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

Diff of /Sprout/ERDB.pm

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

revision 1.42, Wed Apr 19 03:34:15 2006 UTC revision 1.97, Wed May 7 23:08:19 2008 UTC
# Line 6  Line 6 
6      use Data::Dumper;      use Data::Dumper;
7      use XML::Simple;      use XML::Simple;
8      use DBQuery;      use DBQuery;
9      use DBObject;      use ERDBObject;
10      use Stats;      use Stats;
11      use Time::HiRes qw(gettimeofday);      use Time::HiRes qw(gettimeofday);
12      use Digest::MD5 qw(md5_base64);      use Digest::MD5 qw(md5_base64);
13      use FIG;      use CGI;
14        use WikiTools;
15    
16  =head1 Entity-Relationship Database Package  =head1 Entity-Relationship Database Package
17    
# Line 59  Line 60 
60  B<start-position>, which indicates where in the contig that the sequence begins. This attribute  B<start-position>, which indicates where in the contig that the sequence begins. This attribute
61  is implemented as the C<start_position> field in the C<IsMadeUpOf> relation.  is implemented as the C<start_position> field in the C<IsMadeUpOf> relation.
62    
63  The database itself is described by an XML file using the F<ERDatabase.xsd> schema. In addition to  The database itself is described by an XML file. In addition to all the data required to define
64  all the data required to define the entities, relationships, and attributes, the schema provides  the entities, relationships, and attributes, the schema provides space for notes describing
65  space for notes describing the data and what it means. These notes are used by L</ShowMetaData>  the data and what it means. These notes are used by L</ShowMetaData> to generate documentation
66  to generate documentation for the database.  for the database.
67    
68    Special support is provided for text searching. An entity field can be marked as <em>searchable</em>,
69    in which case it will be used to generate a text search index in which the user searches for words
70    in the field instead of a particular field value.
71    
72  Finally, every entity and relationship object has a flag indicating if it is new or old. The object  Finally, every entity and relationship object has a flag indicating if it is new or old. The object
73  is considered I<old> if it was loaded by the L</LoadTables> method. It is considered I<new> if it  is considered I<old> if it was loaded by the L</LoadTables> method. It is considered I<new> if it
74  was inserted by the L</InsertObject> method.  was inserted by the L</InsertObject> method.
75    
 To facilitate testing, the ERDB module supports automatic generation of test data. This process  
 is described in the L</GenerateEntity> and L</GenerateConnection> methods, though it is not yet  
 fully implemented.  
   
76  =head2 XML Database Description  =head2 XML Database Description
77    
78  =head3 Data Types  =head3 Data Types
# Line 91  Line 92 
92    
93  32-bit signed integer  32-bit signed integer
94    
95    =item counter
96    
97    32-bit unsigned integer
98    
99  =item date  =item date
100    
101  64-bit unsigned integer, representing a PERL date/time value  64-bit unsigned integer, representing a PERL date/time value
# Line 110  Line 115 
115  compatability with certain database packages), but the only values supported are  compatability with certain database packages), but the only values supported are
116  0 and 1.  0 and 1.
117    
118    =item id-string
119    
120    variable-length string, maximum 25 characters
121    
122  =item key-string  =item key-string
123    
124  variable-length string, maximum 40 characters  variable-length string, maximum 40 characters
# Line 182  Line 191 
191    
192  Name of the field. The field name should contain only letters, digits, and hyphens (C<->),  Name of the field. The field name should contain only letters, digits, and hyphens (C<->),
193  and the first character should be a letter. Most underlying databases are case-insensitive  and the first character should be a letter. Most underlying databases are case-insensitive
194  with the respect to field names, so a best practice is to use lower-case letters only.  with the respect to field names, so a best practice is to use lower-case letters only. Finally,
195    the name C<search-relevance> has special meaning for full-text searches and should not be
196    used as a field name.
197    
198  =item type  =item type
199    
# Line 201  Line 212 
212  entity, the fields without a relation attribute are said to belong to the  entity, the fields without a relation attribute are said to belong to the
213  I<primary relation>. This relation has the same name as the entity itself.  I<primary relation>. This relation has the same name as the entity itself.
214    
215    =item searchable
216    
217    If specified, then the field is a candidate for full-text searching. A single full-text
218    index will be created for each relation with at least one searchable field in it.
219    For best results, this option should only be used for string or text fields.
220    
221    =item special
222    
223    This attribute allows the subclass to assign special meaning for certain fields.
224    The interpretation is up to the subclass itself. Currently, only entity fields
225    can have this attribute.
226    
227  =back  =back
228    
229  =head3 Indexes  =head3 Indexes
230    
231  An entity can have multiple alternate indexes associated with it. The fields must  An entity can have multiple alternate indexes associated with it. The fields in an
232  be from the primary relation. The alternate indexes assist in ordering results  index must all be from the same relation. The alternate indexes assist in searching
233  from a query. A relationship can have up to two indexes-- a I<to-index> and a  on fields other than the entity ID. A relationship has at least two indexes-- a I<to-index> and a
234  I<from-index>. These order the results when crossing the relationship. For  I<from-index> that 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
236  from-index would order the contigs of a ganome, and the to-index would order  from-index would order the contigs of a ganome, and the to-index would order
237  the genomes of a contig. A relationship's index must specify only fields in  the genomes of a contig. In addition, it can have zero or more alternate
238    indexes. A relationship's index must specify only fields in
239  the relationship.  the relationship.
240    
241  The indexes for an entity must be listed inside the B<Indexes> tag. The from-index  The alternate indexes for an entity or relationship must be listed inside the B<Indexes> tag.
242  of a relationship is specified using the B<FromIndex> tag; the to-index is specified  The from-index of a relationship is specified using the B<FromIndex> tag; the to-index is
243  using the B<ToIndex> tag.  specified using the B<ToIndex> tag.
244    
245  Each index can contain a B<Notes> tag. In addition, it will have an B<IndexFields>  Each index can contain a B<Notes> tag. In addition, it will have an B<IndexFields>
246  tag containing the B<IndexField> tags. These specify, in order, the fields used in  tag containing the B<IndexField> tags. These specify, in order, the fields used in
# Line 234  Line 258 
258    
259  =back  =back
260    
261  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
262    have a B<Unique> attribute. If specified, the index will be generated as a unique
263    index.
264    
265  =head3 Object and Field Names  =head3 Object and Field Names
266    
# Line 278  Line 304 
304    
305  A relationship is described by the C<Relationship> tag. Within a relationship,  A relationship is described by the C<Relationship> tag. Within a relationship,
306  there can be a C<Notes> tag, a C<Fields> tag containing the intersection data  there can be a C<Notes> tag, a C<Fields> tag containing the intersection data
307  fields, a C<FromIndex> tag containing the from-index, and a C<ToIndex> tag containing  fields, a C<FromIndex> tag containing the from-index, a C<ToIndex> tag containing
308  the to-index.  the to-index, and an C<Indexes> tag containing the alternate indexes.
309    
310  The C<Relationship> tag has the following attributes.  The C<Relationship> tag has the following attributes.
311    
# Line 312  Line 338 
338    
339  # 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.
340  # "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
341  # 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
342  # string is specified in the field definition. "avgLen" is the average byte length for estimating  # record sizes. "sort" is the key modifier for the sort command, "notes" is a type description,
343  # record sizes.  # and "indexMod", if non-zero, is the number of characters to use when the field is specified in an
344  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, dataGen => "StringGen('A')" },  # index
345                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, dataGen => "IntGen(0, 99999999)" },  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",
346                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, dataGen => "StringGen(IntGen(10,250))" },                                 indexMod =>   0, notes => "single ASCII character"},
347                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, dataGen => "StringGen(IntGen(80,1000))" },                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n",
348                    date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, dataGen => "DateGen(-7, 7, IntGen(0,1400))" },                                 indexMod =>   0, notes => "signed 32-bit integer"},
349                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, dataGen => "FloatGen(0.0, 100.0)" },                    counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n",
350                    boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, dataGen => "IntGen(0, 1)" },                                 indexMod =>   0, notes => "unsigned 32-bit integer"},
351                      string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, sort => "",
352                                   indexMod =>   0, notes => "character string, 0 to 255 characters"},
353                      text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, sort => "",
354                                   indexMod => 255, notes => "character string, nearly unlimited length, only first 255 characters are indexed"},
355                      date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, sort => "n",
356                                   indexMod =>   0, notes => "signed, 64-bit integer"},
357                      float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, sort => "g",
358                                   indexMod =>   0, notes => "64-bit double precision floating-point number"},
359                      boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, sort => "n",
360                                   indexMod =>   0, notes => "boolean value: 0 if false, 1 if true"},
361                   'hash-string' =>                   'hash-string' =>
362                               { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, dataGen => "SringGen(22)" },                               { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, sort => "",
363                                   indexMod =>   0, notes => "string stored in digested form, used for certain types of key fields"},
364                     'id-string' =>
365                                 { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, sort => "",
366                                   indexMod =>   0, notes => "character string, 0 to 25 characters"},
367                   'key-string' =>                   'key-string' =>
368                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, dataGen => "StringGen(IntGen(10,40))" },                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, sort => "",
369                                   indexMod =>   0, notes => "character string, 0 to 40 characters"},
370                   'name-string' =>                   'name-string' =>
371                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, dataGen => "StringGen(IntGen(10,80))" },                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, sort => "",
372                                   indexMod =>   0, notes => "character string, 0 to 80 characters"},
373                   'medium-string' =>                   'medium-string' =>
374                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, dataGen => "StringGen(IntGen(10,160))" },                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",
375                                   indexMod =>   0, notes => "character string, 0 to 160 characters"},
376                     'long-string' =>
377                                 { sqlType => 'VARCHAR(500)',       maxLen => 500,          avglen => 255, sort => "",
378                                   indexMod =>   0, notes => "character string, 0 to 500 characters"},
379                  );                  );
380    
381  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 338  Line 384 
384                     'MM' => 'many-to-many'                     'MM' => 'many-to-many'
385                   );                   );
386    
387  # Table for interpreting string patterns.  # Options for XML input and output.
388    
389    my %XmlOptions = (GroupTags =>  { Relationships => 'Relationship',
390                                      Entities => 'Entity',
391                                      Fields => 'Field',
392                                      Indexes => 'Index',
393                                      IndexFields => 'IndexField'
394                                    },
395                      KeyAttr =>    { Relationship => 'name',
396                                      Entity => 'name',
397                                      Field => 'name'
398                                    },
399                      SuppressEmpty => 1,
400                     );
401    
402  my %PictureTable = ( 'A' => "abcdefghijklmnopqrstuvwxyz",  my %XmlInOpts  = (
403                       '9' => "0123456789",                    ForceArray => ['Field', 'Index', 'IndexField', 'Relationship', 'Entity'],
404                       'X' => "abcdefghijklmnopqrstuvwxyz0123456789",                    ForceContent => 1,
405                       'V' => "aeiou",                    NormalizeSpace => 2,
406                       'K' => "bcdfghjklmnoprstvwxyz"                   );
407    my %XmlOutOpts = (
408                      RootName => 'Database',
409                      XMLDecl => 1,
410                     );                     );
411    
412  =head2 Public Methods  =head2 Public Methods
413    
414  =head3 new  =head3 new
415    
416  C<< my $database = ERDB->new($dbh, $metaFileName); >>      my $database = ERDB->new($dbh, $metaFileName);
417    
418  Create a new ERDB object.  Create a new ERDB object.
419    
# Line 371  Line 433 
433    
434  sub new {  sub new {
435      # Get the parameters.      # Get the parameters.
436      my ($class, $dbh, $metaFileName, $options) = @_;      my ($class, $dbh, $metaFileName, %options) = @_;
437      # Load the meta-data.      # Load the meta-data.
438      my $metaData = _LoadMetaData($metaFileName);      my $metaData = _LoadMetaData($metaFileName);
439      # Create the object.      # Create the object.
# Line 385  Line 447 
447    
448  =head3 ShowMetaData  =head3 ShowMetaData
449    
450  C<< $erdb->ShowMetaData($fileName); >>      $erdb->ShowMetaData($fileName);
451    
452  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
453  the data to be loaded into the relations.  the data to be loaded into the relations.
# Line 416  Line 478 
478      # Write the HTML heading stuff.      # Write the HTML heading stuff.
479      print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";      print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";
480      print HTMLOUT "</head>\n<body>\n";      print HTMLOUT "</head>\n<body>\n";
481        # Write the documentation.
482        print HTMLOUT $self->DisplayMetaData();
483        # Close the document.
484        print HTMLOUT "</body>\n</html>\n";
485        # Close the file.
