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

Diff of /Sprout/ERDB.pm

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

revision 1.16, Tue Jun 28 23:51:06 2005 UTC revision 1.84, Wed Jan 24 10:22:22 2007 UTC
# Line 9  Line 9 
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 221  Line 257 
257    
258  =back  =back
259    
260  The B<Index>, B<FromIndex>, and B<ToIndex> tags themselves have no attributes.  The B<FromIndex>, and B<ToIndex> tags have no attributes. The B<Index> tag can
261    have a B<Unique> attribute. If specified, the index will be generated as a unique
262    index.
263    
264  =head3 Object and Field Names  =head3 Object and Field Names
265    
# Line 299  Line 337 
337    
338  # Table of information about our datatypes. "sqlType" is the corresponding SQL datatype string.  # Table of information about our datatypes. "sqlType" is the corresponding SQL datatype string.
339  # "maxLen" is the maximum permissible length of the incoming string data used to populate a field  # "maxLen" is the maximum permissible length of the incoming string data used to populate a field
340  # of the specified type. "dataGen" is PERL string that will be evaluated if no test data generation  # of the specified type. "avgLen" is the average byte length for estimating
341   #string is specified in the field definition.  # record sizes. "sort" is the key modifier for the sort command, "notes" is a type description,
342  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            dataGen => "StringGen('A')" },  # and "indexMod", if non-zero, is the number of characters to use when the field is specified in an
343                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           dataGen => "IntGen(0, 99999999)" },  # index
344                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          dataGen => "StringGen(IntGen(10,250))" },  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",
345                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   dataGen => "StringGen(IntGen(80,1000))" },                                 indexMod =>   0, notes => "single ASCII character"},
346                    date =>    { sqlType => 'BIGINT',             maxLen => 80,           dataGen => "DateGen(-7, 7, IntGen(0,1400))" },                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n",
347                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           dataGen => "FloatGen(0.0, 100.0)" },                                 indexMod =>   0, notes => "signed 32-bit integer"},
348                    boolean => { sqlType => 'SMALLINT',           maxLen => 1,            dataGen => "IntGen(0, 1)" },                    counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n",
349                                   indexMod =>   0, notes => "unsigned 32-bit integer"},
350                      string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, sort => "",
351                                   indexMod =>   0, notes => "character string, 0 to 255 characters"},
352                      text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, sort => "",
353                                   indexMod => 255, notes => "character string, nearly unlimited length, only first 255 characters are indexed"},
354                      date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, sort => "n",
355                                   indexMod =>   0, notes => "signed, 64-bit integer"},
356                      float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, sort => "g",
357                                   indexMod =>   0, notes => "64-bit double precision floating-point number"},
358                      boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, sort => "n",
359                                   indexMod =>   0, notes => "boolean value: 0 if false, 1 if true"},
360                     'hash-string' =>
361                                 { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, sort => "",
362                                   indexMod =>   0, notes => "string stored in digested form, used for certain types of key fields"},
363                     'id-string' =>
364                                 { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, sort => "",
365                                   indexMod =>   0, notes => "character string, 0 to 25 characters"},
366                   'key-string' =>                   'key-string' =>
367                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           dataGen => "StringGen(IntGen(10,40))" },                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, sort => "",
368                                   indexMod =>   0, notes => "character string, 0 to 40 characters"},
369                   'name-string' =>                   'name-string' =>
370                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           dataGen => "StringGen(IntGen(10,80))" },                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, sort => "",
371                                   indexMod =>   0, notes => "character string, 0 to 80 characters"},
372                   'medium-string' =>                   'medium-string' =>
373                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          dataGen => "StringGen(IntGen(10,160))" },                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",
374                                   indexMod =>   0, notes => "character string, 0 to 160 characters"},
375                  );                  );
376    
377  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 322  Line 380 
380                     'MM' => 'many-to-many'                     'MM' => 'many-to-many'
381                   );                   );
382    
383  # Table for interpreting string patterns.  # Options for XML input and output.
384    
385    my %XmlOptions = (GroupTags =>  { Relationships => 'Relationship',
386                                      Entities => 'Entity',
387                                      Fields => 'Field',
388                                      Indexes => 'Index',
389                                      IndexFields => 'IndexField'
390                                    },
391                      KeyAttr =>    { Relationship => 'name',
392                                      Entity => 'name',
393                                      Field => 'name'
394                                    },
395                      SuppressEmpty => 1,
396                     );
397    
398  my %PictureTable = ( 'A' => "abcdefghijklmnopqrstuvwxyz",  my %XmlInOpts  = (
399                       '9' => "0123456789",                    ForceArray => ['Field', 'Index', 'IndexField', 'Relationship', 'Entity'],
400                       'X' => "abcdefghijklmnopqrstuvwxyz0123456789",                    ForceContent => 1,
401                       'V' => "aeiou",                    NormalizeSpace => 2,
                      'K' => "bcdfghjklmnoprstvwxyz"  
402                     );                     );
403    my %XmlOutOpts = (
404                      RootName => 'Database',
405                      XMLDecl => 1,
406                     );
407    
408    
409  =head2 Public Methods  =head2 Public Methods
410    
# Line 369  Line 444 
444    
445  =head3 ShowMetaData  =head3 ShowMetaData
446    
447  C<< $database->ShowMetaData($fileName); >>  C<< $erdb->ShowMetaData($fileName); >>
448    
449  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
450  the data to be loaded into the relations.  the data to be loaded into the relations.
# Line 400  Line 475 
475      # Write the HTML heading stuff.      # Write the HTML heading stuff.
476      print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";      print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";
477      print HTMLOUT "</head>\n<body>\n";      print HTMLOUT "</head>\n<body>\n";
478        # Write the documentation.
479        print HTMLOUT $self->DisplayMetaData();
480        # Close the document.
481        print HTMLOUT "</body>\n</html>\n";
482        # Close the file.
483        close HTMLOUT;
484    }
485    
486    =head3 DisplayMetaData
487    
488    C<< my $html = $erdb->DisplayMetaData(); >>
489    
490    Return an HTML description of the database. This description can be used to help users create
491    the data to be loaded into the relations and form queries. The output is raw includable HTML
492    without any HEAD or BODY tags.
493    
494    =over 4
495    
496    =item filename
497    
498    The name of the output file.
499    
500    =back
501    
502    =cut
503    
504    sub DisplayMetaData {
505        # Get the parameters.
506        my ($self) = @_;
507        # Get the metadata and the title string.
508        my $metadata = $self->{_metaData};
509        # Get the title string.
510        my $title = $metadata->{Title};
511        # Get the entity and relationship lists.
512        my $entityList = $metadata->{Entities};
513        my $relationshipList = $metadata->{Relationships};
514        # Declare the return variable.
515        my $retVal = "";
516        # Open the output file.
517        Trace("Building MetaData table of contents.") if T(4);
518      # Here we do the table of contents. It starts as an unordered list of section names. Each      # Here we do the table of contents. It starts as an unordered list of section names. Each
519      # section contains an ordered list of entity or relationship subsections.      # section contains an ordered list of entity or relationship subsections.
520      print HTMLOUT "<ul>\n<li><a href=\"#EntitiesSection\">Entities</a>\n<ol>\n";      $retVal .= "<ul>\n<li><a href=\"#EntitiesSection\">Entities</a>\n<ol>\n";
521      # Loop through the Entities, displaying a list item for each.      # Loop through the Entities, displaying a list item for each.
522      foreach my $key (sort keys %{$entityList}) {      foreach my $key (sort keys %{$entityList}) {
523          # Display this item.          # Display this item.
524          print HTMLOUT "<li><a href=\"#$key\">$key</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$key</a></li>\n";
525      }      }
526      # Close off the entity section and start the relationship section.      # Close off the entity section and start the relationship section.
527      print HTMLOUT "</ol></li>\n<li><a href=\"#RelationshipsSection\">Relationships</a>\n<ol>\n";      $retVal .= "</ol></li>\n<li><a href=\"#RelationshipsSection\">Relationships</a>\n<ol>\n";
528      # Loop through the Relationships.      # Loop through the Relationships.
529      foreach my $key (sort keys %{$relationshipList}) {      foreach my $key (sort keys %{$relationshipList}) {
530          # Display this item.          # Display this item.
531          my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});          my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});
532          print HTMLOUT "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";
533      }      }
534      # Close off the relationship section and list the join table section.      # Close off the relationship section and list the join table section.
535      print HTMLOUT "</ol></li>\n<li><a href=\"#JoinTable\">Join Table</a></li>\n";      $retVal .= "</ol></li>\n<li><a href=\"#JoinTable\">Join Table</a></li>\n";
536      # Close off the table of contents itself.      # Close off the table of contents itself.
537      print HTMLOUT "</ul>\n";      $retVal .=  "</ul>\n";
538      # Now we start with the actual data. Denote we're starting the entity section.      # Now we start with the actual data. Denote we're starting the entity section.
539      print HTMLOUT "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";      $retVal .= "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";
540      # Loop through the entities.      # Loop through the entities.
541      for my $key (sort keys %{$entityList}) {      for my $key (sort keys %{$entityList}) {
542          Trace("Building MetaData entry for $key entity.") if T(4);          Trace("Building MetaData entry for $key entity.") if T(4);
543          # Create the entity header. It contains a bookmark and the entity name.          # Create the entity header. It contains a bookmark and the entity name.
544          print HTMLOUT "<a name=\"$key\"></a><h3>$key</h3>\n";          $retVal .= "<a name=\"$key\"></a><h3>$key</h3>\n";
545          # Get the entity data.          # Get the entity data.
546          my $entityData = $entityList->{$key};          my $entityData = $entityList->{$key};
547          # If there's descriptive text, display it.          # If there's descriptive text, display it.
548          if (my $notes = $entityData->{Notes}) {          if (my $notes = $entityData->{Notes}) {
549              print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
550          }          }
551          # Now we want a list of the entity's relationships. First, we set up the relationship subsection.          # See if we need a list of the entity's relationships.
552          print HTMLOUT "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          my $relCount = keys %{$relationshipList};
553            if ($relCount > 0) {
554                # First, we set up the relationship subsection.
555                $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
556          # Loop through the relationships.          # Loop through the relationships.
557          for my $relationship (sort keys %{$relationshipList}) {          for my $relationship (sort keys %{$relationshipList}) {
558              # Get the relationship data.              # Get the relationship data.
# Line 444  Line 562 
562                  # Get the relationship sentence and append the arity.                  # Get the relationship sentence and append the arity.
563                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);
564                  # Display the relationship data.                  # Display the relationship data.
565                  print HTMLOUT "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";                      $retVal .= "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";
566              }              }
567          }          }
568          # Close off the relationship list.          # Close off the relationship list.
569          print HTMLOUT "</ul>\n";              $retVal .= "</ul>\n";
570            }
571          # Get the entity's relations.          # Get the entity's relations.
572          my $relationList = $entityData->{Relations};          my $relationList = $entityData->{Relations};
573          # Create a header for the relation subsection.          # Create a header for the relation subsection.
574          print HTMLOUT "<h4>Relations for <b>$key</b></h4>\n";          $retVal .= "<h4>Relations for <b>$key</b></h4>\n";
575          # Loop through the relations, displaying them.          # Loop through the relations, displaying them.
576          for my $relation (sort keys %{$relationList}) {          for my $relation (sort keys %{$relationList}) {
577              my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});              my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});
578              print HTMLOUT $htmlString;              $retVal .= $htmlString;
579          }          }
580      }      }
581      # Denote we're starting the relationship section.      # Denote we're starting the relationship section.
582      print HTMLOUT "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";      $retVal .= "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";
583      # Loop through the relationships.      # Loop through the relationships.
584      for my $key (sort keys %{$relationshipList}) {      for my $key (sort keys %{$relationshipList}) {
585          Trace("Building MetaData entry for $key relationship.") if T(4);          Trace("Building MetaData entry for $key relationship.") if T(4);
# Line 468  Line 587 
587          my $relationshipStructure = $relationshipList->{$key};          my $relationshipStructure = $relationshipList->{$key};
588          # Create the relationship header.          # Create the relationship header.
589          my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);          my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);
590          print HTMLOUT "<h3><a name=\"$key\"></a>$headerText</h3>\n";          $retVal .= "<h3><a name=\"$key\"></a>$headerText</h3>\n";
591          # Get the entity names.          # Get the entity names.
592          my $fromEntity = $relationshipStructure->{from};          my $fromEntity = $relationshipStructure->{from};
593          my $toEntity = $relationshipStructure->{to};          my $toEntity = $relationshipStructure->{to};
# Line 478  Line 597 
597          # since both sentences will say the same thing.          # since both sentences will say the same thing.
598          my $arity = $relationshipStructure->{arity};          my $arity = $relationshipStructure->{arity};
599          if ($arity eq "11") {          if ($arity eq "11") {
600              print HTMLOUT "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";
601          } else {          } else {
602              print HTMLOUT "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";
603              if ($arity eq "MM" && $fromEntity ne $toEntity) {              if ($arity eq "MM" && $fromEntity ne $toEntity) {
604                  print HTMLOUT "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";                  $retVal .= "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";
605              }              }
606          }          }
607          print HTMLOUT "</p>\n";          $retVal .= "</p>\n";
608          # If there are notes on this relationship, display them.          # If there are notes on this relationship, display them.
609          if (my $notes = $relationshipStructure->{Notes}) {          if (my $notes = $relationshipStructure->{Notes}) {
610              print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
611          }          }
612          # Generate the relationship's relation table.          # Generate the relationship's relation table.
613          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
614          print HTMLOUT $htmlString;          $retVal .= $htmlString;
615      }      }
616      Trace("Building MetaData join table.") if T(4);      Trace("Building MetaData join table.") if T(4);
617      # Denote we're starting the join table.      # Denote we're starting the join table.
618      print HTMLOUT "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";      $retVal .= "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";
619      # Create a table header.      # Create a table header.
620      print HTMLOUT _OpenTable("Join Table", "Source", "Target", "Join Condition");      $retVal .= _OpenTable("Join Table", "Source", "Target", "Join Condition");
621      # Loop through the joins.      # Loop through the joins.
622      my $joinTable = $metadata->{Joins};      my $joinTable = $metadata->{Joins};
623      my @joinKeys = keys %{$joinTable};      my @joinKeys = keys %{$joinTable};
# Line 506  Line 625 
625          # Separate out the source, the target, and the join clause.          # Separate out the source, the target, and the join clause.
626          $joinKey =~ m!^([^/]+)/(.+)$!;          $joinKey =~ m!^([^/]+)/(.+)$!;
627          my ($sourceRelation, $targetRelation) = ($1, $2);          my ($sourceRelation, $targetRelation) = ($1, $2);
628          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);
629          my $source = $self->ComputeObjectSentence($sourceRelation);          my $source = $self->ComputeObjectSentence($sourceRelation);
630          my $target = $self->ComputeObjectSentence($targetRelation);          my $target = $self->ComputeObjectSentence($targetRelation);
631          my $clause = $joinTable->{$joinKey};          my $clause = $joinTable->{$joinKey};
632          # Display them in a table row.          # Display them in a table row.
633          print HTMLOUT "<tr><td>$source</td><td>$target</td><td>$clause</td></tr>\n";          $retVal .= "<tr><td>$source</td><td>$target</td><td>$clause</td></tr>\n";
634      }      }
635      # Close the table.      # Close the table.
636      print HTMLOUT _CloseTable();      $retVal .= _CloseTable();
637      # Close the document.      Trace("Built MetaData HTML.") if T(3);
638      print HTMLOUT "</body>\n</html>\n";      # Return the HTML.
639      # Close the file.      return $retVal;
     close HTMLOUT;  
     Trace("Built MetaData web page.") if T(3);  
640  }  }
641    
642  =head3 DumpMetaData  =head3 DumpMetaData
643    
644  C<< $database->DumpMetaData(); >>  C<< $erdb->DumpMetaData(); >>
645    
646  Return a dump of the metadata structure.  Return a dump of the metadata structure.
647    
# Line 537  Line 654 
654      return Data::Dumper::Dumper($self->{_metaData});      return Data::Dumper::Dumper($self->{_metaData});
655  }  }
656    
657    =head3 FindIndexForEntity
658    
659    C<< my $indexFound = ERDB::FindIndexForEntity($xml, $entityName, $attributeName); >>
660    
661    This method locates the entry in an entity's index list that begins with the
662    specified attribute name. If the entity has no index list, one will be
663    created. This method works on raw XML, not a live ERDB object.
664    
665    =over 4
666    
667    =item xml
668    
669    The raw XML structure defining the database.
670    
671    =item entityName
672    
673    The name of the relevant entity.
674    
675    =item attributeName
676    
677    The name of the attribute relevant to the search.
678    
679    =item RETURN
680    
681    The numerical index in the index list of the index entry for the specified entity and
682    attribute, or C<undef> if no such index exists.
683    
684    =back
685    
686    =cut
687    
688    sub FindIndexForEntity {
689        # Get the parameters.
690        my ($xml, $entityName, $attributeName) = @_;
691        # Declare the return variable.
692        my $retVal;
693        # Get the named entity.
694        my $entityData = $xml->{Entities}->{$entityName};
695        if (! $entityData) {
696            Confess("Entity $entityName not found in DBD structure.");
697        } else {
698            # Insure it has an index list.
699            if (! exists $entityData->{Indexes}) {
700                $entityData->{Indexes} = [];
701            } else {
702                # Search for the desired index.
703                my $indexList = $entityData->{Indexes};
704                my $n = scalar @{$indexList};
705                Trace("Searching $n indexes in index list for $entityName.") if T(2);
706                # We use an indexed FOR here because we're returning an
707                # index number instead of an object. We do THAT so we can
708                # delete the index from the list if needed.
709                for (my $i = 0; $i < $n && !defined($retVal); $i++) {
710                    my $index = $indexList->[$i];
711                    my $fields = $index->{IndexFields};
712                    # Technically this IF should be safe (that is, we are guaranteed
713                    # the existence of a "$fields->[0]"), because when we load the XML
714                    # we have SuppressEmpty specified.
715                    if ($fields->[0]->{name} eq $attributeName) {
716                        $retVal = $i;
717                    }
718                }
719            }
720        }
721        Trace("Index for $attributeName of $entityName found at position $retVal.") if defined($retVal) && T(3);
722        Trace("Index for $attributeName not found in $entityName.") if !defined($retVal) && T(3);
723        # Return the result.
724        return $retVal;
725    }
726    
727  =head3 CreateTables  =head3 CreateTables
728    
729  C<< $datanase->CreateTables(); >>  C<< $erdb->CreateTables(); >>
730    
731  This method creates the tables for the database from the metadata structure loaded by the  This method creates the tables for the database from the metadata structure loaded by the
732  constructor. It is expected this function will only be used on rare occasions, when the  constructor. It is expected this function will only be used on rare occasions, when the
# Line 551  Line 738 
738  sub CreateTables {  sub CreateTables {
739      # Get the parameters.      # Get the parameters.
