex($relationName);          $self->CreateIndex($relationName);
812      }      }
# Line 736  Line 902 
902          my $fieldType = $fieldTypes->[$i]->{type};          my $fieldType = $fieldTypes->[$i]->{type};
903          # If it's a hash string, digest it in place.          # If it's a hash string, digest it in place.
904          if ($fieldType eq 'hash-string') {          if ($fieldType eq 'hash-string') {
905              $fieldList->[$i] = md5_base64($fieldList->[$i]);              $fieldList->[$i] = $self->DigestKey($fieldList->[$i]);
906            }
907          }          }
908      }      }
909    
910    =head3 DigestKey
911    
912    C<< my $digested = $erdb->DigestKey($keyValue); >>
913    
914    Return the digested value of a symbolic key. The digested value can then be plugged into a
915    key-based search into a table with key-type hash-string.
916    
917    Currently the digesting process is independent of the database structure, but that may not
918    always be the case, so this is an instance method instead of a static method.
919    
920    =over 4
921    
922    =item keyValue
923    
924    Key value to digest.
925    
926    =item RETURN
927    
928    Digested value of the key.
929    
930    =back
931    
932    =cut
933    
934    sub DigestKey {
935        # Get the parameters.
936        my ($self, $keyValue) = @_;
937        # Compute the digest.
938        my $retVal = md5_base64($keyValue);
939        # Return the result.
940        return $retVal;
941  }  }
942    
943  =head3 CreateIndex  =head3 CreateIndex
# Line 764  Line 963 
963      for my $indexName (keys %{$indexHash}) {      for my $indexName (keys %{$indexHash}) {
964          my $indexData = $indexHash->{$indexName};          my $indexData = $indexHash->{$indexName};
965          # Get the index's field list.          # Get the index's field list.
966          my @fieldList = _FixNames(@{$indexData->{IndexFields}});          my @rawFields = @{$indexData->{IndexFields}};
967            # Get a hash of the relation's field types.
968            my %types = map { $_->{name} => $_->{type} } @{$relationData->{Fields}};
969            # We need to check for text fields. We need a append a length limitation for them. To do
970            # that, we need the relation's field list.
971            my $relFields = $relationData->{Fields};
972            for (my $i = 0; $i <= $#rawFields; $i++) {
973                # Get the field type.
974                my $field = $rawFields[$i];
975                my $type = $types{$field};
976                # Ask if it requires using prefix notation for the index.
977                my $mod = $TypeTable{$type}->{indexMod};
978                Trace("Field $field ($i) in $relationName has type $type and indexMod $mod.") if T(3);
979                if ($mod) {
980                    # Append the prefix length to the field name,
981                    $rawFields[$i] .= "($mod)";
982                }
983            }
984            my @fieldList = _FixNames(@rawFields);
985          my $flds = join(', ', @fieldList);          my $flds = join(', ', @fieldList);
986          # Get the index's uniqueness flag.          # Get the index's uniqueness flag.
987          my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
988          # Create the index.          # Create the index.
989          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
990                                      flds => $flds, unique => $unique);                                      flds => $flds, kind => $unique);
991          if ($rv) {          if ($rv) {
992              Trace("Index created: $indexName for $relationName ($flds)") if T(1);              Trace("Index created: $indexName for $relationName ($flds)") if T(1);
993          } else {          } else {
# Line 779  Line 996 
996      }      }
997  }  }
998    
999    =head3 GetSecondaryFields
1000    
1001    C<< my %fieldTuples = $erdb->GetSecondaryFields($entityName); >>
1002    
1003    This method will return a list of the name and type of each of the secondary
1004    fields for a specified entity. Secondary fields are stored in two-column tables
1005    in addition to the primary entity table. This enables the field to have no value
1006    or to have multiple values.
1007    
1008    =over 4
1009    
1010    =item entityName
1011    
1012    Name of the entity whose secondary fields are desired.
1013    
1014    =item RETURN
1015    
1016    Returns a hash mapping the field names to their field types.
1017    
1018    =back
1019    
1020    =cut
1021    
1022    sub GetSecondaryFields {
1023        # Get the parameters.
1024        my ($self, $entityName) = @_;
1025        # Declare the return variable.
1026        my %retVal = ();
1027        # Look for the entity.
1028        my $table = $self->GetFieldTable($entityName);
1029        # Loop through the fields, pulling out the secondaries.
1030        for my $field (sort keys %{$table}) {
1031            if ($table->{$field}->{relation} ne $entityName) {
1032                # Here we have a secondary field.
1033                $retVal{$field} = $table->{$field}->{type};
1034            }
1035        }
1036        # Return the result.
1037        return %retVal;
1038    }
1039    
1040    =head3 GetFieldRelationName
1041    
1042    C<< my $name = $erdb->GetFieldRelationName($objectName, $fieldName); >>
1043    
1044    Return the name of the relation containing a specified field.
1045    
1046    =over 4
1047    
1048    =item objectName
1049    
1050    Name of the entity or relationship containing the field.
1051    
1052    =item fieldName
1053    
1054    Name of the relevant field in that entity or relationship.
1055    
1056    =item RETURN
1057    
1058    Returns the name of the database relation containing the field, or C<undef> if
1059    the field does not exist.
1060    
1061    =back
1062    
1063    =cut
1064    
1065    sub GetFieldRelationName {
1066        # Get the parameters.
1067        my ($self, $objectName, $fieldName) = @_;
1068        # Declare the return variable.
1069        my $retVal;
1070        # Get the object field table.
1071        my $table = $self->GetFieldTable($objectName);
1072        # Only proceed if the field exists.
1073        if (exists $table->{$fieldName}) {
1074            # Determine the name of the relation that contains this field.
1075            $retVal = $table->{$fieldName}->{relation};
1076        }
1077        # Return the result.
1078        return $retVal;
1079    }
1080    
1081    =head3 DeleteValue
1082    
1083    C<< my $numDeleted = $erdb->DeleteValue($entityName, $id, $fieldName, $fieldValue); >>
1084    
1085    Delete secondary field values from the database. This method can be used to delete all
1086    values of a specified field for a particular entity instance, or only a single value.
1087    
1088    Secondary fields are stored in two-column relations separate from an entity's primary
1089    table, and as a result a secondary field can legitimately have no value or multiple
1090    values. Therefore, it makes sense to talk about deleting secondary fields where it
1091    would not make sense for primary fields.
1092    
1093    =over 4
1094    
1095    =item entityName
1096    
1097    Name of the entity from which the fields are to be deleted.
1098    
1099    =item id
1100    
1101    ID of the entity instance to be processed. If the instance is not found, this
1102    method will have no effect. If C<undef> is specified, all values for all of
1103    the entity instances will be deleted.
1104    
1105    =item fieldName
1106    
1107    Name of the field whose values are to be deleted.
1108    
1109    =item fieldValue (optional)
1110    
1111    Value to be deleted. If not specified, then all values of the specified field
1112    will be deleted for the entity instance. If specified, then only the values which
1113    match this parameter will be deleted.
1114    
1115    =item RETURN
1116    
1117    Returns the number of rows deleted.
1118    
1119    =back
1120    
1121    =cut
1122    
1123    sub DeleteValue {
1124        # Get the parameters.
1125        my ($self, $entityName, $id, $fieldName, $fieldValue) = @_;
1126        # Declare the return value.
1127        my $retVal = 0;
1128        # We need to set up an SQL command to do the deletion. First, we
1129        # find the name of the field's relation.
1130        my $table = $self->GetFieldTable($entityName);
1131        my $field = $table->{$fieldName};
1132        my $relation = $field->{relation};
1133        # Make sure this is a secondary field.
1134        if ($relation eq $entityName) {
1135            Confess("Cannot delete values of $fieldName for $entityName.");
1136        } else {
1137            # Set up the SQL command to delete all values.
1138            my $sql = "DELETE FROM $relation";
1139            # Build the filter.
1140            my @filters = ();
1141            my @parms = ();
1142            # Check for a filter by ID.
1143            if (defined $id) {
1144                push @filters, "id = ?";
1145                push @parms, $id;
1146            }
1147            # Check for a filter by value.
1148            if (defined $fieldValue) {
1149                push @filters, "$fieldName = ?";
1150                push @parms, $fieldValue;
1151            }
1152            # Append the filters to the command.
1153            if (@filters) {
1154                $sql .= " WHERE " . join(" AND ", @filters);
1155            }
1156            # Execute the command.
1157            my $dbh = $self->{_dbh};
1158            $retVal = $dbh->SQL($sql, 0, @parms);
1159        }
1160        # Return the result.
1161        return $retVal;
1162    }
1163    
1164  =head3 LoadTables  =head3 LoadTables
1165    
1166  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>
# Line 873  Line 1255 
1255      return sort keys %{$entityList};      return sort keys %{$entityList};
1256  }  }
1257    
1258    =head3 GetDataTypes
1259    
1260    C<< my %types = ERDB::GetDataTypes(); >>
1261    
1262    Return a table of ERDB data types. The table returned is a hash of hashes.
1263    The keys of the big hash are the datatypes. Each smaller hash has several
1264    values used to manage the data. The most interesting is the SQL type (key
1265    C<sqlType>) and the descriptive node (key C<notes>).
1266    
1267    Note that changing the values in the smaller hashes will seriously break
1268    things, so this data should be treated as read-only.
1269    
1270    =cut
1271    
1272    sub GetDataTypes {
1273        return %TypeTable;
1274    }
1275    
1276    
1277  =head3 IsEntity  =head3 IsEntity
1278    
1279  C<< my $flag = $erdb->IsEntity($entityName); >>  C<< my $flag = $erdb->IsEntity($entityName); >>
# Line 902  Line 1303 
1303    
1304  =head3 Get  =head3 Get
1305    
1306  C<< my $query = $erdb->Get(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  C<< my $query = $erdb->Get(\@objectNames, $filterClause, \@params); >>
1307    
1308  This method returns a query object for entities of a specified type using a specified filter.  This method returns a query object for entities of a specified type using a specified filter.
1309  The filter is a standard WHERE/ORDER BY clause with question marks as parameter markers and each  The filter is a standard WHERE/ORDER BY clause with question marks as parameter markers and each
# Line 910  Line 1311 
1311  following call requests all B<Genome> objects for the genus specified in the variable  following call requests all B<Genome> objects for the genus specified in the variable
1312  $genus.  $genus.
1313    
1314  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", [$genus]); >>
1315    
1316  The WHERE clause contains a single question mark, so there is a single additional  The WHERE clause contains a single question mark, so there is a single additional
1317  parameter representing the parameter value. It would also be possible to code  parameter representing the parameter value. It would also be possible to code
# Line 927  Line 1328 
1328  It is possible to specify multiple entity and relationship names in order to retrieve more than  It is possible to specify multiple entity and relationship names in order to retrieve more than
1329  one object's data at the same time, which allows highly complex joined queries. For example,  one object's data at the same time, which allows highly complex joined queries. For example,
1330    
1331  C<< $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]); >>
1332    
1333  If multiple names are specified, then the query processor will automatically determine a  If multiple names are specified, then the query processor will automatically determine a
1334  join path between the entities and relationships. The algorithm used is very simplistic.  join path between the entities and relationships. The algorithm used is very simplistic.
# Line 984  Line 1385 
1385    
1386  C<< "LIMIT 10" >>  C<< "LIMIT 10" >>
1387    
1388  =item param1, param2, ..., paramN  =item params
1389    
1390  Parameter values to be substituted into the filter clause.  Reference to a list of parameter values to be substituted into the filter clause.
1391    
1392  =item RETURN  =item RETURN
1393    
# Line 998  Line 1399 
1399    
1400  sub Get {  sub Get {
1401      # Get the parameters.      # Get the parameters.
1402      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $objectNames, $filterClause, $params) = @_;
1403      # Adjust the list of object names to account for multiple occurrences of the      # Process the SQL stuff.
1404      # same object. We start with a hash table keyed on object name that will      my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1405      # return the object suffix. The first time an object is encountered it will          $self->_SetupSQL($objectNames, $filterClause);
1406      # not be found in the hash. The next time the hash will map the object name      # Create the query.
1407      # to 2, then 3, and so forth.      my $command = "SELECT DISTINCT " . join(".*, ", @{$mappedNameListRef}) .
1408      my %objectHash = ();          ".* $suffix";
1409      # This list will contain the object names as they are to appear in the      my $sth = $self->_GetStatementHandle($command, $params);
1410      # FROM list.      # Now we create the relation map, which enables DBQuery to determine the order, name
1411      my @fromList = ();      # and mapped name for each object in the query.
1412      # This list contains the suffixed object name for each object. It is exactly      my @relationMap = ();
1413      # parallel to the list in the $objectNames parameter.      for my $mappedName (@{$mappedNameListRef}) {
1414      my @mappedNameList = ();          push @relationMap, [$mappedName, $mappedNameHashRef->{$mappedName}];
     # Finally, this hash translates from a mapped name to its original object name.  
     my %mappedNameHash = ();  
     # Now we create the lists. Note that for every single name we push something into  
     # @fromList and @mappedNameList. This insures that those two arrays are exactly  
     # parallel to $objectNames.  
     for my $objectName (@{$objectNames}) {  
         # Get the next suffix for this object.  
         my $suffix = $objectHash{$objectName};  
         if (! $suffix) {  
             # Here we are seeing the object for the first time. The object name  
             # is used as is.  
             push @mappedNameList, $objectName;  
             push @fromList, $objectName;  
             $mappedNameHash{$objectName} = $objectName;  
             # Denote the next suffix will be 2.  
             $objectHash{$objectName} = 2;  
         } else {  
             # Here we've seen the object before. We construct a new name using  
             # the suffix from the hash and update the hash.  
             my $mappedName = "$objectName$suffix";  
             $objectHash{$objectName} = $suffix + 1;  
             # The FROM list has the object name followed by the mapped name. This  
             # tells SQL it's still the same table, but we're using a different name  
             # for it to avoid confusion.  
             push @fromList, "$objectName $mappedName";  
             # The mapped-name list contains the real mapped name.  
             push @mappedNameList, $mappedName;  
             # Finally, enable us to get back from the mapped name to the object name.  
             $mappedNameHash{$mappedName} = $objectName;  
1415          }          }
1416        # Return the statement object.
1417        my $retVal = DBQuery::_new($self, $sth, \@relationMap);
1418        return $retVal;
1419      }      }
1420      # Construct the SELECT statement. The general pattern is  
1421      #  =head3 Search
1422      # SELECT name1.*, name2.*, ... nameN.* FROM name1, name2, ... nameN  
1423      #  C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>
1424      my $dbh = $self->{_dbh};  
1425      my $command = "SELECT DISTINCT " . join('.*, ', @mappedNameList) . ".* FROM " .  Perform a full text search with filtering. The search will be against a specified object
1426                  join(', ', @fromList);  in the object name list. That object will get an extra field containing the search
