[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 1.83, Mon Jan 22 20:23:58 2007 UTC
# Line 11  Line 11 
11      use Time::HiRes qw(gettimeofday);      use Time::HiRes qw(gettimeofday);
12      use Digest::MD5 qw(md5_base64);      use Digest::MD5 qw(md5_base64);
13      use FIG;      use FIG;
14        use CGI;
15    
16  =head1 Entity-Relationship Database Package  =head1 Entity-Relationship Database Package
17    
# Line 59  Line 60 
60  B<start-position>, which indicates where in the contig that the sequence begins. This attribute  B<start-position>, which indicates where in the contig that the sequence begins. This attribute
61  is implemented as the C<start_position> field in the C<IsMadeUpOf> relation.  is implemented as the C<start_position> field in the C<IsMadeUpOf> relation.
62    
63  The database itself is described by an XML file using the F<ERDatabase.xsd> schema. In addition to  The database itself is described by an XML file. In addition to all the data required to define
64  all the data required to define the entities, relationships, and attributes, the schema provides  the entities, relationships, and attributes, the schema provides space for notes describing
65  space for notes describing the data and what it means. These notes are used by L</ShowMetaData>  the data and what it means. These notes are used by L</ShowMetaData> to generate documentation
66  to generate documentation for the database.  for the database.
67    
68    Special support is provided for text searching. An entity field can be marked as <em>searchable</em>,
69    in which case it will be used to generate a text search index in which the user searches for words
70    in the field instead of a particular field value.
71    
72  Finally, every entity and relationship object has a flag indicating if it is new or old. The object  Finally, every entity and relationship object has a flag indicating if it is new or old. The object
73  is considered I<old> if it was loaded by the L</LoadTables> method. It is considered I<new> if it  is considered I<old> if it was loaded by the L</LoadTables> method. It is considered I<new> if it
74  was inserted by the L</InsertObject> method.  was inserted by the L</InsertObject> method.
75    
 To facilitate testing, the ERDB module supports automatic generation of test data. This process  
 is described in the L</GenerateEntity> and L</GenerateConnection> methods, though it is not yet  
 fully implemented.  
   
