[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 1.74, Fri Nov 3 16:49:44 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
230    
231  An entity can have multiple alternate indexes associated with it. The fields must  An entity can have multiple alternate indexes associated with it. The fields must
232  be from the primary relation. The alternate indexes assist in ordering results  all be from the same relation. The alternate indexes assist in ordering results
233  from a query. A relationship can have up to two indexes-- a I<to-index> and a  from a query. A relationship can have up to two indexes-- a I<to-index> and a
234  I<from-index>. These order the results when crossing the relationship. For  I<from-index>. These order the results when crossing the relationship. For
235  example, in the relationship C<HasContig> from C<Genome> to C<Contig>, the  example, in the relationship C<HasContig> from C<Genome> to C<Contig>, the
# Line 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<< $erdb->DumpMetaData(); >>
637    
638  Return a dump of the metadata structure.  Return a dump of the metadata structure.
639    
# Line 537  Line 646 
646      return Data::Dumper::Dumper($self->{_metaData});      return Data::Dumper::Dumper($self->{_metaData});
647  }  }
648    
649    =head3 FindIndexForEntity
650    
651    C<< my $indexFound = ERDB::FindIndexForEntity($xml, $entityName, $attributeName); >>
652    
653    This method locates the entry in an entity's index list that begins with the
654    specified attribute name. If the entity has no index list, one will be
655    created. This method works on raw XML, not a live ERDB object.
656    
657    =over 4
658    
659    =item xml
660    
661    The raw XML structure defining the database.
662    
663    =item entityName
664    
665    The name of the relevant entity.
666    
667    =item attributeName
668    
669    The name of the attribute relevant to the search.
670    
671    =item RETURN
672    
673    The numerical index in the index list of the index entry for the specified entity and
674    attribute, or C<undef> if no such index exists.
675    
676    =back
677    
678    =cut
679    
680    sub FindIndexForEntity {
681        # Get the parameters.
682        my ($xml, $entityName, $attributeName) = @_;
683        # Declare the return variable.
684        my $retVal;
685        # Get the named entity.
686        my $entityData = $xml->{Entities}->{$entityName};
687        if (! $entityData) {
688            Confess("Entity $entityName not found in DBD structure.");
689        } else {
690            # Insure it has an index list.
691            if (! exists $entityData->{Indexes}) {
692                $entityData->{Indexes} = [];
693            } else {
694                # Search for the desired index.
695                my $indexList = $entityData->{Indexes};
696                my $n = scalar @{$indexList};
697                Trace("Searching $n indexes in index list for $entityName.") if T(2);
698                # We use an indexed FOR here because we're returning an
699                # index number instead of an object. We do THAT so we can
700                # delete the index from the list if needed.
701                for (my $i = 0; $i < $n && !defined($retVal); $i++) {
702                    my $index = $indexList->[$i];
703                    my $fields = $index->{IndexFields};
704                    # Technically this IF should be safe (that is, we are guaranteed
705                    # the existence of a "$fields->[0]"), because when we load the XML
706                    # we have SuppressEmpty specified.
707                    if ($fields->[0]->{name} eq $attributeName) {
708                        $retVal = $i;
709                    }
710                }
711            }
712        }
713        Trace("Index for $attributeName of $entityName found at position $retVal.") if defined($retVal) && T(3);
714        Trace("Index for $attributeName not found in $entityName.") if !defined($retVal) && T(3);
715        # Return the result.
716        return $retVal;
717    }
718    
719  =head3 CreateTables  =head3 CreateTables
720    
721  C<< $datanase->CreateTables(); >>  C<< $erdb->CreateTables(); >>
722    
723  This method creates the tables for the database from the metadata structure loaded by the  This method creates the tables for the database from the metadata structure loaded by the
724  constructor. It is expected this function will only be used on rare occasions, when the  constructor. It is expected this function will only be used on rare occasions, when the
# Line 551  Line 730 
730  sub CreateTables {  sub CreateTables {
731      # Get the parameters.      # Get the parameters.
732      my ($self) = @_;      my ($self) = @_;
733      my $metadata = $self->{_metaData};      # Get the relation names.
734      my $dbh = $self->{_dbh};      my @relNames = $self->GetTableNames();
735      # Loop through the entities.      # Loop through the relations.
736      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}}) {  
737              # Create a table for this relation.              # Create a table for this relation.
738              $self->CreateTable($relationName);              $self->CreateTable($relationName);
739              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);  
740      }      }
741  }  }
742    
743  =head3 CreateTable  =head3 CreateTable
744    
745  C<< $database->CreateTable($tableName, $indexFlag); >>  C<< $erdb->CreateTable($tableName, $indexFlag, $estimatedRows); >>
746    
747  Create the table for a relation and optionally create its indexes.  Create the table for a relation and optionally create its indexes.
748    
# Line 587  Line 752 
752    
753  Name of the relation (which will also be the table name).  Name of the relation (which will also be the table name).
754    
755  =item $indexFlag  =item indexFlag
756    
757  TRUE if the indexes for the relation should be created, else FALSE. If FALSE,  TRUE if the indexes for the relation should be created, else FALSE. If FALSE,
758  L</CreateIndexes> must be called later to bring the indexes into existence.  L</CreateIndexes> must be called later to bring the indexes into existence.
759    
760    =item estimatedRows (optional)
761    
762    If specified, the estimated maximum number of rows for the relation. This
763    information allows the creation of tables using storage engines that are
764    faster but require size estimates, such as MyISAM.
765    
766  =back  =back
767    
768  =cut  =cut
769    
770  sub CreateTable {  sub CreateTable {
771      # Get the parameters.      # Get the parameters.
772      my ($self, $relationName, $indexFlag) = @_;      my ($self, $relationName, $indexFlag, $estimatedRows) = @_;
773      # Get the database handle.      # Get the database handle.
774      my $dbh = $self->{_dbh};      my $dbh = $self->{_dbh};
775      # 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 793 
793      # Insure the table is not already there.      # Insure the table is not already there.
794      $dbh->drop_table(tbl => $relationName);      $dbh->drop_table(tbl => $relationName);
795      Trace("Table $relationName dropped.") if T(2);      Trace("Table $relationName dropped.") if T(2);
796        # If there are estimated rows, create an estimate so we can take advantage of
797        # faster DB technologies.
798        my $estimation = undef;
799        if ($estimatedRows) {
800            $estimation = [$self->EstimateRowSize($relationName), $estimatedRows];
801        }
802      # Create the table.      # Create the table.
803      Trace("Creating table $relationName: $fieldThing") if T(2);      Trace("Creating table $relationName: $fieldThing") if T(2);
804      $dbh->create_table(tbl => $relationName, flds => $fieldThing);      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);
805      Trace("Relation $relationName created in database.") if T(2);      Trace("Relation $relationName created in database.") if T(2);
806      # If we want to build the indexes, we do it here.      # If we want to build the indexes, we do it here. Note that the full-text search
807        # index will not be built until the table has been loaded.
808      if ($indexFlag) {      if ($indexFlag) {
809          $self->CreateIndex($relationName);          $self->CreateIndex($relationName);
810      }      }
811  }  }
812    
813    =head3 VerifyFields
814    
815    C<< my $count = $erdb->VerifyFields($relName, \@fieldList); >>
816    
817    Run through the list of proposed field values, insuring that all the character fields are
818    below the maximum length. If any fields are too long, they will be truncated in place.
819    
820    =over 4
821    
822    =item relName
823    
824    Name of the relation for which the specified fields are destined.
825    
826    =item fieldList
827    
828    Reference to a list, in order, of the fields to be put into the relation.
829    
830    =item RETURN
831    
832    Returns the number of fields truncated.
833    
834    =back
835    
836    =cut
837    
838    sub VerifyFields {
839        # Get the parameters.
840        my ($self, $relName, $fieldList) = @_;
841        # Initialize the return value.
842        my $retVal = 0;
843        # Get the relation definition.
844        my $relData = $self->_FindRelation($relName);
845        # Get the list of field descriptors.
846        my $fieldTypes = $relData->{Fields};
847        my $fieldCount = scalar @{$fieldTypes};
848        # Loop through the two lists.
849        for (my $i = 0; $i < $fieldCount; $i++) {
850            # Get the type of the current field.
851            my $fieldType = $fieldTypes->[$i]->{type};
852            # If it's a character field, verify the length.
853            if ($fieldType =~ /string/) {
854                my $maxLen = $TypeTable{$fieldType}->{maxLen};
855                my $oldString = $fieldList->[$i];
856                if (length($oldString) > $maxLen) {
857                    # Here it's too big, so we truncate it.
858                    Trace("Truncating field $i in relation $relName to $maxLen characters from \"$oldString\".") if T(1);
859                    $fieldList->[$i] = substr $oldString, 0, $maxLen;
860                    $retVal++;
861                }
862            }
863        }
864        # Return the truncation count.
865        return $retVal;
866    }
867    
868    =head3 DigestFields
869    
870    C<< $erdb->DigestFields($relName, $fieldList); >>
871    
872    Digest the strings in the field list that correspond to data type C<hash-string> in the
873    specified relation.
874    
875    =over 4
876    
877    =item relName
878    
879    Name of the relation to which the fields belong.
880    
881    =item fieldList
882    
883    List of field contents to be loaded into the relation.
884    
885    =back
886    
887    =cut
888    #: Return Type ;
889    sub DigestFields {
890        # Get the parameters.
891        my ($self, $relName, $fieldList) = @_;
892        # Get the relation definition.
893        my $relData = $self->_FindRelation($relName);
894        # Get the list of field descriptors.
895        my $fieldTypes = $relData->{Fields};
896        my $fieldCount = scalar @{$fieldTypes};
897        # Loop through the two lists.
898        for (my $i = 0; $i < $fieldCount; $i++) {
899            # Get the type of the current field.
900            my $fieldType = $fieldTypes->[$i]->{type};
901            # If it's a hash string, digest it in place.
902            if ($fieldType eq 'hash-string') {
903                $fieldList->[$i] = $self->DigestKey($fieldList->[$i]);
904            }
905        }
906    }
907    
908    =head3 DigestKey
909    
910    C<< my $digested = $erdb->DigestKey($keyValue); >>
911    
912    Return the digested value of a symbolic key. The digested value can then be plugged into a
913    key-based search into a table with key-type hash-string.
914    
915    Currently the digesting process is independent of the database structure, but that may not
916    always be the case, so this is an instance method instead of a static method.
917    
918    =over 4
919    
920    =item keyValue
921    
922    Key value to digest.
923    
924    =item RETURN
925    
926    Digested value of the key.
927    
928    =back
929    
930    =cut
931    
932    sub DigestKey {
933        # Get the parameters.
934        my ($self, $keyValue) = @_;
935        # Compute the digest.
936        my $retVal = md5_base64($keyValue);
937        # Return the result.
938        return $retVal;
939    }
940    
941  =head3 CreateIndex  =head3 CreateIndex
942    
943  C<< $database->CreateIndex($relationName); >>  C<< $erdb->CreateIndex($relationName); >>
944    
945  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
946  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.
947  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
948  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.
949    
950  =cut  =cut
951    
# Line 658  Line 964 
964          my @fieldList = _FixNames(@{$indexData->{IndexFields}});          my @fieldList = _FixNames(@{$indexData->{IndexFields}});
965          my $flds = join(', ', @fieldList);          my $flds = join(', ', @fieldList);
966          # Get the index's uniqueness flag.          # Get the index's uniqueness flag.
967          my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
968          # Create the index.          # Create the index.
969          $dbh->create_index(idx => $indexName, tbl => $relationName, flds => $flds, unique => $unique);          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
970                                        flds => $flds, kind => $unique);
971            if ($rv) {
972          Trace("Index created: $indexName for $relationName ($flds)") if T(1);          Trace("Index created: $indexName for $relationName ($flds)") if T(1);
973            } else {
974                Confess("Error creating index $indexName for $relationName using ($flds): " . $dbh->error_message());
975            }
976      }      }
977  }  }
978    
979  =head3 LoadTables  =head3 LoadTables
980    
981  C<< my $stats = $database->LoadTables($directoryName, $rebuild); >>  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>
982    
983  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
984  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 1021 
1021      $directoryName =~ s!/\\$!!;      $directoryName =~ s!/\\$!!;
1022      # Declare the return variable.      # Declare the return variable.
1023      my $retVal = Stats->new();      my $retVal = Stats->new();
1024      # Get the metadata structure.      # Get the relation names.
1025      my $metaData = $self->{_metaData};      my @relNames = $self->GetTableNames();
1026      # 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}}) {  
1027              # Try to load this relation.              # Try to load this relation.
1028              my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);              my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);
1029              # Accumulate the statistics.              # Accumulate the statistics.
1030              $retVal->Accumulate($result);              $retVal->Accumulate($result);
1031          }          }
     }  
     # 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);  
     }  
1032      # Add the duration of the load to the statistical object.      # Add the duration of the load to the statistical object.
1033      $retVal->Add('duration', gettimeofday - $startTime);      $retVal->Add('duration', gettimeofday - $startTime);
1034      # Return the accumulated statistics.      # Return the accumulated statistics.
1035      return $retVal;      return $retVal;
1036  }  }
1037    
1038    
1039  =head3 GetTableNames  =head3 GetTableNames
1040    
1041  C<< my @names = $database->GetTableNames; >>  C<< my @names = $erdb->GetTableNames; >>
1042    
1043  Return a list of the relations required to implement this database.  Return a list of the relations required to implement this database.