1427      # Check for a filter clause.  relevance. Note that except for the search expression, the parameters of this method are
1428      if ($filterClause) {  the same as those for L</Get> and follow the same rules.
1429          # Here we have one, so we convert its field names and add it to the query. First,  
1430          # We create a copy of the filter string we can work with.  =over 4
1431          my $filterString = $filterClause;  
1432          # Next, we sort the object names by length. This helps protect us from finding  =item searchExpression
1433          # object names inside other object names when we're doing our search and replace.  
1434          my @sortedNames = sort { length($b) - length($a) } @mappedNameList;  Boolean search expression for the text fields of the target object. The default mode for
1435          # We will also keep a list of conditions to add to the WHERE clause in order to link  a Boolean search expression is OR, but we want the default to be AND, so we will
1436          # entities and relationships as well as primary relations to secondary ones.  add a C<+> operator to each word with no other operator before it.
1437          my @joinWhere = ();  
1438          # The final preparatory step is to create a hash table of relation names. The  =item idx
1439          # table begins with the relation names already in the SELECT command. We may  
1440          # need to add relations later if there is filtering on a field in a secondary  Index in the I<$objectNames> list of the table to be searched in full-text mode.
1441          # relation. The secondary relations are the ones that contain multiply-  
1442          # occurring or optional fields.  =item objectNames
1443          my %fromNames = map { $_ => 1 } @sortedNames;  
1444          # We are ready to begin. We loop through the object names, replacing each  List containing the names of the entity and relationship objects to be retrieved.
1445          # object name's field references by the corresponding SQL field reference.  
1446          # Along the way, if we find a secondary relation, we will need to add it  =item filterClause
1447          # to the FROM clause.  
1448          for my $mappedName (@sortedNames) {  WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1449              # Get the length of the object name plus 2. This is the value we add to the  be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
1450              # size of the field name to determine the size of the field reference as a  specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
1451              # whole.  in the filter clause should be added to the parameter list as additional parameters. The
1452              my $nameLength = 2 + length $mappedName;  fields in a filter clause can come from primary entity relations, relationship relations,
1453              # Get the real object name for this mapped name.  or secondary entity relations; however, all of the entities and relationships involved must
1454              my $objectName = $mappedNameHash{$mappedName};  be included in the list of object names.
1455              Trace("Processing $mappedName for object $objectName.") if T(4);  
1456              # Get the object's field list.  =item params
1457              my $fieldList = $self->GetFieldTable($objectName);  
1458              # Find the field references for this object.  Reference to a list of parameter values to be substituted into the filter clause.
1459              while ($filterString =~ m/$mappedName\(([^)]*)\)/g) {  
1460                  # At this point, $1 contains the field name, and the current position  =item RETURN
1461                  # is set immediately after the final parenthesis. We pull out the name of  
1462                  # the field and the position and length of the field reference as a whole.  Returns a query object for the specified search.
1463                  my $fieldName = $1;  
1464                  my $len = $nameLength + length $fieldName;  =back
1465                  my $pos = pos($filterString) - $len;  
1466                  # Insure the field exists.  =cut
1467                  if (!exists $fieldList->{$fieldName}) {  
1468                      Confess("Field $fieldName not found for object $objectName.");  sub Search {
1469                  } else {      # Get the parameters.
1470                      Trace("Processing $fieldName at position $pos.") if T(4);      my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1471                      # Get the field's relation.      # Declare the return variable.
1472                      my $relationName = $fieldList->{$fieldName}->{relation};      my $retVal;
1473                      # Now we have a secondary relation. We need to insure it matches the      # Create a safety copy of the parameter list. Note we have to be careful to insure
1474                      # mapped name of the primary relation. First we peel off the suffix      # a parameter list exists before we copy it.
1475                      # from the mapped name.      my @myParams = ();
1476                      my $mappingSuffix = substr $mappedName, length($objectName);      if (defined $params) {
1477                      # Put the mapping suffix onto the relation name to get the          @myParams = @{$params};
1478                      # mapped relation name.      }
1479                      my $mappedRelationName = "$relationName$mappingSuffix";      # Get the first object's structure so we have access to the searchable fields.
1480                      # Insure the relation is in the FROM clause.      my $object1Name = $objectNames->[$idx];
1481                      if (!exists $fromNames{$mappedRelationName}) {      my $object1Structure = $self->_GetStructure($object1Name);
1482                          # Add the relation to the FROM clause.      # Get the field list.
1483                          if ($mappedRelationName eq $relationName) {      if (! exists $object1Structure->{searchFields}) {
1484                              # The name is un-mapped, so we add it without          Confess("No searchable index for $object1Name.");
                             # any frills.  
                             $command .= ", $relationName";  
                             push @joinWhere, "$objectName.id = $relationName.id";  
                         } else {  
                             # Here we have a mapping situation.  
                             $command .= ", $relationName $mappedRelationName";  
                             push @joinWhere, "$mappedRelationName.id = $mappedName.id";  
                         }  
                         # Denote we have this relation available for future fields.  
                         $fromNames{$mappedRelationName} = 1;  
                     }  
                     # Form an SQL field reference from the relation name and the field name.  
                     my $sqlReference = "$mappedRelationName." . _FixName($fieldName);  
                     # Put it into the filter string in place of the old value.  
                     substr($filterString, $pos, $len) = $sqlReference;  
                     # Reposition the search.  
                     pos $filterString = $pos + length $sqlReference;  
                 }  
             }  
         }  
         # The next step is to join the objects together. We only need to do this if there  
         # is more than one object in the object list. We start with the first object and  
         # run through the objects after it. Note also that we make a safety copy of the  
         # list before running through it.  
         my @mappedObjectList = @mappedNameList;  
         my $lastMappedObject = shift @mappedObjectList;  
         # Get the join table.  
         my $joinTable = $self->{_metaData}->{Joins};  
         # Loop through the object list.  
         for my $thisMappedObject (@mappedObjectList) {  
             # Look for a join using the real object names.  
             my $lastObject = $mappedNameHash{$lastMappedObject};  
             my $thisObject = $mappedNameHash{$thisMappedObject};  
             my $joinKey = "$lastObject/$thisObject";  
             if (!exists $joinTable->{$joinKey}) {  
                 # Here there's no join, so we throw an error.  
                 Confess("No join exists to connect from $lastMappedObject to $thisMappedObject.");  
1485              } else {              } else {
1486                  # Get the join clause.          # Get the field list.
1487                  my $unMappedJoin = $joinTable->{$joinKey};          my @fields = @{$object1Structure->{searchFields}};
1488                  # Fix the names.          # Clean the search expression.
1489                  $unMappedJoin =~ s/$lastObject/$lastMappedObject/;          my $actualKeywords = $self->CleanKeywords($searchExpression);
1490                  $unMappedJoin =~ s/$thisObject/$thisMappedObject/;          # Prefix a "+" to each uncontrolled word. This converts the default
1491                  push @joinWhere, $unMappedJoin;          # search mode from OR to AND.
1492                  # Save this object as the last object for the next iteration.          $actualKeywords =~ s/(^|\s)(\w)/$1\+$2/g;
1493                  $lastMappedObject = $thisMappedObject;          Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1494              }          # We need two match expressions, one for the filter clause and one in the
1495          }          # query itself. Both will use a parameter mark, so we need to push the
1496          # Now we need to handle the whole ORDER BY / LIMIT thing. The important part          # search expression onto the front of the parameter list twice.
1497          # here is we want the filter clause to be empty if there's no WHERE filter.          unshift @myParams, $actualKeywords, $actualKeywords;
1498          # We'll put the ORDER BY / LIMIT clauses in the following variable.          # Build the match expression.
1499          my $orderClause = "";          my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
1500          # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy          my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
1501          # operator so that we find the first occurrence of either verb.          # Process the SQL stuff.
1502          if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {          my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1503              # Here we have an ORDER BY or LIMIT verb. Split it off of the filter string.              $self->_SetupSQL($objectNames, $filterClause, $matchClause);
1504              my $pos = pos $filterString;          # Create the query. Note that the match clause is inserted at the front of
1505              $orderClause = $2 . substr($filterString, $pos);          # the select fields.
1506              $filterString = $1;          my $command = "SELECT DISTINCT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .
1507                ".* $suffix";
1508            my $sth = $self->_GetStatementHandle($command, \@myParams);
1509            # Now we create the relation map, which enables DBQuery to determine the order, name
1510            # and mapped name for each object in the query.
1511            my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
1512            # Return the statement object.
1513            $retVal = DBQuery::_new($self, $sth, \@relationMap, $object1Name);
1514          }          }
1515          # Add the filter and the join clauses (if any) to the SELECT command.      return $retVal;
         if ($filterString) {  
             Trace("Filter string is \"$filterString\".") if T(4);  
             push @joinWhere, "($filterString)";  
1516          }          }
1517          if (@joinWhere) {  
1518              $command .= " WHERE " . join(' AND ', @joinWhere);  =head3 GetFlat
1519    
1520    C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>
1521    
1522    This is a variation of L</GetAll> that asks for only a single field per record and
1523    returns a single flattened list.
1524    
1525    =over 4
1526    
1527    =item objectNames
1528    
1529    List containing the names of the entity and relationship objects to be retrieved.
1530    
1531    =item filterClause
1532    
1533    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1534    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
1535    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
1536    parameter list as additional parameters. The fields in a filter clause can come from primary
1537    entity relations, relationship relations, or secondary entity relations; however, all of the
1538    entities and relationships involved must be included in the list of object names.
1539    
1540    =item parameterList
1541    
1542    List of the parameters to be substituted in for the parameters marks in the filter clause.
1543    
1544    =item field
1545    
1546    Name of the field to be used to get the elements of the list returned.
1547    
1548    =item RETURN
1549    
1550    Returns a list of values.
1551    
1552    =back
1553    
1554    =cut
1555    #: Return Type @;
1556    sub GetFlat {
1557        # Get the parameters.
1558        my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
1559        # Construct the query.
1560        my $query = $self->Get($objectNames, $filterClause, $parameterList);
1561        # Create the result list.
1562        my @retVal = ();
1563        # Loop through the records, adding the field values found to the result list.
1564        while (my $row = $query->Fetch()) {
1565            push @retVal, $row->Value($field);
1566          }          }
1567          # Add the sort or limit clause (if any) to the SELECT command.      # Return the list created.
1568          if ($orderClause) {      return @retVal;
             $command .= " $orderClause";  
1569          }          }
1570    
1571    =head3 SpecialFields
1572    
1573    C<< my %specials = $erdb->SpecialFields($entityName); >>
1574    
1575    Return a hash mapping special fields in the specified entity to the value of their
1576    C<special> attribute. This enables the subclass to get access to the special field
1577    attributes without needed to plumb the internal ERDB data structures.
1578    
1579    =over 4
1580    
1581    =item entityName
1582    
1583    Name of the entity whose special fields are desired.
1584    
1585    =item RETURN
1586    
1587    Returns a hash. The keys of the hash are the special field names, and the values
1588    are the values from each special field's C<special> attribute.
1589    
1590    =back
1591    
1592    =cut
1593    
1594    sub SpecialFields {
1595        # Get the parameters.
1596        my ($self, $entityName) = @_;
1597        # Declare the return variable.
1598        my %retVal = ();
1599        # Find the entity's data structure.
1600        my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1601        # Loop through its fields, adding each special field to the return hash.
1602        my $fieldHash = $entityData->{Fields};
1603        for my $fieldName (keys %{$fieldHash}) {
1604            my $fieldData = $fieldHash->{$fieldName};
1605            if (exists $fieldData->{special}) {
1606                $retVal{$fieldName} = $fieldData->{special};
1607      }      }
     Trace("SQL query: $command") if T(SQL => 3);  
     Trace("PARMS: '" . (join "', '", @params) . "'") if (T(SQL => 4) && (@params > 0));  
     my $sth = $dbh->prepare_command($command);  
     # Execute it with the parameters bound in.  
     $sth->execute(@params) || Confess("SELECT error" . $sth->errstr());  
     # Now we create the relation map, which enables DBQuery to determine the order, name  
     # and mapped name for each object in the query.  
     my @relationMap = ();  
     for my $mappedName (@mappedNameList) {  
         push @relationMap, [$mappedName, $mappedNameHash{$mappedName}];  
1608      }      }
1609      # Return the statement object.      # Return the result.
1610      my $retVal = DBQuery::_new($self, $sth, \@relationMap);      return %retVal;
     return $retVal;  
1611  }  }
1612    
1613  =head3 Delete  =head3 Delete
# Line 1252  Line 1666 
1666      # This final hash is used to remember what work still needs to be done. We push paths      # This final hash is used to remember what work still needs to be done. We push paths
1667      # onto the list, then pop them off to extend the paths. We prime it with the starting      # onto the list, then pop them off to extend the paths. We prime it with the starting
1668      # point. Note that we will work hard to insure that the last item on a path in the      # point. Note that we will work hard to insure that the last item on a path in the
1669      # TODO list is always an entity.      # to-do list is always an entity.
1670      my @todoList = ([$entityName]);      my @todoList = ([$entityName]);
1671      while (@todoList) {      while (@todoList) {
1672          # Get the current path.          # Get the current path.
# Line 1364  Line 1778 
1778      return $retVal;      return $retVal;
1779  }  }
1780    
1781  =head3 GetList  =head3 SortNeeded
   