740      my ($self) = @_;      my ($self) = @_;
741      my $metadata = $self->{_metaData};      # Get the relation names.
742      my $dbh = $self->{_dbh};      my @relNames = $self->GetTableNames();
743      # Loop through the entities.      # Loop through the relations.
744      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}}) {  
745              # Create a table for this relation.              # Create a table for this relation.
746              $self->CreateTable($relationName);              $self->CreateTable($relationName);
747              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);  
748      }      }
749  }  }
750    
751  =head3 CreateTable  =head3 CreateTable
752    
753  C<< $database->CreateTable($tableName, $indexFlag); >>  C<< $erdb->CreateTable($tableName, $indexFlag, $estimatedRows); >>
754    
755  Create the table for a relation and optionally create its indexes.  Create the table for a relation and optionally create its indexes.
756    
# Line 587  Line 760 
760    
761  Name of the relation (which will also be the table name).  Name of the relation (which will also be the table name).
762    
763  =item $indexFlag  =item indexFlag
764    
765  TRUE if the indexes for the relation should be created, else FALSE. If FALSE,  TRUE if the indexes for the relation should be created, else FALSE. If FALSE,
766  L</CreateIndexes> must be called later to bring the indexes into existence.  L</CreateIndexes> must be called later to bring the indexes into existence.
767    
768    =item estimatedRows (optional)
769    
770    If specified, the estimated maximum number of rows for the relation. This
771    information allows the creation of tables using storage engines that are
772    faster but require size estimates, such as MyISAM.
773    
774  =back  =back
775    
776  =cut  =cut
777    
778  sub CreateTable {  sub CreateTable {
779      # Get the parameters.      # Get the parameters.
780      my ($self, $relationName, $indexFlag) = @_;      my ($self, $relationName, $indexFlag, $estimatedRows) = @_;
781      # Get the database handle.      # Get the database handle.
782      my $dbh = $self->{_dbh};      my $dbh = $self->{_dbh};
783      # 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 801 
801      # Insure the table is not already there.      # Insure the table is not already there.
802      $dbh->drop_table(tbl => $relationName);      $dbh->drop_table(tbl => $relationName);
803      Trace("Table $relationName dropped.") if T(2);      Trace("Table $relationName dropped.") if T(2);
804        # If there are estimated rows, create an estimate so we can take advantage of
805        # faster DB technologies.
806        my $estimation = undef;
807        if ($estimatedRows) {
808            $estimation = [$self->EstimateRowSize($relationName), $estimatedRows];
809        }
810      # Create the table.      # Create the table.
811      Trace("Creating table $relationName: $fieldThing") if T(2);      Trace("Creating table $relationName: $fieldThing") if T(2);
812      $dbh->create_table(tbl => $relationName, flds => $fieldThing);      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);
813      Trace("Relation $relationName created in database.") if T(2);      Trace("Relation $relationName created in database.") if T(2);
814      # If we want to build the indexes, we do it here.      # If we want to build the indexes, we do it here. Note that the full-text search
815        # index will not be built until the table has been loaded.
816      if ($indexFlag) {      if ($indexFlag) {
817          $self->CreateIndex($relationName);          $self->CreateIndex($relationName);
818      }      }
819  }  }
820    
821    =head3 VerifyFields
822    
823    C<< my $count = $erdb->VerifyFields($relName, \@fieldList); >>
824    
825    Run through the list of proposed field values, insuring that all the character fields are
826    below the maximum length. If any fields are too long, they will be truncated in place.
827    
828    =over 4
829    
830    =item relName
831    
832    Name of the relation for which the specified fields are destined.
833    
834    =item fieldList
835    
836    Reference to a list, in order, of the fields to be put into the relation.
837    
838    =item RETURN
839    
840    Returns the number of fields truncated.
841    
842    =back
843    
844    =cut
845    
846    sub VerifyFields {
847        # Get the parameters.
848        my ($self, $relName, $fieldList) = @_;
849        # Initialize the return value.
850        my $retVal = 0;
851        # Get the relation definition.
852        my $relData = $self->_FindRelation($relName);
853        # Get the list of field descriptors.
854        my $fieldTypes = $relData->{Fields};
855        my $fieldCount = scalar @{$fieldTypes};
856        # Loop through the two lists.
857        for (my $i = 0; $i < $fieldCount; $i++) {
858            # Get the type of the current field.
859            my $fieldType = $fieldTypes->[$i]->{type};
860            # If it's a character field, verify the length.
861            if ($fieldType =~ /string/) {
862                my $maxLen = $TypeTable{$fieldType}->{maxLen};
863                my $oldString = $fieldList->[$i];
864                if (length($oldString) > $maxLen) {
865                    # Here it's too big, so we truncate it.
866                    Trace("Truncating field $i in relation $relName to $maxLen characters from \"$oldString\".") if T(1);
867                    $fieldList->[$i] = substr $oldString, 0, $maxLen;
868                    $retVal++;
869                }
870            }
871        }
872        # Return the truncation count.
873        return $retVal;
874    }
875    
876    =head3 DigestFields
877    
878    C<< $erdb->DigestFields($relName, $fieldList); >>
879    
880    Digest the strings in the field list that correspond to data type C<hash-string> in the
881    specified relation.
882    
883    =over 4
884    
885    =item relName
886    
887    Name of the relation to which the fields belong.
888    
889    =item fieldList
890    
891    List of field contents to be loaded into the relation.
892    
893    =back
894    
895    =cut
896    #: Return Type ;
897    sub DigestFields {
898        # Get the parameters.
899        my ($self, $relName, $fieldList) = @_;
900        # Get the relation definition.
901        my $relData = $self->_FindRelation($relName);
902        # Get the list of field descriptors.
903        my $fieldTypes = $relData->{Fields};
904        my $fieldCount = scalar @{$fieldTypes};
905        # Loop through the two lists.
906        for (my $i = 0; $i < $fieldCount; $i++) {
907            # Get the type of the current field.
908            my $fieldType = $fieldTypes->[$i]->{type};
909            # If it's a hash string, digest it in place.
910            if ($fieldType eq 'hash-string') {
911                $fieldList->[$i] = $self->DigestKey($fieldList->[$i]);
912            }
913        }
914    }
915    
916    =head3 DigestKey
917    
918    C<< my $digested = $erdb->DigestKey($keyValue); >>
919    
920    Return the digested value of a symbolic key. The digested value can then be plugged into a
921    key-based search into a table with key-type hash-string.
922    
923    Currently the digesting process is independent of the database structure, but that may not
924    always be the case, so this is an instance method instead of a static method.
925    
926    =over 4
927    
928    =item keyValue
929    
930    Key value to digest.
931    
932    =item RETURN
933    
934    Digested value of the key.
935    
936    =back
937    
938    =cut
939    
940    sub DigestKey {
941        # Get the parameters.
942        my ($self, $keyValue) = @_;
943        # Compute the digest.
944        my $retVal = md5_base64($keyValue);
945        # Return the result.
946        return $retVal;
947    }
948    
949  =head3 CreateIndex  =head3 CreateIndex
950    
951  C<< $database->CreateIndex($relationName); >>  C<< $erdb->CreateIndex($relationName); >>
952    
953  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
954  is the case in L</LoadTable>), it is sometimes best to create the indexes after the load.  is the case in L</LoadTable>), it is sometimes best to create the indexes after the load.
# Line 655  Line 969 
969      for my $indexName (keys %{$indexHash}) {      for my $indexName (keys %{$indexHash}) {
970          my $indexData = $indexHash->{$indexName};          my $indexData = $indexHash->{$indexName};
971          # Get the index's field list.          # Get the index's field list.
972          my @fieldList = _FixNames(@{$indexData->{IndexFields}});          my @rawFields = @{$indexData->{IndexFields}};
973            # Get a hash of the relation's field types.
974            my %types = map { $_->{name} => $_->{type} } @{$relationData->{Fields}};
975            # We need to check for text fields so we can append a length limitation for them. To do
976            # that, we need the relation's field list.
977            my $relFields = $relationData->{Fields};
978            for (my $i = 0; $i <= $#rawFields; $i++) {
979                # Get the field type.
980                my $field = $rawFields[$i];
981                my $type = $types{$field};
982                # Ask if it requires using prefix notation for the index.
983                my $mod = $TypeTable{$type}->{indexMod};
984                Trace("Field $field ($i) in $relationName has type $type and indexMod $mod.") if T(3);
985                if ($mod) {
986                    # Append the prefix length to the field name,
987                    $rawFields[$i] .= "($mod)";
988                }
989            }
990            my @fieldList = _FixNames(@rawFields);
991          my $flds = join(', ', @fieldList);          my $flds = join(', ', @fieldList);
992          # Get the index's uniqueness flag.          # Get the index's uniqueness flag.
993          my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
994          # Create the index.          # Create the index.
995          $dbh->create_index(idx => $indexName, tbl => $relationName, flds => $flds, unique => $unique);          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
996                                        flds => $flds, kind => $unique);
997            if ($rv) {
998          Trace("Index created: $indexName for $relationName ($flds)") if T(1);          Trace("Index created: $indexName for $relationName ($flds)") if T(1);
999            } else {
1000                Confess("Error creating index $indexName for $relationName using ($flds): " . $dbh->error_message());
1001            }
1002        }
1003    }
1004    
1005    =head3 GetSecondaryFields
1006    
1007    C<< my %fieldTuples = $erdb->GetSecondaryFields($entityName); >>
1008    
1009    This method will return a list of the name and type of each of the secondary
1010    fields for a specified entity. Secondary fields are stored in two-column tables
1011    in addition to the primary entity table. This enables the field to have no value
1012    or to have multiple values.
1013    
1014    =over 4
1015    
1016    =item entityName
1017    
1018    Name of the entity whose secondary fields are desired.
1019    
1020    =item RETURN
1021    
1022    Returns a hash mapping the field names to their field types.
1023    
1024    =back
1025    
1026    =cut
1027    
1028    sub GetSecondaryFields {
1029        # Get the parameters.
1030        my ($self, $entityName) = @_;
1031        # Declare the return variable.
1032        my %retVal = ();
1033        # Look for the entity.
1034        my $table = $self->GetFieldTable($entityName);
1035        # Loop through the fields, pulling out the secondaries.
1036        for my $field (sort keys %{$table}) {
1037            if ($table->{$field}->{relation} ne $entityName) {
1038                # Here we have a secondary field.
1039                $retVal{$field} = $table->{$field}->{type};
1040            }
1041        }
1042        # Return the result.
1043        return %retVal;
1044    }
1045    
1046    =head3 GetFieldRelationName
1047    
1048    C<< my $name = $erdb->GetFieldRelationName($objectName, $fieldName); >>
1049    
1050    Return the name of the relation containing a specified field.
1051    
1052    =over 4
1053    
1054    =item objectName
1055    
1056    Name of the entity or relationship containing the field.
1057    
1058    =item fieldName
1059    
1060    Name of the relevant field in that entity or relationship.
1061    
1062    =item RETURN
1063    
1064    Returns the name of the database relation containing the field, or C<undef> if
1065    the field does not exist.
1066    
1067    =back
1068    
1069    =cut
1070    
1071    sub GetFieldRelationName {
1072        # Get the parameters.
1073        my ($self, $objectName, $fieldName) = @_;
1074        # Declare the return variable.
1075        my $retVal;
1076        # Get the object field table.
1077        my $table = $self->GetFieldTable($objectName);
1078        # Only proceed if the field exists.
1079        if (exists $table->{$fieldName}) {
1080            # Determine the name of the relation that contains this field.
1081            $retVal = $table->{$fieldName}->{relation};
1082        }
1083        # Return the result.
1084        return $retVal;
1085    }
1086    
1087    =head3 DeleteValue
1088    
1089    C<< my $numDeleted = $erdb->DeleteValue($entityName, $id, $fieldName, $fieldValue); >>
1090    
1091    Delete secondary field values from the database. This method can be used to delete all
1092    values of a specified field for a particular entity instance, or only a single value.
1093    
1094    Secondary fields are stored in two-column relations separate from an entity's primary
1095    table, and as a result a secondary field can legitimately have no value or multiple
1096    values. Therefore, it makes sense to talk about deleting secondary fields where it
1097    would not make sense for primary fields.
1098    
1099    =over 4
1100    
1101    =item entityName
1102    
1103    Name of the entity from which the fields are to be deleted.
1104    
1105    =item id
1106    
1107    ID of the entity instance to be processed. If the instance is not found, this
1108    method will have no effect. If C<undef> is specified, all values for all of
1109    the entity instances will be deleted.
1110    
1111    =item fieldName
1112    
1113    Name of the field whose values are to be deleted.
1114    
1115    =item fieldValue (optional)
1116    
1117    Value to be deleted. If not specified, then all values of the specified field
1118    will be deleted for the entity instance. If specified, then only the values which
1119    match this parameter will be deleted.
1120    
1121    =item RETURN
1122    
1123    Returns the number of rows deleted.
1124    
1125    =back
1126    
1127    =cut
1128    
1129    sub DeleteValue {
1130        # Get the parameters.
1131        my ($self, $entityName, $id, $fieldName, $fieldValue) = @_;
1132        # Declare the return value.
1133        my $retVal = 0;
1134        # We need to set up an SQL command to do the deletion. First, we
1135        # find the name of the field's relation.
1136        my $table = $self->GetFieldTable($entityName);
1137        my $field = $table->{$fieldName};
1138        my $relation = $field->{relation};
1139        # Make sure this is a secondary field.
1140        if ($relation eq $entityName) {
1141            Confess("Cannot delete values of $fieldName for $entityName.");
1142        } else {
1143            # Set up the SQL command to delete all values.
1144            my $sql = "DELETE FROM $relation";
1145            # Build the filter.
1146            my @filters = ();
1147            my @parms = ();
1148            # Check for a filter by ID.
1149            if (defined $id) {
1150                push @filters, "id = ?";
1151                push @parms, $id;
1152            }
1153            # Check for a filter by value.
1154            if (defined $fieldValue) {
1155                push @filters, "$fieldName = ?";
1156                push @parms, $fieldValue;
1157            }
1158            # Append the filters to the command.
1159            if (@filters) {
1160                $sql .= " WHERE " . join(" AND ", @filters);
1161            }
1162            # Execute the command.
1163            my $dbh = $self->{_dbh};
1164            $retVal = $dbh->SQL($sql, 0, @parms);
1165      }      }
1166        # Return the result.
1167        return $retVal;
1168  }  }
1169    
1170  =head3 LoadTables  =head3 LoadTables
1171    
1172  C<< my $stats = $database->LoadTables($directoryName, $rebuild); >>  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>
1173    
1174  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
1175  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 1212 
1212      $directoryName =~ s!/\\$!!;      $directoryName =~ s!/\\$!!;
1213      # Declare the return variable.      # Declare the return variable.
1214      my $retVal = Stats->new();      my $retVal = Stats->new();
1215      # Get the metadata structure.      # Get the relation names.
1216      my $metaData = $self->{_metaData};      my @relNames = $self->GetTableNames();
1217      # 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}}) {  
1218              # Try to load this relation.              # Try to load this relation.
1219              my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);              my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);
1220              # Accumulate the statistics.              # Accumulate the statistics.
1221              $retVal->Accumulate($result);              $retVal->Accumulate($result);
1222          }          }
     }  
     # 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);  
     }  
1223      # Add the duration of the load to the statistical object.      # Add the duration of the load to the statistical object.
1224      $retVal->Add('duration', gettimeofday - $startTime);      $retVal->Add('duration', gettimeofday - $startTime);
1225      # Return the accumulated statistics.      # Return the accumulated statistics.
1226      return $retVal;      return $retVal;
1227  }  }
1228    
1229    
1230  =head3 GetTableNames  =head3 GetTableNames
1231    
1232  C<< my @names = $database->GetTableNames; >>  C<< my @names = $erdb->GetTableNames; >>
1233    
1234  Return a list of the relations required to implement this database.  Return a list of the relations required to implement this database.
1235    
# Line 754  Line 1246 
1246    
1247  =head3 GetEntityTypes  =head3 GetEntityTypes
1248    
1249  C<< my @names = $database->GetEntityTypes; >>  C<< my @names = $erdb->GetEntityTypes; >>
1250    
1251  Return a list of the entity type names.  Return a list of the entity type names.
1252    
# Line 769  Line 1261 
1261      return sort keys %{$entityList};      return sort keys %{$entityList};
1262  }  }
1263    
1264  =head3 Get  =head3 GetDataTypes
1265    
1266  C<< my $query = $database->Get(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  C<< my %types = ERDB::GetDataTypes(); >>
1267    
1268  This method returns a query object for entities of a specified type using a specified filter.  Return a table of ERDB data types. The table returned is a hash of hashes.
1269    The keys of the big hash are the datatypes. Each smaller hash has several
1270    values used to manage the data. The most interesting is the SQL type (key
1271    C<sqlType>) and the descriptive node (key C<notes>).
1272    
1273    Note that changing the values in the smaller hashes will seriously break
1274    things, so this data should be treated as read-only.
1275    
1276    =cut
1277    
1278    sub GetDataTypes {
1279        return %TypeTable;
1280    }
1281    
1282    
1283    =head3 IsEntity
1284    
1285    C<< my $flag = $erdb->IsEntity($entityName); >>
1286    
1287    Return TRUE if the parameter is an entity name, else FALSE.
1288    
1289    =over 4
1290    
1291    =item entityName
1292    
1293    Object name to be tested.
1294    
1295    =item RETURN
1296    
1297    Returns TRUE if the specified string is an entity name, else FALSE.
1298    
1299    =back
1300    
1301    =cut
1302    
1303    sub IsEntity {
1304        # Get the parameters.
1305        my ($self, $entityName) = @_;
1306        # Test to see if it's an entity.
1307        return exists $self->{_metaData}->{Entities}->{$entityName};
1308    }
1309    
1310    =head3 Get
1311    
1312    C<< my $query = $erdb->Get(\@objectNames, $filterClause, \@params); >>
1313    
1314    This method returns a query object for entities of a specified type using a specified filter.
1315  The filter is a standard WHERE/ORDER BY clause with question marks as parameter markers and each  The filter is a standard WHERE/ORDER BY clause with question marks as parameter markers and each
1316  field name represented in the form B<I<objectName>(I<fieldName>)>. For example, the  field name represented in the form B<I<objectName>(I<fieldName>)>. For example, the
1317  following call requests all B<Genome> objects for the genus specified in the variable  following call requests all B<Genome> objects for the genus specified in the variable
1318  $genus.  $genus.