486        close HTMLOUT;
487    }
488    
489    =head3 DisplayMetaData
490    
491        my $html = $erdb->DisplayMetaData();
492    
493    Return an HTML description of the database. This description can be used to help users create
494    the data to be loaded into the relations and form queries. The output is raw includable HTML
495    without any HEAD or BODY tags.
496    
497    =over 4
498    
499    =item filename
500    
501    The name of the output file.
502    
503    =back
504    
505    =cut
506    
507    sub DisplayMetaData {
508        # Get the parameters.
509        my ($self) = @_;
510        # Get the metadata and the title string.
511        my $metadata = $self->{_metaData};
512        # Get the title string.
513        my $title = $metadata->{Title};
514        # Get the entity and relationship lists.
515        my $entityList = $metadata->{Entities};
516        my $relationshipList = $metadata->{Relationships};
517        # Declare the return variable.
518        my $retVal = "";
519        # Open the output file.
520        Trace("Building MetaData table of contents.") if T(4);
521      # 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
522      # section contains an ordered list of entity or relationship subsections.      # section contains an ordered list of entity or relationship subsections.
523      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";
524      # Loop through the Entities, displaying a list item for each.      # Loop through the Entities, displaying a list item for each.
525      foreach my $key (sort keys %{$entityList}) {      foreach my $key (sort keys %{$entityList}) {
526          # Display this item.          # Display this item.
527          print HTMLOUT "<li><a href=\"#$key\">$key</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$key</a></li>\n";
528      }      }
529      # Close off the entity section and start the relationship section.      # Close off the entity section and start the relationship section.
530      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";
531      # Loop through the Relationships.      # Loop through the Relationships.
532      foreach my $key (sort keys %{$relationshipList}) {      foreach my $key (sort keys %{$relationshipList}) {
533          # Display this item.          # Display this item.
534          my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});          my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});
535          print HTMLOUT "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";
536      }      }
537      # Close off the relationship section and list the join table section.      # Close off the relationship section and list the join table section.
538      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";
539      # Close off the table of contents itself.      # Close off the table of contents itself.
540      print HTMLOUT "</ul>\n";      $retVal .=  "</ul>\n";
541      # 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.
542      print HTMLOUT "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";      $retVal .= "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";
543      # Loop through the entities.      # Loop through the entities.
544      for my $key (sort keys %{$entityList}) {      for my $key (sort keys %{$entityList}) {
545          Trace("Building MetaData entry for $key entity.") if T(4);          Trace("Building MetaData entry for $key entity.") if T(4);
546          # Create the entity header. It contains a bookmark and the entity name.          # Create the entity header. It contains a bookmark and the entity name.
547          print HTMLOUT "<a name=\"$key\"></a><h3>$key</h3>\n";          $retVal .= "<a name=\"$key\"></a><h3>$key</h3>\n";
548          # Get the entity data.          # Get the entity data.
549          my $entityData = $entityList->{$key};          my $entityData = $entityList->{$key};
550          # If there's descriptive text, display it.          # If there's descriptive text, display it.
551          if (my $notes = $entityData->{Notes}) {          if (my $notes = $entityData->{Notes}) {
552              print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
553          }          }
554          # 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.
555          print HTMLOUT "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          my $relCount = keys %{$relationshipList};
556            if ($relCount > 0) {
557                # First, we set up the relationship subsection.
558                $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
559          # Loop through the relationships.          # Loop through the relationships.
560          for my $relationship (sort keys %{$relationshipList}) {          for my $relationship (sort keys %{$relationshipList}) {
561              # Get the relationship data.              # Get the relationship data.
# Line 460  Line 565 
565                  # Get the relationship sentence and append the arity.                  # Get the relationship sentence and append the arity.
566                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);
567                  # Display the relationship data.                  # Display the relationship data.
568                  print HTMLOUT "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";                      $retVal .= "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";
569              }              }
570          }          }
571          # Close off the relationship list.          # Close off the relationship list.
572          print HTMLOUT "</ul>\n";              $retVal .= "</ul>\n";
573            }
574          # Get the entity's relations.          # Get the entity's relations.
575          my $relationList = $entityData->{Relations};          my $relationList = $entityData->{Relations};
576          # Create a header for the relation subsection.          # Create a header for the relation subsection.
577          print HTMLOUT "<h4>Relations for <b>$key</b></h4>\n";          $retVal .= "<h4>Relations for <b>$key</b></h4>\n";
578          # Loop through the relations, displaying them.          # Loop through the relations, displaying them.
579          for my $relation (sort keys %{$relationList}) {          for my $relation (sort keys %{$relationList}) {
580              my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});              my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});
581              print HTMLOUT $htmlString;              $retVal .= $htmlString;
582          }          }
583      }      }
584      # Denote we're starting the relationship section.      # Denote we're starting the relationship section.
585      print HTMLOUT "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";      $retVal .= "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";
586      # Loop through the relationships.      # Loop through the relationships.
587      for my $key (sort keys %{$relationshipList}) {      for my $key (sort keys %{$relationshipList}) {
588          Trace("Building MetaData entry for $key relationship.") if T(4);          Trace("Building MetaData entry for $key relationship.") if T(4);
# Line 484  Line 590 
590          my $relationshipStructure = $relationshipList->{$key};          my $relationshipStructure = $relationshipList->{$key};
591          # Create the relationship header.          # Create the relationship header.
592          my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);          my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);
593          print HTMLOUT "<h3><a name=\"$key\"></a>$headerText</h3>\n";          $retVal .= "<h3><a name=\"$key\"></a>$headerText</h3>\n";
594          # Get the entity names.          # Get the entity names.
595          my $fromEntity = $relationshipStructure->{from};          my $fromEntity = $relationshipStructure->{from};
596          my $toEntity = $relationshipStructure->{to};          my $toEntity = $relationshipStructure->{to};
# Line 494  Line 600 
600          # since both sentences will say the same thing.          # since both sentences will say the same thing.
601          my $arity = $relationshipStructure->{arity};          my $arity = $relationshipStructure->{arity};
602          if ($arity eq "11") {          if ($arity eq "11") {
603              print HTMLOUT "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";
604          } else {          } else {
605              print HTMLOUT "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";
606              if ($arity eq "MM" && $fromEntity ne $toEntity) {              if ($arity eq "MM" && $fromEntity ne $toEntity) {
607                  print HTMLOUT "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";                  $retVal .= "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";
608              }              }
609          }          }
610          print HTMLOUT "</p>\n";          $retVal .= "</p>\n";
611          # If there are notes on this relationship, display them.          # If there are notes on this relationship, display them.
612          if (my $notes = $relationshipStructure->{Notes}) {          if (my $notes = $relationshipStructure->{Notes}) {
613              print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
614          }          }
615          # Generate the relationship's relation table.          # Generate the relationship's relation table.
616          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
617          print HTMLOUT $htmlString;          $retVal .= $htmlString;
618      }      }
619      Trace("Building MetaData join table.") if T(4);      Trace("Building MetaData join table.") if T(4);
620      # Denote we're starting the join table.      # Denote we're starting the join table.
621      print HTMLOUT "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";      $retVal .= "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";
622      # Create a table header.      # Create a table header.
623      print HTMLOUT _OpenTable("Join Table", "Source", "Target", "Join Condition");      $retVal .= _OpenTable("Join Table", "Source", "Target", "Join Condition");
624      # Loop through the joins.      # Loop through the joins.
625      my $joinTable = $metadata->{Joins};      my $joinTable = $metadata->{Joins};
626      my @joinKeys = keys %{$joinTable};      my @joinKeys = keys %{$joinTable};
# Line 527  Line 633 
633          my $target = $self->ComputeObjectSentence($targetRelation);          my $target = $self->ComputeObjectSentence($targetRelation);
634          my $clause = $joinTable->{$joinKey};          my $clause = $joinTable->{$joinKey};
635          # Display them in a table row.          # Display them in a table row.
636          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";
637      }      }
638      # Close the table.      # Close the table.
639      print HTMLOUT _CloseTable();      $retVal .= _CloseTable();
640      # Close the document.      Trace("Built MetaData HTML.") if T(3);
641      print HTMLOUT "</body>\n</html>\n";      # Return the HTML.
642      # Close the file.      return $retVal;
     close HTMLOUT;  
     Trace("Built MetaData web page.") if T(3);  
643  }  }
644    
645  =head3 DumpMetaData  =head3 DumpMetaData
646    
647  C<< $erdb->DumpMetaData(); >>      $erdb->DumpMetaData();
648    
649  Return a dump of the metadata structure.  Return a dump of the metadata structure.
650    
# Line 553  Line 657 
657      return Data::Dumper::Dumper($self->{_metaData});      return Data::Dumper::Dumper($self->{_metaData});
658  }  }
659    
660    =head3 GenerateWikiData
661    
662        my @wikiLines = $erdb->GenerateWikiData();
663    
664    Build a description of the database for the wiki. The database will be
665    organized into a single page, with sections for each entity and relationship.
666    The return value is a list of text lines.
667    
668    =cut
669    
670    sub GenerateWikiData {
671        # Get the parameters.
672        my ($self) = @_;
673        # We'll build the wiki text in here.
674        my @retVal = ();
675        # Get the metadata object.
676        my $metadata = $self->{_metaData};
677        # Get the title string. This will become the page name.
678        my $title = $metadata->{Title}->{content};
679        # Get the entity and relationship lists.
680        my $entityList = $metadata->{Entities};
681        my $relationshipList = $metadata->{Relationships};
682        # Start with the introductory text.
683        push @retVal, WikiTools::Heading(2, "Introduction");
684        if (my $notes = $metadata->{Notes}) {
685            push @retVal, WikiNote($notes->{content});
686        }
687        # Start the entity section.
688        push @retVal, WikiTools::Heading(2, "Entities");
689        # Loop through the entities. Note that unlike the situation with HTML, we
690        # don't need to generate the table of contents manually, just the data
691        # itself.
692        for my $key (sort keys %$entityList) {
693            # Create a header for this entity.
694            push @retVal, "", WikiTools::Heading(3, $key);
695            # Get the entity data.
696            my $entityData = $entityList->{$key};
697            # Plant the notes here, if there are any.
698            if (my $notes = $entityData->{Notes}) {
699                push @retVal, "", WikiNote($notes->{content});
700            }
701            # Get the entity's relations.
702            my $relationList = $entityData->{Relations};
703            # Loop through the relations, displaying them.
704            for my $relation (sort keys %{$relationList}) {
705                my $wikiString = _WikiRelationTable($relation, $relationList->{$relation});
706                push @retVal, $wikiString;
707            }
708            # Now we list the entity's relationships (if any). First, we build a list
709            # of the relationships relevant to this entity.
710            my @rels = ();
711            for my $rel (sort keys %$relationshipList) {
712                my $relStructure = $relationshipList->{$rel};
713                if ($relStructure->{from} eq $key || $relStructure->{to} eq $key) {
714                    # Get the relationship sentence.
715                    my $relSentence = _ComputeRelationshipSentence($rel, $relStructure);
716                    # Linkify it.
717                    my $linkedRel = WikiTools::LinkMarkup("#$rel", $rel);
718                    $relSentence =~ s/$rel/$linkedRel/;
719                    push @rels, $relSentence;
720                }
721            }
722            # Add the relationships as a Wiki list.
723            push @retVal, WikiTools::List(@rels);
724        }
725        # Now the entities are documented. Next we do the relationships.
726        push @retVal, WikiTools::Heading(2, "Relationships");
727        for my $key (sort keys %$relationshipList) {
728            my $relationshipData = $relationshipList->{$key};
729            # Create the relationship heading.
730            push @retVal, WikiTools::Heading(3, $key);
731            # Describe the relationship arity. Note there's a bit of trickiness involving recursive
732            # many-to-many relationships. In a normal many-to-many we use two sentences to describe
733            # the arity (one for each direction). This is a bad idea for a recursive relationship,
734            # since both sentences will say the same thing.
735            my $arity = $relationshipData->{arity};
736            my $fromEntity = $relationshipData->{from};
737            my $toEntity = $relationshipData->{to};
738            my @listElements = ();
739            my $boldCode = WikiTools::BoldCode();
740            if ($arity eq "11") {
741                push @listElements, "Each $boldCode$fromEntity$boldCode relates to at most one $boldCode$toEntity$boldCode.";
742            } else {
743                push @listElements, "Each $boldCode$fromEntity$boldCode relates to multiple $boldCode${toEntity}s$boldCode.\n";
744                if ($arity eq "MM" && $fromEntity ne $toEntity) {
745                    push @listElements, "Each $boldCode$toEntity$boldCode relates to multiple $boldCode${fromEntity}s$boldCode.\n";
746                }
747            }
748            push @retVal, WikiTools::List(@listElements);
749            # Plant the notes here, if there are any.