1044    
# Line 754  Line 1055 
1055    
1056  =head3 GetEntityTypes  =head3 GetEntityTypes
1057    
1058  C<< my @names = $database->GetEntityTypes; >>  C<< my @names = $erdb->GetEntityTypes; >>
1059    
1060  Return a list of the entity type names.  Return a list of the entity type names.
1061    
# Line 769  Line 1070 
1070      return sort keys %{$entityList};      return sort keys %{$entityList};
1071  }  }
1072    
1073    =head3 GetDataTypes
1074    
1075    C<< my %types = ERDB::GetDataTypes(); >>
1076    
1077    Return a table of ERDB data types. The table returned is a hash of hashes.
1078    The keys of the big hash are the datatypes. Each smaller hash has several
1079    values used to manage the data. The most interesting is the SQL type (key
1080    C<sqlType>) and the descriptive node (key C<notes>).
1081    
1082    Note that changing the values in the smaller hashes will seriously break
1083    things, so this data should be treated as read-only.
1084    
1085    =cut
1086    
1087    sub GetDataTypes {
1088        return %TypeTable;
1089    }
1090    
1091    
1092    =head3 IsEntity
1093    
1094    C<< my $flag = $erdb->IsEntity($entityName); >>
1095    
1096    Return TRUE if the parameter is an entity name, else FALSE.
1097    
1098    =over 4
1099    
1100    =item entityName
1101    
1102    Object name to be tested.
1103    
1104    =item RETURN
1105    
1106    Returns TRUE if the specified string is an entity name, else FALSE.
1107    
1108    =back
1109    
1110    =cut
1111    
1112    sub IsEntity {
1113        # Get the parameters.
1114        my ($self, $entityName) = @_;
1115        # Test to see if it's an entity.
1116        return exists $self->{_metaData}->{Entities}->{$entityName};
1117    }
1118    
1119  =head3 Get  =head3 Get
1120    
1121  C<< my $query = $database->Get(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  C<< my $query = $erdb->Get(\@objectNames, $filterClause, \@params); >>
1122    
1123  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.
1124  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 1126 
1126  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
1127  $genus.  $genus.
1128    
1129  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", [$genus]); >>
1130    
1131  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
1132  parameter representing the parameter value. It would also be possible to code  parameter representing the parameter value. It would also be possible to code
1133    
1134  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>
1135    
1136  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
1137  characters inside the variable C<$genus>.  characters inside the variable C<$genus>.
# Line 796  Line 1143 
1143  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
1144  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,
1145    
1146  C<< $query = $sprout->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]); >>
1147    
1148  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
1149  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.
1150  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
1151  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
1152  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  
1153  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,
1154  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.
1155    
1156    If an entity or relationship is mentioned twice, the name for the second occurrence will
1157    be suffixed with C<2>, the third occurrence will be suffixed with C<3>, and so forth. So,
1158    for example, if we have C<['Feature', 'HasContig', 'Contig', 'HasContig']>, then the
1159    B<to-link> field of the first B<HasContig> is specified as C<HasContig(to-link)>, while
1160    the B<to-link> field of the second B<HasContig> is specified as C<HasContig2(to-link)>.
1161    
1162  =over 4  =over 4
1163    
1164  =item objectNames  =item objectNames
# Line 829  Line 1181 
1181    
1182  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
1183    
1184    Note that the case is important. Only an uppercase "ORDER BY" with a single space will
1185    be processed. The idea is to make it less likely to find the verb by accident.
1186    
1187  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
1188  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
1189  relation.  relation.
1190    
1191  =item param1, param2, ..., paramN  Finally, you can limit the number of rows returned by adding a LIMIT clause. The LIMIT must
1192    be the last thing in the filter clause, and it contains only the word "LIMIT" followed by
1193    a positive number. So, for example
1194    
1195  Parameter values to be substituted into the filter clause.  C<< "Genome(genus) = ? ORDER BY Genome(species) LIMIT 10" >>
1196    
1197    will only return the first ten genomes for the specified genus. The ORDER BY clause is not
1198    required. For example, to just get the first 10 genomes in the B<Genome> table, you could
1199    use
1200    
1201    C<< "LIMIT 10" >>
1202    
1203    =item params
1204    
1205    Reference to a list of parameter values to be substituted into the filter clause.
1206    
1207  =item RETURN  =item RETURN
1208    
# Line 847  Line 1214 
1214    
1215  sub Get {  sub Get {
1216      # Get the parameters.      # Get the parameters.
1217      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $objectNames, $filterClause, $params) = @_;
1218      # Construct the SELECT statement. The general pattern is      # Process the SQL stuff.
1219      #      my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1220      # SELECT name1.*, name2.*, ... nameN.* FROM name1, name2, ... nameN          $self->_SetupSQL($objectNames, $filterClause);
1221      #      # Create the query.
1222      my $dbh = $self->{_dbh};      my $command = "SELECT DISTINCT " . join(".*, ", @{$mappedNameListRef}) .
1223      my $command = "SELECT DISTINCT " . join('.*, ', @{$objectNames}) . ".* FROM " .          ".* $suffix";
1224                  join(', ', @{$objectNames});      my $sth = $self->_GetStatementHandle($command, $params);
1225      # Check for a filter clause.      # Now we create the relation map, which enables DBQuery to determine the order, name
1226      if ($filterClause) {      # and mapped name for each object in the query.
1227          # Here we have one, so we convert its field names and add it to the query. First,      my @relationMap = ();
1228          # We create a copy of the filter string we can work with.      for my $mappedName (@{$mappedNameListRef}) {
1229          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;  
                 }  
1230              }              }
1231        # Return the statement object.
1232        my $retVal = DBQuery::_new($self, $sth, \@relationMap);
1233        return $retVal;
1234          }          }
1235          # The next step is to join the objects together. We only need to do this if there  
1236          # is more than one object in the object list. We start with the first object and  =head3 Search
1237          # run through the objects after it. Note also that we make a safety copy of the  
1238          # list before running through it.  C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>
1239          my @objectList = @{$objectNames};  
1240          my $lastObject = shift @objectList;  Perform a full text search with filtering. The search will be against a specified object
1241          # Get the join table.  in the object name list. That object will get an extra field containing the search
1242          my $joinTable = $self->{_metaData}->{Joins};  relevance. Note that except for the search expression, the parameters of this method are
1243          # Loop through the object list.  the same as those for L</Get> and follow the same rules.
1244          for my $thisObject (@objectList) {  
1245              # Look for a join.  =over 4
1246              my $joinKey = "$lastObject/$thisObject";  
1247              if (!exists $joinTable->{$joinKey}) {  =item searchExpression
1248                  # Here there's no join, so we throw an error.  
1249                  Confess("No join exists to connect from $lastObject to $thisObject.");  Boolean search expression for the text fields of the target object.
1250    
1251    =item idx
1252    
1253    Index in the I<$objectNames> list of the table to be searched in full-text mode.
1254    
1255    =item objectNames
1256    
1257    List containing the names of the entity and relationship objects to be retrieved.
1258    
1259    =item filterClause
1260    
1261    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1262    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
1263    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
1264    in the filter clause should be added to the parameter list as additional parameters. The
1265    fields in a filter clause can come from primary entity relations, relationship relations,
1266    or secondary entity relations; however, all of the entities and relationships involved must
1267    be included in the list of object names.
1268    
1269    =item params
1270    
1271    Reference to a list of parameter values to be substituted into the filter clause.
1272    
1273    =item RETURN
1274    
1275    Returns a query object for the specified search.
1276    
1277    =back
1278    
1279    =cut
1280    
1281    sub Search {
1282        # Get the parameters.
1283        my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1284        # Declare the return variable.
1285        my $retVal;
1286        # Create a safety copy of the parameter list. Note we have to be careful to insure
1287        # a parameter list exists before we copy it.
1288        my @myParams = ();
1289        if (defined $params) {
1290            @myParams = @{$params};
1291        }
1292        # Get the first object's structure so we have access to the searchable fields.
1293        my $object1Name = $objectNames->[$idx];
1294        my $object1Structure = $self->_GetStructure($object1Name);
1295        # Get the field list.
1296        if (! exists $object1Structure->{searchFields}) {
1297            Confess("No searchable index for $object1Name.");
1298              } else {              } else {
1299                  # Get the join clause and add it to the WHERE list.          # Get the field list.
1300                  push @joinWhere, $joinTable->{$joinKey};          my @fields = @{$object1Structure->{searchFields}};
1301                  # Save this object as the last object for the next iteration.          # Clean the search expression.
1302                  $lastObject = $thisObject;          my $actualKeywords = $self->CleanKeywords($searchExpression);
1303            Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1304            # We need two match expressions, one for the filter clause and one in the
1305            # query itself. Both will use a parameter mark, so we need to push the
1306            # search expression onto the front of the parameter list twice.
1307            unshift @myParams, $actualKeywords, $actualKeywords;
1308            # Build the match expression.
1309            my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
1310            my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
1311            # Process the SQL stuff.
1312            my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1313                $self->_SetupSQL($objectNames, $filterClause, $matchClause);
1314            # Create the query. Note that the match clause is inserted at the front of
1315            # the select fields.
1316            my $command = "SELECT DISTINCT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .
1317                ".* $suffix";
1318            my $sth = $self->_GetStatementHandle($command, \@myParams);
1319            # Now we create the relation map, which enables DBQuery to determine the order, name
1320            # and mapped name for each object in the query.
1321            my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
1322            # Return the statement object.
1323            $retVal = DBQuery::_new($self, $sth, \@relationMap, $object1Name);
1324              }              }
1325        return $retVal;
1326          }          }
1327          # Now we need to handle the whole ORDER BY thing. We'll put the order by clause  
1328          # in the following variable.  =head3 GetFlat
1329          my $orderClause = "";  
1330          # Locate the ORDER BY verb (if any).  C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>
1331          if ($filterString =~ m/^(.*)ORDER BY/g) {  
1332              # Here we have an ORDER BY verb. Split it off of the filter string.  This is a variation of L</GetAll> that asks for only a single field per record and
1333              my $pos = pos $filterString;  returns a single flattened list.
1334              $orderClause = substr($filterString, $pos);  
1335              $filterString = $1;  =over 4
1336    
1337    =item objectNames
1338    
1339    List containing the names of the entity and relationship objects to be retrieved.
1340    
1341    =item filterClause
1342    
1343    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1344    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
1345    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
1346    parameter list as additional parameters. The fields in a filter clause can come from primary
1347    entity relations, relationship relations, or secondary entity relations; however, all of the
1348    entities and relationships involved must be included in the list of object names.
1349    
1350    =item parameterList
1351    
1352    List of the parameters to be substituted in for the parameters marks in the filter clause.
1353    
1354    =item field
1355    
1356    Name of the field to be used to get the elements of the list returned.
1357    
1358    =item RETURN
1359    
1360    Returns a list of values.
1361    
1362    =back
1363    
1364    =cut
1365    #: Return Type @;
1366    sub GetFlat {
1367        # Get the parameters.
1368        my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
1369        # Construct the query.
1370        my $query = $self->Get($objectNames, $filterClause, $parameterList);
1371        # Create the result list.
1372        my @retVal = ();
1373        # Loop through the records, adding the field values found to the result list.
1374        while (my $row = $query->Fetch()) {
1375            push @retVal, $row->Value($field);
1376          }          }
1377          # Add the filter and the join clauses (if any) to the SELECT command.      # Return the list created.
1378          if ($filterString) {      return @retVal;
             push @joinWhere, "($filterString)";  
1379          }          }
1380          if (@joinWhere) {  
1381              $command .= " WHERE " . join(' AND ', @joinWhere);  =head3 SpecialFields
1382    
1383    C<< my %specials = $erdb->SpecialFields($entityName); >>
1384    
1385    Return a hash mapping special fields in the specified entity to the value of their
1386    C<special> attribute. This enables the subclass to get access to the special field
1387    attributes without needed to plumb the internal ERDB data structures.
1388    
1389    =over 4
1390    
1391    =item entityName
1392    
1393    Name of the entity whose special fields are desired.
1394    
1395    =item RETURN
1396    
1397    Returns a hash. The keys of the hash are the special field names, and the values
1398    are the values from each special field's C<special> attribute.
1399    
1400    =back
1401    
1402    =cut
1403    
1404    sub SpecialFields {
1405        # Get the parameters.
1406        my ($self, $entityName) = @_;
1407        # Declare the return variable.
1408        my %retVal = ();
1409        # Find the entity's data structure.
1410        my $entityData = $self->{Entities}->{$entityName};
1411        # Loop through its fields, adding each special field to the return hash.
1412        my $fieldHash = $entityData->{Fields};
1413        for my $fieldName (keys %{$fieldHash}) {
1414            my $fieldData = $fieldHash->{$fieldName};
1415            if (exists $fieldData->{special}) {
1416                $retVal{$fieldName} = $fieldData->{special};
1417          }          }
         # Add the sort clause (if any) to the SELECT command.  
         if ($orderClause) {  
             $command .= " ORDER BY $orderClause";  
1418          }          }
1419        # Return the result.
1420        return %retVal;
1421      }      }
1422      Trace("SQL query: $command") if T(2);  
1423      Trace("PARMS: '" . (join "', '", @params) . "'") if (T(3) && (@params > 0));  =head3 Delete
1424      my $sth = $dbh->prepare_command($command);  
1425      # Execute it with the parameters bound in.  C<< my $stats = $erdb->Delete($entityName, $objectID); >>
1426      $sth->execute(@params) || Confess("SELECT error" . $sth->errstr());  
1427      # Return the statement object.  Delete an entity instance from the database. The instance is deleted along with all entity and
1428      my $retVal = DBQuery::_new($self, $sth, @{$objectNames});  relationship instances dependent on it. The idea of dependence here is recursive. An object is
1429    always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many
1430    relationship connected to a dependent entity or the "to" entity connected to a 1-to-many
1431    dependent relationship.