1319    
1320  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", [$genus]); >>
1321    
1322  The WHERE clause contains a single question mark, so there is a single additional  The WHERE clause contains a single question mark, so there is a single additional
1323  parameter representing the parameter value. It would also be possible to code  parameter representing the parameter value. It would also be possible to code
1324    
1325  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>
1326    
1327  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
1328  characters inside the variable C<$genus>.  characters inside the variable C<$genus>.
# Line 796  Line 1334 
1334  It is possible to specify multiple entity and relationship names in order to retrieve more than  It is possible to specify multiple entity and relationship names in order to retrieve more than
1335  one object's data at the same time, which allows highly complex joined queries. For example,  one object's data at the same time, which allows highly complex joined queries. For example,
1336    
1337  C<< $query = $sprout->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]); >>
1338    
1339  If multiple names are specified, then the query processor will automatically determine a  If multiple names are specified, then the query processor will automatically determine a
1340  join path between the entities and relationships. The algorithm used is very simplistic.  join path between the entities and relationships. The algorithm used is very simplistic.
1341  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
1342  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
1343  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  
1344  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,
1345  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.
1346    
1347    If an entity or relationship is mentioned twice, the name for the second occurrence will
1348    be suffixed with C<2>, the third occurrence will be suffixed with C<3>, and so forth. So,
1349    for example, if we have C<['Feature', 'HasContig', 'Contig', 'HasContig']>, then the
1350    B<to-link> field of the first B<HasContig> is specified as C<HasContig(to-link)>, while
1351    the B<to-link> field of the second B<HasContig> is specified as C<HasContig2(to-link)>.
1352    
1353  =over 4  =over 4
1354    
1355  =item objectNames  =item objectNames
# Line 829  Line 1372 
1372    
1373  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
1374    
1375    Note that the case is important. Only an uppercase "ORDER BY" with a single space will
1376    be processed. The idea is to make it less likely to find the verb by accident.
1377    
1378  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
1379  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
1380  relation.  relation.
1381    
1382  =item param1, param2, ..., paramN  Finally, you can limit the number of rows returned by adding a LIMIT clause. The LIMIT must
1383    be the last thing in the filter clause, and it contains only the word "LIMIT" followed by
1384    a positive number. So, for example
1385    
1386    C<< "Genome(genus) = ? ORDER BY Genome(species) LIMIT 10" >>
1387    
1388    will only return the first ten genomes for the specified genus. The ORDER BY clause is not
1389    required. For example, to just get the first 10 genomes in the B<Genome> table, you could
1390    use
1391    
1392  Parameter values to be substituted into the filter clause.  C<< "LIMIT 10" >>
1393    
1394    =item params
1395    
1396    Reference to a list of parameter values to be substituted into the filter clause.
1397    
1398  =item RETURN  =item RETURN
1399    
# Line 847  Line 1405 
1405    
1406  sub Get {  sub Get {
1407      # Get the parameters.      # Get the parameters.
1408      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $objectNames, $filterClause, $params) = @_;
1409      # Construct the SELECT statement. The general pattern is      # Process the SQL stuff.
1410      #      my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1411      # SELECT name1.*, name2.*, ... nameN.* FROM name1, name2, ... nameN          $self->_SetupSQL($objectNames, $filterClause);
1412      #      # Create the query.
1413      my $dbh = $self->{_dbh};      my $command = "SELECT DISTINCT " . join(".*, ", @{$mappedNameListRef}) .
1414      my $command = "SELECT DISTINCT " . join('.*, ', @{$objectNames}) . ".* FROM " .          ".* $suffix";
1415                  join(', ', @{$objectNames});      my $sth = $self->_GetStatementHandle($command, $params);
1416      # Check for a filter clause.      # Now we create the relation map, which enables DBQuery to determine the order, name
1417      if ($filterClause) {      # and mapped name for each object in the query.
1418          # Here we have one, so we convert its field names and add it to the query. First,      my @relationMap = ();
1419          # We create a copy of the filter string we can work with.      for my $mappedName (@{$mappedNameListRef}) {
1420          my $filterString = $filterClause;          push @relationMap, [$mappedName, $mappedNameHashRef->{$mappedName}];
         # Next, we sort the object names by length. This helps protect us from finding  
         # object names inside other object names when we're doing our search and replace.  
         my @sortedNames = sort { length($b) - length($a) } @{$objectNames};  
         # We will also keep a list of conditions to add to the WHERE clause in order to link  
         # entities and relationships as well as primary relations to secondary ones.  
         my @joinWhere = ();  
         # The final preparatory step is to create a hash table of relation names. The  
         # table begins with the relation names already in the SELECT command.  
         my %fromNames = ();  
         for my $objectName (@sortedNames) {  
             $fromNames{$objectName} = 1;  
         }  
         # We are ready to begin. We loop through the object names, replacing each  
         # object name's field references by the corresponding SQL field reference.  
         # Along the way, if we find a secondary relation, we will need to add it  
         # to the FROM clause.  
         for my $objectName (@sortedNames) {  
             # Get the length of the object name plus 2. This is the value we add to the  
             # size of the field name to determine the size of the field reference as a  
             # whole.  
             my $nameLength = 2 + length $objectName;  
             # Get the object's field list.  
             my $fieldList = $self->_GetFieldTable($objectName);  
             # Find the field references for this object.  
             while ($filterString =~ m/$objectName\(([^)]*)\)/g) {  
                 # At this point, $1 contains the field name, and the current position  
                 # is set immediately after the final parenthesis. We pull out the name of  
                 # the field and the position and length of the field reference as a whole.  
                 my $fieldName = $1;  
                 my $len = $nameLength + length $fieldName;  
                 my $pos = pos($filterString) - $len;  
                 # Insure the field exists.  
                 if (!exists $fieldList->{$fieldName}) {  
                     Confess("Field $fieldName not found for object $objectName.");  
                 } else {  
                     # Get the field's relation.  
                     my $relationName = $fieldList->{$fieldName}->{relation};  
                     # Insure the relation is in the FROM clause.  
                     if (!exists $fromNames{$relationName}) {  
                         # Add the relation to the FROM clause.  
                         $command .= ", $relationName";  
                         # Create its join sub-clause.  
                         push @joinWhere, "$objectName.id = $relationName.id";  
                         # Denote we have it available for future fields.  
                         $fromNames{$relationName} = 1;  
                     }  
                     # Form an SQL field reference from the relation name and the field name.  
                     my $sqlReference = "$relationName." . _FixName($fieldName);  
                     # Put it into the filter string in place of the old value.  
                     substr($filterString, $pos, $len) = $sqlReference;  
                     # Reposition the search.  
                     pos $filterString = $pos + length $sqlReference;  
                 }  
             }  
         }  
         # The next step is to join the objects together. We only need to do this if there  
         # is more than one object in the object list. We start with the first object and  
         # run through the objects after it. Note also that we make a safety copy of the  
         # list before running through it.  
         my @objectList = @{$objectNames};  
         my $lastObject = shift @objectList;  
         # Get the join table.  
         my $joinTable = $self->{_metaData}->{Joins};  
         # Loop through the object list.  
         for my $thisObject (@objectList) {  
             # Look for a join.  
             my $joinKey = "$lastObject/$thisObject";  
             if (!exists $joinTable->{$joinKey}) {  
                 # Here there's no join, so we throw an error.  
                 Confess("No join exists to connect from $lastObject to $thisObject.");  
             } else {  
                 # Get the join clause and add it to the WHERE list.  
                 push @joinWhere, $joinTable->{$joinKey};  
                 # Save this object as the last object for the next iteration.  
                 $lastObject = $thisObject;  
             }  
         }  
         # Now we need to handle the whole ORDER BY thing. We'll put the order by clause  
         # in the following variable.  
         my $orderClause = "";  
         # Locate the ORDER BY verb (if any).  
         if ($filterString =~ m/^(.*)ORDER BY/g) {  
             # Here we have an ORDER BY verb. Split it off of the filter string.  
             my $pos = pos $filterString;  
             $orderClause = substr($filterString, $pos);  
             $filterString = $1;  
         }  
         # Add the filter and the join clauses (if any) to the SELECT command.  
         if ($filterString) {  
             push @joinWhere, "($filterString)";  
         }  
         if (@joinWhere) {  
             $command .= " WHERE " . join(' AND ', @joinWhere);  
         }  
         # Add the sort clause (if any) to the SELECT command.  
         if ($orderClause) {  
             $command .= " ORDER BY $orderClause";  
         }  
1421      }      }
     Trace("SQL query: $command") if T(2);  
     Trace("PARMS: '" . (join "', '", @params) . "'") if (T(3) && (@params > 0));  
     my $sth = $dbh->prepare_command($command);  
     # Execute it with the parameters bound in.  
     $sth->execute(@params) || Confess("SELECT error" . $sth->errstr());  
1422      # Return the statement object.      # Return the statement object.
1423      my $retVal = DBQuery::_new($self, $sth, @{$objectNames});      my $retVal = DBQuery::_new($self, $sth, \@relationMap);
1424      return $retVal;      return $retVal;
1425  }  }
1426    
 =head3 GetList  
1427    
 C<< my @dbObjects = $database->GetList(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  
1428    
1429  Return a list of object descriptors for the specified objects as determined by the  =head3 Search
 specified filter clause.  
1430    
1431  This method is essentially the same as L</Get> except it returns a list of objects rather  C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>
1432  than a query object that can be used to get the results one record at a time.  
1433    Perform a full text search with filtering. The search will be against a specified object
1434    in the object name list. That object will get an extra field containing the search
1435    relevance. Note that except for the search expression, the parameters of this method are
1436    the same as those for L</Get> and follow the same rules.
1437    
1438  =over 4  =over 4
1439    
1440    =item searchExpression
1441    
1442    Boolean search expression for the text fields of the target object. The default mode for
1443    a Boolean search expression is OR, but we want the default to be AND, so we will
1444    add a C<+> operator to each word with no other operator before it.
1445    
1446    =item idx
1447    
1448    Index in the I<$objectNames> list of the table to be searched in full-text mode.
1449    
1450  =item objectNames  =item objectNames
1451    
1452  List containing the names of the entity and relationship objects to be retrieved.  List containing the names of the entity and relationship objects to be retrieved.
# Line 995  Line 1461 
1461  or secondary entity relations; however, all of the entities and relationships involved must  or secondary entity relations; however, all of the entities and relationships involved must
1462  be included in the list of object names.  be included in the list of object names.
1463    
1464  The filter clause can also specify a sort order. To do this, simply follow the filter string  =item params
 with an ORDER BY clause. For example, the following filter string gets all genomes for a  
 particular genus and sorts them by species name.  
   
 C<< "Genome(genus) = ? ORDER BY Genome(species)" >>  
   
 The rules for field references in a sort order are the same as those for field references in the  
 filter clause in general; however, odd things may happen if a sort field is from a secondary  
 relation.  
   
 =item param1, param2, ..., paramN  
1465    
1466  Parameter values to be substituted into the filter clause.  Reference to a list of parameter values to be substituted into the filter clause.
1467    
1468  =item RETURN  =item RETURN
1469    
1470  Returns a list of B<DBObject>s that satisfy the query conditions.  Returns a query object for the specified search.
1471    
1472  =back  =back
1473    
1474  =cut  =cut
1475  #: Return Type @%  
1476  sub GetList {  sub Search {
1477      # Get the parameters.      # Get the parameters.
1478      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1479      # Declare the return variable.      # Declare the return variable.
1480      my @retVal = ();      my $retVal;
1481      # Perform the query.      # Create a safety copy of the parameter list. Note we have to be careful to insure
1482      my $query = $self->Get($objectNames, $filterClause, @params);      # a parameter list exists before we copy it.
1483      # Loop through the results.      my @myParams = ();
1484      while (my $object = $query->Fetch) {      if (defined $params) {
1485          push @retVal, $object;          @myParams = @{$params};
1486        }
1487        # Get the first object's structure so we have access to the searchable fields.
1488        my $object1Name = $objectNames->[$idx];
1489        my $object1Structure = $self->_GetStructure($object1Name);
1490        # Get the field list.
1491        if (! exists $object1Structure->{searchFields}) {
1492            Confess("No searchable index for $object1Name.");
1493        } else {
1494            # Get the field list.
1495            my @fields = @{$object1Structure->{searchFields}};
1496            # Clean the search expression.
1497            my $actualKeywords = $self->CleanKeywords($searchExpression);
1498            # Prefix a "+" to each uncontrolled word. This converts the default
1499            # search mode from OR to AND.
1500            $actualKeywords =~ s/(^|\s)(\w|")/$1\+$2/g;
1501            Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1502            # We need two match expressions, one for the filter clause and one in the
1503            # query itself. Both will use a parameter mark, so we need to push the
1504            # search expression onto the front of the parameter list twice.
1505            unshift @myParams, $actualKeywords, $actualKeywords;
1506            # Build the match expression.
1507            my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
1508            my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
1509            # Process the SQL stuff.
1510            my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1511                $self->_SetupSQL($objectNames, $filterClause, $matchClause);
1512            # Create the query. Note that the match clause is inserted at the front of
1513            # the select fields.
1514            my $command = "SELECT DISTINCT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .
1515                ".* $suffix";
1516            my $sth = $self->_GetStatementHandle($command, \@myParams);
1517            # Now we create the relation map, which enables DBQuery to determine the order, name
1518            # and mapped name for each object in the query.
1519            my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
1520            # Return the statement object.
1521            $retVal = DBQuery::_new($self, $sth, \@relationMap, $object1Name);
1522      }      }
1523      # Return the result.      return $retVal;
     return @retVal;  
1524  }  }
1525    
1526  =head3 ComputeObjectSentence  =head3 GetFlat
1527    
1528  C<< my $sentence = $database->ComputeObjectSentence($objectName); >>  C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>
1529    
1530  Check an object name, and if it is a relationship convert it to a relationship sentence.  This is a variation of L</GetAll> that asks for only a single field per record and
1531    returns a single flattened list.
1532    
1533  =over 4  =over 4
1534    
1535  =item objectName  =item objectNames
1536    
1537  Name of the entity or relationship.  List containing the names of the entity and relationship objects to be retrieved.
1538    
1539    =item filterClause
1540    
1541    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1542    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
1543    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
1544    parameter list as additional parameters. The fields in a filter clause can come from primary
1545    entity relations, relationship relations, or secondary entity relations; however, all of the
1546    entities and relationships involved must be included in the list of object names.
1547    
1548    =item parameterList
1549    
1550    List of the parameters to be substituted in for the parameters marks in the filter clause.
1551    
1552    =item field
1553    
1554    Name of the field to be used to get the elements of the list returned.
1555    
1556  =item RETURN  =item RETURN
1557    
1558  Returns a string containing the entity name or a relationship sentence.  Returns a list of values.
1559    
1560  =back  =back
1561    
1562  =cut  =cut
1563    #: Return Type @;
1564  sub ComputeObjectSentence {  sub GetFlat {
1565      # Get the parameters.      # Get the parameters.
1566      my ($self, $objectName) = @_;      my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
1567      # Set the default return value.      # Construct the query.
1568      my $retVal = $objectName;      my $query = $self->Get($objectNames, $filterClause, $parameterList);
1569      # Look for the object as a relationship.      # Create the result list.
1570      my $relTable = $self->{_metaData}->{Relationships};      my @retVal = ();
1571      if (exists $relTable->{$objectName}) {      # Loop through the records, adding the field values found to the result list.
1572          # Get the relationship sentence.      while (my $row = $query->Fetch()) {
1573          $retVal = _ComputeRelationshipSentence($objectName, $relTable->{$objectName});          push @retVal, $row->Value($field);
1574      }      }
1575      # Return the result.      # Return the list created.
1576      return $retVal;      return @retVal;
1577  }  }
1578    
1579  =head3 DumpRelations  =head3 SpecialFields
1580    
1581  C<< $database->DumpRelations($outputDirectory); >>  C<< my %specials = $erdb->SpecialFields($entityName); >>
1582    
1583  Write the contents of all the relations to tab-delimited files in the specified directory.  Return a hash mapping special fields in the specified entity to the value of their
1584  Each file will have the same name as the relation dumped, with an extension of DTX.  C<special> attribute. This enables the subclass to get access to the special field
1585    attributes without needed to plumb the internal ERDB data structures.
1586    
1587  =over 4  =over 4
1588    
1589  =item outputDirectory  =item entityName
1590    
1591  Name of the directory into which the relation files should be dumped.  Name of the entity whose special fields are desired.
1592    
1593    =item RETURN
1594    
1595    Returns a hash. The keys of the hash are the special field names, and the values
1596    are the values from each special field's C<special> attribute.
1597    
1598  =back  =back
1599    
1600  =cut  =cut
1601    
1602  sub DumpRelations {  sub SpecialFields {
1603      # Get the parameters.      # Get the parameters.
1604      my ($self, $outputDirectory) = @_;      my ($self, $entityName) = @_;
1605      # Now we need to run through all the relations. First, we loop through the entities.      # Declare the return variable.
1606      my $metaData = $self->{_metaData};      my %retVal = ();
1607      my $entities = $metaData->{Entities};      # Find the entity's data structure.
1608      for my $entityName (keys %{$entities}) {      my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1609          my $entityStructure = $entities->{$entityName};      # Loop through its fields, adding each special field to the return hash.
1610          # Get the entity's relations.      my $fieldHash = $entityData->{Fields};
1611          my $relationList = $entityStructure->{Relations};      for my $fieldName (keys %{$fieldHash}) {
1612          # Loop through the relations, dumping them.          my $fieldData = $fieldHash->{$fieldName};
1613          for my $relationName (keys %{$relationList}) {          if (exists $fieldData->{special}) {
1614              my $relation = $relationList->{$relationName};              $retVal{$fieldName} = $fieldData->{special};
             $self->_DumpRelation($outputDirectory, $relationName, $relation);  
         }  
1615      }      }
     # Next, we loop through the relationships.  
     my $relationships = $metaData->{Relationships};  
     for my $relationshipName (keys %{$relationships}) {  
         my $relationshipStructure = $relationships->{$relationshipName};  
         # Dump this relationship's relation.  
         $self->_DumpRelation($outputDirectory, $relationshipName, $relationshipStructure->{Relations}->{$relationshipName});  
1616      }      }
1617        # Return the result.
1618        return %retVal;
1619  }  }
1620    
1621  =head3 InsertObject  =head3 Delete
1622    
1623  C<< my $ok = $database->InsertObject($objectType, \%fieldHash); >>  C<< my $stats = $erdb->Delete($entityName, $objectID, %options); >>
1624    
1625  Insert an object into the database. The object is defined by a type name and then a hash  Delete an entity instance from the database. The instance is deleted along with all entity and
1626  of field names to values. Field values in the primary relation are represented by scalars.  relationship instances dependent on it. The definition of I<dependence> is recursive.