76  =head2 XML Database Description  =head2 XML Database Description
77    
78  =head3 Data Types  =head3 Data Types
# Line 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 234  Line 257 
257    
258  =back  =back
259    
260  The B<Index>, B<FromIndex>, and B<ToIndex> tags themselves have no attributes.  The B<FromIndex>, and B<ToIndex> tags have no attributes. The B<Index> tag can
261    have a B<Unique> attribute. If specified, the index will be generated as a unique
262    index.
263    
264  =head3 Object and Field Names  =head3 Object and Field Names
265    
# Line 312  Line 337 
337    
338  # Table of information about our datatypes. "sqlType" is the corresponding SQL datatype string.  # Table of information about our datatypes. "sqlType" is the corresponding SQL datatype string.
339  # "maxLen" is the maximum permissible length of the incoming string data used to populate a field  # "maxLen" is the maximum permissible length of the incoming string data used to populate a field
340  # of the specified type. "dataGen" is PERL string that will be evaluated if no test data generation  # of the specified type. "avgLen" is the average byte length for estimating
341  # string is specified in the field definition. "avgLen" is the average byte length for estimating  # record sizes. "sort" is the key modifier for the sort command, "notes" is a type description,
342  # record sizes.  # and "indexMod", if non-zero, is the number of characters to use when the field is specified in an
343  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, dataGen => "StringGen('A')" },  # index
344                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, dataGen => "IntGen(0, 99999999)" },  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",
345                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, dataGen => "StringGen(IntGen(10,250))" },                                 indexMod =>   0, notes => "single ASCII character"},
346                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, dataGen => "StringGen(IntGen(80,1000))" },                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n",
347                    date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, dataGen => "DateGen(-7, 7, IntGen(0,1400))" },                                 indexMod =>   0, notes => "signed 32-bit integer"},
348                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, dataGen => "FloatGen(0.0, 100.0)" },                    counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n",
349                    boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, dataGen => "IntGen(0, 1)" },                                 indexMod =>   0, notes => "unsigned 32-bit integer"},
350                      string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, sort => "",
351                                   indexMod =>   0, notes => "character string, 0 to 255 characters"},
352                      text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, sort => "",
353                                   indexMod => 255, notes => "character string, nearly unlimited length, only first 255 characters are indexed"},
354                      date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, sort => "n",
355                                   indexMod =>   0, notes => "signed, 64-bit integer"},
356                      float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, sort => "g",
357                                   indexMod =>   0, notes => "64-bit double precision floating-point number"},
358                      boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, sort => "n",
359                                   indexMod =>   0, notes => "boolean value: 0 if false, 1 if true"},
360                   'hash-string' =>                   'hash-string' =>
361                               { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, dataGen => "SringGen(22)" },                               { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, sort => "",
362                                   indexMod =>   0, notes => "string stored in digested form, used for certain types of key fields"},
363                     'id-string' =>
364                                 { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, sort => "",
365                                   indexMod =>   0, notes => "character string, 0 to 25 characters"},
366                   'key-string' =>                   'key-string' =>
367                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, dataGen => "StringGen(IntGen(10,40))" },                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, sort => "",
368                                   indexMod =>   0, notes => "character string, 0 to 40 characters"},
369                   'name-string' =>                   'name-string' =>
370                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, dataGen => "StringGen(IntGen(10,80))" },                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, sort => "",
371                                   indexMod =>   0, notes => "character string, 0 to 80 characters"},
372                   'medium-string' =>                   'medium-string' =>
373                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, dataGen => "StringGen(IntGen(10,160))" },                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",
374                                   indexMod =>   0, notes => "character string, 0 to 160 characters"},
375                  );                  );
376    
377  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 338  Line 380 
380                     'MM' => 'many-to-many'                     'MM' => 'many-to-many'
381                   );                   );
382    
383  # Table for interpreting string patterns.  # Options for XML input and output.
384    
385    my %XmlOptions = (GroupTags =>  { Relationships => 'Relationship',
386                                      Entities => 'Entity',
387                                      Fields => 'Field',
388                                      Indexes => 'Index',
389                                      IndexFields => 'IndexField'
390                                    },
391                      KeyAttr =>    { Relationship => 'name',
392                                      Entity => 'name',
393                                      Field => 'name'
394                                    },
395                      SuppressEmpty => 1,
396                     );
397    
398  my %PictureTable = ( 'A' => "abcdefghijklmnopqrstuvwxyz",  my %XmlInOpts  = (
399                       '9' => "0123456789",                    ForceArray => ['Field', 'Index', 'IndexField', 'Relationship', 'Entity'],
400                       'X' => "abcdefghijklmnopqrstuvwxyz0123456789",                    ForceContent => 1,
401                       'V' => "aeiou",                    NormalizeSpace => 2,
402                       'K' => "bcdfghjklmnoprstvwxyz"                   );
403    my %XmlOutOpts = (
404                      RootName => 'Database',
405                      XMLDecl => 1,
406                     );                     );
407    
408    
409  =head2 Public Methods  =head2 Public Methods
410    
411  =head3 new  =head3 new
# Line 416  Line 475 
475      # Write the HTML heading stuff.      # Write the HTML heading stuff.
476      print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";      print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";
477      print HTMLOUT "</head>\n<body>\n";      print HTMLOUT "</head>\n<body>\n";
478        # Write the documentation.
479        print HTMLOUT $self->DisplayMetaData();
480        # Close the document.
481        print HTMLOUT "</body>\n</html>\n";
482        # Close the file.
483        close HTMLOUT;
484    }
485    
486    =head3 DisplayMetaData
487    
488    C<< my $html = $erdb->DisplayMetaData(); >>
489    
490    Return an HTML description of the database. This description can be used to help users create
491    the data to be loaded into the relations and form queries. The output is raw includable HTML
492    without any HEAD or BODY tags.
493    
494    =over 4
495    
496    =item filename
497    
498    The name of the output file.
499    
500    =back
501    
502    =cut
503    
504    sub DisplayMetaData {
505        # Get the parameters.
506        my ($self) = @_;
507        # Get the metadata and the title string.
508        my $metadata = $self->{_metaData};
509        # Get the title string.
510        my $title = $metadata->{Title};
511        # Get the entity and relationship lists.
512        my $entityList = $metadata->{Entities};
513        my $relationshipList = $metadata->{Relationships};
514        # Declare the return variable.
515        my $retVal = "";
516        # Open the output file.
517        Trace("Building MetaData table of contents.") if T(4);
518      # 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
519      # section contains an ordered list of entity or relationship subsections.      # section contains an ordered list of entity or relationship subsections.
520      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";
521      # Loop through the Entities, displaying a list item for each.      # Loop through the Entities, displaying a list item for each.
522      foreach my $key (sort keys %{$entityList}) {      foreach my $key (sort keys %{$entityList}) {
523          # Display this item.          # Display this item.
524          print HTMLOUT "<li><a href=\"#$key\">$key</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$key</a></li>\n";
525      }      }
526      # Close off the entity section and start the relationship section.      # Close off the entity section and start the relationship section.
527      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";
528      # Loop through the Relationships.      # Loop through the Relationships.
529      foreach my $key (sort keys %{$relationshipList}) {      foreach my $key (sort keys %{$relationshipList}) {
530          # Display this item.          # Display this item.
531          my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});          my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});
532          print HTMLOUT "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";
533      }      }
534      # Close off the relationship section and list the join table section.      # Close off the relationship section and list the join table section.
535      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";
536      # Close off the table of contents itself.      # Close off the table of contents itself.
537      print HTMLOUT "</ul>\n";      $retVal .=  "</ul>\n";
538      # 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.
539      print HTMLOUT "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";      $retVal .= "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";
540      # Loop through the entities.      # Loop through the entities.
541      for my $key (sort keys %{$entityList}) {      for my $key (sort keys %{$entityList}) {
542          Trace("Building MetaData entry for $key entity.") if T(4);          Trace("Building MetaData entry for $key entity.") if T(4);
543          # Create the entity header. It contains a bookmark and the entity name.          # Create the entity header. It contains a bookmark and the entity name.
544          print HTMLOUT "<a name=\"$key\"></a><h3>$key</h3>\n";          $retVal .= "<a name=\"$key\"></a><h3>$key</h3>\n";
545          # Get the entity data.          # Get the entity data.
546          my $entityData = $entityList->{$key};          my $entityData = $entityList->{$key};
547          # If there's descriptive text, display it.          # If there's descriptive text, display it.
548          if (my $notes = $entityData->{Notes}) {          if (my $notes = $entityData->{Notes}) {
549              print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
550          }          }
551          # Now we want a list of the entity's relationships. First, we set up the relationship subsection.          # See if we need a list of the entity's relationships.
552          print HTMLOUT "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          my $relCount = keys %{$relationshipList};
553            if ($relCount > 0) {
554                # First, we set up the relationship subsection.
555                $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
556          # Loop through the relationships.          # Loop through the relationships.
557          for my $relationship (sort keys %{$relationshipList}) {          for my $relationship (sort keys %{$relationshipList}) {
558              # Get the relationship data.              # Get the relationship data.
# Line 460  Line 562 
562                  # Get the relationship sentence and append the arity.                  # Get the relationship sentence and append the arity.
563                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);
564                  # Display the relationship data.                  # Display the relationship data.
565                  print HTMLOUT "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";                      $retVal .= "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";
566              }              }
567          }          }
568          # Close off the relationship list.          # Close off the relationship list.
569          print HTMLOUT "</ul>\n";              $retVal .= "</ul>\n";
570            }
571          # Get the entity's relations.          # Get the entity's relations.
572          my $relationList = $entityData->{Relations};          my $relationList = $entityData->{Relations};
573          # Create a header for the relation subsection.          # Create a header for the relation subsection.
574          print HTMLOUT "<h4>Relations for <b>$key</b></h4>\n";          $retVal .= "<h4>Relations for <b>$key</b></h4>\n";
575          # Loop through the relations, displaying them.          # Loop through the relations, displaying them.
576          for my $relation (sort keys %{$relationList}) {          for my $relation (sort keys %{$relationList}) {
577              my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});              my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});
578              print HTMLOUT $htmlString;              $retVal .= $htmlString;
579          }          }
580      }      }
581      # Denote we're starting the relationship section.      # Denote we're starting the relationship section.
582      print HTMLOUT "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";      $retVal .= "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";
583      # Loop through the relationships.      # Loop through the relationships.
584      for my $key (sort keys %{$relationshipList}) {      for my $key (sort keys %{$relationshipList}) {
585          Trace("Building MetaData entry for $key relationship.") if T(4);          Trace("Building MetaData entry for $key relationship.") if T(4);
# Line 484  Line 587 
587          my $relationshipStructure = $relationshipList->{$key};          my $relationshipStructure = $relationshipList->{$key};
588          # Create the relationship header.          # Create the relationship header.
589          my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);          my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);
590          print HTMLOUT "<h3><a name=\"$key\"></a>$headerText</h3>\n";          $retVal .= "<h3><a name=\"$key\"></a>$headerText</h3>\n";
591          # Get the entity names.          # Get the entity names.
592          my $fromEntity = $relationshipStructure->{from};          my $fromEntity = $relationshipStructure->{from};
593          my $toEntity = $relationshipStructure->{to};          my $toEntity = $relationshipStructure->{to};
# Line 494  Line 597 
597          # since both sentences will say the same thing.          # since both sentences will say the same thing.
598          my $arity = $relationshipStructure->{arity};          my $arity = $relationshipStructure->{arity};
599          if ($arity eq "11") {          if ($arity eq "11") {
600              print HTMLOUT "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";
601          } else {          } else {
602              print HTMLOUT "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";
603              if ($arity eq "MM" && $fromEntity ne $toEntity) {              if ($arity eq "MM" && $fromEntity ne $toEntity) {
604                  print HTMLOUT "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";                  $retVal .= "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";
605              }              }
606          }          }
607          print HTMLOUT "</p>\n";          $retVal .= "</p>\n";
608          # If there are notes on this relationship, display them.          # If there are notes on this relationship, display them.
609          if (my $notes = $relationshipStructure->{Notes}) {          if (my $notes = $relationshipStructure->{Notes}) {
610              print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
611          }          }
612          # Generate the relationship's relation table.          # Generate the relationship's relation table.
613          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
614          print HTMLOUT $htmlString;          $retVal .= $htmlString;
615      }      }
616      Trace("Building MetaData join table.") if T(4);      Trace("Building MetaData join table.") if T(4);
617      # Denote we're starting the join table.      # Denote we're starting the join table.
618      print HTMLOUT "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";      $retVal .= "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";
619      # Create a table header.      # Create a table header.
620      print HTMLOUT _OpenTable("Join Table", "Source", "Target", "Join Condition");      $retVal .= _OpenTable("Join Table", "Source", "Target", "Join Condition");
621      # Loop through the joins.      # Loop through the joins.
622      my $joinTable = $metadata->{Joins};      my $joinTable = $metadata->{Joins};
623      my @joinKeys = keys %{$joinTable};      my @joinKeys = keys %{$joinTable};
# Line 527  Line 630 
630          my $target = $self->ComputeObjectSentence($targetRelation);          my $target = $self->ComputeObjectSentence($targetRelation);
631          my $clause = $joinTable->{$joinKey};          my $clause = $joinTable->{$joinKey};
632          # Display them in a table row.          # Display them in a table row.
633          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";
634      }      }
635      # Close the table.      # Close the table.
636      print HTMLOUT _CloseTable();      $retVal .= _CloseTable();
637      # Close the document.      Trace("Built MetaData HTML.") if T(3);
638      print HTMLOUT "</body>\n</html>\n";      # Return the HTML.
639      # Close the file.      return $retVal;
     close HTMLOUT;  
     Trace("Built MetaData web page.") if T(3);  
640  }  }
641    
642  =head3 DumpMetaData  =head3 DumpMetaData
# Line 553  Line 654 
654      return Data::Dumper::Dumper($self->{_metaData});      return Data::Dumper::Dumper($self->{_metaData});
655  }  }
656    
657    =head3 FindIndexForEntity
658    
659    C<< my $indexFound = ERDB::FindIndexForEntity($xml, $entityName, $attributeName); >>
660    
661    This method locates the entry in an entity's index list that begins with the
662    specified attribute name. If the entity has no index list, one will be
663    created. This method works on raw XML, not a live ERDB object.
664    
665    =over 4
666    
667    =item xml
668    
669    The raw XML structure defining the database.
670    
671    =item entityName
672    
673    The name of the relevant entity.
674    
675    =item attributeName
676    
677    The name of the attribute relevant to the search.
678    
679    =item RETURN
680    
681    The numerical index in the index list of the index entry for the specified entity and
682    attribute, or C<undef> if no such index exists.
683    
684    =back
685    
686    =cut
687    
688    sub FindIndexForEntity {
689        # Get the parameters.
690        my ($xml, $entityName, $attributeName) = @_;
691        # Declare the return variable.
692        my $retVal;
693        # Get the named entity.
694        my $entityData = $xml->{Entities}->{$entityName};
695        if (! $entityData) {
696            Confess("Entity $entityName not found in DBD structure.");
697        } else {
698            # Insure it has an index list.
699            if (! exists $entityData->{Indexes}) {
700                $entityData->{Indexes} = [];
701            } else {
702                # Search for the desired index.
703                my $indexList = $entityData->{Indexes};
704                my $n = scalar @{$indexList};
705                Trace("Searching $n indexes in index list for $entityName.") if T(2);
706                # We use an indexed FOR here because we're returning an
707                # index number instead of an object. We do THAT so we can
708                # delete the index from the list if needed.
709                for (my $i = 0; $i < $n && !defined($retVal); $i++) {
710                    my $index = $indexList->[$i];
711                    my $fields = $index->{IndexFields};
712                    # Technically this IF should be safe (that is, we are guaranteed
713                    # the existence of a "$fields->[0]"), because when we load the XML
714                    # we have SuppressEmpty specified.
715                    if ($fields->[0]->{name} eq $attributeName) {
716                        $retVal = $i;
717                    }
718                }
719            }
720        }
721        Trace("Index for $attributeName of $entityName found at position $retVal.") if defined($retVal) && T(3);
722        Trace("Index for $attributeName not found in $entityName.") if !defined($retVal) && T(3);
723        # Return the result.
724        return $retVal;
725    }
726    
727  =head3 CreateTables  =head3 CreateTables
728    
729  C<< $erdb->CreateTables(); >>  C<< $erdb->CreateTables(); >>
# Line 640  Line 811 
811      Trace("Creating table $relationName: $fieldThing") if T(2);      Trace("Creating table $relationName: $fieldThing") if T(2);
812      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);
813      Trace("Relation $relationName created in database.") if T(2);      Trace("Relation $relationName created in database.") if T(2);
814      # If we want to build the indexes, we do it here.      # If we want to build the indexes, we do it here. Note that the full-text search
815        # index will not be built until the table has been loaded.
816      if ($indexFlag) {      if ($indexFlag) {
817          $self->CreateIndex($relationName);          $self->CreateIndex($relationName);
818      }      }
# Line 736  Line 908 
908          my $fieldType = $fieldTypes->[$i]->{type};          my $fieldType = $fieldTypes->[$i]->{type};
909          # If it's a hash string, digest it in place.          # If it's a hash string, digest it in place.
910          if ($fieldType eq 'hash-string') {          if ($fieldType eq 'hash-string') {
911              $fieldList->[$i] = md5_base64($fieldList->[$i]);              $fieldList->[$i] = $self->DigestKey($fieldList->[$i]);
912            }
913          }          }
914      }      }
915    
916    =head3 DigestKey
917    
918    C<< my $digested = $erdb->DigestKey($keyValue); >>
919    
920    Return the digested value of a symbolic key. The digested value can then be plugged into a
921    key-based search into a table with key-type hash-string.
922    
923    Currently the digesting process is independent of the database structure, but that may not
924    always be the case, so this is an instance method instead of a static method.
925    
926    =over 4
927    
928    =item keyValue
929    
930    Key value to digest.
931    
932    =item RETURN
933    
934    Digested value of the key.
935    
936    =back
937    
938    =cut
939    
940    sub DigestKey {
941        # Get the parameters.
942        my ($self, $keyValue) = @_;
943        # Compute the digest.
944        my $retVal = md5_base64($keyValue);
945        # Return the result.
946        return $retVal;
947  }  }
948    
949  =head3 CreateIndex  =head3 CreateIndex
# Line 764  Line 969 
969      for my $indexName (keys %{$indexHash}) {      for my $indexName (keys %{$indexHash}) {
970          my $indexData = $indexHash->{$indexName};          my $indexData = $indexHash->{$indexName};
971          # Get the index's field list.          # Get the index's field list.
972          my @fieldList = _FixNames(@{$indexData->{IndexFields}});          my @rawFields = @{$indexData->{IndexFields}};
973            # Get a hash of the relation's field types.
974            my %types = map { $_->{name} => $_->{type} } @{$relationData->{Fields}};
975            # We need to check for text fields so we can append a length limitation for them. To do
976            # that, we need the relation's field list.
977            my $relFields = $relationData->{Fields};
978            for (my $i = 0; $i <= $#rawFields; $i++) {
979                # Get the field type.
980                my $field = $rawFields[$i];
981                my $type = $types{$field};
982                # Ask if it requires using prefix notation for the index.
983                my $mod = $TypeTable{$type}->{indexMod};
984                Trace("Field $field ($i) in $relationName has type $type and indexMod $mod.") if T(3);
985                if ($mod) {
986                    # Append the prefix length to the field name,
987                    $rawFields[$i] .= "($mod)";
988                }
989            }
990            my @fieldList = _FixNames(@rawFields);
991          my $flds = join(', ', @fieldList);          my $flds = join(', ', @fieldList);
992          # Get the index's uniqueness flag.          # Get the index's uniqueness flag.
993          my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
994          # Create the index.          # Create the index.
995          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
996                                      flds => $flds, unique => $unique);                                      flds => $flds, kind => $unique);
997          if ($rv) {          if ($rv) {
998              Trace("Index created: $indexName for $relationName ($flds)") if T(1);              Trace("Index created: $indexName for $relationName ($flds)") if T(1);
999          } else {          } else {
# Line 779  Line 1002 
1002      }      }
1003  }  }
1004    
1005    =head3 GetSecondaryFields
1006    
1007    C<< my %fieldTuples = $erdb->GetSecondaryFields($entityName); >>
1008    
1009    This method will return a list of the name and type of each of the secondary
1010    fields for a specified entity. Secondary fields are stored in two-column tables
1011    in addition to the primary entity table. This enables the field to have no value
1012    or to have multiple values.
1013    
1014    =over 4
1015    
1016    =item entityName
1017    
1018    Name of the entity whose secondary fields are desired.
1019    
1020    =item RETURN
1021    
1022    Returns a hash mapping the field names to their field types.
1023    
1024    =back
1025    
1026    =cut
1027    
1028    sub GetSecondaryFields {
1029        # Get the parameters.
1030        my ($self, $entityName) = @_;
1031        # Declare the return variable.
1032        my %retVal = ();
1033        # Look for the entity.
1034        my $table = $self->GetFieldTable($entityName);
1035        # Loop through the fields, pulling out the secondaries.
1036        for my $field (sort keys %{$table}) {
1037            if ($table->{$field}->{relation} ne $entityName) {
1038                # Here we have a secondary field.
1039                $retVal{$field} = $table->{$field}->{type};
1040            }
1041        }
1042        # Return the result.
1043        return %retVal;
1044    }
1045    
1046    =head3 GetFieldRelationName
1047    
1048    C<< my $name = $erdb->GetFieldRelationName($objectName, $fieldName); >>
1049    
1050    Return the name of the relation containing a specified field.
1051    
1052    =over 4
1053    
1054    =item objectName
1055    
1056    Name of the entity or relationship containing the field.
1057    
1058    =item fieldName
1059    
1060    Name of the relevant field in that entity or relationship.
1061    
1062    =item RETURN
1063    
1064    Returns the name of the database relation containing the field, or C<undef> if
1065    the field does not exist.
1066    
1067    =back
1068    
1069    =cut
1070    
1071    sub GetFieldRelationName {
1072        # Get the parameters.
1073        my ($self, $objectName, $fieldName) = @_;
1074        # Declare the return variable.
1075        my $retVal;
1076        # Get the object field table.
1077        my $table = $self->GetFieldTable($objectName);
1078        # Only proceed if the field exists.
1079        if (exists $table->{$fieldName}) {
1080            # Determine the name of the relation that contains this field.
1081            $retVal = $table->{$fieldName}->{relation};
1082        }
1083        # Return the result.
1084        return $retVal;
1085    }
1086    
1087    =head3 DeleteValue
1088    
1089    C<< my $numDeleted = $erdb->DeleteValue($entityName, $id, $fieldName, $fieldValue); >>
1090    
1091    Delete secondary field values from the database. This method can be used to delete all
1092    values of a specified field for a particular entity instance, or only a single value.
1093    
1094    Secondary fields are stored in two-column relations separate from an entity's primary
1095    table, and as a result a secondary field can legitimately have no value or multiple
1096    values. Therefore, it makes sense to talk about deleting secondary fields where it
1097    would not make sense for primary fields.