 C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  
   
 Return a list of object descriptors for the specified objects as determined by the  
 specified filter clause.  
   
 This method is essentially the same as L</Get> except it returns a list of objects rather  
 than a query object that can be used to get the results one record at a time.  
1782    
1783  =over 4  C<< my $parms = $erdb->SortNeeded($relationName); >>
1784    
1785  =item objectNames  Return the pipe command for the sort that should be applied to the specified
1786    relation when creating the load file.
1787    
1788  List containing the names of the entity and relationship objects to be retrieved.  For example, if the load file should be sorted ascending by the first
1789    field, this method would return
1790    
1791  =item filterClause      sort -k1 -t"\t"
1792    
1793  WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  If the first field is numeric, the method would return
 be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be  
 specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified  
 in the filter clause should be added to the parameter list as additional parameters. The  
 fields in a filter clause can come from primary entity relations, relationship relations,  
 or secondary entity relations; however, all of the entities and relationships involved must  
 be included in the list of object names.  
1794    
1795  The filter clause can also specify a sort order. To do this, simply follow the filter string      sort -k1n -t"\t"
 with an ORDER BY clause. For example, the following filter string gets all genomes for a  
 particular genus and sorts them by species name.  
1796    
1797  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>  Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate
1798    keys using a sort.
1799    
1800  The rules for field references in a sort order are the same as those for field references in the  =over 4
 filter clause in general; however, odd things may happen if a sort field is from a secondary  
 relation.  
1801    
1802  =item param1, param2, ..., paramN  =item relationName
1803    
1804  Parameter values to be substituted into the filter clause.  Name of the relation to be examined.
1805    
1806  =item RETURN  =item
1807    
1808  Returns a list of B<DBObject>s that satisfy the query conditions.  Returns the sort command to use for sorting the relation, suitable for piping.
1809    
1810  =back  =back
1811    
1812  =cut  =cut
1813  #: Return Type @%  #: Return Type $;
1814  sub GetList {  sub SortNeeded {
1815      # Get the parameters.      # Get the parameters.
1816      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $relationName) = @_;
1817        # Declare a descriptor to hold the names of the key fields.
1818        my @keyNames = ();
1819        # Get the relation structure.
1820        my $relationData = $self->_FindRelation($relationName);
1821        # Find out if the relation is a primary entity relation,
1822        # a relationship relation, or a secondary entity relation.
1823        my $entityTable = $self->{_metaData}->{Entities};
1824        my $relationshipTable = $self->{_metaData}->{Relationships};
1825        if (exists $entityTable->{$relationName}) {
1826            # Here we have a primary entity relation.
1827            push @keyNames, "id";
1828        } elsif (exists $relationshipTable->{$relationName}) {
1829            # Here we have a relationship. We sort using the FROM index.
1830            my $relationshipData = $relationshipTable->{$relationName};
1831            my $index = $relationData->{Indexes}->{idxFrom};
1832            push @keyNames, @{$index->{IndexFields}};
1833        } else {
1834            # Here we have a secondary entity relation, so we have a sort on the ID field.
1835            push @keyNames, "id";
1836        }
1837        # Now we parse the key names into sort parameters. First, we prime the return
1838        # string.
1839        my $retVal = "sort -t\"\t\" ";
1840        # Get the relation's field list.
1841        my @fields = @{$relationData->{Fields}};
1842        # Loop through the keys.
1843        for my $keyData (@keyNames) {
1844            # Get the key and the ordering.
1845            my ($keyName, $ordering);
1846            if ($keyData =~ /^([^ ]+) DESC/) {
1847                ($keyName, $ordering) = ($1, "descending");
1848            } else {
1849                ($keyName, $ordering) = ($keyData, "ascending");
1850            }
1851            # Find the key's position and type.
1852            my $fieldSpec;
1853            for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {
1854                my $thisField = $fields[$i];
1855                if ($thisField->{name} eq $keyName) {
1856                    # Get the sort modifier for this field type. The modifier
1857                    # decides whether we're using a character, numeric, or
1858                    # floating-point sort.
1859                    my $modifier = $TypeTable{$thisField->{type}}->{sort};
1860                    # If the index is descending for this field, denote we want
1861                    # to reverse the sort order on this field.
1862                    if ($ordering eq 'descending') {
1863                        $modifier .= "r";
1864                    }
1865                    # Store the position and modifier into the field spec, which
1866                    # will stop the inner loop. Note that the field number is
1867                    # 1-based in the sort command, so we have to increment the
1868                    # index.
1869                    $fieldSpec = ($i + 1) . $modifier;
1870                }
1871            }
1872            # Add this field to the sort command.
1873            $retVal .= " -k$fieldSpec";
1874        }
1875        # Return the result.
1876        return $retVal;
1877    }
1878    
1879    =head3 GetList
1880    
1881    C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>
1882    
1883    Return a list of object descriptors for the specified objects as determined by the
1884    specified filter clause.
1885    
1886    This method is essentially the same as L</Get> except it returns a list of objects rather
1887    than a query object that can be used to get the results one record at a time.
1888    
1889    =over 4
1890    
1891    =item objectNames
1892    
1893    List containing the names of the entity and relationship objects to be retrieved.
1894    
1895    =item filterClause
1896    
1897    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1898    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
1899    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
1900    in the filter clause should be added to the parameter list as additional parameters. The
1901    fields in a filter clause can come from primary entity relations, relationship relations,
1902    or secondary entity relations; however, all of the entities and relationships involved must
1903    be included in the list of object names.
1904    
1905    The filter clause can also specify a sort order. To do this, simply follow the filter string
1906    with an ORDER BY clause. For example, the following filter string gets all genomes for a
1907    particular genus and sorts them by species name.
1908    
1909    C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
1910    
1911    The rules for field references in a sort order are the same as those for field references in the
1912    filter clause in general; however, odd things may happen if a sort field is from a secondary
1913    relation.
1914    
1915    =item params
1916    
1917    Reference to a list of parameter values to be substituted into the filter clause.
1918    
1919    =item RETURN
1920    
1921    Returns a list of B<DBObject>s that satisfy the query conditions.
1922    
1923    =back
1924    
1925    =cut
1926    #: Return Type @%
1927    sub GetList {
1928        # Get the parameters.
1929        my ($self, $objectNames, $filterClause, $params) = @_;
1930      # Declare the return variable.      # Declare the return variable.
1931      my @retVal = ();      my @retVal = ();
1932      # Perform the query.      # Perform the query.
1933      my $query = $self->Get($objectNames, $filterClause, @params);      my $query = $self->Get($objectNames, $filterClause, $params);
1934      # Loop through the results.      # Loop through the results.
1935      while (my $object = $query->Fetch) {      while (my $object = $query->Fetch) {
1936          push @retVal, $object;          push @retVal, $object;
# Line 1427  Line 1939 
1939      return @retVal;      return @retVal;
1940  }  }
1941    
1942    =head3 GetCount
1943    
1944    C<< my $count = $erdb->GetCount(\@objectNames, $filter, \@params); >>
1945    
1946    Return the number of rows found by a specified query. This method would
1947    normally be used to count the records in a single table. For example, in a
1948    genetics database
1949    
1950        my $count = $erdb->GetCount(['Genome'], 'Genome(genus-species) LIKE ?', ['homo %']);
1951    
1952    would return the number of genomes for the genus I<homo>. It is conceivable, however,
1953    to use it to return records based on a join. For example,
1954    
1955        my $count = $erdb->GetCount(['HasFeature', 'Genome'], 'Genome(genus-species) LIKE ?',
1956                                    ['homo %']);
1957    
1958    would return the number of features for genomes in the genus I<homo>. Note that
1959    only the rows from the first table are counted. If the above command were
1960    
1961        my $count = $erdb->GetCount(['Genome', 'Feature'], 'Genome(genus-species) LIKE ?',
1962                                    ['homo %']);
1963    
1964    it would return the number of genomes, not the number of genome/feature pairs.
1965    
1966    =over 4
1967    
1968    =item objectNames
1969    
1970    Reference to a list of the objects (entities and relationships) included in the
1971    query.
1972    
1973    =item filter
1974    
1975    A filter clause for restricting the query. The rules are the same as for the L</Get>
1976    method.
1977    
1978    =item params
1979    
1980    Reference to a list of the parameter values to be substituted for the parameter marks
1981    in the filter.
1982    
1983    =item RETURN
1984    
1985    Returns a count of the number of records in the first table that would satisfy
1986    the query.
1987    
1988    =back
1989    
1990    =cut
1991    
1992    sub GetCount {
1993        # Get the parameters.
1994        my ($self, $objectNames, $filter, $params) = @_;
1995        # Insure the params argument is an array reference if the caller left it off.
1996        if (! defined($params)) {
1997            $params = [];
1998        }
1999        # Declare the return variable.
2000        my $retVal;
2001        # Find out if we're counting an entity or a relationship.
2002        my $countedField;
2003        if ($self->IsEntity($objectNames->[0])) {
2004            $countedField = "id";
2005        } else {
2006            # For a relationship we count the to-link because it's usually more
2007            # numerous. Note we're automatically converting to the SQL form
2008            # of the field name (to_link vs. to-link).
2009            $countedField = "to_link";
2010        }
2011        # Create the SQL command suffix to get the desired records.
2012        my ($suffix, $mappedNameListRef, $mappedNameHashRef) = $self->_SetupSQL($objectNames,
2013                                                                                $filter);
2014        # Prefix it with text telling it we want a record count.
2015        my $firstObject = $mappedNameListRef->[0];
2016        my $command = "SELECT COUNT($firstObject.$countedField) $suffix";
2017        # Prepare and execute the command.
2018        my $sth = $self->_GetStatementHandle($command, $params);
2019        # Get the count value.
2020        ($retVal) = $sth->fetchrow_array();
2021        # Check for a problem.
2022        if (! defined($retVal)) {
2023            if ($sth->err) {
2024                # Here we had an SQL error.
2025                Confess("Error retrieving row count: " . $sth->errstr());
2026            } else {
2027                # Here we have no result.
2028                Confess("No result attempting to retrieve row count.");
2029            }
2030        }
2031        # Return the result.
2032        return $retVal;
2033    }
2034    
2035  =head3 ComputeObjectSentence  =head3 ComputeObjectSentence
2036    
2037  C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>  C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>
# Line 1504  Line 2109 
2109      }      }
2110  }  }
2111    
2112    =head3 InsertValue
2113    
2114    C<< $erdb->InsertValue($entityID, $fieldName, $value); >>
2115    
2116    This method will insert a new value into the database. The value must be one
2117    associated with a secondary relation, since primary values cannot be inserted:
2118    they occur exactly once. Secondary values, on the other hand, can be missing
2119    or multiply-occurring.
2120    
2121    =over 4
2122    
2123    =item entityID
2124    
2125    ID of the object that is to receive the new value.
2126    
2127    =item fieldName
2128    
2129    Field name for the new value-- this includes the entity name, since
2130    field names are of the format I<objectName>C<(>I<fieldName>C<)>.
2131    
2132    =item value
2133    
2134    New value to be put in the field.
2135    
2136    =back
2137    
2138    =cut
2139    
2140    sub InsertValue {
2141        # Get the parameters.
2142        my ($self, $entityID, $fieldName, $value) = @_;
2143        # Parse the entity name and the real field name.
2144        if ($fieldName =~ /^([^(]+)\(([^)]+)\)/) {
2145            my $entityName = $1;
2146            my $fieldTitle = $2;
2147            # Get its descriptor.
2148            if (!$self->IsEntity($entityName)) {
2149                Confess("$entityName is not a valid entity.");
2150            } else {
2151                my $entityData = $self->{_metaData}->{Entities}->{$entityName};
2152                # Find the relation containing this field.
2153                my $fieldHash = $entityData->{Fields};
2154                if (! exists $fieldHash->{$fieldTitle}) {
2155                    Confess("$fieldTitle not found in $entityName.");
2156                } else {
2157                    my $relation = $fieldHash->{$fieldTitle}->{relation};
2158                    if ($relation eq $entityName) {
2159                        Confess("Cannot do InsertValue on primary field $fieldTitle of $entityName.");
2160                    } else {
2161                        # Now we can create an INSERT statement.
2162                        my $dbh = $self->{_dbh};
2163                        my $fixedName = _FixName($fieldTitle);
2164                        my $statement = "INSERT INTO $relation (id, $fixedName) VALUES(?, ?)";
2165                        # Execute the command.
2166                        $dbh->SQL($statement, 0, $entityID, $value);
2167                    }
2168                }
2169            }
2170        } else {
2171            Confess("$fieldName is not a valid field name.");
2172        }
2173    }
2174    
2175  =head3 InsertObject  =head3 InsertObject
2176    
2177  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>
# Line 1520  Line 2188 
2188  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
2189  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>.
2190    
2191  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'}); >>
2192    
2193  =over 4  =over 4
2194    
# Line 1712  Line 2380 
2380      };      };
2381      if (!defined $rv) {      if (!defined $rv) {
2382          $retVal->AddMessage($@) if ($@);          $retVal->AddMessage($@) if ($@);
2383          $retVal->AddMessage("Table load failed for $relationName using $fileName.");          $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2384          Trace("Table load failed for $relationName.") if T(1);          Trace("Table load failed for $relationName.") if T(1);
2385      } else {      } else {
2386          # Here we successfully loaded the table.          # Here we successfully loaded the table.
# Line 1720  Line 2388 
2388          my $size = -s $fileName;          my $size = -s $fileName;
2389          Trace("$size bytes loaded into $relationName.") if T(2);          Trace("$size bytes loaded into $relationName.") if T(2);
2390          # If we're rebuilding, we need to create the table indexes.          # If we're rebuilding, we need to create the table indexes.
2391          if ($truncateFlag && ! $dbh->{_preIndex}) {          if ($truncateFlag) {
2392                # Indexes are created here for PostGres. For PostGres, indexes are
2393                # best built at the end. For MySQL, the reverse is true.
2394                if (! $dbh->{_preIndex}) {
2395              eval {              eval {
2396                  $self->CreateIndex($relationName);                  $self->CreateIndex($relationName);
2397              };              };
# Line 1728  Line 2399 
2399                  $retVal->AddMessage($@);                  $retVal->AddMessage($@);
2400              }              }
2401          }          }
2402                # The full-text index (if any) is always built last, even for MySQL.
2403                # First we need to see if this table has a full-text index. Only
2404                # primary relations are allowed that privilege.
2405                if ($self->_IsPrimary($relationName)) {
2406                    # Get the relation's entity/relationship structure.
2407                    my $structure = $self->_GetStructure($relationName);
2408                    # Check for a searchable fields list.
2409                    if (exists $structure->{searchFields}) {
2410                        # Here we know that we need to create a full-text search index.
2411                        # Get an SQL-formatted field name list.
2412                        my $fields = join(", ", $self->_FixNames(@{$structure->{searchFields}}));
2413                        # Create the index.
2414                        $dbh->create_index(tbl => $relationName, idx => "search_idx",
2415                                           flds => $fields, kind => 'fulltext');
2416                    }
2417                }
2418            }
2419      }      }
2420      # Analyze the table to improve performance.      # Analyze the table to improve performance.
2421        Trace("Analyzing and compacting $relationName.") if T(3);
2422      $dbh->vacuum_it($relationName);      $dbh->vacuum_it($relationName);
2423        Trace("$relationName load completed.") if T(3);
2424      # Return the statistics.      # Return the statistics.
2425      return $retVal;      return $retVal;
2426  }  }
2427    
2428  =head3 GenerateEntity  =head3 DropRelation
2429    
2430  C<< my $fieldHash = $erdb->GenerateEntity($id, $type, \%values); >>  C<< $erdb->DropRelation($relationName); >>
2431    
2432  Generate the data for a new entity instance. This method creates a field hash suitable for  Physically drop a relation from the database.
 passing as a parameter to L</InsertObject>. The ID is specified by the callr, but the rest  
 of the fields are generated using information in the database schema.  
   