 (Note that for relationships, the primary relation is the B<only> relation.)  
 Field values for the other relations comprising the entity are always list references. For  
 example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases  
 C<ZP_00210270.1> and C<gi|46206278>.  
1627    
1628  C<< $database->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>  An object is always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many
1629    relationship connected to a dependent entity or if it is the "to" entity connected to a 1-to-many
1630    dependent relationship.
1631    
1632  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and  =over 4
 property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.  
1633    
1634  C<< $database->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>  =item entityName
1635    
1636  =over 4  Name of the entity type for the instance being deleted.
1637    
1638  =item newObjectType  =item objectID
1639    
1640  Type name of the object to insert.  ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),
1641    then it is presumed to by a LIKE pattern.
1642    
1643  =item fieldHash  =item options
1644    
1645  Hash of field names to values.  A hash detailing the options for this delete operation.
1646    
1647  =item RETURN  =item RETURN
1648    
1649  Returns 1 if successful, 0 if an error occurred.  Returns a statistics object indicating how many records of each particular table were
1650    deleted.
1651    
1652  =back  =back
1653    
1654  =cut  The permissible options for this method are as follows.
1655    
1656  sub InsertObject {  =over 4
1657    
1658    =item testMode
1659    
1660    If TRUE, then the delete statements will be traced, but no changes will be made to the database.
1661    
1662    =item keepRoot
1663    
1664    If TRUE, then the entity instances will not be deleted, only the dependent records.
1665    
1666    =back
1667    
1668    =cut
1669    #: Return Type $%;
1670    sub Delete {
1671      # Get the parameters.      # Get the parameters.
1672      my ($self, $newObjectType, $fieldHash) = @_;      my ($self, $entityName, $objectID, %options) = @_;
1673      # Denote that so far we appear successful.      # Declare the return variable.
1674      my $retVal = 1;      my $retVal = Stats->new();
1675      # Get the database handle.      # Get the DBKernel object.
1676      my $dbh = $self->{_dbh};      my $db = $self->{_dbh};
1677      # Get the relation list.      # We're going to generate all the paths branching out from the starting entity. One of
1678      my $relationTable = $self->_GetRelationTable($newObjectType);      # the things we have to be careful about is preventing loops. We'll use a hash to
1679      # Loop through the relations. We'll build insert statements for each one. If a relation is      # determine if we've hit a loop.
1680      # secondary, we may end up generating multiple insert statements. If an error occurs, we      my %alreadyFound = ();
1681      # stop the loop.      # These next lists will serve as our result stack. We start by pushing object lists onto
1682      my @relationList = keys %{$relationTable};      # the stack, and then popping them off to do the deletes. This means the deletes will
1683      for (my $i = 0; $retVal && $i <= $#relationList; $i++) {      # start with the longer paths before getting to the shorter ones. That, in turn, makes
1684          my $relationName = $relationList[$i];      # sure we don't delete records that might be needed to forge relationships back to the
1685          my $relationDefinition = $relationTable->{$relationName};      # original item. We have two lists-- one for TO-relationships, and one for
1686          # Get the relation's fields. For each field we will collect a value in the corresponding      # FROM-relationships and entities.
1687          # position of the @valueList array. If one of the fields is missing, we will add it to the      my @fromPathList = ();
1688          # @missing list.      my @toPathList = ();
1689          my @fieldList = @{$relationDefinition->{Fields}};      # This final list is used to remember what work still needs to be done. We push paths
1690          my @fieldNameList = ();      # onto the list, then pop them off to extend the paths. We prime it with the starting
1691          my @valueList = ();      # point. Note that we will work hard to insure that the last item on a path in the
1692          my @missing = ();      # to-do list is always an entity.
1693          my $recordCount = 1;      my @todoList = ([$entityName]);
1694          for my $fieldDescriptor (@fieldList) {      while (@todoList) {
1695              # Get the field name and save it. Note we need to fix it up so the hyphens          # Get the current path.
1696              # are converted to underscores.          my $current = pop @todoList;
1697              my $fieldName = $fieldDescriptor->{name};          # Copy it into a list.
1698              push @fieldNameList, _FixName($fieldName);          my @stackedPath = @{$current};
1699              # Look for the named field in the incoming structure. Note that we are looking          # Pull off the last item on the path. It will always be an entity.
1700              # for the real field name, not the fixed-up one!          my $myEntityName = pop @stackedPath;
1701              if (exists $fieldHash->{$fieldName}) {          # Add it to the alreadyFound list.
1702                  # Here we found the field. Stash it in the value list.          $alreadyFound{$myEntityName} = 1;
1703                  my $value = $fieldHash->{$fieldName};          # Figure out if we need to delete this entity.
1704                  push @valueList, $value;          if ($myEntityName ne $entityName || ! $options{keepRoot}) {
1705                  # If the value is a list, we may need to increment the record count.              # Get the entity data.
1706                  if (ref $value eq "ARRAY") {              my $entityData = $self->_GetStructure($myEntityName);
1707                      my $thisCount = @{$value};              # Loop through the entity's relations. A DELETE command will be needed for each of them.
1708                      if ($recordCount == 1) {              my $relations = $entityData->{Relations};
1709                          # Here we have our first list, so we save its count.              for my $relation (keys %{$relations}) {
1710                          $recordCount = $thisCount;                  my @augmentedList = (@stackedPath, $relation);
1711                      } elsif ($recordCount != $thisCount) {                  push @fromPathList, \@augmentedList;
                         # Here we have a second list, so its length has to match the  
                         # previous lists.  
                         Trace("Field $value in new $newObjectType object has an invalid list length $thisCount. Expected $recordCount.") if T(0);  
                         $retVal = 0;  
1712                      }                      }
1713                  }                  }
1714            # Now we need to look for relationships connected to this entity.
1715            my $relationshipList = $self->{_metaData}->{Relationships};
1716            for my $relationshipName (keys %{$relationshipList}) {
1717                my $relationship = $relationshipList->{$relationshipName};
1718                # Check the FROM field. We're only interested if it's us.
1719                if ($relationship->{from} eq $myEntityName) {
1720                    # Add the path to this relationship.
1721                    my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1722                    push @fromPathList, \@augmentedList;
1723                    # Check the arity. If it's MM we're done. If it's 1M
1724                    # and the target hasn't been seen yet, we want to
1725                    # stack the entity for future processing.
1726                    if ($relationship->{arity} eq '1M') {
1727                        my $toEntity = $relationship->{to};
1728                        if (! exists $alreadyFound{$toEntity}) {
1729                            # Here we have a new entity that's dependent on
1730                            # the current entity, so we need to stack it.
1731                            my @stackList = (@augmentedList, $toEntity);
1732                            push @fromPathList, \@stackList;
1733              } else {              } else {
1734                  # Here the field is not present. Flag it as missing.                          Trace("$toEntity ignored because it occurred previously.") if T(4);
                 push @missing, $fieldName;  
1735              }              }
1736          }          }
         # If we are the primary relation, add the new-record flag.  
         if ($relationName eq $newObjectType) {  
             push @valueList, 1;  
             push @fieldNameList, "new_record";  
1737          }          }
1738          # Only proceed if there are no missing fields.              # Now check the TO field. In this case only the relationship needs
1739          if (@missing > 0) {              # deletion.
1740              Trace("Relation $relationName for $newObjectType skipped due to missing fields: " .              if ($relationship->{to} eq $myEntityName) {
1741                  join(' ', @missing)) if T(1);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1742          } else {                  push @toPathList, \@augmentedList;
             # Build the INSERT statement.  
             my $statement = "INSERT INTO $relationName (" . join (', ', @fieldNameList) .  
                 ") VALUES (";  
             # Create a marker list of the proper size and put it in the statement.  
             my @markers = ();  
             while (@markers < @fieldNameList) { push @markers, '?'; }  
             $statement .= join(', ', @markers) . ")";  
             # We have the insert statement, so prepare it.  
             my $sth = $dbh->prepare_command($statement);  
             Trace("Insert statement prepared: $statement") if T(3);  
             # Now we loop through the values. If a value is scalar, we use it unmodified. If it's  
             # a list, we use the current element. The values are stored in the @parameterList array.  
             my $done = 0;  
             for (my $i = 0; $i < $recordCount; $i++) {  
                 # Clear the parameter list array.  
                 my @parameterList = ();  
                 # Loop through the values.  
                 for my $value (@valueList) {  
                     # Check to see if this is a scalar value.  
                     if (ref $value eq "ARRAY") {  
                         # Here we have a list value. Pull the current entry.  
                         push @parameterList, $value->[$i];  
                     } else {  
                         # Here we have a scalar value. Use it unmodified.  
                         push @parameterList, $value;  
1743                      }                      }
1744                  }                  }
                 # Execute the INSERT statement with the specified parameter list.  
                 $retVal = $sth->execute(@parameterList);  
                 if (!$retVal) {  
                     my $errorString = $sth->errstr();  
                     Trace("Insert error: $errorString.") if T(0);  
1745                  }                  }
1746        # Create the first qualifier for the WHERE clause. This selects the
1747        # keys of the primary entity records to be deleted. When we're deleting
1748        # from a dependent table, we construct a join path from the first qualifier
1749        # to the table containing the dependent records to delete.
1750        my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
1751        # We need to make two passes. The first is through the to-list, and
1752        # the second through the from-list. The from-list is second because
1753        # the to-list may need to pass through some of the entities the
1754        # from-list would delete.
1755        my %stackList = ( from_link => \@fromPathList, to_link => \@toPathList );
1756        # Now it's time to do the deletes. We do it in two passes.
1757        for my $keyName ('to_link', 'from_link') {
1758            # Get the list for this key.
1759            my @pathList = @{$stackList{$keyName}};
1760            Trace(scalar(@pathList) . " entries in path list for $keyName.") if T(3);
1761            # Loop through this list.
1762            while (my $path = pop @pathList) {
1763                # Get the table whose rows are to be deleted.
1764                my @pathTables = @{$path};
1765                # Start the DELETE statement. We need to call DBKernel because the
1766                # syntax of a DELETE-USING varies among DBMSs.
1767                my $target = $pathTables[$#pathTables];
1768                my $stmt = $db->SetUsing(@pathTables);
1769                # Now start the WHERE. The first thing is the ID field from the starting table. That
1770                # starting table will either be the entity relation or one of the entity's
1771                # sub-relations.
1772                $stmt .= " WHERE $pathTables[0].id $qualifier";
1773                # Now we run through the remaining entities in the path, connecting them up.
1774                for (my $i = 1; $i <= $#pathTables; $i += 2) {
1775                    # Connect the current relationship to the preceding entity.
1776                    my ($entity, $rel) = @pathTables[$i-1,$i];
1777                    # The style of connection depends on the direction of the relationship.
1778                    $stmt .= " AND $entity.id = $rel.$keyName";
1779                    if ($i + 1 <= $#pathTables) {
1780                        # Here there's a next entity, so connect that to the relationship's
1781                        # to-link.
1782                        my $entity2 = $pathTables[$i+1];
1783                        $stmt .= " AND $rel.to_link = $entity2.id";
1784                    }
1785                }
1786                # Now we have our desired DELETE statement.
1787                if ($options{testMode}) {
1788                    # Here the user wants to trace without executing.
1789                    Trace($stmt) if T(0);
1790                } else {
1791                    # Here we can delete. Note that the SQL method dies with a confession
1792                    # if an error occurs, so we just go ahead and do it.
1793                    Trace("Executing delete from $target using '$objectID'.") if T(3);
1794                    my $rv = $db->SQL($stmt, 0, $objectID);
1795                    # Accumulate the statistics for this delete. The only rows deleted
1796                    # are from the target table, so we use its name to record the
1797                    # statistic.
1798                    $retVal->Add($target, $rv);
1799              }              }
1800          }          }
1801      }      }
1802      # Return the success indicator.      # Return the result.
1803      return $retVal;      return $retVal;
1804  }  }
1805    
1806  =head3 LoadTable  =head3 Disconnect
1807    
1808  C<< my %results = $database->LoadTable($fileName, $relationName, $truncateFlag); >>  C<< $erdb->Disconnect($relationshipName, $originEntityName, $originEntityID); >>
1809    
1810  Load data from a tab-delimited file into a specified table, optionally re-creating the table  Disconnect an entity instance from all the objects to which it is related. This
1811  first.  will delete each relationship instance that connects to the specified entity.
1812    
1813  =over 4  =over 4
1814    
1815  =item fileName  =item relationshipName
   
 Name of the file from which the table data should be loaded.  
   
 =item relationName  
1816    
1817  Name of the relation to be loaded. This is the same as the table name.  Name of the relationship whose instances are to be deleted.
1818    
1819  =item truncateFlag  =item originEntityName
1820    
1821  TRUE if the table should be dropped and re-created, else FALSE  Name of the entity that is to be disconnected.
1822    
1823  =item RETURN  =item originEntityID
1824    
1825  Returns a statistical object containing the number of records read and a list of  ID of the entity that is to be disconnected.
 the error messages.  
1826    
1827  =back  =back
1828    
1829  =cut  =cut
1830  sub LoadTable {  
1831    sub Disconnect {
1832      # Get the parameters.      # Get the parameters.
1833      my ($self, $fileName, $relationName, $truncateFlag) = @_;      my ($self, $relationshipName, $originEntityName, $originEntityID) = @_;
1834      # Create the statistical return object.      # Get the relationship descriptor.
1835      my $retVal = _GetLoadStats();      my $structure = $self->_GetStructure($relationshipName);
1836      # Trace the fact of the load.      # Insure we have a relationship.
1837      Trace("Loading table $relationName from $fileName") if T(2);      if (! exists $structure->{from}) {
1838            Confess("$relationshipName is not a relationship in the database.");
1839        } else {
1840      # Get the database handle.      # Get the database handle.
1841      my $dbh = $self->{_dbh};      my $dbh = $self->{_dbh};
1842      # Get the relation data.          # We'll set this value to 1 if we find our entity.
1843      my $relation = $self->_FindRelation($relationName);          my $found = 0;
1844      # Check the truncation flag.          # Loop through the ends of the relationship.
1845      if ($truncateFlag) {          for my $dir ('from', 'to') {
1846          Trace("Creating table $relationName") if T(2);              if ($structure->{$dir} eq $originEntityName) {
1847          # Re-create the table without its index.                  # Delete all relationship instances on this side of the entity instance.
1848          $self->CreateTable($relationName, 0);                  Trace("Disconnecting in $dir direction with ID \"$originEntityID\".");
1849          # If this is a pre-index DBMS, create the index here.                  $dbh->SQL("DELETE FROM $relationshipName WHERE ${dir}_link = ?", 0, $originEntityID);
1850          if ($dbh->{_preIndex}) {                  $found = 1;
             eval {  
                 $self->CreateIndex($relationName);  
             };  
             if ($@) {  
                 $retVal->AddMessage($@);  
             }  
         }  
1851      }      }
     # 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);  
     # Load the table.  
     my $rv;  
     eval {  
         $rv = $dbh->load_table(file => $tempName, tbl => $relationName);  
     };  
     if (!defined $rv) {  
         $retVal->AddMessage($@) if ($@);  
         $retVal->AddMessage("Table load failed for $relationName using $tempName.");  
         Trace("Table load failed for $relationName.") if T(1);  
     } else {  
         # Here we successfully loaded the table. Trace the number of records loaded.  
         Trace("$retVal->{records} records read for $relationName.") if T(2);  
         # If we're rebuilding, we need to create the table indexes.  
         if ($truncateFlag && ! $dbh->{_preIndex}) {  
             eval {  
                 $self->CreateIndex($relationName);  
             };  
             if ($@) {  
                 $retVal->AddMessage($@);  
1852              }              }
1853            # Insure we found the entity on at least one end.
1854            if (! $found) {
1855                Confess("Entity \"$originEntityName\" does not use $relationshipName.");
1856          }          }
         # Analyze the table to help optimize tables.  
1857      }      }
     # Commit the database changes.  
     $dbh->commit_tran;  
     $dbh->vacuum_it($relationName);  
     # Delete the temporary file.  
     unlink $tempName;  
     # Return the statistics.  
     return $retVal;  
1858  }  }
1859    
1860  =head3 GenerateEntity  =head3 DeleteRow
1861    
1862  C<< my $fieldHash = $database->GenerateEntity($id, $type, \%values); >>  C<< $erdb->DeleteRow($relationshipName, $fromLink, $toLink, \%values); >>
1863    
1864  Generate the data for a new entity instance. This method creates a field hash suitable for  Delete a row from a relationship. In most cases, only the from-link and to-link are
1865  passing as a parameter to L</InsertObject>. The ID is specified by the callr, but the rest  needed; however, for relationships with intersection data values can be specified
1866  of the fields are generated using information in the database schema.  for the other fields using a hash.
   
 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.  
1867    
1868  =over 4  =over 4
1869    
1870  =item id  =item relationshipName
1871    
1872  ID to assign to the new entity.  Name of the relationship from which the row is to be deleted.
1873    
1874  =item type  =item fromLink
1875    
1876    ID of the entity instance in the From direction.
1877    
1878    =item toLink
1879    
1880  Type name for the new entity.  ID of the entity instance in the To direction.
1881    
1882  =item values  =item values
1883    
1884  Hash containing additional values that might be needed by the data generation methods (optional).  Reference to a hash of other values to be used for filtering the delete.
1885    
1886  =back  =back
1887    
1888  =cut  =cut
1889    
1890  sub GenerateEntity {  sub DeleteRow {
1891      # Get the parameters.      # Get the parameters.
1892      my ($self, $id, $type, $values) = @_;      my ($self, $relationshipName, $fromLink, $toLink, $values) = @_;
1893      # Create the return hash.      # Create a hash of all the filter information.
1894      my $this = { id => $id };      my %filter = ('from-link' => $fromLink, 'to-link' => $toLink);
1895      # Get the metadata structure.      if (defined $values) {
1896      my $metadata = $self->{_metaData};          for my $key (keys %{$values}) {
1897      # Get this entity's list of fields.              $filter{$key} = $values->{$key};
1898      if (!exists $metadata->{Entities}->{$type}) {          }
1899          Confess("Unrecognized entity type $type in GenerateEntity.");      }
1900      } else {      # Build an SQL statement out of the hash.
1901          my $entity = $metadata->{Entities}->{$type};      my @filters = ();
1902          my $fields = $entity->{Fields};      my @parms = ();
1903          # Generate data from the fields.      for my $key (keys %filter) {
1904          _GenerateFields($this, $fields, $type, $values);          push @filters, _FixName($key) . " = ?";
1905            push @parms, $filter{$key};
1906      }      }
1907      # Return the hash created.      Trace("Parms for delete row are " . join(", ", map { "\"$_\"" } @parms) . ".") if T(SQL => 4);
1908      return $this;      my $command = "DELETE FROM $relationshipName WHERE " .