1098    
1099    =over 4
1100    
1101    =item entityName
1102    
1103    Name of the entity from which the fields are to be deleted.
1104    
1105    =item id
1106    
1107    ID of the entity instance to be processed. If the instance is not found, this
1108    method will have no effect. If C<undef> is specified, all values for all of
1109    the entity instances will be deleted.
1110    
1111    =item fieldName
1112    
1113    Name of the field whose values are to be deleted.
1114    
1115    =item fieldValue (optional)
1116    
1117    Value to be deleted. If not specified, then all values of the specified field
1118    will be deleted for the entity instance. If specified, then only the values which
1119    match this parameter will be deleted.
1120    
1121    =item RETURN
1122    
1123    Returns the number of rows deleted.
1124    
1125    =back
1126    
1127    =cut
1128    
1129    sub DeleteValue {
1130        # Get the parameters.
1131        my ($self, $entityName, $id, $fieldName, $fieldValue) = @_;
1132        # Declare the return value.
1133        my $retVal = 0;
1134        # We need to set up an SQL command to do the deletion. First, we
1135        # find the name of the field's relation.
1136        my $table = $self->GetFieldTable($entityName);
1137        my $field = $table->{$fieldName};
1138        my $relation = $field->{relation};
1139        # Make sure this is a secondary field.
1140        if ($relation eq $entityName) {
1141            Confess("Cannot delete values of $fieldName for $entityName.");
1142        } else {
1143            # Set up the SQL command to delete all values.
1144            my $sql = "DELETE FROM $relation";
1145            # Build the filter.
1146            my @filters = ();
1147            my @parms = ();
1148            # Check for a filter by ID.
1149            if (defined $id) {
1150                push @filters, "id = ?";
1151                push @parms, $id;
1152            }
1153            # Check for a filter by value.
1154            if (defined $fieldValue) {
1155                push @filters, "$fieldName = ?";
1156                push @parms, $fieldValue;
1157            }
1158            # Append the filters to the command.
1159            if (@filters) {
1160                $sql .= " WHERE " . join(" AND ", @filters);
1161            }
1162            # Execute the command.
1163            my $dbh = $self->{_dbh};
1164            $retVal = $dbh->SQL($sql, 0, @parms);
1165        }
1166        # Return the result.
1167        return $retVal;
1168    }
1169    
1170  =head3 LoadTables  =head3 LoadTables
1171    
1172  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>
# Line 873  Line 1261 
1261      return sort keys %{$entityList};      return sort keys %{$entityList};
1262  }  }
1263    
1264    =head3 GetDataTypes
1265    
1266    C<< my %types = ERDB::GetDataTypes(); >>
1267    
1268    Return a table of ERDB data types. The table returned is a hash of hashes.
1269    The keys of the big hash are the datatypes. Each smaller hash has several
1270    values used to manage the data. The most interesting is the SQL type (key
1271    C<sqlType>) and the descriptive node (key C<notes>).
1272    
1273    Note that changing the values in the smaller hashes will seriously break
1274    things, so this data should be treated as read-only.
1275    
1276    =cut
1277    
1278    sub GetDataTypes {
1279        return %TypeTable;
1280    }
1281    
1282    
1283  =head3 IsEntity  =head3 IsEntity
1284    
1285  C<< my $flag = $erdb->IsEntity($entityName); >>  C<< my $flag = $erdb->IsEntity($entityName); >>
# Line 902  Line 1309 
1309    
1310  =head3 Get  =head3 Get
1311    
1312  C<< my $query = $erdb->Get(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  C<< my $query = $erdb->Get(\@objectNames, $filterClause, \@params); >>
1313    
1314  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.
1315  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 1317 
1317  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
1318  $genus.  $genus.
1319    
1320  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", [$genus]); >>
1321    
1322  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
1323  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 1334 
1334  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
1335  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,
1336    
1337  C<< $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]); >>
1338    
1339  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
1340  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 1391 
1391    
1392  C<< "LIMIT 10" >>  C<< "LIMIT 10" >>
1393    
1394  =item param1, param2, ..., paramN  =item params
1395    
1396  Parameter values to be substituted into the filter clause.  Reference to a list of parameter values to be substituted into the filter clause.
1397    
1398  =item RETURN  =item RETURN
1399    
# Line 998  Line 1405 
1405    
1406  sub Get {  sub Get {
1407      # Get the parameters.      # Get the parameters.
1408      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $objectNames, $filterClause, $params) = @_;
1409      # Adjust the list of object names to account for multiple occurrences of the      # Process the SQL stuff.
1410      # same object. We start with a hash table keyed on object name that will      my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1411      # return the object suffix. The first time an object is encountered it will          $self->_SetupSQL($objectNames, $filterClause);
1412      # not be found in the hash. The next time the hash will map the object name      # Create the query.
1413      # to 2, then 3, and so forth.      my $command = "SELECT DISTINCT " . join(".*, ", @{$mappedNameListRef}) .
1414      my %objectHash = ();          ".* $suffix";
1415      # This list will contain the object names as they are to appear in the      my $sth = $self->_GetStatementHandle($command, $params);
1416      # FROM list.      # Now we create the relation map, which enables DBQuery to determine the order, name
1417      my @fromList = ();      # and mapped name for each object in the query.
1418      # This list contains the suffixed object name for each object. It is exactly      my @relationMap = ();
1419      # parallel to the list in the $objectNames parameter.      for my $mappedName (@{$mappedNameListRef}) {
1420      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;  
1421          }          }
1422        # Return the statement object.
1423        my $retVal = DBQuery::_new($self, $sth, \@relationMap);
1424        return $retVal;
1425      }      }
1426      # Construct the SELECT statement. The general pattern is  
1427      #  
1428      # SELECT name1.*, name2.*, ... nameN.* FROM name1, name2, ... nameN  
1429      #  =head3 Search
1430      my $dbh = $self->{_dbh};  
1431      my $command = "SELECT DISTINCT " . join('.*, ', @mappedNameList) . ".* FROM " .  C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>
1432                  join(', ', @fromList);  
1433      # Check for a filter clause.  Perform a full text search with filtering. The search will be against a specified object
1434      if ($filterClause) {  in the object name list. That object will get an extra field containing the search
1435          # Here we have one, so we convert its field names and add it to the query. First,  relevance. Note that except for the search expression, the parameters of this method are
1436          # We create a copy of the filter string we can work with.  the same as those for L</Get> and follow the same rules.
1437          my $filterString = $filterClause;  
1438          # Next, we sort the object names by length. This helps protect us from finding  =over 4
1439          # object names inside other object names when we're doing our search and replace.  
1440          my @sortedNames = sort { length($b) - length($a) } @mappedNameList;  =item searchExpression
1441          # We will also keep a list of conditions to add to the WHERE clause in order to link  
1442          # entities and relationships as well as primary relations to secondary ones.  Boolean search expression for the text fields of the target object. The default mode for
1443          my @joinWhere = ();  a Boolean search expression is OR, but we want the default to be AND, so we will
1444          # The final preparatory step is to create a hash table of relation names. The  add a C<+> operator to each word with no other operator before it.
1445          # table begins with the relation names already in the SELECT command. We may  
1446          # need to add relations later if there is filtering on a field in a secondary  =item idx
1447          # relation. The secondary relations are the ones that contain multiply-  
1448          # occurring or optional fields.  Index in the I<$objectNames> list of the table to be searched in full-text mode.
1449          my %fromNames = map { $_ => 1 } @sortedNames;  
1450          # We are ready to begin. We loop through the object names, replacing each  =item objectNames
1451          # object name's field references by the corresponding SQL field reference.  
1452          # Along the way, if we find a secondary relation, we will need to add it  List containing the names of the entity and relationship objects to be retrieved.
1453          # to the FROM clause.  
1454          for my $mappedName (@sortedNames) {  =item filterClause
1455              # Get the length of the object name plus 2. This is the value we add to the  
1456              # size of the field name to determine the size of the field reference as a  WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1457              # whole.  be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
1458              my $nameLength = 2 + length $mappedName;  specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
1459              # Get the real object name for this mapped name.  in the filter clause should be added to the parameter list as additional parameters. The
1460              my $objectName = $mappedNameHash{$mappedName};  fields in a filter clause can come from primary entity relations, relationship relations,
1461              Trace("Processing $mappedName for object $objectName.") if T(4);  or secondary entity relations; however, all of the entities and relationships involved must
1462              # Get the object's field list.  be included in the list of object names.
1463              my $fieldList = $self->GetFieldTable($objectName);  
1464              # Find the field references for this object.  =item params
1465              while ($filterString =~ m/$mappedName\(([^)]*)\)/g) {  
1466                  # At this point, $1 contains the field name, and the current position  Reference to a list of parameter values to be substituted into the filter clause.
1467                  # is set immediately after the final parenthesis. We pull out the name of  
1468                  # the field and the position and length of the field reference as a whole.  =item RETURN
1469                  my $fieldName = $1;  
1470                  my $len = $nameLength + length $fieldName;  Returns a query object for the specified search.
1471                  my $pos = pos($filterString) - $len;  
1472                  # Insure the field exists.  =back
1473                  if (!exists $fieldList->{$fieldName}) {  
1474                      Confess("Field $fieldName not found for object $objectName.");  =cut
1475                  } else {  
1476                      Trace("Processing $fieldName at position $pos.") if T(4);  sub Search {
1477                      # Get the field's relation.      # Get the parameters.
1478                      my $relationName = $fieldList->{$fieldName}->{relation};      my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1479                      # Now we have a secondary relation. We need to insure it matches the      # Declare the return variable.
1480                      # mapped name of the primary relation. First we peel off the suffix      my $retVal;
1481                      # from the mapped name.      # Create a safety copy of the parameter list. Note we have to be careful to insure
1482                      my $mappingSuffix = substr $mappedName, length($objectName);      # a parameter list exists before we copy it.
1483                      # Put the mapping suffix onto the relation name to get the      my @myParams = ();
1484                      # mapped relation name.      if (defined $params) {
1485                      my $mappedRelationName = "$relationName$mappingSuffix";          @myParams = @{$params};
1486                      # Insure the relation is in the FROM clause.      }
1487                      if (!exists $fromNames{$mappedRelationName}) {      # Get the first object's structure so we have access to the searchable fields.
1488                          # Add the relation to the FROM clause.      my $object1Name = $objectNames->[$idx];
1489                          if ($mappedRelationName eq $relationName) {      my $object1Structure = $self->_GetStructure($object1Name);
1490                              # The name is un-mapped, so we add it without      # Get the field list.
1491                              # any frills.      if (! exists $object1Structure->{searchFields}) {
1492                              $command .= ", $relationName";          Confess("No searchable index for $object1Name.");
                             push @joinWhere, "$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.");  
1493              } else {              } else {
1494                  # Get the join clause.          # Get the field list.
1495                  my $unMappedJoin = $joinTable->{$joinKey};          my @fields = @{$object1Structure->{searchFields}};
1496                  # Fix the names.          # Clean the search expression.
1497                  $unMappedJoin =~ s/$lastObject/$lastMappedObject/;          my $actualKeywords = $self->CleanKeywords($searchExpression);
1498                  $unMappedJoin =~ s/$thisObject/$thisMappedObject/;          # Prefix a "+" to each uncontrolled word. This converts the default
1499                  push @joinWhere, $unMappedJoin;          # search mode from OR to AND.
1500                  # Save this object as the last object for the next iteration.          $actualKeywords =~ s/(^|\s)(\w|")/$1\+$2/g;
1501                  $lastMappedObject = $thisMappedObject;          Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1502              }          # We need two match expressions, one for the filter clause and one in the
1503          }          # query itself. Both will use a parameter mark, so we need to push the
1504          # Now we need to handle the whole ORDER BY / LIMIT thing. The important part          # search expression onto the front of the parameter list twice.
1505          # here is we want the filter clause to be empty if there's no WHERE filter.          unshift @myParams, $actualKeywords, $actualKeywords;
1506          # We'll put the ORDER BY / LIMIT clauses in the following variable.          # Build the match expression.
1507          my $orderClause = "";          my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
1508          # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy          my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
1509          # operator so that we find the first occurrence of either verb.          # Process the SQL stuff.
1510          if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {          my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1511              # Here we have an ORDER BY or LIMIT verb. Split it off of the filter string.              $self->_SetupSQL($objectNames, $filterClause, $matchClause);
1512              my $pos = pos $filterString;          # Create the query. Note that the match clause is inserted at the front of
1513              $orderClause = $2 . substr($filterString, $pos);          # the select fields.
1514              $filterString = $1;          my $command = "SELECT DISTINCT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .
1515                ".* $suffix";
1516            my $sth = $self->_GetStatementHandle($command, \@myParams);
1517            # Now we create the relation map, which enables DBQuery to determine the order, name
1518            # and mapped name for each object in the query.
1519            my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
1520            # Return the statement object.
1521            $retVal = DBQuery::_new($self, $sth, \@relationMap, $object1Name);
1522          }          }
1523          # 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)";  
1524          }          }
1525          if (@joinWhere) {  
1526              $command .= " WHERE " . join(' AND ', @joinWhere);  =head3 GetFlat
1527    
1528    C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>
1529    
1530    This is a variation of L</GetAll> that asks for only a single field per record and
1531    returns a single flattened list.
1532    
1533    =over 4
1534    
1535    =item objectNames
1536    
1537    List containing the names of the entity and relationship objects to be retrieved.
1538    
1539    =item filterClause
1540    
1541    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1542    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
1543    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
1544    parameter list as additional parameters. The fields in a filter clause can come from primary
1545    entity relations, relationship relations, or secondary entity relations; however, all of the
1546    entities and relationships involved must be included in the list of object names.
1547    
1548    =item parameterList
1549    
1550    List of the parameters to be substituted in for the parameters marks in the filter clause.
1551    
1552    =item field
1553    
1554    Name of the field to be used to get the elements of the list returned.
1555    
1556    =item RETURN
1557    
1558    Returns a list of values.
1559    
1560    =back
1561    
1562    =cut
1563    #: Return Type @;
1564    sub GetFlat {
1565        # Get the parameters.
1566        my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
1567        # Construct the query.
1568        my $query = $self->Get($objectNames, $filterClause, $parameterList);
1569        # Create the result list.
1570        my @retVal = ();
1571        # Loop through the records, adding the field values found to the result list.
1572        while (my $row = $query->Fetch()) {
1573            push @retVal, $row->Value($field);
1574          }          }
1575          # Add the sort or limit clause (if any) to the SELECT command.      # Return the list created.
1576          if ($orderClause) {      return @retVal;
             $command .= " $orderClause";  
1577          }          }
1578    
1579    =head3 SpecialFields
1580    
1581    C<< my %specials = $erdb->SpecialFields($entityName); >>
1582    
1583    Return a hash mapping special fields in the specified entity to the value of their
1584    C<special> attribute. This enables the subclass to get access to the special field
1585    attributes without needed to plumb the internal ERDB data structures.
1586    
1587    =over 4
1588    
1589    =item entityName
1590    
1591    Name of the entity whose special fields are desired.
1592    
1593    =item RETURN
1594    
1595    Returns a hash. The keys of the hash are the special field names, and the values
1596    are the values from each special field's C<special> attribute.
1597    
1598    =back
1599    
1600    =cut
1601    
1602    sub SpecialFields {
1603        # Get the parameters.
1604        my ($self, $entityName) = @_;
1605        # Declare the return variable.
1606        my %retVal = ();
1607        # Find the entity's data structure.
1608        my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1609        # Loop through its fields, adding each special field to the return hash.
1610        my $fieldHash = $entityData->{Fields};
1611        for my $fieldName (keys %{$fieldHash}) {
1612            my $fieldData = $fieldHash->{$fieldName};
1613            if (exists $fieldData->{special}) {
1614                $retVal{$fieldName} = $fieldData->{special};
1615      }      }
     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}];  
1616      }      }
1617      # Return the statement object.      # Return the result.
1618      my $retVal = DBQuery::_new($self, $sth, \@relationMap);      return %retVal;
     return $retVal;  
1619  }  }
1620    
1621  =head3 Delete  =head3 Delete
1622    
1623  C<< my $stats = $erdb->Delete($entityName, $objectID); >>  C<< my $stats = $erdb->Delete($entityName, $objectID, %options); >>
1624    
1625  Delete an entity instance from the database. The instance is deleted along with all entity and  Delete an entity instance from the database. The instance is deleted along with all entity and
1626  relationship instances dependent on it. The idea of dependence here is recursive. An object is  relationship instances dependent on it. The definition of I<dependence> is recursive.
1627  always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many  
1628  relationship connected to a dependent entity or the "to" entity connected to a 1-to-many  An object is always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many
1629    relationship connected to a dependent entity or if it is the "to" entity connected to a 1-to-many
1630  dependent relationship.  dependent relationship.
1631    
1632  =over 4  =over 4
# Line 1217  Line 1640 
1640  ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),  ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),
1641  then it is presumed to by a LIKE pattern.  then it is presumed to by a LIKE pattern.
1642    
1643  =item testFlag  =item options
1644    
1645  If TRUE, the delete statements will be traced without being executed.  A hash detailing the options for this delete operation.
1646    
1647  =item RETURN  =item RETURN
1648    
# Line 1228  Line 1651 
1651    
1652  =back  =back
1653    
1654    The permissible options for this method are as follows.
1655    
1656    =over 4
1657    
1658    =item testMode
1659    
1660    If TRUE, then the delete statements will be traced, but no changes will be made to the database.
1661    
1662    =item keepRoot
1663    
1664    If TRUE, then the entity instances will not be deleted, only the dependent records.
1665    
1666    =back
1667    
1668  =cut  =cut
1669  #: Return Type $%;  #: Return Type $%;
1670  sub Delete {  sub Delete {
1671      # Get the parameters.      # Get the parameters.
1672      my ($self, $entityName, $objectID, $testFlag) = @_;      my ($self, $entityName, $objectID, %options) = @_;
1673      # Declare the return variable.      # Declare the return variable.
1674      my $retVal = Stats->new();      my $retVal = Stats->new();
1675      # Get the DBKernel object.      # Get the DBKernel object.
# Line 1249  Line 1686 
1686      # FROM-relationships and entities.      # FROM-relationships and entities.
1687      my @fromPathList = ();      my @fromPathList = ();
1688      my @toPathList = ();      my @toPathList = ();
1689      # This final hash is used to remember what work still needs to be done. We push paths      # This final list is used to remember what work still needs to be done. We push paths
1690      # onto the list, then pop them off to extend the paths. We prime it with the starting      # onto the list, then pop them off to extend the paths. We prime it with the starting
1691      # point. Note that we will work hard to insure that the last item on a path in the      # point. Note that we will work hard to insure that the last item on a path in the
1692      # TODO list is always an entity.      # to-do list is always an entity.
1693      my @todoList = ([$entityName]);      my @todoList = ([$entityName]);
1694      while (@todoList) {      while (@todoList) {
1695          # Get the current path.          # Get the current path.
# Line 1260  Line 1697 
1697          # Copy it into a list.          # Copy it into a list.
1698          my @stackedPath = @{$current};          my @stackedPath = @{$current};
1699          # Pull off the last item on the path. It will always be an entity.          # Pull off the last item on the path. It will always be an entity.
1700          my $entityName = pop @stackedPath;          my $myEntityName = pop @stackedPath;
1701          # Add it to the alreadyFound list.          # Add it to the alreadyFound list.
1702          $alreadyFound{$entityName} = 1;          $alreadyFound{$myEntityName} = 1;
1703            # Figure out if we need to delete this entity.
1704            if ($myEntityName ne $entityName || ! $options{keepRoot}) {
1705          # Get the entity data.          # Get the entity data.
1706          my $entityData = $self->_GetStructure($entityName);              my $entityData = $self->_GetStructure($myEntityName);
1707          # The first task is to loop through the entity's relation. A DELETE command will              # Loop through the entity's relations. A DELETE command will be needed for each of them.
         # be needed for each of them.  
1708          my $relations = $entityData->{Relations};          my $relations = $entityData->{Relations};
1709          for my $relation (keys %{$relations}) {          for my $relation (keys %{$relations}) {
1710              my @augmentedList = (@stackedPath, $relation);              my @augmentedList = (@stackedPath, $relation);
1711              push @fromPathList, \@augmentedList;              push @fromPathList, \@augmentedList;
1712          }          }
1713            }
1714          # Now we need to look for relationships connected to this entity.          # Now we need to look for relationships connected to this entity.
1715          my $relationshipList = $self->{_metaData}->{Relationships};          my $relationshipList = $self->{_metaData}->{Relationships};
1716          for my $relationshipName (keys %{$relationshipList}) {          for my $relationshipName (keys %{$relationshipList}) {
1717              my $relationship = $relationshipList->{$relationshipName};              my $relationship = $relationshipList->{$relationshipName};
1718              # Check the FROM field. We're only interested if it's us.              # Check the FROM field. We're only interested if it's us.
1719              if ($relationship->{from} eq $entityName) {              if ($relationship->{from} eq $myEntityName) {
1720                  # Add the path to this relationship.                  # Add the path to this relationship.
1721                  my @augmentedList = (@stackedPath, $entityName, $relationshipName);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1722                  push @fromPathList, \@augmentedList;                  push @fromPathList, \@augmentedList;
1723                  # Check the arity. If it's MM we're done. If it's 1M                  # Check the arity. If it's MM we're done. If it's 1M
1724                  # and the target hasn't been seen yet, we want to                  # and the target hasn't been seen yet, we want to
# Line 1298  Line 1737 
1737              }              }
1738              # Now check the TO field. In this case only the relationship needs              # Now check the TO field. In this case only the relationship needs
1739              # deletion.              # deletion.
1740              if ($relationship->{to} eq $entityName) {              if ($relationship->{to} eq $myEntityName) {
1741                  my @augmentedList = (@stackedPath, $entityName, $relationshipName);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1742                  push @toPathList, \@augmentedList;                  push @toPathList, \@augmentedList;
1743              }              }
1744          }          }
1745      }      }
1746      # Create the first qualifier for the WHERE clause. This selects the      # Create the first qualifier for the WHERE clause. This selects the
1747      # keys of the primary entity records to be deleted. When we're deleting      # keys of the primary entity records to be deleted. When we're deleting
1748      # from a dependent table, we construct a join page from the first qualifier      # from a dependent table, we construct a join path from the first qualifier
1749      # to the table containing the dependent records to delete.      # to the table containing the dependent records to delete.
1750      my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");      my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
1751      # We need to make two passes. The first is through the to-list, and      # We need to make two passes. The first is through the to-list, and
# Line 1345  Line 1784 
1784                  }                  }
1785              }              }
1786              # Now we have our desired DELETE statement.              # Now we have our desired DELETE statement.
1787              if ($testFlag) {              if ($options{testMode}) {
1788                  # Here the user wants to trace without executing.                  # Here the user wants to trace without executing.
1789                  Trace($stmt) if T(0);                  Trace($stmt) if T(0);
1790              } else {              } else {
1791                  # Here we can delete. Note that the SQL method dies with a confessing                  # Here we can delete. Note that the SQL method dies with a confession
1792                  # if an error occurs, so we just go ahead and do it.                  # if an error occurs, so we just go ahead and do it.
1793                  Trace("Executing delete from $target using '$objectID'.") if T(3);                  Trace("Executing delete from $target using '$objectID'.") if T(3);
1794                  my $rv = $db->SQL($stmt, 0, $objectID);                  my $rv = $db->SQL($stmt, 0, $objectID);
# Line 1364  Line 1803 
1803      return $retVal;      return $retVal;
1804  }  }
1805    
1806  =head3 GetList  =head3 Disconnect
   