 Each data type has a default algorithm for generating random test data. This can be overridden  
 by including a B<DataGen> element in the field. If this happens, the content of the element is  
 executed as a PERL program in the context of this module. The element may make use of a C<$this>  
 variable which contains the field hash as it has been built up to the current point. If any  
 fields are dependent on other fields, the C<pass> attribute can be used to control the order  
 in which the fields are generated. A field with a high data pass number will be generated after  
 a field with a lower one. If any external values are needed, they should be passed in via the  
 optional third parameter, which will be available to the data generation script under the name  
 C<$value>. Several useful utility methods are provided for generating random values, including  
 L</IntGen>, L</StringGen>, L</FloatGen>, and L</DateGen>. Note that dates are stored and generated  
 in the form of a timestamp number rather than a string.  
2433    
2434  =over 4  =over 4
2435    
2436  =item id  =item relationName
   
 ID to assign to the new entity.  
   
 =item type  
   
 Type name for the new entity.  
   
 =item values  
2437    
2438  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
2439    no effect.
2440    
2441  =back  =back
2442    
2443  =cut  =cut
2444    
2445  sub GenerateEntity {  sub DropRelation {
2446      # Get the parameters.      # Get the parameters.
2447      my ($self, $id, $type, $values) = @_;      my ($self, $relationName) = @_;
2448      # Create the return hash.      # Get the database handle.
2449      my $this = { id => $id };      my $dbh = $self->{_dbh};
2450      # Get the metadata structure.      # Drop the relation. The method used here has no effect if the relation
2451      my $metadata = $self->{_metaData};      # does not exist.
2452      # Get this entity's list of fields.      Trace("Invoking DB Kernel to drop $relationName.") if T(3);
2453      if (!exists $metadata->{Entities}->{$type}) {      $dbh->drop_table(tbl => $relationName);
         Confess("Unrecognized entity type $type in GenerateEntity.");  
     } else {  
         my $entity = $metadata->{Entities}->{$type};  
         my $fields = $entity->{Fields};  
         # Generate data from the fields.  
         _GenerateFields($this, $fields, $type, $values);  
     }  
     # Return the hash created.  
     return $this;  
2454  }  }
2455    
2456  =head3 GetEntity  =head3 GetEntity
# Line 1822  Line 2482 
2482      # Get the parameters.      # Get the parameters.
2483      my ($self, $entityType, $ID) = @_;      my ($self, $entityType, $ID) = @_;
2484      # Create a query.      # Create a query.
2485      my $query = $self->Get([$entityType], "$entityType(id) = ?", $ID);      my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);
2486      # Get the first (and only) object.      # Get the first (and only) object.
2487      my $retVal = $query->Fetch();      my $retVal = $query->Fetch();
2488      # Return the result.      # Return the result.
2489      return $retVal;      return $retVal;
2490  }  }
2491    
2492    =head3 GetChoices
2493    
2494    C<< my @values = $erdb->GetChoices($entityName, $fieldName); >>
2495    
2496    Return a list of all the values for the specified field that are represented in the
2497    specified entity.
2498    
2499    Note that if the field is not indexed, then this will be a very slow operation.
2500    
2501    =over 4
2502    
2503    =item entityName
2504    
2505    Name of an entity in the database.
2506    
2507    =item fieldName
2508    
2509    Name of a field belonging to the entity. This is a raw field name without
2510    the standard parenthesized notation used in most calls.
2511    
2512    =item RETURN
2513    
2514    Returns a list of the distinct values for the specified field in the database.
2515    
2516    =back
2517    
2518    =cut
2519    
2520    sub GetChoices {
2521        # Get the parameters.
2522        my ($self, $entityName, $fieldName) = @_;
2523        # Declare the return variable.
2524        my @retVal;
2525        # Get the entity data structure.
2526        my $entityData = $self->_GetStructure($entityName);
2527        # Get the field.
2528        my $fieldHash = $entityData->{Fields};
2529        if (! exists $fieldHash->{$fieldName}) {
2530            Confess("$fieldName not found in $entityName.");
2531        } else {
2532            # Get the name of the relation containing the field.
2533            my $relation = $fieldHash->{$fieldName}->{relation};
2534            # Fix up the field name.
2535            my $realName = _FixName($fieldName);
2536            # Get the database handle.
2537            my $dbh = $self->{_dbh};
2538            # Query the database.
2539            my $results = $dbh->SQL("SELECT DISTINCT $realName FROM $relation");
2540            # Clean the results. They are stored as a list of lists, and we just want the one list.
2541            @retVal = sort map { $_->[0] } @{$results};
2542        }
2543        # Return the result.
2544        return @retVal;
2545    }
2546    
2547  =head3 GetEntityValues  =head3 GetEntityValues
2548    
2549  C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>  C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>
2550    
2551  Return a list of values from a specified entity instance.  Return a list of values from a specified entity instance. If the entity instance
2552    does not exist, an empty list is returned.
2553    
2554  =over 4  =over 4
2555    
# Line 1935  Line 2651 
2651      # list is a scalar we convert it into a singleton list.      # list is a scalar we convert it into a singleton list.
2652      my @parmList = ();      my @parmList = ();
2653      if (ref $parameterList eq "ARRAY") {      if (ref $parameterList eq "ARRAY") {
2654            Trace("GetAll parm list is an array.") if T(4);
2655          @parmList = @{$parameterList};          @parmList = @{$parameterList};
2656      } else {      } else {
2657            Trace("GetAll parm list is a scalar: $parameterList.") if T(4);
2658          push @parmList, $parameterList;          push @parmList, $parameterList;
2659      }      }
2660      # Insure the counter has a value.      # Insure the counter has a value.
# Line 1948  Line 2666 
2666          $filterClause .= " LIMIT $count";          $filterClause .= " LIMIT $count";
2667      }      }
2668      # Create the query.      # Create the query.
2669      my $query = $self->Get($objectNames, $filterClause, @parmList);      my $query = $self->Get($objectNames, $filterClause, \@parmList);
2670      # Set up a counter of the number of records read.      # Set up a counter of the number of records read.
2671      my $fetched = 0;      my $fetched = 0;
2672      # Loop through the records returned, extracting the fields. Note that if the      # Loop through the records returned, extracting the fields. Note that if the
# Line 1959  Line 2677 
2677          push @retVal, \@rowData;          push @retVal, \@rowData;
2678          $fetched++;          $fetched++;
2679      }      }
2680        Trace("$fetched rows returned in GetAll.") if T(SQL => 4);
2681      # Return the resulting list.      # Return the resulting list.
2682      return @retVal;      return @retVal;
2683  }  }
2684    
2685    =head3 Exists
2686    
2687    C<< my $found = $sprout->Exists($entityName, $entityID); >>
2688    
2689    Return TRUE if an entity exists, else FALSE.
2690    
2691    =over 4
2692    
2693    =item entityName
2694    
2695    Name of the entity type (e.g. C<Feature>) relevant to the existence check.
2696    
2697    =item entityID
2698    
2699    ID of the entity instance whose existence is to be checked.
2700    
2701    =item RETURN
2702    
2703    Returns TRUE if the entity instance exists, else FALSE.
2704    
2705    =back
2706    
2707    =cut
2708    #: Return Type $;
2709    sub Exists {
2710        # Get the parameters.
2711        my ($self, $entityName, $entityID) = @_;
2712        # Check for the entity instance.
2713        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
2714        my $testInstance = $self->GetEntity($entityName, $entityID);
2715        # Return an existence indicator.
2716        my $retVal = ($testInstance ? 1 : 0);
2717        return $retVal;
2718    }
2719    
2720  =head3 EstimateRowSize  =head3 EstimateRowSize
2721    
2722  C<< my $rowSize = $erdb->EstimateRowSize($relName); >>  C<< my $rowSize = $erdb->EstimateRowSize($relName); >>
# Line 2030  Line 2784 
2784      return $objectData->{Fields};      return $objectData->{Fields};
2785  }  }
2786    
2787  =head3 GetUsefulCrossValues  =head3 SplitKeywords
2788    
2789  C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>  C<< my @keywords = ERDB::SplitKeywords($keywordString); >>
2790    
2791  Return a list of the useful attributes that would be returned by a B<Cross> call  This method returns a list of the positive keywords in the specified
2792  from an entity of the source entity type through the specified relationship. This  keyword string. All of the operators will have been stripped off,
2793  means it will return the fields of the target entity type and the intersection data  and if the keyword is preceded by a minus operator (C<->), it will
2794  fields in the relationship. Only primary table fields are returned. In other words,  not be in the list returned. The idea here is to get a list of the
2795  the field names returned will be for fields where there is always one and only one  keywords the user wants to see. The list will be processed to remove
2796  value.  duplicates.
2797    
2798  =over 4  It is possible to create a string that confuses this method. For example
2799    
2800  =item sourceEntity      frog toad -frog
2801    
2802  Name of the entity from which the relationship crossing will start.  would return both C<frog> and C<toad>. If this is a problem we can deal
2803    with it later.
2804    
2805  =item relationship  =over 4
2806    
2807  Name of the relationship being crossed.  =item keywordString
2808    
2809    The keyword string to be parsed.
2810    
2811  =item RETURN  =item RETURN
2812    
2813  Returns a list of field names in Sprout field format (I<objectName>C<(>I<fieldName>C<)>.  Returns a list of the words in the keyword string the user wants to
2814    see.
2815    
2816  =back  =back
2817    
2818  =cut  =cut
2819  #: Return Type @;  
2820  sub GetUsefulCrossValues {  sub SplitKeywords {
2821      # Get the parameters.      # Get the parameters.
2822      my ($self, $sourceEntity, $relationship) = @_;      my ($keywordString) = @_;
2823      # Declare the return variable.      # Make a safety copy of the string. (This helps during debugging.)
2824      my @retVal = ();      my $workString = $keywordString;
2825      # Determine the target entity for the relationship. This is whichever entity is not      # Convert operators we don't care about to spaces.
2826      # the source entity. So, if the source entity is the FROM, we'll get the name of      $workString =~ tr/+"()<>/ /;
2827      # the TO, and vice versa.      # Split the rest of the string along space boundaries. Note that we
2828      my $relStructure = $self->_GetStructure($relationship);      # eliminate any words that are zero length or begin with a minus sign.
2829      my $targetEntityType = ($relStructure->{from} eq $sourceEntity ? "to" : "from");      my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
2830      my $targetEntity = $relStructure->{$targetEntityType};      # Use a hash to remove duplicates.
2831      # Get the field table for the entity.      my %words = map { $_ => 1 } @wordList;
     my $entityFields = $self->GetFieldTable($targetEntity);  
     # The field table is a hash. The hash key is the field name. The hash value is a structure.  
     # For the entity fields, the key aspect of the target structure is that the {relation} value  
     # must match the entity name.  
     my @fieldList = map { "$targetEntity($_)" } grep { $entityFields->{$_}->{relation} eq $targetEntity }  
                         keys %{$entityFields};  
     # Push the fields found onto the return variable.  
     push @retVal, sort @fieldList;  
     # Get the field table for the relationship.  
     my $relationshipFields = $self->GetFieldTable($relationship);  
     # Here we have a different rule. We want all the fields other than "from-link" and "to-link".  
     # This may end up being an empty set.  
     my @fieldList2 = map { "$relationship($_)" } grep { $_ ne "from-link" && $_ ne "to-link" }  
                         keys %{$relationshipFields};  
     # Push these onto the return list.  
     push @retVal, sort @fieldList2;  
2832      # Return the result.      # Return the result.