1909                      join(" AND ", @filters);
1910        # Execute it.
1911        my $dbh = $self->{_dbh};
1912        $dbh->SQL($command, undef, @parms);
1913  }  }
1914    
1915  =head3 GetEntity  =head3 SortNeeded
1916    
1917  C<< my $entityObject = $sprout->GetEntity($entityType, $ID); >>  C<< my $parms = $erdb->SortNeeded($relationName); >>
1918    
1919  Return an object describing the entity instance with a specified ID.  Return the pipe command for the sort that should be applied to the specified
1920    relation when creating the load file.
1921    
1922  =over 4  For example, if the load file should be sorted ascending by the first
1923    field, this method would return
1924    
1925  =item entityType      sort -k1 -t"\t"
1926    
1927  Entity type name.  If the first field is numeric, the method would return
1928    
1929  =item ID      sort -k1n -t"\t"
1930    
1931  ID of the desired entity.  Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate
1932    keys using a sort.
1933    
1934  =item RETURN  =over 4
1935    
1936  Returns a B<DBObject> representing the desired entity instance, or an undefined value if no  =item relationName
1937  instance is found with the specified key.  
1938    Name of the relation to be examined.
1939    
1940    =item
1941    
1942    Returns the sort command to use for sorting the relation, suitable for piping.
1943    
1944  =back  =back
1945    
1946  =cut  =cut
1947    #: Return Type $;
1948  sub GetEntity {  sub SortNeeded {
1949      # Get the parameters.      # Get the parameters.
1950      my ($self, $entityType, $ID) = @_;      my ($self, $relationName) = @_;
1951      # Create a query.      # Declare a descriptor to hold the names of the key fields.
1952      my $query = $self->Get([$entityType], "$entityType(id) = ?", $ID);      my @keyNames = ();
1953      # Get the first (and only) object.      # Get the relation structure.
1954      my $retVal = $query->Fetch();      my $relationData = $self->_FindRelation($relationName);
1955        # Find out if the relation is a primary entity relation,
1956        # a relationship relation, or a secondary entity relation.
1957        my $entityTable = $self->{_metaData}->{Entities};
1958        my $relationshipTable = $self->{_metaData}->{Relationships};
1959        if (exists $entityTable->{$relationName}) {
1960            # Here we have a primary entity relation.
1961            push @keyNames, "id";
1962        } elsif (exists $relationshipTable->{$relationName}) {
1963            # Here we have a relationship. We sort using the FROM index.
1964            my $relationshipData = $relationshipTable->{$relationName};
1965            my $index = $relationData->{Indexes}->{idxFrom};
1966            push @keyNames, @{$index->{IndexFields}};
1967        } else {
1968            # Here we have a secondary entity relation, so we have a sort on the ID field.
1969            push @keyNames, "id";
1970        }
1971        # Now we parse the key names into sort parameters. First, we prime the return
1972        # string.
1973        my $retVal = "sort -t\"\t\" ";
1974        # Get the relation's field list.
1975        my @fields = @{$relationData->{Fields}};
1976        # Loop through the keys.
1977        for my $keyData (@keyNames) {
1978            # Get the key and the ordering.
1979            my ($keyName, $ordering);
1980            if ($keyData =~ /^([^ ]+) DESC/) {
1981                ($keyName, $ordering) = ($1, "descending");
1982            } else {
1983                ($keyName, $ordering) = ($keyData, "ascending");
1984            }
1985            # Find the key's position and type.
1986            my $fieldSpec;
1987            for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {
1988                my $thisField = $fields[$i];
1989                if ($thisField->{name} eq $keyName) {
1990                    # Get the sort modifier for this field type. The modifier
1991                    # decides whether we're using a character, numeric, or
1992                    # floating-point sort.
1993                    my $modifier = $TypeTable{$thisField->{type}}->{sort};
1994                    # If the index is descending for this field, denote we want
1995                    # to reverse the sort order on this field.
1996                    if ($ordering eq 'descending') {
1997                        $modifier .= "r";
1998                    }
1999                    # Store the position and modifier into the field spec, which
2000                    # will stop the inner loop. Note that the field number is
2001                    # 1-based in the sort command, so we have to increment the
2002                    # index.
2003                    $fieldSpec = ($i + 1) . $modifier;
2004                }
2005            }
2006            # Add this field to the sort command.
2007            $retVal .= " -k$fieldSpec";
2008        }
2009      # Return the result.      # Return the result.
2010      return $retVal;      return $retVal;
2011  }  }
2012    
2013  =head3 GetEntityValues  =head3 GetList
2014    
2015  C<< my @values = GetEntityValues($entityType, $ID, \@fields); >>  C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>
2016    
2017  Return a list of values from a specified entity instance.  Return a list of object descriptors for the specified objects as determined by the
2018    specified filter clause.
2019    
2020    This method is essentially the same as L</Get> except it returns a list of objects rather
2021    than a query object that can be used to get the results one record at a time.
2022    
2023  =over 4  =over 4
2024    
2025  =item entityType  =item objectNames
2026    
2027  Entity type name.  List containing the names of the entity and relationship objects to be retrieved.
2028    
2029  =item ID  =item filterClause
2030    
2031  ID of the desired entity.  WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
2032    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
2033    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
2034    in the filter clause should be added to the parameter list as additional parameters. The
2035    fields in a filter clause can come from primary entity relations, relationship relations,
2036    or secondary entity relations; however, all of the entities and relationships involved must
2037    be included in the list of object names.
2038    
2039  =item fields  The filter clause can also specify a sort order. To do this, simply follow the filter string
2040    with an ORDER BY clause. For example, the following filter string gets all genomes for a
2041    particular genus and sorts them by species name.
2042    
2043  List of field names, each of the form I<objectName>C<(>I<fieldName>C<)>.  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
2044    
2045    The rules for field references in a sort order are the same as those for field references in the
2046    filter clause in general; however, odd things may happen if a sort field is from a secondary
2047    relation.
2048    
2049    =item params
2050    
2051    Reference to a list of parameter values to be substituted into the filter clause.
2052    
2053  =item RETURN  =item RETURN
2054    
2055  Returns a flattened list of the values of the specified fields for the specified entity.  Returns a list of B<DBObject>s that satisfy the query conditions.
2056    
2057  =back  =back
2058    
2059  =cut  =cut
2060    #: Return Type @%
2061  sub GetEntityValues {  sub GetList {
2062      # Get the parameters.      # Get the parameters.
2063      my ($self, $entityType, $ID, $fields) = @_;      my ($self, $objectNames, $filterClause, $params) = @_;
2064      # Get the specified entity.      # Declare the return variable.
     my $entity = $self->GetEntity($entityType, $ID);  
     # Declare the return list.  
2065      my @retVal = ();      my @retVal = ();
2066      # If we found the entity, push the values into the return list.      # Perform the query.
2067      if ($entity) {      my $query = $self->Get($objectNames, $filterClause, $params);
2068          push @retVal, $entity->Values($fields);      # Loop through the results.
2069        while (my $object = $query->Fetch) {
2070            push @retVal, $object;
2071      }      }
2072      # Return the result.      # Return the result.
2073      return @retVal;      return @retVal;
2074  }  }
2075    
2076  =head3 GetAll  =head3 GetCount
2077    
2078  C<< my @list = $sprout->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>  C<< my $count = $erdb->GetCount(\@objectNames, $filter, \@params); >>
2079    
2080  Return a list of values taken from the objects returned by a query. The first three  Return the number of rows found by a specified query. This method would
2081  parameters correspond to the parameters of the L</Get> method. The final parameter is  normally be used to count the records in a single table. For example, in a
2082  a list of the fields desired from each record found by the query. The field name  genetics database
 syntax is the standard syntax used for fields in the B<ERDB> system--  
 B<I<objectName>(I<fieldName>)>-- where I<objectName> is the name of the relevant entity  
 or relationship and I<fieldName> is the name of the field.  
2083    
2084  The list returned will be a list of lists. Each element of the list will contain      my $count = $erdb->GetCount(['Genome'], 'Genome(genus-species) LIKE ?', ['homo %']);
 the values returned for the fields specified in the fourth parameter. If one of the  
 fields specified returns multiple values, they are flattened in with the rest. For  
 example, the following call will return a list of the features in a particular  
 spreadsheet cell, and each feature will be represented by a list containing the  
 feature ID followed by all of its aliases.  
2085    
2086  C<< $query = $sprout->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>  would return the number of genomes for the genus I<homo>. It is conceivable, however,
2087    to use it to return records based on a join. For example,
2088    
2089  =over 4      my $count = $erdb->GetCount(['HasFeature', 'Genome'], 'Genome(genus-species) LIKE ?',
2090                                    ['homo %']);
2091    
2092  =item objectNames  would return the number of features for genomes in the genus I<homo>. Note that
2093    only the rows from the first table are counted. If the above command were
2094    
2095  List containing the names of the entity and relationship objects to be retrieved.      my $count = $erdb->GetCount(['Genome', 'Feature'], 'Genome(genus-species) LIKE ?',
2096                                    ['homo %']);
2097    
2098  =item filterClause  it would return the number of genomes, not the number of genome/feature pairs.
2099    
2100  WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  =over 4
 be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form  
 B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the  
 parameter list as additional parameters. The fields in a filter clause can come from primary  
 entity relations, relationship relations, or secondary entity relations; however, all of the  
 entities and relationships involved must be included in the list of object names.  
2101    
2102  =item parameterList  =item objectNames
2103    
2104  List of the parameters to be substituted in for the parameters marks in the filter clause.  Reference to a list of the objects (entities and relationships) included in the
2105    query.
2106    
2107  =item fields  =item filter
2108    
2109  List of the fields to be returned in each element of the list returned.  A filter clause for restricting the query. The rules are the same as for the L</Get>
2110    method.
2111    
2112  =item count  =item params
2113    
2114  Maximum number of records to return. If omitted or 0, all available records will be returned.  Reference to a list of the parameter values to be substituted for the parameter marks
2115    in the filter.
2116    
2117  =item RETURN  =item RETURN
2118    
2119  Returns a list of list references. Each element of the return list contains the values for the  Returns a count of the number of records in the first table that would satisfy
2120  fields specified in the B<fields> parameter.  the query.
2121    
2122  =back  =back
2123    
2124  =cut  =cut
2125  #: Return Type @@;  
2126  sub GetAll {  sub GetCount {
2127        # Get the parameters.
2128        my ($self, $objectNames, $filter, $params) = @_;
2129        # Insure the params argument is an array reference if the caller left it off.
2130        if (! defined($params)) {
2131            $params = [];
2132        }
2133        # Declare the return variable.
2134        my $retVal;
2135        # Find out if we're counting an entity or a relationship.
2136        my $countedField;
2137        if ($self->IsEntity($objectNames->[0])) {
2138            $countedField = "id";
2139        } else {
2140            # For a relationship we count the to-link because it's usually more
2141            # numerous. Note we're automatically converting to the SQL form
2142            # of the field name (to_link vs. to-link).
2143            $countedField = "to_link";
2144        }
2145        # Create the SQL command suffix to get the desired records.
2146        my ($suffix, $mappedNameListRef, $mappedNameHashRef) = $self->_SetupSQL($objectNames,
2147                                                                                $filter);
2148        # Prefix it with text telling it we want a record count.
2149        my $firstObject = $mappedNameListRef->[0];
2150        my $command = "SELECT COUNT($firstObject.$countedField) $suffix";
2151        # Prepare and execute the command.
2152        my $sth = $self->_GetStatementHandle($command, $params);
2153        # Get the count value.
2154        ($retVal) = $sth->fetchrow_array();
2155        # Check for a problem.
2156        if (! defined($retVal)) {
2157            if ($sth->err) {
2158                # Here we had an SQL error.
2159                Confess("Error retrieving row count: " . $sth->errstr());
2160            } else {
2161                # Here we have no result.
2162                Confess("No result attempting to retrieve row count.");
2163            }
2164        }
2165        # Return the result.
2166        return $retVal;
2167    }
2168    
2169    =head3 ComputeObjectSentence
2170    
2171    C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>
2172    
2173    Check an object name, and if it is a relationship convert it to a relationship sentence.
2174    
2175    =over 4
2176    
2177    =item objectName
2178    
2179    Name of the entity or relationship.
2180    
2181    =item RETURN
2182    
2183    Returns a string containing the entity name or a relationship sentence.
2184    
2185    =back
2186    
2187    =cut
2188    
2189    sub ComputeObjectSentence {
2190        # Get the parameters.
2191        my ($self, $objectName) = @_;
2192        # Set the default return value.
2193        my $retVal = $objectName;
2194        # Look for the object as a relationship.
2195        my $relTable = $self->{_metaData}->{Relationships};
2196        if (exists $relTable->{$objectName}) {
2197            # Get the relationship sentence.
2198            $retVal = _ComputeRelationshipSentence($objectName, $relTable->{$objectName});
2199        }
2200        # Return the result.
2201        return $retVal;
2202    }
2203    
2204    =head3 DumpRelations
2205    
2206    C<< $erdb->DumpRelations($outputDirectory); >>
2207    
2208    Write the contents of all the relations to tab-delimited files in the specified directory.
2209    Each file will have the same name as the relation dumped, with an extension of DTX.
2210    
2211    =over 4
2212    
2213    =item outputDirectory
2214    
2215    Name of the directory into which the relation files should be dumped.
2216    
2217    =back
2218    
2219    =cut
2220    
2221    sub DumpRelations {
2222        # Get the parameters.
2223        my ($self, $outputDirectory) = @_;
2224        # Now we need to run through all the relations. First, we loop through the entities.
2225        my $metaData = $self->{_metaData};
2226        my $entities = $metaData->{Entities};
2227        for my $entityName (keys %{$entities}) {
2228            my $entityStructure = $entities->{$entityName};
2229            # Get the entity's relations.
2230            my $relationList = $entityStructure->{Relations};
2231            # Loop through the relations, dumping them.
2232            for my $relationName (keys %{$relationList}) {
2233                my $relation = $relationList->{$relationName};
2234                $self->_DumpRelation($outputDirectory, $relationName, $relation);
2235            }
2236        }
2237        # Next, we loop through the relationships.
2238        my $relationships = $metaData->{Relationships};
2239        for my $relationshipName (keys %{$relationships}) {
2240            my $relationshipStructure = $relationships->{$relationshipName};
2241            # Dump this relationship's relation.
2242            $self->_DumpRelation($outputDirectory, $relationshipName, $relationshipStructure->{Relations}->{$relationshipName});
2243        }
2244    }
2245    
2246    =head3 InsertValue
2247    
2248    C<< $erdb->InsertValue($entityID, $fieldName, $value); >>
2249    
2250    This method will insert a new value into the database. The value must be one
2251    associated with a secondary relation, since primary values cannot be inserted:
2252    they occur exactly once. Secondary values, on the other hand, can be missing
2253    or multiply-occurring.
2254    
2255    =over 4
2256    
2257    =item entityID
2258    
2259    ID of the object that is to receive the new value.
2260    
2261    =item fieldName
2262    
2263    Field name for the new value-- this includes the entity name, since
2264    field names are of the format I<objectName>C<(>I<fieldName>C<)>.
2265    
2266    =item value
2267    
2268    New value to be put in the field.
2269    
2270    =back
2271    
2272    =cut
2273    
2274    sub InsertValue {
2275        # Get the parameters.
2276        my ($self, $entityID, $fieldName, $value) = @_;
2277        # Parse the entity name and the real field name.
2278        if ($fieldName =~ /^([^(]+)\(([^)]+)\)/) {
2279            my $entityName = $1;
2280            my $fieldTitle = $2;
2281            # Get its descriptor.
2282            if (!$self->IsEntity($entityName)) {
2283                Confess("$entityName is not a valid entity.");
2284            } else {
2285                my $entityData = $self->{_metaData}->{Entities}->{$entityName};
2286                # Find the relation containing this field.
2287                my $fieldHash = $entityData->{Fields};
2288                if (! exists $fieldHash->{$fieldTitle}) {
2289                    Confess("$fieldTitle not found in $entityName.");
2290                } else {
2291                    my $relation = $fieldHash->{$fieldTitle}->{relation};
2292                    if ($relation eq $entityName) {
2293                        Confess("Cannot do InsertValue on primary field $fieldTitle of $entityName.");
2294                    } else {
2295                        # Now we can create an INSERT statement.
2296                        my $dbh = $self->{_dbh};
2297                        my $fixedName = _FixName($fieldTitle);
2298                        my $statement = "INSERT INTO $relation (id, $fixedName) VALUES(?, ?)";
2299                        # Execute the command.
2300                        $dbh->SQL($statement, 0, $entityID, $value);
2301                    }
2302                }
2303            }
2304        } else {
2305            Confess("$fieldName is not a valid field name.");
2306        }
2307    }
2308    
2309    =head3 InsertObject
2310    
2311    C<< $erdb->InsertObject($objectType, \%fieldHash); >>
2312    
2313    Insert an object into the database. The object is defined by a type name and then a hash
2314    of field names to values. Field values in the primary relation are represented by scalars.
2315    (Note that for relationships, the primary relation is the B<only> relation.)
2316    Field values for the other relations comprising the entity are always list references. For
2317    example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases
2318    C<ZP_00210270.1> and C<gi|46206278>.
2319    
2320    C<< $erdb->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>
2321    
2322    The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
2323    property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
2324    
2325    C<< $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>
2326    
2327    =over 4
2328    
2329    =item newObjectType
2330    
2331    Type name of the object to insert.
2332    
2333    =item fieldHash
2334    
2335    Hash of field names to values.
2336    
2337    =back
2338    
2339    =cut
2340    
2341    sub InsertObject {
2342        # Get the parameters.
2343        my ($self, $newObjectType, $fieldHash) = @_;
2344        # Denote that so far we appear successful.
2345        my $retVal = 1;
2346        # Get the database handle.
2347        my $dbh = $self->{_dbh};
2348        # Get the relation list.
2349        my $relationTable = $self->_GetRelationTable($newObjectType);
2350        # Loop through the relations. We'll build insert statements for each one. If a relation is
2351        # secondary, we may end up generating multiple insert statements. If an error occurs, we
2352        # stop the loop.
2353        my @relationList = keys %{$relationTable};
2354        for (my $i = 0; $retVal && $i <= $#relationList; $i++) {
2355            my $relationName = $relationList[$i];
2356            my $relationDefinition = $relationTable->{$relationName};
2357            # Get the relation's fields. For each field we will collect a value in the corresponding
2358            # position of the @valueList array. If one of the fields is missing, we will add it to the
2359            # @missing list.