 C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  
1807    
1808  Return a list of object descriptors for the specified objects as determined by the  C<< $erdb->Disconnect($relationshipName, $originEntityName, $originEntityID); >>
 specified filter clause.  
1809    
1810  This method is essentially the same as L</Get> except it returns a list of objects rather  Disconnect an entity instance from all the objects to which it is related. This
1811  than a query object that can be used to get the results one record at a time.  will delete each relationship instance that connects to the specified entity.
1812    
1813  =over 4  =over 4
1814    
1815  =item objectNames  =item relationshipName
1816    
1817  List containing the names of the entity and relationship objects to be retrieved.  Name of the relationship whose instances are to be deleted.
1818    
1819  =item filterClause  =item originEntityName
1820    
1821  WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  Name of the entity that is to be disconnected.
 be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be  
 specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified  
 in the filter clause should be added to the parameter list as additional parameters. The  
 fields in a filter clause can come from primary entity relations, relationship relations,  
 or secondary entity relations; however, all of the entities and relationships involved must  
 be included in the list of object names.  
1822    
1823  The filter clause can also specify a sort order. To do this, simply follow the filter string  =item originEntityID
 with an ORDER BY clause. For example, the following filter string gets all genomes for a  
 particular genus and sorts them by species name.  
1824    
1825  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>  ID of the entity that is to be disconnected.
1826    
1827    =back
1828    
1829    =cut
1830    
1831    sub Disconnect {
1832        # Get the parameters.
1833        my ($self, $relationshipName, $originEntityName, $originEntityID) = @_;
1834        # Get the relationship descriptor.
1835        my $structure = $self->_GetStructure($relationshipName);
1836        # Insure we have a relationship.
1837        if (! exists $structure->{from}) {
1838            Confess("$relationshipName is not a relationship in the database.");
1839        } else {
1840            # Get the database handle.
1841            my $dbh = $self->{_dbh};
1842            # We'll set this value to 1 if we find our entity.
1843            my $found = 0;
1844            # Loop through the ends of the relationship.
1845            for my $dir ('from', 'to') {
1846                if ($structure->{$dir} eq $originEntityName) {
1847                    # Delete all relationship instances on this side of the entity instance.
1848                    $dbh->SQL("DELETE FROM $relationshipName WHERE ${dir}_link = ?", 0, $originEntityID);
1849                    $found = 1;
1850                }
1851            }
1852            # Insure we found the entity on at least one end.
1853            if (! $found) {
1854                Confess("Entity \"$originEntityName\" does not use $relationshipName.");
1855            }
1856        }
1857    }
1858    
1859    =head3 DeleteRow
1860    
1861    C<< $erdb->DeleteRow($relationshipName, $fromLink, $toLink, \%values); >>
1862    
1863    Delete a row from a relationship. In most cases, only the from-link and to-link are
1864    needed; however, for relationships with intersection data values can be specified
1865    for the other fields using a hash.
1866    
1867    =over 4
1868    
1869    =item relationshipName
1870    
1871    Name of the relationship from which the row is to be deleted.
1872    
1873    =item fromLink
1874    
1875    ID of the entity instance in the From direction.
1876    
1877    =item toLink
1878    
1879    ID of the entity instance in the To direction.
1880    
1881    =item values
1882    
1883    Reference to a hash of other values to be used for filtering the delete.
1884    
1885    =back
1886    
1887    =cut
1888    
1889    sub DeleteRow {
1890        # Get the parameters.
1891        my ($self, $relationshipName, $fromLink, $toLink, $values) = @_;
1892        # Create a hash of all the filter information.
1893        my %filter = ('from-link' => $fromLink, 'to-link' => $toLink);
1894        if (defined $values) {
1895            for my $key (keys %{$values}) {
1896                $filter{$key} = $values->{$key};
1897            }
1898        }
1899        # Build an SQL statement out of the hash.
1900        my @filters = ();
1901        my @parms = ();
1902        for my $key (keys %filter) {
1903            push @filters, _FixName($key) . " = ?";
1904            push @parms, $filter{$key};
1905        }
1906        Trace("Parms for delete row are " . join(", ", map { "\"$_\"" } @parms) . ".") if T(SQL => 4);
1907        my $command = "DELETE FROM $relationshipName WHERE " .
1908                      join(" AND ", @filters);
1909        # Execute it.
1910        my $dbh = $self->{_dbh};
1911        $dbh->SQL($command, undef, @parms);
1912    }
1913    
1914    =head3 SortNeeded
1915    
1916    C<< my $parms = $erdb->SortNeeded($relationName); >>
1917    
1918    Return the pipe command for the sort that should be applied to the specified
1919    relation when creating the load file.
1920    
1921    For example, if the load file should be sorted ascending by the first
1922    field, this method would return
1923    
1924        sort -k1 -t"\t"
1925    
1926    If the first field is numeric, the method would return
1927    
1928        sort -k1n -t"\t"
1929    
1930    Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate
1931    keys using a sort.
1932    
1933    =over 4
1934    
1935    =item relationName
1936    
1937    Name of the relation to be examined.
1938    
1939    =item
1940    
1941    Returns the sort command to use for sorting the relation, suitable for piping.
1942    
1943    =back
1944    
1945    =cut
1946    #: Return Type $;
1947    sub SortNeeded {
1948        # Get the parameters.
1949        my ($self, $relationName) = @_;
1950        # Declare a descriptor to hold the names of the key fields.
1951        my @keyNames = ();
1952        # Get the relation structure.
1953        my $relationData = $self->_FindRelation($relationName);
1954        # Find out if the relation is a primary entity relation,
1955        # a relationship relation, or a secondary entity relation.
1956        my $entityTable = $self->{_metaData}->{Entities};
1957        my $relationshipTable = $self->{_metaData}->{Relationships};
1958        if (exists $entityTable->{$relationName}) {
1959            # Here we have a primary entity relation.
1960            push @keyNames, "id";
1961        } elsif (exists $relationshipTable->{$relationName}) {
1962            # Here we have a relationship. We sort using the FROM index.
1963            my $relationshipData = $relationshipTable->{$relationName};
1964            my $index = $relationData->{Indexes}->{idxFrom};
1965            push @keyNames, @{$index->{IndexFields}};
1966        } else {
1967            # Here we have a secondary entity relation, so we have a sort on the ID field.
1968            push @keyNames, "id";
1969        }
1970        # Now we parse the key names into sort parameters. First, we prime the return
1971        # string.
1972        my $retVal = "sort -t\"\t\" ";
1973        # Get the relation's field list.
1974        my @fields = @{$relationData->{Fields}};
1975        # Loop through the keys.
1976        for my $keyData (@keyNames) {
1977            # Get the key and the ordering.
1978            my ($keyName, $ordering);
1979            if ($keyData =~ /^([^ ]+) DESC/) {
1980                ($keyName, $ordering) = ($1, "descending");
1981            } else {
1982                ($keyName, $ordering) = ($keyData, "ascending");
1983            }
1984            # Find the key's position and type.
1985            my $fieldSpec;
1986            for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {
1987                my $thisField = $fields[$i];
1988                if ($thisField->{name} eq $keyName) {
1989                    # Get the sort modifier for this field type. The modifier
1990                    # decides whether we're using a character, numeric, or
1991                    # floating-point sort.
1992                    my $modifier = $TypeTable{$thisField->{type}}->{sort};
1993                    # If the index is descending for this field, denote we want
1994                    # to reverse the sort order on this field.
1995                    if ($ordering eq 'descending') {
1996                        $modifier .= "r";
1997                    }
1998                    # Store the position and modifier into the field spec, which
1999                    # will stop the inner loop. Note that the field number is
2000                    # 1-based in the sort command, so we have to increment the
2001                    # index.
2002                    $fieldSpec = ($i + 1) . $modifier;
2003                }
2004            }
2005            # Add this field to the sort command.
2006            $retVal .= " -k$fieldSpec";
2007        }
2008        # Return the result.
2009        return $retVal;
2010    }
2011    
2012    =head3 GetList
2013    
2014    C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>
2015    
2016    Return a list of object descriptors for the specified objects as determined by the
2017    specified filter clause.
2018    
2019    This method is essentially the same as L</Get> except it returns a list of objects rather
2020    than a query object that can be used to get the results one record at a time.
2021    
2022    =over 4
2023    
2024    =item objectNames
2025    
2026    List containing the names of the entity and relationship objects to be retrieved.
2027    
2028    =item filterClause
2029    
2030    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
2031    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
2032    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
2033    in the filter clause should be added to the parameter list as additional parameters. The
2034    fields in a filter clause can come from primary entity relations, relationship relations,
2035    or secondary entity relations; however, all of the entities and relationships involved must
2036    be included in the list of object names.
2037    
2038    The filter clause can also specify a sort order. To do this, simply follow the filter string
2039    with an ORDER BY clause. For example, the following filter string gets all genomes for a
2040    particular genus and sorts them by species name.
2041    
2042    C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
2043    
2044  The rules for field references in a sort order are the same as those for field references in the  The rules for field references in a sort order are the same as those for field references in the
2045  filter clause in general; however, odd things may happen if a sort field is from a secondary  filter clause in general; however, odd things may happen if a sort field is from a secondary
2046  relation.  relation.
2047    
2048  =item param1, param2, ..., paramN  =item params
2049    
2050  Parameter values to be substituted into the filter clause.  Reference to a list of parameter values to be substituted into the filter clause.
2051    
2052  =item RETURN  =item RETURN
2053    
# Line 1414  Line 2059 
2059  #: Return Type @%  #: Return Type @%
2060  sub GetList {  sub GetList {
2061      # Get the parameters.      # Get the parameters.
2062      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $objectNames, $filterClause, $params) = @_;
2063      # Declare the return variable.      # Declare the return variable.
2064      my @retVal = ();      my @retVal = ();
2065      # Perform the query.      # Perform the query.
2066      my $query = $self->Get($objectNames, $filterClause, @params);      my $query = $self->Get($objectNames, $filterClause, $params);
2067      # Loop through the results.      # Loop through the results.
2068      while (my $object = $query->Fetch) {      while (my $object = $query->Fetch) {
2069          push @retVal, $object;          push @retVal, $object;
# Line 1427  Line 2072 
2072      return @retVal;      return @retVal;
2073  }  }
2074    
2075    =head3 GetCount
2076    
2077    C<< my $count = $erdb->GetCount(\@objectNames, $filter, \@params); >>
2078    
2079    Return the number of rows found by a specified query. This method would
2080    normally be used to count the records in a single table. For example, in a
2081    genetics database
2082    
2083        my $count = $erdb->GetCount(['Genome'], 'Genome(genus-species) LIKE ?', ['homo %']);
2084    
2085    would return the number of genomes for the genus I<homo>. It is conceivable, however,
2086    to use it to return records based on a join. For example,
2087    
2088        my $count = $erdb->GetCount(['HasFeature', 'Genome'], 'Genome(genus-species) LIKE ?',
2089                                    ['homo %']);
2090    
2091    would return the number of features for genomes in the genus I<homo>. Note that
2092    only the rows from the first table are counted. If the above command were
2093    
2094        my $count = $erdb->GetCount(['Genome', 'Feature'], 'Genome(genus-species) LIKE ?',
2095                                    ['homo %']);
2096    
2097    it would return the number of genomes, not the number of genome/feature pairs.
2098    
2099    =over 4
2100    
2101    =item objectNames
2102    
2103    Reference to a list of the objects (entities and relationships) included in the
2104    query.
2105    
2106    =item filter
2107    
2108    A filter clause for restricting the query. The rules are the same as for the L</Get>
2109    method.
2110    
2111    =item params
2112    
2113    Reference to a list of the parameter values to be substituted for the parameter marks
2114    in the filter.
2115    
2116    =item RETURN
2117    
2118    Returns a count of the number of records in the first table that would satisfy
2119    the query.
2120    
2121    =back
2122    
2123    =cut
2124    
2125    sub GetCount {
2126        # Get the parameters.
2127        my ($self, $objectNames, $filter, $params) = @_;
2128        # Insure the params argument is an array reference if the caller left it off.
2129        if (! defined($params)) {
2130            $params = [];
2131        }
2132        # Declare the return variable.
2133        my $retVal;
2134        # Find out if we're counting an entity or a relationship.
2135        my $countedField;
2136        if ($self->IsEntity($objectNames->[0])) {
2137            $countedField = "id";
2138        } else {
2139            # For a relationship we count the to-link because it's usually more
2140            # numerous. Note we're automatically converting to the SQL form
2141            # of the field name (to_link vs. to-link).
2142            $countedField = "to_link";
2143        }
2144        # Create the SQL command suffix to get the desired records.
2145        my ($suffix, $mappedNameListRef, $mappedNameHashRef) = $self->_SetupSQL($objectNames,
2146                                                                                $filter);
2147        # Prefix it with text telling it we want a record count.
2148        my $firstObject = $mappedNameListRef->[0];
2149        my $command = "SELECT COUNT($firstObject.$countedField) $suffix";
2150        # Prepare and execute the command.
2151        my $sth = $self->_GetStatementHandle($command, $params);
2152        # Get the count value.
2153        ($retVal) = $sth->fetchrow_array();
2154        # Check for a problem.
2155        if (! defined($retVal)) {
2156            if ($sth->err) {
2157                # Here we had an SQL error.
2158                Confess("Error retrieving row count: " . $sth->errstr());
2159            } else {
2160                # Here we have no result.
2161                Confess("No result attempting to retrieve row count.");
2162            }
2163        }
2164        # Return the result.
2165        return $retVal;
2166    }
2167    
2168  =head3 ComputeObjectSentence  =head3 ComputeObjectSentence
2169    
2170  C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>  C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>
# Line 1504  Line 2242 
2242      }      }
2243  }  }
2244    
2245    =head3 InsertValue
2246    
2247    C<< $erdb->InsertValue($entityID, $fieldName, $value); >>
2248    
2249    This method will insert a new value into the database. The value must be one
2250    associated with a secondary relation, since primary values cannot be inserted:
2251    they occur exactly once. Secondary values, on the other hand, can be missing
2252    or multiply-occurring.
2253    
2254    =over 4
2255    
2256    =item entityID
2257    
2258    ID of the object that is to receive the new value.
2259    
2260    =item fieldName
2261    
2262    Field name for the new value-- this includes the entity name, since
2263    field names are of the format I<objectName>C<(>I<fieldName>C<)>.
2264    
2265    =item value
2266    
2267    New value to be put in the field.
2268    
2269    =back
2270    
2271    =cut
2272    
2273    sub InsertValue {
2274        # Get the parameters.
2275        my ($self, $entityID, $fieldName, $value) = @_;
2276        # Parse the entity name and the real field name.
2277        if ($fieldName =~ /^([^(]+)\(([^)]+)\)/) {
2278            my $entityName = $1;
2279            my $fieldTitle = $2;
2280            # Get its descriptor.
2281            if (!$self->IsEntity($entityName)) {
2282                Confess("$entityName is not a valid entity.");
2283            } else {
2284                my $entityData = $self->{_metaData}->{Entities}->{$entityName};
2285                # Find the relation containing this field.
2286                my $fieldHash = $entityData->{Fields};
2287                if (! exists $fieldHash->{$fieldTitle}) {
2288                    Confess("$fieldTitle not found in $entityName.");
2289                } else {
2290                    my $relation = $fieldHash->{$fieldTitle}->{relation};
2291                    if ($relation eq $entityName) {
2292                        Confess("Cannot do InsertValue on primary field $fieldTitle of $entityName.");
2293                    } else {
2294                        # Now we can create an INSERT statement.
2295                        my $dbh = $self->{_dbh};
2296                        my $fixedName = _FixName($fieldTitle);
2297                        my $statement = "INSERT INTO $relation (id, $fixedName) VALUES(?, ?)";
2298                        # Execute the command.
2299                        $dbh->SQL($statement, 0, $entityID, $value);
2300                    }
2301                }
2302            }
2303        } else {
2304            Confess("$fieldName is not a valid field name.");
2305        }
2306    }
2307    
2308  =head3 InsertObject  =head3 InsertObject
2309    
2310  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>  C<< $erdb->InsertObject($objectType, \%fieldHash); >>
2311    
2312  Insert an object into the database. The object is defined by a type name and then a hash  Insert an object into the database. The object is defined by a type name and then a hash
2313  of field names to values. Field values in the primary relation are represented by scalars.  of field names to values. Field values in the primary relation are represented by scalars.
# Line 1520  Line 2321 
2321  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
2322  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>.
2323    
2324  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'}); >>
2325    
2326  =over 4  =over 4
2327    
# Line 1532  Line 2333 
2333    
2334  Hash of field names to values.  Hash of field names to values.
2335    
 =item RETURN  
   