2833      return @retVal;      return sort keys %words;
2834  }  }
2835    
2836  =head2 Internal Utility Methods  =head3 ValidateFieldName
2837    
2838  =head3 GetLoadStats  C<< my $okFlag = ERDB::ValidateFieldName($fieldName); >>
2839    
2840  Return a blank statistics object for use by the load methods.  Return TRUE if the specified field name is valid, else FALSE. Valid field names must
2841    be hyphenated words subject to certain restrictions.
2842    
2843  This is a static method.  =over 4
2844    
2845  =cut  =item fieldName
2846    
2847  sub _GetLoadStats{  Field name to be validated.
2848      return Stats->new();  
2849    =item RETURN
2850    
2851    Returns TRUE if the field name is valid, else FALSE.
2852    
2853    =back
2854    
2855    =cut
2856    
2857    sub ValidateFieldName {
2858        # Get the parameters.
2859        my ($fieldName) = @_;
2860        # Declare the return variable. The field name is valid until we hear
2861        # differently.
2862        my $retVal = 1;
2863        # Look for bad stuff in the name.
2864        if ($fieldName =~ /--/) {
2865            # Here we have a doubled minus sign.
2866            Trace("Field name $fieldName has a doubled hyphen.") if T(1);
2867            $retVal = 0;
2868        } elsif ($fieldName !~ /^[A-Za-z]/) {
2869            # Here the field name is missing the initial letter.
2870            Trace("Field name $fieldName does not begin with a letter.") if T(1);
2871            $retVal = 0;
2872        } else {
2873            # Strip out the minus signs. Everything remaining must be a letter,
2874            # underscore, or digit.
2875            my $strippedName = $fieldName;
2876            $strippedName =~ s/-//g;
2877            if ($strippedName !~ /^(\w|\d)+$/) {
2878                Trace("Field name $fieldName contains illegal characters.") if T(1);
2879                $retVal = 0;
2880            }
2881        }
2882        # Return the result.
2883        return $retVal;
2884  }  }
2885    
2886  =head3 GenerateFields  =head3 ReadMetaXML
2887    
2888  Generate field values from a field structure and store in a specified table. The field names  C<< my $rawMetaData = ERDB::ReadDBD($fileName); >>
 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.  
2889    
2890  This is a static method.  This method reads a raw database definition XML file and returns it.
2891    Normally, the metadata used by the ERDB system has been processed and
2892    modified to make it easier to load and retrieve the data; however,
2893    this method can be used to get the data in its raw form.
2894    
2895  =over 4  =over 4
2896    
2897  =item this  =item fileName
2898    
2899  Hash table into which the field values should be placed.  Name of the XML file to read.
2900    
2901  =item fields  =item RETURN
2902    
2903  Field structure from which the field descriptors should be taken.  Returns a hash reference containing the raw XML data from the specified file.
2904    
2905  =item type  =back
2906    
2907    =cut
2908    
2909    sub ReadMetaXML {
2910        # Get the parameters.
2911        my ($fileName) = @_;
2912        # Read the XML.
2913        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
2914        Trace("XML metadata loaded from file $fileName.") if T(1);
2915        # Return the result.
2916        return $retVal;
2917    }
2918    
2919    =head3 GetEntityFieldHash
2920    
2921    C<< my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName); >>
2922    
2923    Get the field hash of the named entity in the specified raw XML structure.
2924    The field hash may not exist, in which case we need to create it.
2925    
2926    =over 4
2927    
2928    =item structure
2929    
2930    Raw XML structure defininng the database. This is not the run-time XML used by
2931    an ERDB object, since that has all sorts of optimizations built-in.
2932    
2933    =item entityName
2934    
2935    Name of the entity whose field structure is desired.
2936    
2937    =item RETURN
2938    
2939    Returns the field hash used to define the entity's fields.
2940    
2941    =back
2942    
2943    =cut
2944    
2945    sub GetEntityFieldHash {
2946        # Get the parameters.
2947        my ($structure, $entityName) = @_;
2948        # Get the entity structure.
2949        my $entityData = $structure->{Entities}->{$entityName};
2950        # Look for a field structure.
2951        my $retVal = $entityData->{Fields};
2952        # If it doesn't exist, create it.
2953        if (! defined($retVal)) {
2954            $entityData->{Fields} = {};
2955            $retVal = $entityData->{Fields};
2956        }
2957        # Return the result.
2958        return $retVal;
2959    }
2960    
2961    =head3 WriteMetaXML
2962    
2963    C<< ERDB::WriteMetaXML($structure, $fileName); >>
2964    
2965    Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
2966    used to update the database definition. It must be used with care, however, since it
2967    will only work on a raw structure, not on the processed structure created by an ERDB
2968    constructor.
2969    
2970    =over 4
2971    
2972    =item structure
2973    
2974    XML structure to be written to the file.
2975    
2976    =item fileName
2977    
2978    Name of the output file to which the updated XML should be stored.
2979    
2980    =back
2981    
2982    =cut
2983    
2984    sub WriteMetaXML {
2985        # Get the parameters.
2986        my ($structure, $fileName) = @_;
2987        # Compute the output.
2988        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
2989        # Write it to the file.
2990        my $xmlOut = Open(undef, ">$fileName");
2991        print $xmlOut $fileString;
2992    }
2993    
2994    
2995    =head3 HTMLNote
2996    
2997    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
2998    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
2999    Except for C<[p]>, all the codes are closed by slash-codes. So, for
3000    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
3001    
3002    C<< my $realHtml = ERDB::HTMLNote($dataString); >>
3003    
3004    =over 4
3005    
3006    =item dataString
3007    
3008    String to convert to HTML.
3009    
3010    =item RETURN
3011    
3012    An HTML string derived from the input string.
3013    
3014    =back
3015    
3016    =cut
3017    
3018    sub HTMLNote {
3019        # Get the parameter.
3020        my ($dataString) = @_;
3021        # HTML-escape the text.
3022        my $retVal = CGI::escapeHTML($dataString);
3023        # Substitute the bulletin board codes.
3024        $retVal =~ s!\[(/?[bi])\]!<$1>!g;
3025        $retVal =~ s!\[p\]!</p><p>!g;
3026        # Return the result.
3027        return $retVal;
3028    }
3029    
3030    
3031    =head2 Data Mining Methods
3032    
3033    =head3 GetUsefulCrossValues
3034    
3035    C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>
3036    
3037    Return a list of the useful attributes that would be returned by a B<Cross> call
3038    from an entity of the source entity type through the specified relationship. This
3039    means it will return the fields of the target entity type and the intersection data
3040    fields in the relationship. Only primary table fields are returned. In other words,
3041    the field names returned will be for fields where there is always one and only one
3042    value.
3043    
3044    =over 4
3045    
3046    =item sourceEntity
3047    
3048    Name of the entity from which the relationship crossing will start.
3049    
3050    =item relationship
3051    
3052    Name of the relationship being crossed.
3053    
3054    =item RETURN
3055    
3056    Returns a list of field names in Sprout field format (I<objectName>C<(>I<fieldName>C<)>.
3057    
3058    =back
3059    
3060    =cut
3061    #: Return Type @;
3062    sub GetUsefulCrossValues {
3063        # Get the parameters.
3064        my ($self, $sourceEntity, $relationship) = @_;
3065        # Declare the return variable.
3066        my @retVal = ();
3067        # Determine the target entity for the relationship. This is whichever entity is not
3068        # the source entity. So, if the source entity is the FROM, we'll get the name of
3069        # the TO, and vice versa.
3070        my $relStructure = $self->_GetStructure($relationship);
3071        my $targetEntityType = ($relStructure->{from} eq $sourceEntity ? "to" : "from");
3072        my $targetEntity = $relStructure->{$targetEntityType};
3073        # Get the field table for the entity.
3074        my $entityFields = $self->GetFieldTable($targetEntity);
3075        # The field table is a hash. The hash key is the field name. The hash value is a structure.
3076        # For the entity fields, the key aspect of the target structure is that the {relation} value
3077        # must match the entity name.
3078        my @fieldList = map { "$targetEntity($_)" } grep { $entityFields->{$_}->{relation} eq $targetEntity }
3079                            keys %{$entityFields};
3080        # Push the fields found onto the return variable.
3081        push @retVal, sort @fieldList;
3082        # Get the field table for the relationship.
3083        my $relationshipFields = $self->GetFieldTable($relationship);
3084        # Here we have a different rule. We want all the fields other than "from-link" and "to-link".
3085        # This may end up being an empty set.
3086        my @fieldList2 = map { "$relationship($_)" } grep { $_ ne "from-link" && $_ ne "to-link" }
3087                            keys %{$relationshipFields};
3088        # Push these onto the return list.
3089        push @retVal, sort @fieldList2;
3090        # Return the result.
3091        return @retVal;
3092    }
3093    
3094    =head3 FindColumn
3095    
3096    C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>
3097    
3098    Return the location a desired column in a data mining header line. The data
3099    mining header line is a tab-separated list of column names. The column
3100    identifier is either the numerical index of a column or the actual column
3101    name.
3102    
3103    =over 4
3104    
3105    =item headerLine
3106    
3107    The header line from a data mining command, which consists of a tab-separated
3108    list of column names.
3109    
3110    =item columnIdentifier
3111    
3112    Either the ordinal number of the desired column (1-based), or the name of the
3113    desired column.
3114    
3115    =item RETURN
3116    
3117    Returns the array index (0-based) of the desired column.
3118    
3119    =back
3120    
3121    =cut
3122    
3123    sub FindColumn {
3124        # Get the parameters.
3125        my ($headerLine, $columnIdentifier) = @_;
3126        # Declare the return variable.
3127        my $retVal;
3128        # Split the header line into column names.
3129        my @headers = ParseColumns($headerLine);
3130        # Determine whether we have a number or a name.
3131        if ($columnIdentifier =~ /^\d+$/) {
3132            # Here we have a number. Subtract 1 and validate the result.
3133            $retVal = $columnIdentifier - 1;
3134            if ($retVal < 0 || $retVal > $#headers) {
3135                Confess("Invalid column identifer \"$columnIdentifier\": value out of range.");
3136            }
3137        } else {
3138            # Here we have a name. We need to find it in the list.
3139            for (my $i = 0; $i <= $#headers && ! defined($retVal); $i++) {
3140                if ($headers[$i] eq $columnIdentifier) {
3141                    $retVal = $i;
3142                }
3143            }
3144            if (! defined($retVal)) {
3145                Confess("Invalid column identifier \"$columnIdentifier\": value not found.");
3146            }
3147        }
3148        # Return the result.
3149        return $retVal;
3150    }
3151    
3152    =head3 ParseColumns
3153    
3154    C<< my @columns = ERDB::ParseColumns($line); >>
3155    
3156    Convert the specified data line to a list of columns.
3157    
3158    =over 4
3159    
3160    =item line
3161    
3162    A data mining input, consisting of a tab-separated list of columns terminated by a
3163    new-line.
3164    
3165    =item RETURN
3166    
3167    Returns a list consisting of the column values.
3168    
3169    =back
3170    
3171    =cut
3172    
3173    sub ParseColumns {
3174        # Get the parameters.
3175        my ($line) = @_;
3176        # Chop off the line-end.
3177        chomp $line;
3178        # Split it into a list.
3179        my @retVal = split(/\t/, $line);
3180        # Return the result.
3181        return @retVal;
3182    }
3183    
3184    =head2 Virtual Methods
3185    
3186    =head3 CleanKeywords
3187    
3188    C<< my $cleanedString = $erdb->CleanKeywords($searchExpression); >>