750            if (my $notes = $relationshipData->{Notes}) {
751                push @retVal, "", WikiNote($notes->{content});
752            }
753            # Finally, the relationship table.
754            my $wikiString = _WikiRelationTable($key, $relationshipData->{Relations}->{$key});
755            push @retVal, $wikiString;
756        }
757        # All done. Return the lines.
758        return @retVal;
759    }
760    
761    
762    =head3 CreatePPO
763    
764        ERDB::CreatePPO($erdbXMLFile, $ppoXMLFile);
765    
766    Create a PPO XML file from an ERDB data definition XML file. At the
767    current time, the PPO XML file can be used to create a database with
768    similar functionality. Eventually, the PPO will be able to use the
769    created XML to access the live ERDB database.
770    
771    =over 4
772    
773    =item erdbXMLFile
774    
775    Name of the XML data definition file for the ERDB database. This
776    file must exist.
777    
778    =item ppoXMLFile
779    
780    Output file for the PPO XML definition. If this file exists, it
781    will be overwritten.
782    
783    =back
784    
785    =cut
786    
787    sub CreatePPO {
788        # Get the parameters.
789        my ($erdbXMLFile, $ppoXMLFile) = @_;
790        # First, we want to slurp in the ERDB XML file in its raw form.
791        my $xml = ReadMetaXML($erdbXMLFile);
792        # Create a variable to hold all of the objects in the PPO project.
793        my @objects = ();
794        # Get the relationship hash.
795        my $relationships = $xml->{Relationships};
796        # Loop through the entities.
797        my $entities = $xml->{Entities};
798        for my $entityName (keys %{$entities}) {
799            # Get the entity's data structures.
800            my $entityObject = $entities->{$entityName};
801            # We put the object's fields in here, according to their type.
802            my (@object_refs, @scalars, @indexes, @arrays);
803            # Create the ID field for the entity. We get the key type from the
804            # entity object and compute the corresponding SQL type.
805            my $type = $TypeTable{$entityObject->{keyType}}->{sqlType};
806            push @scalars, { label => 'id', type => $type };
807            # Loop through the entity fields.
808            for my $fieldName ( keys %{$entityObject->{Fields}} ) {
809                # Get the field object.
810                my $fieldObject = $entityObject->{Fields}->{$fieldName};
811                # Convert it to a scalar tag.
812                my $scalar = _CreatePPOField($fieldName, $fieldObject);
813                # If we have a relation, this field is stored in an array.
814                # otherwise, it is a scalar. The array tag has scalars
815                # stored as an XML array. In ERDB, there is only ever one,
816                # but PPO can have more.
817                my $relation = $fieldObject->{relation};
818                if ($relation) {
819                    push @arrays, { scalar => [$scalar] };
820                } else {
821                    push @scalars, $scalar;
822                }
823            }
824            # Loop through the relationships. If this entity is the to-entity
825            # on a relationship of 1M arity, then it is implemented as a PPO
826            # object reference.
827            for my $relationshipName (keys %{$relationships}) {
828                # Get the relationship data.
829                my $relationshipData = $relationships->{$relationshipName};
830                # If we have a from for this entity and an arity of 1M, we
831                # have an object reference.
832                if ($relationshipData->{to} eq $entityName &&
833                    $relationshipData->{arity} eq '1M') {
834                    # Build the object reference tag.
835                    push @object_refs, { label => $relationshipName,
836                                         type => $relationshipData->{from} };
837                }
838            }
839            # Create the indexes.
840            my $indexList = $entityObject->{Indexes};
841            push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
842            # Build the object XML tree.
843            my $object = { label => $entityName,
844                           object_ref => \@object_refs,
845                           scalar => \@scalars,
846                           index => \@indexes,
847                           array => \@arrays
848                          };
849            # Push the object onto the objects list.
850            push @objects, $object;
851        }
852        # Loop through the relationships, searching for MMs. The 1Ms were
853        # already handled by the entity search above.
854        for my $relationshipName (keys %{$relationships}) {
855            # Get this relationship's object.
856            my $relationshipObject = $relationships->{$relationshipName};
857            # Only proceed if it's many-to-many.
858            if ($relationshipObject->{arity} eq 'MM') {
859                # Create the tag lists for the relationship object.
860                my (@object_refs, @scalars, @indexes);
861                # The relationship will be created as an object with object
862                # references for its links to the participating entities.
863                my %links = ( from_link => $relationshipObject->{from},
864                              to_link => $relationshipObject->{to} );
865                for my $link (keys %links) {
866                    # Create an object_ref tag for this piece of the
867                    # relationship (from or to).
868                    my $object_ref = { label => $link,
869                                       type => $links{$link} };
870                    push @object_refs, $object_ref;
871                }
872                # Loop through the intersection data fields, creating scalar tags.
873                # There are no fancy array tags in a relationship.
874                for my $fieldName (keys %{$relationshipObject->{Fields}}) {
875                    my $fieldObject = $relationshipObject->{Fields}->{$fieldName};
876                    push @scalars, _CreatePPOField($fieldName, $fieldObject);
877                }
878                # Finally, the indexes: currently we cannot support the to-index and
879                # from-index in PPO, so we just process the alternate indexes.
880                my $indexList = $relationshipObject->{Indexes};
881                push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
882                # Wrap up all the stuff about this relationship.
883                my $object = { label => $relationshipName,
884                               scalar => \@scalars,
885                               object_ref => \@object_refs,
886                               index => \@indexes
887                             };
888                # Push it into the object list.
889                push @objects, $object;
890            }
891        }
892        # Compute a title.
893        my $title;
894        if ($erdbXMLFile =~ /(\/|^)([^\/]+)DBD\.xml/) {
895            # Here we have a standard file name we can use for a title.
896            $title = $2;
897        } else {
898            # Here the file name is non-standard, so we carve up the
899            # database title.
900            $title = $xml->{Title}->{content};
901            $title =~ s/\s\.,//g;
902        }
903        # Wrap up the XML as a project.
904        my $ppoXML = { project => { label => $title,
905                                    object => \@objects }};
906        # Write out the results.
907        my $ppoString = XML::Simple::XMLout($ppoXML,
908                                            AttrIndent => 1,
909                                            KeepRoot => 1);
910        Tracer::PutFile($ppoXMLFile, [ $ppoString ]);
911    }
912    
913    =head3 FindIndexForEntity
914    
915        my $indexFound = ERDB::FindIndexForEntity($xml, $entityName, $attributeName);
916    
917    This method locates the entry in an entity's index list that begins with the
918    specified attribute name. If the entity has no index list, one will be
919    created. This method works on raw XML, not a live ERDB object.
920    
921    =over 4
922    
923    =item xml
924    
925    The raw XML structure defining the database.
926    
927    =item entityName
928    
929    The name of the relevant entity.
930    
931    =item attributeName
932    
933    The name of the attribute relevant to the search.
934    
935    =item RETURN
936    
937    The numerical index in the index list of the index entry for the specified entity and
938    attribute, or C<undef> if no such index exists.
939    
940    =back
941    
942    =cut
943    
944    sub FindIndexForEntity {
945        # Get the parameters.
946        my ($xml, $entityName, $attributeName) = @_;
947        # Declare the return variable.
948        my $retVal;
949        # Get the named entity.
950        my $entityData = $xml->{Entities}->{$entityName};
951        if (! $entityData) {
952            Confess("Entity $entityName not found in DBD structure.");
953        } else {
954            # Insure it has an index list.
955            if (! exists $entityData->{Indexes}) {
956                $entityData->{Indexes} = [];
957            } else {
958                # Search for the desired index.
959                my $indexList = $entityData->{Indexes};
960                my $n = scalar @{$indexList};
961                Trace("Searching $n indexes in index list for $entityName.") if T(2);
962                # We use an indexed FOR here because we're returning an
963                # index number instead of an object. We do THAT so we can
964                # delete the index from the list if needed.
965                for (my $i = 0; $i < $n && !defined($retVal); $i++) {
966                    my $index = $indexList->[$i];
967                    my $fields = $index->{IndexFields};
968                    # Technically this IF should be safe (that is, we are guaranteed
969                    # the existence of a "$fields->[0]"), because when we load the XML
970                    # we have SuppressEmpty specified.
971                    if ($fields->[0]->{name} eq $attributeName) {
972                        $retVal = $i;
973                    }
974                }
975            }
976        }
977        Trace("Index for $attributeName of $entityName found at position $retVal.") if defined($retVal) && T(3);
978        Trace("Index for $attributeName not found in $entityName.") if !defined($retVal) && T(3);
979        # Return the result.
980        return $retVal;
981    }
982    
983  =head3 CreateTables  =head3 CreateTables
984    
985  C<< $erdb->CreateTables(); >>      $erdb->CreateTables();
986    
987  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
988  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 572  Line 999 
999      # Loop through the relations.      # Loop through the relations.
1000      for my $relationName (@relNames) {      for my $relationName (@relNames) {
1001          # Create a table for this relation.          # Create a table for this relation.
1002          $self->CreateTable($relationName);          $self->CreateTable($relationName, 1);
1003          Trace("Relation $relationName created.") if T(2);          Trace("Relation $relationName created.") if T(2);
1004      }      }
1005  }  }
1006    
1007  =head3 CreateTable  =head3 CreateTable
1008    
1009  C<< $erdb->CreateTable($tableName, $indexFlag, $estimatedRows); >>      $erdb->CreateTable($tableName, $indexFlag, $estimatedRows);
1010    
1011  Create the table for a relation and optionally create its indexes.  Create the table for a relation and optionally create its indexes.
1012    
# Line 635  Line 1062 
1062      my $estimation = undef;      my $estimation = undef;
1063      if ($estimatedRows) {      if ($estimatedRows) {
1064          $estimation = [$self->EstimateRowSize($relationName), $estimatedRows];          $estimation = [$self->EstimateRowSize($relationName), $estimatedRows];
1065            Trace("$estimation->[1] rows of $estimation->[0] bytes each.") if T(3);
1066      }      }
1067      # Create the table.      # Create the table.
1068      Trace("Creating table $relationName: $fieldThing") if T(2);      Trace("Creating table $relationName: $fieldThing") if T(2);
1069      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);
1070      Trace("Relation $relationName created in database.") if T(2);      Trace("Relation $relationName created in database.") if T(2);
1071      # If we want to build the indexes, we do it here.      # If we want to build the indexes, we do it here. Note that the full-text search
1072        # index will not be built until the table has been loaded.
1073      if ($indexFlag) {      if ($indexFlag) {
1074          $self->CreateIndex($relationName);          $self->CreateIndex($relationName);
1075      }      }
# Line 648  Line 1077 
1077    
1078  =head3 VerifyFields  =head3 VerifyFields
1079    
1080  C<< my $count = $erdb->VerifyFields($relName, \@fieldList); >>      my $count = $erdb->VerifyFields($relName, \@fieldList);
1081    
1082  Run through the list of proposed field values, insuring that all the character fields are  Run through the list of proposed field values, insuring that all the character fields are
1083  below the maximum length. If any fields are too long, they will be truncated in place.  below the maximum length. If any fields are too long, they will be truncated in place.
# Line 691  Line 1120 
1120              my $oldString = $fieldList->[$i];              my $oldString = $fieldList->[$i];
1121              if (length($oldString) > $maxLen) {              if (length($oldString) > $maxLen) {
1122                  # Here it's too big, so we truncate it.                  # Here it's too big, so we truncate it.
1123                  Trace("Truncating field $i in relation $relName to $maxLen characters from \"$oldString\".") if T(1);                  Trace("Truncating field $i ($fieldTypes->[$i]->{name}) in relation $relName to $maxLen characters from \"$oldString\".") if T(1);
1124                  $fieldList->[$i] = substr $oldString, 0, $maxLen;                  $fieldList->[$i] = substr $oldString, 0, $maxLen;
1125                  $retVal++;                  $retVal++;
1126              }              }
# Line 703  Line 1132 
1132    
1133  =head3 DigestFields  =head3 DigestFields
1134    
1135  C<< $erdb->DigestFields($relName, $fieldList); >>      $erdb->DigestFields($relName, $fieldList);
1136    
1137  Digest the strings in the field list that correspond to data type C<hash-string> in the  Digest the strings in the field list that correspond to data type C<hash-string> in the
1138  specified relation.  specified relation.
# Line 736  Line 1165 
1165          my $fieldType = $fieldTypes->[$i]->{type};          my $fieldType = $fieldTypes->[$i]->{type};
1166          # If it's a hash string, digest it in place.          # If it's a hash string, digest it in place.