 Returns 1 if successful, 0 if an error occurred.  
   
2336  =back  =back
2337    
2338  =cut  =cut
# Line 1634  Line 2431 
2431                  $retVal = $sth->execute(@parameterList);                  $retVal = $sth->execute(@parameterList);
2432                  if (!$retVal) {                  if (!$retVal) {
2433                      my $errorString = $sth->errstr();                      my $errorString = $sth->errstr();
2434                      Trace("Insert error: $errorString.") if T(0);                      Confess("Error inserting into $relationName: $errorString");
2435                  }                  }
2436              }              }
2437          }          }
2438      }      }
2439      # Return the success indicator.      # Return a 1 for backward compatability.
2440      return $retVal;      return 1;
2441    }
2442    
2443    =head3 UpdateEntity
2444    
2445    C<< $erdb->UpdateEntity($entityName, $id, \%fields); >>
2446    
2447    Update the values of an entity. This is an unprotected update, so it should only be
2448    done if the database resides on a database server.
2449    
2450    =over 4
2451    
2452    =item entityName
2453    
2454    Name of the entity to update. (This is the entity type.)
2455    
2456    =item id
2457    
2458    ID of the entity to update. If no entity exists with this ID, an error will be thrown.
2459    
2460    =item fields
2461    
2462    Reference to a hash mapping field names to their new values. All of the fields named
2463    must be in the entity's primary relation, and they cannot any of them be the ID field.
2464    
2465    =back
2466    
2467    =cut
2468    
2469    sub UpdateEntity {
2470        # Get the parameters.
2471        my ($self, $entityName, $id, $fields) = @_;
2472        # Get a list of the field names being updated.
2473        my @fieldList = keys %{$fields};
2474        # Verify that the fields exist.
2475        my $checker = $self->GetFieldTable($entityName);
2476        for my $field (@fieldList) {
2477            if ($field eq 'id') {
2478                Confess("Cannot update the ID field for entity $entityName.");
2479            } elsif ($checker->{$field}->{relation} ne $entityName) {
2480                Confess("Cannot find $field in primary relation of $entityName.");
2481            }
2482        }
2483        # Build the SQL statement.
2484        my @sets = ();
2485        my @valueList = ();
2486        for my $field (@fieldList) {
2487            push @sets, _FixName($field) . " = ?";
2488            push @valueList, $fields->{$field};
2489        }
2490        my $command = "UPDATE $entityName SET " . join(", ", @sets) . " WHERE id = ?";
2491        # Add the ID to the list of binding values.
2492        push @valueList, $id;
2493        # Call SQL to do the work.
2494        my $rows = $self->{_dbh}->SQL($command, 0, @valueList);
2495        # Check for errors.
2496        if ($rows == 0) {
2497            Confess("Entity $id of type $entityName not found.");
2498        }
2499  }  }
2500    
2501  =head3 LoadTable  =head3 LoadTable
2502    
2503  C<< my %results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>  C<< my $results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>
2504    
2505  Load data from a tab-delimited file into a specified table, optionally re-creating the table  Load data from a tab-delimited file into a specified table, optionally re-creating the table
2506  first.  first.
# Line 1712  Line 2567 
2567      };      };
2568      if (!defined $rv) {      if (!defined $rv) {
2569          $retVal->AddMessage($@) if ($@);          $retVal->AddMessage($@) if ($@);
2570          $retVal->AddMessage("Table load failed for $relationName using $fileName.");          $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2571          Trace("Table load failed for $relationName.") if T(1);          Trace("Table load failed for $relationName.") if T(1);
2572      } else {      } else {
2573          # Here we successfully loaded the table.          # Here we successfully loaded the table.
# Line 1720  Line 2575 
2575          my $size = -s $fileName;          my $size = -s $fileName;
2576          Trace("$size bytes loaded into $relationName.") if T(2);          Trace("$size bytes loaded into $relationName.") if T(2);
2577          # If we're rebuilding, we need to create the table indexes.          # If we're rebuilding, we need to create the table indexes.
2578          if ($truncateFlag && ! $dbh->{_preIndex}) {          if ($truncateFlag) {
2579                # Indexes are created here for PostGres. For PostGres, indexes are
2580                # best built at the end. For MySQL, the reverse is true.
2581                if (! $dbh->{_preIndex}) {
2582              eval {              eval {
2583                  $self->CreateIndex($relationName);                  $self->CreateIndex($relationName);
2584              };              };
# Line 1728  Line 2586 
2586                  $retVal->AddMessage($@);                  $retVal->AddMessage($@);
2587              }              }
2588          }          }
2589                # The full-text index (if any) is always built last, even for MySQL.
2590                # First we need to see if this table has a full-text index. Only
2591                # primary relations are allowed that privilege.
2592                Trace("Checking for full-text index on $relationName.") if T(2);
2593                if ($self->_IsPrimary($relationName)) {
2594                    $self->CreateSearchIndex($relationName);
2595                }
2596            }
2597      }      }
2598      # Analyze the table to improve performance.      # Analyze the table to improve performance.
2599        Trace("Analyzing and compacting $relationName.") if T(3);
2600      $dbh->vacuum_it($relationName);      $dbh->vacuum_it($relationName);
2601        Trace("$relationName load completed.") if T(3);
2602      # Return the statistics.      # Return the statistics.
2603      return $retVal;      return $retVal;
2604  }  }
2605    
2606  =head3 GenerateEntity  =head3 CreateSearchIndex
2607    
2608  C<< my $fieldHash = $erdb->GenerateEntity($id, $type, \%values); >>  C<< $erdb->CreateSearchIndex($objectName); >>
2609    
2610  Generate the data for a new entity instance. This method creates a field hash suitable for  Check for a full-text search index on the specified entity or relationship object, and
2611  passing as a parameter to L</InsertObject>. The ID is specified by the callr, but the rest  if one is required, rebuild it.
 of the fields are generated using information in the database schema.  
   
 Each data type has a default algorithm for generating random test data. This can be overridden  
 by including a B<DataGen> element in the field. If this happens, the content of the element is  
 executed as a PERL program in the context of this module. The element may make use of a C<$this>  
 variable which contains the field hash as it has been built up to the current point. If any  
 fields are dependent on other fields, the C<pass> attribute can be used to control the order  
 in which the fields are generated. A field with a high data pass number will be generated after  
 a field with a lower one. If any external values are needed, they should be passed in via the  
 optional third parameter, which will be available to the data generation script under the name  
 C<$value>. Several useful utility methods are provided for generating random values, including  
 L</IntGen>, L</StringGen>, L</FloatGen>, and L</DateGen>. Note that dates are stored and generated  
 in the form of a timestamp number rather than a string.  
2612    
2613  =over 4  =over 4
2614    
2615  =item id  =item objectName
   
 ID to assign to the new entity.  
   
 =item type  
   
 Type name for the new entity.  
   
 =item values  
2616    
2617  Hash containing additional values that might be needed by the data generation methods (optional).  Name of the entity or relationship to be indexed.
2618    
2619  =back  =back
2620    
2621  =cut  =cut
2622    
2623  sub GenerateEntity {  sub CreateSearchIndex {
2624      # Get the parameters.      # Get the parameters.
2625      my ($self, $id, $type, $values) = @_;      my ($self, $objectName) = @_;
2626      # Create the return hash.      # Get the relation's entity/relationship structure.
2627      my $this = { id => $id };      my $structure = $self->_GetStructure($objectName);
2628      # Get the metadata structure.      # Get the database handle.
2629      my $metadata = $self->{_metaData};      my $dbh = $self->{_dbh};
2630      # Get this entity's list of fields.      Trace("Checking for search fields in $objectName.") if T(3);
2631      if (!exists $metadata->{Entities}->{$type}) {      # Check for a searchable fields list.
2632          Confess("Unrecognized entity type $type in GenerateEntity.");      if (exists $structure->{searchFields}) {
2633      } else {          # Here we know that we need to create a full-text search index.
2634          my $entity = $metadata->{Entities}->{$type};          # Get an SQL-formatted field name list.
2635          my $fields = $entity->{Fields};          my $fields = join(", ", _FixNames(@{$structure->{searchFields}}));
2636          # Generate data from the fields.          # Create the index. If it already exists, it will be dropped.
2637          _GenerateFields($this, $fields, $type, $values);          $dbh->create_index(tbl => $objectName, idx => "search_idx",
2638                               flds => $fields, kind => 'fulltext');
2639            Trace("Index created for $fields in $objectName.") if T(2);
2640      }      }
     # Return the hash created.  
     return $this;  
2641  }  }
2642    
2643  =head3 GetEntity  =head3 DropRelation
2644    
2645  C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>  C<< $erdb->DropRelation($relationName); >>
2646    
2647  Return an object describing the entity instance with a specified ID.  Physically drop a relation from the database.
2648    
2649  =over 4  =over 4
2650    
2651  =item entityType  =item relationName
   
 Entity type name.  
   
 =item ID  
   
 ID of the desired entity.  
   