1432    
1433    =over 4
1434    
1435    =item entityName
1436    
1437    Name of the entity type for the instance being deleted.
1438    
1439    =item objectID
1440    
1441    ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),
1442    then it is presumed to by a LIKE pattern.
1443    
1444    =item testFlag
1445    
1446    If TRUE, the delete statements will be traced without being executed.
1447    
1448    =item RETURN
1449    
1450    Returns a statistics object indicating how many records of each particular table were
1451    deleted.
1452    
1453    =back
1454    
1455    =cut
1456    #: Return Type $%;
1457    sub Delete {
1458        # Get the parameters.
1459        my ($self, $entityName, $objectID, $testFlag) = @_;
1460        # Declare the return variable.
1461        my $retVal = Stats->new();
1462        # Get the DBKernel object.
1463        my $db = $self->{_dbh};
1464        # We're going to generate all the paths branching out from the starting entity. One of
1465        # the things we have to be careful about is preventing loops. We'll use a hash to
1466        # determine if we've hit a loop.
1467        my %alreadyFound = ();
1468        # These next lists will serve as our result stack. We start by pushing object lists onto
1469        # the stack, and then popping them off to do the deletes. This means the deletes will
1470        # start with the longer paths before getting to the shorter ones. That, in turn, makes
1471        # sure we don't delete records that might be needed to forge relationships back to the
1472        # original item. We have two lists-- one for TO-relationships, and one for
1473        # FROM-relationships and entities.
1474        my @fromPathList = ();
1475        my @toPathList = ();
1476        # This final hash is used to remember what work still needs to be done. We push paths
1477        # onto the list, then pop them off to extend the paths. We prime it with the starting
1478        # point. Note that we will work hard to insure that the last item on a path in the
1479        # TODO list is always an entity.
1480        my @todoList = ([$entityName]);
1481        while (@todoList) {
1482            # Get the current path.
1483            my $current = pop @todoList;
1484            # Copy it into a list.
1485            my @stackedPath = @{$current};
1486            # Pull off the last item on the path. It will always be an entity.
1487            my $entityName = pop @stackedPath;
1488            # Add it to the alreadyFound list.
1489            $alreadyFound{$entityName} = 1;
1490            # Get the entity data.
1491            my $entityData = $self->_GetStructure($entityName);
1492            # The first task is to loop through the entity's relation. A DELETE command will
1493            # be needed for each of them.
1494            my $relations = $entityData->{Relations};
1495            for my $relation (keys %{$relations}) {
1496                my @augmentedList = (@stackedPath, $relation);
1497                push @fromPathList, \@augmentedList;
1498            }
1499            # Now we need to look for relationships connected to this entity.
1500            my $relationshipList = $self->{_metaData}->{Relationships};
1501            for my $relationshipName (keys %{$relationshipList}) {
1502                my $relationship = $relationshipList->{$relationshipName};
1503                # Check the FROM field. We're only interested if it's us.
1504                if ($relationship->{from} eq $entityName) {
1505                    # Add the path to this relationship.
1506                    my @augmentedList = (@stackedPath, $entityName, $relationshipName);
1507                    push @fromPathList, \@augmentedList;
1508                    # Check the arity. If it's MM we're done. If it's 1M
1509                    # and the target hasn't been seen yet, we want to
1510                    # stack the entity for future processing.
1511                    if ($relationship->{arity} eq '1M') {
1512                        my $toEntity = $relationship->{to};
1513                        if (! exists $alreadyFound{$toEntity}) {
1514                            # Here we have a new entity that's dependent on
1515                            # the current entity, so we need to stack it.
1516                            my @stackList = (@augmentedList, $toEntity);
1517                            push @fromPathList, \@stackList;
1518                        } else {
1519                            Trace("$toEntity ignored because it occurred previously.") if T(4);
1520                        }
1521                    }
1522                }
1523                # Now check the TO field. In this case only the relationship needs
1524                # deletion.
1525                if ($relationship->{to} eq $entityName) {
1526                    my @augmentedList = (@stackedPath, $entityName, $relationshipName);
1527                    push @toPathList, \@augmentedList;
1528                }
1529            }
1530        }
1531        # Create the first qualifier for the WHERE clause. This selects the
1532        # keys of the primary entity records to be deleted. When we're deleting
1533        # from a dependent table, we construct a join page from the first qualifier
1534        # to the table containing the dependent records to delete.
1535        my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
1536        # We need to make two passes. The first is through the to-list, and
1537        # the second through the from-list. The from-list is second because
1538        # the to-list may need to pass through some of the entities the
1539        # from-list would delete.
1540        my %stackList = ( from_link => \@fromPathList, to_link => \@toPathList );
1541        # Now it's time to do the deletes. We do it in two passes.
1542        for my $keyName ('to_link', 'from_link') {
1543            # Get the list for this key.
1544            my @pathList = @{$stackList{$keyName}};
1545            Trace(scalar(@pathList) . " entries in path list for $keyName.") if T(3);
1546            # Loop through this list.
1547            while (my $path = pop @pathList) {
1548                # Get the table whose rows are to be deleted.
1549                my @pathTables = @{$path};
1550                # Start the DELETE statement. We need to call DBKernel because the
1551                # syntax of a DELETE-USING varies among DBMSs.
1552                my $target = $pathTables[$#pathTables];
1553                my $stmt = $db->SetUsing(@pathTables);
1554                # Now start the WHERE. The first thing is the ID field from the starting table. That
1555                # starting table will either be the entity relation or one of the entity's
1556                # sub-relations.
1557                $stmt .= " WHERE $pathTables[0].id $qualifier";
1558                # Now we run through the remaining entities in the path, connecting them up.
1559                for (my $i = 1; $i <= $#pathTables; $i += 2) {
1560                    # Connect the current relationship to the preceding entity.
1561                    my ($entity, $rel) = @pathTables[$i-1,$i];
1562                    # The style of connection depends on the direction of the relationship.
1563                    $stmt .= " AND $entity.id = $rel.$keyName";
1564                    if ($i + 1 <= $#pathTables) {
1565                        # Here there's a next entity, so connect that to the relationship's
1566                        # to-link.
1567                        my $entity2 = $pathTables[$i+1];
1568                        $stmt .= " AND $rel.to_link = $entity2.id";
1569                    }
1570                }
1571                # Now we have our desired DELETE statement.
1572                if ($testFlag) {
1573                    # Here the user wants to trace without executing.
1574                    Trace($stmt) if T(0);
1575                } else {
1576                    # Here we can delete. Note that the SQL method dies with a confessing
1577                    # if an error occurs, so we just go ahead and do it.
1578                    Trace("Executing delete from $target using '$objectID'.") if T(3);
1579                    my $rv = $db->SQL($stmt, 0, $objectID);
1580                    # Accumulate the statistics for this delete. The only rows deleted
1581                    # are from the target table, so we use its name to record the
1582                    # statistic.
1583                    $retVal->Add($target, $rv);
1584                }
1585            }
1586        }
1587        # Return the result.
1588        return $retVal;
1589    }
1590    
1591    =head3 SortNeeded
1592    
1593    C<< my $parms = $erdb->SortNeeded($relationName); >>
1594    
1595    Return the pipe command for the sort that should be applied to the specified
1596    relation when creating the load file.
1597    
1598    For example, if the load file should be sorted ascending by the first
1599    field, this method would return
1600    
1601        sort -k1 -t"\t"
1602    
1603    If the first field is numeric, the method would return
1604    
1605        sort -k1n -t"\t"
1606    
1607    Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate
1608    keys using a sort.
1609    
1610    =over 4
1611    
1612    =item relationName
1613    
1614    Name of the relation to be examined.
1615    
1616    =item
1617    
1618    Returns the sort command to use for sorting the relation, suitable for piping.
1619    
1620    =back
1621    
1622    =cut
1623    #: Return Type $;
1624    sub SortNeeded {
1625        # Get the parameters.
1626        my ($self, $relationName) = @_;
1627        # Declare a descriptor to hold the names of the key fields.
1628        my @keyNames = ();
1629        # Get the relation structure.
1630        my $relationData = $self->_FindRelation($relationName);
1631        # Find out if the relation is a primary entity relation,
1632        # a relationship relation, or a secondary entity relation.
1633        my $entityTable = $self->{_metaData}->{Entities};
1634        my $relationshipTable = $self->{_metaData}->{Relationships};
1635        if (exists $entityTable->{$relationName}) {
1636            # Here we have a primary entity relation.
1637            push @keyNames, "id";
1638        } elsif (exists $relationshipTable->{$relationName}) {
1639            # Here we have a relationship. We sort using the FROM index.
1640            my $relationshipData = $relationshipTable->{$relationName};
1641            my $index = $relationData->{Indexes}->{"idx${relationName}From"};
1642            push @keyNames, @{$index->{IndexFields}};
1643        } else {
1644            # Here we have a secondary entity relation, so we have a sort on the ID field.
1645            push @keyNames, "id";
1646        }
1647        # Now we parse the key names into sort parameters. First, we prime the return
1648        # string.
1649        my $retVal = "sort -t\"\t\" ";
1650        # Get the relation's field list.
1651        my @fields = @{$relationData->{Fields}};
1652        # Loop through the keys.
1653        for my $keyData (@keyNames) {
1654            # Get the key and the ordering.
1655            my ($keyName, $ordering);
1656            if ($keyData =~ /^([^ ]+) DESC/) {
1657                ($keyName, $ordering) = ($1, "descending");
1658            } else {
1659                ($keyName, $ordering) = ($keyData, "ascending");
1660            }
1661            # Find the key's position and type.
1662            my $fieldSpec;
1663            for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {
1664                my $thisField = $fields[$i];
1665                if ($thisField->{name} eq $keyName) {
1666                    # Get the sort modifier for this field type. The modifier
1667                    # decides whether we're using a character, numeric, or
1668                    # floating-point sort.
1669                    my $modifier = $TypeTable{$thisField->{type}}->{sort};
1670                    # If the index is descending for this field, denote we want
1671                    # to reverse the sort order on this field.
1672                    if ($ordering eq 'descending') {
1673                        $modifier .= "r";
1674                    }
1675                    # Store the position and modifier into the field spec, which
1676                    # will stop the inner loop. Note that the field number is
1677                    # 1-based in the sort command, so we have to increment the
1678                    # index.
1679                    $fieldSpec = ($i + 1) . $modifier;
1680                }
1681            }
1682            # Add this field to the sort command.
1683            $retVal .= " -k$fieldSpec";
1684        }
1685        # Return the result.
1686      return $retVal;      return $retVal;
1687  }  }
1688    
1689  =head3 GetList  =head3 GetList
1690    
1691  C<< my @dbObjects = $database->GetList(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>
1692    
1693  Return a list of object descriptors for the specified objects as determined by the  Return a list of object descriptors for the specified objects as determined by the
1694  specified filter clause.  specified filter clause.
# Line 1005  Line 1722 
1722  filter clause in general; however, odd things may happen if a sort field is from a secondary  filter clause in general; however, odd things may happen if a sort field is from a secondary
1723  relation.  relation.
1724    
1725  =item param1, param2, ..., paramN  =item params
1726    
1727  Parameter values to be substituted into the filter clause.  Reference to a list of parameter values to be substituted into the filter clause.
1728    
1729  =item RETURN  =item RETURN
1730    
# Line 1019  Line 1736 
1736  #: Return Type @%  #: Return Type @%
1737  sub GetList {  sub GetList {
1738      # Get the parameters.      # Get the parameters.
1739      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $objectNames, $filterClause, $params) = @_;
1740      # Declare the return variable.      # Declare the return variable.
1741      my @retVal = ();      my @retVal = ();
1742      # Perform the query.      # Perform the query.
1743      my $query = $self->Get($objectNames, $filterClause, @params);      my $query = $self->Get($objectNames, $filterClause, $params);
1744      # Loop through the results.      # Loop through the results.
1745      while (my $object = $query->Fetch) {      while (my $object = $query->Fetch) {
1746          push @retVal, $object;          push @retVal, $object;
# Line 1032  Line 1749 
1749      return @retVal;      return @retVal;
1750  }  }
1751    
1752    =head3 GetCount
1753    
1754    C<< my $count = $erdb->GetCount(\@objectNames, $filter, \@params); >>
1755    
1756    Return the number of rows found by a specified query. This method would
1757    normally be used to count the records in a single table. For example, in a
1758    genetics database
1759    
1760        my $count = $erdb->GetCount(['Genome'], 'Genome(genus-species) LIKE ?', ['homo %']);
1761    
1762    would return the number of genomes for the genus I<homo>. It is conceivable, however,
1763    to use it to return records based on a join. For example,
1764    
1765        my $count = $erdb->GetCount(['HasFeature', 'Genome'], 'Genome(genus-species) LIKE ?',
1766                                    ['homo %']);
1767    
1768    would return the number of features for genomes in the genus I<homo>. Note that
1769    only the rows from the first table are counted. If the above command were
1770    
1771        my $count = $erdb->GetCount(['Genome', 'Feature'], 'Genome(genus-species) LIKE ?',
1772                                    ['homo %']);
1773    
1774    it would return the number of genomes, not the number of genome/feature pairs.
1775    
1776    =over 4
1777    
1778    =item objectNames
1779    
1780    Reference to a list of the objects (entities and relationships) included in the
1781    query.