1167          if ($fieldType eq 'hash-string') {          if ($fieldType eq 'hash-string') {
1168              $fieldList->[$i] = md5_base64($fieldList->[$i]);              $fieldList->[$i] = $self->DigestKey($fieldList->[$i]);
1169            }
1170          }          }
1171      }      }
1172    
1173    =head3 DigestKey
1174    
1175        my $digested = $erdb->DigestKey($keyValue);
1176    
1177    Return the digested value of a symbolic key. The digested value can then be plugged into a
1178    key-based search into a table with key-type hash-string.
1179    
1180    Currently the digesting process is independent of the database structure, but that may not
1181    always be the case, so this is an instance method instead of a static method.
1182    
1183    =over 4
1184    
1185    =item keyValue
1186    
1187    Key value to digest.
1188    
1189    =item RETURN
1190    
1191    Digested value of the key.
1192    
1193    =back
1194    
1195    =cut
1196    
1197    sub DigestKey {
1198        # Get the parameters.
1199        my ($self, $keyValue) = @_;
1200        # Compute the digest.
1201        my $retVal = md5_base64($keyValue);
1202        # Return the result.
1203        return $retVal;
1204  }  }
1205    
1206  =head3 CreateIndex  =head3 CreateIndex
1207    
1208  C<< $erdb->CreateIndex($relationName); >>      $erdb->CreateIndex($relationName);
1209    
1210  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
1211  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 764  Line 1226 
1226      for my $indexName (keys %{$indexHash}) {      for my $indexName (keys %{$indexHash}) {
1227          my $indexData = $indexHash->{$indexName};          my $indexData = $indexHash->{$indexName};
1228          # Get the index's field list.          # Get the index's field list.
1229          my @fieldList = _FixNames(@{$indexData->{IndexFields}});          my @rawFields = @{$indexData->{IndexFields}};
1230            # Get a hash of the relation's field types.
1231            my %types = map { $_->{name} => $_->{type} } @{$relationData->{Fields}};
1232            # We need to check for text fields so we can append a length limitation for them. To do
1233            # that, we need the relation's field list.
1234            my $relFields = $relationData->{Fields};
1235            for (my $i = 0; $i <= $#rawFields; $i++) {
1236                # Get the field type.
1237                my $field = $rawFields[$i];
1238                my $type = $types{$field};
1239                # Ask if it requires using prefix notation for the index.
1240                my $mod = $TypeTable{$type}->{indexMod};
1241                Trace("Field $field ($i) in $relationName has type $type and indexMod $mod.") if T(3);
1242                if ($mod) {
1243                    # Append the prefix length to the field name,
1244                    $rawFields[$i] .= "($mod)";
1245                }
1246            }
1247            my @fieldList = _FixNames(@rawFields);
1248          my $flds = join(', ', @fieldList);          my $flds = join(', ', @fieldList);
1249          # Get the index's uniqueness flag.          # Get the index's uniqueness flag.
1250          my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
1251          # Create the index.          # Create the index.
1252          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
1253                                      flds => $flds, unique => $unique);                                      flds => $flds, kind => $unique);
1254          if ($rv) {          if ($rv) {
1255              Trace("Index created: $indexName for $relationName ($flds)") if T(1);              Trace("Index created: $indexName for $relationName ($flds)") if T(1);
1256          } else {          } else {
# Line 779  Line 1259 
1259      }      }
1260  }  }
1261    
1262  =head3 LoadTables  =head3 GetSecondaryFields
   
 C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>  
1263    
1264  This method will load the database tables from a directory. The tables must already have been created      my %fieldTuples = $erdb->GetSecondaryFields($entityName);
 in the database. (This can be done by calling L</CreateTables>.) The caller passes in a directory name;  
 all of the relations to be loaded must have a file in the directory with the same name as the relation  
 (optionally with a suffix of C<.dtx>). Each file must be a tab-delimited table of field values. Each  
 line of the file will be loaded as a row of the target relation table. The field values should be in  
 the same order as the fields in the relation tables generated by L</ShowMetaData>. The old data is  
 erased before the new data is loaded in.  
1265    
1266  A certain amount of translation automatically takes place. Ctrl-M characters are deleted, and  This method will return a list of the name and type of each of the secondary
1267  tab and new-line characters inside a field are escaped as C<\t> and C<\n>, respectively. Dates must  fields for a specified entity. Secondary fields are stored in two-column tables
1268  be entered as a Unix timestamp, that is, as an integer number of seconds since the base epoch.  in addition to the primary entity table. This enables the field to have no value
1269    or to have multiple values.
1270    
1271  =over 4  =over 4
1272    
1273  =item directoryName  =item entityName
   
 Name of the directory containing the relation files to be loaded.  
   
 =item rebuild  
1274    
1275  TRUE if the tables should be dropped and rebuilt, else FALSE. This is, unfortunately, the  Name of the entity whose secondary fields are desired.
 only way to erase existing data in the tables, since the TRUNCATE command is not supported  
 by all of the DB engines we use.  
1276    
1277  =item RETURN  =item RETURN
1278    
1279  Returns a statistical object describing the number of records read and a list of the error messages.  Returns a hash mapping the field names to their field types.
1280    
1281  =back  =back
1282    
1283  =cut  =cut
1284    
1285  sub LoadTables {  sub GetSecondaryFields {
1286      # Get the parameters.      # Get the parameters.
1287      my ($self, $directoryName, $rebuild) = @_;      my ($self, $entityName) = @_;
     # Start the timer.  
     my $startTime = gettimeofday;  
     # Clean any trailing slash from the directory name.  
     $directoryName =~ s!/\\$!!;  
1288      # Declare the return variable.      # Declare the return variable.
1289      my $retVal = Stats->new();      my %retVal = ();
1290      # Get the relation names.      # Look for the entity.
1291      my @relNames = $self->GetTableNames();      my $table = $self->GetFieldTable($entityName);
1292      for my $relationName (@relNames) {      # Loop through the fields, pulling out the secondaries.
1293          # Try to load this relation.      for my $field (sort keys %{$table}) {
1294          my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);          if ($table->{$field}->{relation} ne $entityName) {
1295          # Accumulate the statistics.              # Here we have a secondary field.
1296          $retVal->Accumulate($result);              $retVal{$field} = $table->{$field}->{type};
1297      }      }
1298      # Add the duration of the load to the statistical object.      }
1299      $retVal->Add('duration', gettimeofday - $startTime);      # Return the result.
1300      # Return the accumulated statistics.      return %retVal;
     return $retVal;  
1301  }  }
1302    
1303    =head3 GetFieldRelationName
1304    
1305  =head3 GetTableNames      my $name = $erdb->GetFieldRelationName($objectName, $fieldName);
1306    
1307  C<< my @names = $erdb->GetTableNames; >>  Return the name of the relation containing a specified field.
1308    
1309  Return a list of the relations required to implement this database.  =over 4
1310    
1311  =cut  =item objectName
1312    
1313  sub GetTableNames {  Name of the entity or relationship containing the field.
     # Get the parameters.  
     my ($self) = @_;  
     # Get the relation list from the metadata.  
     my $relationTable = $self->{_metaData}->{RelationTable};  
     # Return the relation names.  
     return keys %{$relationTable};  
 }  
1314    
1315  =head3 GetEntityTypes  =item fieldName
1316    
1317  C<< my @names = $erdb->GetEntityTypes; >>  Name of the relevant field in that entity or relationship.
1318    
1319  Return a list of the entity type names.  =item RETURN
1320    
1321    Returns the name of the database relation containing the field, or C<undef> if
1322    the field does not exist.
1323    
1324    =back
1325    
1326  =cut  =cut
1327    
1328  sub GetEntityTypes {  sub GetFieldRelationName {
1329      # Get the database object.      # Get the parameters.
1330      my ($self) = @_;      my ($self, $objectName, $fieldName) = @_;
1331      # Get the entity list from the metadata object.      # Declare the return variable.
1332      my $entityList = $self->{_metaData}->{Entities};      my $retVal;
1333      # Return the list of entity names in alphabetical order.      # Get the object field table.
1334      return sort keys %{$entityList};      my $table = $self->GetFieldTable($objectName);
1335        # Only proceed if the field exists.
1336        if (exists $table->{$fieldName}) {
1337            # Determine the name of the relation that contains this field.
1338            $retVal = $table->{$fieldName}->{relation};
1339        }
1340        # Return the result.
1341        return $retVal;
1342  }  }
1343    
1344    =head3 DeleteValue
1345    
1346        my $numDeleted = $erdb->DeleteValue($entityName, $id, $fieldName, $fieldValue);
1347    
1348    Delete secondary field values from the database. This method can be used to delete all
1349    values of a specified field for a particular entity instance, or only a single value.
1350    
1351    Secondary fields are stored in two-column relations separate from an entity's primary
1352    table, and as a result a secondary field can legitimately have no value or multiple
1353    values. Therefore, it makes sense to talk about deleting secondary fields where it
1354    would not make sense for primary fields.
1355    
1356    =over 4
1357    
1358    =item entityName
1359    
1360    Name of the entity from which the fields are to be deleted.
1361    
1362    =item id
1363    
1364    ID of the entity instance to be processed. If the instance is not found, this
1365    method will have no effect. If C<undef> is specified, all values for all of
1366    the entity instances will be deleted.
1367    
1368    =item fieldName
1369    
1370    Name of the field whose values are to be deleted.
1371    
1372    =item fieldValue (optional)
1373    
1374    Value to be deleted. If not specified, then all values of the specified field
1375    will be deleted for the entity instance. If specified, then only the values which
1376    match this parameter will be deleted.
1377    
1378    =item RETURN
1379    
1380    Returns the number of rows deleted.
1381    
1382    =back
1383    
1384    =cut
1385    
1386    sub DeleteValue {
1387        # Get the parameters.
1388        my ($self, $entityName, $id, $fieldName, $fieldValue) = @_;
1389        # Declare the return value.
1390        my $retVal = 0;
1391        # We need to set up an SQL command to do the deletion. First, we
1392        # find the name of the field's relation.
1393        my $table = $self->GetFieldTable($entityName);
1394        my $field = $table->{$fieldName};
1395        my $relation = $field->{relation};
1396        # Make sure this is a secondary field.
1397        if ($relation eq $entityName) {
1398            Confess("Cannot delete values of $fieldName for $entityName.");
1399        } else {
1400            # Set up the SQL command to delete all values.
1401            my $sql = "DELETE FROM $relation";
1402            # Build the filter.
1403            my @filters = ();
1404            my @parms = ();
1405            # Check for a filter by ID.
1406            if (defined $id) {
1407                push @filters, "id = ?";
1408                push @parms, $id;
1409            }
1410            # Check for a filter by value.
1411            if (defined $fieldValue) {
1412                push @filters, "$fieldName = ?";
1413                push @parms, $fieldValue;
1414            }
1415            # Append the filters to the command.
1416            if (@filters) {
1417                $sql .= " WHERE " . join(" AND ", @filters);
1418            }
1419            # Execute the command.
1420            my $dbh = $self->{_dbh};
1421            $retVal = $dbh->SQL($sql, 0, @parms);
1422        }
1423        # Return the result.
1424        return $retVal;
1425    }
1426    
1427    =head3 LoadTables
1428    
1429        my $stats = $erdb->LoadTables($directoryName, $rebuild);
1430    
1431    This method will load the database tables from a directory. The tables must already have been created
1432    in the database. (This can be done by calling L</CreateTables>.) The caller passes in a directory name;
1433    all of the relations to be loaded must have a file in the directory with the same name as the relation
1434    (optionally with a suffix of C<.dtx>). Each file must be a tab-delimited table of field values. Each
1435    line of the file will be loaded as a row of the target relation table. The field values should be in
1436    the same order as the fields in the relation tables generated by L</ShowMetaData>. The old data is
1437    erased before the new data is loaded in.
1438    
1439    A certain amount of translation automatically takes place. Ctrl-M characters are deleted, and
1440    tab and new-line characters inside a field are escaped as C<\t> and C<\n>, respectively. Dates must
1441    be entered as a Unix timestamp, that is, as an integer number of seconds since the base epoch.
1442    
1443    =over 4
1444    
1445    =item directoryName
1446    
1447    Name of the directory containing the relation files to be loaded.
1448    
1449    =item rebuild
1450    
1451    TRUE if the tables should be dropped and rebuilt, else FALSE. This is, unfortunately, the
1452    only way to erase existing data in the tables, since the TRUNCATE command is not supported
1453    by all of the DB engines we use.
1454    
1455    =item RETURN
1456    
1457    Returns a statistical object describing the number of records read and a list of the error messages.
1458    
1459    =back
1460    
1461    =cut
1462    
1463    sub LoadTables {
1464        # Get the parameters.
1465        my ($self, $directoryName, $rebuild) = @_;
1466        # Start the timer.