 =item RETURN  
2652    
2653  Returns a B<DBObject> representing the desired entity instance, or an undefined value if no  Name of the relation to drop. If it does not exist, this method will have
2654  instance is found with the specified key.  no effect.
2655    
2656  =back  =back
2657    
2658  =cut  =cut
2659    
2660  sub GetEntity {  sub DropRelation {
2661      # Get the parameters.      # Get the parameters.
2662      my ($self, $entityType, $ID) = @_;      my ($self, $relationName) = @_;
2663      # Create a query.      # Get the database handle.
2664      my $query = $self->Get([$entityType], "$entityType(id) = ?", $ID);      my $dbh = $self->{_dbh};
2665      # Get the first (and only) object.      # Drop the relation. The method used here has no effect if the relation
2666      my $retVal = $query->Fetch();      # does not exist.
2667      # Return the result.      Trace("Invoking DB Kernel to drop $relationName.") if T(3);
2668      return $retVal;      $dbh->drop_table(tbl => $relationName);
2669  }  }
2670    
2671  =head3 GetEntityValues  =head3 MatchSqlPattern
2672    
2673  C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>  C<< my $matched = ERDB::MatchSqlPattern($value, $pattern); >>
2674    
2675  Return a list of values from a specified entity instance.  Determine whether or not a specified value matches an SQL pattern. An SQL
2676    pattern has two wild card characters: C<%> that matches multiple characters,
2677    and C<_> that matches a single character. These can be escaped using a
2678    backslash (C<\>). We pull this off by converting the SQL pattern to a
2679    PERL regular expression. As per SQL rules, the match is case-insensitive.
2680    
2681  =over 4  =over 4
2682    
2683  =item entityType  =item value
2684    
2685  Entity type name.  Value to be matched against the pattern. Note that an undefined or empty
2686    value will not match anything.
2687    
2688  =item ID  =item pattern
2689    
2690  ID of the desired entity.  SQL pattern against which to match the value. An undefined or empty pattern will
2691    match everything.
2692    
2693    =item RETURN
2694    
2695    Returns TRUE if the value and pattern match, else FALSE.
2696    
2697    =back
2698    
2699    =cut
2700    
2701    sub MatchSqlPattern {
2702        # Get the parameters.
2703        my ($value, $pattern) = @_;
2704        # Declare the return variable.
2705        my $retVal;
2706        # Insure we have a pattern.
2707        if (! defined($pattern) || $pattern eq "") {
2708            $retVal = 1;
2709        } else {
2710            # Break the pattern into pieces around the wildcard characters. Because we
2711            # use parentheses in the split function's delimiter expression, we'll get
2712            # list elements for the delimiters as well as the rest of the string.
2713            my @pieces = split /([_%]|\\[_%])/, $pattern;
2714            # Check some fast special cases.
2715            if ($pattern eq '%') {
2716                # A null pattern matches everything.
2717                $retVal = 1;
2718            } elsif (@pieces == 1) {
2719                # No wildcards, so we have a literal comparison. Note we're case-insensitive.
2720                $retVal = (lc($value) eq lc($pattern));
2721            } elsif (@pieces == 2 && $pieces[1] eq '%') {
2722                # A wildcard at the end, so we have a substring match. This is also case-insensitive.
2723                $retVal = (lc(substr($value, 0, length($pieces[0]))) eq lc($pieces[0]));
2724            } else {
2725                # Okay, we have to do it the hard way. Convert each piece to a PERL pattern.
2726                my $realPattern = "";
2727                for my $piece (@pieces) {
2728                    # Determine the type of piece.
2729                    if ($piece eq "") {
2730                        # Empty pieces are ignored.
2731                    } elsif ($piece eq "%") {
2732                        # Here we have a multi-character wildcard. Note that it can match
2733                        # zero or more characters.
2734                        $realPattern .= ".*"
2735                    } elsif ($piece eq "_") {
2736                        # Here we have a single-character wildcard.
2737                        $realPattern .= ".";
2738                    } elsif ($piece eq "\\%" || $piece eq "\\_") {
2739                        # This is an escape sequence (which is a rare thing, actually).
2740                        $realPattern .= substr($piece, 1, 1);
2741                    } else {
2742                        # Here we have raw text.
2743                        $realPattern .= quotemeta($piece);
2744                    }
2745                }
2746                # Do the match.
2747                $retVal = ($value =~ /^$realPattern$/i ? 1 : 0);
2748            }
2749        }
2750        # Return the result.
2751        return $retVal;
2752    }
2753    
2754    =head3 GetEntity
2755    
2756    C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>
2757    
2758    Return an object describing the entity instance with a specified ID.
2759    
2760    =over 4
2761    
2762    =item entityType
2763    
2764    Entity type name.
2765    
2766    =item ID
2767    
2768    ID of the desired entity.
2769    
2770    =item RETURN
2771    
2772    Returns a B<DBObject> representing the desired entity instance, or an undefined value if no
2773    instance is found with the specified key.
2774    
2775    =back
2776    
2777    =cut
2778    
2779    sub GetEntity {
2780        # Get the parameters.
2781        my ($self, $entityType, $ID) = @_;
2782        # Create a query.
2783        my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);
2784        # Get the first (and only) object.
2785        my $retVal = $query->Fetch();
2786        # Return the result.
2787        return $retVal;
2788    }
2789    
2790    =head3 GetChoices
2791    
2792    C<< my @values = $erdb->GetChoices($entityName, $fieldName); >>
2793    
2794    Return a list of all the values for the specified field that are represented in the
2795    specified entity.
2796    
2797    Note that if the field is not indexed, then this will be a very slow operation.
2798    
2799    =over 4
2800    
2801    =item entityName
2802    
2803    Name of an entity in the database.
2804    
2805    =item fieldName
2806    
2807    Name of a field belonging to the entity. This is a raw field name without
2808    the standard parenthesized notation used in most calls.
2809    
2810    =item RETURN
2811    
2812    Returns a list of the distinct values for the specified field in the database.
2813    
2814    =back
2815    
2816    =cut
2817    
2818    sub GetChoices {
2819        # Get the parameters.
2820        my ($self, $entityName, $fieldName) = @_;
2821        # Declare the return variable.
2822        my @retVal;
2823        # Get the entity data structure.
2824        my $entityData = $self->_GetStructure($entityName);
2825        # Get the field.
2826        my $fieldHash = $entityData->{Fields};
2827        if (! exists $fieldHash->{$fieldName}) {
2828            Confess("$fieldName not found in $entityName.");
2829        } else {
2830            # Get the name of the relation containing the field.
2831            my $relation = $fieldHash->{$fieldName}->{relation};
2832            # Fix up the field name.
2833            my $realName = _FixName($fieldName);
2834            # Get the database handle.
2835            my $dbh = $self->{_dbh};
2836            # Query the database.
2837            my $results = $dbh->SQL("SELECT DISTINCT $realName FROM $relation");
2838            # Clean the results. They are stored as a list of lists, and we just want the one list.
2839            @retVal = sort map { $_->[0] } @{$results};
2840        }
2841        # Return the result.
2842        return @retVal;
2843    }
2844    
2845    =head3 GetEntityValues
2846    
2847    C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>
2848    
2849    Return a list of values from a specified entity instance. If the entity instance
2850    does not exist, an empty list is returned.
2851    
2852    =over 4
2853    
2854    =item entityType
2855    
2856    Entity type name.
2857    
2858    =item ID
2859    
2860    ID of the desired entity.
2861    
2862  =item fields  =item fields
2863    
# Line 1890  Line 2904 
2904  spreadsheet cell, and each feature will be represented by a list containing the  spreadsheet cell, and each feature will be represented by a list containing the
2905  feature ID followed by all of its aliases.  feature ID followed by all of its aliases.
2906    
2907  C<< $query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>  C<< @query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>
2908    
2909  =over 4  =over 4
2910    
# Line 1935  Line 2949 
2949      # list is a scalar we convert it into a singleton list.      # list is a scalar we convert it into a singleton list.
2950      my @parmList = ();      my @parmList = ();
2951      if (ref $parameterList eq "ARRAY") {      if (ref $parameterList eq "ARRAY") {
2952            Trace("GetAll parm list is an array.") if T(4);
2953          @parmList = @{$parameterList};          @parmList = @{$parameterList};
2954      } else {      } else {
2955            Trace("GetAll parm list is a scalar: $parameterList.") if T(4);
2956          push @parmList, $parameterList;          push @parmList, $parameterList;
2957      }      }
2958      # Insure the counter has a value.      # Insure the counter has a value.
# Line 1948  Line 2964 
2964          $filterClause .= " LIMIT $count";          $filterClause .= " LIMIT $count";
2965      }      }
2966      # Create the query.      # Create the query.
2967      my $query = $self->Get($objectNames, $filterClause, @parmList);      my $query = $self->Get($objectNames, $filterClause, \@parmList);
2968      # Set up a counter of the number of records read.      # Set up a counter of the number of records read.
2969      my $fetched = 0;      my $fetched = 0;
2970      # 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 2975 
2975          push @retVal, \@rowData;          push @retVal, \@rowData;
2976          $fetched++;          $fetched++;
2977      }      }
2978        Trace("$fetched rows returned in GetAll.") if T(SQL => 4);
2979      # Return the resulting list.      # Return the resulting list.
2980      return @retVal;      return @retVal;
2981  }  }
2982    
2983    =head3 Exists
2984    
2985    C<< my $found = $sprout->Exists($entityName, $entityID); >>
2986    
2987    Return TRUE if an entity exists, else FALSE.
2988    
2989    =over 4
2990    
2991    =item entityName
2992    
2993    Name of the entity type (e.g. C<Feature>) relevant to the existence check.
2994    
2995    =item entityID
2996    
2997    ID of the entity instance whose existence is to be checked.
2998    
2999    =item RETURN
3000    
3001    Returns TRUE if the entity instance exists, else FALSE.
3002    
3003    =back
3004    
3005    =cut
3006    #: Return Type $;
3007    sub Exists {
3008        # Get the parameters.
3009        my ($self, $entityName, $entityID) = @_;
3010        # Check for the entity instance.
3011        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
3012        my $testInstance = $self->GetEntity($entityName, $entityID);
3013        # Return an existence indicator.
3014        my $retVal = ($testInstance ? 1 : 0);
3015        return $retVal;
3016    }
3017    
3018  =head3 EstimateRowSize  =head3 EstimateRowSize
3019    
3020  C<< my $rowSize = $erdb->EstimateRowSize($relName); >>  C<< my $rowSize = $erdb->EstimateRowSize($relName); >>
# Line 2030  Line 3082 
3082      return $objectData->{Fields};      return $objectData->{Fields};
3083  }  }
3084    
3085  =head3 GetUsefulCrossValues  =head3 SplitKeywords
3086    
3087  C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>  C<< my @keywords = ERDB::SplitKeywords($keywordString); >>
3088    
3089  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
3090  from an entity of the source entity type through the specified relationship. This  keyword string. All of the operators will have been stripped off,
3091  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
3092  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
3093  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
3094  value.  duplicates.
3095    
3096  =over 4  It is possible to create a string that confuses this method. For example
3097    
3098  =item sourceEntity      frog toad -frog
3099    
3100  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
3101    with it later.
3102    
3103  =item relationship  =over 4
3104    
3105  Name of the relationship being crossed.  =item keywordString
3106    
3107    The keyword string to be parsed.
3108    
3109  =item RETURN  =item RETURN
3110    
3111  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
3112    see.
3113    
3114  =back  =back
3115    
3116  =cut  =cut
3117  #: Return Type @;  
3118  sub GetUsefulCrossValues {  sub SplitKeywords {
3119      # Get the parameters.      # Get the parameters.
3120      my ($self, $sourceEntity, $relationship) = @_;      my ($keywordString) = @_;
3121      # Declare the return variable.      # Make a safety copy of the string. (This helps during debugging.)
3122      my @retVal = ();      my $workString = $keywordString;
3123      # Determine the target entity for the relationship. This is whichever entity is not      # Convert operators we don't care about to spaces.
3124      # the source entity. So, if the source entity is the FROM, we'll get the name of      $workString =~ tr/+"()<>/ /;
3125      # the TO, and vice versa.      # Split the rest of the string along space boundaries. Note that we
3126      my $relStructure = $self->_GetStructure($relationship);      # eliminate any words that are zero length or begin with a minus sign.
3127      my $targetEntityType = ($relStructure->{from} eq $sourceEntity ? "to" : "from");      my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
3128      my $targetEntity = $relStructure->{$targetEntityType};      # Use a hash to remove duplicates.
3129      # 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;  
3130      # Return the result.      # Return the result.
3131      return @retVal;      return sort keys %words;
3132  }  }
3133    
3134  =head2 Internal Utility Methods  =head3 ValidateFieldName
3135    
3136  =head3 GetLoadStats  C<< my $okFlag = ERDB::ValidateFieldName($fieldName); >>
3137    
3138  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
3139    be hyphenated words subject to certain restrictions.
3140    
3141  This is a static method.  =over 4
3142    
3143    =item fieldName
3144    
3145    Field name to be validated.
3146    
3147    =item RETURN
3148    
3149    Returns TRUE if the field name is valid, else FALSE.
3150    
3151    =back
3152    
3153  =cut  =cut
3154    
3155  sub _GetLoadStats{  sub ValidateFieldName {
3156      return Stats->new();      # Get the parameters.
3157        my ($fieldName) = @_;
3158        # Declare the return variable. The field name is valid until we hear
3159        # differently.
3160        my $retVal = 1;
3161        # Compute the maximum name length.
3162        my $maxLen = $TypeTable{'name-string'}->{maxLen};
3163        # Look for bad stuff in the name.
3164        if ($fieldName =~ /--/) {
3165            # Here we have a doubled minus sign.
3166            Trace("Field name $fieldName has a doubled hyphen.") if T(1);
3167            $retVal = 0;
3168        } elsif ($fieldName !~ /^[A-Za-z]/) {
3169            # Here the field name is missing the initial letter.
3170            Trace("Field name $fieldName does not begin with a letter.") if T(1);
3171            $retVal = 0;
3172        } elsif (length($fieldName) > $maxLen) {
3173            # Here the field name is too long.
3174            Trace("Maximum field name length is $maxLen. Field name must be truncated to " . substr($fieldName,0, $maxLen) . ".");
3175        } else {
3176            # Strip out the minus signs. Everything remaining must be a letter,
3177            # underscore, or digit.
3178            my $strippedName = $fieldName;
3179            $strippedName =~ s/-//g;
3180            if ($strippedName !~ /^(\w|\d)+$/) {
3181                Trace("Field name $fieldName contains illegal characters.") if T(1);
3182                $retVal = 0;
3183            }
3184        }
3185        # Return the result.
3186        return $retVal;
3187  }  }
3188    
3189  =head3 GenerateFields  =head3 ReadMetaXML
3190    
3191  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.  
3192    
3193  This is a static method.  This method reads a raw database definition XML file and returns it.
3194    Normally, the metadata used by the ERDB system has been processed and
3195    modified to make it easier to load and retrieve the data; however,
3196    this method can be used to get the data in its raw form.
3197    
3198  =over 4  =over 4
3199    
3200  =item this  =item fileName
3201    
3202  Hash table into which the field values should be placed.  Name of the XML file to read.
3203    
3204  =item fields  =item RETURN
3205    
3206  Field structure from which the field descriptors should be taken.  Returns a hash reference containing the raw XML data from the specified file.
3207    
3208  =item type  =back
3209    
3210    =cut
3211    
3212    sub ReadMetaXML {
3213        # Get the parameters.
3214        my ($fileName) = @_;
3215        # Read the XML.
3216        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
3217        Trace("XML metadata loaded from file $fileName.") if T(1);
3218        # Return the result.
3219        return $retVal;
3220    }
3221    
3222    =head3 GetEntityFieldHash
3223    
3224    C<< my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName); >>
3225    
3226  Type name of the object whose fields are being generated.  Get the field hash of the named entity in the specified raw XML structure.
3227    The field hash may not exist, in which case we need to create it.
3228    
3229  =item values (optional)  =over 4
3230    
3231    =item structure
3232    
3233  Reference to a value structure from which additional values can be taken.  Raw XML structure defininng the database. This is not the run-time XML used by
3234    an ERDB object, since that has all sorts of optimizations built-in.
3235    
3236  =item from (optiona)  =item entityName
3237    
3238  Reference to the source entity instance if relationship data is being generated.  Name of the entity whose field structure is desired.
3239    
3240  =item to (optional)  =item RETURN
3241    
3242  Reference to the target entity instance if relationship data is being generated.  Returns the field hash used to define the entity's fields.
3243    
3244  =back  =back
3245    
3246  =cut  =cut
3247    
3248  sub _GenerateFields {  sub GetEntityFieldHash {
3249      # Get the parameters.      # Get the parameters.
3250      my ($this, $fields, $type, $values, $from, $to) = @_;      my ($structure, $entityName) = @_;
3251      # Sort the field names by pass number.      # Get the entity structure.
3252      my @fieldNames = sort { $fields->{$a}->{DataGen}->{pass} <=> $fields->{$b}->{DataGen}->{pass} } keys %{$fields};      my $entityData = $structure->{Entities}->{$entityName};
3253      # Loop through the field names, generating data.      # Look for a field structure.
3254      for my $name (@fieldNames) {      my $retVal = $entityData->{Fields};
3255          # Only proceed if this field needs to be generated.      # If it doesn't exist, create it.
3256          if (!exists $this->{$name}) {      if (! defined($retVal)) {
3257              # Get this field's data generation descriptor.          $entityData->{Fields} = {};
3258              my $fieldDescriptor = $fields->{$name};          $retVal = $entityData->{Fields};
             my $data = $fieldDescriptor->{DataGen};  
             # Get the code to generate the field value.  
             my $codeString = $data->{content};  
             # Determine whether or not this field is in the primary relation.  
             if ($fieldDescriptor->{relation} eq $type) {  
                 # Here we have a primary relation field. Store the field value as  
                 # a scalar.  
                 $this->{$name} = eval($codeString);  
             } else {  
                 # Here we have a secondary relation field. Create a null list  
                 # and push the desired number of field values onto it.  
                 my @fieldValues = ();  
                 my $count = IntGen(0,$data->{testCount});  
                 for (my $i = 0; $i < $count; $i++) {  
                     my $newValue = eval($codeString);  
                     push @fieldValues, $newValue;  
                 }  
                 # Store the value list in the main hash.  
                 $this->{$name} = \@fieldValues;  
3259              }              }
3260        # Return the result.
3261        return $retVal;
3262          }          }
3263    
3264    =head3 WriteMetaXML
3265    
3266    C<< ERDB::WriteMetaXML($structure, $fileName); >>
3267    
3268    Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
3269    used to update the database definition. It must be used with care, however, since it
