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

Diff of /Sprout/ERDB.pm

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

revision 1.11, Thu Jun 23 21:24:49 2005 UTC revision 1.73, Fri Nov 3 00:33:26 2006 UTC
# Line 2  Line 2 
2    
3      use strict;      use strict;
4      use Tracer;      use Tracer;
5      use DBKernel;      use DBrtns;
6      use Data::Dumper;      use Data::Dumper;
7      use XML::Simple;      use XML::Simple;
8      use DBQuery;      use DBQuery;
9      use DBObject;      use DBObject;
10      use Stats;      use Stats;
11      use Time::HiRes qw(gettimeofday);      use Time::HiRes qw(gettimeofday);
12        use Digest::MD5 qw(md5_base64);
13        use FIG;
14        use CGI;
15    
16  =head1 Entity-Relationship Database Package  =head1 Entity-Relationship Database Package
17    
# Line 57  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 89  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 108  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 124  Line 135 
135    
136  variable-length string, maximum 255 characters  variable-length string, maximum 255 characters
137    
138    =item hash-string
139    
140    variable-length string, maximum 22 characters
141    
142  =back  =back
143    
144    The hash-string data type has a special meaning. The actual key passed into the loader will
145    be a string, but it will be digested into a 22-character MD5 code to save space. Although the
146    MD5 algorithm is not perfect, it is extremely unlikely two strings will have the same
147    digest. Therefore, it is presumed the keys will be unique. When the database is actually
148    in use, the hashed keys will be presented rather than the original values. For this reason,
149    they should not be used for entities where the key is meaningful.
150    
151  =head3 Global Tags  =head3 Global Tags
152    
153  The entire database definition must be inside a B<Database> tag. The display name of  The entire database definition must be inside a B<Database> tag. The display name of
# Line 169  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 188  Line 212 
212  entity, the fields without a relation attribute are said to belong to the  entity, the fields without a relation attribute are said to belong to the
213  I<primary relation>. This relation has the same name as the entity itself.  I<primary relation>. This relation has the same name as the entity itself.
214    
215    =item searchable
216    
217    If specified, then the field is a candidate for full-text searching. A single full-text
218    index will be created for each relation with at least one searchable field in it.
219    For best results, this option should only be used for string or text fields.
220    
221    =item special
222    
223    This attribute allows the subclass to assign special meaning for certain fields.
224    The interpretation is up to the subclass itself. Currently, only entity fields
225    can have this attribute.
226    
227  =back  =back
228    
229  =head3 Indexes  =head3 Indexes
# Line 299  Line 335 
335    
336  # Table of information about our datatypes. "sqlType" is the corresponding SQL datatype string.  # Table of information about our datatypes. "sqlType" is the corresponding SQL datatype string.
337  # "maxLen" is the maximum permissible length of the incoming string data used to populate a field  # "maxLen" is the maximum permissible length of the incoming string data used to populate a field
338  # of the specified type. "dataGen" is PERL string that will be evaluated if no test data generation  # of the specified type. "avgLen" is the average byte length for estimating
339   #string is specified in the field definition.  # record sizes. "sort" is the key modifier for the sort command, "notes" is a type description.
340  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            dataGen => "StringGen('A')" },  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",
341                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           dataGen => "IntGen(0, 99999999)" },                                 notes => "single ASCII character"},
342                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          dataGen => "StringGen(IntGen(10,250))" },                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n",
343                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   dataGen => "StringGen(IntGen(80,1000))" },                                 notes => "signed 32-bit integer"},
344                    date =>    { sqlType => 'BIGINT',             maxLen => 80,           dataGen => "DateGen(-7, 7, IntGen(0,1400))" },                    counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n",
345                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           dataGen => "FloatGen(0.0, 100.0)" },                                 notes => "unsigned 32-bit integer"},
346                    boolean => { sqlType => 'SMALLINT',           maxLen => 1,            dataGen => "IntGen(0, 1)" },                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, sort => "",
347                                   notes => "character string, 0 to 255 characters"},
348                      text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, sort => "",
349                                   notes => "character string, nearly unlimited length, cannot be indexed"},
350                      date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, sort => "n",
351                                   notes => "signed, 64-bit integer"},
352                      float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, sort => "g",
353                                   notes => "64-bit double precision floating-point number"},
354                      boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, sort => "n",
355                                   notes => "boolean value: 0 if false, 1 if true"},
356                     'hash-string' =>
357                                 { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, sort => "",
358                                   notes => "string stored in digested form, used for certain types of key fields"},
359                     'id-string' =>
360                                 { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, sort => "",
361                                   notes => "character string, 0 to 25 characters"},
362                   'key-string' =>                   'key-string' =>
363                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           dataGen => "StringGen(IntGen(10,40))" },                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, sort => "",
364                                   notes => "character string, 0 to 40 characters"},
365                   'name-string' =>                   'name-string' =>
366                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           dataGen => "StringGen(IntGen(10,80))" },                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, sort => "",
367                                   notes => "character string, 0 to 80 characters"},
368                   'medium-string' =>                   'medium-string' =>
369                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          dataGen => "StringGen(IntGen(10,160))" },                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",
370                                   notes => "character string, 0 to 160 characters"},
371                  );                  );
372    
373  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 322  Line 376 
376                     'MM' => 'many-to-many'                     'MM' => 'many-to-many'
377                   );                   );
378    
379  # Table for interpreting string patterns.  # Options for XML input and output.
380    
381    my %XmlOptions = (GroupTags =>  { Relationships => 'Relationship',
382                                      Entities => 'Entity',
383                                      Fields => 'Field',
384                                      Indexes => 'Index',
385                                      IndexFields => 'IndexField'
386                                    },
387                      KeyAttr =>    { Relationship => 'name',
388                                      Entity => 'name',
389                                      Field => 'name'
390                                    },
391                      SuppressEmpty => 1,
392                     );
393    
394  my %PictureTable = ( 'A' => "abcdefghijklmnopqrstuvwxyz",  my %XmlInOpts  = (
395                       '9' => "0123456789",                    ForceArray => ['Field', 'Index', 'IndexField'],
396                       'X' => "abcdefghijklmnopqrstuvwxyz0123456789",                    ForceContent => 1,
397                       'V' => "aeiou",                    NormalizeSpace => 2,
398                       'K' => "bcdfghjklmnoprstvwxyz"                   );
399    my %XmlOutOpts = (
400                      RootName => 'Database',
401                      XMLDecl => 1,
402                     );                     );
403    
404    
405  =head2 Public Methods  =head2 Public Methods
406    
407  =head3 new  =head3 new
# Line 369  Line 440 
440    
441  =head3 ShowMetaData  =head3 ShowMetaData
442    
443  C<< $database->ShowMetaData($fileName); >>  C<< $erdb->ShowMetaData($fileName); >>
444    
445  This method outputs a description of the database. This description can be used to help users create  This method outputs a description of the database. This description can be used to help users create
446  the data to be loaded into the relations.  the data to be loaded into the relations.
# Line 400  Line 471 
471      # Write the HTML heading stuff.      # Write the HTML heading stuff.
472      print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";      print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";
473      print HTMLOUT "</head>\n<body>\n";      print HTMLOUT "</head>\n<body>\n";
474        # Write the documentation.
475        print HTMLOUT $self->DisplayMetaData();
476        # Close the document.
477        print HTMLOUT "</body>\n</html>\n";
478        # Close the file.
479        close HTMLOUT;
480    }
481    
482    =head3 DisplayMetaData
483    
484    C<< my $html = $erdb->DisplayMetaData(); >>
485    
486    Return an HTML description of the database. This description can be used to help users create
487    the data to be loaded into the relations and form queries. The output is raw includable HTML
488    without any HEAD or BODY tags.
489    
490    =over 4
491    
492    =item filename
493    
494    The name of the output file.
495    
496    =back
497    
498    =cut
499    
500    sub DisplayMetaData {
501        # Get the parameters.
502        my ($self) = @_;
503        # Get the metadata and the title string.
504        my $metadata = $self->{_metaData};
505        # Get the title string.
506        my $title = $metadata->{Title};
507        # Get the entity and relationship lists.
508        my $entityList = $metadata->{Entities};
509        my $relationshipList = $metadata->{Relationships};
510        # Declare the return variable.
511        my $retVal = "";
512        # Open the output file.
513        Trace("Building MetaData table of contents.") if T(4);
514      # 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
515      # section contains an ordered list of entity or relationship subsections.      # section contains an ordered list of entity or relationship subsections.
516      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";
517      # Loop through the Entities, displaying a list item for each.      # Loop through the Entities, displaying a list item for each.
518      foreach my $key (sort keys %{$entityList}) {      foreach my $key (sort keys %{$entityList}) {
519          # Display this item.          # Display this item.
520          print HTMLOUT "<li><a href=\"#$key\">$key</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$key</a></li>\n";
521      }      }
522      # Close off the entity section and start the relationship section.      # Close off the entity section and start the relationship section.
523      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";
524      # Loop through the Relationships.      # Loop through the Relationships.
525      foreach my $key (sort keys %{$relationshipList}) {      foreach my $key (sort keys %{$relationshipList}) {
526          # Display this item.          # Display this item.
527          my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});          my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});
528          print HTMLOUT "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";
529      }      }
530      # Close off the relationship section and list the join table section.      # Close off the relationship section and list the join table section.
531      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";
532      # Close off the table of contents itself.      # Close off the table of contents itself.
533      print HTMLOUT "</ul>\n";      $retVal .=  "</ul>\n";
534      # 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.
535      print HTMLOUT "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";      $retVal .= "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";
536      # Loop through the entities.      # Loop through the entities.
537      for my $key (sort keys %{$entityList}) {      for my $key (sort keys %{$entityList}) {
538          Trace("Building MetaData entry for $key entity.") if T(4);          Trace("Building MetaData entry for $key entity.") if T(4);
539          # Create the entity header. It contains a bookmark and the entity name.          # Create the entity header. It contains a bookmark and the entity name.
540          print HTMLOUT "<a name=\"$key\"></a><h3>$key</h3>\n";          $retVal .= "<a name=\"$key\"></a><h3>$key</h3>\n";
541          # Get the entity data.          # Get the entity data.
542          my $entityData = $entityList->{$key};          my $entityData = $entityList->{$key};
543          # If there's descriptive text, display it.          # If there's descriptive text, display it.
544          if (my $notes = $entityData->{Notes}) {          if (my $notes = $entityData->{Notes}) {
545              print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
546          }          }
547          # Now we want a list of the entity's relationships. First, we set up the relationship subsection.          # Now we want a list of the entity's relationships. First, we set up the relationship subsection.
548          print HTMLOUT "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
549          # Loop through the relationships.          # Loop through the relationships.
550          for my $relationship (sort keys %{$relationshipList}) {          for my $relationship (sort keys %{$relationshipList}) {
551              # Get the relationship data.              # Get the relationship data.
# Line 444  Line 555 
555                  # Get the relationship sentence and append the arity.                  # Get the relationship sentence and append the arity.
556                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);
557                  # Display the relationship data.                  # Display the relationship data.
558                  print HTMLOUT "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";                  $retVal .= "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";
559              }              }
560          }          }
561          # Close off the relationship list.          # Close off the relationship list.
562          print HTMLOUT "</ul>\n";          $retVal .= "</ul>\n";
563          # Get the entity's relations.          # Get the entity's relations.
564          my $relationList = $entityData->{Relations};          my $relationList = $entityData->{Relations};
565          # Create a header for the relation subsection.          # Create a header for the relation subsection.
566          print HTMLOUT "<h4>Relations for <b>$key</b></h4>\n";          $retVal .= "<h4>Relations for <b>$key</b></h4>\n";
567          # Loop through the relations, displaying them.          # Loop through the relations, displaying them.
568          for my $relation (sort keys %{$relationList}) {          for my $relation (sort keys %{$relationList}) {
569              my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});              my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});
570              print HTMLOUT $htmlString;              $retVal .= $htmlString;
571          }          }
572      }      }
573      # Denote we're starting the relationship section.      # Denote we're starting the relationship section.
574      print HTMLOUT "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";      $retVal .= "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";
575      # Loop through the relationships.      # Loop through the relationships.
576      for my $key (sort keys %{$relationshipList}) {      for my $key (sort keys %{$relationshipList}) {
577          Trace("Building MetaData entry for $key relationship.") if T(4);          Trace("Building MetaData entry for $key relationship.") if T(4);
# Line 468  Line 579 
579          my $relationshipStructure = $relationshipList->{$key};          my $relationshipStructure = $relationshipList->{$key};
580          # Create the relationship header.          # Create the relationship header.
581          my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);          my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);
582          print HTMLOUT "<h3><a name=\"$key\"></a>$headerText</h3>\n";          $retVal .= "<h3><a name=\"$key\"></a>$headerText</h3>\n";
583          # Get the entity names.          # Get the entity names.
584          my $fromEntity = $relationshipStructure->{from};          my $fromEntity = $relationshipStructure->{from};
585          my $toEntity = $relationshipStructure->{to};          my $toEntity = $relationshipStructure->{to};
# Line 478  Line 589 
589          # since both sentences will say the same thing.          # since both sentences will say the same thing.
590          my $arity = $relationshipStructure->{arity};          my $arity = $relationshipStructure->{arity};
591          if ($arity eq "11") {          if ($arity eq "11") {
592              print HTMLOUT "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";
593          } else {          } else {
594              print HTMLOUT "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";
595              if ($arity eq "MM" && $fromEntity ne $toEntity) {              if ($arity eq "MM" && $fromEntity ne $toEntity) {
596                  print HTMLOUT "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";                  $retVal .= "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";
597              }              }
598          }          }
599          print HTMLOUT "</p>\n";          $retVal .= "</p>\n";
600          # If there are notes on this relationship, display them.          # If there are notes on this relationship, display them.
601          if (my $notes = $relationshipStructure->{Notes}) {          if (my $notes = $relationshipStructure->{Notes}) {
602              print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
603          }          }
604          # Generate the relationship's relation table.          # Generate the relationship's relation table.
605          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
606          print HTMLOUT $htmlString;          $retVal .= $htmlString;
607      }      }
608      Trace("Building MetaData join table.") if T(4);      Trace("Building MetaData join table.") if T(4);
609      # Denote we're starting the join table.      # Denote we're starting the join table.
610      print HTMLOUT "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";      $retVal .= "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";
611      # Create a table header.      # Create a table header.
612      print HTMLOUT _OpenTable("Join Table", "Source", "Target", "Join Condition");      $retVal .= _OpenTable("Join Table", "Source", "Target", "Join Condition");
613      # Loop through the joins.      # Loop through the joins.
614      my $joinTable = $metadata->{Joins};      my $joinTable = $metadata->{Joins};
615      my @joinKeys = keys %{$joinTable};      my @joinKeys = keys %{$joinTable};
# Line 506  Line 617 
617          # Separate out the source, the target, and the join clause.          # Separate out the source, the target, and the join clause.
618          $joinKey =~ m!^([^/]+)/(.+)$!;          $joinKey =~ m!^([^/]+)/(.+)$!;
619          my ($sourceRelation, $targetRelation) = ($1, $2);          my ($sourceRelation, $targetRelation) = ($1, $2);
620          Trace("Join with key $joinKey is from $sourceRelation to $targetRelation.") if T(4);          Trace("Join with key $joinKey is from $sourceRelation to $targetRelation.") if T(Joins => 4);
621          my $source = $self->ComputeObjectSentence($sourceRelation);          my $source = $self->ComputeObjectSentence($sourceRelation);
622          my $target = $self->ComputeObjectSentence($targetRelation);          my $target = $self->ComputeObjectSentence($targetRelation);
623          my $clause = $joinTable->{$joinKey};          my $clause = $joinTable->{$joinKey};
624          # Display them in a table row.          # Display them in a table row.
625          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";
626      }      }
627      # Close the table.      # Close the table.
628      print HTMLOUT _CloseTable();      $retVal .= _CloseTable();
629      # Close the document.      Trace("Built MetaData HTML.") if T(3);
630      print HTMLOUT "</body>\n</html>\n";      # Return the HTML.
631      # Close the file.      return $retVal;
     close HTMLOUT;  
     Trace("Built MetaData web page.") if T(3);  
632  }  }
633    
634  =head3 DumpMetaData  =head3 DumpMetaData
635    
636  C<< $database->DumpMetaData(); >>  C<< $erdb->DumpMetaData(); >>
637    
638  Return a dump of the metadata structure.  Return a dump of the metadata structure.
639    
# Line 539  Line 648 
648    
649  =head3 CreateTables  =head3 CreateTables
650    
651  C<< $datanase->CreateTables(); >>  C<< $erdb->CreateTables(); >>
652    
653  This method creates the tables for the database from the metadata structure loaded by the  This method creates the tables for the database from the metadata structure loaded by the
654  constructor. It is expected this function will only be used on rare occasions, when the  constructor. It is expected this function will only be used on rare occasions, when the
# Line 551  Line 660 
660  sub CreateTables {  sub CreateTables {
661      # Get the parameters.      # Get the parameters.
662      my ($self) = @_;      my ($self) = @_;
663      my $metadata = $self->{_metaData};      # Get the relation names.
664      my $dbh = $self->{_dbh};      my @relNames = $self->GetTableNames();
665      # Loop through the entities.      # Loop through the relations.
666      my $entityHash = $metadata->{Entities};      for my $relationName (@relNames) {
     for my $entityName (keys %{$entityHash}) {  
         my $entityData = $entityHash->{$entityName};  
         # Tell the user what we're doing.  
         Trace("Creating relations for entity $entityName.") if T(1);  
         # Loop through the entity's relations.  
         for my $relationName (keys %{$entityData->{Relations}}) {  
667              # Create a table for this relation.              # Create a table for this relation.
668              $self->CreateTable($relationName);              $self->CreateTable($relationName);
669              Trace("Relation $relationName created.") if T(1);          Trace("Relation $relationName created.") if T(2);
         }  
     }  
     # Loop through the relationships.  
     my $relationshipTable = $metadata->{Relationships};  
     for my $relationshipName (keys %{$metadata->{Relationships}}) {  
         # Create a table for this relationship.  
         Trace("Creating relationship $relationshipName.") if T(1);  
         $self->CreateTable($relationshipName);  
670      }      }
671  }  }
672    
673  =head3 CreateTable  =head3 CreateTable
674    
675  C<< $database->CreateTable($tableName, $indexFlag); >>  C<< $erdb->CreateTable($tableName, $indexFlag, $estimatedRows); >>
676    
677  Create the table for a relation and optionally create its indexes.  Create the table for a relation and optionally create its indexes.
678    
# Line 587  Line 682 
682    
683  Name of the relation (which will also be the table name).  Name of the relation (which will also be the table name).