1467        my $startTime = gettimeofday;
1468        # Clean any trailing slash from the directory name.
1469        $directoryName =~ s!/\\$!!;
1470        # Declare the return variable.
1471        my $retVal = Stats->new();
1472        # Get the relation names.
1473        my @relNames = $self->GetTableNames();
1474        for my $relationName (@relNames) {
1475            # Try to load this relation.
1476            my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);
1477            # Accumulate the statistics.
1478            $retVal->Accumulate($result);
1479        }
1480        # Add the duration of the load to the statistical object.
1481        $retVal->Add('duration', gettimeofday - $startTime);
1482        # Return the accumulated statistics.
1483        return $retVal;
1484    }
1485    
1486    
1487    =head3 GetTableNames
1488    
1489        my @names = $erdb->GetTableNames;
1490    
1491    Return a list of the relations required to implement this database.
1492    
1493    =cut
1494    
1495    sub GetTableNames {
1496        # Get the parameters.
1497        my ($self) = @_;
1498        # Get the relation list from the metadata.
1499        my $relationTable = $self->{_metaData}->{RelationTable};
1500        # Return the relation names.
1501        return keys %{$relationTable};
1502    }
1503    
1504    =head3 GetEntityTypes
1505    
1506        my @names = $erdb->GetEntityTypes;
1507    
1508    Return a list of the entity type names.
1509    
1510    =cut
1511    
1512    sub GetEntityTypes {
1513        # Get the database object.
1514        my ($self) = @_;
1515        # Get the entity list from the metadata object.
1516        my $entityList = $self->{_metaData}->{Entities};
1517        # Return the list of entity names in alphabetical order.
1518        return sort keys %{$entityList};
1519    }
1520    
1521    =head3 GetDataTypes
1522    
1523        my %types = ERDB::GetDataTypes();
1524    
1525    Return a table of ERDB data types. The table returned is a hash of hashes.
1526    The keys of the big hash are the datatypes. Each smaller hash has several
1527    values used to manage the data. The most interesting is the SQL type (key
1528    C<sqlType>) and the descriptive node (key C<notes>).
1529    
1530    Note that changing the values in the smaller hashes will seriously break
1531    things, so this data should be treated as read-only.
1532    
1533    =cut
1534    
1535    sub GetDataTypes {
1536        return %TypeTable;
1537    }
1538    
1539    
1540  =head3 IsEntity  =head3 IsEntity
1541    
1542  C<< my $flag = $erdb->IsEntity($entityName); >>      my $flag = $erdb->IsEntity($entityName);
1543    
1544  Return TRUE if the parameter is an entity name, else FALSE.  Return TRUE if the parameter is an entity name, else FALSE.
1545    
# Line 902  Line 1566 
1566    
1567  =head3 Get  =head3 Get
1568    
1569  C<< my $query = $erdb->Get(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>      my $query = $erdb->Get(\@objectNames, $filterClause, \@params);
1570    
1571  This method returns a query object for entities of a specified type using a specified filter.  This method returns a query object for entities of a specified type using a specified filter.
1572  The filter is a standard WHERE/ORDER BY clause with question marks as parameter markers and each  The filter is a standard WHERE/ORDER BY clause with question marks as parameter markers and each
# Line 910  Line 1574 
1574  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
1575  $genus.  $genus.
1576    
1577  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", $genus); >>      $query = $erdb->Get(['Genome'], "Genome(genus) = ?", [$genus]);
1578    
1579  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
1580  parameter representing the parameter value. It would also be possible to code  parameter representing the parameter value. It would also be possible to code
1581    
1582  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>      $query = $erdb->Get(['Genome'], "Genome(genus) = \'$genus\'");
1583    
1584  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
1585  characters inside the variable C<$genus>.  characters inside the variable C<$genus>.
# Line 927  Line 1591 
1591  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
1592  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,
1593    
1594  C<< $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", $genus); >>      $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]);
1595    
1596  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
1597  join path between the entities and relationships. The algorithm used is very simplistic.  join path between the entities and relationships. The algorithm used is very simplistic.
# Line 963  Line 1627 
1627  with an ORDER BY clause. For example, the following filter string gets all genomes for a  with an ORDER BY clause. For example, the following filter string gets all genomes for a
1628  particular genus and sorts them by species name.  particular genus and sorts them by species name.
1629    
1630  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>      "Genome(genus) = ? ORDER BY Genome(species)"
1631    
1632  Note that the case is important. Only an uppercase "ORDER BY" with a single space will  Note that the case is important. Only an uppercase "ORDER BY" with a single space will
1633  be processed. The idea is to make it less likely to find the verb by accident.  be processed. The idea is to make it less likely to find the verb by accident.
# Line 976  Line 1640 
1640  be the last thing in the filter clause, and it contains only the word "LIMIT" followed by  be the last thing in the filter clause, and it contains only the word "LIMIT" followed by
1641  a positive number. So, for example  a positive number. So, for example
1642    
1643  C<< "Genome(genus) = ? ORDER BY Genome(species) LIMIT 10" >>      "Genome(genus) = ? ORDER BY Genome(species) LIMIT 10"
1644    
1645  will only return the first ten genomes for the specified genus. The ORDER BY clause is not  will only return the first ten genomes for the specified genus. The ORDER BY clause is not
1646  required. For example, to just get the first 10 genomes in the B<Genome> table, you could  required. For example, to just get the first 10 genomes in the B<Genome> table, you could
1647  use  use
1648    
1649  C<< "LIMIT 10" >>      "LIMIT 10"
1650    
1651  =item param1, param2, ..., paramN  =item params
1652    
1653  Parameter values to be substituted into the filter clause.  Reference to a list of parameter values to be substituted into the filter clause.
1654    
1655  =item RETURN  =item RETURN
1656    
# Line 998  Line 1662 
1662    
1663  sub Get {  sub Get {
1664      # Get the parameters.      # Get the parameters.
1665      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $objectNames, $filterClause, $params) = @_;
1666      # Adjust the list of object names to account for multiple occurrences of the      # Process the SQL stuff.
1667      # same object. We start with a hash table keyed on object name that will      my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1668      # return the object suffix. The first time an object is encountered it will          $self->_SetupSQL($objectNames, $filterClause);
1669      # not be found in the hash. The next time the hash will map the object name      # Create the query.
1670      # to 2, then 3, and so forth.      my $command = "SELECT " . join(".*, ", @{$mappedNameListRef}) .
1671      my %objectHash = ();          ".* $suffix";
1672      # This list will contain the object names as they are to appear in the      my $sth = $self->_GetStatementHandle($command, $params);
1673      # FROM list.      # Now we create the relation map, which enables DBQuery to determine the order, name
1674      my @fromList = ();      # and mapped name for each object in the query.
1675      # This list contains the suffixed object name for each object. It is exactly      my @relationMap = ();
1676      # parallel to the list in the $objectNames parameter.      for my $mappedName (@{$mappedNameListRef}) {
1677      my @mappedNameList = ();          push @relationMap, [$mappedName, $mappedNameHashRef->{$mappedName}];
1678      # Finally, this hash translates from a mapped name to its original object name.      }
1679      my %mappedNameHash = ();      # Return the statement object.
1680      # Now we create the lists. Note that for every single name we push something into      my $retVal = DBQuery::_new($self, $sth, \@relationMap);
1681      # @fromList and @mappedNameList. This insures that those two arrays are exactly      return $retVal;
1682      # parallel to $objectNames.  }
1683      for my $objectName (@{$objectNames}) {  
1684          # Get the next suffix for this object.  
1685          my $suffix = $objectHash{$objectName};  
1686          if (! $suffix) {  =head3 Search
1687              # Here we are seeing the object for the first time. The object name  
1688              # is used as is.      my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params);
1689              push @mappedNameList, $objectName;  
1690              push @fromList, $objectName;  Perform a full text search with filtering. The search will be against a specified object
1691              $mappedNameHash{$objectName} = $objectName;  in the object name list. That object will get an extra field containing the search
1692              # Denote the next suffix will be 2.  relevance. Note that except for the search expression, the parameters of this method are
1693              $objectHash{$objectName} = 2;  the same as those for L</Get> and follow the same rules.
1694    
1695    =over 4
1696    
1697    =item searchExpression
1698    
1699    Boolean search expression for the text fields of the target object. The default mode for
1700    a Boolean search expression is OR, but we want the default to be AND, so we will
1701    add a C<+> operator to each word with no other operator before it.
1702    
1703    =item idx
1704    
1705    Index in the I<$objectNames> list of the table to be searched in full-text mode.
1706    
1707    =item objectNames
1708    
1709    List containing the names of the entity and relationship objects to be retrieved.
1710    
1711    =item filterClause
1712    
1713    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1714    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
1715    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
1716    in the filter clause should be added to the parameter list as additional parameters. The
1717    fields in a filter clause can come from primary entity relations, relationship relations,
1718    or secondary entity relations; however, all of the entities and relationships involved must
1719    be included in the list of object names.
1720    
1721    =item params
1722    
1723    Reference to a list of parameter values to be substituted into the filter clause.
1724    
1725    =item RETURN
1726    
1727    Returns a query object for the specified search.
1728    
1729    =back
1730    
1731    =cut
1732    
1733    sub Search {
1734        # Get the parameters.
1735        my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1736        # Declare the return variable.
1737        my $retVal;
1738        # Create a safety copy of the parameter list. Note we have to be careful to insure
1739        # a parameter list exists before we copy it.
1740        my @myParams = ();
1741        if (defined $params) {
1742            @myParams = @{$params};
1743        }
1744        # Get the first object's structure so we have access to the searchable fields.
1745        my $object1Name = $objectNames->[$idx];
1746        my $object1Structure = $self->_GetStructure($object1Name);
1747        # Get the field list.
1748        if (! exists $object1Structure->{searchFields}) {
1749            Confess("No searchable index for $object1Name.");
1750          } else {          } else {
1751              # Here we've seen the object before. We construct a new name using          # Get the field list.
1752              # the suffix from the hash and update the hash.          my @fields = @{$object1Structure->{searchFields}};
1753              my $mappedName = "$objectName$suffix";          # Clean the search expression.
1754              $objectHash{$objectName} = $suffix + 1;          my $actualKeywords = $self->CleanKeywords($searchExpression);
1755              # The FROM list has the object name followed by the mapped name. This          # Prefix a "+" to each uncontrolled word. This converts the default
1756              # tells SQL it's still the same table, but we're using a different name          # search mode from OR to AND.
1757              # for it to avoid confusion.          $actualKeywords =~ s/(^|\s)(\w|")/$1\+$2/g;
1758              push @fromList, "$objectName $mappedName";          Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1759              # The mapped-name list contains the real mapped name.          # We need two match expressions, one for the filter clause and one in the
1760              push @mappedNameList, $mappedName;          # query itself. Both will use a parameter mark, so we need to push the
1761              # Finally, enable us to get back from the mapped name to the object name.          # search expression onto the front of the parameter list twice.
1762              $mappedNameHash{$mappedName} = $objectName;          unshift @myParams, $actualKeywords, $actualKeywords;
1763            # Build the match expression.
1764            my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
1765            my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
1766            # Process the SQL stuff.
1767            my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1768                $self->_SetupSQL($objectNames, $filterClause, $matchClause);
1769            # Create the query. Note that the match clause is inserted at the front of
1770            # the select fields.
1771            my $command = "SELECT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .
1772                ".* $suffix";
1773            my $sth = $self->_GetStatementHandle($command, \@myParams);
1774            # Now we create the relation map, which enables DBQuery to determine the order, name
1775            # and mapped name for each object in the query.
1776            my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
1777            # Return the statement object.
1778            $retVal = DBQuery::_new($self, $sth, \@relationMap, $object1Name);
1779          }          }
1780        return $retVal;
1781      }      }
1782      # Construct the SELECT statement. The general pattern is  
1783      #  =head3 GetFlat
1784      # SELECT name1.*, name2.*, ... nameN.* FROM name1, name2, ... nameN  
1785      #      my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field);
1786      my $dbh = $self->{_dbh};  
1787      my $command = "SELECT DISTINCT " . join('.*, ', @mappedNameList) . ".* FROM " .  This is a variation of L</GetAll> that asks for only a single field per record and
1788                  join(', ', @fromList);  returns a single flattened list.
1789      # Check for a filter clause.  
1790      if ($filterClause) {  =over 4
1791          # Here we have one, so we convert its field names and add it to the query. First,  
1792          # We create a copy of the filter string we can work with.  =item objectNames
1793          my $filterString = $filterClause;  
1794          # Next, we sort the object names by length. This helps protect us from finding  List containing the names of the entity and relationship objects to be retrieved.
1795          # object names inside other object names when we're doing our search and replace.  