2360            my @fieldList = @{$relationDefinition->{Fields}};
2361            my @fieldNameList = ();
2362            my @valueList = ();
2363            my @missing = ();
2364            my $recordCount = 1;
2365            for my $fieldDescriptor (@fieldList) {
2366                # Get the field name and save it. Note we need to fix it up so the hyphens
2367                # are converted to underscores.
2368                my $fieldName = $fieldDescriptor->{name};
2369                push @fieldNameList, _FixName($fieldName);
2370                # Look for the named field in the incoming structure. Note that we are looking
2371                # for the real field name, not the fixed-up one!
2372                if (exists $fieldHash->{$fieldName}) {
2373                    # Here we found the field. Stash it in the value list.
2374                    my $value = $fieldHash->{$fieldName};
2375                    push @valueList, $value;
2376                    # If the value is a list, we may need to increment the record count.
2377                    if (ref $value eq "ARRAY") {
2378                        my $thisCount = @{$value};
2379                        if ($recordCount == 1) {
2380                            # Here we have our first list, so we save its count.
2381                            $recordCount = $thisCount;
2382                        } elsif ($recordCount != $thisCount) {
2383                            # Here we have a second list, so its length has to match the
2384                            # previous lists.
2385                            Trace("Field $value in new $newObjectType object has an invalid list length $thisCount. Expected $recordCount.") if T(0);
2386                            $retVal = 0;
2387                        }
2388                    }
2389                } else {
2390                    # Here the field is not present. Flag it as missing.
2391                    push @missing, $fieldName;
2392                }
2393            }
2394            # If we are the primary relation, add the new-record flag.
2395            if ($relationName eq $newObjectType) {
2396                push @valueList, 1;
2397                push @fieldNameList, "new_record";
2398            }
2399            # Only proceed if there are no missing fields.
2400            if (@missing > 0) {
2401                Trace("Relation $relationName for $newObjectType skipped due to missing fields: " .
2402                    join(' ', @missing)) if T(1);
2403            } else {
2404                # Build the INSERT statement.
2405                my $statement = "INSERT INTO $relationName (" . join (', ', @fieldNameList) .
2406                    ") VALUES (";
2407                # Create a marker list of the proper size and put it in the statement.
2408                my @markers = ();
2409                while (@markers < @fieldNameList) { push @markers, '?'; }
2410                $statement .= join(', ', @markers) . ")";
2411                # We have the insert statement, so prepare it.
2412                my $sth = $dbh->prepare_command($statement);
2413                Trace("Insert statement prepared: $statement") if T(3);
2414                # Now we loop through the values. If a value is scalar, we use it unmodified. If it's
2415                # a list, we use the current element. The values are stored in the @parameterList array.
2416                my $done = 0;
2417                for (my $i = 0; $i < $recordCount; $i++) {
2418                    # Clear the parameter list array.
2419                    my @parameterList = ();
2420                    # Loop through the values.
2421                    for my $value (@valueList) {
2422                        # Check to see if this is a scalar value.
2423                        if (ref $value eq "ARRAY") {
2424                            # Here we have a list value. Pull the current entry.
2425                            push @parameterList, $value->[$i];
2426                        } else {
2427                            # Here we have a scalar value. Use it unmodified.
2428                            push @parameterList, $value;
2429                        }
2430                    }
2431                    # Execute the INSERT statement with the specified parameter list.
2432                    $retVal = $sth->execute(@parameterList);
2433                    if (!$retVal) {
2434                        my $errorString = $sth->errstr();
2435                        Confess("Error inserting into $relationName: $errorString");
2436                    }
2437                }
2438            }
2439        }
2440        # Return a 1 for backward compatability.
2441        return 1;
2442    }
2443    
2444    =head3 UpdateEntity
2445    
2446    C<< $erdb->UpdateEntity($entityName, $id, \%fields); >>
2447    
2448    Update the values of an entity. This is an unprotected update, so it should only be
2449    done if the database resides on a database server.
2450    
2451    =over 4
2452    
2453    =item entityName
2454    
2455    Name of the entity to update. (This is the entity type.)
2456    
2457    =item id
2458    
2459    ID of the entity to update. If no entity exists with this ID, an error will be thrown.
2460    
2461    =item fields
2462    
2463    Reference to a hash mapping field names to their new values. All of the fields named
2464    must be in the entity's primary relation, and they cannot any of them be the ID field.
2465    
2466    =back
2467    
2468    =cut
2469    
2470    sub UpdateEntity {
2471        # Get the parameters.
2472        my ($self, $entityName, $id, $fields) = @_;
2473        # Get a list of the field names being updated.
2474        my @fieldList = keys %{$fields};
2475        # Verify that the fields exist.
2476        my $checker = $self->GetFieldTable($entityName);
2477        for my $field (@fieldList) {
2478            if ($field eq 'id') {
2479                Confess("Cannot update the ID field for entity $entityName.");
2480            } elsif ($checker->{$field}->{relation} ne $entityName) {
2481                Confess("Cannot find $field in primary relation of $entityName.");
2482            }
2483        }
2484        # Build the SQL statement.
2485        my @sets = ();
2486        my @valueList = ();
2487        for my $field (@fieldList) {
2488            push @sets, _FixName($field) . " = ?";
2489            push @valueList, $fields->{$field};
2490        }
2491        my $command = "UPDATE $entityName SET " . join(", ", @sets) . " WHERE id = ?";
2492        # Add the ID to the list of binding values.
2493        push @valueList, $id;
2494        # Call SQL to do the work.
2495        my $rows = $self->{_dbh}->SQL($command, 0, @valueList);
2496        # Check for errors.
2497        if ($rows == 0) {
2498            Confess("Entity $id of type $entityName not found.");
2499        }
2500    }
2501    
2502    =head3 LoadTable
2503    
2504    C<< my $results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>
2505    
2506    Load data from a tab-delimited file into a specified table, optionally re-creating the table
2507    first.
2508    
2509    =over 4
2510    
2511    =item fileName
2512    
2513    Name of the file from which the table data should be loaded.
2514    
2515    =item relationName
2516    
2517    Name of the relation to be loaded. This is the same as the table name.
2518    
2519    =item truncateFlag
2520    
2521    TRUE if the table should be dropped and re-created, else FALSE
2522    
2523    =item RETURN
2524    
2525    Returns a statistical object containing a list of the error messages.
2526    
2527    =back
2528    
2529    =cut
2530    sub LoadTable {
2531        # Get the parameters.
2532        my ($self, $fileName, $relationName, $truncateFlag) = @_;
2533        # Create the statistical return object.
2534        my $retVal = _GetLoadStats();
2535        # Trace the fact of the load.
2536        Trace("Loading table $relationName from $fileName") if T(2);
2537        # Get the database handle.
2538        my $dbh = $self->{_dbh};
2539        # Get the input file size.
2540        my $fileSize = -s $fileName;
2541        # Get the relation data.
2542        my $relation = $self->_FindRelation($relationName);
2543        # Check the truncation flag.
2544        if ($truncateFlag) {
2545            Trace("Creating table $relationName") if T(2);
2546            # Compute the row count estimate. We take the size of the load file,
2547            # divide it by the estimated row size, and then multiply by 1.5 to
2548            # leave extra room. We postulate a minimum row count of 1000 to
2549            # prevent problems with incoming empty load files.
2550            my $rowSize = $self->EstimateRowSize($relationName);
2551            my $estimate = FIG::max($fileSize * 1.5 / $rowSize, 1000);
2552            # Re-create the table without its index.
2553            $self->CreateTable($relationName, 0, $estimate);
2554            # If this is a pre-index DBMS, create the index here.
2555            if ($dbh->{_preIndex}) {
2556                eval {
2557                    $self->CreateIndex($relationName);
2558                };
2559                if ($@) {
2560                    $retVal->AddMessage($@);
2561                }
2562            }
2563        }
2564        # Load the table.
2565        my $rv;
2566        eval {
2567            $rv = $dbh->load_table(file => $fileName, tbl => $relationName);
2568        };
2569        if (!defined $rv) {
2570            $retVal->AddMessage($@) if ($@);
2571            $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2572            Trace("Table load failed for $relationName.") if T(1);
2573        } else {
2574            # Here we successfully loaded the table.
2575            $retVal->Add("tables");
2576            my $size = -s $fileName;
2577            Trace("$size bytes loaded into $relationName.") if T(2);
2578            # If we're rebuilding, we need to create the table indexes.
2579            if ($truncateFlag) {
2580                # Indexes are created here for PostGres. For PostGres, indexes are
2581                # best built at the end. For MySQL, the reverse is true.
2582                if (! $dbh->{_preIndex}) {
2583                    eval {
2584                        $self->CreateIndex($relationName);
2585                    };
2586                    if ($@) {
2587                        $retVal->AddMessage($@);
2588                    }
2589                }
2590                # The full-text index (if any) is always built last, even for MySQL.
2591                # First we need to see if this table has a full-text index. Only
2592                # primary relations are allowed that privilege.
2593                Trace("Checking for full-text index on $relationName.") if T(2);
2594                if ($self->_IsPrimary($relationName)) {
2595                    $self->CreateSearchIndex($relationName);
2596                }
2597            }
2598        }
2599        # Analyze the table to improve performance.
2600        Trace("Analyzing and compacting $relationName.") if T(3);
2601        $dbh->vacuum_it($relationName);
2602        Trace("$relationName load completed.") if T(3);
2603        # Return the statistics.
2604        return $retVal;
2605    }
2606    
2607    =head3 CreateSearchIndex
2608    
2609    C<< $erdb->CreateSearchIndex($objectName); >>
2610    
2611    Check for a full-text search index on the specified entity or relationship object, and
2612    if one is required, rebuild it.
2613    
2614    =over 4
2615    
2616    =item objectName
2617    
2618    Name of the entity or relationship to be indexed.
2619    
2620    =back
2621    
2622    =cut
2623    
2624    sub CreateSearchIndex {
2625        # Get the parameters.
2626        my ($self, $objectName) = @_;
2627        # Get the relation's entity/relationship structure.
2628        my $structure = $self->_GetStructure($objectName);
2629        # Get the database handle.
2630        my $dbh = $self->{_dbh};
2631        Trace("Checking for search fields in $objectName.") if T(3);
2632        # Check for a searchable fields list.
2633        if (exists $structure->{searchFields}) {
2634            # Here we know that we need to create a full-text search index.
2635            # Get an SQL-formatted field name list.
2636            my $fields = join(", ", _FixNames(@{$structure->{searchFields}}));
2637            # Create the index. If it already exists, it will be dropped.
2638            $dbh->create_index(tbl => $objectName, idx => "search_idx",
2639                               flds => $fields, kind => 'fulltext');
2640            Trace("Index created for $fields in $objectName.") if T(2);
2641        }
2642    }
2643    
2644    =head3 DropRelation
2645    
2646    C<< $erdb->DropRelation($relationName); >>
2647    
2648    Physically drop a relation from the database.
2649    
2650    =over 4
2651    
2652    =item relationName
2653    
2654    Name of the relation to drop. If it does not exist, this method will have
2655    no effect.
2656    
2657    =back
2658    
2659    =cut
2660    
2661    sub DropRelation {
2662        # Get the parameters.
2663        my ($self, $relationName) = @_;
2664        # Get the database handle.
2665        my $dbh = $self->{_dbh};
2666        # Drop the relation. The method used here has no effect if the relation
2667        # does not exist.
2668        Trace("Invoking DB Kernel to drop $relationName.") if T(3);
2669        $dbh->drop_table(tbl => $relationName);
2670    }
2671    
2672    =head3 MatchSqlPattern
2673    
2674    C<< my $matched = ERDB::MatchSqlPattern($value, $pattern); >>
2675    
2676    Determine whether or not a specified value matches an SQL pattern. An SQL
2677    pattern has two wild card characters: C<%> that matches multiple characters,
2678    and C<_> that matches a single character. These can be escaped using a
2679    backslash (C<\>). We pull this off by converting the SQL pattern to a
2680    PERL regular expression. As per SQL rules, the match is case-insensitive.
2681    
2682    =over 4
2683    
2684    =item value
2685    
2686    Value to be matched against the pattern. Note that an undefined or empty
2687    value will not match anything.
2688    
2689    =item pattern
2690    
2691    SQL pattern against which to match the value. An undefined or empty pattern will
2692    match everything.
2693    
2694    =item RETURN
2695    
2696    Returns TRUE if the value and pattern match, else FALSE.
2697    
2698    =back
2699    
2700    =cut
2701    
2702    sub MatchSqlPattern {
2703        # Get the parameters.
2704        my ($value, $pattern) = @_;
2705        # Declare the return variable.
2706        my $retVal;
2707        # Insure we have a pattern.
2708        if (! defined($pattern) || $pattern eq "") {
2709            $retVal = 1;
2710        } else {
2711            # Break the pattern into pieces around the wildcard characters. Because we
2712            # use parentheses in the split function's delimiter expression, we'll get
2713            # list elements for the delimiters as well as the rest of the string.
2714            my @pieces = split /([_%]|\\[_%])/, $pattern;
2715            # Check some fast special cases.
2716            if ($pattern eq '%') {
2717                # A null pattern matches everything.
2718                $retVal = 1;
2719            } elsif (@pieces == 1) {
2720                # No wildcards, so we have a literal comparison. Note we're case-insensitive.
2721                $retVal = (lc($value) eq lc($pattern));
2722            } elsif (@pieces == 2 && $pieces[1] eq '%') {
2723                # A wildcard at the end, so we have a substring match. This is also case-insensitive.
2724                $retVal = (lc(substr($value, 0, length($pieces[0]))) eq lc($pieces[0]));
2725            } else {
2726                # Okay, we have to do it the hard way. Convert each piece to a PERL pattern.
2727                my $realPattern = "";
2728                for my $piece (@pieces) {
2729                    # Determine the type of piece.
2730                    if ($piece eq "") {
2731                        # Empty pieces are ignored.
2732                    } elsif ($piece eq "%") {
2733                        # Here we have a multi-character wildcard. Note that it can match
2734                        # zero or more characters.
2735                        $realPattern .= ".*"
2736                    } elsif ($piece eq "_") {
2737                        # Here we have a single-character wildcard.
2738                        $realPattern .= ".";
2739                    } elsif ($piece eq "\\%" || $piece eq "\\_") {
2740                        # This is an escape sequence (which is a rare thing, actually).
2741                        $realPattern .= substr($piece, 1, 1);
2742                    } else {
2743                        # Here we have raw text.
2744                        $realPattern .= quotemeta($piece);
2745                    }
2746                }
2747                # Do the match.
2748                $retVal = ($value =~ /^$realPattern$/i ? 1 : 0);
2749            }
2750        }
2751        # Return the result.
2752        return $retVal;
2753    }
2754    
2755    =head3 GetEntity
2756    
2757    C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>
2758    
2759    Return an object describing the entity instance with a specified ID.
2760    
2761    =over 4
2762    
2763    =item entityType
2764    
2765    Entity type name.
2766    
2767    =item ID
2768    
2769    ID of the desired entity.
2770    
2771    =item RETURN
2772    
2773    Returns a B<DBObject> representing the desired entity instance, or an undefined value if no
2774    instance is found with the specified key.
2775    
2776    =back
2777    
2778    =cut
2779    
2780    sub GetEntity {
2781        # Get the parameters.
2782        my ($self, $entityType, $ID) = @_;
2783        # Create a query.
2784        my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);
2785        # Get the first (and only) object.
2786        my $retVal = $query->Fetch();
2787        # Return the result.
2788        return $retVal;
2789    }
2790    
2791    =head3 GetChoices
2792    
2793    C<< my @values = $erdb->GetChoices($entityName, $fieldName); >>
2794    
2795    Return a list of all the values for the specified field that are represented in the
2796    specified entity.
2797    
2798    Note that if the field is not indexed, then this will be a very slow operation.
2799    
2800    =over 4
2801    
2802    =item entityName
2803    
2804    Name of an entity in the database.
2805    
2806    =item fieldName
2807    
2808    Name of a field belonging to the entity. This is a raw field name without
2809    the standard parenthesized notation used in most calls.
2810    
2811    =item RETURN
2812    
2813    Returns a list of the distinct values for the specified field in the database.
2814    
2815    =back
2816    
2817    =cut
2818    
2819    sub GetChoices {
2820        # Get the parameters.
2821        my ($self, $entityName, $fieldName) = @_;
2822        # Declare the return variable.
2823        my @retVal;
2824        # Get the entity data structure.
2825        my $entityData = $self->_GetStructure($entityName);
2826        # Get the field.
2827        my $fieldHash = $entityData->{Fields};
2828        if (! exists $fieldHash->{$fieldName}) {
2829            Confess("$fieldName not found in $entityName.");
2830        } else {
2831            # Get the name of the relation containing the field.
2832            my $relation = $fieldHash->{$fieldName}->{relation};
2833            # Fix up the field name.
2834            my $realName = _FixName($fieldName);
2835            # Get the database handle.
2836            my $dbh = $self->{_dbh};
2837            # Query the database.
2838            my $results = $dbh->SQL("SELECT DISTINCT $realName FROM $relation");
2839            # Clean the results. They are stored as a list of lists, and we just want the one list.
2840            @retVal = sort map { $_->[0] } @{$results};
2841        }
2842        # Return the result.
2843        return @retVal;
2844    }
2845    
2846    =head3 GetEntityValues
2847    
2848    C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>
2849    
2850    Return a list of values from a specified entity instance. If the entity instance
2851    does not exist, an empty list is returned.
2852    
2853    =over 4
2854    
2855    =item entityType
2856    
2857    Entity type name.
2858    
2859    =item ID
2860    
2861    ID of the desired entity.
2862    
2863    =item fields
2864    
2865    List of field names, each of the form I<objectName>C<(>I<fieldName>C<)>.
2866    
2867    =item RETURN
2868    
2869    Returns a flattened list of the values of the specified fields for the specified entity.
2870    
2871    =back
2872    
2873    =cut
2874    
2875    sub GetEntityValues {
2876        # Get the parameters.
2877        my ($self, $entityType, $ID, $fields) = @_;
2878        # Get the specified entity.
2879        my $entity = $self->GetEntity($entityType, $ID);
2880        # Declare the return list.
2881        my @retVal = ();
2882        # If we found the entity, push the values into the return list.
2883        if ($entity) {
2884            push @retVal, $entity->Values($fields);
2885        }
2886        # Return the result.