684    
685  =item $indexFlag  =item indexFlag
686    
687  TRUE if the indexes for the relation should be created, else FALSE. If FALSE,  TRUE if the indexes for the relation should be created, else FALSE. If FALSE,
688  L</CreateIndexes> must be called later to bring the indexes into existence.  L</CreateIndexes> must be called later to bring the indexes into existence.
689    
690    =item estimatedRows (optional)
691    
692    If specified, the estimated maximum number of rows for the relation. This
693    information allows the creation of tables using storage engines that are
694    faster but require size estimates, such as MyISAM.
695    
696  =back  =back
697    
698  =cut  =cut
699    
700  sub CreateTable {  sub CreateTable {
701      # Get the parameters.      # Get the parameters.
702      my ($self, $relationName, $indexFlag) = @_;      my ($self, $relationName, $indexFlag, $estimatedRows) = @_;
703      # Get the database handle.      # Get the database handle.
704      my $dbh = $self->{_dbh};      my $dbh = $self->{_dbh};
705      # Get the relation data and determine whether or not the relation is primary.      # Get the relation data and determine whether or not the relation is primary.
# Line 622  Line 723 
723      # Insure the table is not already there.      # Insure the table is not already there.
724      $dbh->drop_table(tbl => $relationName);      $dbh->drop_table(tbl => $relationName);
725      Trace("Table $relationName dropped.") if T(2);      Trace("Table $relationName dropped.") if T(2);
726        # If there are estimated rows, create an estimate so we can take advantage of
727        # faster DB technologies.
728        my $estimation = undef;
729        if ($estimatedRows) {
730            $estimation = [$self->EstimateRowSize($relationName), $estimatedRows];
731        }
732      # Create the table.      # Create the table.
733      Trace("Creating table $relationName: $fieldThing") if T(2);      Trace("Creating table $relationName: $fieldThing") if T(2);
734      $dbh->create_table(tbl => $relationName, flds => $fieldThing);      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);
735      Trace("Relation $relationName created in database.") if T(2);      Trace("Relation $relationName created in database.") if T(2);
736      # If we want to build the indexes, we do it here.      # If we want to build the indexes, we do it here. Note that the full-text search
737        # index will not be built until the table has been loaded.
738      if ($indexFlag) {      if ($indexFlag) {
739          $self->CreateIndex($relationName);          $self->CreateIndex($relationName);
740      }      }
741  }  }
742    
743    =head3 VerifyFields
744    
745    C<< my $count = $erdb->VerifyFields($relName, \@fieldList); >>
746    
747    Run through the list of proposed field values, insuring that all the character fields are
748    below the maximum length. If any fields are too long, they will be truncated in place.
749    
750    =over 4
751    
752    =item relName
753    
754    Name of the relation for which the specified fields are destined.
755    
756    =item fieldList
757    
758    Reference to a list, in order, of the fields to be put into the relation.
759    
760    =item RETURN
761    
762    Returns the number of fields truncated.
763    
764    =back
765    
766    =cut
767    
768    sub VerifyFields {
769        # Get the parameters.
770        my ($self, $relName, $fieldList) = @_;
771        # Initialize the return value.
772        my $retVal = 0;
773        # Get the relation definition.
774        my $relData = $self->_FindRelation($relName);
775        # Get the list of field descriptors.
776        my $fieldTypes = $relData->{Fields};
777        my $fieldCount = scalar @{$fieldTypes};
778        # Loop through the two lists.
779        for (my $i = 0; $i < $fieldCount; $i++) {
780            # Get the type of the current field.
781            my $fieldType = $fieldTypes->[$i]->{type};
782            # If it's a character field, verify the length.
783            if ($fieldType =~ /string/) {
784                my $maxLen = $TypeTable{$fieldType}->{maxLen};
785                my $oldString = $fieldList->[$i];
786                if (length($oldString) > $maxLen) {
787                    # Here it's too big, so we truncate it.
788                    Trace("Truncating field $i in relation $relName to $maxLen characters from \"$oldString\".") if T(1);
789                    $fieldList->[$i] = substr $oldString, 0, $maxLen;
790                    $retVal++;
791                }
792            }
793        }
794        # Return the truncation count.
795        return $retVal;
796    }
797    
798    =head3 DigestFields
799    
800    C<< $erdb->DigestFields($relName, $fieldList); >>
801    
802    Digest the strings in the field list that correspond to data type C<hash-string> in the
803    specified relation.
804    
805    =over 4
806    
807    =item relName
808    
809    Name of the relation to which the fields belong.
810    
811    =item fieldList
812    
813    List of field contents to be loaded into the relation.
814    
815    =back
816    
817    =cut
818    #: Return Type ;
819    sub DigestFields {
820        # Get the parameters.
821        my ($self, $relName, $fieldList) = @_;
822        # Get the relation definition.
823        my $relData = $self->_FindRelation($relName);
824        # Get the list of field descriptors.
825        my $fieldTypes = $relData->{Fields};
826        my $fieldCount = scalar @{$fieldTypes};
827        # Loop through the two lists.
828        for (my $i = 0; $i < $fieldCount; $i++) {
829            # Get the type of the current field.
830            my $fieldType = $fieldTypes->[$i]->{type};
831            # If it's a hash string, digest it in place.
832            if ($fieldType eq 'hash-string') {
833                $fieldList->[$i] = $self->DigestKey($fieldList->[$i]);
834            }
835        }
836    }
837    
838    =head3 DigestKey
839    
840    C<< my $digested = $erdb->DigestKey($keyValue); >>
841    
842    Return the digested value of a symbolic key. The digested value can then be plugged into a
843    key-based search into a table with key-type hash-string.
844    
845    Currently the digesting process is independent of the database structure, but that may not
846    always be the case, so this is an instance method instead of a static method.
847    
848    =over 4
849    
850    =item keyValue
851    
852    Key value to digest.
853    
854    =item RETURN
855    
856    Digested value of the key.
857    
858    =back
859    
860    =cut
861    
862    sub DigestKey {
863        # Get the parameters.
864        my ($self, $keyValue) = @_;
865        # Compute the digest.
866        my $retVal = md5_base64($keyValue);
867        # Return the result.
868        return $retVal;
869    }
870    
871  =head3 CreateIndex  =head3 CreateIndex
872    
873  C<< $database->CreateIndex($relationName); >>  C<< $erdb->CreateIndex($relationName); >>
874    
875  Create the indexes for a relation. If a table is being loaded from a large source file (as  Create the indexes for a relation. If a table is being loaded from a large source file (as
876  is the case in L</LoadTable>), it is best to create the indexes after the load. If that is  is the case in L</LoadTable>), it is sometimes best to create the indexes after the load.
877  the case, then L</CreateTable> should be called with the index flag set to FALSE, and this  If that is the case, then L</CreateTable> should be called with the index flag set to
878  method used after the load to create the indexes for the table.  FALSE, and this method used after the load to create the indexes for the table.
879    
880  =cut  =cut
881    
# Line 658  Line 894 
894          my @fieldList = _FixNames(@{$indexData->{IndexFields}});          my @fieldList = _FixNames(@{$indexData->{IndexFields}});
895          my $flds = join(', ', @fieldList);          my $flds = join(', ', @fieldList);
896          # Get the index's uniqueness flag.          # Get the index's uniqueness flag.
897          my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
898          # Create the index.          # Create the index.
899          $dbh->create_index(idx => $indexName, tbl => $relationName, flds => $flds, unique => $unique);          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
900                                        flds => $flds, kind => $unique);
901            if ($rv) {
902          Trace("Index created: $indexName for $relationName ($flds)") if T(1);          Trace("Index created: $indexName for $relationName ($flds)") if T(1);
903            } else {
904                Confess("Error creating index $indexName for $relationName using ($flds): " . $dbh->error_message());
905            }
906      }      }
907  }  }
908    
909  =head3 LoadTables  =head3 LoadTables
910    
911  C<< my $stats = $database->LoadTables($directoryName, $rebuild); >>  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>
912    
913  This method will load the database tables from a directory. The tables must already have been created  This method will load the database tables from a directory. The tables must already have been created
914  in the database. (This can be done by calling L</CreateTables>.) The caller passes in a directory name;  in the database. (This can be done by calling L</CreateTables>.) The caller passes in a directory name;
# Line 710  Line 951 
951      $directoryName =~ s!/\\$!!;      $directoryName =~ s!/\\$!!;
952      # Declare the return variable.      # Declare the return variable.
953      my $retVal = Stats->new();      my $retVal = Stats->new();
954      # Get the metadata structure.      # Get the relation names.
955      my $metaData = $self->{_metaData};      my @relNames = $self->GetTableNames();
956      # Loop through the entities.      for my $relationName (@relNames) {
     for my $entity (values %{$metaData->{Entities}}) {  
         # Loop through the entity's relations.  
         for my $relationName (keys %{$entity->{Relations}}) {  
957              # Try to load this relation.              # Try to load this relation.
958              my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);              my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);
959              # Accumulate the statistics.              # Accumulate the statistics.
960              $retVal->Accumulate($result);              $retVal->Accumulate($result);
961          }          }
     }  
     # Loop through the relationships.  
     for my $relationshipName (keys %{$metaData->{Relationships}}) {  
         # Try to load this relationship's relation.  
         my $result = $self->_LoadRelation($directoryName, $relationshipName, $rebuild);  
         # Accumulate the statistics.  
         $retVal->Accumulate($result);  
     }  
962      # Add the duration of the load to the statistical object.      # Add the duration of the load to the statistical object.
963      $retVal->Add('duration', gettimeofday - $startTime);      $retVal->Add('duration', gettimeofday - $startTime);
964      # Return the accumulated statistics.      # Return the accumulated statistics.
965      return $retVal;      return $retVal;
966  }  }
967    
968    
969  =head3 GetTableNames  =head3 GetTableNames
970    
971  C<< my @names = $database->GetTableNames; >>  C<< my @names = $erdb->GetTableNames; >>
972    
973  Return a list of the relations required to implement this database.  Return a list of the relations required to implement this database.
974    
# Line 754  Line 985 
985    
986  =head3 GetEntityTypes  =head3 GetEntityTypes
987    
988  C<< my @names = $database->GetEntityTypes; >>  C<< my @names = $erdb->GetEntityTypes; >>
989    
990  Return a list of the entity type names.  Return a list of the entity type names.
991    
# Line 769  Line 1000 
1000      return sort keys %{$entityList};      return sort keys %{$entityList};
1001  }  }
1002    
1003    =head3 GetDataTypes
1004    
1005    C<< my %types = ERDB::GetDataTypes(); >>
1006    
1007    Return a table of ERDB data types. The table returned is a hash of hashes.
1008    The keys of the big hash are the datatypes. Each smaller hash has several
1009    values used to manage the data. The most interesting is the SQL type (key
1010    C<sqlType>) and the descriptive node (key C<notes>).
1011    
1012    Note that changing the values in the smaller hashes will seriously break
1013    things, so this data should be treated as read-only.
1014    
1015    =cut
1016    
1017    sub GetDataTypes {
1018        return %TypeTable;
1019    }
1020    
1021    
1022    =head3 IsEntity
1023    
1024    C<< my $flag = $erdb->IsEntity($entityName); >>
1025    
1026    Return TRUE if the parameter is an entity name, else FALSE.
1027    
1028    =over 4
1029    
1030    =item entityName
1031    
1032    Object name to be tested.
1033    
1034    =item RETURN
1035    
1036    Returns TRUE if the specified string is an entity name, else FALSE.
1037    
1038    =back
1039    
1040    =cut
1041    
1042    sub IsEntity {
1043        # Get the parameters.
1044        my ($self, $entityName) = @_;
1045        # Test to see if it's an entity.
1046        return exists $self->{_metaData}->{Entities}->{$entityName};
1047    }
1048    
1049  =head3 Get  =head3 Get
1050    
1051  C<< my $query = $database->Get(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  C<< my $query = $erdb->Get(\@objectNames, $filterClause, \@params); >>
1052    
1053  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.
1054  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 779  Line 1056 
1056  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
1057  $genus.  $genus.
1058    
1059  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", [$genus]); >>
1060    
1061  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
1062  parameter representing the parameter value. It would also be possible to code  parameter representing the parameter value. It would also be possible to code
1063    
1064  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>
1065    
1066  however, this version of the call would generate a syntax error if there were any quote  however, this version of the call would generate a syntax error if there were any quote
1067  characters inside the variable C<$genus>.  characters inside the variable C<$genus>.
# Line 796  Line 1073 
1073  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
1074  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,
1075    
1076  C<< $query = $sprout->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]); >>
1077    
1078  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
1079  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.
1080  In particular, you can't specify any entity or relationship more than once, and if a  In particular, if a relationship is recursive, the path is determined by the order in which
1081  relationship is recursive, the path is determined by the order in which the entity  the entity and the relationship appear. For example, consider a recursive relationship
1082  and the relationship appear. For example, consider a recursive relationship B<IsParentOf>  B<IsParentOf> which relates B<People> objects to other B<People> objects. If the join path is
 which relates B<People> objects to other B<People> objects. If the join path is  
1083  coded as C<['People', 'IsParentOf']>, then the people returned will be parents. If, however,  coded as C<['People', 'IsParentOf']>, then the people returned will be parents. If, however,
1084  the join path is C<['IsParentOf', 'People']>, then the people returned will be children.  the join path is C<['IsParentOf', 'People']>, then the people returned will be children.
1085    
1086    If an entity or relationship is mentioned twice, the name for the second occurrence will
1087    be suffixed with C<2>, the third occurrence will be suffixed with C<3>, and so forth. So,
1088    for example, if we have C<['Feature', 'HasContig', 'Contig', 'HasContig']>, then the
1089    B<to-link> field of the first B<HasContig> is specified as C<HasContig(to-link)>, while
1090    the B<to-link> field of the second B<HasContig> is specified as C<HasContig2(to-link)>.
1091    
1092  =over 4  =over 4
1093    
1094  =item objectNames  =item objectNames
# Line 829  Line 1111 
1111    
1112  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
1113    
1114    Note that the case is important. Only an uppercase "ORDER BY" with a single space will
1115    be processed. The idea is to make it less likely to find the verb by accident.
1116    
1117  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
1118  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
1119  relation.  relation.
1120    
1121  =item param1, param2, ..., paramN  Finally, you can limit the number of rows returned by adding a LIMIT clause. The LIMIT must
1122    be the last thing in the filter clause, and it contains only the word "LIMIT" followed by
1123    a positive number. So, for example
1124    
1125    C<< "Genome(genus) = ? ORDER BY Genome(species) LIMIT 10" >>
1126    
1127    will only return the first ten genomes for the specified genus. The ORDER BY clause is not
1128    required. For example, to just get the first 10 genomes in the B<Genome> table, you could
1129    use
1130    
1131    C<< "LIMIT 10" >>
1132    
1133  Parameter values to be substituted into the filter clause.  =item params
1134    
1135    Reference to a list of parameter values to be substituted into the filter clause.
1136    
1137  =item RETURN  =item RETURN
1138    
# Line 847  Line 1144 
1144    
1145  sub Get {  sub Get {
1146      # Get the parameters.      # Get the parameters.
1147      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $objectNames, $filterClause, $params) = @_;
1148      # Construct the SELECT statement. The general pattern is      # Process the SQL stuff.
1149      #      my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1150      # SELECT name1.*, name2.*, ... nameN.* FROM name1, name2, ... nameN          $self->_SetupSQL($objectNames, $filterClause);
1151      #      # Create the query.
1152      my $dbh = $self->{_dbh};      my $command = "SELECT DISTINCT " . join(".*, ", @{$mappedNameListRef}) .
1153      my $command = "SELECT DISTINCT " . join('.*, ', @{$objectNames}) . ".* FROM " .          ".* $suffix";
1154                  join(', ', @{$objectNames});      my $sth = $self->_GetStatementHandle($command, $params);
1155      # Check for a filter clause.      # Now we create the relation map, which enables DBQuery to determine the order, name
1156      if ($filterClause) {      # and mapped name for each object in the query.
1157          # Here we have one, so we convert its field names and add it to the query. First,      my @relationMap = ();
1158          # We create a copy of the filter string we can work with.      for my $mappedName (@{$mappedNameListRef}) {
1159          my $filterString = $filterClause;          push @relationMap, [$mappedName, $mappedNameHashRef->{$mappedName}];
         # Next, we sort the object names by length. This helps protect us from finding  
         # object names inside other object names when we're doing our search and replace.  
         my @sortedNames = sort { length($b) - length($a) } @{$objectNames};  
         # We will also keep a list of conditions to add to the WHERE clause in order to link  
         # entities and relationships as well as primary relations to secondary ones.  
         my @joinWhere = ();  
         # The final preparatory step is to create a hash table of relation names. The  
         # table begins with the relation names already in the SELECT command.  
         my %fromNames = ();  
         for my $objectName (@sortedNames) {  
             $fromNames{$objectName} = 1;  
         }  
         # We are ready to begin. We loop through the object names, replacing each  
         # object name's field references by the corresponding SQL field reference.  
         # Along the way, if we find a secondary relation, we will need to add it  
         # to the FROM clause.  
         for my $objectName (@sortedNames) {  
             # Get the length of the object name plus 2. This is the value we add to the  
             # size of the field name to determine the size of the field reference as a  
             # whole.  
             my $nameLength = 2 + length $objectName;  
             # Get the object's field list.  
             my $fieldList = $self->_GetFieldTable($objectName);  
             # Find the field references for this object.  
             while ($filterString =~ m/$objectName\(([^)]*)\)/g) {  
                 # At this point, $1 contains the field name, and the current position  
                 # is set immediately after the final parenthesis. We pull out the name of  
                 # the field and the position and length of the field reference as a whole.  
                 my $fieldName = $1;  
                 my $len = $nameLength + length $fieldName;  
                 my $pos = pos($filterString) - $len;  
                 # Insure the field exists.  
                 if (!exists $fieldList->{$fieldName}) {  
                     Confess("Field $fieldName not found for object $objectName.");  
                 } else {  
                     # Get the field's relation.  
                     my $relationName = $fieldList->{$fieldName}->{relation};  
                     # Insure the relation is in the FROM clause.  
                     if (!exists $fromNames{$relationName}) {  
                         # Add the relation to the FROM clause.  
                         $command .= ", $relationName";  
                         # Create its join sub-clause.  
                         push @joinWhere, "$objectName.id = $relationName.id";  
                         # Denote we have it available for future fields.  
                         $fromNames{$relationName} = 1;  
                     }  
                     # Form an SQL field reference from the relation name and the field name.  
                     my $sqlReference = "$relationName." . _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 $sqlReference;  
                 }  
             }  
         }  
         # The next step is to join the objects together. We only need to do this if there  
         # is more than one object in the object list. We start with the first object and  
         # run through the objects after it. Note also that we make a safety copy of the  
         # list before running through it.  
         my @objectList = @{$objectNames};  
         my $lastObject = shift @objectList;  
         # Get the join table.  
         my $joinTable = $self->{_metaData}->{Joins};  
         # Loop through the object list.  
         for my $thisObject (@objectList) {  
             # Look for a join.  
             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 $lastObject to $thisObject.");  
             } else {  
                 # Get the join clause and add it to the WHERE list.  
                 push @joinWhere, $joinTable->{$joinKey};  
                 # Save this object as the last object for the next iteration.  
                 $lastObject = $thisObject;  
             }  
         }  
         # Now we need to handle the whole ORDER BY thing. We'll put the order by clause  
         # in the following variable.  
         my $orderClause = "";  
         # Locate the ORDER BY verb (if any).  
         if ($filterString =~ m/^(.*)ORDER BY/g) {  
             # Here we have an ORDER BY verb. Split it off of the filter string.  
             my $pos = pos $filterString;  
             $orderClause = substr($filterString, $pos);  
             $filterString = $1;  
         }  
         # Add the filter and the join clauses (if any) to the SELECT command.  
         if ($filterString) {  
             push @joinWhere, "($filterString)";  
         }  
         if (@joinWhere) {  
             $command .= " WHERE " . join(' AND ', @joinWhere);  
         }  
         # Add the sort clause (if any) to the SELECT command.  
         if ($orderClause) {  
             $command .= " ORDER BY $orderClause";  
         }  
1160      }      }
     Trace("SQL query: $command") if T(2);  
     Trace("PARMS: '" . (join "', '", @params) . "'") if (T(3) && (@params > 0));  
     my $sth = $dbh->prepare_command($command);  
     # Execute it with the parameters bound in.  
     $sth->execute(@params) || Confess("SELECT error" . $sth->errstr());  
1161      # Return the statement object.      # Return the statement object.
1162      my $retVal = DBQuery::_new($self, $sth, @{$objectNames});      my $retVal = DBQuery::_new($self, $sth, \@relationMap);
1163      return $retVal;      return $retVal;
1164  }  }
1165    
1166  =head3 GetList  =head3 Search
   