1796          my @sortedNames = sort { length($b) - length($a) } @mappedNameList;  =item filterClause
1797          # We will also keep a list of conditions to add to the WHERE clause in order to link  
1798          # entities and relationships as well as primary relations to secondary ones.  WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1799          my @joinWhere = ();  be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
1800          # The final preparatory step is to create a hash table of relation names. The  B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
1801          # table begins with the relation names already in the SELECT command. We may  parameter list as additional parameters. The fields in a filter clause can come from primary
1802          # need to add relations later if there is filtering on a field in a secondary  entity relations, relationship relations, or secondary entity relations; however, all of the
1803          # relation. The secondary relations are the ones that contain multiply-  entities and relationships involved must be included in the list of object names.
1804          # occurring or optional fields.  
1805          my %fromNames = map { $_ => 1 } @sortedNames;  =item parameterList
1806          # We are ready to begin. We loop through the object names, replacing each  
1807          # object name's field references by the corresponding SQL field reference.  List of the parameters to be substituted in for the parameters marks in the filter clause.
1808          # Along the way, if we find a secondary relation, we will need to add it  
1809          # to the FROM clause.  =item field
1810          for my $mappedName (@sortedNames) {  
1811              # Get the length of the object name plus 2. This is the value we add to the  Name of the field to be used to get the elements of the list returned.
1812              # size of the field name to determine the size of the field reference as a  
1813              # whole.  =item RETURN
1814              my $nameLength = 2 + length $mappedName;  
1815              # Get the real object name for this mapped name.  Returns a list of values.
1816              my $objectName = $mappedNameHash{$mappedName};  
1817              Trace("Processing $mappedName for object $objectName.") if T(4);  =back
1818              # Get the object's field list.  
1819              my $fieldList = $self->GetFieldTable($objectName);  =cut
1820              # Find the field references for this object.  #: Return Type @;
1821              while ($filterString =~ m/$mappedName\(([^)]*)\)/g) {  sub GetFlat {
1822                  # At this point, $1 contains the field name, and the current position      # Get the parameters.
1823                  # is set immediately after the final parenthesis. We pull out the name of      my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
1824                  # the field and the position and length of the field reference as a whole.      # Construct the query.
1825                  my $fieldName = $1;      my $query = $self->Get($objectNames, $filterClause, $parameterList);
1826                  my $len = $nameLength + length $fieldName;      # Create the result list.
1827                  my $pos = pos($filterString) - $len;      my @retVal = ();
1828                  # Insure the field exists.      # Loop through the records, adding the field values found to the result list.
1829                  if (!exists $fieldList->{$fieldName}) {      while (my $row = $query->Fetch()) {
1830                      Confess("Field $fieldName not found for object $objectName.");          push @retVal, $row->Value($field);
                 } else {  
                     Trace("Processing $fieldName at position $pos.") if T(4);  
                     # Get the field's relation.  
                     my $relationName = $fieldList->{$fieldName}->{relation};  
                     # Now we have a secondary relation. We need to insure it matches the  
                     # mapped name of the primary relation. First we peel off the suffix  
                     # from the mapped name.  
                     my $mappingSuffix = substr $mappedName, length($objectName);  
                     # Put the mapping suffix onto the relation name to get the  
                     # mapped relation name.  
                     my $mappedRelationName = "$relationName$mappingSuffix";  
                     # Insure the relation is in the FROM clause.  
                     if (!exists $fromNames{$mappedRelationName}) {  
                         # Add the relation to the FROM clause.  
                         if ($mappedRelationName eq $relationName) {  
                             # The name is un-mapped, so we add it without  
                             # any frills.  
                             $command .= ", $relationName";  
                             push @joinWhere, "$objectName.id = $relationName.id";  
                         } else {  
                             # Here we have a mapping situation.  
                             $command .= ", $relationName $mappedRelationName";  
                             push @joinWhere, "$mappedRelationName.id = $mappedName.id";  
                         }  
                         # Denote we have this relation available for future fields.  
                         $fromNames{$mappedRelationName} = 1;  
                     }  
                     # Form an SQL field reference from the relation name and the field name.  
                     my $sqlReference = "$mappedRelationName." . _FixName($fieldName);  
                     # Put it into the filter string in place of the old value.  
                     substr($filterString, $pos, $len) = $sqlReference;  
                     # Reposition the search.  
                     pos $filterString = $pos + length $sqlReference;  
                 }  
             }  
         }  
         # The next step is to join the objects together. We only need to do this if there  
         # is more than one object in the object list. We start with the first object and  
         # run through the objects after it. Note also that we make a safety copy of the  
         # list before running through it.  
         my @mappedObjectList = @mappedNameList;  
         my $lastMappedObject = shift @mappedObjectList;  
         # Get the join table.  
         my $joinTable = $self->{_metaData}->{Joins};  
         # Loop through the object list.  
         for my $thisMappedObject (@mappedObjectList) {  
             # Look for a join using the real object names.  
             my $lastObject = $mappedNameHash{$lastMappedObject};  
             my $thisObject = $mappedNameHash{$thisMappedObject};  
             my $joinKey = "$lastObject/$thisObject";  
             if (!exists $joinTable->{$joinKey}) {  
                 # Here there's no join, so we throw an error.  
                 Confess("No join exists to connect from $lastMappedObject to $thisMappedObject.");  
             } else {  
                 # Get the join clause.  
                 my $unMappedJoin = $joinTable->{$joinKey};  
                 # Fix the names.  
                 $unMappedJoin =~ s/$lastObject/$lastMappedObject/;  
                 $unMappedJoin =~ s/$thisObject/$thisMappedObject/;  
                 push @joinWhere, $unMappedJoin;  
                 # Save this object as the last object for the next iteration.  
                 $lastMappedObject = $thisMappedObject;  
             }  
         }  
         # Now we need to handle the whole ORDER BY / LIMIT thing. The important part  
         # here is we want the filter clause to be empty if there's no WHERE filter.  
         # We'll put the ORDER BY / LIMIT clauses in the following variable.  
         my $orderClause = "";  
         # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy  
         # operator so that we find the first occurrence of either verb.  
         if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {  
             # Here we have an ORDER BY or LIMIT verb. Split it off of the filter string.  
             my $pos = pos $filterString;  
             $orderClause = $2 . substr($filterString, $pos);  
             $filterString = $1;  
         }  
         # Add the filter and the join clauses (if any) to the SELECT command.  
         if ($filterString) {  
             Trace("Filter string is \"$filterString\".") if T(4);  
             push @joinWhere, "($filterString)";  
         }  
         if (@joinWhere) {  
             $command .= " WHERE " . join(' AND ', @joinWhere);  
1831          }          }
1832          # Add the sort or limit clause (if any) to the SELECT command.      # Return the list created.
1833          if ($orderClause) {      return @retVal;
             $command .= " $orderClause";  
1834          }          }
1835    
1836    =head3 SpecialFields
1837    
1838        my %specials = $erdb->SpecialFields($entityName);
1839    
1840    Return a hash mapping special fields in the specified entity to the value of their
1841    C<special> attribute. This enables the subclass to get access to the special field
1842    attributes without needed to plumb the internal ERDB data structures.
1843    
1844    =over 4
1845    
1846    =item entityName
1847    
1848    Name of the entity whose special fields are desired.
1849    
1850    =item RETURN
1851    
1852    Returns a hash. The keys of the hash are the special field names, and the values
1853    are the values from each special field's C<special> attribute.
1854    
1855    =back
1856    
1857    =cut
1858    
1859    sub SpecialFields {
1860        # Get the parameters.
1861        my ($self, $entityName) = @_;
1862        # Declare the return variable.
1863        my %retVal = ();
1864        # Find the entity's data structure.
1865        my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1866        # Loop through its fields, adding each special field to the return hash.
1867        my $fieldHash = $entityData->{Fields};
1868        for my $fieldName (keys %{$fieldHash}) {
1869            my $fieldData = $fieldHash->{$fieldName};
1870            if (exists $fieldData->{special}) {
1871                $retVal{$fieldName} = $fieldData->{special};
1872      }      }
     Trace("SQL query: $command") if T(SQL => 3);  
     Trace("PARMS: '" . (join "', '", @params) . "'") if (T(SQL => 4) && (@params > 0));  
     my $sth = $dbh->prepare_command($command);  
     # Execute it with the parameters bound in.  
     $sth->execute(@params) || Confess("SELECT error" . $sth->errstr());  
     # Now we create the relation map, which enables DBQuery to determine the order, name  
     # and mapped name for each object in the query.  
     my @relationMap = ();  
     for my $mappedName (@mappedNameList) {  
         push @relationMap, [$mappedName, $mappedNameHash{$mappedName}];  
1873      }      }
1874      # Return the statement object.      # Return the result.
1875      my $retVal = DBQuery::_new($self, $sth, \@relationMap);      return %retVal;
     return $retVal;  
1876  }  }
1877    
1878  =head3 Delete  =head3 Delete
1879    
1880  C<< my $stats = $erdb->Delete($entityName, $objectID); >>      my $stats = $erdb->Delete($entityName, $objectID, %options);
1881    
1882  Delete an entity instance from the database. The instance is deleted along with all entity and  Delete an entity instance from the database. The instance is deleted along with all entity and
1883  relationship instances dependent on it. The idea of dependence here is recursive. An object is  relationship instances dependent on it. The definition of I<dependence> is recursive.
1884  always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many  
1885  relationship connected to a dependent entity or the "to" entity connected to a 1-to-many  An object is always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many
1886    relationship connected to a dependent entity or if it is the "to" entity connected to a 1-to-many
1887  dependent relationship.  dependent relationship.
1888    
1889  =over 4  =over 4
# Line 1217  Line 1897 
1897  ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),  ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),
1898  then it is presumed to by a LIKE pattern.  then it is presumed to by a LIKE pattern.
1899    
1900  =item testFlag  =item options
1901    
1902  If TRUE, the delete statements will be traced without being executed.  A hash detailing the options for this delete operation.
1903    
1904  =item RETURN  =item RETURN
1905    
# Line 1228  Line 1908 
1908    
1909  =back  =back
1910    
1911    The permissible options for this method are as follows.
1912    
1913    =over 4
1914    
1915    =item testMode
1916    
1917    If TRUE, then the delete statements will be traced, but no changes will be made to the database.
1918    
1919    =item keepRoot
1920    
1921    If TRUE, then the entity instances will not be deleted, only the dependent records.
1922    
1923    =back
1924    
1925  =cut  =cut
1926  #: Return Type $%;  #: Return Type $%;
1927  sub Delete {  sub Delete {
1928      # Get the parameters.      # Get the parameters.
1929      my ($self, $entityName, $objectID, $testFlag) = @_;      my ($self, $entityName, $objectID, %options) = @_;
1930      # Declare the return variable.      # Declare the return variable.
1931      my $retVal = Stats->new();      my $retVal = Stats->new();
1932      # Get the DBKernel object.      # Get the DBKernel object.
# Line 1249  Line 1943 
1943      # FROM-relationships and entities.      # FROM-relationships and entities.
1944      my @fromPathList = ();      my @fromPathList = ();
1945      my @toPathList = ();      my @toPathList = ();
1946      # This final hash is used to remember what work still needs to be done. We push paths      # This final list is used to remember what work still needs to be done. We push paths
1947      # onto the list, then pop them off to extend the paths. We prime it with the starting      # onto the list, then pop them off to extend the paths. We prime it with the starting
1948      # point. Note that we will work hard to insure that the last item on a path in the      # point. Note that we will work hard to insure that the last item on a path in the
1949      # TODO list is always an entity.      # to-do list is always an entity.
1950      my @todoList = ([$entityName]);      my @todoList = ([$entityName]);
1951      while (@todoList) {      while (@todoList) {
1952          # Get the current path.          # Get the current path.
# Line 1260  Line 1954 
1954          # Copy it into a list.          # Copy it into a list.
1955          my @stackedPath = @{$current};          my @stackedPath = @{$current};
1956          # Pull off the last item on the path. It will always be an entity.          # Pull off the last item on the path. It will always be an entity.
1957          my $entityName = pop @stackedPath;          my $myEntityName = pop @stackedPath;
1958          # Add it to the alreadyFound list.          # Add it to the alreadyFound list.
1959          $alreadyFound{$entityName} = 1;          $alreadyFound{$myEntityName} = 1;
1960            # Figure out if we need to delete this entity.
1961            if ($myEntityName ne $entityName || ! $options{keepRoot}) {
1962          # Get the entity data.          # Get the entity data.
1963          my $entityData = $self->_GetStructure($entityName);              my $entityData = $self->_GetStructure($myEntityName);
1964          # The first task is to loop through the entity's relation. A DELETE command will              # Loop through the entity's relations. A DELETE command will be needed for each of them.