3189    
3190    Clean up a search expression or keyword list. This is a virtual method that may
3191    be overridden by the subclass. The base-class method removes extra spaces
3192    and converts everything to lower case.
3193    
3194    =over 4
3195    
3196    =item searchExpression
3197    
3198    Search expression or keyword list to clean. Note that a search expression may
3199    contain boolean operators which need to be preserved. This includes leading
3200    minus signs.
3201    
3202    =item RETURN
3203    
3204    Cleaned expression or keyword list.
3205    
3206    =back
3207    
3208    =cut
3209    
3210    sub CleanKeywords {
3211        # Get the parameters.
3212        my ($self, $searchExpression) = @_;
3213        # Lower-case the expression and copy it into the return variable. Note that we insure we
3214        # don't accidentally end up with an undefined value.
3215        my $retVal = lc($searchExpression || "");
3216        # Remove extra spaces.
3217        $retVal =~ s/\s+/ /g;
3218        $retVal =~ s/(^\s+)|(\s+$)//g;
3219        # Return the result.
3220        return $retVal;
3221    }
3222    
3223  Type name of the object whose fields are being generated.  =head3 GetSourceObject
3224    
3225  =item values (optional)  C<< my $source = $erdb->GetSourceObject($entityName); >>
3226    
3227  Reference to a value structure from which additional values can be taken.  Return the object to be used in loading special attributes of the specified entity. The
3228    algorithm for loading special attributes is stored in the C<DataGen> elements of the
3229    XML
3230    
3231  =item from (optiona)  =head2 Internal Utility Methods
3232    
3233    =head3 _RelationMap
3234    
3235    C<< my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef); >>
3236    
3237    Create the relation map for an SQL query. The relation map is used by B<DBObject>
3238    to determine how to interpret the results of the query.
3239    
3240  Reference to the source entity instance if relationship data is being generated.  =over 4
3241    
3242    =item mappedNameHashRef
3243    
3244  =item to (optional)  Reference to a hash that maps modified object names to real object names.
3245    
3246  Reference to the target entity instance if relationship data is being generated.  =item mappedNameListRef
3247    
3248    Reference to a list of modified object names in the order they appear in the
3249    SELECT list.
3250    
3251    =item RETURN
3252    
3253    Returns a list of 2-tuples. Each tuple consists of an object name as used in the
3254    query followed by the actual name of that object. This enables the B<DBObject> to
3255    determine the order of the tables in the query and which object name belongs to each
3256    mapped object name. Most of the time these two values are the same; however, if a
3257    relation occurs twice in the query, the relation name in the field list and WHERE
3258    clause will use a mapped name (generally the actual relation name with a numeric
3259    suffix) that does not match the actual relation name.
3260    
3261  =back  =back
3262    
3263  =cut  =cut
3264    
3265  sub _GenerateFields {  sub _RelationMap {
3266      # Get the parameters.      # Get the parameters.
3267      my ($this, $fields, $type, $values, $from, $to) = @_;      my ($mappedNameHashRef, $mappedNameListRef) = @_;
3268      # Sort the field names by pass number.      # Declare the return variable.
3269      my @fieldNames = sort { $fields->{$a}->{DataGen}->{pass} <=> $fields->{$b}->{DataGen}->{pass} } keys %{$fields};      my @retVal = ();
3270      # Loop through the field names, generating data.      # Build the map.
3271      for my $name (@fieldNames) {      for my $mappedName (@{$mappedNameListRef}) {
3272          # Only proceed if this field needs to be generated.          push @retVal, [$mappedName, $mappedNameHashRef->{$mappedName}];
3273          if (!exists $this->{$name}) {      }
3274              # Get this field's data generation descriptor.      # Return it.
3275              my $fieldDescriptor = $fields->{$name};      return @retVal;
3276              my $data = $fieldDescriptor->{DataGen};  }
3277              # Get the code to generate the field value.  
3278              my $codeString = $data->{content};  
3279              # Determine whether or not this field is in the primary relation.  =head3 _SetupSQL
3280              if ($fieldDescriptor->{relation} eq $type) {  
3281                  # Here we have a primary relation field. Store the field value as  Process a list of object names and a filter clause so that they can be used to
3282                  # a scalar.  build an SQL statement. This method takes in a reference to a list of object names
3283                  $this->{$name} = eval($codeString);  and a filter clause. It will return a corrected filter clause, a list of mapped
3284    names and the mapped name hash.
3285    
3286    This is an instance method.
3287    
3288    =over 4
3289    
3290    =item objectNames
3291    
3292    Reference to a list of the object names to be included in the query.
3293    
3294    =item filterClause
3295    
3296    A string containing the WHERE clause for the query (without the C<WHERE>) and also
3297    optionally the C<ORDER BY> and C<LIMIT> clauses.
3298    
3299    =item matchClause
3300    
3301    An optional full-text search clause. If specified, it will be inserted at the
3302    front of the WHERE clause. It should already be SQL-formatted; that is, the
3303    field names should be in the form I<table>C<.>I<fieldName>.
3304    
3305    =item RETURN
3306    
3307    Returns a three-element list. The first element is the SQL statement suffix, beginning
3308    with the FROM clause. The second element is a reference to a list of the names to be
3309    used in retrieving the fields. The third element is a hash mapping the names to the
3310    objects they represent.
3311    
3312    =back
3313    
3314    =cut
3315    
3316    sub _SetupSQL {
3317        my ($self, $objectNames, $filterClause, $matchClause) = @_;
3318        # Adjust the list of object names to account for multiple occurrences of the
3319        # same object. We start with a hash table keyed on object name that will
3320        # return the object suffix. The first time an object is encountered it will
3321        # not be found in the hash. The next time the hash will map the object name
3322        # to 2, then 3, and so forth.
3323        my %objectHash = ();
3324        # This list will contain the object names as they are to appear in the
3325        # FROM list.
3326        my @fromList = ();
3327        # This list contains the suffixed object name for each object. It is exactly
3328        # parallel to the list in the $objectNames parameter.
3329        my @mappedNameList = ();
3330        # Finally, this hash translates from a mapped name to its original object name.
3331        my %mappedNameHash = ();
3332        # Now we create the lists. Note that for every single name we push something into
3333        # @fromList and @mappedNameList. This insures that those two arrays are exactly
3334        # parallel to $objectNames.
3335        for my $objectName (@{$objectNames}) {
3336            # Get the next suffix for this object.
3337            my $suffix = $objectHash{$objectName};
3338            if (! $suffix) {
3339                # Here we are seeing the object for the first time. The object name
3340                # is used as is.
3341                push @mappedNameList, $objectName;
3342                push @fromList, $objectName;
3343                $mappedNameHash{$objectName} = $objectName;
3344                # Denote the next suffix will be 2.
3345                $objectHash{$objectName} = 2;
3346            } else {
3347                # Here we've seen the object before. We construct a new name using
3348                # the suffix from the hash and update the hash.
3349                my $mappedName = "$objectName$suffix";
3350                $objectHash{$objectName} = $suffix + 1;
3351                # The FROM list has the object name followed by the mapped name. This
3352                # tells SQL it's still the same table, but we're using a different name
3353                # for it to avoid confusion.
3354                push @fromList, "$objectName $mappedName";
3355                # The mapped-name list contains the real mapped name.
3356                push @mappedNameList, $mappedName;
3357                # Finally, enable us to get back from the mapped name to the object name.
3358                $mappedNameHash{$mappedName} = $objectName;
3359            }
3360        }
3361        # Begin the SELECT suffix. It starts with
3362        #
3363        # FROM name1, name2, ... nameN
3364        #
3365        my $suffix = "FROM " . join(', ', @fromList);
3366        # Now for the WHERE. First, we need a place for the filter string.
3367        my $filterString = "";
3368        # We will also keep a list of conditions to add to the WHERE clause in order to link
3369        # entities and relationships as well as primary relations to secondary ones.
3370        my @joinWhere = ();
3371        # Check for a filter clause.
3372        if ($filterClause) {
3373            # Here we have one, so we convert its field names and add it to the query. First,
3374            # We create a copy of the filter string we can work with.
3375            $filterString = $filterClause;
3376            # Next, we sort the object names by length. This helps protect us from finding
3377            # object names inside other object names when we're doing our search and replace.
3378            my @sortedNames = sort { length($b) - length($a) } @mappedNameList;
3379            # The final preparatory step is to create a hash table of relation names. The
3380            # table begins with the relation names already in the SELECT command. We may
3381            # need to add relations later if there is filtering on a field in a secondary
3382            # relation. The secondary relations are the ones that contain multiply-
3383            # occurring or optional fields.
3384            my %fromNames = map { $_ => 1 } @sortedNames;
3385            # We are ready to begin. We loop through the object names, replacing each
3386            # object name's field references by the corresponding SQL field reference.
3387            # Along the way, if we find a secondary relation, we will need to add it
3388            # to the FROM clause.
3389            for my $mappedName (@sortedNames) {
3390                # Get the length of the object name plus 2. This is the value we add to the
3391                # size of the field name to determine the size of the field reference as a
3392                # whole.
3393                my $nameLength = 2 + length $mappedName;
3394                # Get the real object name for this mapped name.
3395                my $objectName = $mappedNameHash{$mappedName};
3396                Trace("Processing $mappedName for object $objectName.") if T(4);
3397                # Get the object's field list.
3398                my $fieldList = $self->GetFieldTable($objectName);
3399                # Find the field references for this object.
3400                while ($filterString =~ m/$mappedName\(([^)]*)\)/g) {
3401                    # At this point, $1 contains the field name, and the current position
3402                    # is set immediately after the final parenthesis. We pull out the name of
3403                    # the field and the position and length of the field reference as a whole.
3404                    my $fieldName = $1;
3405                    my $len = $nameLength + length $fieldName;
3406                    my $pos = pos($filterString) - $len;
3407                    # Insure the field exists.
3408                    if (!exists $fieldList->{$fieldName}) {
3409                        Confess("Field $fieldName not found for object $objectName.");
3410                    } else {
3411                        Trace("Processing $fieldName at position $pos.") if T(4);
3412                        # Get the field's relation.
3413                        my $relationName = $fieldList->{$fieldName}->{relation};
3414                        # Now we have a secondary relation. We need to insure it matches the
3415                        # mapped name of the primary relation. First we peel off the suffix
3416                        # from the mapped name.
3417                        my $mappingSuffix = substr $mappedName, length($objectName);
3418                        # Put the mapping suffix onto the relation name to get the
3419                        # mapped relation name.