 C<< my @dbObjects = $database->GetList(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  
1167    
1168  Return a list of object descriptors for the specified objects as determined by the  C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>
 specified filter clause.  
1169    
1170  This method is essentially the same as L</Get> except it returns a list of objects rather  Perform a full text search with filtering. The search will be against a specified object
1171  than a query object that can be used to get the results one record at a time.  in the object name list. That object will get an extra field containing the search
1172    relevance. Note that except for the search expression, the parameters of this method are
1173    the same as those for L</Get> and follow the same rules.
1174    
1175  =over 4  =over 4
1176    
1177  =item objectNames  =item searchExpression
1178    
1179  List containing the names of the entity and relationship objects to be retrieved.  Boolean search expression for the text fields of the target object.
1180    
1181  =item filterClause  =item idx
1182    
1183    Index in the I<$objectNames> list of the table to be searched in full-text mode.
1184    
1185    =item objectNames
1186    
1187    List containing the names of the entity and relationship objects to be retrieved.
1188    
1189    =item filterClause
1190    
1191    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1192    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
1193    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
1194    in the filter clause should be added to the parameter list as additional parameters. The
1195    fields in a filter clause can come from primary entity relations, relationship relations,
1196    or secondary entity relations; however, all of the entities and relationships involved must
1197    be included in the list of object names.
1198    
1199    =item params
1200    
1201    Reference to a list of parameter values to be substituted into the filter clause.
1202    
1203    =item RETURN
1204    
1205    Returns a query object for the specified search.
1206    
1207    =back
1208    
1209    =cut
1210    
1211    sub Search {
1212        # Get the parameters.
1213        my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1214        # Declare the return variable.
1215        my $retVal;
1216        # Create a safety copy of the parameter list. Note we have to be careful to insure
1217        # a parameter list exists before we copy it.
1218        my @myParams = ();
1219        if (defined $params) {
1220            @myParams = @{$params};
1221        }
1222        # Get the first object's structure so we have access to the searchable fields.
1223        my $object1Name = $objectNames->[$idx];
1224        my $object1Structure = $self->_GetStructure($object1Name);
1225        # Get the field list.
1226        if (! exists $object1Structure->{searchFields}) {
1227            Confess("No searchable index for $object1Name.");
1228        } else {
1229            # Get the field list.
1230            my @fields = @{$object1Structure->{searchFields}};
1231            # Clean the search expression.
1232            my $actualKeywords = $self->CleanKeywords($searchExpression);
1233            Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1234            # We need two match expressions, one for the filter clause and one in the
1235            # query itself. Both will use a parameter mark, so we need to push the
1236            # search expression onto the front of the parameter list twice.
1237            unshift @myParams, $actualKeywords, $actualKeywords;
1238            # Build the match expression.
1239            my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
1240            my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
1241            # Process the SQL stuff.
1242            my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1243                $self->_SetupSQL($objectNames, $filterClause, $matchClause);
1244            # Create the query. Note that the match clause is inserted at the front of
1245            # the select fields.
1246            my $command = "SELECT DISTINCT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .
1247                ".* $suffix";
1248            my $sth = $self->_GetStatementHandle($command, \@myParams);
1249            # Now we create the relation map, which enables DBQuery to determine the order, name
1250            # and mapped name for each object in the query.
1251            my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
1252            # Return the statement object.
1253            $retVal = DBQuery::_new($self, $sth, \@relationMap, $object1Name);
1254        }
1255        return $retVal;
1256    }
1257    
1258    =head3 GetFlat
1259    
1260    C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>
1261    
1262    This is a variation of L</GetAll> that asks for only a single field per record and
1263    returns a single flattened list.
1264    
1265    =over 4
1266    
1267    =item objectNames
1268    
1269    List containing the names of the entity and relationship objects to be retrieved.
1270    
1271    =item filterClause
1272    
1273    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1274    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
1275    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
1276    parameter list as additional parameters. The fields in a filter clause can come from primary
1277    entity relations, relationship relations, or secondary entity relations; however, all of the
1278    entities and relationships involved must be included in the list of object names.
1279    
1280    =item parameterList
1281    
1282    List of the parameters to be substituted in for the parameters marks in the filter clause.
1283    
1284    =item field
1285    
1286    Name of the field to be used to get the elements of the list returned.
1287    
1288    =item RETURN
1289    
1290    Returns a list of values.
1291    
1292    =back
1293    
1294    =cut
1295    #: Return Type @;
1296    sub GetFlat {
1297        # Get the parameters.
1298        my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
1299        # Construct the query.
1300        my $query = $self->Get($objectNames, $filterClause, $parameterList);
1301        # Create the result list.
1302        my @retVal = ();
1303        # Loop through the records, adding the field values found to the result list.
1304        while (my $row = $query->Fetch()) {
1305            push @retVal, $row->Value($field);
1306        }
1307        # Return the list created.
1308        return @retVal;
1309    }
1310    
1311    =head3 SpecialFields
1312    
1313    C<< my %specials = $erdb->SpecialFields($entityName); >>
1314    
1315    Return a hash mapping special fields in the specified entity to the value of their
1316    C<special> attribute. This enables the subclass to get access to the special field
1317    attributes without needed to plumb the internal ERDB data structures.
1318    
1319    =over 4
1320    
1321    =item entityName
1322    
1323    Name of the entity whose special fields are desired.
1324    
1325    =item RETURN
1326    
1327    Returns a hash. The keys of the hash are the special field names, and the values
1328    are the values from each special field's C<special> attribute.
1329    
1330    =back
1331    
1332    =cut
1333    
1334    sub SpecialFields {
1335        # Get the parameters.
1336        my ($self, $entityName) = @_;
1337        # Declare the return variable.
1338        my %retVal = ();
1339        # Find the entity's data structure.
1340        my $entityData = $self->{Entities}->{$entityName};
1341        # Loop through its fields, adding each special field to the return hash.
1342        my $fieldHash = $entityData->{Fields};
1343        for my $fieldName (keys %{$fieldHash}) {
1344            my $fieldData = $fieldHash->{$fieldName};
1345            if (exists $fieldData->{special}) {
1346                $retVal{$fieldName} = $fieldData->{special};
1347            }
1348        }
1349        # Return the result.
1350        return %retVal;
1351    }
1352    
1353    =head3 Delete
1354    
1355    C<< my $stats = $erdb->Delete($entityName, $objectID); >>
1356    
1357    Delete an entity instance from the database. The instance is deleted along with all entity and
1358    relationship instances dependent on it. The idea of dependence here is recursive. An object is
1359    always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many
1360    relationship connected to a dependent entity or the "to" entity connected to a 1-to-many
1361    dependent relationship.
1362    
1363    =over 4
1364    
1365    =item entityName
1366    
1367    Name of the entity type for the instance being deleted.
1368    
1369    =item objectID
1370    
1371    ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),
1372    then it is presumed to by a LIKE pattern.
1373    
1374    =item testFlag
1375    
1376    If TRUE, the delete statements will be traced without being executed.
1377    
1378    =item RETURN
1379    
1380    Returns a statistics object indicating how many records of each particular table were
1381    deleted.
1382    
1383    =back
1384    
1385    =cut
1386    #: Return Type $%;
1387    sub Delete {
1388        # Get the parameters.
1389        my ($self, $entityName, $objectID, $testFlag) = @_;
1390        # Declare the return variable.
1391        my $retVal = Stats->new();
1392        # Get the DBKernel object.
1393        my $db = $self->{_dbh};
1394        # We're going to generate all the paths branching out from the starting entity. One of
1395        # the things we have to be careful about is preventing loops. We'll use a hash to
1396        # determine if we've hit a loop.
1397        my %alreadyFound = ();
1398        # These next lists will serve as our result stack. We start by pushing object lists onto
1399        # the stack, and then popping them off to do the deletes. This means the deletes will
1400        # start with the longer paths before getting to the shorter ones. That, in turn, makes
1401        # sure we don't delete records that might be needed to forge relationships back to the
1402        # original item. We have two lists-- one for TO-relationships, and one for
1403        # FROM-relationships and entities.
1404        my @fromPathList = ();
1405        my @toPathList = ();
1406        # This final hash is used to remember what work still needs to be done. We push paths
1407        # onto the list, then pop them off to extend the paths. We prime it with the starting
1408        # point. Note that we will work hard to insure that the last item on a path in the
1409        # TODO list is always an entity.
1410        my @todoList = ([$entityName]);
1411        while (@todoList) {
1412            # Get the current path.
1413            my $current = pop @todoList;
1414            # Copy it into a list.
1415            my @stackedPath = @{$current};
1416            # Pull off the last item on the path. It will always be an entity.
1417            my $entityName = pop @stackedPath;
1418            # Add it to the alreadyFound list.
1419            $alreadyFound{$entityName} = 1;
1420            # Get the entity data.
1421            my $entityData = $self->_GetStructure($entityName);
1422            # The first task is to loop through the entity's relation. A DELETE command will
1423            # be needed for each of them.
1424            my $relations = $entityData->{Relations};
1425            for my $relation (keys %{$relations}) {
1426                my @augmentedList = (@stackedPath, $relation);
1427                push @fromPathList, \@augmentedList;
1428            }
1429            # Now we need to look for relationships connected to this entity.
1430            my $relationshipList = $self->{_metaData}->{Relationships};
1431            for my $relationshipName (keys %{$relationshipList}) {
1432                my $relationship = $relationshipList->{$relationshipName};
1433                # Check the FROM field. We're only interested if it's us.
1434                if ($relationship->{from} eq $entityName) {
1435                    # Add the path to this relationship.
1436                    my @augmentedList = (@stackedPath, $entityName, $relationshipName);
1437                    push @fromPathList, \@augmentedList;
1438                    # Check the arity. If it's MM we're done. If it's 1M
1439                    # and the target hasn't been seen yet, we want to
1440                    # stack the entity for future processing.
1441                    if ($relationship->{arity} eq '1M') {
1442                        my $toEntity = $relationship->{to};
1443                        if (! exists $alreadyFound{$toEntity}) {
1444                            # Here we have a new entity that's dependent on
1445                            # the current entity, so we need to stack it.
1446                            my @stackList = (@augmentedList, $toEntity);
1447                            push @fromPathList, \@stackList;
1448                        } else {
1449                            Trace("$toEntity ignored because it occurred previously.") if T(4);
1450                        }
1451                    }
1452                }
1453                # Now check the TO field. In this case only the relationship needs
1454                # deletion.
1455                if ($relationship->{to} eq $entityName) {
1456                    my @augmentedList = (@stackedPath, $entityName, $relationshipName);
1457                    push @toPathList, \@augmentedList;
1458                }
1459            }
1460        }
1461        # Create the first qualifier for the WHERE clause. This selects the
1462        # keys of the primary entity records to be deleted. When we're deleting
1463        # from a dependent table, we construct a join page from the first qualifier
1464        # to the table containing the dependent records to delete.
1465        my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
1466        # We need to make two passes. The first is through the to-list, and
1467        # the second through the from-list. The from-list is second because
1468        # the to-list may need to pass through some of the entities the
1469        # from-list would delete.
1470        my %stackList = ( from_link => \@fromPathList, to_link => \@toPathList );
1471        # Now it's time to do the deletes. We do it in two passes.
1472        for my $keyName ('to_link', 'from_link') {
1473            # Get the list for this key.
1474            my @pathList = @{$stackList{$keyName}};
1475            Trace(scalar(@pathList) . " entries in path list for $keyName.") if T(3);
1476            # Loop through this list.
1477            while (my $path = pop @pathList) {
1478                # Get the table whose rows are to be deleted.
1479                my @pathTables = @{$path};
1480                # Start the DELETE statement. We need to call DBKernel because the
1481                # syntax of a DELETE-USING varies among DBMSs.
1482                my $target = $pathTables[$#pathTables];
1483                my $stmt = $db->SetUsing(@pathTables);
1484                # Now start the WHERE. The first thing is the ID field from the starting table. That
1485                # starting table will either be the entity relation or one of the entity's
1486                # sub-relations.
1487                $stmt .= " WHERE $pathTables[0].id $qualifier";
1488                # Now we run through the remaining entities in the path, connecting them up.
1489                for (my $i = 1; $i <= $#pathTables; $i += 2) {
1490                    # Connect the current relationship to the preceding entity.
1491                    my ($entity, $rel) = @pathTables[$i-1,$i];
1492                    # The style of connection depends on the direction of the relationship.
1493                    $stmt .= " AND $entity.id = $rel.$keyName";
1494                    if ($i + 1 <= $#pathTables) {
1495                        # Here there's a next entity, so connect that to the relationship's
1496                        # to-link.
1497                        my $entity2 = $pathTables[$i+1];
1498                        $stmt .= " AND $rel.to_link = $entity2.id";
1499                    }
1500                }
1501                # Now we have our desired DELETE statement.
1502                if ($testFlag) {
1503                    # Here the user wants to trace without executing.
1504                    Trace($stmt) if T(0);
1505                } else {
1506                    # Here we can delete. Note that the SQL method dies with a confessing
1507                    # if an error occurs, so we just go ahead and do it.
1508                    Trace("Executing delete from $target using '$objectID'.") if T(3);
1509                    my $rv = $db->SQL($stmt, 0, $objectID);
1510                    # Accumulate the statistics for this delete. The only rows deleted
1511                    # are from the target table, so we use its name to record the
1512                    # statistic.
1513                    $retVal->Add($target, $rv);
1514                }
1515            }
1516        }
1517        # Return the result.
1518        return $retVal;
1519    }
1520    
1521    =head3 SortNeeded
1522    
1523    C<< my $parms = $erdb->SortNeeded($relationName); >>
1524    
1525    Return the pipe command for the sort that should be applied to the specified
1526    relation when creating the load file.
1527    
1528    For example, if the load file should be sorted ascending by the first
1529    field, this method would return
1530    
1531        sort -k1 -t"\t"
1532    
1533    If the first field is numeric, the method would return
1534    
1535        sort -k1n -t"\t"
1536    
1537    Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate
1538    keys using a sort.
1539    
1540    =over 4
1541    
1542    =item relationName
1543    
1544    Name of the relation to be examined.
1545    
1546    =item
1547    
1548    Returns the sort command to use for sorting the relation, suitable for piping.
1549    
1550    =back
1551    
1552    =cut
1553    #: Return Type $;
1554    sub SortNeeded {
1555        # Get the parameters.
1556        my ($self, $relationName) = @_;
1557        # Declare a descriptor to hold the names of the key fields.
1558        my @keyNames = ();
1559        # Get the relation structure.
1560        my $relationData = $self->_FindRelation($relationName);
1561        # Find out if the relation is a primary entity relation,
1562        # a relationship relation, or a secondary entity relation.
1563        my $entityTable = $self->{_metaData}->{Entities};
1564        my $relationshipTable = $self->{_metaData}->{Relationships};
1565        if (exists $entityTable->{$relationName}) {
1566            # Here we have a primary entity relation.
1567            push @keyNames, "id";
1568        } elsif (exists $relationshipTable->{$relationName}) {
1569            # Here we have a relationship. We sort using the FROM index.
1570            my $relationshipData = $relationshipTable->{$relationName};
1571            my $index = $relationData->{Indexes}->{"idx${relationName}From"};
1572            push @keyNames, @{$index->{IndexFields}};
1573        } else {
1574            # Here we have a secondary entity relation, so we have a sort on the ID field.
1575            push @keyNames, "id";
1576        }
1577        # Now we parse the key names into sort parameters. First, we prime the return
1578        # string.
1579        my $retVal = "sort -t\"\t\" ";
1580        # Get the relation's field list.
1581        my @fields = @{$relationData->{Fields}};
1582        # Loop through the keys.
1583        for my $keyData (@keyNames) {
1584            # Get the key and the ordering.
1585            my ($keyName, $ordering);
1586            if ($keyData =~ /^([^ ]+) DESC/) {
1587                ($keyName, $ordering) = ($1, "descending");
1588            } else {
1589                ($keyName, $ordering) = ($keyData, "ascending");
1590            }
1591            # Find the key's position and type.
1592            my $fieldSpec;
1593            for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {
1594                my $thisField = $fields[$i];
1595                if ($thisField->{name} eq $keyName) {
1596                    # Get the sort modifier for this field type. The modifier
1597                    # decides whether we're using a character, numeric, or
1598                    # floating-point sort.
1599                    my $modifier = $TypeTable{$thisField->{type}}->{sort};
1600                    # If the index is descending for this field, denote we want
1601                    # to reverse the sort order on this field.
1602                    if ($ordering eq 'descending') {
1603                        $modifier .= "r";
1604                    }
1605                    # Store the position and modifier into the field spec, which
1606                    # will stop the inner loop. Note that the field number is
1607                    # 1-based in the sort command, so we have to increment the
1608                    # index.
1609                    $fieldSpec = ($i + 1) . $modifier;
1610                }
1611            }
1612            # Add this field to the sort command.
1613            $retVal .= " -k$fieldSpec";
1614        }
1615        # Return the result.
1616        return $retVal;
1617    }
1618    
1619    =head3 GetList
1620    
1621    C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>
1622    
1623    Return a list of object descriptors for the specified objects as determined by the
1624    specified filter clause.
1625    
1626    This method is essentially the same as L</Get> except it returns a list of objects rather
1627    than a query object that can be used to get the results one record at a time.
1628    
1629    =over 4
1630    
1631    =item objectNames
1632    
1633    List containing the names of the entity and relationship objects to be retrieved.
1634    
1635    =item filterClause
1636    
1637  WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1638  be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be  be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
# Line 1005  Line 1652 
1652  filter clause in general; however, odd things may happen if a sort field is from a secondary  filter clause in general; however, odd things may happen if a sort field is from a secondary
1653  relation.  relation.
1654    
1655  =item param1, param2, ..., paramN  =item params
1656    
1657  Parameter values to be substituted into the filter clause.  Reference to a list of parameter values to be substituted into the filter clause.
1658    
1659  =item RETURN  =item RETURN
1660    
# Line 1019  Line 1666 
1666  #: Return Type @%  #: Return Type @%
1667  sub GetList {  sub GetList {
1668      # Get the parameters.      # Get the parameters.
1669      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $objectNames, $filterClause, $params) = @_;
1670      # Declare the return variable.      # Declare the return variable.
1671      my @retVal = ();      my @retVal = ();
1672      # Perform the query.      # Perform the query.
1673      my $query = $self->Get($objectNames, $filterClause, @params);      my $query = $self->Get($objectNames, $filterClause, $params);
1674      # Loop through the results.      # Loop through the results.
1675      while (my $object = $query->Fetch) {      while (my $object = $query->Fetch) {
1676          push @retVal, $object;          push @retVal, $object;
# Line 1032  Line 1679 
1679      return @retVal;      return @retVal;
1680  }  }
1681    
1682    =head3 GetCount
1683    
1684    C<< my $count = $erdb->GetCount(\@objectNames, $filter, \@params); >>
1685    
1686    Return the number of rows found by a specified query. This method would
1687    normally be used to count the records in a single table. For example, in a
1688    genetics database
1689    
1690        my $count = $erdb->GetCount(['Genome'], 'Genome(genus-species) LIKE ?', ['homo %']);
1691    
1692    would return the number of genomes for the genus I<homo>. It is conceivable, however,
1693    to use it to return records based on a join. For example,
1694    
1695        my $count = $erdb->GetCount(['HasFeature', 'Genome'], 'Genome(genus-species) LIKE ?',
1696                                    ['homo %']);
1697    
1698    would return the number of features for genomes in the genus I<homo>. Note that
1699    only the rows from the first table are counted. If the above command were
1700    
1701        my $count = $erdb->GetCount(['Genome', 'Feature'], 'Genome(genus-species) LIKE ?',
1702                                    ['homo %']);
1703    
1704    it would return the number of genomes, not the number of genome/feature pairs.
1705    
1706    =over 4
1707    
1708    =item objectNames
1709    
1710    Reference to a list of the objects (entities and relationships) included in the
1711    query.
1712    
1713    =item filter
1714    
1715    A filter clause for restricting the query. The rules are the same as for the L</Get>
1716    method.
1717    
1718    =item params
1719    
1720    Reference to a list of the parameter values to be substituted for the parameter marks
1721    in the filter.
1722    
1723    =item RETURN
1724    
1725    Returns a count of the number of records in the first table that would satisfy
1726    the query.
1727    
1728    =back
1729    
1730    =cut
1731    
1732    sub GetCount {
1733        # Get the parameters.
1734        my ($self, $objectNames, $filter, $params) = @_;
1735        # Insure the params argument is an array reference if the caller left it off.
1736        if (! defined($params)) {
1737            $params = [];
1738        }
1739        # Declare the return variable.
1740        my $retVal;
1741        # Find out if we're counting an entity or a relationship.
1742        my $countedField;
1743        if ($self->IsEntity($objectNames->[0])) {
1744            $countedField = "id";
1745        } else {
1746            # For a relationship we count the to-link because it's usually more
1747            # numerous. Note we're automatically converting to the SQL form
1748            # of the field name (to_link vs. to-link).
1749            $countedField = "to_link";
1750        }
1751        # Create the SQL command suffix to get the desired records.
1752        my ($suffix, $mappedNameListRef, $mappedNameHashRef) = $self->_SetupSQL($objectNames,
1753                                                                                $filter);
1754        # Prefix it with text telling it we want a record count.
1755        my $firstObject = $mappedNameListRef->[0];
1756        my $command = "SELECT COUNT($firstObject.$countedField) $suffix";
1757        # Prepare and execute the command.
1758        my $sth = $self->_GetStatementHandle($command, $params);
1759        # Get the count value.
1760        ($retVal) = $sth->fetchrow_array();
1761        # Check for a problem.
1762        if (! defined($retVal)) {
1763            if ($sth->err) {
1764                # Here we had an SQL error.
1765                Confess("Error retrieving row count: " . $sth->errstr());
1766            } else {
1767                # Here we have no result.
1768                Confess("No result attempting to retrieve row count.");
1769            }
1770        }
1771        # Return the result.
1772        return $retVal;
1773    }
1774    
1775  =head3 ComputeObjectSentence  =head3 ComputeObjectSentence
1776    
1777  C<< my $sentence = $database->ComputeObjectSentence($objectName); >>  C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>
1778    
1779  Check an object name, and if it is a relationship convert it to a relationship sentence.  Check an object name, and if it is a relationship convert it to a relationship sentence.
1780    
# Line 1069  Line 1809 
1809    
1810  =head3 DumpRelations  =head3 DumpRelations
1811    
1812  C<< $database->DumpRelations($outputDirectory); >>  C<< $erdb->DumpRelations($outputDirectory); >>
1813    
1814  Write the contents of all the relations to tab-delimited files in the specified directory.  Write the contents of all the relations to tab-delimited files in the specified directory.
1815  Each file will have the same name as the relation dumped, with an extension of DTX.  Each file will have the same name as the relation dumped, with an extension of DTX.
# Line 1109  Line 1849 
1849      }      }
1850  }  }
1851    
1852    =head3 InsertValue
1853    
1854    C<< $erdb->InsertValue($entityID, $fieldName, $value); >>
1855    
1856    This method will insert a new value into the database. The value must be one
1857    associated with a secondary relation, since primary values cannot be inserted:
1858    they occur exactly once. Secondary values, on the other hand, can be missing
1859    or multiply-occurring.
1860    
1861    =over 4
1862    
1863    =item entityID
1864    
1865    ID of the object that is to receive the new value.
1866    
1867    =item fieldName
1868    
1869    Field name for the new value-- this includes the entity name, since
1870    field names are of the format I<objectName>C<(>I<fieldName>C<)>.
1871    
1872    =item value
1873    
1874    New value to be put in the field.
1875    
1876    =back
1877    
1878    =cut
1879    
1880    sub InsertValue {
1881        # Get the parameters.
1882        my ($self, $entityID, $fieldName, $value) = @_;
1883        # Parse the entity name and the real field name.
1884        if ($fieldName =~ /^([^(]+)\(([^)]+)\)/) {
1885            my $entityName = $1;
1886            my $fieldTitle = $2;
1887            # Get its descriptor.
1888            if (!$self->IsEntity($entityName)) {
1889                Confess("$entityName is not a valid entity.");
1890            } else {
1891                my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1892                # Find the relation containing this field.
1893                my $fieldHash = $entityData->{Fields};
1894                if (! exists $fieldHash->{$fieldTitle}) {
1895                    Confess("$fieldTitle not found in $entityName.");
1896                } else {
1897                    my $relation = $fieldHash->{$fieldTitle}->{relation};
1898                    if ($relation eq $entityName) {
1899                        Confess("Cannot do InsertValue on primary field $fieldTitle of $entityName.");
1900                    } else {
1901                        # Now we can create an INSERT statement.
1902                        my $dbh = $self->{_dbh};
1903                        my $fixedName = _FixName($fieldTitle);
1904                        my $statement = "INSERT INTO $relation (id, $fixedName) VALUES(?, ?)";
1905                        # Execute the command.
1906                        $dbh->SQL($statement, 0, $entityID, $value);
1907                    }
1908                }
1909            }
1910        } else {
1911            Confess("$fieldName is not a valid field name.");
1912        }
1913    }
1914    
1915  =head3 InsertObject  =head3 InsertObject
1916    
1917  C<< my $ok = $database->InsertObject($objectType, \%fieldHash); >>  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>
1918    
1919  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
1920  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 1120  Line 1923 
1923  example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases  example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases
1924  C<ZP_00210270.1> and C<gi|46206278>.  C<ZP_00210270.1> and C<gi|46206278>.
1925    
1926  C<< $database->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>  C<< $erdb->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>
1927    
1928  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
1929  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
1930    
1931  C<< $database->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>  C<< $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>
1932    
1933  =over 4  =over 4
1934    
# Line 1250  Line 2053 
2053    
2054  =head3 LoadTable  =head3 LoadTable
2055    
2056  C<< my %results = $database->LoadTable($fileName, $relationName, $truncateFlag); >>  C<< my %results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>
2057    
2058  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
2059  first.  first.
# Line 1271  Line 2074 
2074    
2075  =item RETURN  =item RETURN
2076    
2077  Returns a statistical object containing the number of records read and a list of  Returns a statistical object containing a list of the error messages.
 the error messages.  
2078    
2079  =back  =back
2080    
# Line 1286  Line 2088 
2088      Trace("Loading table $relationName from $fileName") if T(2);      Trace("Loading table $relationName from $fileName") if T(2);
2089      # Get the database handle.      # Get the database handle.
2090      my $dbh = $self->{_dbh};      my $dbh = $self->{_dbh};
2091        # Get the input file size.
2092        my $fileSize = -s $fileName;
2093      # Get the relation data.      # Get the relation data.
2094      my $relation = $self->_FindRelation($relationName);      my $relation = $self->_FindRelation($relationName);
2095      # Check the truncation flag.      # Check the truncation flag.
2096      if ($truncateFlag) {      if ($truncateFlag) {
2097          Trace("Creating table $relationName") if T(2);          Trace("Creating table $relationName") if T(2);
2098            # Compute the row count estimate. We take the size of the load file,
2099            # divide it by the estimated row size, and then multiply by 1.5 to
2100            # leave extra room. We postulate a minimum row count of 1000 to
2101            # prevent problems with incoming empty load files.
2102            my $rowSize = $self->EstimateRowSize($relationName);
2103            my $estimate = FIG::max($fileSize * 1.5 / $rowSize, 1000);
2104          # Re-create the table without its index.          # Re-create the table without its index.
2105          $self->CreateTable($relationName, 0);          $self->CreateTable($relationName, 0, $estimate);
2106          # If this is a pre-index DBMS, create the index here.          # If this is a pre-index DBMS, create the index here.
2107          if ($dbh->{_preIndex}) {          if ($dbh->{_preIndex}) {
2108              eval {              eval {
# Line 1303  Line 2113 
2113              }              }
2114          }          }
2115      }      }
     # Determine whether or not this is a primary relation. Primary relations have an extra  
     # field indicating whether or not a given object is new or was loaded from the flat files.  
     my $primary = $self->_IsPrimary($relationName);  
     # Get the number of fields in this relation.  
     my @fieldList = @{$relation->{Fields}};  
     my $fieldCount = @fieldList;  
     # Start a database transaction.  
     $dbh->begin_tran;  
     # Open the relation file. We need to create a cleaned-up copy before loading.  
     open TABLEIN, '<', $fileName;  
     my $tempName = "$fileName.tbl";  
     open TABLEOUT, '>', $tempName;  
     my $inputCount = 0;  
     # Loop through the file.  
     while (<TABLEIN>) {  
         $inputCount++;  
         # Chop off the new-line character.  
         my $record = Tracer::Strip($_);  
         # Only proceed if the record is non-blank.  
         if ($record) {  
             # Escape all the backslashes found in the line.  
             $record =~ s/\\/\\\\/g;  
             # Insure the number of fields is correct.  
             my @fields = split /\t/, $record;  
             while (@fields > $fieldCount) {  
                 my $extraField = $fields[$#fields];  
                 delete $fields[$#fields];  
                 if ($extraField) {  
                     Trace("Nonblank extra field value \"$extraField\" deleted from record $inputCount of $fileName.") if T(1);  
                 }  
             }  
             while (@fields < $fieldCount) {  
                 push @fields, "";  
             }  
             # If this is a primary relation, add a 0 for the new-record flag (indicating that  
             # this record is not new, but part of the original load).  
             if ($primary) {  
                 push @fields, "0";  
             }  
             # Write the record.  
             $record = join "\t", @fields;  
             print TABLEOUT "$record\n";  
             # Count the record written.  
             my $count = $retVal->Add('records');  
             my $len = length $record;  
             Trace("Record $count written with $len characters.") if T(4);  
         } else {  
             # Here we have a blank record.  
             $retVal->Add('skipped');  
         }  
     }  
     # Close the files.  
     close TABLEIN;  
     close TABLEOUT;  
     Trace("Temporary file $tempName created.") if T(2);  
2116      # Load the table.      # Load the table.
2117      my $rv;      my $rv;
2118      eval {      eval {
2119          $rv = $dbh->load_table(file => $tempName, tbl => $relationName);          $rv = $dbh->load_table(file => $fileName, tbl => $relationName);
2120      };      };
2121      if (!defined $rv) {      if (!defined $rv) {
2122          $retVal->AddMessage($@) if ($@);          $retVal->AddMessage($@) if ($@);
2123          $retVal->AddMessage("Table load failed for $relationName using $tempName.");          $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2124          Trace("Table load failed for $relationName.") if T(1);          Trace("Table load failed for $relationName.") if T(1);
2125      } else {      } else {
2126          # Here we successfully loaded the table. Trace the number of records loaded.          # Here we successfully loaded the table.
2127          Trace("$retVal->{records} records read for $relationName.") if T(2);          $retVal->Add("tables");
2128            my $size = -s $fileName;
2129            Trace("$size bytes loaded into $relationName.") if T(2);
2130          # If we're rebuilding, we need to create the table indexes.          # If we're rebuilding, we need to create the table indexes.
2131          if ($truncateFlag && ! $dbh->{_preIndex}) {          if ($truncateFlag) {
2132                # Indexes are created here for PostGres. For PostGres, indexes are
2133                # best built at the end. For MySQL, the reverse is true.
2134                if (! $dbh->{_preIndex}) {
2135              eval {              eval {
2136                  $self->CreateIndex($relationName);                  $self->CreateIndex($relationName);
2137              };              };
# Line 1379  Line 2139 
2139                  $retVal->AddMessage($@);                  $retVal->AddMessage($@);
2140              }              }
2141          }          }
2142                # The full-text index (if any) is always built last, even for MySQL.
2143                # First we need to see if this table has a full-text index. Only
2144                # primary relations are allowed that privilege.
2145                if ($self->_IsPrimary($relationName)) {
2146                    # Get the relation's entity/relationship structure.
2147                    my $structure = $self->_GetStructure($relationName);
2148                    # Check for a searchable fields list.
2149                    if (exists $structure->{searchFields}) {
2150                        # Here we know that we need to create a full-text search index.
2151                        # Get an SQL-formatted field name list.
2152                        my $fields = join(", ", $self->_FixNames(@{$structure->{searchFields}}));
2153                        # Create the index.
2154                        $dbh->create_index(tbl => $relationName, idx => "search_idx_$relationName",
2155                                           flds => $fields, kind => 'fulltext');
2156                    }
2157                }
2158      }      }
2159      # Commit the database changes.      }
2160      $dbh->commit_tran;      # Analyze the table to improve performance.
2161      # Delete the temporary file.      Trace("Analyzing and compacting $relationName.") if T(3);
2162      unlink $tempName;      $dbh->vacuum_it($relationName);
2163        Trace("$relationName load completed.") if T(3);
2164      # Return the statistics.      # Return the statistics.
2165      return $retVal;      return $retVal;
2166  }  }
2167    
2168  =head3 GenerateEntity  =head3 DropRelation
   