         # be needed for each of them.  
1965          my $relations = $entityData->{Relations};          my $relations = $entityData->{Relations};
1966          for my $relation (keys %{$relations}) {          for my $relation (keys %{$relations}) {
1967              my @augmentedList = (@stackedPath, $relation);              my @augmentedList = (@stackedPath, $relation);
1968              push @fromPathList, \@augmentedList;              push @fromPathList, \@augmentedList;
1969          }          }
1970            }
1971          # Now we need to look for relationships connected to this entity.          # Now we need to look for relationships connected to this entity.
1972          my $relationshipList = $self->{_metaData}->{Relationships};          my $relationshipList = $self->{_metaData}->{Relationships};
1973          for my $relationshipName (keys %{$relationshipList}) {          for my $relationshipName (keys %{$relationshipList}) {
1974              my $relationship = $relationshipList->{$relationshipName};              my $relationship = $relationshipList->{$relationshipName};
1975              # Check the FROM field. We're only interested if it's us.              # Check the FROM field. We're only interested if it's us.
1976              if ($relationship->{from} eq $entityName) {              if ($relationship->{from} eq $myEntityName) {
1977                  # Add the path to this relationship.                  # Add the path to this relationship.
1978                  my @augmentedList = (@stackedPath, $entityName, $relationshipName);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1979                  push @fromPathList, \@augmentedList;                  push @fromPathList, \@augmentedList;
1980                  # Check the arity. If it's MM we're done. If it's 1M                  # Check the arity. If it's MM we're done. If it's 1M
1981                  # and the target hasn't been seen yet, we want to                  # and the target hasn't been seen yet, we want to
# Line 1298  Line 1994 
1994              }              }
1995              # Now check the TO field. In this case only the relationship needs              # Now check the TO field. In this case only the relationship needs
1996              # deletion.              # deletion.
1997              if ($relationship->{to} eq $entityName) {              if ($relationship->{to} eq $myEntityName) {
1998                  my @augmentedList = (@stackedPath, $entityName, $relationshipName);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1999                  push @toPathList, \@augmentedList;                  push @toPathList, \@augmentedList;
2000              }              }
2001          }          }
2002      }      }
2003      # Create the first qualifier for the WHERE clause. This selects the      # Create the first qualifier for the WHERE clause. This selects the
2004      # keys of the primary entity records to be deleted. When we're deleting      # keys of the primary entity records to be deleted. When we're deleting
2005      # from a dependent table, we construct a join page from the first qualifier      # from a dependent table, we construct a join path from the first qualifier
2006      # to the table containing the dependent records to delete.      # to the table containing the dependent records to delete.
2007      my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");      my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
2008      # We need to make two passes. The first is through the to-list, and      # We need to make two passes. The first is through the to-list, and
# Line 1345  Line 2041 
2041                  }                  }
2042              }              }
2043              # Now we have our desired DELETE statement.              # Now we have our desired DELETE statement.
2044              if ($testFlag) {              if ($options{testMode}) {
2045                  # Here the user wants to trace without executing.                  # Here the user wants to trace without executing.
2046                  Trace($stmt) if T(0);                  Trace($stmt) if T(0);
2047              } else {              } else {
2048                  # Here we can delete. Note that the SQL method dies with a confessing                  # Here we can delete. Note that the SQL method dies with a confession
2049                  # if an error occurs, so we just go ahead and do it.                  # if an error occurs, so we just go ahead and do it.
2050                  Trace("Executing delete from $target using '$objectID'.") if T(3);                  Trace("Executing delete from $target using '$objectID'.") if T(3);
2051                  my $rv = $db->SQL($stmt, 0, $objectID);                  my $rv = $db->SQL($stmt, 0, $objectID);
# Line 1364  Line 2060 
2060      return $retVal;      return $retVal;
2061  }  }
2062    
2063  =head3 GetList  =head3 Disconnect
   
 C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  
2064    
2065  Return a list of object descriptors for the specified objects as determined by the      $erdb->Disconnect($relationshipName, $originEntityName, $originEntityID);
 specified filter clause.  
2066    
2067  This method is essentially the same as L</Get> except it returns a list of objects rather  Disconnect an entity instance from all the objects to which it is related. This
2068  than a query object that can be used to get the results one record at a time.  will delete each relationship instance that connects to the specified entity.
2069    
2070  =over 4  =over 4
2071    
2072  =item objectNames  =item relationshipName
   
 List containing the names of the entity and relationship objects to be retrieved.  
   
 =item filterClause  
   
 WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  
 be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be  
 specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified  
 in the filter clause should be added to the parameter list as additional parameters. The  
 fields in a filter clause can come from primary entity relations, relationship relations,  
 or secondary entity relations; however, all of the entities and relationships involved must  
 be included in the list of object names.  
   
 The filter clause can also specify a sort order. To do this, simply follow the filter string  
 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)" >>  
2073    
2074  The rules for field references in a sort order are the same as those for field references in the  Name of the relationship whose instances are to be deleted.
 filter clause in general; however, odd things may happen if a sort field is from a secondary  
 relation.  
2075    
2076  =item param1, param2, ..., paramN  =item originEntityName
2077    
2078  Parameter values to be substituted into the filter clause.  Name of the entity that is to be disconnected.
2079    
2080  =item RETURN  =item originEntityID
2081    
2082  Returns a list of B<DBObject>s that satisfy the query conditions.  ID of the entity that is to be disconnected.
2083    
2084  =back  =back
2085    
2086  =cut  =cut
2087  #: Return Type @%  
2088  sub GetList {  sub Disconnect {
2089      # Get the parameters.      # Get the parameters.
2090      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $relationshipName, $originEntityName, $originEntityID) = @_;
2091      # Declare the return variable.      # Get the relationship descriptor.
2092      my @retVal = ();      my $structure = $self->_GetStructure($relationshipName);
2093      # Perform the query.      # Insure we have a relationship.
2094      my $query = $self->Get($objectNames, $filterClause, @params);      if (! exists $structure->{from}) {
2095      # Loop through the results.          Confess("$relationshipName is not a relationship in the database.");
2096      while (my $object = $query->Fetch) {      } else {
2097          push @retVal, $object;          # Get the database handle.
2098            my $dbh = $self->{_dbh};
2099            # We'll set this value to 1 if we find our entity.
2100            my $found = 0;
2101            # Loop through the ends of the relationship.
2102            for my $dir ('from', 'to') {
2103                if ($structure->{$dir} eq $originEntityName) {
2104                    $found = 1;
2105                    # Here we want to delete all relationship instances on this side of the
2106                    # entity instance.
2107                    Trace("Disconnecting in $dir direction with ID \"$originEntityID\".");
2108                    # We do this delete in batches to keep it from dragging down the
2109                    # server.
2110                    my $limitClause = ($FIG_Config::delete_limit ? "LIMIT $FIG_Config::delete_limit" : "");
2111                    my $done = 0;
2112                    while (! $done) {
2113                        # Do the delete.
2114                        my $rows = $dbh->SQL("DELETE FROM $relationshipName WHERE ${dir}_link = ? $limitClause", 0, $originEntityID);
2115                        # See if we're done. We're done if no rows were found or the delete is unlimited.
2116                        $done = ($rows == 0 || ! $limitClause);
2117                    }
2118                }
2119            }
2120            # Insure we found the entity on at least one end.
2121            if (! $found) {
2122                Confess("Entity \"$originEntityName\" does not use $relationshipName.");
2123            }
2124      }      }
     # Return the result.  
     return @retVal;  
2125  }  }
2126    
2127  =head3 ComputeObjectSentence  =head3 DeleteRow
2128    
2129  C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>      $erdb->DeleteRow($relationshipName, $fromLink, $toLink, \%values);
2130    
2131  Check an object name, and if it is a relationship convert it to a relationship sentence.  Delete a row from a relationship. In most cases, only the from-link and to-link are
2132    needed; however, for relationships with intersection data values can be specified
2133    for the other fields using a hash.
2134    
2135  =over 4  =over 4
2136    
2137  =item objectName  =item relationshipName
2138    
2139  Name of the entity or relationship.  Name of the relationship from which the row is to be deleted.
2140    
2141  =item RETURN  =item fromLink
2142    
2143  Returns a string containing the entity name or a relationship sentence.  ID of the entity instance in the From direction.
2144    
2145    =item toLink
2146    
2147    ID of the entity instance in the To direction.
2148    
2149    =item values
2150    
2151    Reference to a hash of other values to be used for filtering the delete.
2152    
2153  =back  =back
2154    
2155  =cut  =cut
2156    
2157  sub ComputeObjectSentence {  sub DeleteRow {
2158      # Get the parameters.      # Get the parameters.
2159      my ($self, $objectName) = @_;      my ($self, $relationshipName, $fromLink, $toLink, $values) = @_;
2160      # Set the default return value.      # Create a hash of all the filter information.
2161      my $retVal = $objectName;      my %filter = ('from-link' => $fromLink, 'to-link' => $toLink);
2162      # Look for the object as a relationship.      if (defined $values) {
2163      my $relTable = $self->{_metaData}->{Relationships};          for my $key (keys %{$values}) {
2164      if (exists $relTable->{$objectName}) {              $filter{$key} = $values->{$key};
         # Get the relationship sentence.  
         $retVal = _ComputeRelationshipSentence($objectName, $relTable->{$objectName});  
2165      }      }
2166      # Return the result.      }
2167      return $retVal;      # Build an SQL statement out of the hash.
2168        my @filters = ();
2169        my @parms = ();
2170        for my $key (keys %filter) {
2171            push @filters, _FixName($key) . " = ?";
2172            push @parms, $filter{$key};
2173        }
2174        Trace("Parms for delete row are " . join(", ", map { "\"$_\"" } @parms) . ".") if T(SQL => 4);
2175        my $command = "DELETE FROM $relationshipName WHERE " .
2176                      join(" AND ", @filters);
2177        # Execute it.
2178        my $dbh = $self->{_dbh};
2179        $dbh->SQL($command, undef, @parms);
2180  }  }
2181    
2182  =head3 DumpRelations  =head3 DeleteLike
2183    
2184  C<< $erdb->DumpRelations($outputDirectory); >>      my $deleteCount = $erdb->DeleteLike($relName, $filter, \@parms);
2185    
2186  Write the contents of all the relations to tab-delimited files in the specified directory.  Delete all the relationship rows that satisfy a particular filter condition. Unlike a normal
2187  Each file will have the same name as the relation dumped, with an extension of DTX.  filter, only fields from the relationship itself can be used.
2188    
2189  =over 4  =over 4
2190    
2191  =item outputDirectory  =item relName
2192    
2193  Name of the directory into which the relation files should be dumped.  Name of the relationship whose records are to be deleted.
2194    
2195  =back  =item filter
2196    
2197  =cut  A filter clause (L</Get>-style) for the delete query.
2198    
2199  sub DumpRelations {  =item parms
2200      # Get the parameters.  
2201      my ($self, $outputDirectory) = @_;  Reference to a list of parameters for the filter clause.
2202    
2203    =item RETURN
2204    
2205    Returns a count of the number of rows deleted.
2206    
2207    =back
2208    
2209    =cut
2210    
2211    sub DeleteLike {
2212        # Get the parameters.
2213        my ($self, $objectName, $filter, $parms) = @_;
2214        # Declare the return variable.
2215        my $retVal;
2216        # Insure the parms argument is an array reference if the caller left it off.
2217        if (! defined($parms)) {
2218            $parms = [];
2219        }
2220        # Insure we have a relationship. The main reason for this is if we delete an entity
2221        # instance we have to yank out a bunch of other stuff with it.
2222        if ($self->IsEntity($objectName)) {
2223            Confess("Cannot use DeleteLike on $objectName, because it is not a relationship.");
2224        } else {
2225            # Create the SQL command suffix to get the desierd records.
2226            my ($suffix) = $self->_SetupSQL([$objectName], $filter);
2227            # Convert it to a DELETE command.
2228            my $command = "DELETE $suffix";
2229            # Execute the command.
2230            my $dbh = $self->{_dbh};
2231            my $result = $dbh->SQL($command, 0, @{$parms});
2232            # Check the results. Note we convert the "0D0" result to a real zero.
2233            # A failure causes an abnormal termination, so the caller isn't going to
2234            # worry about it.
2235            if (! defined $result) {
2236                Confess("Error deleting from $objectName: " . $dbh->errstr());
2237            } elsif ($result == 0) {
2238                $retVal = 0;
2239            } else {
2240                $retVal = $result;
2241            }
2242        }
2243        # Return the result count.
2244        return $retVal;
2245    }
2246    
2247    =head3 SortNeeded
2248    
2249        my $parms = $erdb->SortNeeded($relationName);
2250    
2251    Return the pipe command for the sort that should be applied to the specified
2252    relation when creating the load file.