1782    
1783    =item filter
1784    
1785    A filter clause for restricting the query. The rules are the same as for the L</Get>
1786    method.
1787    
1788    =item params
1789    
1790    Reference to a list of the parameter values to be substituted for the parameter marks
1791    in the filter.
1792    
1793    =item RETURN
1794    
1795    Returns a count of the number of records in the first table that would satisfy
1796    the query.
1797    
1798    =back
1799    
1800    =cut
1801    
1802    sub GetCount {
1803        # Get the parameters.
1804        my ($self, $objectNames, $filter, $params) = @_;
1805        # Insure the params argument is an array reference if the caller left it off.
1806        if (! defined($params)) {
1807            $params = [];
1808        }
1809        # Declare the return variable.
1810        my $retVal;
1811        # Find out if we're counting an entity or a relationship.
1812        my $countedField;
1813        if ($self->IsEntity($objectNames->[0])) {
1814            $countedField = "id";
1815        } else {
1816            # For a relationship we count the to-link because it's usually more
1817            # numerous. Note we're automatically converting to the SQL form
1818            # of the field name (to_link vs. to-link).
1819            $countedField = "to_link";
1820        }
1821        # Create the SQL command suffix to get the desired records.
1822        my ($suffix, $mappedNameListRef, $mappedNameHashRef) = $self->_SetupSQL($objectNames,
1823                                                                                $filter);
1824        # Prefix it with text telling it we want a record count.
1825        my $firstObject = $mappedNameListRef->[0];
1826        my $command = "SELECT COUNT($firstObject.$countedField) $suffix";
1827        # Prepare and execute the command.
1828        my $sth = $self->_GetStatementHandle($command, $params);
1829        # Get the count value.
1830        ($retVal) = $sth->fetchrow_array();
1831        # Check for a problem.
1832        if (! defined($retVal)) {
1833            if ($sth->err) {
1834                # Here we had an SQL error.
1835                Confess("Error retrieving row count: " . $sth->errstr());
1836            } else {
1837                # Here we have no result.
1838                Confess("No result attempting to retrieve row count.");
1839            }
1840        }
1841        # Return the result.
1842        return $retVal;
1843    }
1844    
1845  =head3 ComputeObjectSentence  =head3 ComputeObjectSentence
1846    
1847  C<< my $sentence = $database->ComputeObjectSentence($objectName); >>  C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>
1848    
1849  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.
1850    
# Line 1069  Line 1879 
1879    
1880  =head3 DumpRelations  =head3 DumpRelations
1881    
1882  C<< $database->DumpRelations($outputDirectory); >>  C<< $erdb->DumpRelations($outputDirectory); >>
1883    
1884  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.
1885  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 1919 
1919      }      }
1920  }  }
1921    
1922    =head3 InsertValue
1923    
1924    C<< $erdb->InsertValue($entityID, $fieldName, $value); >>
1925    
1926    This method will insert a new value into the database. The value must be one
1927    associated with a secondary relation, since primary values cannot be inserted:
1928    they occur exactly once. Secondary values, on the other hand, can be missing
1929    or multiply-occurring.
1930    
1931    =over 4
1932    
1933    =item entityID
1934    
1935    ID of the object that is to receive the new value.
1936    
1937    =item fieldName
1938    
1939    Field name for the new value-- this includes the entity name, since
1940    field names are of the format I<objectName>C<(>I<fieldName>C<)>.
1941    
1942    =item value
1943    
1944    New value to be put in the field.
1945    
1946    =back
1947    
1948    =cut
1949    
1950    sub InsertValue {
1951        # Get the parameters.
1952        my ($self, $entityID, $fieldName, $value) = @_;
1953        # Parse the entity name and the real field name.
1954        if ($fieldName =~ /^([^(]+)\(([^)]+)\)/) {
1955            my $entityName = $1;
1956            my $fieldTitle = $2;
1957            # Get its descriptor.
1958            if (!$self->IsEntity($entityName)) {
1959                Confess("$entityName is not a valid entity.");
1960            } else {
1961                my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1962                # Find the relation containing this field.
1963                my $fieldHash = $entityData->{Fields};
1964                if (! exists $fieldHash->{$fieldTitle}) {
1965                    Confess("$fieldTitle not found in $entityName.");
1966                } else {
1967                    my $relation = $fieldHash->{$fieldTitle}->{relation};
1968                    if ($relation eq $entityName) {
1969                        Confess("Cannot do InsertValue on primary field $fieldTitle of $entityName.");
1970                    } else {
1971                        # Now we can create an INSERT statement.
1972                        my $dbh = $self->{_dbh};
1973                        my $fixedName = _FixName($fieldTitle);
1974                        my $statement = "INSERT INTO $relation (id, $fixedName) VALUES(?, ?)";
1975                        # Execute the command.
1976                        $dbh->SQL($statement, 0, $entityID, $value);
1977                    }
1978                }
1979            }
1980        } else {
1981            Confess("$fieldName is not a valid field name.");
1982        }
1983    }
1984    
1985  =head3 InsertObject  =head3 InsertObject
1986    
1987  C<< my $ok = $database->InsertObject($objectType, \%fieldHash); >>  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>
1988    
1989  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
1990  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 1993 
1993  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
1994  C<ZP_00210270.1> and C<gi|46206278>.  C<ZP_00210270.1> and C<gi|46206278>.
1995    
1996  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']}); >>
1997    
1998  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
1999  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>.
2000    
2001  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'}); >>
2002    
2003  =over 4  =over 4
2004    
# Line 1250  Line 2123 
2123    
2124  =head3 LoadTable  =head3 LoadTable
2125    
2126  C<< my %results = $database->LoadTable($fileName, $relationName, $truncateFlag); >>  C<< my %results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>
2127    
2128  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
2129  first.  first.
# Line 1271  Line 2144 
2144    
2145  =item RETURN  =item RETURN
2146    
2147  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.  
2148    
2149  =back  =back
2150    
# Line 1286  Line 2158 
2158      Trace("Loading table $relationName from $fileName") if T(2);      Trace("Loading table $relationName from $fileName") if T(2);
2159      # Get the database handle.      # Get the database handle.
2160      my $dbh = $self->{_dbh};      my $dbh = $self->{_dbh};
2161        # Get the input file size.
2162        my $fileSize = -s $fileName;
2163      # Get the relation data.      # Get the relation data.
2164      my $relation = $self->_FindRelation($relationName);      my $relation = $self->_FindRelation($relationName);
2165      # Check the truncation flag.      # Check the truncation flag.
2166      if ($truncateFlag) {      if ($truncateFlag) {
2167          Trace("Creating table $relationName") if T(2);          Trace("Creating table $relationName") if T(2);
2168            # Compute the row count estimate. We take the size of the load file,
2169            # divide it by the estimated row size, and then multiply by 1.5 to
2170            # leave extra room. We postulate a minimum row count of 1000 to
2171            # prevent problems with incoming empty load files.
2172            my $rowSize = $self->EstimateRowSize($relationName);
2173            my $estimate = FIG::max($fileSize * 1.5 / $rowSize, 1000);
2174          # Re-create the table without its index.          # Re-create the table without its index.
2175          $self->CreateTable($relationName, 0);          $self->CreateTable($relationName, 0, $estimate);
2176          # If this is a pre-index DBMS, create the index here.          # If this is a pre-index DBMS, create the index here.
2177          if ($dbh->{_preIndex}) {          if ($dbh->{_preIndex}) {
2178              eval {              eval {
# Line 1303  Line 2183 
2183              }              }
2184          }          }
2185      }      }
     # 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);  
2186      # Load the table.      # Load the table.
2187      my $rv;      my $rv;
2188      eval {      eval {
2189          $rv = $dbh->load_table(file => $tempName, tbl => $relationName);          $rv = $dbh->load_table(file => $fileName, tbl => $relationName);
2190      };      };
2191      if (!defined $rv) {      if (!defined $rv) {
2192          $retVal->AddMessage($@) if ($@);          $retVal->AddMessage($@) if ($@);
2193          $retVal->AddMessage("Table load failed for $relationName using $tempName.");          $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2194          Trace("Table load failed for $relationName.") if T(1);          Trace("Table load failed for $relationName.") if T(1);
2195      } else {      } else {
2196          # Here we successfully loaded the table. Trace the number of records loaded.          # Here we successfully loaded the table.
2197          Trace("$retVal->{records} records read for $relationName.") if T(2);          $retVal->Add("tables");
2198            my $size = -s $fileName;
2199            Trace("$size bytes loaded into $relationName.") if T(2);
2200          # If we're rebuilding, we need to create the table indexes.          # If we're rebuilding, we need to create the table indexes.
2201          if ($truncateFlag && ! $dbh->{_preIndex}) {          if ($truncateFlag) {
2202                # Indexes are created here for PostGres. For PostGres, indexes are
2203                # best built at the end. For MySQL, the reverse is true.
2204                if (! $dbh->{_preIndex}) {
2205              eval {              eval {
2206                  $self->CreateIndex($relationName);                  $self->CreateIndex($relationName);
2207              };              };
# Line 1379  Line 2209 
2209                  $retVal->AddMessage($@);                  $retVal->AddMessage($@);
2210              }              }
2211          }          }
2212                # The full-text index (if any) is always built last, even for MySQL.
2213                # First we need to see if this table has a full-text index. Only
2214                # primary relations are allowed that privilege.
2215                if ($self->_IsPrimary($relationName)) {
2216                    # Get the relation's entity/relationship structure.
2217                    my $structure = $self->_GetStructure($relationName);
2218                    # Check for a searchable fields list.
2219                    if (exists $structure->{searchFields}) {
2220                        # Here we know that we need to create a full-text search index.
2221                        # Get an SQL-formatted field name list.
2222                        my $fields = join(", ", $self->_FixNames(@{$structure->{searchFields}}));
2223                        # Create the index.
2224                        $dbh->create_index(tbl => $relationName, idx => "search_idx_$relationName",
2225                                           flds => $fields, kind => 'fulltext');
2226                    }
2227                }
2228            }
2229      }      }
2230      # Commit the database changes.      # Analyze the table to improve performance.
2231      $dbh->commit_tran;      Trace("Analyzing and compacting $relationName.") if T(3);
2232      # Delete the temporary file.      $dbh->vacuum_it($relationName);
2233      unlink $tempName;      Trace("$relationName load completed.") if T(3);
2234      # Return the statistics.      # Return the statistics.
2235      return $retVal;      return $retVal;
2236  }  }
2237    
2238  =head3 GenerateEntity  =head3 DropRelation
2239    
2240  C<< my $fieldHash = $database->GenerateEntity($id, $type, \%values); >>  C<< $erdb->DropRelation($relationName); >>
2241    
2242  Generate the data for a new entity instance. This method creates a field hash suitable for  Physically drop a relation from the database.
 passing as a parameter to L</InsertObject>. The ID is specified by the callr, but the rest  
 of the fields are generated using information in the database schema.  
   
 Each data type has a default algorithm for generating random test data. This can be overridden  
 by including a B<DataGen> element in the field. If this happens, the content of the element is  
 executed as a PERL program in the context of this module. The element may make use of a C<$this>  
 variable which contains the field hash as it has been built up to the current point. If any  
 fields are dependent on other fields, the C<pass> attribute can be used to control the order  
 in which the fields are generated. A field with a high data pass number will be generated after  
 a field with a lower one. If any external values are needed, they should be passed in via the  
 optional third parameter, which will be available to the data generation script under the name  
 C<$value>. Several useful utility methods are provided for generating random values, including  
 L</IntGen>, L</StringGen>, L</FloatGen>, and L</DateGen>. Note that dates are stored and generated  
 in the form of a timestamp number rather than a string.  
2243    
2244  =over 4  =over 4
2245    
2246  =item id  =item relationName
   
 ID to assign to the new entity.  
2247    
2248  =item type  Name of the relation to drop. If it does not exist, this method will have
2249    no effect.
2250    
2251  Type name for the new entity.  =back
2252    
2253  =item values  =cut
2254    
2255  Hash containing additional values that might be needed by the data generation methods (optional).  sub DropRelation {
   
 =back  
   
 =cut  
   
 sub GenerateEntity {  
2256      # Get the parameters.      # Get the parameters.
2257      my ($self, $id, $type, $values) = @_;      my ($self, $relationName) = @_;
2258      # Create the return hash.      # Get the database handle.
2259      my $this = { id => $id };      my $dbh = $self->{_dbh};
2260      # Get the metadata structure.      # Drop the relation. The method used here has no effect if the relation
2261      my $metadata = $self->{_metaData};      # does not exist.
2262      # Get this entity's list of fields.      Trace("Invoking DB Kernel to drop $relationName.") if T(3);
2263      if (!exists $metadata->{Entities}->{$type}) {      $dbh->drop_table(tbl => $relationName);
         Confess("Unrecognized entity type $type in GenerateEntity.");  
     } else {  
         my $entity = $metadata->{Entities}->{$type};  
         my $fields = $entity->{Fields};  
         # Generate data from the fields.  
         _GenerateFields($this, $fields, $type, $values);  
     }  
     # Return the hash created.  
     return $this;  
2264  }  }
2265    
2266  =head3 GetEntity  =head3 GetEntity
2267    
2268  C<< my $entityObject = $sprout->GetEntity($entityType, $ID); >>  C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>
2269    
2270  Return an object describing the entity instance with a specified ID.  Return an object describing the entity instance with a specified ID.
2271    
# Line 1475  Line 2292 
2292      # Get the parameters.      # Get the parameters.