 C<< my $fieldHash = $database->GenerateEntity($id, $type, \%values); >>  
2169    
2170  Generate the data for a new entity instance. This method creates a field hash suitable for  C<< $erdb->DropRelation($relationName); >>
 passing as a parameter to L</InsertObject>. The ID is specified by the callr, but the rest  
 of the fields are generated using information in the database schema.  
2171    
2172  Each data type has a default algorithm for generating random test data. This can be overridden  Physically drop a relation from the database.
 by including a B<DataGen> element in the field. If this happens, the content of the element is  
 executed as a PERL program in the context of this module. The element may make use of a C<$this>  
 variable which contains the field hash as it has been built up to the current point. If any  
 fields are dependent on other fields, the C<pass> attribute can be used to control the order  
 in which the fields are generated. A field with a high data pass number will be generated after  
 a field with a lower one. If any external values are needed, they should be passed in via the  
 optional third parameter, which will be available to the data generation script under the name  
 C<$value>. Several useful utility methods are provided for generating random values, including  
 L</IntGen>, L</StringGen>, L</FloatGen>, and L</DateGen>. Note that dates are stored and generated  
 in the form of a timestamp number rather than a string.  
2173    
2174  =over 4  =over 4
2175    
2176  =item id  =item relationName
2177    
2178  ID to assign to the new entity.  Name of the relation to drop. If it does not exist, this method will have
2179    no effect.
 =item type  
   
 Type name for the new entity.  
   