3270    will only work on a raw structure, not on the processed structure created by an ERDB
3271    constructor.
3272    
3273    =over 4
3274    
3275    =item structure
3276    
3277    XML structure to be written to the file.
3278    
3279    =item fileName
3280    
3281    Name of the output file to which the updated XML should be stored.
3282    
3283    =back
3284    
3285    =cut
3286    
3287    sub WriteMetaXML {
3288        # Get the parameters.
3289        my ($structure, $fileName) = @_;
3290        # Compute the output.
3291        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
3292        # Write it to the file.
3293        my $xmlOut = Open(undef, ">$fileName");
3294        print $xmlOut $fileString;
3295      }      }
3296    
3297    
3298    =head3 HTMLNote
3299    
3300    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
3301    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
3302    Except for C<[p]>, all the codes are closed by slash-codes. So, for
3303    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
3304    
3305    C<< my $realHtml = ERDB::HTMLNote($dataString); >>
3306    
3307    =over 4
3308    
3309    =item dataString
3310    
3311    String to convert to HTML.
3312    
3313    =item RETURN
3314    
3315    An HTML string derived from the input string.
3316    
3317    =back
3318    
3319    =cut
3320    
3321    sub HTMLNote {
3322        # Get the parameter.
3323        my ($dataString) = @_;
3324        # HTML-escape the text.
3325        my $retVal = CGI::escapeHTML($dataString);
3326        # Substitute the bulletin board codes.
3327        $retVal =~ s!\[(/?[bi])\]!<$1>!g;
3328        $retVal =~ s!\[p\]!</p><p>!g;
3329        $retVal =~ s!\[link\s+([^\]]+)\]!<a href="$1">!g;
3330        $retVal =~ s!\[/link\]!</a>!g;
3331        # Return the result.
3332        return $retVal;
3333    }
3334    
3335    
3336    =head2 Data Mining Methods
3337    
3338    =head3 GetUsefulCrossValues
3339    
3340    C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>
3341    
3342    Return a list of the useful attributes that would be returned by a B<Cross> call
3343    from an entity of the source entity type through the specified relationship. This
3344    means it will return the fields of the target entity type and the intersection data
3345    fields in the relationship. Only primary table fields are returned. In other words,
3346    the field names returned will be for fields where there is always one and only one
3347    value.
3348    
3349    =over 4
3350    
3351    =item sourceEntity
3352    
3353    Name of the entity from which the relationship crossing will start.
3354    
3355    =item relationship
3356    
3357    Name of the relationship being crossed.
3358    
3359    =item RETURN
3360    
3361    Returns a list of field names in Sprout field format (I<objectName>C<(>I<fieldName>C<)>.
3362    
3363    =back
3364    
3365    =cut
3366    #: Return Type @;
3367    sub GetUsefulCrossValues {
3368        # Get the parameters.
3369        my ($self, $sourceEntity, $relationship) = @_;
3370        # Declare the return variable.
3371        my @retVal = ();
3372        # Determine the target entity for the relationship. This is whichever entity is not
3373        # the source entity. So, if the source entity is the FROM, we'll get the name of
3374        # the TO, and vice versa.
3375        my $relStructure = $self->_GetStructure($relationship);
3376        my $targetEntityType = ($relStructure->{from} eq $sourceEntity ? "to" : "from");
3377        my $targetEntity = $relStructure->{$targetEntityType};
3378        # Get the field table for the entity.
3379        my $entityFields = $self->GetFieldTable($targetEntity);
3380        # The field table is a hash. The hash key is the field name. The hash value is a structure.
3381        # For the entity fields, the key aspect of the target structure is that the {relation} value
3382        # must match the entity name.
3383        my @fieldList = map { "$targetEntity($_)" } grep { $entityFields->{$_}->{relation} eq $targetEntity }
3384                            keys %{$entityFields};
3385        # Push the fields found onto the return variable.
3386        push @retVal, sort @fieldList;
3387        # Get the field table for the relationship.
3388        my $relationshipFields = $self->GetFieldTable($relationship);
3389        # Here we have a different rule. We want all the fields other than "from-link" and "to-link".
3390        # This may end up being an empty set.
3391        my @fieldList2 = map { "$relationship($_)" } grep { $_ ne "from-link" && $_ ne "to-link" }
3392                            keys %{$relationshipFields};
3393        # Push these onto the return list.
3394        push @retVal, sort @fieldList2;
3395        # Return the result.
3396        return @retVal;
3397    }
3398    
3399    =head3 FindColumn
3400    
3401    C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>
3402    
3403    Return the location a desired column in a data mining header line. The data
3404    mining header line is a tab-separated list of column names. The column
3405    identifier is either the numerical index of a column or the actual column
3406    name.
3407    
3408    =over 4
3409    
3410    =item headerLine
3411    
3412    The header line from a data mining command, which consists of a tab-separated
3413    list of column names.
3414    
3415    =item columnIdentifier
3416    
3417    Either the ordinal number of the desired column (1-based), or the name of the
3418    desired column.
3419    
3420    =item RETURN
3421    
3422    Returns the array index (0-based) of the desired column.
3423    
3424    =back
3425    
3426    =cut
3427    
3428    sub FindColumn {
3429        # Get the parameters.
3430        my ($headerLine, $columnIdentifier) = @_;
3431        # Declare the return variable.
3432        my $retVal;
3433        # Split the header line into column names.
3434        my @headers = ParseColumns($headerLine);
3435        # Determine whether we have a number or a name.
3436        if ($columnIdentifier =~ /^\d+$/) {
3437            # Here we have a number. Subtract 1 and validate the result.
3438            $retVal = $columnIdentifier - 1;
3439            if ($retVal < 0 || $retVal > $#headers) {
3440                Confess("Invalid column identifer \"$columnIdentifier\": value out of range.");
3441            }
3442        } else {
3443            # Here we have a name. We need to find it in the list.
3444            for (my $i = 0; $i <= $#headers && ! defined($retVal); $i++) {
3445                if ($headers[$i] eq $columnIdentifier) {
3446                    $retVal = $i;
3447                }
3448            }
3449            if (! defined($retVal)) {
3450                Confess("Invalid column identifier \"$columnIdentifier\": value not found.");
3451            }
3452        }
3453        # Return the result.
3454        return $retVal;
3455    }
3456    
3457    =head3 ParseColumns
3458    
3459    C<< my @columns = ERDB::ParseColumns($line); >>
3460    
3461    Convert the specified data line to a list of columns.
3462    
3463    =over 4
3464    
3465    =item line
3466    
3467    A data mining input, consisting of a tab-separated list of columns terminated by a
3468    new-line.
3469    
3470    =item RETURN
3471    
3472    Returns a list consisting of the column values.
3473    
3474    =back
3475    
3476    =cut
3477    
3478    sub ParseColumns {
3479        # Get the parameters.
3480        my ($line) = @_;
3481        # Chop off the line-end.
3482        chomp $line;
3483        # Split it into a list.
3484        my @retVal = split(/\t/, $line);
3485        # Return the result.
3486        return @retVal;
3487    }
3488    
3489    =head2 Virtual Methods
3490    
3491    =head3 CleanKeywords
3492    
3493    C<< my $cleanedString = $erdb->CleanKeywords($searchExpression); >>
3494    
3495    Clean up a search expression or keyword list. This is a virtual method that may
3496    be overridden by the subclass. The base-class method removes extra spaces
3497    and converts everything to lower case.
3498    
3499    =over 4
3500    
3501    =item searchExpression
3502    
3503    Search expression or keyword list to clean. Note that a search expression may
3504    contain boolean operators which need to be preserved. This includes leading
3505    minus signs.
3506    
3507    =item RETURN
3508    
3509    Cleaned expression or keyword list.
3510    
3511    =back
3512    
3513    =cut
3514    
3515    sub CleanKeywords {
3516        # Get the parameters.
3517        my ($self, $searchExpression) = @_;
3518        # Lower-case the expression and copy it into the return variable. Note that we insure we
3519        # don't accidentally end up with an undefined value.
3520        my $retVal = lc($searchExpression || "");
3521        # Remove extra spaces.
3522        $retVal =~ s/\s+/ /g;
3523        $retVal =~ s/(^\s+)|(\s+$)//g;
3524        # Return the result.
3525        return $retVal;
3526    }
3527    
3528    =head3 GetSourceObject
3529    
3530    C<< my $source = $erdb->GetSourceObject($entityName); >>
3531    
3532    Return the object to be used in loading special attributes of the specified entity. The
3533    algorithm for loading special attributes is stored in the C<DataGen> elements of the
3534    XML
3535    
3536    =head2 Internal Utility Methods
3537    
3538    =head3 _RelationMap
3539    
3540    C<< my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef); >>
3541    
3542    Create the relation map for an SQL query. The relation map is used by B<DBObject>
3543    to determine how to interpret the results of the query.
3544    
3545    =over 4
3546    
3547    =item mappedNameHashRef
3548    
3549    Reference to a hash that maps modified object names to real object names.
3550    
3551    =item mappedNameListRef
3552    
3553    Reference to a list of modified object names in the order they appear in the
3554    SELECT list.
3555    
3556    =item RETURN
3557    
3558    Returns a list of 2-tuples. Each tuple consists of an object name as used in the
3559    query followed by the actual name of that object. This enables the B<DBObject> to
3560    determine the order of the tables in the query and which object name belongs to each
3561    mapped object name. Most of the time these two values are the same; however, if a
3562    relation occurs twice in the query, the relation name in the field list and WHERE
3563    clause will use a mapped name (generally the actual relation name with a numeric
3564    suffix) that does not match the actual relation name.
3565    
3566    =back
3567    
3568    =cut
3569    
3570    sub _RelationMap {
3571        # Get the parameters.
3572        my ($mappedNameHashRef, $mappedNameListRef) = @_;
3573        # Declare the return variable.
3574        my @retVal = ();
3575        # Build the map.
3576        for my $mappedName (@{$mappedNameListRef}) {
3577            push @retVal, [$mappedName, $mappedNameHashRef->{$mappedName}];
3578        }
3579        # Return it.
3580        return @retVal;
3581    }
3582    
3583    
3584    =head3 _SetupSQL
3585    
3586    Process a list of object names and a filter clause so that they can be used to
3587    build an SQL statement. This method takes in a reference to a list of object names
3588    and a filter clause. It will return a corrected filter clause, a list of mapped
3589    names and the mapped name hash.
3590    
3591    This is an instance method.
3592    
3593    =over 4
3594    
3595    =item objectNames
3596    
3597    Reference to a list of the object names to be included in the query.
3598    
3599    =item filterClause
3600    
3601    A string containing the WHERE clause for the query (without the C<WHERE>) and also
3602    optionally the C<ORDER BY> and C<LIMIT> clauses.
3603    
3604    =item matchClause
3605    
3606    An optional full-text search clause. If specified, it will be inserted at the
3607    front of the WHERE clause. It should already be SQL-formatted; that is, the
3608    field names should be in the form I<table>C<.>I<fieldName>.
3609    
3610    =item RETURN
3611    
3612    Returns a three-element list. The first element is the SQL statement suffix, beginning
3613    with the FROM clause. The second element is a reference to a list of the names to be
3614    used in retrieving the fields. The third element is a hash mapping the names to the
3615    objects they represent.
3616    
3617    =back
3618    
3619    =cut
3620    
3621    sub _SetupSQL {
3622        my ($self, $objectNames, $filterClause, $matchClause) = @_;
3623        # Adjust the list of object names to account for multiple occurrences of the
3624        # same object. We start with a hash table keyed on object name that will
3625        # return the object suffix. The first time an object is encountered it will
3626        # not be found in the hash. The next time the hash will map the object name
3627        # to 2, then 3, and so forth.
3628        my %objectHash = ();
3629        # This list will contain the object names as they are to appear in the
3630        # FROM list.
3631        my @fromList = ();
3632        # This list contains the suffixed object name for each object. It is exactly
3633        # parallel to the list in the $objectNames parameter.
3634        my @mappedNameList = ();
3635        # Finally, this hash translates from a mapped name to its original object name.
3636        my %mappedNameHash = ();
3637        # Now we create the lists. Note that for every single name we push something into
3638        # @fromList and @mappedNameList. This insures that those two arrays are exactly
3639        # parallel to $objectNames.
3640        for my $objectName (@{$objectNames}) {
3641            # Get the next suffix for this object.
3642            my $suffix = $objectHash{$objectName};
3643            if (! $suffix) {
3644                # Here we are seeing the object for the first time. The object name
3645                # is used as is.
3646                push @mappedNameList, $objectName;
3647                push @fromList, $objectName;
3648                $mappedNameHash{$objectName} = $objectName;
3649                # Denote the next suffix will be 2.
3650                $objectHash{$objectName} = 2;
3651            } else {
3652                # Here we've seen the object before. We construct a new name using
3653                # the suffix from the hash and update the hash.
3654                my $mappedName = "$objectName$suffix";
3655                $objectHash{$objectName} = $suffix + 1;
3656                # The FROM list has the object name followed by the mapped name. This
3657                # tells SQL it's still the same table, but we're using a different name
3658                # for it to avoid confusion.
3659                push @fromList, "$objectName $mappedName";
3660                # The mapped-name list contains the real mapped name.
3661                push @mappedNameList, $mappedName;
3662                # Finally, enable us to get back from the mapped name to the object name.
3663                $mappedNameHash{$mappedName} = $objectName;
3664            }
3665        }
3666        # Begin the SELECT suffix. It starts with
3667        #
3668        # FROM name1, name2, ... nameN
3669        #
3670        my $suffix = "FROM " . join(', ', @fromList);
3671        # Now for the WHERE. First, we need a place for the filter string.
3672        my $filterString = "";
3673        # We will also keep a list of conditions to add to the WHERE clause in order to link
3674        # entities and relationships as well as primary relations to secondary ones.
3675        my @joinWhere = ();
3676        # Check for a filter clause.
3677        if ($filterClause) {
3678            # Here we have one, so we convert its field names and add it to the query. First,
3679            # We create a copy of the filter string we can work with.
3680            $filterString = $filterClause;
3681            # Next, we sort the object names by length. This helps protect us from finding
3682            # object names inside other object names when we're doing our search and replace.
3683            my @sortedNames = sort { length($b) - length($a) } @mappedNameList;
3684            # The final preparatory step is to create a hash table of relation names. The
3685            # table begins with the relation names already in the SELECT command. We may
3686            # need to add relations later if there is filtering on a field in a secondary
3687            # relation. The secondary relations are the ones that contain multiply-
3688            # occurring or optional fields.
3689            my %fromNames = map { $_ => 1 } @sortedNames;
3690            # We are ready to begin. We loop through the object names, replacing each
3691            # object name's field references by the corresponding SQL field reference.
3692            # Along the way, if we find a secondary relation, we will need to add it
3693            # to the FROM clause.
3694            for my $mappedName (@sortedNames) {
3695                # Get the length of the object name plus 2. This is the value we add to the
3696                # size of the field name to determine the size of the field reference as a
3697                # whole.
3698                my $nameLength = 2 + length $mappedName;
3699                # Get the real object name for this mapped name.
3700                my $objectName = $mappedNameHash{$mappedName};
3701                Trace("Processing $mappedName for object $objectName.") if T(4);
3702                # Get the object's field list.
3703                my $fieldList = $self->GetFieldTable($objectName);
3704                # Find the field references for this object.
3705                while ($filterString =~ m/$mappedName\(([^)]*)\)/g) {
3706                    # At this point, $1 contains the field name, and the current position
3707                    # is set immediately after the final parenthesis. We pull out the name of
3708                    # the field and the position and length of the field reference as a whole.
3709                    my $fieldName = $1;
3710                    my $len = $nameLength + length $fieldName;
3711                    my $pos = pos($filterString) - $len;
3712                    # Insure the field exists.
3713                    if (!exists $fieldList->{$fieldName}) {
3714                        Confess("Field $fieldName not found for object $objectName.");
3715                    } else {
3716                        Trace("Processing $fieldName at position $pos.") if T(4);
3717                        # Get the field's relation.
3718                        my $relationName = $fieldList->{$fieldName}->{relation};
3719                        # Now we have a secondary relation. We need to insure it matches the
3720                        # mapped name of the primary relation. First we peel off the suffix
3721                        # from the mapped name.
3722                        my $mappingSuffix = substr $mappedName, length($objectName);
3723                        # Put the mapping suffix onto the relation name to get the
3724                        # mapped relation name.
3725                        my $mappedRelationName = "$relationName$mappingSuffix";
3726                        # Insure the relation is in the FROM clause.
3727                        if (!exists $fromNames{$mappedRelationName}) {
3728                            # Add the relation to the FROM clause.
3729                            if ($mappedRelationName eq $relationName) {
3730                                # The name is un-mapped, so we add it without
3731                                # any frills.
3732                                $suffix .= ", $relationName";
3733                                push @joinWhere, "$objectName.id = $relationName.id";
3734                            } else {
3735                                # Here we have a mapping situation.
3736                                $suffix .= ", $relationName $mappedRelationName";
3737                                push @joinWhere, "$mappedRelationName.id = $mappedName.id";
3738                            }
3739                            # Denote we have this relation available for future fields.
3740                            $fromNames{$mappedRelationName} = 1;
3741                        }
3742                        # Form an SQL field reference from the relation name and the field name.
3743                        my $sqlReference = "$mappedRelationName." . _FixName($fieldName);
3744                        # Put it into the filter string in place of the old value.
3745                        substr($filterString, $pos, $len) = $sqlReference;
3746                        # Reposition the search.
3747                        pos $filterString = $pos + length $sqlReference;
3748                    }
3749                }
3750            }
3751        }
3752        # The next step is to join the objects together. We only need to do this if there
3753        # is more than one object in the object list. We start with the first object and
3754        # run through the objects after it. Note also that we make a safety copy of the