2293      my ($self, $entityType, $ID) = @_;      my ($self, $entityType, $ID) = @_;
2294      # Create a query.      # Create a query.
2295      my $query = $self->Get([$entityType], "$entityType(id) = ?", $ID);      my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);
2296      # Get the first (and only) object.      # Get the first (and only) object.
2297      my $retVal = $query->Fetch();      my $retVal = $query->Fetch();
2298      # Return the result.      # Return the result.
2299      return $retVal;      return $retVal;
2300  }  }
2301    
2302    =head3 GetChoices
2303    
2304    C<< my @values = $erdb->GetChoices($entityName, $fieldName); >>
2305    
2306    Return a list of all the values for the specified field that are represented in the
2307    specified entity.
2308    
2309    Note that if the field is not indexed, then this will be a very slow operation.
2310    
2311    =over 4
2312    
2313    =item entityName
2314    
2315    Name of an entity in the database.
2316    
2317    =item fieldName
2318    
2319    Name of a field belonging to the entity. This is a raw field name without
2320    the standard parenthesized notation used in most calls.
2321    
2322    =item RETURN
2323    
2324    Returns a list of the distinct values for the specified field in the database.
2325    
2326    =back
2327    
2328    =cut
2329    
2330    sub GetChoices {
2331        # Get the parameters.
2332        my ($self, $entityName, $fieldName) = @_;
2333        # Declare the return variable.
2334        my @retVal;
2335        # Get the entity data structure.
2336        my $entityData = $self->_GetStructure($entityName);
2337        # Get the field.
2338        my $fieldHash = $entityData->{Fields};
2339        if (! exists $fieldHash->{$fieldName}) {
2340            Confess("$fieldName not found in $entityName.");
2341        } else {
2342            # Get the name of the relation containing the field.
2343            my $relation = $fieldHash->{$fieldName}->{relation};
2344            # Fix up the field name.
2345            my $realName = _FixName($fieldName);
2346            # Get the database handle.
2347            my $dbh = $self->{_dbh};
2348            # Query the database.
2349            my $results = $dbh->SQL("SELECT DISTINCT $realName FROM $relation");
2350            # Clean the results. They are stored as a list of lists, and we just want the one list.
2351            @retVal = sort map { $_->[0] } @{$results};
2352        }
2353        # Return the result.
2354        return @retVal;
2355    }
2356    
2357  =head3 GetEntityValues  =head3 GetEntityValues
2358    
2359  C<< my @values = GetEntityValues($entityType, $ID, \@fields); >>  C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>
2360    
2361  Return a list of values from a specified entity instance.  Return a list of values from a specified entity instance. If the entity instance
2362    does not exist, an empty list is returned.
2363    
2364  =over 4  =over 4
2365    
# Line 1527  Line 2400 
2400    
2401  =head3 GetAll  =head3 GetAll
2402    
2403  C<< my @list = $sprout->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>  C<< my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>
2404    
2405  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
2406  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 2416 
2416  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
2417  feature ID followed by all of its aliases.  feature ID followed by all of its aliases.
2418    
2419  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)']); >>
2420    
2421  =over 4  =over 4
2422    
# Line 1588  Line 2461 
2461      # list is a scalar we convert it into a singleton list.      # list is a scalar we convert it into a singleton list.
2462      my @parmList = ();      my @parmList = ();
2463      if (ref $parameterList eq "ARRAY") {      if (ref $parameterList eq "ARRAY") {
2464            Trace("GetAll parm list is an array.") if T(4);
2465          @parmList = @{$parameterList};          @parmList = @{$parameterList};
2466      } else {      } else {
2467            Trace("GetAll parm list is a scalar: $parameterList.") if T(4);
2468          push @parmList, $parameterList;          push @parmList, $parameterList;
2469      }      }
     # Create the query.  
     my $query = $self->Get($objectNames, $filterClause, @parmList);  
     # Set up a counter of the number of records read.  
     my $fetched = 0;  
2470      # Insure the counter has a value.      # Insure the counter has a value.
2471      if (!defined $count) {      if (!defined $count) {
2472          $count = 0;          $count = 0;
2473      }      }
2474        # Add the row limit to the filter clause.
2475        if ($count > 0) {
2476            $filterClause .= " LIMIT $count";
2477        }
2478        # Create the query.
2479        my $query = $self->Get($objectNames, $filterClause, \@parmList);
2480        # Set up a counter of the number of records read.
2481        my $fetched = 0;
2482      # Loop through the records returned, extracting the fields. Note that if the      # Loop through the records returned, extracting the fields. Note that if the
2483      # 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.
2484      my @retVal = ();      my @retVal = ();
# Line 1608  Line 2487 
2487          push @retVal, \@rowData;          push @retVal, \@rowData;
2488          $fetched++;          $fetched++;
2489      }      }
2490        Trace("$fetched rows returned in GetAll.") if T(SQL => 4);
2491      # Return the resulting list.      # Return the resulting list.
2492      return @retVal;      return @retVal;
2493  }  }
2494    
2495  =head2 Internal Utility Methods  =head3 Exists
2496    
2497  =head3 GetLoadStats  C<< my $found = $sprout->Exists($entityName, $entityID); >>
2498    
2499  Return a blank statistics object for use by the load methods.  Return TRUE if an entity exists, else FALSE.
2500    
2501  This is a static method.  =over 4
2502    
2503    =item entityName
2504    
2505    Name of the entity type (e.g. C<Feature>) relevant to the existence check.
2506    
2507    =item entityID
2508    
2509    ID of the entity instance whose existence is to be checked.
2510    
2511    =item RETURN
2512    
2513    Returns TRUE if the entity instance exists, else FALSE.
2514    
2515    =back
2516    
2517  =cut  =cut
2518    #: Return Type $;
2519    sub Exists {
2520        # Get the parameters.
2521        my ($self, $entityName, $entityID) = @_;
2522        # Check for the entity instance.
2523        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
2524        my $testInstance = $self->GetEntity($entityName, $entityID);
2525        # Return an existence indicator.
2526        my $retVal = ($testInstance ? 1 : 0);
2527        return $retVal;
2528    }
2529    
2530  sub _GetLoadStats {  =head3 EstimateRowSize
2531      return Stats->new('records');  
2532    C<< my $rowSize = $erdb->EstimateRowSize($relName); >>
2533    
2534    Estimate the row size of the specified relation. The estimated row size is computed by adding
2535    up the average length for each data type.
2536    
2537    =over 4
2538    
2539    =item relName
2540    
2541    Name of the relation whose estimated row size is desired.
2542    
2543    =item RETURN
2544    
2545    Returns an estimate of the row size for the specified relation.
2546    
2547    =back
2548    
2549    =cut
2550    #: Return Type $;
2551    sub EstimateRowSize {
2552        # Get the parameters.
2553        my ($self, $relName) = @_;
2554        # Declare the return variable.
2555        my $retVal = 0;
2556        # Find the relation descriptor.
2557        my $relation = $self->_FindRelation($relName);
2558        # Get the list of fields.
2559        for my $fieldData (@{$relation->{Fields}}) {
2560            # Get the field type and add its length.
2561            my $fieldLen = $TypeTable{$fieldData->{type}}->{avgLen};
2562            $retVal += $fieldLen;
2563        }
2564        # Return the result.
2565        return $retVal;
2566  }  }
2567    
2568  =head3 GenerateFields  =head3 GetFieldTable
2569    
2570  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.  
2571    
2572  This is a static method.  Get the field structure for a specified entity or relationship.
2573    
2574  =over 4  =over 4
2575    
2576  =item this  =item objectName
2577    
2578  Hash table into which the field values should be placed.  Name of the desired entity or relationship.
2579    
2580  =item fields  =item RETURN
2581    
2582  Field structure from which the field descriptors should be taken.  The table containing the field descriptors for the specified object.
2583    
2584  =item type  =back
2585    
2586    =cut
2587    
2588    sub GetFieldTable {
2589        # Get the parameters.
2590        my ($self, $objectName) = @_;
2591        # Get the descriptor from the metadata.
2592        my $objectData = $self->_GetStructure($objectName);
2593        # Return the object's field table.
2594        return $objectData->{Fields};
2595    }
2596    
2597    =head3 SplitKeywords
2598    
2599    C<< my @keywords = ERDB::SplitKeywords($keywordString); >>
2600    
2601    This method returns a list of the positive keywords in the specified
2602    keyword string. All of the operators will have been stripped off,
2603    and if the keyword is preceded by a minus operator (C<->), it will
2604    not be in the list returned. The idea here is to get a list of the
2605    keywords the user wants to see. The list will be processed to remove
2606    duplicates.
2607    
2608    It is possible to create a string that confuses this method. For example
2609    
2610        frog toad -frog
2611    
2612    would return both C<frog> and C<toad>. If this is a problem we can deal
2613    with it later.
2614    
2615    =over 4
2616    
2617    =item keywordString
2618    
2619    The keyword string to be parsed.
2620    
2621    =item RETURN
2622    
2623    Returns a list of the words in the keyword string the user wants to
2624    see.
2625    
2626    =back
2627    
2628    =cut
2629    
2630    sub SplitKeywords {
2631        # Get the parameters.
2632        my ($keywordString) = @_;
2633        # Make a safety copy of the string. (This helps during debugging.)
2634        my $workString = $keywordString;
2635        # Convert operators we don't care about to spaces.
2636        $workString =~ tr/+"()<>/ /;
2637        # Split the rest of the string along space boundaries. Note that we
2638        # eliminate any words that are zero length or begin with a minus sign.
2639        my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
2640        # Use a hash to remove duplicates.
2641        my %words = map { $_ => 1 } @wordList;
2642        # Return the result.
2643        return sort keys %words;
2644    }
2645    
2646  Type name of the object whose fields are being generated.  =head3 ValidateFieldName
2647    
2648  =item values (optional)  C<< my $okFlag = ERDB::ValidateFieldName($fieldName); >>
2649    
2650  Reference to a value structure from which additional values can be taken.  Return TRUE if the specified field name is valid, else FALSE. Valid field names must
2651    be hyphenated words subject to certain restrictions.
2652    
2653  =item from (optiona)  =over 4
2654    
2655    =item fieldName
2656    
2657  Reference to the source entity instance if relationship data is being generated.  Field name to be validated.
2658    
2659  =item to (optional)  =item RETURN
2660    
2661  Reference to the target entity instance if relationship data is being generated.  Returns TRUE if the field name is valid, else FALSE.
2662    
2663  =back  =back
2664    
2665  =cut  =cut
2666    
2667  sub _GenerateFields {  sub ValidateFieldName {
2668      # Get the parameters.      # Get the parameters.
2669      my ($this, $fields, $type, $values, $from, $to) = @_;      my ($fieldName) = @_;
2670      # Sort the field names by pass number.      # Declare the return variable. The field name is valid until we hear
2671      my @fieldNames = sort { $fields->{$a}->{DataGen}->{pass} <=> $fields->{$b}->{DataGen}->{pass} } keys %{$fields};      # differently.
2672      # Loop through the field names, generating data.      my $retVal = 1;
2673      for my $name (@fieldNames) {      # Look for bad stuff in the name.
2674          # Only proceed if this field needs to be generated.      if ($fieldName =~ /--/) {
2675          if (!exists $this->{$name}) {          # Here we have a doubled minus sign.
2676              # Get this field's data generation descriptor.          Trace("Field name $fieldName has a doubled hyphen.") if T(1);
2677              my $fieldDescriptor = $fields->{$name};          $retVal = 0;
2678              my $data = $fieldDescriptor->{DataGen};      } elsif ($fieldName !~ /^[A-Za-z]/) {
2679              # Get the code to generate the field value.          # Here the field name is missing the initial letter.
2680              my $codeString = $data->{content};          Trace("Field name $fieldName does not begin with a letter.") if T(1);
2681              # Determine whether or not this field is in the primary relation.          $retVal = 0;
             if ($fieldDescriptor->{relation} eq $type) {  
                 # Here we have a primary relation field. Store the field value as  
                 # a scalar.  
                 $this->{$name} = eval($codeString);  
2682              } else {              } else {
2683                  # Here we have a secondary relation field. Create a null list          # Strip out the minus signs. Everything remaining must be a letter
2684                  # and push the desired number of field values onto it.          # or digit.
2685                  my @fieldValues = ();          my $strippedName = $fieldName;
2686                  my $count = IntGen(0,$data->{testCount});          $strippedName =~ s/-//g;
2687                  for (my $i = 0; $i < $count; $i++) {          if ($strippedName !~ /^[A-Za-z0-9]+$/) {
2688                      my $newValue = eval($codeString);              Trace("Field name $fieldName contains illegal characters.") if T(1);
2689                      push @fieldValues, $newValue;              $retVal = 0;
2690                  }                  }
                 # Store the value list in the main hash.  
                 $this->{$name} = \@fieldValues;  
2691              }              }
2692        # Return the result.
2693        return $retVal;
2694    }
2695    
2696    =head3 ReadMetaXML
2697    
2698    C<< my $rawMetaData = ERDB::ReadDBD($fileName); >>
2699    
2700    This method reads a raw database definition XML file and returns it.
2701    Normally, the metadata used by the ERDB system has been processed and
2702    modified to make it easier to load and retrieve the data; however,
2703    this method can be used to get the data in its raw form.
2704    
2705    =over 4
2706    
2707    =item fileName
2708    
2709    Name of the XML file to read.
2710    
2711    =item RETURN
2712    
2713    Returns a hash reference containing the raw XML data from the specified file.
2714    
2715    =back
2716    
2717    =cut
2718    
2719    sub ReadMetaXML {
2720        # Get the parameters.