 =item values  
   
 Hash containing additional values that might be needed by the data generation methods (optional).  
2180    
2181  =back  =back
2182    
2183  =cut  =cut
2184    
2185  sub GenerateEntity {  sub DropRelation {
2186      # Get the parameters.      # Get the parameters.
2187      my ($self, $id, $type, $values) = @_;      my ($self, $relationName) = @_;
2188      # Create the return hash.      # Get the database handle.
2189      my $this = { id => $id };      my $dbh = $self->{_dbh};
2190      # Get the metadata structure.      # Drop the relation. The method used here has no effect if the relation
2191      my $metadata = $self->{_metaData};      # does not exist.
2192      # Get this entity's list of fields.      $dbh->drop_table($relationName);
     if (!exists $metadata->{Entities}->{$type}) {  
         Confess("Unrecognized entity type $type in GenerateEntity.");  
     } else {  
         my $entity = $metadata->{Entities}->{$type};  
         my $fields = $entity->{Fields};  
         # Generate data from the fields.  
         _GenerateFields($this, $fields, $type, $values);  
     }  
     # Return the hash created.  
     return $this;  
2193  }  }
2194    
2195  =head3 GetEntity  =head3 GetEntity
2196    
2197  C<< my $entityObject = $sprout->GetEntity($entityType, $ID); >>  C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>
2198    
2199  Return an object describing the entity instance with a specified ID.  Return an object describing the entity instance with a specified ID.
2200    
# Line 1475  Line 2221 
2221      # Get the parameters.      # Get the parameters.
2222      my ($self, $entityType, $ID) = @_;      my ($self, $entityType, $ID) = @_;
2223      # Create a query.      # Create a query.
2224      my $query = $self->Get([$entityType], "$entityType(id) = ?", $ID);      my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);
2225      # Get the first (and only) object.      # Get the first (and only) object.
2226      my $retVal = $query->Fetch();      my $retVal = $query->Fetch();
2227      # Return the result.      # Return the result.
2228      return $retVal;      return $retVal;
2229  }  }
2230    
2231    =head3 GetChoices
2232    
2233    C<< my @values = $erdb->GetChoices($entityName, $fieldName); >>
2234    
2235    Return a list of all the values for the specified field that are represented in the
2236    specified entity.
2237    
2238    Note that if the field is not indexed, then this will be a very slow operation.
2239    
2240    =over 4
2241    
2242    =item entityName
2243    
2244    Name of an entity in the database.
2245    
2246    =item fieldName
2247    
2248    Name of a field belonging to the entity. This is a raw field name without
2249    the standard parenthesized notation used in most calls.
2250    
2251    =item RETURN
2252    
2253    Returns a list of the distinct values for the specified field in the database.
2254    
2255    =back
2256    
2257    =cut
2258    
2259    sub GetChoices {
2260        # Get the parameters.
2261        my ($self, $entityName, $fieldName) = @_;
2262        # Declare the return variable.
2263        my @retVal;
2264        # Get the entity data structure.
2265        my $entityData = $self->_GetStructure($entityName);
2266        # Get the field.
2267        my $fieldHash = $entityData->{Fields};
2268        if (! exists $fieldHash->{$fieldName}) {
2269            Confess("$fieldName not found in $entityName.");
2270        } else {
2271            # Get the name of the relation containing the field.
2272            my $relation = $fieldHash->{$fieldName}->{relation};
2273            # Fix up the field name.
2274            my $realName = _FixName($fieldName);
2275            # Get the database handle.
2276            my $dbh = $self->{_dbh};
2277            # Query the database.
2278            my $results = $dbh->SQL("SELECT DISTINCT $realName FROM $relation");
2279            # Clean the results. They are stored as a list of lists, and we just want the one list.
2280            @retVal = sort map { $_->[0] } @{$results};
2281        }
2282        # Return the result.
2283        return @retVal;
2284    }
2285    
2286  =head3 GetEntityValues  =head3 GetEntityValues
2287    
2288  C<< my @values = GetEntityValues($entityType, $ID, \@fields); >>  C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>
2289    
2290  Return a list of values from a specified entity instance.  Return a list of values from a specified entity instance. If the entity instance
2291    does not exist, an empty list is returned.
2292    
2293  =over 4  =over 4
2294    
# Line 1527  Line 2329 
2329    
2330  =head3 GetAll  =head3 GetAll
2331    
2332  C<< my @list = $sprout->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>  C<< my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>
2333    
2334  Return a list of values taken from the objects returned by a query. The first three  Return a list of values taken from the objects returned by a query. The first three
2335  parameters correspond to the parameters of the L</Get> method. The final parameter is  parameters correspond to the parameters of the L</Get> method. The final parameter is
# Line 1543  Line 2345 
2345  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
2346  feature ID followed by all of its aliases.  feature ID followed by all of its aliases.
2347    
2348  C<< $query = $sprout->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>  C<< $query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>
2349    
2350  =over 4  =over 4
2351    
# Line 1588  Line 2390 
2390      # list is a scalar we convert it into a singleton list.      # list is a scalar we convert it into a singleton list.
2391      my @parmList = ();      my @parmList = ();
2392      if (ref $parameterList eq "ARRAY") {      if (ref $parameterList eq "ARRAY") {
2393            Trace("GetAll parm list is an array.") if T(4);
2394          @parmList = @{$parameterList};          @parmList = @{$parameterList};
2395      } else {      } else {
2396            Trace("GetAll parm list is a scalar: $parameterList.") if T(4);
2397          push @parmList, $parameterList;          push @parmList, $parameterList;
2398      }      }
     # Create the query.  
     my $query = $self->Get($objectNames, $filterClause, @parmList);  
     # Set up a counter of the number of records read.  
     my $fetched = 0;  
2399      # Insure the counter has a value.      # Insure the counter has a value.
2400      if (!defined $count) {      if (!defined $count) {
2401          $count = 0;          $count = 0;
2402      }      }
2403        # Add the row limit to the filter clause.
2404        if ($count > 0) {
2405            $filterClause .= " LIMIT $count";
2406        }
2407        # Create the query.
2408        my $query = $self->Get($objectNames, $filterClause, \@parmList);
2409        # Set up a counter of the number of records read.
2410        my $fetched = 0;
2411      # Loop through the records returned, extracting the fields. Note that if the      # Loop through the records returned, extracting the fields. Note that if the
2412      # counter is non-zero, we stop when the number of records read hits the count.      # counter is non-zero, we stop when the number of records read hits the count.
2413      my @retVal = ();      my @retVal = ();
# Line 1608  Line 2416 
2416          push @retVal, \@rowData;          push @retVal, \@rowData;
2417          $fetched++;          $fetched++;
2418      }      }
2419        Trace("$fetched rows returned in GetAll.") if T(SQL => 4);
2420      # Return the resulting list.      # Return the resulting list.
2421      return @retVal;      return @retVal;
2422  }  }
2423    
2424  =head2 Internal Utility Methods  =head3 Exists
2425    
2426  =head3 GetLoadStats  C<< my $found = $sprout->Exists($entityName, $entityID); >>
2427    
2428  Return a blank statistics object for use by the load methods.  Return TRUE if an entity exists, else FALSE.
2429    
2430  This is a static method.  =over 4
2431    
2432    =item entityName
2433    
2434    Name of the entity type (e.g. C<Feature>) relevant to the existence check.
2435    
2436    =item entityID
2437    
2438    ID of the entity instance whose existence is to be checked.
2439    
2440    =item RETURN
2441    
2442    Returns TRUE if the entity instance exists, else FALSE.
2443    
2444    =back
2445    
2446  =cut  =cut
2447    #: Return Type $;
2448    sub Exists {
2449        # Get the parameters.
2450        my ($self, $entityName, $entityID) = @_;
2451        # Check for the entity instance.
2452        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
2453        my $testInstance = $self->GetEntity($entityName, $entityID);
2454        # Return an existence indicator.
2455        my $retVal = ($testInstance ? 1 : 0);
2456        return $retVal;
2457    }
2458    
2459  sub _GetLoadStats {  =head3 EstimateRowSize
2460      return Stats->new('records');  
2461    C<< my $rowSize = $erdb->EstimateRowSize($relName); >>
2462    
2463    Estimate the row size of the specified relation. The estimated row size is computed by adding
2464    up the average length for each data type.
2465    
2466    =over 4
2467    
2468    =item relName
2469    
2470    Name of the relation whose estimated row size is desired.
2471    
2472    =item RETURN
2473    
2474    Returns an estimate of the row size for the specified relation.
2475    
2476    =back
2477    
2478    =cut
2479    #: Return Type $;
2480    sub EstimateRowSize {
2481        # Get the parameters.
2482        my ($self, $relName) = @_;
2483        # Declare the return variable.
2484        my $retVal = 0;
2485        # Find the relation descriptor.
2486        my $relation = $self->_FindRelation($relName);
2487        # Get the list of fields.
2488        for my $fieldData (@{$relation->{Fields}}) {
2489            # Get the field type and add its length.
2490            my $fieldLen = $TypeTable{$fieldData->{type}}->{avgLen};
2491            $retVal += $fieldLen;
2492        }
2493        # Return the result.
2494        return $retVal;
2495  }  }
2496    
2497  =head3 GenerateFields  =head3 GetFieldTable
2498    
2499  Generate field values from a field structure and store in a specified table. The field names  C<< my $fieldHash = $self->GetFieldTable($objectnName); >>
 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.  
2500    
2501  This is a static method.  Get the field structure for a specified entity or relationship.
2502    
2503  =over 4  =over 4
2504    
2505  =item this  =item objectName
2506    
2507  Hash table into which the field values should be placed.  Name of the desired entity or relationship.
2508    
2509  =item fields  =item RETURN
2510    
2511  Field structure from which the field descriptors should be taken.  The table containing the field descriptors for the specified object.
2512    
2513  =item type  =back
2514    
2515  Type name of the object whose fields are being generated.  =cut
2516    
2517  =item values (optional)  sub GetFieldTable {
2518        # Get the parameters.
2519        my ($self, $objectName) = @_;
2520        # Get the descriptor from the metadata.
2521        my $objectData = $self->_GetStructure($objectName);
2522        # Return the object's field table.
2523        return $objectData->{Fields};
2524    }
2525    
2526    =head3 SplitKeywords
2527    
2528  Reference to a value structure from which additional values can be taken.  C<< my @keywords = ERDB::SplitKeywords($keywordString); >>
2529    
2530  =item from (optiona)  This method returns a list of the positive keywords in the specified
2531    keyword string. All of the operators will have been stripped off,
2532    and if the keyword is preceded by a minus operator (C<->), it will
2533    not be in the list returned. The idea here is to get a list of the
2534    keywords the user wants to see. The list will be processed to remove
2535    duplicates.
2536    
2537  Reference to the source entity instance if relationship data is being generated.  It is possible to create a string that confuses this method. For example
2538    
2539  =item to (optional)      frog toad -frog
2540    
2541  Reference to the target entity instance if relationship data is being generated.  would return both C<frog> and C<toad>. If this is a problem we can deal
2542    with it later.
2543    
2544    =over 4
2545    
2546    =item keywordString
2547    
2548    The keyword string to be parsed.
2549    
2550    =item RETURN
2551    
2552    Returns a list of the words in the keyword string the user wants to
2553    see.
2554    
2555  =back  =back
2556    
2557  =cut  =cut
2558    
2559  sub _GenerateFields {  sub SplitKeywords {
2560      # Get the parameters.      # Get the parameters.
2561      my ($this, $fields, $type, $values, $from, $to) = @_;      my ($keywordString) = @_;
2562      # Sort the field names by pass number.      # Make a safety copy of the string. (This helps during debugging.)
2563      my @fieldNames = sort { $fields->{$a}->{DataGen}->{pass} <=> $fields->{$b}->{DataGen}->{pass} } keys %{$fields};      my $workString = $keywordString;
2564      # Loop through the field names, generating data.      # Convert operators we don't care about to spaces.
2565      for my $name (@fieldNames) {      $workString =~ tr/+"()<>/ /;
2566          # Only proceed if this field needs to be generated.      # Split the rest of the string along space boundaries. Note that we
2567          if (!exists $this->{$name}) {      # eliminate any words that are zero length or begin with a minus sign.
2568              # Get this field's data generation descriptor.      my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
2569              my $fieldDescriptor = $fields->{$name};      # Use a hash to remove duplicates.
2570              my $data = $fieldDescriptor->{DataGen};      my %words = map { $_ => 1 } @wordList;
2571              # Get the code to generate the field value.      # Return the result.
2572              my $codeString = $data->{content};      return sort keys %words;
2573              # Determine whether or not this field is in the primary relation.  }
2574              if ($fieldDescriptor->{relation} eq $type) {  
2575                  # Here we have a primary relation field. Store the field value as  =head3 ValidateFieldName
2576                  # a scalar.  
2577                  $this->{$name} = eval($codeString);  C<< my $okFlag = ERDB::ValidateFieldName($fieldName); >>
2578    
2579    Return TRUE if the specified field name is valid, else FALSE. Valid field names must
2580    be hyphenated words subject to certain restrictions.
2581    
2582    =over 4
2583    
2584    =item fieldName
2585    
2586    Field name to be validated.
2587    
2588    =item RETURN
2589    
2590    Returns TRUE if the field name is valid, else FALSE.
2591    
2592    =back
2593    
2594    =cut
2595    
2596    sub ValidateFieldName {
2597        # Get the parameters.
2598        my ($fieldName) = @_;
2599        # Declare the return variable. The field name is valid until we hear
2600        # differently.
2601        my $retVal = 1;
2602        # Look for bad stuff in the name.
2603        if ($fieldName =~ /--/) {
2604            # Here we have a doubled minus sign.
2605            Trace("Field name $fieldName has a doubled hyphen.") if T(1);
2606            $retVal = 0;
2607        } elsif ($fieldName !~ /^[A-Za-z]/) {
2608            # Here the field name is missing the initial letter.
2609            Trace("Field name $fieldName does not begin with a letter.") if T(1);
2610            $retVal = 0;
2611              } else {              } else {
2612                  # Here we have a secondary relation field. Create a null list          # Strip out the minus signs. Everything remaining must be a letter
2613                  # and push the desired number of field values onto it.          # or digit.
2614                  my @fieldValues = ();          my $strippedName = $fieldName;
2615                  my $count = IntGen(0,$data->{testCount});          $strippedName =~ s/-//g;
2616                  for (my $i = 0; $i < $count; $i++) {          if ($strippedName !~ /^[A-Za-z0-9]+$/) {
2617                      my $newValue = eval($codeString);              Trace("Field name $fieldName contains illegal characters.") if T(1);
2618                      push @fieldValues, $newValue;              $retVal = 0;
2619                  }                  }
                 # Store the value list in the main hash.  
                 $this->{$name} = \@fieldValues;  
2620              }              }
2621        # Return the result.
2622        return $retVal;
2623    }
2624    
2625    =head3 ReadMetaXML
2626    
2627    C<< my $rawMetaData = ERDB::ReadDBD($fileName); >>
2628    
2629    This method reads a raw database definition XML file and returns it.
2630    Normally, the metadata used by the ERDB system has been processed and
2631    modified to make it easier to load and retrieve the data; however,
2632    this method can be used to get the data in its raw form.
2633    
2634    =over 4
2635    
2636    =item fileName
2637    
2638    Name of the XML file to read.
2639    
2640    =item RETURN
2641    
2642    Returns a hash reference containing the raw XML data from the specified file.
2643    
2644    =back
2645    
2646    =cut
2647    
2648    sub ReadMetaXML {
2649        # Get the parameters.
2650        my ($fileName) = @_;
2651        # Read the XML.
2652        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
2653        Trace("XML metadata loaded from file $fileName.") if T(1);
2654        # Return the result.
2655        return $retVal;
2656    }
2657    
2658    =head3 GetEntityFieldHash
2659    
2660    C<< my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName); >>
2661    
2662    Get the field hash of the named entity in the specified raw XML structure.
2663    The field hash may not exist, in which case we need to create it.
2664    
2665    =over 4
2666    
2667    =item structure
2668    
2669    Raw XML structure defininng the database. This is not the run-time XML used by
2670    an ERDB object, since that has all sorts of optimizations built-in.
2671    
2672    =item entityName
2673    
2674    Name of the entity whose field structure is desired.
2675    
2676    =item RETURN
2677    
2678    Returns the field hash used to define the entity's fields.
2679    
2680    =back
2681    
2682    =cut
2683    
2684    sub GetEntityFieldHash {
2685        # Get the parameters.
2686        my ($structure, $entityName) = @_;
2687        # Get the entity structure.
2688        my $entityData = $structure->{Entities}->{$entityName};
2689        # Look for a field structure.
2690        my $retVal = $entityData->{Fields};
2691        # If it doesn't exist, create it.
2692        if (! defined($retVal)) {
2693            $entityData->{Fields} = {};
2694            $retVal = $entityData->{Fields};
2695        }
2696        # Return the result.
2697        return $retVal;
2698          }          }
2699    
2700    =head3 WriteMetaXML
2701    
2702    C<< ERDB::WriteMetaXML($structure, $fileName); >>
2703    
2704    Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
2705    used to update the database definition. It must be used with care, however, since it
2706    will only work on a raw structure, not on the processed structure created by an ERDB
2707    constructor.
2708    
2709    =over 4
2710    
2711    =item structure
2712    
2713    XML structure to be written to the file.
2714    
2715    =item fileName
2716    
2717    Name of the output file to which the updated XML should be stored.
2718    
2719    =back
2720    
2721    =cut
2722    
2723    sub WriteMetaXML {
2724        # Get the parameters.
2725        my ($structure, $fileName) = @_;
2726        # Compute the output.
2727        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
2728        # Write it to the file.
2729        my $xmlOut = Open(undef, ">$fileName");
2730        print $xmlOut $fileString;
2731      }      }
2732    
2733    
2734    =head3 HTMLNote
2735    
2736    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
2737    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
2738    Except for C<[p]>, all the codes are closed by slash-codes. So, for
2739    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
2740    
2741    C<< my $realHtml = ERDB::HTMLNote($dataString); >>
2742    
2743    =over 4
2744    
2745    =item dataString
2746    
2747    String to convert to HTML.
2748    
2749    =item RETURN
2750    
2751    An HTML string derived from the input string.
2752    
2753    =back
2754    
2755    =cut
2756    
2757    sub HTMLNote {
2758        # Get the parameter.
2759        my ($dataString) = @_;
2760        # HTML-escape the text.
2761        my $retVal = CGI::escapeHTML($dataString);
2762        # Substitute the bulletin board codes.
2763        $retVal =~ s!\[(/?[bi])\]!<$1>!g;
2764        $retVal =~ s!\[p\]!</p><p>!g;
2765        # Return the result.
2766        return $retVal;
2767  }  }
2768    
 =head3 DumpRelation  
2769    
2770  Dump the specified relation's to the specified output file in tab-delimited format.  =head2 Data Mining Methods
2771    
2772    =head3 GetUsefulCrossValues
2773    
2774    C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>
2775    
2776    Return a list of the useful attributes that would be returned by a B<Cross> call
2777    from an entity of the source entity type through the specified relationship. This
2778    means it will return the fields of the target entity type and the intersection data
2779    fields in the relationship. Only primary table fields are returned. In other words,
2780    the field names returned will be for fields where there is always one and only one
2781    value.
2782    
2783    =over 4
2784    
2785    =item sourceEntity
2786    
2787    Name of the entity from which the relationship crossing will start.
2788    
2789    =item relationship
2790    
2791    Name of the relationship being crossed.
2792    
2793    =item RETURN
2794    
2795    Returns a list of field names in Sprout field format (I<objectName>C<(>I<fieldName>C<)>.
2796    
2797    =back
2798    
2799    =cut
2800    #: Return Type @;
2801    sub GetUsefulCrossValues {
2802        # Get the parameters.
2803        my ($self, $sourceEntity, $relationship) = @_;
2804        # Declare the return variable.
2805        my @retVal = ();
2806        # Determine the target entity for the relationship. This is whichever entity is not
2807        # the source entity. So, if the source entity is the FROM, we'll get the name of
2808        # the TO, and vice versa.
2809        my $relStructure = $self->_GetStructure($relationship);
2810        my $targetEntityType = ($relStructure->{from} eq $sourceEntity ? "to" : "from");
2811        my $targetEntity = $relStructure->{$targetEntityType};
2812        # Get the field table for the entity.
2813        my $entityFields = $self->GetFieldTable($targetEntity);
2814        # The field table is a hash. The hash key is the field name. The hash value is a structure.
2815        # For the entity fields, the key aspect of the target structure is that the {relation} value
2816        # must match the entity name.
2817        my @fieldList = map { "$targetEntity($_)" } grep { $entityFields->{$_}->{relation} eq $targetEntity }
2818                            keys %{$entityFields};