2887        return @retVal;
2888    }
2889    
2890    =head3 GetAll
2891    
2892    C<< my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>
2893    
2894    Return a list of values taken from the objects returned by a query. The first three
2895    parameters correspond to the parameters of the L</Get> method. The final parameter is
2896    a list of the fields desired from each record found by the query. The field name
2897    syntax is the standard syntax used for fields in the B<ERDB> system--
2898    B<I<objectName>(I<fieldName>)>-- where I<objectName> is the name of the relevant entity
2899    or relationship and I<fieldName> is the name of the field.
2900    
2901    The list returned will be a list of lists. Each element of the list will contain
2902    the values returned for the fields specified in the fourth parameter. If one of the
2903    fields specified returns multiple values, they are flattened in with the rest. For
2904    example, the following call will return a list of the features in a particular
2905    spreadsheet cell, and each feature will be represented by a list containing the
2906    feature ID followed by all of its aliases.
2907    
2908    C<< @query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>
2909    
2910    =over 4
2911    
2912    =item objectNames
2913    
2914    List containing the names of the entity and relationship objects to be retrieved.
2915    
2916    =item filterClause
2917    
2918    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
2919    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
2920    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
2921    parameter list as additional parameters. The fields in a filter clause can come from primary
2922    entity relations, relationship relations, or secondary entity relations; however, all of the
2923    entities and relationships involved must be included in the list of object names.
2924    
2925    =item parameterList
2926    
2927    List of the parameters to be substituted in for the parameters marks in the filter clause.
2928    
2929    =item fields
2930    
2931    List of the fields to be returned in each element of the list returned.
2932    
2933    =item count
2934    
2935    Maximum number of records to return. If omitted or 0, all available records will be returned.
2936    
2937    =item RETURN
2938    
2939    Returns a list of list references. Each element of the return list contains the values for the
2940    fields specified in the B<fields> parameter.
2941    
2942    =back
2943    
2944    =cut
2945    #: Return Type @@;
2946    sub GetAll {
2947        # Get the parameters.
2948        my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
2949        # Translate the parameters from a list reference to a list. If the parameter
2950        # list is a scalar we convert it into a singleton list.
2951        my @parmList = ();
2952        if (ref $parameterList eq "ARRAY") {
2953            Trace("GetAll parm list is an array.") if T(4);
2954            @parmList = @{$parameterList};
2955        } else {
2956            Trace("GetAll parm list is a scalar: $parameterList.") if T(4);
2957            push @parmList, $parameterList;
2958        }
2959        # Insure the counter has a value.
2960        if (!defined $count) {
2961            $count = 0;
2962        }
2963        # Add the row limit to the filter clause.
2964        if ($count > 0) {
2965            $filterClause .= " LIMIT $count";
2966        }
2967        # Create the query.
2968        my $query = $self->Get($objectNames, $filterClause, \@parmList);
2969        # Set up a counter of the number of records read.
2970        my $fetched = 0;
2971        # Loop through the records returned, extracting the fields. Note that if the
2972        # counter is non-zero, we stop when the number of records read hits the count.
2973        my @retVal = ();
2974        while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {
2975            my @rowData = $row->Values($fields);
2976            push @retVal, \@rowData;
2977            $fetched++;
2978        }
2979        Trace("$fetched rows returned in GetAll.") if T(SQL => 4);
2980        # Return the resulting list.
2981        return @retVal;
2982    }
2983    
2984    =head3 Exists
2985    
2986    C<< my $found = $sprout->Exists($entityName, $entityID); >>
2987    
2988    Return TRUE if an entity exists, else FALSE.
2989    
2990    =over 4
2991    
2992    =item entityName
2993    
2994    Name of the entity type (e.g. C<Feature>) relevant to the existence check.
2995    
2996    =item entityID
2997    
2998    ID of the entity instance whose existence is to be checked.
2999    
3000    =item RETURN
3001    
3002    Returns TRUE if the entity instance exists, else FALSE.
3003    
3004    =back
3005    
3006    =cut
3007    #: Return Type $;
3008    sub Exists {
3009        # Get the parameters.
3010        my ($self, $entityName, $entityID) = @_;
3011        # Check for the entity instance.
3012        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
3013        my $testInstance = $self->GetEntity($entityName, $entityID);
3014        # Return an existence indicator.
3015        my $retVal = ($testInstance ? 1 : 0);
3016        return $retVal;
3017    }
3018    
3019    =head3 EstimateRowSize
3020    
3021    C<< my $rowSize = $erdb->EstimateRowSize($relName); >>
3022    
3023    Estimate the row size of the specified relation. The estimated row size is computed by adding
3024    up the average length for each data type.
3025    
3026    =over 4
3027    
3028    =item relName
3029    
3030    Name of the relation whose estimated row size is desired.
3031    
3032    =item RETURN
3033    
3034    Returns an estimate of the row size for the specified relation.
3035    
3036    =back
3037    
3038    =cut
3039    #: Return Type $;
3040    sub EstimateRowSize {
3041        # Get the parameters.
3042        my ($self, $relName) = @_;
3043        # Declare the return variable.
3044        my $retVal = 0;
3045        # Find the relation descriptor.
3046        my $relation = $self->_FindRelation($relName);
3047        # Get the list of fields.
3048        for my $fieldData (@{$relation->{Fields}}) {
3049            # Get the field type and add its length.
3050            my $fieldLen = $TypeTable{$fieldData->{type}}->{avgLen};
3051            $retVal += $fieldLen;
3052        }
3053        # Return the result.
3054        return $retVal;
3055    }
3056    
3057    =head3 GetFieldTable
3058    
3059    C<< my $fieldHash = $self->GetFieldTable($objectnName); >>
3060    
3061    Get the field structure for a specified entity or relationship.
3062    
3063    =over 4
3064    
3065    =item objectName
3066    
3067    Name of the desired entity or relationship.
3068    
3069    =item RETURN
3070    
3071    The table containing the field descriptors for the specified object.
3072    
3073    =back
3074    
3075    =cut
3076    
3077    sub GetFieldTable {
3078        # Get the parameters.
3079        my ($self, $objectName) = @_;
3080        # Get the descriptor from the metadata.
3081        my $objectData = $self->_GetStructure($objectName);
3082        # Return the object's field table.
3083        return $objectData->{Fields};
3084    }
3085    
3086    =head3 SplitKeywords
3087    
3088    C<< my @keywords = ERDB::SplitKeywords($keywordString); >>
3089    
3090    This method returns a list of the positive keywords in the specified
3091    keyword string. All of the operators will have been stripped off,
3092    and if the keyword is preceded by a minus operator (C<->), it will
3093    not be in the list returned. The idea here is to get a list of the
3094    keywords the user wants to see. The list will be processed to remove
3095    duplicates.
3096    
3097    It is possible to create a string that confuses this method. For example
3098    
3099        frog toad -frog
3100    
3101    would return both C<frog> and C<toad>. If this is a problem we can deal
3102    with it later.
3103    
3104    =over 4
3105    
3106    =item keywordString
3107    
3108    The keyword string to be parsed.
3109    
3110    =item RETURN
3111    
3112    Returns a list of the words in the keyword string the user wants to
3113    see.
3114    
3115    =back
3116    
3117    =cut
3118    
3119    sub SplitKeywords {
3120        # Get the parameters.
3121        my ($keywordString) = @_;
3122        # Make a safety copy of the string. (This helps during debugging.)
3123        my $workString = $keywordString;
3124        # Convert operators we don't care about to spaces.
3125        $workString =~ tr/+"()<>/ /;
3126        # Split the rest of the string along space boundaries. Note that we
3127        # eliminate any words that are zero length or begin with a minus sign.
3128        my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
3129        # Use a hash to remove duplicates.
3130        my %words = map { $_ => 1 } @wordList;
3131        # Return the result.
3132        return sort keys %words;
3133    }
3134    
3135    =head3 ValidateFieldName
3136    
3137    C<< my $okFlag = ERDB::ValidateFieldName($fieldName); >>
3138    
3139    Return TRUE if the specified field name is valid, else FALSE. Valid field names must
3140    be hyphenated words subject to certain restrictions.
3141    
3142    =over 4
3143    
3144    =item fieldName
3145    
3146    Field name to be validated.
3147    
3148    =item RETURN
3149    
3150    Returns TRUE if the field name is valid, else FALSE.
3151    
3152    =back
3153    
3154    =cut
3155    
3156    sub ValidateFieldName {
3157        # Get the parameters.
3158        my ($fieldName) = @_;
3159        # Declare the return variable. The field name is valid until we hear
3160        # differently.
3161        my $retVal = 1;
3162        # Compute the maximum name length.
3163        my $maxLen = $TypeTable{'name-string'}->{maxLen};
3164        # Look for bad stuff in the name.
3165        if ($fieldName =~ /--/) {
3166            # Here we have a doubled minus sign.
3167            Trace("Field name $fieldName has a doubled hyphen.") if T(1);
3168            $retVal = 0;
3169        } elsif ($fieldName !~ /^[A-Za-z]/) {
3170            # Here the field name is missing the initial letter.
3171            Trace("Field name $fieldName does not begin with a letter.") if T(1);
3172            $retVal = 0;
3173        } elsif (length($fieldName) > $maxLen) {
3174            # Here the field name is too long.
3175            Trace("Maximum field name length is $maxLen. Field name must be truncated to " . substr($fieldName,0, $maxLen) . ".");
3176        } else {
3177            # Strip out the minus signs. Everything remaining must be a letter,
3178            # underscore, or digit.
3179            my $strippedName = $fieldName;
3180            $strippedName =~ s/-//g;
3181            if ($strippedName !~ /^(\w|\d)+$/) {
3182                Trace("Field name $fieldName contains illegal characters.") if T(1);
3183                $retVal = 0;
3184            }
3185        }
3186        # Return the result.
3187        return $retVal;
3188    }
3189    
3190    =head3 ReadMetaXML
3191    
3192    C<< my $rawMetaData = ERDB::ReadDBD($fileName); >>
3193    
3194    This method reads a raw database definition XML file and returns it.
3195    Normally, the metadata used by the ERDB system has been processed and
3196    modified to make it easier to load and retrieve the data; however,
3197    this method can be used to get the data in its raw form.
3198    
3199    =over 4
3200    
3201    =item fileName
3202    
3203    Name of the XML file to read.
3204    
3205    =item RETURN
3206    
3207    Returns a hash reference containing the raw XML data from the specified file.
3208    
3209    =back
3210    
3211    =cut
3212    
3213    sub ReadMetaXML {
3214        # Get the parameters.
3215        my ($fileName) = @_;
3216        # Read the XML.
3217        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
3218        Trace("XML metadata loaded from file $fileName.") if T(1);
3219        # Return the result.
3220        return $retVal;
3221    }
3222    
3223    =head3 GetEntityFieldHash
3224    
3225    C<< my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName); >>
3226    
3227    Get the field hash of the named entity in the specified raw XML structure.
3228    The field hash may not exist, in which case we need to create it.
3229    
3230    =over 4
3231    
3232    =item structure
3233    
3234    Raw XML structure defininng the database. This is not the run-time XML used by
3235    an ERDB object, since that has all sorts of optimizations built-in.
3236    
3237    =item entityName
3238    
3239    Name of the entity whose field structure is desired.
3240    
3241    =item RETURN
3242    
3243    Returns the field hash used to define the entity's fields.
3244    
3245    =back
3246    
3247    =cut
3248    
3249    sub GetEntityFieldHash {
3250        # Get the parameters.
3251        my ($structure, $entityName) = @_;
3252        # Get the entity structure.
3253        my $entityData = $structure->{Entities}->{$entityName};
3254        # Look for a field structure.
3255        my $retVal = $entityData->{Fields};
3256        # If it doesn't exist, create it.
3257        if (! defined($retVal)) {
3258            $entityData->{Fields} = {};
3259            $retVal = $entityData->{Fields};
3260        }
3261        # Return the result.
3262        return $retVal;
3263    }
3264    
3265    =head3 WriteMetaXML
3266    
3267    C<< ERDB::WriteMetaXML($structure, $fileName); >>
3268    
3269    Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
3270    used to update the database definition. It must be used with care, however, since it
3271    will only work on a raw structure, not on the processed structure created by an ERDB
3272    constructor.
3273    
3274    =over 4
3275    
3276    =item structure
3277    
3278    XML structure to be written to the file.
3279    
3280    =item fileName
3281    
3282    Name of the output file to which the updated XML should be stored.
3283    
3284    =back
3285    
3286    =cut
3287    
3288    sub WriteMetaXML {
3289        # Get the parameters.
3290        my ($structure, $fileName) = @_;
3291        # Compute the output.
3292        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
3293        # Write it to the file.
3294        my $xmlOut = Open(undef, ">$fileName");
3295        print $xmlOut $fileString;
3296    }
3297    
3298    
3299    =head3 HTMLNote
3300    
3301    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
3302    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
3303    Except for C<[p]>, all the codes are closed by slash-codes. So, for
3304    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
3305    
3306    C<< my $realHtml = ERDB::HTMLNote($dataString); >>
3307    
3308    =over 4
3309    
3310    =item dataString
3311    
3312    String to convert to HTML.
3313    
3314    =item RETURN
3315    
3316    An HTML string derived from the input string.
3317    
3318    =back
3319    
3320    =cut
3321    
3322    sub HTMLNote {
3323        # Get the parameter.
3324        my ($dataString) = @_;
3325        # HTML-escape the text.
3326        my $retVal = CGI::escapeHTML($dataString);
3327        # Substitute the bulletin board codes.
3328        $retVal =~ s!\[(/?[bi])\]!<$1>!g;
3329        $retVal =~ s!\[p\]!</p><p>!g;
3330        $retVal =~ s!\[link\s+([^\]]+)\]!<a href="$1">!g;
3331        $retVal =~ s!\[/link\]!</a>!g;
3332        # Return the result.
3333        return $retVal;
3334    }
3335    
3336    
3337    =head2 Data Mining Methods
3338    
3339    =head3 GetUsefulCrossValues
3340    
3341    C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>
3342    
3343    Return a list of the useful attributes that would be returned by a B<Cross> call
3344    from an entity of the source entity type through the specified relationship. This
3345    means it will return the fields of the target entity type and the intersection data
3346    fields in the relationship. Only primary table fields are returned. In other words,
3347    the field names returned will be for fields where there is always one and only one
3348    value.
3349    
3350    =over 4
3351    
3352    =item sourceEntity
3353    
3354    Name of the entity from which the relationship crossing will start.
3355    
3356    =item relationship
3357    
3358    Name of the relationship being crossed.
3359    
3360    =item RETURN
3361    
3362    Returns a list of field names in Sprout field format (I<objectName>C<(>I<fieldName>C<)>.
3363    
3364    =back
3365    
3366    =cut
3367    #: Return Type @;
3368    sub GetUsefulCrossValues {
3369      # Get the parameters.      # Get the parameters.
3370      my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;      my ($self, $sourceEntity, $relationship) = @_;
3371      # Translate the parameters from a list reference to a list. If the parameter      # Declare the return variable.
3372      # list is a scalar we convert it into a singleton list.      my @retVal = ();
3373      my @parmList = ();      # Determine the target entity for the relationship. This is whichever entity is not
3374      if (ref $parameterList eq "ARRAY") {      # the source entity. So, if the source entity is the FROM, we'll get the name of
3375          @parmList = @{$parameterList};      # the TO, and vice versa.
3376        my $relStructure = $self->_GetStructure($relationship);
3377        my $targetEntityType = ($relStructure->{from} eq $sourceEntity ? "to" : "from");
3378        my $targetEntity = $relStructure->{$targetEntityType};
3379        # Get the field table for the entity.
3380        my $entityFields = $self->GetFieldTable($targetEntity);
3381        # The field table is a hash. The hash key is the field name. The hash value is a structure.
3382        # For the entity fields, the key aspect of the target structure is that the {relation} value
3383        # must match the entity name.
3384        my @fieldList = map { "$targetEntity($_)" } grep { $entityFields->{$_}->{relation} eq $targetEntity }
3385                            keys %{$entityFields};
3386        # Push the fields found onto the return variable.
3387        push @retVal, sort @fieldList;
3388        # Get the field table for the relationship.
3389        my $relationshipFields = $self->GetFieldTable($relationship);
3390        # Here we have a different rule. We want all the fields other than "from-link" and "to-link".
3391        # This may end up being an empty set.
3392        my @fieldList2 = map { "$relationship($_)" } grep { $_ ne "from-link" && $_ ne "to-link" }
3393                            keys %{$relationshipFields};
3394        # Push these onto the return list.
3395        push @retVal, sort @fieldList2;
3396        # Return the result.
3397        return @retVal;
3398    }
3399    
3400    =head3 FindColumn
3401    
3402    C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>
3403    
3404    Return the location a desired column in a data mining header line. The data
3405    mining header line is a tab-separated list of column names. The column
3406    identifier is either the numerical index of a column or the actual column
3407    name.
3408    
3409    =over 4
3410    
3411    =item headerLine
3412    
3413    The header line from a data mining command, which consists of a tab-separated
3414    list of column names.
3415    
3416    =item columnIdentifier
3417    
3418    Either the ordinal number of the desired column (1-based), or the name of the
3419    desired column.
3420    
3421    =item RETURN
3422    
3423    Returns the array index (0-based) of the desired column.
3424    
3425    =back
3426    
3427    =cut
3428    
3429    sub FindColumn {
3430        # Get the parameters.
3431        my ($headerLine, $columnIdentifier) = @_;
3432        # Declare the return variable.
3433        my $retVal;
3434        # Split the header line into column names.
3435        my @headers = ParseColumns($headerLine);
3436        # Determine whether we have a number or a name.
3437        if ($columnIdentifier =~ /^\d+$/) {
3438            # Here we have a number. Subtract 1 and validate the result.
3439            $retVal = $columnIdentifier - 1;
3440            if ($retVal < 0 || $retVal > $#headers) {
3441                Confess("Invalid column identifer \"$columnIdentifier\": value out of range.");
3442            }
3443      } else {      } else {
3444          push @parmList, $parameterList;          # Here we have a name. We need to find it in the list.
3445            for (my $i = 0; $i <= $#headers && ! defined($retVal); $i++) {
3446                if ($headers[$i] eq $columnIdentifier) {
3447                    $retVal = $i;
3448      }      }
     # Create the query.  
     my $query = $self->Get($objectNames, $filterClause, @parmList);  
     # Set up a counter of the number of records read.  
     my $fetched = 0;  
     # Insure the counter has a value.  
     if (!defined $count) {  
         $count = 0;  
3449      }      }
3450      # Loop through the records returned, extracting the fields. Note that if the          if (! defined($retVal)) {
3451      # counter is non-zero, we stop when the number of records read hits the count.              Confess("Invalid column identifier \"$columnIdentifier\": value not found.");
     my @retVal = ();  
     while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {  
         my @rowData = $row->Values($fields);  
         push @retVal, \@rowData;  
         $fetched++;  
3452      }      }
3453      # Return the resulting list.      }
3454      return @retVal;      # Return the result.