2721        my ($fileName) = @_;
2722        # Read the XML.
2723        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
2724        Trace("XML metadata loaded from file $fileName.") if T(1);
2725        # Return the result.
2726        return $retVal;
2727          }          }
2728    
2729    =head3 GetEntityFieldHash
2730    
2731    C<< my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName); >>
2732    
2733    Get the field hash of the named entity in the specified raw XML structure.
2734    The field hash may not exist, in which case we need to create it.
2735    
2736    =over 4
2737    
2738    =item structure
2739    
2740    Raw XML structure defininng the database. This is not the run-time XML used by
2741    an ERDB object, since that has all sorts of optimizations built-in.
2742    
2743    =item entityName
2744    
2745    Name of the entity whose field structure is desired.
2746    
2747    =item RETURN
2748    
2749    Returns the field hash used to define the entity's fields.
2750    
2751    =back
2752    
2753    =cut
2754    
2755    sub GetEntityFieldHash {
2756        # Get the parameters.
2757        my ($structure, $entityName) = @_;
2758        # Get the entity structure.
2759        my $entityData = $structure->{Entities}->{$entityName};
2760        # Look for a field structure.
2761        my $retVal = $entityData->{Fields};
2762        # If it doesn't exist, create it.
2763        if (! defined($retVal)) {
2764            $entityData->{Fields} = {};
2765            $retVal = $entityData->{Fields};
2766      }      }
2767        # Return the result.
2768        return $retVal;
2769  }  }
2770    
2771  =head3 DumpRelation  =head3 WriteMetaXML
2772    
2773    C<< ERDB::WriteMetaXML($structure, $fileName); >>
2774    
2775  Dump the specified relation's to the specified output file in tab-delimited format.  Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
2776    used to update the database definition. It must be used with care, however, since it
2777    will only work on a raw structure, not on the processed structure created by an ERDB
2778    constructor.
2779    
2780    =over 4
2781    
2782    =item structure
2783    
2784    XML structure to be written to the file.
2785    
2786    =item fileName
2787    
2788    Name of the output file to which the updated XML should be stored.
2789    
2790    =back
2791    
2792    =cut
2793    
2794    sub WriteMetaXML {
2795        # Get the parameters.
2796        my ($structure, $fileName) = @_;
2797        # Compute the output.
2798        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
2799        # Write it to the file.
2800        my $xmlOut = Open(undef, ">$fileName");
2801        print $xmlOut $fileString;
2802    }
2803    
2804    
2805    =head3 HTMLNote
2806    
2807    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
2808    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
2809    Except for C<[p]>, all the codes are closed by slash-codes. So, for
2810    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
2811    
2812    C<< my $realHtml = ERDB::HTMLNote($dataString); >>
2813    
2814    =over 4
2815    
2816    =item dataString
2817    
2818    String to convert to HTML.
2819    
2820    =item RETURN
2821    
2822    An HTML string derived from the input string.
2823    
2824    =back
2825    
2826    =cut
2827    
2828    sub HTMLNote {
2829        # Get the parameter.
2830        my ($dataString) = @_;
2831        # HTML-escape the text.
2832        my $retVal = CGI::escapeHTML($dataString);
2833        # Substitute the bulletin board codes.
2834        $retVal =~ s!\[(/?[bi])\]!<$1>!g;
2835        $retVal =~ s!\[p\]!</p><p>!g;
2836        # Return the result.
2837        return $retVal;
2838    }
2839    
2840    
2841    =head2 Data Mining Methods
2842    
2843    =head3 GetUsefulCrossValues
2844    
2845    C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>
2846    
2847    Return a list of the useful attributes that would be returned by a B<Cross> call
2848    from an entity of the source entity type through the specified relationship. This
2849    means it will return the fields of the target entity type and the intersection data
2850    fields in the relationship. Only primary table fields are returned. In other words,
2851    the field names returned will be for fields where there is always one and only one
2852    value.
2853    
2854    =over 4
2855    
2856    =item sourceEntity
2857    
2858    Name of the entity from which the relationship crossing will start.
2859    
2860    =item relationship
2861    
2862    Name of the relationship being crossed.
2863    
2864    =item RETURN
2865    
2866    Returns a list of field names in Sprout field format (I<objectName>C<(>I<fieldName>C<)>.
2867    
2868    =back
2869    
2870    =cut
2871    #: Return Type @;
2872    sub GetUsefulCrossValues {
2873        # Get the parameters.
2874        my ($self, $sourceEntity, $relationship) = @_;
2875        # Declare the return variable.
2876        my @retVal = ();
2877        # Determine the target entity for the relationship. This is whichever entity is not
2878        # the source entity. So, if the source entity is the FROM, we'll get the name of
2879        # the TO, and vice versa.
2880        my $relStructure = $self->_GetStructure($relationship);
2881        my $targetEntityType = ($relStructure->{from} eq $sourceEntity ? "to" : "from");
2882        my $targetEntity = $relStructure->{$targetEntityType};
2883        # Get the field table for the entity.
2884        my $entityFields = $self->GetFieldTable($targetEntity);
2885        # The field table is a hash. The hash key is the field name. The hash value is a structure.
2886        # For the entity fields, the key aspect of the target structure is that the {relation} value
2887        # must match the entity name.
2888        my @fieldList = map { "$targetEntity($_)" } grep { $entityFields->{$_}->{relation} eq $targetEntity }
2889                            keys %{$entityFields};
2890        # Push the fields found onto the return variable.
2891        push @retVal, sort @fieldList;
2892        # Get the field table for the relationship.
2893        my $relationshipFields = $self->GetFieldTable($relationship);
2894        # Here we have a different rule. We want all the fields other than "from-link" and "to-link".
2895        # This may end up being an empty set.
2896        my @fieldList2 = map { "$relationship($_)" } grep { $_ ne "from-link" && $_ ne "to-link" }
2897                            keys %{$relationshipFields};
2898        # Push these onto the return list.
2899        push @retVal, sort @fieldList2;
2900        # Return the result.
2901        return @retVal;
2902    }
2903    
2904    =head3 FindColumn
2905    
2906    C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>
2907    
2908    Return the location a desired column in a data mining header line. The data
2909    mining header line is a tab-separated list of column names. The column
2910    identifier is either the numerical index of a column or the actual column
2911    name.
2912    
2913    =over 4
2914    
2915    =item headerLine
2916    
2917    The header line from a data mining command, which consists of a tab-separated
2918    list of column names.
2919    
2920    =item columnIdentifier
2921    
2922    Either the ordinal number of the desired column (1-based), or the name of the
2923    desired column.
2924    
2925    =item RETURN
2926    
2927    Returns the array index (0-based) of the desired column.
2928    
2929    =back
2930    
2931    =cut
2932    
2933    sub FindColumn {
2934        # Get the parameters.
2935        my ($headerLine, $columnIdentifier) = @_;
2936        # Declare the return variable.
2937        my $retVal;
2938        # Split the header line into column names.
2939        my @headers = ParseColumns($headerLine);
2940        # Determine whether we have a number or a name.
2941        if ($columnIdentifier =~ /^\d+$/) {
2942            # Here we have a number. Subtract 1 and validate the result.
2943            $retVal = $columnIdentifier - 1;
2944            if ($retVal < 0 || $retVal > $#headers) {
2945                Confess("Invalid column identifer \"$columnIdentifier\": value out of range.");
2946            }
2947        } else {
2948            # Here we have a name. We need to find it in the list.
2949            for (my $i = 0; $i <= $#headers && ! defined($retVal); $i++) {
2950                if ($headers[$i] eq $columnIdentifier) {
2951                    $retVal = $i;
2952                }
2953            }
2954            if (! defined($retVal)) {
2955                Confess("Invalid column identifier \"$columnIdentifier\": value not found.");
2956            }
2957        }
2958        # Return the result.
2959        return $retVal;
2960    }
2961    
2962    =head3 ParseColumns
2963    
2964    C<< my @columns = ERDB::ParseColumns($line); >>
2965    
2966    Convert the specified data line to a list of columns.
2967    
2968    =over 4
2969    
2970    =item line
2971    
2972    A data mining input, consisting of a tab-separated list of columns terminated by a
2973    new-line.
2974    
2975    =item RETURN
2976    
2977    Returns a list consisting of the column values.
2978    
2979    =back
2980    
2981    =cut
2982    
2983    sub ParseColumns {
2984        # Get the parameters.
2985        my ($line) = @_;
2986        # Chop off the line-end.
2987        chomp $line;
2988        # Split it into a list.
2989        my @retVal = split(/\t/, $line);
2990        # Return the result.
2991        return @retVal;
2992    }
2993    
2994    =head2 Virtual Methods
2995    
2996    =head3 CleanKeywords
2997    
2998    C<< my $cleanedString = $erdb->CleanKeywords($searchExpression); >>
2999    
3000    Clean up a search expression or keyword list. This is a virtual method that may
3001    be overridden by the subclass. The base-class method removes extra spaces
3002    and converts everything to lower case.
3003    
3004    =over 4
3005    
3006    =item searchExpression
3007    
3008    Search expression or keyword list to clean. Note that a search expression may
3009    contain boolean operators which need to be preserved. This includes leading
3010    minus signs.
3011    
3012    =item RETURN
3013    
3014    Cleaned expression or keyword list.
3015    
3016    =back
3017    
3018    =cut
3019    
3020    sub CleanKeywords {
3021        # Get the parameters.
3022        my ($self, $searchExpression) = @_;
3023        # Lower-case the expression and copy it into the return variable. Note that we insure we
3024        # don't accidentally end up with an undefined value.
3025        my $retVal = lc($searchExpression || "");
3026        # Remove extra spaces.
3027        $retVal =~ s/\s+/ /g;
3028        $retVal =~ s/(^\s+)|(\s+$)//g;
3029        # Return the result.
3030        return $retVal;
3031    }
3032    
3033    =head3 GetSourceObject
3034    
3035    C<< my $source = $erdb->GetSourceObject($entityName); >>
3036    
3037    Return the object to be used in loading special attributes of the specified entity. The
3038    algorithm for loading special attributes is stored in the C<DataGen> elements of the
3039    XML
3040    
3041    =head2 Internal Utility Methods
3042    
3043    =head3 _RelationMap
3044    
3045    C<< my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef); >>
3046    
3047    Create the relation map for an SQL query. The relation map is used by B<DBObject>
3048    to determine how to interpret the results of the query.
3049    
3050    =over 4
3051    
3052    =item mappedNameHashRef
3053    
3054    Reference to a hash that maps modified object names to real object names.
3055    
3056    =item mappedNameListRef
3057    
3058    Reference to a list of modified object names in the order they appear in the
3059    SELECT list.
3060    
3061    =item RETURN
3062    
3063    Returns a list of 2-tuples. Each tuple consists of an object name as used in the
3064    query followed by the actual name of that object. This enables the B<DBObject> to
3065    determine the order of the tables in the query and which object name belongs to each
3066    mapped object name. Most of the time these two values are the same; however, if a
3067    relation occurs twice in the query, the relation name in the field list and WHERE
3068    clause will use a mapped name (generally the actual relation name with a numeric
3069    suffix) that does not match the actual relation name.
3070    
3071    =back
3072    
3073    =cut
3074    
3075    sub _RelationMap {
3076        # Get the parameters.
3077        my ($mappedNameHashRef, $mappedNameListRef) = @_;
3078        # Declare the return variable.
3079        my @retVal = ();
3080        # Build the map.
3081        for my $mappedName (@{$mappedNameListRef}) {
3082            push @retVal, [$mappedName, $mappedNameHashRef->{$mappedName}];
3083        }
3084        # Return it.
3085        return @retVal;
3086    }
3087    
3088    
3089    =head3 _SetupSQL
3090    
3091    Process a list of object names and a filter clause so that they can be used to
3092    build an SQL statement. This method takes in a reference to a list of object names
3093    and a filter clause. It will return a corrected filter clause, a list of mapped
3094    names and the mapped name hash.
3095    
3096    This is an instance method.
3097    
3098    =over 4
3099    
3100    =item objectNames
3101    
3102    Reference to a list of the object names to be included in the query.
3103    
3104    =item filterClause
3105    
3106    A string containing the WHERE clause for the query (without the C<WHERE>) and also
3107    optionally the C<ORDER BY> and C<LIMIT> clauses.
3108    
3109    =item matchClause
3110    
3111    An optional full-text search clause. If specified, it will be inserted at the
3112    front of the WHERE clause. It should already be SQL-formatted; that is, the
3113    field names should be in the form I<table>C<.>I<fieldName>.
3114    
3115    =item RETURN
3116    
3117    Returns a three-element list. The first element is the SQL statement suffix, beginning
3118    with the FROM clause. The second element is a reference to a list of the names to be
3119    used in retrieving the fields. The third element is a hash mapping the names to the
3120    objects they represent.
3121    
3122    =back
3123    
3124    =cut
3125    
3126    sub _SetupSQL {
3127        my ($self, $objectNames, $filterClause, $matchClause) = @_;
3128        # Adjust the list of object names to account for multiple occurrences of the
3129        # same object. We start with a hash table keyed on object name that will
3130        # return the object suffix. The first time an object is encountered it will
3131        # not be found in the hash. The next time the hash will map the object name
3132        # to 2, then 3, and so forth.
3133        my %objectHash = ();
3134        # This list will contain the object names as they are to appear in the
3135        # FROM list.
3136        my @fromList = ();
3137        # This list contains the suffixed object name for each object. It is exactly
3138        # parallel to the list in the $objectNames parameter.