2819        # Push the fields found onto the return variable.
2820        push @retVal, sort @fieldList;
2821        # Get the field table for the relationship.
2822        my $relationshipFields = $self->GetFieldTable($relationship);
2823        # Here we have a different rule. We want all the fields other than "from-link" and "to-link".
2824        # This may end up being an empty set.
2825        my @fieldList2 = map { "$relationship($_)" } grep { $_ ne "from-link" && $_ ne "to-link" }
2826                            keys %{$relationshipFields};
2827        # Push these onto the return list.
2828        push @retVal, sort @fieldList2;
2829        # Return the result.
2830        return @retVal;
2831    }
2832    
2833    =head3 FindColumn
2834    
2835    C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>
2836    
2837    Return the location a desired column in a data mining header line. The data
2838    mining header line is a tab-separated list of column names. The column
2839    identifier is either the numerical index of a column or the actual column
2840    name.
2841    
2842    =over 4
2843    
2844    =item headerLine
2845    
2846    The header line from a data mining command, which consists of a tab-separated
2847    list of column names.
2848    
2849    =item columnIdentifier
2850    
2851    Either the ordinal number of the desired column (1-based), or the name of the
2852    desired column.
2853    
2854    =item RETURN
2855    
2856    Returns the array index (0-based) of the desired column.
2857    
2858    =back
2859    
2860    =cut
2861    
2862    sub FindColumn {
2863        # Get the parameters.
2864        my ($headerLine, $columnIdentifier) = @_;
2865        # Declare the return variable.
2866        my $retVal;
2867        # Split the header line into column names.
2868        my @headers = ParseColumns($headerLine);
2869        # Determine whether we have a number or a name.
2870        if ($columnIdentifier =~ /^\d+$/) {
2871            # Here we have a number. Subtract 1 and validate the result.
2872            $retVal = $columnIdentifier - 1;
2873            if ($retVal < 0 || $retVal > $#headers) {
2874                Confess("Invalid column identifer \"$columnIdentifier\": value out of range.");
2875            }
2876        } else {
2877            # Here we have a name. We need to find it in the list.
2878            for (my $i = 0; $i <= $#headers && ! defined($retVal); $i++) {
2879                if ($headers[$i] eq $columnIdentifier) {
2880                    $retVal = $i;
2881                }
2882            }
2883            if (! defined($retVal)) {
2884                Confess("Invalid column identifier \"$columnIdentifier\": value not found.");
2885            }
2886        }
2887        # Return the result.
2888        return $retVal;
2889    }
2890    
2891    =head3 ParseColumns
2892    
2893    C<< my @columns = ERDB::ParseColumns($line); >>
2894    
2895    Convert the specified data line to a list of columns.
2896    
2897    =over 4
2898    
2899    =item line
2900    
2901    A data mining input, consisting of a tab-separated list of columns terminated by a
2902    new-line.
2903    
2904    =item RETURN
2905    
2906    Returns a list consisting of the column values.
2907    
2908    =back
2909    
2910    =cut
2911    
2912    sub ParseColumns {
2913        # Get the parameters.
2914        my ($line) = @_;
2915        # Chop off the line-end.
2916        chomp $line;
2917        # Split it into a list.
2918        my @retVal = split(/\t/, $line);
2919        # Return the result.
2920        return @retVal;
2921    }
2922    
2923    =head2 Virtual Methods
2924    
2925    =head3 CleanKeywords
2926    
2927    C<< my $cleanedString = $erdb->CleanKeywords($searchExpression); >>
2928    
2929    Clean up a search expression or keyword list. This is a virtual method that may
2930    be overridden by the subclass. The base-class method removes extra spaces
2931    and converts everything to lower case.
2932    
2933    =over 4
2934    
2935    =item searchExpression
2936    
2937    Search expression or keyword list to clean. Note that a search expression may
2938    contain boolean operators which need to be preserved. This includes leading
2939    minus signs.
2940    
2941    =item RETURN
2942    
2943    Cleaned expression or keyword list.
2944    
2945    =back
2946    
2947    =cut
2948    
2949    sub CleanKeywords {
2950        # Get the parameters.
2951        my ($self, $searchExpression) = @_;
2952        # Lower-case the expression and copy it into the return variable. Note that we insure we
2953        # don't accidentally end up with an undefined value.
2954        my $retVal = lc($searchExpression || "");
2955        # Remove extra spaces.
2956        $retVal =~ s/\s+/ /g;
2957        $retVal =~ s/(^\s+)|(\s+$)//g;
2958        # Return the result.
2959        return $retVal;
2960    }
2961    
2962    =head3 GetSourceObject
2963    
2964    C<< my $source = $erdb->GetSourceObject($entityName); >>
2965    
2966    Return the object to be used in loading special attributes of the specified entity. The
2967    algorithm for loading special attributes is stored in the C<DataGen> elements of the
2968    XML
2969    
2970    =head2 Internal Utility Methods
2971    
2972    =head3 _RelationMap
2973    
2974    C<< my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef); >>
2975    
2976    Create the relation map for an SQL query. The relation map is used by B<DBObject>
2977    to determine how to interpret the results of the query.
2978    
2979    =over 4
2980    
2981    =item mappedNameHashRef
2982    
2983    Reference to a hash that maps modified object names to real object names.
2984    
2985    =item mappedNameListRef
2986    
2987    Reference to a list of modified object names in the order they appear in the
2988    SELECT list.
2989    
2990    =item RETURN
2991    
2992    Returns a list of 2-tuples. Each tuple consists of an object name as used in the
2993    query followed by the actual name of that object. This enables the B<DBObject> to
2994    determine the order of the tables in the query and which object name belongs to each
2995    mapped object name. Most of the time these two values are the same; however, if a
2996    relation occurs twice in the query, the relation name in the field list and WHERE
2997    clause will use a mapped name (generally the actual relation name with a numeric
2998    suffix) that does not match the actual relation name.
2999    
3000    =back
3001    
3002    =cut
3003    
3004    sub _RelationMap {
3005        # Get the parameters.
3006        my ($mappedNameHashRef, $mappedNameListRef) = @_;
3007        # Declare the return variable.
3008        my @retVal = ();
3009        # Build the map.
3010        for my $mappedName (@{$mappedNameListRef}) {
3011            push @retVal, [$mappedName, $mappedNameHashRef->{$mappedName}];
3012        }
3013        # Return it.
3014        return @retVal;
3015    }
3016    
3017    
3018    =head3 _SetupSQL
3019    
3020    Process a list of object names and a filter clause so that they can be used to
3021    build an SQL statement. This method takes in a reference to a list of object names
3022    and a filter clause. It will return a corrected filter clause, a list of mapped
3023    names and the mapped name hash.
3024    
3025    This is an instance method.
3026    
3027    =over 4
3028    
3029    =item objectNames
3030    
3031    Reference to a list of the object names to be included in the query.
3032    
3033    =item filterClause
3034    
3035    A string containing the WHERE clause for the query (without the C<WHERE>) and also
3036    optionally the C<ORDER BY> and C<LIMIT> clauses.
3037    
3038    =item matchClause
3039    
3040    An optional full-text search clause. If specified, it will be inserted at the
3041    front of the WHERE clause. It should already be SQL-formatted; that is, the
3042    field names should be in the form I<table>C<.>I<fieldName>.
3043    
3044    =item RETURN
3045    
3046    Returns a three-element list. The first element is the SQL statement suffix, beginning
3047    with the FROM clause. The second element is a reference to a list of the names to be
3048    used in retrieving the fields. The third element is a hash mapping the names to the
3049    objects they represent.
3050    
3051    =back
3052    
3053    =cut
3054    
3055    sub _SetupSQL {
3056        my ($self, $objectNames, $filterClause, $matchClause) = @_;
3057        # Adjust the list of object names to account for multiple occurrences of the
3058        # same object. We start with a hash table keyed on object name that will
3059        # return the object suffix. The first time an object is encountered it will
3060        # not be found in the hash. The next time the hash will map the object name
3061        # to 2, then 3, and so forth.
3062        my %objectHash = ();
3063        # This list will contain the object names as they are to appear in the
3064        # FROM list.
3065        my @fromList = ();
3066        # This list contains the suffixed object name for each object. It is exactly
3067        # parallel to the list in the $objectNames parameter.
3068        my @mappedNameList = ();
3069        # Finally, this hash translates from a mapped name to its original object name.
3070        my %mappedNameHash = ();
3071        # Now we create the lists. Note that for every single name we push something into
3072        # @fromList and @mappedNameList. This insures that those two arrays are exactly
3073        # parallel to $objectNames.
3074        for my $objectName (@{$objectNames}) {
3075            # Get the next suffix for this object.
3076            my $suffix = $objectHash{$objectName};
3077            if (! $suffix) {
3078                # Here we are seeing the object for the first time. The object name
3079                # is used as is.
3080                push @mappedNameList, $objectName;
3081                push @fromList, $objectName;
3082                $mappedNameHash{$objectName} = $objectName;
3083                # Denote the next suffix will be 2.
3084                $objectHash{$objectName} = 2;
3085            } else {
3086                # Here we've seen the object before. We construct a new name using
3087                # the suffix from the hash and update the hash.
3088                my $mappedName = "$objectName$suffix";
3089                $objectHash{$objectName} = $suffix + 1;
3090                # The FROM list has the object name followed by the mapped name. This
3091                # tells SQL it's still the same table, but we're using a different name
3092                # for it to avoid confusion.
3093                push @fromList, "$objectName $mappedName";
3094                # The mapped-name list contains the real mapped name.
3095                push @mappedNameList, $mappedName;
3096                # Finally, enable us to get back from the mapped name to the object name.
3097                $mappedNameHash{$mappedName} = $objectName;
3098            }
3099        }
3100        # Begin the SELECT suffix. It starts with
3101        #
3102        # FROM name1, name2, ... nameN
3103        #
3104        my $suffix = "FROM " . join(', ', @fromList);
3105        # Now for the WHERE. First, we need a place for the filter string.
3106        my $filterString = "";
3107        # We will also keep a list of conditions to add to the WHERE clause in order to link
3108        # entities and relationships as well as primary relations to secondary ones.
3109        my @joinWhere = ();
3110        # Check for a filter clause.
3111        if ($filterClause) {
3112            # Here we have one, so we convert its field names and add it to the query. First,
3113            # We create a copy of the filter string we can work with.
3114            $filterString = $filterClause;
3115            # Next, we sort the object names by length. This helps protect us from finding
3116            # object names inside other object names when we're doing our search and replace.
3117            my @sortedNames = sort { length($b) - length($a) } @mappedNameList;
3118            # The final preparatory step is to create a hash table of relation names. The
3119            # table begins with the relation names already in the SELECT command. We may
3120            # need to add relations later if there is filtering on a field in a secondary
3121            # relation. The secondary relations are the ones that contain multiply-
3122            # occurring or optional fields.
3123            my %fromNames = map { $_ => 1 } @sortedNames;
3124            # We are ready to begin. We loop through the object names, replacing each
3125            # object name's field references by the corresponding SQL field reference.
3126            # Along the way, if we find a secondary relation, we will need to add it
3127            # to the FROM clause.
3128            for my $mappedName (@sortedNames) {
3129                # Get the length of the object name plus 2. This is the value we add to the
3130                # size of the field name to determine the size of the field reference as a
3131                # whole.
3132                my $nameLength = 2 + length $mappedName;
3133                # Get the real object name for this mapped name.
3134                my $objectName = $mappedNameHash{$mappedName};
3135                Trace("Processing $mappedName for object $objectName.") if T(4);
3136                # Get the object's field list.
3137                my $fieldList = $self->GetFieldTable($objectName);
3138                # Find the field references for this object.
3139                while ($filterString =~ m/$mappedName\(([^)]*)\)/g) {
3140                    # At this point, $1 contains the field name, and the current position
3141                    # is set immediately after the final parenthesis. We pull out the name of
3142                    # the field and the position and length of the field reference as a whole.
3143                    my $fieldName = $1;
3144                    my $len = $nameLength + length $fieldName;
3145                    my $pos = pos($filterString) - $len;
3146                    # Insure the field exists.
3147                    if (!exists $fieldList->{$fieldName}) {
3148                        Confess("Field $fieldName not found for object $objectName.");
3149                    } else {
3150                        Trace("Processing $fieldName at position $pos.") if T(4);
3151                        # Get the field's relation.
3152                        my $relationName = $fieldList->{$fieldName}->{relation};
3153                        # Now we have a secondary relation. We need to insure it matches the
3154                        # mapped name of the primary relation. First we peel off the suffix
3155                        # from the mapped name.
3156                        my $mappingSuffix = substr $mappedName, length($objectName);
3157                        # Put the mapping suffix onto the relation name to get the
3158                        # mapped relation name.
3159                        my $mappedRelationName = "$relationName$mappingSuffix";
3160                        # Insure the relation is in the FROM clause.
3161                        if (!exists $fromNames{$mappedRelationName}) {
3162                            # Add the relation to the FROM clause.
3163                            if ($mappedRelationName eq $relationName) {
3164                                # The name is un-mapped, so we add it without
3165                                # any frills.
3166                                $suffix .= ", $relationName";
3167                                push @joinWhere, "$objectName.id = $relationName.id";
3168                            } else {
3169                                # Here we have a mapping situation.
3170                                $suffix .= ", $relationName $mappedRelationName";
3171                                push @joinWhere, "$mappedRelationName.id = $mappedName.id";
3172                            }
3173                            # Denote we have this relation available for future fields.
3174                            $fromNames{$mappedRelationName} = 1;
3175                        }
3176                        # Form an SQL field reference from the relation name and the field name.
3177                        my $sqlReference = "$mappedRelationName." . _FixName($fieldName);
3178                        # Put it into the filter string in place of the old value.
3179                        substr($filterString, $pos, $len) = $sqlReference;
3180                        # Reposition the search.
3181                        pos $filterString = $pos + length $sqlReference;
3182                    }
3183                }
3184            }
3185        }
3186        # The next step is to join the objects together. We only need to do this if there
3187        # is more than one object in the object list. We start with the first object and
3188        # run through the objects after it. Note also that we make a safety copy of the
3189        # list before running through it, because we shift off the first object before
3190        # processing the rest.
3191        my @mappedObjectList = @mappedNameList;
3192        my $lastMappedObject = shift @mappedObjectList;
3193        # Get the join table.
3194        my $joinTable = $self->{_metaData}->{Joins};
3195        # Loop through the object list.
3196        for my $thisMappedObject (@mappedObjectList) {
3197            # Look for a join using the real object names.
3198            my $lastObject = $mappedNameHash{$lastMappedObject};
3199            my $thisObject = $mappedNameHash{$thisMappedObject};
3200            my $joinKey = "$lastObject/$thisObject";
3201            if (!exists $joinTable->{$joinKey}) {
3202                # Here there's no join, so we throw an error.
3203                Confess("No join exists to connect from $lastMappedObject to $thisMappedObject.");
3204            } else {
3205                # Get the join clause.
3206                my $unMappedJoin = $joinTable->{$joinKey};
3207                # Fix the names.
3208                $unMappedJoin =~ s/$lastObject/$lastMappedObject/;
3209                $unMappedJoin =~ s/$thisObject/$thisMappedObject/;
3210                push @joinWhere, $unMappedJoin;
3211                # Save this object as the last object for the next iteration.
3212                $lastMappedObject = $thisMappedObject;
3213            }
3214        }
3215        # Now we need to handle the whole ORDER BY / LIMIT thing. The important part
3216        # here is we want the filter clause to be empty if there's no WHERE filter.
3217        # We'll put the ORDER BY / LIMIT clauses in the following variable.
3218        my $orderClause = "";
3219        # This is only necessary if we have a filter string in which the ORDER BY
3220        # and LIMIT clauses can live.
3221        if ($filterString) {
3222            # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy
3223            # operator so that we find the first occurrence of either verb.
3224            if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {
3225                # Here we have an ORDER BY or LIMIT verb. Split it off of the filter string.
3226                my $pos = pos $filterString;
3227                $orderClause = $2 . substr($filterString, $pos);
3228                $filterString = $1;
3229            }
3230        }
3231        # All the things that are supposed to be in the WHERE clause of the
3232        # SELECT command need to be put into @joinWhere so we can string them
3233        # together. We begin with the match clause. This is important,
3234        # because the match clause's parameter mark must precede any parameter
3235        # marks in the filter string.
3236        if ($matchClause) {
3237            push @joinWhere, $matchClause;
3238        }
3239        # Add the filter string. We put it in parentheses to avoid operator
3240        # precedence problems with the match clause or the joins.
3241        if ($filterString) {
3242            Trace("Filter string is \"$filterString\".") if T(4);
3243            push @joinWhere, "($filterString)";
3244        }
3245        # String it all together into a big filter clause.
3246        if (@joinWhere) {
3247            $suffix .= " WHERE " . join(' AND ', @joinWhere);
3248        }
3249        # Add the sort or limit clause (if any).
3250        if ($orderClause) {
3251            $suffix .= " $orderClause";
3252        }
3253        # Return the suffix, the mapped name list, and the mapped name hash.
3254        return ($suffix, \@mappedNameList, \%mappedNameHash);
3255    }
3256    
3257    =head3 _GetStatementHandle
3258    
3259    This method will prepare and execute an SQL query, returning the statement handle.
3260    The main reason for doing this here is so that everybody who does SQL queries gets
3261    the benefit of tracing.
3262    
3263    This is an instance method.
3264    
3265    =over 4
3266    
3267    =item command
3268    
3269    Command to prepare and execute.
3270    
3271    =item params
3272    
3273    Reference to a list of the values to be substituted in for the parameter marks.
3274    
3275    =item RETURN
3276    
3277    Returns a prepared and executed statement handle from which the caller can extract
3278    results.
3279    
3280    =back
3281    
3282    =cut
3283    
3284    sub _GetStatementHandle {
3285        # Get the parameters.
3286        my ($self, $command, $params) = @_;
3287        # Trace the query.
3288        Trace("SQL query: $command") if T(SQL => 3);
3289        Trace("PARMS: '" . (join "', '", @{$params}) . "'") if (T(SQL => 4) && (@{$params} > 0));
3290        # Get the database handle.
3291        my $dbh = $self->{_dbh};
3292        # Prepare the command.
3293        my $sth = $dbh->prepare_command($command);
3294        # Execute it with the parameters bound in.
3295        $sth->execute(@{$params}) || Confess("SELECT error" . $sth->errstr());
3296        # Return the statement handle.
3297        return $sth;
3298    }
3299    
3300    =head3 _GetLoadStats
3301    
3302    Return a blank statistics object for use by the load methods.
3303    
3304    This is a static method.
3305    
3306    =cut
3307    
3308    sub _GetLoadStats{
3309        return Stats->new();
3310    }
3311    
3312    =head3 _DumpRelation
3313    
3314    Dump the specified relation to the specified output file in tab-delimited format.
3315    
3316  This is an instance method.  This is an instance method.
3317    
# Line 1750  Line 3359 
3359      close DTXOUT;      close DTXOUT;
3360  }  }
3361    
3362  =head3 GetStructure  =head3 _GetStructure
3363    
3364  Get the data structure for a specified entity or relationship.  Get the data structure for a specified entity or relationship.
3365    
# Line 1789  Line 3398 
3398      return $retVal;      return $retVal;
3399  }  }
3400    
3401  =head3 GetRelationTable  
3402    
3403    =head3 _GetRelationTable
3404    
3405  Get the list of relations for a specified entity or relationship.  Get the list of relations for a specified entity or relationship.
3406    
# Line 1818  Line 3429 
3429      return $objectData->{Relations};      return $objectData->{Relations};
3430  }  }
3431    
3432  =head3 GetFieldTable  =head3 _ValidateFieldNames
   