3455        return $retVal;
3456  }  }
3457    
3458  =head2 Internal Utility Methods  =head3 ParseColumns
3459    
3460  =head3 GetLoadStats  C<< my @columns = ERDB::ParseColumns($line); >>
3461    
3462  Return a blank statistics object for use by the load methods.  Convert the specified data line to a list of columns.
3463    
3464  This is a static method.  =over 4
3465    
3466    =item line
3467    
3468    A data mining input, consisting of a tab-separated list of columns terminated by a
3469    new-line.
3470    
3471    =item RETURN
3472    
3473    Returns a list consisting of the column values.
3474    
3475    =back
3476    
3477  =cut  =cut
3478    
3479  sub _GetLoadStats {  sub ParseColumns {
3480      return Stats->new('records');      # Get the parameters.
3481        my ($line) = @_;
3482        # Chop off the line-end.
3483        chomp $line;
3484        # Split it into a list.
3485        my @retVal = split(/\t/, $line);
3486        # Return the result.
3487        return @retVal;
3488  }  }
3489    
3490  =head3 GenerateFields  =head2 Virtual Methods
3491    
3492  Generate field values from a field structure and store in a specified table. The field names  =head3 CleanKeywords
 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.  
3493    
3494  This is a static method.  C<< my $cleanedString = $erdb->CleanKeywords($searchExpression); >>
3495    
3496    Clean up a search expression or keyword list. This is a virtual method that may
3497    be overridden by the subclass. The base-class method removes extra spaces
3498    and converts everything to lower case.
3499    
3500  =over 4  =over 4
3501    
3502  =item this  =item searchExpression
3503    
3504  Hash table into which the field values should be placed.  Search expression or keyword list to clean. Note that a search expression may
3505    contain boolean operators which need to be preserved. This includes leading
3506    minus signs.
3507    
3508  =item fields  =item RETURN
3509    
3510  Field structure from which the field descriptors should be taken.  Cleaned expression or keyword list.
3511    
3512  =item type  =back
3513    
3514    =cut
3515    
3516    sub CleanKeywords {
3517        # Get the parameters.
3518        my ($self, $searchExpression) = @_;
3519        # Lower-case the expression and copy it into the return variable. Note that we insure we
3520        # don't accidentally end up with an undefined value.
3521        my $retVal = lc($searchExpression || "");
3522        # Remove extra spaces.
3523        $retVal =~ s/\s+/ /g;
3524        $retVal =~ s/(^\s+)|(\s+$)//g;
3525        # Return the result.
3526        return $retVal;
3527    }
3528    
3529    =head3 GetSourceObject
3530    
3531  Type name of the object whose fields are being generated.  C<< my $source = $erdb->GetSourceObject($entityName); >>
3532    
3533  =item values (optional)  Return the object to be used in loading special attributes of the specified entity. The
3534    algorithm for loading special attributes is stored in the C<DataGen> elements of the
3535    XML
3536    
3537  Reference to a value structure from which additional values can be taken.  =head2 Internal Utility Methods
3538    
3539    =head3 _RelationMap
3540    
3541    C<< my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef); >>
3542    
3543    Create the relation map for an SQL query. The relation map is used by B<DBObject>
3544    to determine how to interpret the results of the query.
3545    
3546    =over 4
3547    
3548    =item mappedNameHashRef
3549    
3550    Reference to a hash that maps modified object names to real object names.
3551    
3552  =item from (optiona)  =item mappedNameListRef
3553    
3554  Reference to the source entity instance if relationship data is being generated.  Reference to a list of modified object names in the order they appear in the
3555    SELECT list.
3556    
3557  =item to (optional)  =item RETURN
3558    
3559  Reference to the target entity instance if relationship data is being generated.  Returns a list of 2-tuples. Each tuple consists of an object name as used in the
3560    query followed by the actual name of that object. This enables the B<DBObject> to
3561    determine the order of the tables in the query and which object name belongs to each
3562    mapped object name. Most of the time these two values are the same; however, if a
3563    relation occurs twice in the query, the relation name in the field list and WHERE
3564    clause will use a mapped name (generally the actual relation name with a numeric
3565    suffix) that does not match the actual relation name.
3566    
3567  =back  =back
3568    
3569  =cut  =cut
3570    
3571  sub _GenerateFields {  sub _RelationMap {
3572      # Get the parameters.      # Get the parameters.
3573      my ($this, $fields, $type, $values, $from, $to) = @_;      my ($mappedNameHashRef, $mappedNameListRef) = @_;
3574      # Sort the field names by pass number.      # Declare the return variable.
3575      my @fieldNames = sort { $fields->{$a}->{DataGen}->{pass} <=> $fields->{$b}->{DataGen}->{pass} } keys %{$fields};      my @retVal = ();
3576      # Loop through the field names, generating data.      # Build the map.
3577      for my $name (@fieldNames) {      for my $mappedName (@{$mappedNameListRef}) {
3578          # Only proceed if this field needs to be generated.          push @retVal, [$mappedName, $mappedNameHashRef->{$mappedName}];
3579          if (!exists $this->{$name}) {      }
3580              # Get this field's data generation descriptor.      # Return it.
3581              my $fieldDescriptor = $fields->{$name};      return @retVal;
3582              my $data = $fieldDescriptor->{DataGen};  }
3583              # Get the code to generate the field value.  
3584              my $codeString = $data->{content};  
3585              # Determine whether or not this field is in the primary relation.  =head3 _SetupSQL
3586              if ($fieldDescriptor->{relation} eq $type) {  
3587                  # Here we have a primary relation field. Store the field value as  Process a list of object names and a filter clause so that they can be used to
3588                  # a scalar.  build an SQL statement. This method takes in a reference to a list of object names
3589                  $this->{$name} = eval($codeString);  and a filter clause. It will return a corrected filter clause, a list of mapped
3590    names and the mapped name hash.
3591    
3592    This is an instance method.
3593    
3594    =over 4
3595    
3596    =item objectNames
3597    
3598    Reference to a list of the object names to be included in the query.
3599    
3600    =item filterClause
3601    
3602    A string containing the WHERE clause for the query (without the C<WHERE>) and also
3603    optionally the C<ORDER BY> and C<LIMIT> clauses.
3604    
3605    =item matchClause
3606    
3607    An optional full-text search clause. If specified, it will be inserted at the
3608    front of the WHERE clause. It should already be SQL-formatted; that is, the
3609    field names should be in the form I<table>C<.>I<fieldName>.
3610    
3611    =item RETURN
3612    
3613    Returns a three-element list. The first element is the SQL statement suffix, beginning
3614    with the FROM clause. The second element is a reference to a list of the names to be
3615    used in retrieving the fields. The third element is a hash mapping the names to the
3616    objects they represent.
3617    
3618    =back
3619    
3620    =cut
3621    
3622    sub _SetupSQL {
3623        my ($self, $objectNames, $filterClause, $matchClause) = @_;
3624        # Adjust the list of object names to account for multiple occurrences of the
3625        # same object. We start with a hash table keyed on object name that will
3626        # return the object suffix. The first time an object is encountered it will
3627        # not be found in the hash. The next time the hash will map the object name
3628        # to 2, then 3, and so forth.
3629        my %objectHash = ();
3630        # This list will contain the object names as they are to appear in the
3631        # FROM list.
3632        my @fromList = ();
3633        # This list contains the suffixed object name for each object. It is exactly
3634        # parallel to the list in the $objectNames parameter.
3635        my @mappedNameList = ();
3636        # Finally, this hash translates from a mapped name to its original object name.
3637        my %mappedNameHash = ();
3638        # Now we create the lists. Note that for every single name we push something into
3639        # @fromList and @mappedNameList. This insures that those two arrays are exactly
3640        # parallel to $objectNames.
3641        for my $objectName (@{$objectNames}) {
3642            # Get the next suffix for this object.
3643            my $suffix = $objectHash{$objectName};
3644            if (! $suffix) {
3645                # Here we are seeing the object for the first time. The object name
3646                # is used as is.
3647                push @mappedNameList, $objectName;
3648                push @fromList, $objectName;
3649                $mappedNameHash{$objectName} = $objectName;
3650                # Denote the next suffix will be 2.
3651                $objectHash{$objectName} = 2;
3652            } else {
3653                # Here we've seen the object before. We construct a new name using
3654                # the suffix from the hash and update the hash.
3655                my $mappedName = "$objectName$suffix";
3656                $objectHash{$objectName} = $suffix + 1;
3657                # The FROM list has the object name followed by the mapped name. This
3658                # tells SQL it's still the same table, but we're using a different name
3659                # for it to avoid confusion.
3660                push @fromList, "$objectName $mappedName";
3661                # The mapped-name list contains the real mapped name.
3662                push @mappedNameList, $mappedName;
3663                # Finally, enable us to get back from the mapped name to the object name.
3664                $mappedNameHash{$mappedName} = $objectName;
3665            }
3666        }
3667        # Begin the SELECT suffix. It starts with
3668        #
3669        # FROM name1, name2, ... nameN
3670        #
3671        my $suffix = "FROM " . join(', ', @fromList);
3672        # Now for the WHERE. First, we need a place for the filter string.
3673        my $filterString = "";
3674        # We will also keep a list of conditions to add to the WHERE clause in order to link
3675        # entities and relationships as well as primary relations to secondary ones.
3676        my @joinWhere = ();
3677        # Check for a filter clause.
3678        if ($filterClause) {
3679            # Here we have one, so we convert its field names and add it to the query. First,
3680            # We create a copy of the filter string we can work with.
3681            $filterString = $filterClause;
3682            # Next, we sort the object names by length. This helps protect us from finding
3683            # object names inside other object names when we're doing our search and replace.
3684            my @sortedNames = sort { length($b) - length($a) } @mappedNameList;
3685            # The final preparatory step is to create a hash table of relation names. The
3686            # table begins with the relation names already in the SELECT command. We may
3687            # need to add relations later if there is filtering on a field in a secondary
3688            # relation. The secondary relations are the ones that contain multiply-
3689            # occurring or optional fields.
3690            my %fromNames = map { $_ => 1 } @sortedNames;
3691            # We are ready to begin. We loop through the object names, replacing each
3692            # object name's field references by the corresponding SQL field reference.
3693            # Along the way, if we find a secondary relation, we will need to add it
3694            # to the FROM clause.
3695            for my $mappedName (@sortedNames) {
3696                # Get the length of the object name plus 2. This is the value we add to the
3697                # size of the field name to determine the size of the field reference as a
3698                # whole.
3699                my $nameLength = 2 + length $mappedName;
3700                # Get the real object name for this mapped name.
3701                my $objectName = $mappedNameHash{$mappedName};
3702                Trace("Processing $mappedName for object $objectName.") if T(4);
3703                # Get the object's field list.
3704                my $fieldList = $self->GetFieldTable($objectName);
3705                # Find the field references for this object.
3706                while ($filterString =~ m/$mappedName\(([^)]*)\)/g) {
3707                    # At this point, $1 contains the field name, and the current position
3708                    # is set immediately after the final parenthesis. We pull out the name of
3709                    # the field and the position and length of the field reference as a whole.
3710                    my $fieldName = $1;
3711                    my $len = $nameLength + length $fieldName;
3712                    my $pos = pos($filterString) - $len;
3713                    # Insure the field exists.
3714                    if (!exists $fieldList->{$fieldName}) {
3715                        Confess("Field $fieldName not found for object $objectName.");
3716                    } else {
3717                        Trace("Processing $fieldName at position $pos.") if T(4);
3718                        # Get the field's relation.
3719                        my $relationName = $fieldList->{$fieldName}->{relation};
3720                        # Now we have a secondary relation. We need to insure it matches the
3721                        # mapped name of the primary relation. First we peel off the suffix
3722                        # from the mapped name.
3723                        my $mappingSuffix = substr $mappedName, length($objectName);
3724                        # Put the mapping suffix onto the relation name to get the
3725                        # mapped relation name.
3726                        my $mappedRelationName = "$relationName$mappingSuffix";
3727                        # Insure the relation is in the FROM clause.
3728                        if (!exists $fromNames{$mappedRelationName}) {
3729                            # Add the relation to the FROM clause.
3730                            if ($mappedRelationName eq $relationName) {
3731                                # The name is un-mapped, so we add it without
3732                                # any frills.
3733                                $suffix .= ", $relationName";
3734                                push @joinWhere, "$objectName.id = $relationName.id";
3735                            } else {
3736                                # Here we have a mapping situation.
3737                                $suffix .= ", $relationName $mappedRelationName";
3738                                push @joinWhere, "$mappedRelationName.id = $mappedName.id";
3739                            }
3740                            # Denote we have this relation available for future fields.
3741                            $fromNames{$mappedRelationName} = 1;
3742                        }
3743                        # Form an SQL field reference from the relation name and the field name.
3744                        my $sqlReference = "$mappedRelationName." . _FixName($fieldName);
3745                        # Put it into the filter string in place of the old value.
3746                        substr($filterString, $pos, $len) = $sqlReference;
3747                        # Reposition the search.
3748                        pos $filterString = $pos + length $sqlReference;
3749                    }
3750                }
3751            }
3752        }
3753        # The next step is to join the objects together. We only need to do this if there
3754        # is more than one object in the object list. We start with the first object and
3755        # run through the objects after it. Note also that we make a safety copy of the
3756        # list before running through it, because we shift off the first object before
3757        # processing the rest.
3758        my @mappedObjectList = @mappedNameList;
3759        my $lastMappedObject = shift @mappedObjectList;
3760        # Get the join table.
3761        my $joinTable = $self->{_metaData}->{Joins};
3762        # Loop through the object list.
3763        for my $thisMappedObject (@mappedObjectList) {
3764            # Look for a join using the real object names.
3765            my $lastObject = $mappedNameHash{$lastMappedObject};
3766            my $thisObject = $mappedNameHash{$thisMappedObject};
3767            my $joinKey = "$lastObject/$thisObject";
3768            if (!exists $joinTable->{$joinKey}) {
3769                # Here there's no join, so we throw an error.
3770                Confess("No join exists to connect from $lastMappedObject to $thisMappedObject.");
3771              } else {              } else {
3772                  # Here we have a secondary relation field. Create a null list              # Get the join clause.
3773                  # and push the desired number of field values onto it.              my $unMappedJoin = $joinTable->{$joinKey};
3774                  my @fieldValues = ();              # Fix the names.
3775                  my $count = IntGen(0,$data->{testCount});              $unMappedJoin =~ s/$lastObject/$lastMappedObject/;
3776                  for (my $i = 0; $i < $count; $i++) {              $unMappedJoin =~ s/$thisObject/$thisMappedObject/;
3777                      my $newValue = eval($codeString);              push @joinWhere, $unMappedJoin;
3778                      push @fieldValues, $newValue;              # Save this object as the last object for the next iteration.
3779                $lastMappedObject = $thisMappedObject;
3780            }
3781        }
3782        # Now we need to handle the whole ORDER BY / LIMIT thing. The important part
3783        # here is we want the filter clause to be empty if there's no WHERE filter.
3784        # We'll put the ORDER BY / LIMIT clauses in the following variable.
3785        my $orderClause = "";
3786        # This is only necessary if we have a filter string in which the ORDER BY
3787        # and LIMIT clauses can live.
3788        if ($filterString) {
3789            # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy
3790            # operator so that we find the first occurrence of either verb.
3791            if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {
3792                # Here we have an ORDER BY or LIMIT verb. Split it off of the filter string.
3793                my $pos = pos $filterString;
3794                $orderClause = $2 . substr($filterString, $pos);
3795                $filterString = $1;
3796            }
3797        }
3798        # All the things that are supposed to be in the WHERE clause of the
3799        # SELECT command need to be put into @joinWhere so we can string them
3800        # together. We begin with the match clause. This is important,
3801        # because the match clause's parameter mark must precede any parameter
3802        # marks in the filter string.
3803        if ($matchClause) {
3804            push @joinWhere, $matchClause;
3805        }
3806        # Add the filter string. We put it in parentheses to avoid operator
3807        # precedence problems with the match clause or the joins.
3808        if ($filterString) {
3809            Trace("Filter string is \"$filterString\".") if T(4);
3810            push @joinWhere, "($filterString)";
3811        }
3812        # String it all together into a big filter clause.
3813        if (@joinWhere) {
3814            $suffix .= " WHERE " . join(' AND ', @joinWhere);
3815                  }                  }
3816                  # Store the value list in the main hash.      # Add the sort or limit clause (if any).
3817                  $this->{$name} = \@fieldValues;      if ($orderClause) {
3818            $suffix .= " $orderClause";
3819              }              }
3820        # Return the suffix, the mapped name list, and the mapped name hash.
3821        return ($suffix, \@mappedNameList, \%mappedNameHash);
3822          }          }
3823    
3824    =head3 _GetStatementHandle
3825    
3826    This method will prepare and execute an SQL query, returning the statement handle.
3827    The main reason for doing this here is so that everybody who does SQL queries gets
3828    the benefit of tracing.
3829    
3830    This is an instance method.
3831    
3832    =over 4
3833    
3834    =item command
3835    
3836    Command to prepare and execute.
3837    
3838    =item params
3839    
3840    Reference to a list of the values to be substituted in for the parameter marks.
3841    
3842    =item RETURN
3843    
3844    Returns a prepared and executed statement handle from which the caller can extract
3845    results.
3846    
3847    =back
3848    
3849    =cut
3850    
3851    sub _GetStatementHandle {
3852        # Get the parameters.
3853        my ($self, $command, $params) = @_;
3854        # Trace the query.
3855        Trace("SQL query: $command") if T(SQL => 3);
3856        Trace("PARMS: '" . (join "', '", @{$params}) . "'") if (T(SQL => 4) && (@{$params} > 0));
3857        # Get the database handle.
3858        my $dbh = $self->{_dbh};
3859        # Prepare the command.
3860        my $sth = $dbh->prepare_command($command);
3861        # Execute it with the parameters bound in.
3862        $sth->execute(@{$params}) || Confess("SELECT error:  " . $sth->errstr());
3863        # Return the statement handle.
3864        return $sth;
3865      }      }
3866    
3867    =head3 _GetLoadStats
3868    
3869    Return a blank statistics object for use by the load methods.
3870    
3871    This is a static method.
3872    
3873    =cut
3874    
3875    sub _GetLoadStats{
3876        return Stats->new();
3877  }  }
3878    
3879  =head3 DumpRelation  =head3 _DumpRelation
3880    
3881  Dump the specified relation's to the specified output file in tab-delimited format.  Dump the specified relation to the specified output file in tab-delimited format.
3882    
3883  This is an instance method.  This is an instance method.
3884    
# Line 1752  Line 3926