3420                        my $mappedRelationName = "$relationName$mappingSuffix";
3421                        # Insure the relation is in the FROM clause.
3422                        if (!exists $fromNames{$mappedRelationName}) {
3423                            # Add the relation to the FROM clause.
3424                            if ($mappedRelationName eq $relationName) {
3425                                # The name is un-mapped, so we add it without
3426                                # any frills.
3427                                $suffix .= ", $relationName";
3428                                push @joinWhere, "$objectName.id = $relationName.id";
3429                            } else {
3430                                # Here we have a mapping situation.
3431                                $suffix .= ", $relationName $mappedRelationName";
3432                                push @joinWhere, "$mappedRelationName.id = $mappedName.id";
3433                            }
3434                            # Denote we have this relation available for future fields.
3435                            $fromNames{$mappedRelationName} = 1;
3436                        }
3437                        # Form an SQL field reference from the relation name and the field name.
3438                        my $sqlReference = "$mappedRelationName." . _FixName($fieldName);
3439                        # Put it into the filter string in place of the old value.
3440                        substr($filterString, $pos, $len) = $sqlReference;
3441                        # Reposition the search.
3442                        pos $filterString = $pos + length $sqlReference;
3443                    }
3444                }
3445            }
3446        }
3447        # The next step is to join the objects together. We only need to do this if there
3448        # is more than one object in the object list. We start with the first object and
3449        # run through the objects after it. Note also that we make a safety copy of the
3450        # list before running through it, because we shift off the first object before
3451        # processing the rest.
3452        my @mappedObjectList = @mappedNameList;
3453        my $lastMappedObject = shift @mappedObjectList;
3454        # Get the join table.
3455        my $joinTable = $self->{_metaData}->{Joins};
3456        # Loop through the object list.
3457        for my $thisMappedObject (@mappedObjectList) {
3458            # Look for a join using the real object names.
3459            my $lastObject = $mappedNameHash{$lastMappedObject};
3460            my $thisObject = $mappedNameHash{$thisMappedObject};
3461            my $joinKey = "$lastObject/$thisObject";
3462            if (!exists $joinTable->{$joinKey}) {
3463                # Here there's no join, so we throw an error.
3464                Confess("No join exists to connect from $lastMappedObject to $thisMappedObject.");
3465              } else {              } else {
3466                  # Here we have a secondary relation field. Create a null list              # Get the join clause.
3467                  # and push the desired number of field values onto it.              my $unMappedJoin = $joinTable->{$joinKey};
3468                  my @fieldValues = ();              # Fix the names.
3469                  my $count = IntGen(0,$data->{testCount});              $unMappedJoin =~ s/$lastObject/$lastMappedObject/;
3470                  for (my $i = 0; $i < $count; $i++) {              $unMappedJoin =~ s/$thisObject/$thisMappedObject/;
3471                      my $newValue = eval($codeString);              push @joinWhere, $unMappedJoin;
3472                      push @fieldValues, $newValue;              # Save this object as the last object for the next iteration.
3473                $lastMappedObject = $thisMappedObject;
3474            }
3475        }
3476        # Now we need to handle the whole ORDER BY / LIMIT thing. The important part
3477        # here is we want the filter clause to be empty if there's no WHERE filter.
3478        # We'll put the ORDER BY / LIMIT clauses in the following variable.
3479        my $orderClause = "";
3480        # This is only necessary if we have a filter string in which the ORDER BY
3481        # and LIMIT clauses can live.
3482        if ($filterString) {
3483            # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy
3484            # operator so that we find the first occurrence of either verb.
3485            if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {
3486                # Here we have an ORDER BY or LIMIT verb. Split it off of the filter string.
3487                my $pos = pos $filterString;
3488                $orderClause = $2 . substr($filterString, $pos);
3489                $filterString = $1;
3490            }
3491                  }                  }
3492                  # Store the value list in the main hash.      # All the things that are supposed to be in the WHERE clause of the
3493                  $this->{$name} = \@fieldValues;      # SELECT command need to be put into @joinWhere so we can string them
3494        # together. We begin with the match clause. This is important,
3495        # because the match clause's parameter mark must precede any parameter
3496        # marks in the filter string.
3497        if ($matchClause) {
3498            push @joinWhere, $matchClause;
3499              }              }
3500        # Add the filter string. We put it in parentheses to avoid operator
3501        # precedence problems with the match clause or the joins.
3502        if ($filterString) {
3503            Trace("Filter string is \"$filterString\".") if T(4);
3504            push @joinWhere, "($filterString)";
3505          }          }
3506        # String it all together into a big filter clause.
3507        if (@joinWhere) {
3508            $suffix .= " WHERE " . join(' AND ', @joinWhere);
3509        }
3510        # Add the sort or limit clause (if any).
3511        if ($orderClause) {
3512            $suffix .= " $orderClause";
3513        }
3514        # Return the suffix, the mapped name list, and the mapped name hash.
3515        return ($suffix, \@mappedNameList, \%mappedNameHash);
3516    }
3517    
3518    =head3 _GetStatementHandle
3519    
3520    This method will prepare and execute an SQL query, returning the statement handle.
3521    The main reason for doing this here is so that everybody who does SQL queries gets
3522    the benefit of tracing.
3523    
3524    This is an instance method.
3525    
3526    =over 4
3527    
3528    =item command
3529    
3530    Command to prepare and execute.
3531    
3532    =item params
3533    
3534    Reference to a list of the values to be substituted in for the parameter marks.
3535    
3536    =item RETURN
3537    
3538    Returns a prepared and executed statement handle from which the caller can extract
3539    results.
3540    
3541    =back
3542    
3543    =cut
3544    
3545    sub _GetStatementHandle {
3546        # Get the parameters.
3547        my ($self, $command, $params) = @_;
3548        # Trace the query.
3549        Trace("SQL query: $command") if T(SQL => 3);
3550        Trace("PARMS: '" . (join "', '", @{$params}) . "'") if (T(SQL => 4) && (@{$params} > 0));
3551        # Get the database handle.
3552        my $dbh = $self->{_dbh};
3553        # Prepare the command.
3554        my $sth = $dbh->prepare_command($command);
3555        # Execute it with the parameters bound in.
3556        $sth->execute(@{$params}) || Confess("SELECT error:  " . $sth->errstr());
3557        # Return the statement handle.
3558        return $sth;
3559      }      }
3560    
3561    =head3 _GetLoadStats
3562    
3563    Return a blank statistics object for use by the load methods.
3564    
3565    This is a static method.
3566    
3567    =cut
3568    
3569    sub _GetLoadStats{
3570        return Stats->new();
3571  }  }
3572    
3573  =head3 DumpRelation  =head3 _DumpRelation
3574    
3575  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.
3576    
3577  This is an instance method.  This is an instance method.
3578    
# Line 2229  Line 3620 
3620      close DTXOUT;      close DTXOUT;
3621  }  }
3622    
3623  =head3 GetStructure  =head3 _GetStructure
3624    
3625  Get the data structure for a specified entity or relationship.  Get the data structure for a specified entity or relationship.
3626    
# Line 2268  Line 3659 
3659      return $retVal;      return $retVal;
3660  }  }
3661    
3662  =head3 GetRelationTable  
3663    
3664    =head3 _GetRelationTable
3665    
3666  Get the list of relations for a specified entity or relationship.  Get the list of relations for a specified entity or relationship.
3667    
# Line 2297  Line 3690 
3690      return $objectData->{Relations};      return $objectData->{Relations};
3691  }  }
3692    
3693  =head3 ValidateFieldNames  =head3 _ValidateFieldNames
3694    
3695  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
3696  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 2324  Line 3717 
3717          for my $object (values %{$metadata->{$section}}) {          for my $object (values %{$metadata->{$section}}) {
3718              # Loop through the object's fields.              # Loop through the object's fields.
3719              for my $fieldName (keys %{$object->{Fields}}) {              for my $fieldName (keys %{$object->{Fields}}) {
3720                  # Now we make some initial validations.                  # If this field name is invalid, set the return value to zero
3721                  if ($fieldName =~ /--/) {                  # so we know we encountered an error.
3722                      # Here we have a doubled minus sign.                  if (! ValidateFieldName($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";  
3723                          $retVal = 0;                          $retVal = 0;
3724                      }                      }
3725                  }                  }
3726              }              }
3727          }          }
     }  
3728      # If an error was found, fail.      # If an error was found, fail.
3729      if ($retVal  == 0) {      if ($retVal  == 0) {
3730          Confess("Errors found in field names.");          Confess("Errors found in field names.");
3731      }      }
3732  }  }
3733    
3734  =head3 LoadRelation  =head3 _LoadRelation
3735    
3736  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
3737  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 2412  Line 3791 
3791      return $retVal;      return $retVal;
3792  }  }
3793    
3794  =head3 LoadMetaData  
3795    =head3 _LoadMetaData
3796    
3797  This method loads the data describing this database from an XML file into a metadata structure.  This method loads the data describing this database from an XML file into a metadata structure.
3798  The resulting structure is a set of nested hash tables containing all the information needed to  The resulting structure is a set of nested hash tables containing all the information needed to
# Line 2437  Line 3817 
3817  sub _LoadMetaData {  sub _LoadMetaData {
3818      # Get the parameters.      # Get the parameters.
3819      my ($filename) = @_;      my ($filename) = @_;
3820      Trace("Reading Sprout DBD from $filename.") if T(2);      Trace("Reading DBD from $filename.") if T(2);
3821      # 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
3822      # get the exact structure we want.      # get the exact structure we want.
3823      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 $filename.") if T(1);  
3824      # Before we go any farther, we need to validate the field and object names. If an error is found,      # Before we go any farther, we need to validate the field and object names. If an error is found,
3825      # the method below will fail.      # the method below will fail.
3826      _ValidateFieldNames($metadata);      _ValidateFieldNames($metadata);
# Line 2583  Line 3950 
3950              my $count = 0;              my $count = 0;
3951              for my $index (@{$indexList}) {              for my $index (@{$indexList}) {
3952                  # Add this index to the index table.                  # Add this index to the index table.
3953                  _AddIndex("idx$relationName$count", $relation, $index);                  _AddIndex("idx$count", $relation, $index);
3954                  # Increment the counter so that the next index has a different name.                  # Increment the counter so that the next index has a different name.
3955                  $count++;                  $count++;
3956              }              }
# Line 2739  Line 4106 
4106      return $metadata;      return $metadata;
4107  }  }
4108    
4109  =head3 SortNeeded  =head3 _CreateRelationshipIndex
   