3139        my @mappedNameList = ();
3140        # Finally, this hash translates from a mapped name to its original object name.
3141        my %mappedNameHash = ();
3142        # Now we create the lists. Note that for every single name we push something into
3143        # @fromList and @mappedNameList. This insures that those two arrays are exactly
3144        # parallel to $objectNames.
3145        for my $objectName (@{$objectNames}) {
3146            # Get the next suffix for this object.
3147            my $suffix = $objectHash{$objectName};
3148            if (! $suffix) {
3149                # Here we are seeing the object for the first time. The object name
3150                # is used as is.
3151                push @mappedNameList, $objectName;
3152                push @fromList, $objectName;
3153                $mappedNameHash{$objectName} = $objectName;
3154                # Denote the next suffix will be 2.
3155                $objectHash{$objectName} = 2;
3156            } else {
3157                # Here we've seen the object before. We construct a new name using
3158                # the suffix from the hash and update the hash.
3159                my $mappedName = "$objectName$suffix";
3160                $objectHash{$objectName} = $suffix + 1;
3161                # The FROM list has the object name followed by the mapped name. This
3162                # tells SQL it's still the same table, but we're using a different name
3163                # for it to avoid confusion.
3164                push @fromList, "$objectName $mappedName";
3165                # The mapped-name list contains the real mapped name.
3166                push @mappedNameList, $mappedName;
3167                # Finally, enable us to get back from the mapped name to the object name.
3168                $mappedNameHash{$mappedName} = $objectName;
3169            }
3170        }
3171        # Begin the SELECT suffix. It starts with
3172        #
3173        # FROM name1, name2, ... nameN
3174        #
3175        my $suffix = "FROM " . join(', ', @fromList);
3176        # Now for the WHERE. First, we need a place for the filter string.
3177        my $filterString = "";
3178        # We will also keep a list of conditions to add to the WHERE clause in order to link
3179        # entities and relationships as well as primary relations to secondary ones.
3180        my @joinWhere = ();
3181        # Check for a filter clause.
3182        if ($filterClause) {
3183            # Here we have one, so we convert its field names and add it to the query. First,
3184            # We create a copy of the filter string we can work with.
3185            $filterString = $filterClause;
3186            # Next, we sort the object names by length. This helps protect us from finding
3187            # object names inside other object names when we're doing our search and replace.
3188            my @sortedNames = sort { length($b) - length($a) } @mappedNameList;
3189            # The final preparatory step is to create a hash table of relation names. The
3190            # table begins with the relation names already in the SELECT command. We may
3191            # need to add relations later if there is filtering on a field in a secondary
3192            # relation. The secondary relations are the ones that contain multiply-
3193            # occurring or optional fields.
3194            my %fromNames = map { $_ => 1 } @sortedNames;
3195            # We are ready to begin. We loop through the object names, replacing each
3196            # object name's field references by the corresponding SQL field reference.
3197            # Along the way, if we find a secondary relation, we will need to add it
3198            # to the FROM clause.
3199            for my $mappedName (@sortedNames) {
3200                # Get the length of the object name plus 2. This is the value we add to the
3201                # size of the field name to determine the size of the field reference as a
3202                # whole.
3203                my $nameLength = 2 + length $mappedName;
3204                # Get the real object name for this mapped name.
3205                my $objectName = $mappedNameHash{$mappedName};
3206                Trace("Processing $mappedName for object $objectName.") if T(4);
3207                # Get the object's field list.
3208                my $fieldList = $self->GetFieldTable($objectName);
3209                # Find the field references for this object.
3210                while ($filterString =~ m/$mappedName\(([^)]*)\)/g) {
3211                    # At this point, $1 contains the field name, and the current position
3212                    # is set immediately after the final parenthesis. We pull out the name of
3213                    # the field and the position and length of the field reference as a whole.
3214                    my $fieldName = $1;
3215                    my $len = $nameLength + length $fieldName;
3216                    my $pos = pos($filterString) - $len;
3217                    # Insure the field exists.
3218                    if (!exists $fieldList->{$fieldName}) {
3219                        Confess("Field $fieldName not found for object $objectName.");
3220                    } else {
3221                        Trace("Processing $fieldName at position $pos.") if T(4);
3222                        # Get the field's relation.
3223                        my $relationName = $fieldList->{$fieldName}->{relation};
3224                        # Now we have a secondary relation. We need to insure it matches the
3225                        # mapped name of the primary relation. First we peel off the suffix
3226                        # from the mapped name.
3227                        my $mappingSuffix = substr $mappedName, length($objectName);
3228                        # Put the mapping suffix onto the relation name to get the
3229                        # mapped relation name.
3230                        my $mappedRelationName = "$relationName$mappingSuffix";
3231                        # Insure the relation is in the FROM clause.
3232                        if (!exists $fromNames{$mappedRelationName}) {
3233                            # Add the relation to the FROM clause.
3234                            if ($mappedRelationName eq $relationName) {
3235                                # The name is un-mapped, so we add it without
3236                                # any frills.
3237                                $suffix .= ", $relationName";
3238                                push @joinWhere, "$objectName.id = $relationName.id";
3239                            } else {
3240                                # Here we have a mapping situation.
3241                                $suffix .= ", $relationName $mappedRelationName";
3242                                push @joinWhere, "$mappedRelationName.id = $mappedName.id";
3243                            }
3244                            # Denote we have this relation available for future fields.
3245                            $fromNames{$mappedRelationName} = 1;
3246                        }
3247                        # Form an SQL field reference from the relation name and the field name.
3248                        my $sqlReference = "$mappedRelationName." . _FixName($fieldName);
3249                        # Put it into the filter string in place of the old value.
3250                        substr($filterString, $pos, $len) = $sqlReference;
3251                        # Reposition the search.
3252                        pos $filterString = $pos + length $sqlReference;
3253                    }
3254                }
3255            }
3256        }
3257        # The next step is to join the objects together. We only need to do this if there
3258        # is more than one object in the object list. We start with the first object and
3259        # run through the objects after it. Note also that we make a safety copy of the
3260        # list before running through it, because we shift off the first object before
3261        # processing the rest.
3262        my @mappedObjectList = @mappedNameList;
3263        my $lastMappedObject = shift @mappedObjectList;
3264        # Get the join table.
3265        my $joinTable = $self->{_metaData}->{Joins};
3266        # Loop through the object list.
3267        for my $thisMappedObject (@mappedObjectList) {
3268            # Look for a join using the real object names.
3269            my $lastObject = $mappedNameHash{$lastMappedObject};
3270            my $thisObject = $mappedNameHash{$thisMappedObject};
3271            my $joinKey = "$lastObject/$thisObject";
3272            if (!exists $joinTable->{$joinKey}) {
3273                # Here there's no join, so we throw an error.
3274                Confess("No join exists to connect from $lastMappedObject to $thisMappedObject.");
3275            } else {
3276                # Get the join clause.
3277                my $unMappedJoin = $joinTable->{$joinKey};
3278                # Fix the names.
3279                $unMappedJoin =~ s/$lastObject/$lastMappedObject/;
3280                $unMappedJoin =~ s/$thisObject/$thisMappedObject/;
3281                push @joinWhere, $unMappedJoin;
3282                # Save this object as the last object for the next iteration.
3283                $lastMappedObject = $thisMappedObject;
3284            }
3285        }
3286        # Now we need to handle the whole ORDER BY / LIMIT thing. The important part
3287        # here is we want the filter clause to be empty if there's no WHERE filter.
3288        # We'll put the ORDER BY / LIMIT clauses in the following variable.
3289        my $orderClause = "";
3290        # This is only necessary if we have a filter string in which the ORDER BY
3291        # and LIMIT clauses can live.
3292        if ($filterString) {
3293            # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy
3294            # operator so that we find the first occurrence of either verb.
3295            if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {
3296                # Here we have an ORDER BY or LIMIT verb. Split it off of the filter string.
3297                my $pos = pos $filterString;
3298                $orderClause = $2 . substr($filterString, $pos);
3299                $filterString = $1;
3300            }
3301        }
3302        # All the things that are supposed to be in the WHERE clause of the
3303        # SELECT command need to be put into @joinWhere so we can string them
3304        # together. We begin with the match clause. This is important,
3305        # because the match clause's parameter mark must precede any parameter
3306        # marks in the filter string.
3307        if ($matchClause) {
3308            push @joinWhere, $matchClause;
3309        }
3310        # Add the filter string. We put it in parentheses to avoid operator
3311        # precedence problems with the match clause or the joins.
3312        if ($filterString) {
3313            Trace("Filter string is \"$filterString\".") if T(4);
3314            push @joinWhere, "($filterString)";
3315        }
3316        # String it all together into a big filter clause.
3317        if (@joinWhere) {
3318            $suffix .= " WHERE " . join(' AND ', @joinWhere);
3319        }
3320        # Add the sort or limit clause (if any).
3321        if ($orderClause) {
3322            $suffix .= " $orderClause";
3323        }
3324        # Return the suffix, the mapped name list, and the mapped name hash.
3325        return ($suffix, \@mappedNameList, \%mappedNameHash);
3326    }
3327    
3328    =head3 _GetStatementHandle
3329    
3330    This method will prepare and execute an SQL query, returning the statement handle.
3331    The main reason for doing this here is so that everybody who does SQL queries gets
3332    the benefit of tracing.
3333    
3334    This is an instance method.
3335    
3336    =over 4
3337    
3338    =item command
3339    
3340    Command to prepare and execute.
3341    
3342    =item params
3343    
3344    Reference to a list of the values to be substituted in for the parameter marks.
3345    
3346    =item RETURN
3347    
3348    Returns a prepared and executed statement handle from which the caller can extract
3349    results.
3350    
3351    =back
3352    
3353    =cut
3354    
3355    sub _GetStatementHandle {
3356        # Get the parameters.
3357        my ($self, $command, $params) = @_;
3358        # Trace the query.
3359        Trace("SQL query: $command") if T(SQL => 3);
3360        Trace("PARMS: '" . (join "', '", @{$params}) . "'") if (T(SQL => 4) && (@{$params} > 0));
3361        # Get the database handle.
3362        my $dbh = $self->{_dbh};
3363        # Prepare the command.
3364        my $sth = $dbh->prepare_command($command);
3365        # Execute it with the parameters bound in.
3366        $sth->execute(@{$params}) || Confess("SELECT error" . $sth->errstr());
3367        # Return the statement handle.
3368        return $sth;
3369    }
3370    
3371    =head3 _GetLoadStats
3372    
3373    Return a blank statistics object for use by the load methods.
3374    
3375    This is a static method.
3376    
3377    =cut
3378    
3379    sub _GetLoadStats{
3380        return Stats->new();
3381    }
3382    
3383    =head3 _DumpRelation
3384    
3385    Dump the specified relation to the specified output file in tab-delimited format.
3386    
3387  This is an instance method.  This is an instance method.
3388    
# Line 1750  Line 3430 
3430      close DTXOUT;      close DTXOUT;
3431  }  }
3432    
3433  =head3 GetStructure  =head3 _GetStructure
3434    
3435  Get the data structure for a specified entity or relationship.  Get the data structure for a specified entity or relationship.
3436    
# Line 1789  Line 3469 
3469      return $retVal;      return $retVal;
3470  }  }
3471    
3472  =head3 GetRelationTable  
3473    
3474    =head3 _GetRelationTable
3475    
3476  Get the list of relations for a specified entity or relationship.  Get the list of relations for a specified entity or relationship.
3477    
# Line 1818  Line 3500 
3500      return $objectData->{Relations};      return $objectData->{Relations};
3501  }  }
3502    
3503  =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  
3504    
3505  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
3506  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 3527 
3527          for my $object (values %{$metadata->{$section}}) {          for my $object (values %{$metadata->{$section}}) {
3528              # Loop through the object's fields.              # Loop through the object's fields.
3529              for my $fieldName (keys %{$object->{Fields}}) {              for my $fieldName (keys %{$object->{Fields}}) {
3530                  # Now we make some initial validations.                  # If this field name is invalid, set the return value to zero
3531                  if ($fieldName =~ /--/) {                  # so we know we encountered an error.
3532                      # Here we have a doubled minus sign.                  if (! ValidateFieldName($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";  
3533                          $retVal = 0;                          $retVal = 0;
3534                      }                      }
3535                  }                  }
3536              }              }
3537          }          }
     }  
3538      # If an error was found, fail.      # If an error was found, fail.
3539      if ($retVal  == 0) {      if ($retVal  == 0) {
3540          Confess("Errors found in field names.");          Confess("Errors found in field names.");
3541      }      }
3542  }  }
3543    
3544  =head3 LoadRelation  =head3 _LoadRelation
3545    
3546  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
3547  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 3601 
3601      return $retVal;      return $retVal;
3602  }  }
3603    
3604  =head3 LoadMetaData  
3605    =head3 _LoadMetaData
3606    
3607  This method loads the data describing this database from an XML file into a metadata structure.  This method loads the data describing this database from an XML file into a metadata structure.
3608  The resulting structure is a set of nested hash tables containing all the information needed to  The resulting structure is a set of nested hash tables containing all the information needed to
# Line 1987  Line 3627 
3627  sub _LoadMetaData {  sub _LoadMetaData {
3628      # Get the parameters.      # Get the parameters.
3629      my ($filename) = @_;      my ($filename) = @_;
3630        Trace("Reading Sprout DBD from $filename.") if T(2);
3631      # 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
3632      # get the exact structure we want.      # get the exact structure we want.