 Get the field structure for a specified entity or relationship.  
   
 This is an instance method.  
   
 =over 4  
   
 =item objectName  
   
 Name of the desired entity or relationship.  
   
 =item RETURN  
   
 The table containing the field descriptors for the specified object.  
   
 =back  
   
 =cut  
   
 sub _GetFieldTable {  
     # Get the parameters.  
     my ($self, $objectName) = @_;  
     # Get the descriptor from the metadata.  
     my $objectData = $self->_GetStructure($objectName);  
     # Return the object's field table.  
     return $objectData->{Fields};  
 }  
   
 =head3 ValidateFieldNames  
3433    
3434  Determine whether or not the field names are valid. A description of the problems with the names  Determine whether or not the field names are valid. A description of the problems with the names
3435  will be written to the standard error output. If there is an error, this method will abort. This is  will be written to the standard error output. If there is an error, this method will abort. This is
# Line 1874  Line 3456 
3456          for my $object (values %{$metadata->{$section}}) {          for my $object (values %{$metadata->{$section}}) {
3457              # Loop through the object's fields.              # Loop through the object's fields.
3458              for my $fieldName (keys %{$object->{Fields}}) {              for my $fieldName (keys %{$object->{Fields}}) {
3459                  # Now we make some initial validations.                  # If this field name is invalid, set the return value to zero
3460                  if ($fieldName =~ /--/) {                  # so we know we encountered an error.
3461                      # Here we have a doubled minus sign.                  if (! ValidateFieldName($fieldName)) {
                     print STDERR "Field name $fieldName has a doubled hyphen.\n";  
                     $retVal = 0;  
                 } elsif ($fieldName !~ /^[A-Za-z]/) {  
                     # Here the field name is missing the initial letter.  
                     print STDERR "Field name $fieldName does not begin with a letter.\n";  
                     $retVal = 0;  
                 } else {  
                     # Strip out the minus signs. Everything remaining must be a letter  
                     # or digit.  
                     my $strippedName = $fieldName;  
                     $strippedName =~ s/-//g;  
                     if ($strippedName !~ /^[A-Za-z0-9]+$/) {  
                         print STDERR "Field name $fieldName contains illegal characters.\n";  
3462                          $retVal = 0;                          $retVal = 0;
3463                      }                      }
3464                  }                  }
3465              }              }
3466          }          }
     }  
3467      # If an error was found, fail.      # If an error was found, fail.
3468      if ($retVal  == 0) {      if ($retVal  == 0) {
3469          Confess("Errors found in field names.");          Confess("Errors found in field names.");
3470      }      }
3471  }  }
3472    
3473  =head3 LoadRelation  =head3 _LoadRelation
3474    
3475  Load a relation from the data in a tab-delimited disk file. The load will only take place if a disk  Load a relation from the data in a tab-delimited disk file. The load will only take place if a disk
3476  file with the same name as the relation exists in the specified directory.  file with the same name as the relation exists in the specified directory.
# Line 1962  Line 3530 
3530      return $retVal;      return $retVal;
3531  }  }
3532    
3533  =head3 LoadMetaData  
3534    =head3 _LoadMetaData
3535    
3536  This method loads the data describing this database from an XML file into a metadata structure.  This method loads the data describing this database from an XML file into a metadata structure.
3537  The resulting structure is a set of nested hash tables containing all the information needed to  The resulting structure is a set of nested hash tables containing all the information needed to
# Line 1987  Line 3556 
3556  sub _LoadMetaData {  sub _LoadMetaData {
3557      # Get the parameters.      # Get the parameters.
3558      my ($filename) = @_;      my ($filename) = @_;
3559        Trace("Reading Sprout DBD from $filename.") if T(2);
3560      # Slurp the XML file into a variable. Extensive use of options is used to insure we      # Slurp the XML file into a variable. Extensive use of options is used to insure we
3561      # get the exact structure we want.      # get the exact structure we want.
3562      my $metadata = XML::Simple::XMLin($filename,      my $metadata = ReadMetaXML($filename);
                                       GroupTags => { Relationships => 'Relationship',  
                                                      Entities => 'Entity',  
                                                      Fields => 'Field',  
                                                      Indexes => 'Index',  
                                                      IndexFields => 'IndexField'},  
                                       KeyAttr => { Relationship => 'name',  
                                                    Entity => 'name',  
                                                    Field => 'name'},  
                                       ForceArray => ['Field', 'Index', 'IndexField'],  
                                       ForceContent => 1,  
                                       NormalizeSpace => 2  
                                       );  
     Trace("XML metadata loaded from file $filename.") if T(1);  
3563      # Before we go any farther, we need to validate the field and object names. If an error is found,      # Before we go any farther, we need to validate the field and object names. If an error is found,
3564      # the method below will fail.      # the method below will fail.
3565      _ValidateFieldNames($metadata);      _ValidateFieldNames($metadata);
# Line 2014  Line 3571 
3571      for my $entityName (keys %{$entityList}) {      for my $entityName (keys %{$entityList}) {
3572          my $entityStructure = $entityList->{$entityName};          my $entityStructure = $entityList->{$entityName};
3573          #          #
3574          # The first step is to run creating all the entity's default values. For C<Field> elements,          # The first step is to create all the entity's default values. For C<Field> elements,
3575          # the relation name must be added where it is not specified. For relationships,          # the relation name must be added where it is not specified. For relationships,
3576          # the B<from-link> and B<to-link> fields must be inserted, and for entities an B<id>          # the B<from-link> and B<to-link> fields must be inserted, and for entities an B<id>
3577          # field must be added to each relation. Finally, each field will have a C<PrettySort> attribute          # field must be added to each relation. Finally, each field will have a C<PrettySort> attribute
# Line 2193  Line 3750 
3750          my @fromList = ();          my @fromList = ();
3751          my @toList = ();          my @toList = ();
3752          my @bothList = ();          my @bothList = ();
3753          Trace("Join table build for $entityName.") if T(3);          Trace("Join table build for $entityName.") if T(metadata => 4);
3754          for my $relationshipName (keys %{$relationshipList}) {          for my $relationshipName (keys %{$relationshipList}) {
3755              my $relationship = $relationshipList->{$relationshipName};              my $relationship = $relationshipList->{$relationshipName};
3756              # Determine if this relationship has our entity in one of its link fields.              # Determine if this relationship has our entity in one of its link fields.
3757              my $fromEntity = $relationship->{from};              my $fromEntity = $relationship->{from};
3758              my $toEntity = $relationship->{to};              my $toEntity = $relationship->{to};
3759              Trace("Join check for relationship $relationshipName from $fromEntity to $toEntity.") if T(3);              Trace("Join check for relationship $relationshipName from $fromEntity to $toEntity.") if T(Joins => 4);
3760              if ($fromEntity eq $entityName) {              if ($fromEntity eq $entityName) {
3761                  if ($toEntity eq $entityName) {                  if ($toEntity eq $entityName) {
3762                      # Here the relationship is recursive.                      # Here the relationship is recursive.
3763                      push @bothList, $relationshipName;                      push @bothList, $relationshipName;
3764                      Trace("Relationship $relationshipName put in both-list.") if T(3);                      Trace("Relationship $relationshipName put in both-list.") if T(metadata => 4);
3765                  } else {                  } else {
3766                      # Here the relationship comes from the entity.                      # Here the relationship comes from the entity.
3767                      push @fromList, $relationshipName;                      push @fromList, $relationshipName;
3768                      Trace("Relationship $relationshipName put in from-list.") if T(3);                      Trace("Relationship $relationshipName put in from-list.") if T(metadata => 4);
3769                  }                  }
3770              } elsif ($toEntity eq $entityName) {              } elsif ($toEntity eq $entityName) {
3771                  # Here the relationship goes to the entity.                  # Here the relationship goes to the entity.
3772                  push @toList, $relationshipName;                  push @toList, $relationshipName;
3773                  Trace("Relationship $relationshipName put in to-list.") if T(3);                  Trace("Relationship $relationshipName put in to-list.") if T(metadata => 4);
3774              }              }
3775          }          }
3776          # Create the nonrecursive joins. Note that we build two hashes for running          # Create the nonrecursive joins. Note that we build two hashes for running
# Line 2229  Line 3786 
3786                  # Create joins between the entity and this relationship.                  # Create joins between the entity and this relationship.
3787                  my $linkField = "$relationshipName.${linkType}_link";                  my $linkField = "$relationshipName.${linkType}_link";
3788                  my $joinClause = "$entityName.id = $linkField";                  my $joinClause = "$entityName.id = $linkField";
3789                  Trace("Entity join clause is $joinClause for $entityName and $relationshipName.") if T(4);                  Trace("Entity join clause is $joinClause for $entityName and $relationshipName.") if T(metadata => 4);
3790                  $joinTable{"$entityName/$relationshipName"} = $joinClause;                  $joinTable{"$entityName/$relationshipName"} = $joinClause;
3791                  $joinTable{"$relationshipName/$entityName"} = $joinClause;                  $joinTable{"$relationshipName/$entityName"} = $joinClause;
3792                  # Create joins between this relationship and the other relationships.                  # Create joins between this relationship and the other relationships.
# Line 2250  Line 3807 
3807                              # relationship and itself are prohibited.                              # relationship and itself are prohibited.
3808                              my $relJoinClause = "$otherName.${otherType}_link = $linkField";                              my $relJoinClause = "$otherName.${otherType}_link = $linkField";
3809                              $joinTable{$joinKey} = $relJoinClause;                              $joinTable{$joinKey} = $relJoinClause;
3810                              Trace("Relationship join clause is $relJoinClause for $joinKey.") if T(4);                              Trace("Relationship join clause is $relJoinClause for $joinKey.") if T(metadata => 4);
3811                          }                          }
3812                      }                      }
3813                  }                  }
# Line 2259  Line 3816 
3816                  # relationship can only be ambiguous with another recursive relationship,                  # relationship can only be ambiguous with another recursive relationship,
3817                  # and the incoming relationship from the outer loop is never recursive.                  # and the incoming relationship from the outer loop is never recursive.
3818                  for my $otherName (@bothList) {                  for my $otherName (@bothList) {
3819                      Trace("Setting up relationship joins to recursive relationship $otherName with $relationshipName.") if T(3);                      Trace("Setting up relationship joins to recursive relationship $otherName with $relationshipName.") if T(metadata => 4);
3820                      # Join from the left.                      # Join from the left.
3821                      $joinTable{"$relationshipName/$otherName"} =                      $joinTable{"$relationshipName/$otherName"} =
3822                          "$linkField = $otherName.from_link";                          "$linkField = $otherName.from_link";
# Line 2274  Line 3831 
3831          # rise to situations where we can't create the path we want; however, it is always          # rise to situations where we can't create the path we want; however, it is always
3832          # possible to get the same effect using multiple queries.          # possible to get the same effect using multiple queries.
3833          for my $relationshipName (@bothList) {          for my $relationshipName (@bothList) {
3834              Trace("Setting up entity joins to recursive relationship $relationshipName with $entityName.") if T(3);              Trace("Setting up entity joins to recursive relationship $relationshipName with $entityName.") if T(metadata => 4);
3835              # Join to the entity from each direction.              # Join to the entity from each direction.
3836              $joinTable{"$entityName/$relationshipName"} =              $joinTable{"$entityName/$relationshipName"} =
3837                  "$entityName.id = $relationshipName.from_link";                  "$entityName.id = $relationshipName.from_link";
# Line 2288  Line 3845 
3845      return $metadata;      return $metadata;
3846  }  }
3847    
3848  =head3 CreateRelationshipIndex  =head3 _CreateRelationshipIndex
3849    
3850  Create an index for a relationship's relation.  Create an index for a relationship's relation.
3851    
# Line 2325  Line 3882 
3882      # index descriptor does not exist, it will be created automatically so we can add      # index descriptor does not exist, it will be created automatically so we can add
3883      # the field to it.      # the field to it.
3884      unshift @{$newIndex->{IndexFields}}, $firstField;      unshift @{$newIndex->{IndexFields}}, $firstField;
3885        # If this is a one-to-many relationship, the "To" index is unique.
3886        if ($relationshipStructure->{arity} eq "1M" && $indexKey eq "To") {
3887            $newIndex->{Unique} = 'true';
3888        }
3889      # Add the index to the relation.      # Add the index to the relation.
3890      _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);      _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);
3891  }  }
3892    
3893  =head3 AddIndex  =head3 _AddIndex
3894    
3895  Add an index to a relation structure.  Add an index to a relation structure.
3896    
# Line 2375  Line 3936 
3936      $relationStructure->{Indexes}->{$indexName} = $newIndex;      $relationStructure->{Indexes}->{$indexName} = $newIndex;
3937  }  }
3938    
3939  =head3 FixupFields  =head3 _FixupFields
3940    
3941  This method fixes the field list for an entity or relationship. It will add the caller-specified  This method fixes the field list for an entity or relationship. It will add the caller-specified
3942  relation name to fields that do not have a name and set the C<PrettySort> value as specified.  relation name to fields that do not have a name and set the C<PrettySort> value as specified.
# Line 2413  Line 3974 
3974          # Here it doesn't, so we create a new one.          # Here it doesn't, so we create a new one.
3975          $structure->{Fields} = { };          $structure->{Fields} = { };
3976      } else {      } else {
3977          # Here we have a field list. Loop through its fields.          # Here we have a field list. We need to track the searchable fields, so we
3978            # create a list for stashing them.
3979            my @textFields = ();
3980            # Loop through the fields.
3981          my $fieldStructures = $structure->{Fields};          my $fieldStructures = $structure->{Fields};
3982          for my $fieldName (keys %{$fieldStructures}) {          for my $fieldName (keys %{$fieldStructures}) {
3983              Trace("Processing field $fieldName of $defaultRelationName.") if T(4);              Trace("Processing field $fieldName of $defaultRelationName.") if T(4);
# Line 2422  Line 3986 
3986              my $type = $fieldData->{type};              my $type = $fieldData->{type};
3987              # Plug in a relation name if it is needed.              # Plug in a relation name if it is needed.
3988              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });
3989              # Plug in a data generator if we need one.              # Check for searchability.
3990              if (!exists $fieldData->{DataGen}) {              if ($fieldData->{searchable}) {
3991                  # The data generator will use the default for the field's type.                  # Only allow this for a primary relation.
3992                  $fieldData->{DataGen} = { content => $TypeTable{$type}->{dataGen} };                  if ($fieldData->{relation} ne $defaultRelationName) {
3993                        Confess("Field $fieldName of $defaultRelationName is in secondary relations and cannot be searchable.");
3994                    } else {
3995                        push @textFields, $fieldName;
3996                    }
3997              }              }
             # Plug in the defaults for the optional data generation parameters.  
             Tracer::MergeOptions($fieldData->{DataGen}, { testCount => 1, pass => 0 });  
3998              # Add the PrettySortValue.              # Add the PrettySortValue.
3999              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);
4000          }          }
4001            # If there are searchable fields, remember the fact.
4002            if (@textFields) {
4003                $structure->{searchFields} = \@textFields;
4004            }
4005      }      }
4006  }  }
4007    
4008  =head3 FixName  =head3 _FixName
4009    
4010  Fix the incoming field name so that it is a legal SQL column name.  Fix the incoming field name so that it is a legal SQL column name.
4011    
# Line 2464  Line 4034 
4034      return $fieldName;      return $fieldName;
4035  }  }
4036    
4037  =head3 FixNames  =head3 _FixNames
4038    
4039  Fix all the field names in a list.  Fix all the field names in a list.
4040    
# Line 2495  Line 4065 
4065      return @result;      return @result;
4066  }  }
4067    
4068  =head3 AddField  =head3 _AddField
4069    
4070  Add a field to a field list.  Add a field to a field list.
4071    
# Line 2530  Line 4100 
4100      $fieldList->{$fieldName} = $fieldStructure;      $fieldList->{$fieldName} = $fieldStructure;
4101  }  }
4102    
4103  =head3 ReOrderRelationTable  =head3 _ReOrderRelationTable
4104    
4105  This method will take a relation table and re-sort it according to the implicit ordering of the  This method will take a relation table and re-sort it according to the implicit ordering of the
4106  C<PrettySort> property. Instead of a hash based on field names, it will return a list of fields.  C<PrettySort> property. Instead of a hash based on field names, it will return a list of fields.
# Line 2591  Line 4161 
4161    
4162  }  }
4163    
4164  =head3 IsPrimary  =head3 _IsPrimary
4165    
4166  Return TRUE if a specified relation is a primary relation, else FALSE. A relation is primary  Return TRUE if a specified relation is a primary relation, else FALSE. A relation is primary
4167  if it has the same name as an entity or relationship.  if it has the same name as an entity or relationship.
# Line 2627  Line 4197 
4197      return $retVal;      return $retVal;
4198  }  }
4199    
4200  =head3 FindRelation  =head3 _FindRelation
4201    
4202  Return the descriptor for the specified relation.  Return the descriptor for the specified relation.
4203    
# Line 2658  Line 4228 
4228    
4229  =head2 HTML Documentation Utility Methods  =head2 HTML Documentation Utility Methods
4230    
4231  =head3 ComputeRelationshipSentence  =head3 _ComputeRelationshipSentence
4232    
4233  The relationship sentence consists of the relationship name between the names of the  The relationship sentence consists of the relationship name between the names of the
4234  two related entities and an arity indicator.  two related entities and an arity indicator.
# Line 2696  Line 4266 
4266      return $result;      return $result;
4267  }  }
4268    
4269  =head3 ComputeRelationshipHeading  =head3 _ComputeRelationshipHeading
4270    
4271  The relationship heading is the L<relationship sentence|/ComputeRelationshipSentence> with the entity  The relationship heading is the L<relationship sentence|/ComputeRelationshipSentence> with the entity
4272  names hyperlinked to the appropriate entity sections of the document.  names hyperlinked to the appropriate entity sections of the document.
# Line 2733  Line 4303 
4303      return $result;      return $result;
4304  }  }
4305    
4306  =head3 ShowRelationTable  =head3 _ShowRelationTable
4307    
4308  Generate the HTML string for a particular relation. The relation's data will be formatted as an HTML  Generate the HTML string for a particular relation. The relation's data will be formatted as an HTML
4309  table with three columns-- the field name, the field type, and the field description.  table with three columns-- the field name, the field type, and the field description.
# Line 2783  Line 4353 
4353          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";
4354          # Add any note text.          # Add any note text.
4355          if (my $note = $indexData->{Notes}) {          if (my $note = $indexData->{Notes}) {
4356              $htmlString .= "<li>" . _HTMLNote($note->{content}) . "</li>\n";              $htmlString .= "<li>" . HTMLNote($note->{content}) . "</li>\n";
4357          }          }
4358          # Add the fiield list.          # Add the fiield list.
4359          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";
# Line 2794  Line 4364 
4364      $htmlString .= "</ul>\n";      $htmlString .= "</ul>\n";
4365  }  }
4366    
4367  =head3 OpenFieldTable  =head3 _OpenFieldTable
4368    
4369  This method creates the header string for the field table generated by L</ShowMetaData>.  This method creates the header string for the field table generated by L</ShowMetaData>.
4370    
# Line 2819  Line 4389 
4389      return _OpenTable($tablename, 'Field', 'Type', 'Description');      return _OpenTable($tablename, 'Field', 'Type', 'Description');
4390  }  }
4391    
4392  =head3 OpenTable  =head3 _OpenTable
4393    
4394  This method creates the header string for an HTML table.  This method creates the header string for an HTML table.
4395    
# Line 2859  Line 4429 
4429      return $htmlString;      return $htmlString;
4430  }  }
4431    
4432  =head3 CloseTable  =head3 _CloseTable
4433    
4434  This method returns the HTML for closing a table.  This method returns the HTML for closing a table.
4435    
# Line 2871  Line 4441 
4441      return "</table></p>\n";      return "</table></p>\n";
4442  }  }
4443    
4444  =head3 ShowField  =head3 _ShowField
4445    
4446  This method returns the HTML for displaying a row of field information in a field table.  This method returns the HTML for displaying a row of field information in a field table.
4447    
# Line 2898  Line 4468 
4468      my $htmlString = "<tr><th align=\"left\">$fieldData->{name}</th><td>$fieldData->{type}</td>";      my $htmlString = "<tr><th align=\"left\">$fieldData->{name}</th><td>$fieldData->{type}</td>";
4469      # If we have content, add it as a third column.      # If we have content, add it as a third column.
4470      if (exists $fieldData->{Notes}) {      if (exists $fieldData->{Notes}) {
4471          $htmlString .= "<td>" . _HTMLNote($fieldData->{Notes}->{content}) . "</td>";          $htmlString .= "<td>" . HTMLNote($fieldData->{Notes}->{content}) . "</td>";
4472      }      }
4473      # Close off the row.      # Close off the row.
4474      $htmlString .= "</tr>\n";      $htmlString .= "</tr>\n";
# Line 2906  Line 4476 
4476      return $htmlString;      return $htmlString;
4477  }  }
4478    
 =head3 HTMLNote  
   
 Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes  
 supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.  
 Except for C<[p]>, all the codes are closed by slash-codes. So, for  
 example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.  
   
 This is a static method.  
   
 =over 4  
   
 =item dataString  
   
 String to convert to HTML.  
   
 =item RETURN  
   
 An HTML string derived from the input string.  
   
 =back  
   
 =cut  
   
 sub _HTMLNote {  
     # Get the parameter.  
     my ($dataString) = @_;  
     # Substitute the codes.  
     $dataString =~ s!\[(/?[bi])\]!<$1>!g;  
     $dataString =~ s!\[p\]!</p><p>!g;  
     # Return the result.  
     return $dataString;  
 }  
   
 =head2 Data Generation Utilities  
   
 =head3 IntGen  
   
 C<< my $integer = IntGen($min, $max); >>  
   
 Returns a random number between the specified minimum and maximum (inclusive).  
   
 =over 4  
   
 =item min  
   
 Minimum permissible return value.  
   
 =item max  
   
 Maximum permissible return value.  
   
 =item RETURN  
   
 Returns a value no lower than the minimum and no greater than the maximum.  
   
 =back  
   
 =cut  
   
 sub IntGen {  
     # Get the parameters.  
     my ($min, $max) = @_;  
     # Determine the range of possible values. Note we put some space well above the  
     # maximum value to give it a fighting chance of apppearing in the list.  
     my $span = $max + 0.99 - $min;  
     # Create an integer in the range.  
     my $retVal = $min + int(rand($span));  
     # Return the result.  
     return $retVal;  
 }  
   
 =head3 RandChar  
   
 C<< my $char = RandChar($sourceString); >>  
   
 Select a random character from a string.  
   
 =over 4  
   
 =item sourceString  
   
 String from which the random character should be selected.  
   
 =item RETURN  
   
 Returns a single character from the incoming string.  
   
 =back  
   
 =cut  
   
 sub RandChar {  
     # Get the parameter.  
     my ($sourceString) = @_;  
     # Select a random character.  
     my $retVal = IntGen(0, (length $sourceString) - 1);  
     # Return it.  
     return substr($sourceString, $retVal, 1);  
 }  
   
 =head3 RandChars  
   
 C<< my $string = RandChars($sourceString, $length); >>  
   
 Create a string from characters taken from a source string.  
   
 =over 4  
   
 =item sourceString  
   
 String from which the random characters should be selected.  
   
 =item length  
   
 Number of characters to put in the output string.  
   
 =item RETURN  
   
 Returns a string of the specified length consisting of characters taken from the  
 source string.  
   
 =back  
   
 =cut  
   
 sub RandChars {  
     # Get the parameters.  
     my ($sourceString, $length) = @_;  
     # Call RandChar repeatedly to generate the string.  
     my $retVal = "";  
     for (my $i = 0; $i < $length; $i++) {  
         $retVal .= RandChar($sourceString);  
     }  
     # Return the result.  
     return $retVal;  
 }  
   
 =head3 RandParam  
   
 C<< my $value = RandParam($parm1, $parm2, ... $parmN); >>  
   
 Return a randomly-selected value from the parameter list.  
   
 =over 4  
   
 =item parm1, parm2, ... parmN  
   
 List of values of which one will be selected.  
   
 =item RETURN  
   
 Returns a randomly-chosen value from the specified list.  
   
 =back  
   
 =cut  
   
 sub RandParam {  
     # Get the parameter.  
     my @parms = @_;  
     # Choose a random parameter from the list.  
     my $chosenIndex = IntGen(0, $#parms);  
     return $parms[$chosenIndex];  
 }  
   
 =head3 StringGen  
   
 C<< my $string = StringGen($pattern1, $pattern2, ... $patternN); >>  
   
 Returns a random string derived from a randomly-chosen format pattern. The pattern  
 can either be a number (indicating the number of characters desired, or the letter  
 C<P> followed by a picture. The picture should contain C<A> when a letter is desired,  
 C<9> when a digit is desired, C<V> when a vowel is desired, C<K> when a consonant is  
 desired, and C<X> when a letter or a digit is desired. Any other character will be  
 translated as a literal.  
   
 =over 4  
   
 =item pattern1, pattern2, ... patternN  
   
 List of patterns to be used to generate string values.  
   
 =item RETURN  
   
 A single string generated from a pattern.  
   
 =back  
   
 =cut  
   
 sub StringGen {  
     # Get the parameters.  
     my @patterns = @_;  
     # Choose the appropriate pattern.  
     my $chosenPattern = RandParam(@patterns);  
     # Declare the return variable.  
     my $retVal = "";  
     # Determine whether this is a count or a picture pattern.  
     if ($chosenPattern =~ m/^\d+/) {  
         # Here we have a count. Get the string of source characters.  
         my $letterString = $PictureTable{'X'};  
         my $stringLen = length $letterString;  
         # Save the number of characters we have to generate.  
         my $charsLeft = $chosenPattern;  
         # Loop until the return variable is full.  
         while ($charsLeft > 0) {  
             # Generate a random position in the soruce string.  
             my $stringIndex = IntGen(0, $stringLen - 1);  
             # Compute the number of characters to pull out of the source string.  
             my $chunkSize = $stringLen - $stringIndex;  
             if ($chunkSize > $charsLeft) { $chunkSize = $charsLeft; }  
             # Stuff this chunk into the return value.  
             $retVal .= substr($letterString, $stringIndex, $chunkSize);  
             # Record the data moved.  
             $charsLeft -= $chunkSize;  
         }  
     } elsif ($chosenPattern =~ m/^P/) {  
         # Here we have a picture string. We will move through the picture one  
         # character at a time generating data.  
         for (my $i = 1; $i < length $chosenPattern; $i++) {  
             # Get this picture character.  
             my $chr = substr($chosenPattern, $i, 1);  
             # Check to see if the picture char is one we recognize.  
             if (exists $PictureTable{$chr}) {  
                 # Choose a random character from the available values for this  
                 # picture character.  
                 $retVal .= RandChar($PictureTable{$chr});  
             } else {  
                 # Copy in the picture character as a literal.  
                 $retVal .= $chr;  
             }  
         }  
     } else {  
         # Here we have neither a picture string or a letter count, so we treat  
         # the string as a literal.  
         $retVal = $chosenPattern;  
     }  
     # Return the string formed.  
     return $retVal;  
 }  
   
 =head3 DateGen  
   
 C<< my $date = DateGen($startDayOffset, $endDayOffset, $minutes); >>  
   
 Return a numeric timestamp within the specified range of days with the specified minute  
 value. The range of days is specified relevant to the current day. Thus, the call  
   
 C<< my $date = DateGen(-1, 5, 720); >>  
   
 will return a timestamp at noon (72 minutes past midnight) sometime during the week that  
 began on the preceding day. If you want a random minute of the day, simply combine with  
 a call to L</IntGen>, as follows.  
   
 C<< my $date = DateGen(-1, 5, IntGen(0, 1439)); >>  
   
 =over 4  
   
 =item startDayOffset  
   
 The earliest day that can be returned, relative to the current day.  
   
 =item endDayOffset  
   
 The latest day that can be returned, related to the current day.  
   
 =item minutes  
   
 Number of minutes into the selected day that should be used.  
   
 =back  
   
 =cut  
   
 sub DateGen {  
     # Get the parameters.  
     my ($startDayOffset, $endDayOffset, $minutes) = @_;  
     # Get midnight of the current day.  
     my $now = time();  
     my ($sec, $min, $hour) = localtime($now);  
     my $today = $now - (($hour * 60 + $min) * 60 + $sec);  
     # Compute the day we want.  
     my $newDay = IntGen($startDayOffset, $endDayOffset) * 86400 + $today;  
     # Add the minutes.  
     my $retVal = $newDay + $minutes * 60;  
     # Return the result.  
     return $retVal;  
 }  
   
 =head3 FloatGen  
   
 C<< my $number = FloatGen($min, $max); >>  
   
 Return a random floating-point number greater than or equal to the specified minimum and  
 less than the specified maximum.  
   
 =over 4  
   
 =item min  
   
 Minimum permissible value for the number returned.  
   
 =item max  
   
 Maximum permissible value for the number returned.  
   
 =item RETURN  
   
 Returns a floating-point number anywhere in the specified range.  
   
 =back  
   
 =cut  
   
 sub FloatGen {  
     # Get the parameters.  
     my ($min, $max) = @_;  
     # Generate the result.  
     my $retVal = rand($max - $min) + $min;  
     return $retVal;  
 }  
   
 =head3 ListGen  
   
 C<< my @list = ListGen($pattern, $count); >>  
   
 Return a list containing a fixed number of randomly-generated strings.  
   
 =over 4  
   
 =item pattern  
   
 A pattern (in the form expected by L</StringGen>) that should be used to generate the  
 strings in the list.  
   
 =item count  
   
 The number of list entries to generate.  
   
 =item RETURN  
   
 Returns a list consisting of the specified number of strings.  
   
 =back  
   
 =cut  
   
 sub ListGen {  
     # Get the parameters.  
     my ($pattern, $count) = @_;  
     # Generate the list.  
     my @retVal = ();  
     for (my $i = 0; $i < $count; $i++) {  
         push @retVal, StringGen($pattern);  
     }  
     # Return it.  
     return @retVal;  
 }  
   
4479  1;  1;

Legend:
Removed from v.1.11  
changed lines
  Added in v.1.73

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3