3755        # list before running through it, because we shift off the first object before
3756        # processing the rest.
3757        my @mappedObjectList = @mappedNameList;
3758        my $lastMappedObject = shift @mappedObjectList;
3759        # Get the join table.
3760        my $joinTable = $self->{_metaData}->{Joins};
3761        # Loop through the object list.
3762        for my $thisMappedObject (@mappedObjectList) {
3763            # Look for a join using the real object names.
3764            my $lastObject = $mappedNameHash{$lastMappedObject};
3765            my $thisObject = $mappedNameHash{$thisMappedObject};
3766            my $joinKey = "$lastObject/$thisObject";
3767            if (!exists $joinTable->{$joinKey}) {
3768                # Here there's no join, so we throw an error.
3769                Confess("No join exists to connect from $lastMappedObject to $thisMappedObject.");
3770            } else {
3771                # Get the join clause.
3772                my $unMappedJoin = $joinTable->{$joinKey};
3773                # Fix the names.
3774                $unMappedJoin =~ s/$lastObject/$lastMappedObject/;
3775                $unMappedJoin =~ s/$thisObject/$thisMappedObject/;
3776                push @joinWhere, $unMappedJoin;
3777                # Save this object as the last object for the next iteration.
3778                $lastMappedObject = $thisMappedObject;
3779            }
3780        }
3781        # Now we need to handle the whole ORDER BY / LIMIT thing. The important part
3782        # here is we want the filter clause to be empty if there's no WHERE filter.
3783        # We'll put the ORDER BY / LIMIT clauses in the following variable.
3784        my $orderClause = "";
3785        # This is only necessary if we have a filter string in which the ORDER BY
3786        # and LIMIT clauses can live.
3787        if ($filterString) {
3788            # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy
3789            # operator so that we find the first occurrence of either verb.
3790            if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {
3791                # Here we have an ORDER BY or LIMIT verb. Split it off of the filter string.
3792                my $pos = pos $filterString;
3793                $orderClause = $2 . substr($filterString, $pos);
3794                $filterString = $1;
3795            }
3796        }
3797        # All the things that are supposed to be in the WHERE clause of the
3798        # SELECT command need to be put into @joinWhere so we can string them
3799        # together. We begin with the match clause. This is important,
3800        # because the match clause's parameter mark must precede any parameter
3801        # marks in the filter string.
3802        if ($matchClause) {
3803            push @joinWhere, $matchClause;
3804        }
3805        # Add the filter string. We put it in parentheses to avoid operator
3806        # precedence problems with the match clause or the joins.
3807        if ($filterString) {
3808            Trace("Filter string is \"$filterString\".") if T(4);
3809            push @joinWhere, "($filterString)";
3810        }
3811        # String it all together into a big filter clause.
3812        if (@joinWhere) {
3813            $suffix .= " WHERE " . join(' AND ', @joinWhere);
3814        }
3815        # Add the sort or limit clause (if any).
3816        if ($orderClause) {
3817            $suffix .= " $orderClause";
3818        }
3819        # Return the suffix, the mapped name list, and the mapped name hash.
3820        return ($suffix, \@mappedNameList, \%mappedNameHash);
3821    }
3822    
3823    =head3 _GetStatementHandle
3824    
3825    This method will prepare and execute an SQL query, returning the statement handle.
3826    The main reason for doing this here is so that everybody who does SQL queries gets
3827    the benefit of tracing.
3828    
3829    This is an instance method.
3830    
3831    =over 4
3832    
3833    =item command
3834    
3835    Command to prepare and execute.
3836    
3837    =item params
3838    
3839    Reference to a list of the values to be substituted in for the parameter marks.
3840    
3841    =item RETURN
3842    
3843    Returns a prepared and executed statement handle from which the caller can extract
3844    results.
3845    
3846    =back
3847    
3848    =cut
3849    
3850    sub _GetStatementHandle {
3851        # Get the parameters.
3852        my ($self, $command, $params) = @_;
3853        # Trace the query.
3854        Trace("SQL query: $command") if T(SQL => 3);
3855        Trace("PARMS: '" . (join "', '", @{$params}) . "'") if (T(SQL => 4) && (@{$params} > 0));
3856        # Get the database handle.
3857        my $dbh = $self->{_dbh};
3858        # Prepare the command.
3859        my $sth = $dbh->prepare_command($command);
3860        # Execute it with the parameters bound in.
3861        $sth->execute(@{$params}) || Confess("SELECT error:  " . $sth->errstr());
3862        # Return the statement handle.
3863        return $sth;
3864    }
3865    
3866    =head3 _GetLoadStats
3867    
3868    Return a blank statistics object for use by the load methods.
3869    
3870    This is a static method.
3871    
3872    =cut
3873    
3874    sub _GetLoadStats{
3875        return Stats->new();
3876  }  }
3877    
3878  =head3 DumpRelation  =head3 _DumpRelation
3879    
3880  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.
3881    
3882  This is an instance method.  This is an instance method.
3883    
# Line 2229  Line 3925 
3925      close DTXOUT;      close DTXOUT;
3926  }  }
3927    
3928  =head3 GetStructure  =head3 _GetStructure
3929    
3930  Get the data structure for a specified entity or relationship.  Get the data structure for a specified entity or relationship.
3931    
# Line 2268  Line 3964 
3964      return $retVal;      return $retVal;
3965  }  }
3966    
3967  =head3 GetRelationTable  
3968    
3969    =head3 _GetRelationTable
3970    
3971  Get the list of relations for a specified entity or relationship.  Get the list of relations for a specified entity or relationship.
3972    
# Line 2297  Line 3995 
3995      return $objectData->{Relations};      return $objectData->{Relations};
3996  }  }
3997    
3998  =head3 ValidateFieldNames  =head3 _ValidateFieldNames
3999    
4000  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
4001  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 4022 
4022          for my $object (values %{$metadata->{$section}}) {          for my $object (values %{$metadata->{$section}}) {
4023              # Loop through the object's fields.              # Loop through the object's fields.
4024              for my $fieldName (keys %{$object->{Fields}}) {              for my $fieldName (keys %{$object->{Fields}}) {
4025                  # Now we make some initial validations.                  # If this field name is invalid, set the return value to zero
4026                  if ($fieldName =~ /--/) {                  # so we know we encountered an error.
4027                      # Here we have a doubled minus sign.                  if (! ValidateFieldName($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";  
4028                          $retVal = 0;                          $retVal = 0;
4029                      }                      }
4030                  }                  }
4031              }              }
4032          }          }
     }  
4033      # If an error was found, fail.      # If an error was found, fail.
4034      if ($retVal  == 0) {      if ($retVal  == 0) {
4035          Confess("Errors found in field names.");          Confess("Errors found in field names.");
4036      }      }
4037  }  }
4038    
4039  =head3 LoadRelation  =head3 _LoadRelation
4040    
4041  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
4042  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 4096 
4096      return $retVal;      return $retVal;
4097  }  }
4098    
4099  =head3 LoadMetaData  
4100    =head3 _LoadMetaData
4101    
4102  This method loads the data describing this database from an XML file into a metadata structure.  This method loads the data describing this database from an XML file into a metadata structure.
4103  The resulting structure is a set of nested hash tables containing all the information needed to  The resulting structure is a set of nested hash tables containing all the information needed to
# Line 2437  Line 4122 
4122  sub _LoadMetaData {  sub _LoadMetaData {
4123      # Get the parameters.      # Get the parameters.
4124      my ($filename) = @_;      my ($filename) = @_;
4125      Trace("Reading Sprout DBD from $filename.") if T(2);      Trace("Reading DBD from $filename.") if T(2);
4126      # 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
4127      # get the exact structure we want.      # get the exact structure we want.
4128      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 $filename.") if T(1);  
4129      # Before we go any farther, we need to validate the field and object names. If an error is found,      # Before we go any farther, we need to validate the field and object names. If an error is found,
4130      # the method below will fail.      # the method below will fail.
4131      _ValidateFieldNames($metadata);      _ValidateFieldNames($metadata);
# Line 2583  Line 4255 
4255              my $count = 0;              my $count = 0;
4256              for my $index (@{$indexList}) {              for my $index (@{$indexList}) {
4257                  # Add this index to the index table.                  # Add this index to the index table.
4258                  _AddIndex("idx$relationName$count", $relation, $index);                  _AddIndex("idx$count", $relation, $index);
4259                  # Increment the counter so that the next index has a different name.                  # Increment the counter so that the next index has a different name.
4260                  $count++;                  $count++;
4261              }              }
# Line 2600  Line 4272 
4272          _FixupFields($relationshipStructure, $relationshipName, 2, 3);          _FixupFields($relationshipStructure, $relationshipName, 2, 3);
4273          # Format a description for the FROM field.          # Format a description for the FROM field.
4274          my $fromEntity = $relationshipStructure->{from};          my $fromEntity = $relationshipStructure->{from};
4275          my $fromComment = "<b>id</b> of the source <b><a href=\"#$fromEntity\">$fromEntity</a></b>.";          my $fromComment = "[b]id[/b] of the source [b][link #$fromEntity]$fromEntity\[/link][/b].";
4276          # Get the FROM entity's key type.          # Get the FROM entity's key type.
4277          my $fromType = $entityList->{$fromEntity}->{keyType};          my $fromType = $entityList->{$fromEntity}->{keyType};
4278          # Add the FROM field.          # Add the FROM field.
# Line 2610  Line 4282 
4282                                                      PrettySort => 1});                                                      PrettySort => 1});
4283          # Format a description for the TO field.          # Format a description for the TO field.
4284          my $toEntity = $relationshipStructure->{to};          my $toEntity = $relationshipStructure->{to};
4285          my $toComment = "<b>id</b> of the target <b><a href=\"#$toEntity\">$toEntity</a></b>.";          my $toComment = "[b]id[/b] of the target [b][link #$toEntity]$toEntity\[/link][/b].";
4286          # Get the TO entity's key type.          # Get the TO entity's key type.
4287          my $toType = $entityList->{$toEntity}->{keyType};          my $toType = $entityList->{$toEntity}->{keyType};
4288          # Add the TO field.          # Add the TO field.
# Line 2739  Line 4411 
4411      return $metadata;      return $metadata;
4412  }  }
4413    
4414  =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  
4415    
4416  Create an index for a relationship's relation.  Create an index for a relationship's relation.
4417    
# Line 2820  Line 4453 
4453          $newIndex->{Unique} = 'true';          $newIndex->{Unique} = 'true';
4454      }      }
4455      # Add the index to the relation.      # Add the index to the relation.
4456      _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);      _AddIndex("idx$indexKey", $relationStructure, $newIndex);
4457  }  }
4458    
4459  =head3 AddIndex  =head3 _AddIndex
4460    
4461  Add an index to a relation structure.  Add an index to a relation structure.
4462    
# Line 2869  Line 4502 
4502      $relationStructure->{Indexes}->{$indexName} = $newIndex;      $relationStructure->{Indexes}->{$indexName} = $newIndex;
4503  }  }
4504    
4505  =head3 FixupFields  =head3 _FixupFields
4506    
4507  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
4508  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 4540 
4540          # Here it doesn't, so we create a new one.          # Here it doesn't, so we create a new one.
4541          $structure->{Fields} = { };          $structure->{Fields} = { };
4542      } else {      } else {
4543          # 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
4544            # create a list for stashing them.
4545            my @textFields = ();
4546            # Loop through the fields.
4547          my $fieldStructures = $structure->{Fields};          my $fieldStructures = $structure->{Fields};
4548          for my $fieldName (keys %{$fieldStructures}) {          for my $fieldName (keys %{$fieldStructures}) {
4549              Trace("Processing field $fieldName of $defaultRelationName.") if T(4);              Trace("Processing field $fieldName of $defaultRelationName.") if T(4);
# Line 2916  Line 4552 
4552              my $type = $fieldData->{type};              my $type = $fieldData->{type};
4553              # Plug in a relation name if it is needed.              # Plug in a relation name if it is needed.
4554              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });
4555              # Plug in a data generator if we need one.              # Check for searchability.
4556              if (!exists $fieldData->{DataGen}) {              if ($fieldData->{searchable}) {
4557                  # The data generator will use the default for the field's type.                  # Only allow this for a primary relation.
4558                  $fieldData->{DataGen} = { content => $TypeTable{$type}->{dataGen} };                  if ($fieldData->{relation} ne $defaultRelationName) {
4559                        Confess("Field $fieldName of $defaultRelationName is in secondary relations and cannot be searchable.");
4560                    } else {
4561                        push @textFields, $fieldName;
4562                    }
4563              }              }
             # Plug in the defaults for the optional data generation parameters.  
             Tracer::MergeOptions($fieldData->{DataGen}, { testCount => 1, pass => 0 });  
4564              # Add the PrettySortValue.              # Add the PrettySortValue.
4565              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);
4566          }          }
4567            # If there are searchable fields, remember the fact.
4568            if (@textFields) {
4569                $structure->{searchFields} = \@textFields;
4570            }
4571      }      }
4572  }  }
4573    
4574  =head3 FixName  =head3 _FixName
4575    
4576  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.
4577    
# Line 2958  Line 4600 
4600      return $fieldName;      return $fieldName;
4601  }  }
4602    
4603  =head3 FixNames  =head3 _FixNames
4604    
4605  Fix all the field names in a list.  Fix all the field names in a list.
4606    
# Line 2989  Line 4631 
4631      return @result;      return @result;
4632  }  }
4633    
4634  =head3 AddField  =head3 _AddField
4635    
4636  Add a field to a field list.  Add a field to a field list.
4637    
# Line 3024  Line 4666 
4666      $fieldList->{$fieldName} = $fieldStructure;      $fieldList->{$fieldName} = $fieldStructure;
4667  }  }
4668    
4669  =head3 ReOrderRelationTable  =head3 _ReOrderRelationTable
4670    
4671  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
4672  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 4727 
4727    
4728  }  }
4729    
4730  =head3 IsPrimary  =head3 _IsPrimary
4731    
4732  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
4733  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 4763 
4763      return $retVal;      return $retVal;
4764  }  }
4765    
4766  =head3 FindRelation  =head3 _FindRelation
4767    
4768  Return the descriptor for the specified relation.  Return the descriptor for the specified relation.
4769    
# Line 3152  Line 4794 
4794    
4795  =head2 HTML Documentation Utility Methods  =head2 HTML Documentation Utility Methods
4796    
4797  =head3 ComputeRelationshipSentence  =head3 _ComputeRelationshipSentence
4798    
4799  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
4800  two related entities and an arity indicator.  two related entities and an arity indicator.
# Line 3190  Line 4832 
4832      return $result;      return $result;
4833  }  }
4834    
4835  =head3 ComputeRelationshipHeading  =head3 _ComputeRelationshipHeading
4836    
4837  The relationship heading is the L<relationship sentence|/ComputeRelationshipSentence> with the entity  The relationship heading is the L<relationship sentence|/ComputeRelationshipSentence> with the entity
4838  names hyperlinked to the appropriate entity sections of the document.  names hyperlinked to the appropriate entity sections of the document.
# Line 3227  Line 4869 
4869      return $result;      return $result;
4870  }  }
4871    
4872  =head3 ShowRelationTable  =head3 _ShowRelationTable
4873    
4874  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
4875  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 4919 
4919          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";
4920          # Add any note text.          # Add any note text.
4921          if (my $note = $indexData->{Notes}) {          if (my $note = $indexData->{Notes}) {
4922              $htmlString .= "<li>" . _HTMLNote($note->{content}) . "</li>\n";              $htmlString .= "<li>" . HTMLNote($note->{content}) . "</li>\n";
4923          }          }
4924          # Add the fiield list.          # Add the fiield list.
4925          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";
# Line 3288  Line 4930 
4930      $htmlString .= "</ul>\n";      $htmlString .= "</ul>\n";
4931  }  }
4932    
4933  =head3 OpenFieldTable  =head3 _OpenFieldTable
4934    
4935  This method creates the header string for the field table generated by L</ShowMetaData>.  This method creates the header string for the field table generated by L</ShowMetaData>.
4936    
# Line 3313  Line 4955 
4955      return _OpenTable($tablename, 'Field', 'Type', 'Description');      return _OpenTable($tablename, 'Field', 'Type', 'Description');
4956  }  }
4957    
4958  =head3 OpenTable  =head3 _OpenTable
4959    
4960  This method creates the header string for an HTML table.  This method creates the header string for an HTML table.
4961    
# Line 3343  Line 4985 
4985      # Compute the number of columns.      # Compute the number of columns.
4986      my $colCount = @colNames;      my $colCount = @colNames;
4987      # Generate the title row.      # Generate the title row.
4988      my $htmlString = "<p><table border=\"2\"><tr><td colspan=\"$colCount\" align=\"center\">$tablename</td></tr>\n";      my $htmlString = "<table border=\"2\"><tr><td colspan=\"$colCount\" align=\"center\">$tablename</td></tr>\n";
4989      # Loop through the columns, adding the column header rows.      # Loop through the columns, adding the column header rows.
4990      $htmlString .= "<tr>";      $htmlString .= "<tr>";
4991      for my $colName (@colNames) {      for my $colName (@colNames) {
# Line 3353  Line 4995 
4995      return $htmlString;      return $htmlString;
4996  }  }
4997    
4998  =head3 CloseTable  =head3 _CloseTable
4999    
5000  This method returns the HTML for closing a table.  This method returns the HTML for closing a table.
5001    
# Line 3362  Line 5004 
5004  =cut  =cut
5005    
5006  sub _CloseTable {  sub _CloseTable {
5007      return "</table></p>\n";      return "</table>\n";
5008  }  }
5009    
5010  =head3 ShowField  =head3 _ShowField
5011    
5012  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.
5013    
# Line 3392  Line 5034 
5034      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>";
5035      # If we have content, add it as a third column.      # If we have content, add it as a third column.
5036      if (exists $fieldData->{Notes}) {      if (exists $fieldData->{Notes}) {
5037          $htmlString .= "<td>" . _HTMLNote($fieldData->{Notes}->{content}) . "</td>";          $htmlString .= "<td>" . HTMLNote($fieldData->{Notes}->{content}) . "</td>";
5038      }      }
5039      # Close off the row.      # Close off the row.
5040      $htmlString .= "</tr>\n";      $htmlString .= "</tr>\n";
# Line 3400  Line 5042 
5042      return $htmlString;      return $htmlString;
5043  }  }
5044    
 =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;  
 }  
   
5045  1;  1;

Legend:
Removed from v.1.42  
changed lines
  Added in v.1.83

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3