 C<< my $flag = $erdb->SortNeeded($relationName); >>  
   
 Return TRUE if the specified relation should be sorted during loading to remove duplicate keys,  
 else FALSE.  
   
 =over 4  
   
 =item relationName  
   
 Name of the relation to be examined.  
   
 =item RETURN  
   
 Returns TRUE if the relation needs a sort, else FALSE.  
   
 =back  
   
 =cut  
 #: Return Type $;  
 sub SortNeeded {  
     # Get the parameters.  
     my ($self, $relationName) = @_;  
     # Declare the return variable.  
     my $retVal = 0;  
     # Find out if the relation is a primary entity relation.  
     my $entityTable = $self->{Entities};  
     if (exists $entityTable->{$relationName}) {  
         my $keyType = $entityTable->{$relationName}->{keyType};  
         # If the key is not a hash string, we must do the sort.  
         if ($keyType ne 'hash-string') {  
             $retVal = 1;  
         }  
     }  
     # Return the result.  
     return $retVal;  
 }  
   
 =head3 CreateRelationshipIndex  
4110    
4111  Create an index for a relationship's relation.  Create an index for a relationship's relation.
4112    
# Line 2820  Line 4148 
4148          $newIndex->{Unique} = 'true';          $newIndex->{Unique} = 'true';
4149      }      }
4150      # Add the index to the relation.      # Add the index to the relation.
4151      _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);      _AddIndex("idx$indexKey", $relationStructure, $newIndex);
4152  }  }
4153    
4154  =head3 AddIndex  =head3 _AddIndex
4155    
4156  Add an index to a relation structure.  Add an index to a relation structure.
4157    
# Line 2869  Line 4197 
4197      $relationStructure->{Indexes}->{$indexName} = $newIndex;      $relationStructure->{Indexes}->{$indexName} = $newIndex;
4198  }  }
4199    
4200  =head3 FixupFields  =head3 _FixupFields
4201    
4202  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
4203  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 2907  Line 4235 
4235          # Here it doesn't, so we create a new one.          # Here it doesn't, so we create a new one.
4236          $structure->{Fields} = { };          $structure->{Fields} = { };
4237      } else {      } else {
4238          # 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
4239            # create a list for stashing them.
4240            my @textFields = ();
4241            # Loop through the fields.
4242          my $fieldStructures = $structure->{Fields};          my $fieldStructures = $structure->{Fields};
4243          for my $fieldName (keys %{$fieldStructures}) {          for my $fieldName (keys %{$fieldStructures}) {
4244              Trace("Processing field $fieldName of $defaultRelationName.") if T(4);              Trace("Processing field $fieldName of $defaultRelationName.") if T(4);
# Line 2916  Line 4247 
4247              my $type = $fieldData->{type};              my $type = $fieldData->{type};
4248              # Plug in a relation name if it is needed.              # Plug in a relation name if it is needed.
4249              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });
4250              # Plug in a data generator if we need one.              # Check for searchability.
4251              if (!exists $fieldData->{DataGen}) {              if ($fieldData->{searchable}) {
4252                  # The data generator will use the default for the field's type.                  # Only allow this for a primary relation.
4253                  $fieldData->{DataGen} = { content => $TypeTable{$type}->{dataGen} };                  if ($fieldData->{relation} ne $defaultRelationName) {
4254                        Confess("Field $fieldName of $defaultRelationName is in secondary relations and cannot be searchable.");
4255                    } else {
4256                        push @textFields, $fieldName;
4257                    }
4258              }              }
             # Plug in the defaults for the optional data generation parameters.  
             Tracer::MergeOptions($fieldData->{DataGen}, { testCount => 1, pass => 0 });  
4259              # Add the PrettySortValue.              # Add the PrettySortValue.
4260              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);
4261          }          }
4262            # If there are searchable fields, remember the fact.
4263            if (@textFields) {
4264                $structure->{searchFields} = \@textFields;
4265            }
4266      }      }
4267  }  }
4268    
4269  =head3 FixName  =head3 _FixName
4270    
4271  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.
4272    
# Line 2958  Line 4295 
4295      return $fieldName;      return $fieldName;
4296  }  }
4297    
4298  =head3 FixNames  =head3 _FixNames
4299    
4300  Fix all the field names in a list.  Fix all the field names in a list.
4301    
# Line 2989  Line 4326 
4326      return @result;      return @result;
4327  }  }
4328    
4329  =head3 AddField  =head3 _AddField
4330    
4331  Add a field to a field list.  Add a field to a field list.
4332    
# Line 3024  Line 4361 
4361      $fieldList->{$fieldName} = $fieldStructure;      $fieldList->{$fieldName} = $fieldStructure;
4362  }  }
4363    
4364  =head3 ReOrderRelationTable  =head3 _ReOrderRelationTable
4365    
4366  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
4367  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 3085  Line 4422 
4422    
4423  }  }
4424    
4425  =head3 IsPrimary  =head3 _IsPrimary
4426    
4427  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
4428  if it has the same name as an entity or relationship.  if it has the same name as an entity or relationship.
# Line 3121  Line 4458 
4458      return $retVal;      return $retVal;
4459  }  }
4460    
4461  =head3 FindRelation  =head3 _FindRelation
4462    
4463  Return the descriptor for the specified relation.  Return the descriptor for the specified relation.
4464    
# Line 3152  Line 4489 
4489    
4490  =head2 HTML Documentation Utility Methods  =head2 HTML Documentation Utility Methods
4491    
4492  =head3 ComputeRelationshipSentence  =head3 _ComputeRelationshipSentence
4493    
4494  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
4495  two related entities and an arity indicator.  two related entities and an arity indicator.
# Line 3190  Line 4527 
4527      return $result;      return $result;
4528  }  }
4529    
4530  =head3 ComputeRelationshipHeading  =head3 _ComputeRelationshipHeading
4531    
4532  The relationship heading is the L<relationship sentence|/ComputeRelationshipSentence> with the entity  The relationship heading is the L<relationship sentence|/ComputeRelationshipSentence> with the entity
4533  names hyperlinked to the appropriate entity sections of the document.  names hyperlinked to the appropriate entity sections of the document.
# Line 3227  Line 4564 
4564      return $result;      return $result;
4565  }  }
4566    
4567  =head3 ShowRelationTable  =head3 _ShowRelationTable
4568    
4569  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
4570  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 3277  Line 4614 
4614          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";
4615          # Add any note text.          # Add any note text.
4616          if (my $note = $indexData->{Notes}) {          if (my $note = $indexData->{Notes}) {
4617              $htmlString .= "<li>" . _HTMLNote($note->{content}) . "</li>\n";              $htmlString .= "<li>" . HTMLNote($note->{content}) . "</li>\n";
4618          }          }
4619          # Add the fiield list.          # Add the fiield list.
4620          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";
# Line 3288  Line 4625 
4625      $htmlString .= "</ul>\n";      $htmlString .= "</ul>\n";
4626  }  }
4627    
4628  =head3 OpenFieldTable  =head3 _OpenFieldTable
4629    
4630  This method creates the header string for the field table generated by L</ShowMetaData>.  This method creates the header string for the field table generated by L</ShowMetaData>.
4631    
# Line 3313  Line 4650 
4650      return _OpenTable($tablename, 'Field', 'Type', 'Description');      return _OpenTable($tablename, 'Field', 'Type', 'Description');
4651  }  }
4652    
4653  =head3 OpenTable  =head3 _OpenTable
4654    
4655  This method creates the header string for an HTML table.  This method creates the header string for an HTML table.
4656    
# Line 3353  Line 4690 
4690      return $htmlString;      return $htmlString;
4691  }  }
4692    
4693  =head3 CloseTable  =head3 _CloseTable
4694    
4695  This method returns the HTML for closing a table.  This method returns the HTML for closing a table.
4696    
# Line 3365  Line 4702 
4702      return "</table></p>\n";      return "</table></p>\n";
4703  }  }
4704    
4705  =head3 ShowField  =head3 _ShowField
4706    
4707  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.
4708    
# Line 3392  Line 4729 
4729      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>";
4730      # If we have content, add it as a third column.      # If we have content, add it as a third column.
4731      if (exists $fieldData->{Notes}) {      if (exists $fieldData->{Notes}) {
4732          $htmlString .= "<td>" . _HTMLNote($fieldData->{Notes}->{content}) . "</td>";          $htmlString .= "<td>" . HTMLNote($fieldData->{Notes}->{content}) . "</td>";
4733      }      }
4734      # Close off the row.      # Close off the row.
4735      $htmlString .= "</tr>\n";      $htmlString .= "</tr>\n";
# Line 3400  Line 4737 
4737      return $htmlString;      return $htmlString;
4738  }  }
4739    
 =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;  
 }  
   
4740  1;  1;

Legend:
Removed from v.1.42  
changed lines
  Added in v.1.76

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3