3633      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 $filename.") if T(1);  
3634      # Before we go any farther, we need to validate the field and object names. If an error is found,      # Before we go any farther, we need to validate the field and object names. If an error is found,
3635      # the method below will fail.      # the method below will fail.
3636      _ValidateFieldNames($metadata);      _ValidateFieldNames($metadata);
# Line 2014  Line 3642 
3642      for my $entityName (keys %{$entityList}) {      for my $entityName (keys %{$entityList}) {
3643          my $entityStructure = $entityList->{$entityName};          my $entityStructure = $entityList->{$entityName};
3644          #          #
3645          # 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,
3646          # 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,
3647          # 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>
3648          # 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 3821 
3821          my @fromList = ();          my @fromList = ();
3822          my @toList = ();          my @toList = ();
3823          my @bothList = ();          my @bothList = ();
3824          Trace("Join table build for $entityName.") if T(3);          Trace("Join table build for $entityName.") if T(metadata => 4);
3825          for my $relationshipName (keys %{$relationshipList}) {          for my $relationshipName (keys %{$relationshipList}) {
3826              my $relationship = $relationshipList->{$relationshipName};              my $relationship = $relationshipList->{$relationshipName};
3827              # 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.
3828              my $fromEntity = $relationship->{from};              my $fromEntity = $relationship->{from};
3829              my $toEntity = $relationship->{to};              my $toEntity = $relationship->{to};
3830              Trace("Join check for relationship $relationshipName from $fromEntity to $toEntity.") if T(3);              Trace("Join check for relationship $relationshipName from $fromEntity to $toEntity.") if T(Joins => 4);
3831              if ($fromEntity eq $entityName) {              if ($fromEntity eq $entityName) {
3832                  if ($toEntity eq $entityName) {                  if ($toEntity eq $entityName) {
3833                      # Here the relationship is recursive.                      # Here the relationship is recursive.
3834                      push @bothList, $relationshipName;                      push @bothList, $relationshipName;
3835                      Trace("Relationship $relationshipName put in both-list.") if T(3);                      Trace("Relationship $relationshipName put in both-list.") if T(metadata => 4);
3836                  } else {                  } else {
3837                      # Here the relationship comes from the entity.                      # Here the relationship comes from the entity.
3838                      push @fromList, $relationshipName;                      push @fromList, $relationshipName;
3839                      Trace("Relationship $relationshipName put in from-list.") if T(3);                      Trace("Relationship $relationshipName put in from-list.") if T(metadata => 4);
3840                  }                  }
3841              } elsif ($toEntity eq $entityName) {              } elsif ($toEntity eq $entityName) {
3842                  # Here the relationship goes to the entity.                  # Here the relationship goes to the entity.
3843                  push @toList, $relationshipName;                  push @toList, $relationshipName;
3844                  Trace("Relationship $relationshipName put in to-list.") if T(3);                  Trace("Relationship $relationshipName put in to-list.") if T(metadata => 4);
3845              }              }
3846          }          }
3847          # 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 3857 
3857                  # Create joins between the entity and this relationship.                  # Create joins between the entity and this relationship.
3858                  my $linkField = "$relationshipName.${linkType}_link";                  my $linkField = "$relationshipName.${linkType}_link";
3859                  my $joinClause = "$entityName.id = $linkField";                  my $joinClause = "$entityName.id = $linkField";
3860                  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);
3861                  $joinTable{"$entityName/$relationshipName"} = $joinClause;                  $joinTable{"$entityName/$relationshipName"} = $joinClause;
3862                  $joinTable{"$relationshipName/$entityName"} = $joinClause;                  $joinTable{"$relationshipName/$entityName"} = $joinClause;
3863                  # Create joins between this relationship and the other relationships.                  # Create joins between this relationship and the other relationships.
# Line 2250  Line 3878 
3878                              # relationship and itself are prohibited.                              # relationship and itself are prohibited.
3879                              my $relJoinClause = "$otherName.${otherType}_link = $linkField";                              my $relJoinClause = "$otherName.${otherType}_link = $linkField";
3880                              $joinTable{$joinKey} = $relJoinClause;                              $joinTable{$joinKey} = $relJoinClause;
3881                              Trace("Relationship join clause is $relJoinClause for $joinKey.") if T(4);                              Trace("Relationship join clause is $relJoinClause for $joinKey.") if T(metadata => 4);
3882                          }                          }
3883                      }                      }
3884                  }                  }
# Line 2259  Line 3887 
3887                  # relationship can only be ambiguous with another recursive relationship,                  # relationship can only be ambiguous with another recursive relationship,
3888                  # and the incoming relationship from the outer loop is never recursive.                  # and the incoming relationship from the outer loop is never recursive.
3889                  for my $otherName (@bothList) {                  for my $otherName (@bothList) {
3890                      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);
3891                      # Join from the left.                      # Join from the left.
3892                      $joinTable{"$relationshipName/$otherName"} =                      $joinTable{"$relationshipName/$otherName"} =
3893                          "$linkField = $otherName.from_link";                          "$linkField = $otherName.from_link";
# Line 2274  Line 3902 
3902          # 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
3903          # possible to get the same effect using multiple queries.          # possible to get the same effect using multiple queries.
3904          for my $relationshipName (@bothList) {          for my $relationshipName (@bothList) {
3905              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);
3906              # Join to the entity from each direction.              # Join to the entity from each direction.
3907              $joinTable{"$entityName/$relationshipName"} =              $joinTable{"$entityName/$relationshipName"} =
3908                  "$entityName.id = $relationshipName.from_link";                  "$entityName.id = $relationshipName.from_link";
# Line 2288  Line 3916 
3916      return $metadata;      return $metadata;
3917  }  }
3918    
3919  =head3 CreateRelationshipIndex  =head3 _CreateRelationshipIndex
3920    
3921  Create an index for a relationship's relation.  Create an index for a relationship's relation.
3922    
# Line 2325  Line 3953 
3953      # index descriptor does not exist, it will be created automatically so we can add      # index descriptor does not exist, it will be created automatically so we can add
3954      # the field to it.      # the field to it.
3955      unshift @{$newIndex->{IndexFields}}, $firstField;      unshift @{$newIndex->{IndexFields}}, $firstField;
3956        # If this is a one-to-many relationship, the "To" index is unique.
3957        if ($relationshipStructure->{arity} eq "1M" && $indexKey eq "To") {
3958            $newIndex->{Unique} = 'true';
3959        }
3960      # Add the index to the relation.      # Add the index to the relation.
3961      _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);      _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);
3962  }  }
3963    
3964  =head3 AddIndex  =head3 _AddIndex
3965    
3966  Add an index to a relation structure.  Add an index to a relation structure.
3967    
# Line 2375  Line 4007 
4007      $relationStructure->{Indexes}->{$indexName} = $newIndex;      $relationStructure->{Indexes}->{$indexName} = $newIndex;
4008  }  }
4009    
4010  =head3 FixupFields  =head3 _FixupFields
4011    
4012  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
4013  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 4045 
4045          # Here it doesn't, so we create a new one.          # Here it doesn't, so we create a new one.
4046          $structure->{Fields} = { };          $structure->{Fields} = { };
4047      } else {      } else {
4048          # 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
4049            # create a list for stashing them.
4050            my @textFields = ();
4051            # Loop through the fields.
4052          my $fieldStructures = $structure->{Fields};          my $fieldStructures = $structure->{Fields};
4053          for my $fieldName (keys %{$fieldStructures}) {          for my $fieldName (keys %{$fieldStructures}) {
4054              Trace("Processing field $fieldName of $defaultRelationName.") if T(4);              Trace("Processing field $fieldName of $defaultRelationName.") if T(4);
# Line 2422  Line 4057 
4057              my $type = $fieldData->{type};              my $type = $fieldData->{type};
4058              # Plug in a relation name if it is needed.              # Plug in a relation name if it is needed.
4059              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });
4060              # Plug in a data generator if we need one.              # Check for searchability.
4061              if (!exists $fieldData->{DataGen}) {              if ($fieldData->{searchable}) {
4062                  # The data generator will use the default for the field's type.                  # Only allow this for a primary relation.
4063                  $fieldData->{DataGen} = { content => $TypeTable{$type}->{dataGen} };                  if ($fieldData->{relation} ne $defaultRelationName) {
4064                        Confess("Field $fieldName of $defaultRelationName is in secondary relations and cannot be searchable.");
4065                    } else {
4066                        push @textFields, $fieldName;
4067                    }
4068              }              }
             # Plug in the defaults for the optional data generation parameters.  
             Tracer::MergeOptions($fieldData->{DataGen}, { testCount => 1, pass => 0 });  
4069              # Add the PrettySortValue.              # Add the PrettySortValue.
4070              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);
4071          }          }
4072            # If there are searchable fields, remember the fact.
4073            if (@textFields) {
4074                $structure->{searchFields} = \@textFields;
4075            }
4076      }      }
4077  }  }
4078    
4079  =head3 FixName  =head3 _FixName
4080    
4081  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.
4082    
# Line 2464  Line 4105 
4105      return $fieldName;      return $fieldName;
4106  }  }
4107    
4108  =head3 FixNames  =head3 _FixNames
4109    
4110  Fix all the field names in a list.  Fix all the field names in a list.
4111    
# Line 2495  Line 4136 
4136      return @result;      return @result;
4137  }  }
4138    
4139  =head3 AddField  =head3 _AddField
4140    
4141  Add a field to a field list.  Add a field to a field list.
4142    
# Line 2530  Line 4171 
4171      $fieldList->{$fieldName} = $fieldStructure;      $fieldList->{$fieldName} = $fieldStructure;
4172  }  }
4173    
4174  =head3 ReOrderRelationTable  =head3 _ReOrderRelationTable
4175    
4176  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
4177  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 4232 
4232    
4233  }  }
4234    
4235  =head3 IsPrimary  =head3 _IsPrimary
4236    
4237  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
4238  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 4268 
4268      return $retVal;      return $retVal;
4269  }  }
4270    
4271  =head3 FindRelation  =head3 _FindRelation
4272    
4273  Return the descriptor for the specified relation.  Return the descriptor for the specified relation.
4274    
# Line 2658  Line 4299 
4299    
4300  =head2 HTML Documentation Utility Methods  =head2 HTML Documentation Utility Methods
4301    
4302  =head3 ComputeRelationshipSentence  =head3 _ComputeRelationshipSentence
4303    
4304  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
4305  two related entities and an arity indicator.  two related entities and an arity indicator.
# Line 2696  Line 4337 
4337      return $result;      return $result;
4338  }  }
4339    
4340  =head3 ComputeRelationshipHeading  =head3 _ComputeRelationshipHeading
4341    
4342  The relationship heading is the L<relationship sentence|/ComputeRelationshipSentence> with the entity  The relationship heading is the L<relationship sentence|/ComputeRelationshipSentence> with the entity
4343  names hyperlinked to the appropriate entity sections of the document.  names hyperlinked to the appropriate entity sections of the document.
# Line 2733  Line 4374 
4374      return $result;      return $result;
4375  }  }
4376    
4377  =head3 ShowRelationTable  =head3 _ShowRelationTable
4378    
4379  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
4380  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 4424 
4424          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";
4425          # Add any note text.          # Add any note text.
4426          if (my $note = $indexData->{Notes}) {          if (my $note = $indexData->{Notes}) {
4427              $htmlString .= "<li>" . _HTMLNote($note->{content}) . "</li>\n";              $htmlString .= "<li>" . HTMLNote($note->{content}) . "</li>\n";
4428          }          }
4429          # Add the fiield list.          # Add the fiield list.
4430          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";
# Line 2794  Line 4435 
4435      $htmlString .= "</ul>\n";      $htmlString .= "</ul>\n";
4436  }  }
4437    
4438  =head3 OpenFieldTable  =head3 _OpenFieldTable
4439    
4440  This method creates the header string for the field table generated by L</ShowMetaData>.  This method creates the header string for the field table generated by L</ShowMetaData>.
4441    
# Line 2819  Line 4460 
4460      return _OpenTable($tablename, 'Field', 'Type', 'Description');      return _OpenTable($tablename, 'Field', 'Type', 'Description');
4461  }  }
4462    
4463  =head3 OpenTable  =head3 _OpenTable
4464    
4465  This method creates the header string for an HTML table.  This method creates the header string for an HTML table.
4466    
# Line 2859  Line 4500 
4500      return $htmlString;      return $htmlString;
4501  }  }
4502    
4503  =head3 CloseTable  =head3 _CloseTable
4504    
4505  This method returns the HTML for closing a table.  This method returns the HTML for closing a table.
4506    
# Line 2871  Line 4512 
4512      return "</table></p>\n";      return "</table></p>\n";
4513  }  }
4514    
4515  =head3 ShowField  =head3 _ShowField
4516    
4517  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.
4518    
# Line 2898  Line 4539 
4539      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>";
4540      # If we have content, add it as a third column.      # If we have content, add it as a third column.
4541      if (exists $fieldData->{Notes}) {      if (exists $fieldData->{Notes}) {
4542          $htmlString .= "<td>" . _HTMLNote($fieldData->{Notes}->{content}) . "</td>";          $htmlString .= "<td>" . HTMLNote($fieldData->{Notes}->{content}) . "</td>";
4543      }      }
4544      # Close off the row.      # Close off the row.
4545      $htmlString .= "</tr>\n";      $htmlString .= "</tr>\n";
# Line 2906  Line 4547 
4547      return $htmlString;      return $htmlString;
4548  }  }
4549    
 =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;  
 }  
   
4550  1;  1;

Legend:
Removed from v.1.11  
changed lines
  Added in v.1.74

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3