2253    
2254    For example, if the load file should be sorted ascending by the first
2255    field, this method would return
2256    
2257        sort -k1 -t"\t"
2258    
2259    If the first field is numeric, the method would return
2260    
2261        sort -k1n -t"\t"
2262    
2263    Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate
2264    keys using a sort.
2265    
2266    =over 4
2267    
2268    =item relationName
2269    
2270    Name of the relation to be examined.
2271    
2272    =item
2273    
2274    Returns the sort command to use for sorting the relation, suitable for piping.
2275    
2276    =back
2277    
2278    =cut
2279    #: Return Type $;
2280    sub SortNeeded {
2281        # Get the parameters.
2282        my ($self, $relationName) = @_;
2283        # Declare a descriptor to hold the names of the key fields.
2284        my @keyNames = ();
2285        # Get the relation structure.
2286        my $relationData = $self->_FindRelation($relationName);
2287        # Find out if the relation is a primary entity relation,
2288        # a relationship relation, or a secondary entity relation.
2289        my $entityTable = $self->{_metaData}->{Entities};
2290        my $relationshipTable = $self->{_metaData}->{Relationships};
2291        if (exists $entityTable->{$relationName}) {
2292            # Here we have a primary entity relation.
2293            push @keyNames, "id";
2294        } elsif (exists $relationshipTable->{$relationName}) {
2295            # Here we have a relationship. We sort using the FROM index.
2296            my $relationshipData = $relationshipTable->{$relationName};
2297            my $index = $relationData->{Indexes}->{idxFrom};
2298            push @keyNames, @{$index->{IndexFields}};
2299        } else {
2300            # Here we have a secondary entity relation, so we have a sort on the ID field.
2301            push @keyNames, "id";
2302        }
2303        # Now we parse the key names into sort parameters. First, we prime the return
2304        # string.
2305        my $retVal = "sort -t\"\t\" ";
2306        # Get the relation's field list.
2307        my @fields = @{$relationData->{Fields}};
2308        # Loop through the keys.
2309        for my $keyData (@keyNames) {
2310            # Get the key and the ordering.
2311            my ($keyName, $ordering);
2312            if ($keyData =~ /^([^ ]+) DESC/) {
2313                ($keyName, $ordering) = ($1, "descending");
2314            } else {
2315                ($keyName, $ordering) = ($keyData, "ascending");
2316            }
2317            # Find the key's position and type.
2318            my $fieldSpec;
2319            for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {
2320                my $thisField = $fields[$i];
2321                if ($thisField->{name} eq $keyName) {
2322                    # Get the sort modifier for this field type. The modifier
2323                    # decides whether we're using a character, numeric, or
2324                    # floating-point sort.
2325                    my $modifier = $TypeTable{$thisField->{type}}->{sort};
2326                    # If the index is descending for this field, denote we want
2327                    # to reverse the sort order on this field.
2328                    if ($ordering eq 'descending') {
2329                        $modifier .= "r";
2330                    }
2331                    # Store the position and modifier into the field spec, which
2332                    # will stop the inner loop. Note that the field number is
2333                    # 1-based in the sort command, so we have to increment the
2334                    # index.
2335                    $fieldSpec = ($i + 1) . $modifier;
2336                }
2337            }
2338            # Add this field to the sort command.
2339            $retVal .= " -k$fieldSpec";
2340        }
2341        # Return the result.
2342        return $retVal;
2343    }
2344    
2345    =head3 GetList
2346    
2347        my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params);
2348    
2349    Return a list of object descriptors for the specified objects as determined by the
2350    specified filter clause.
2351    
2352    This method is essentially the same as L</Get> except it returns a list of objects rather
2353    than a query object that can be used to get the results one record at a time.
2354    
2355    =over 4
2356    
2357    =item objectNames
2358    
2359    List containing the names of the entity and relationship objects to be retrieved.
2360    
2361    =item filterClause
2362    
2363    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
2364    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
2365    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
2366    in the filter clause should be added to the parameter list as additional parameters. The
2367    fields in a filter clause can come from primary entity relations, relationship relations,
2368    or secondary entity relations; however, all of the entities and relationships involved must
2369    be included in the list of object names.
2370    
2371    The filter clause can also specify a sort order. To do this, simply follow the filter string
2372    with an ORDER BY clause. For example, the following filter string gets all genomes for a
2373    particular genus and sorts them by species name.
2374    
2375        "Genome(genus) = ? ORDER BY Genome(species)"
2376    
2377    The rules for field references in a sort order are the same as those for field references in the
2378    filter clause in general; however, odd things may happen if a sort field is from a secondary
2379    relation.
2380    
2381    =item params
2382    
2383    Reference to a list of parameter values to be substituted into the filter clause.
2384    
2385    =item RETURN
2386    
2387    Returns a list of B<ERDBObject>s that satisfy the query conditions.
2388    
2389    =back
2390    
2391    =cut
2392    #: Return Type @%
2393    sub GetList {
2394        # Get the parameters.
2395        my ($self, $objectNames, $filterClause, $params) = @_;
2396        # Declare the return variable.
2397        my @retVal = ();
2398        # Perform the query.
2399        my $query = $self->Get($objectNames, $filterClause, $params);
2400        # Loop through the results.
2401        while (my $object = $query->Fetch) {
2402            push @retVal, $object;
2403        }
2404        # Return the result.
2405        return @retVal;
2406    }
2407    
2408    =head3 GetCount
2409    
2410        my $count = $erdb->GetCount(\@objectNames, $filter, \@params);
2411    
2412    Return the number of rows found by a specified query. This method would
2413    normally be used to count the records in a single table. For example, in a
2414    genetics database
2415    
2416        my $count = $erdb->GetCount(['Genome'], 'Genome(genus-species) LIKE ?', ['homo %']);
2417    
2418    would return the number of genomes for the genus I<homo>. It is conceivable, however,
2419    to use it to return records based on a join. For example,
2420    
2421        my $count = $erdb->GetCount(['HasFeature', 'Genome'], 'Genome(genus-species) LIKE ?',
2422                                    ['homo %']);
2423    
2424    would return the number of features for genomes in the genus I<homo>. Note that
2425    only the rows from the first table are counted. If the above command were
2426    
2427        my $count = $erdb->GetCount(['Genome', 'Feature'], 'Genome(genus-species) LIKE ?',
2428                                    ['homo %']);
2429    
2430    it would return the number of genomes, not the number of genome/feature pairs.
2431    
2432    =over 4
2433    
2434    =item objectNames
2435    
2436    Reference to a list of the objects (entities and relationships) included in the
2437    query.
2438    
2439    =item filter
2440    
2441    A filter clause for restricting the query. The rules are the same as for the L</Get>
2442    method.
2443    
2444    =item params
2445    
2446    Reference to a list of the parameter values to be substituted for the parameter marks
2447    in the filter.
2448    
2449    =item RETURN
2450    
2451    Returns a count of the number of records in the first table that would satisfy
2452    the query.
2453    
2454    =back
2455    
2456    =cut
2457    
2458    sub GetCount {
2459        # Get the parameters.
2460        my ($self, $objectNames, $filter, $params) = @_;
2461        # Insure the params argument is an array reference if the caller left it off.
2462        if (! defined($params)) {
2463            $params = [];
2464        }
2465        # Declare the return variable.
2466        my $retVal;
2467        # Find out if we're counting an entity or a relationship.
2468        my $countedField;
2469        if ($self->IsEntity($objectNames->[0])) {
2470            $countedField = "id";
2471        } else {
2472            # For a relationship we count the to-link because it's usually more
2473            # numerous. Note we're automatically converting to the SQL form
2474            # of the field name (to_link vs. to-link).
2475            $countedField = "to_link";
2476        }
2477        # Create the SQL command suffix to get the desired records.
2478        my ($suffix, $mappedNameListRef, $mappedNameHashRef) = $self->_SetupSQL($objectNames,
2479                                                                                $filter);
2480        # Prefix it with text telling it we want a record count.
2481        my $firstObject = $mappedNameListRef->[0];
2482        my $command = "SELECT COUNT($firstObject.$countedField) $suffix";
2483        # Prepare and execute the command.
2484        my $sth = $self->_GetStatementHandle($command, $params);
2485        # Get the count value.
2486        ($retVal) = $sth->fetchrow_array();
2487        # Check for a problem.
2488        if (! defined($retVal)) {
2489            if ($sth->err) {
2490                # Here we had an SQL error.
2491                Confess("Error retrieving row count: " . $sth->errstr());
2492            } else {
2493                # Here we have no result.
2494                Confess("No result attempting to retrieve row count.");
2495            }
2496        }
2497        # Return the result.
2498        return $retVal;
2499    }
2500    
2501    =head3 ComputeObjectSentence
2502    
2503        my $sentence = $erdb->ComputeObjectSentence($objectName);
2504    
2505    Check an object name, and if it is a relationship convert it to a relationship sentence.
2506    
2507    =over 4
2508    
2509    =item objectName
2510    
2511    Name of the entity or relationship.
2512    
2513    =item RETURN
2514    
2515    Returns a string containing the entity name or a relationship sentence.
2516    
2517    =back
2518    
2519    =cut
2520    
2521    sub ComputeObjectSentence {
2522        # Get the parameters.
2523        my ($self, $objectName) = @_;
2524        # Set the default return value.
2525        my $retVal = $objectName;
2526        # Look for the object as a relationship.
2527        my $relTable = $self->{_metaData}->{Relationships};
2528        if (exists $relTable->{$objectName}) {
2529            # Get the relationship sentence.
2530            $retVal = _ComputeRelationshipSentence($objectName, $relTable->{$objectName});
2531        }
2532        # Return the result.
2533        return $retVal;
2534    }
2535    
2536    =head3 DumpRelations
2537    
2538        $erdb->DumpRelations($outputDirectory);
2539    
2540    Write the contents of all the relations to tab-delimited files in the specified directory.
2541    Each file will have the same name as the relation dumped, with an extension of DTX.
2542    
2543    =over 4
2544    
2545    =item outputDirectory
2546    
2547    Name of the directory into which the relation files should be dumped.
2548    
2549    =back
2550    
2551    =cut
2552    
2553    sub DumpRelations {
2554        # Get the parameters.
2555        my ($self, $outputDirectory) = @_;
2556      # Now we need to run through all the relations. First, we loop through the entities.      # Now we need to run through all the relations. First, we loop through the entities.
2557      my $metaData = $self->{_metaData};      my $metaData = $self->{_metaData};
2558      my $entities = $metaData->{Entities};      my $entities = $metaData->{Entities};
# Line 1504  Line 2575 
2575      }      }
2576  }  }
2577    
2578    =head3 InsertValue
2579    
2580        $erdb->InsertValue($entityID, $fieldName, $value);
2581    
2582    This method will insert a new value into the database. The value must be one
2583    associated with a secondary relation, since primary values cannot be inserted:
2584    they occur exactly once. Secondary values, on the other hand, can be missing
2585    or multiply-occurring.
2586    
2587    =over 4
2588    
2589    =item entityID
2590    
2591    ID of the object that is to receive the new value.
2592    
2593    =item fieldName
2594    
2595    Field name for the new value-- this includes the entity name, since
2596    field names are of the format I<objectName>C<(>I<fieldName>C<)>.
2597    
2598    =item value
2599    
2600    New value to be put in the field.
2601    
2602    =back
2603    
2604    =cut
2605    
2606    sub InsertValue {
2607        # Get the parameters.
2608        my ($self, $entityID, $fieldName, $value) = @_;
2609        # Parse the entity name and the real field name.
2610        if ($fieldName =~ /^([^(]+)\(([^)]+)\)/) {
2611            my $entityName = $1;
2612            my $fieldTitle = $2;
2613            # Get its descriptor.
2614            if (!$self->IsEntity($entityName)) {
2615                Confess("$entityName is not a valid entity.");
2616            } else {
2617                my $entityData = $self->{_metaData}->{Entities}->{$entityName};
2618                # Find the relation containing this field.
2619                my $fieldHash = $entityData->{Fields};
2620                if (! exists $fieldHash->{$fieldTitle}) {
2621                    Confess("$fieldTitle not found in $entityName.");
2622                } else {
2623                    my $relation = $fieldHash->{$fieldTitle}->{relation};
2624                    if ($relation eq $entityName) {
2625                        Confess("Cannot do InsertValue on primary field $fieldTitle of $entityName.");
2626                    } else {
2627                        # Now we can create an INSERT statement.
2628                        my $dbh = $self->{_dbh};
2629                        my $fixedName = _FixName($fieldTitle);
2630                        my $statement = "INSERT INTO $relation (id, $fixedName) VALUES(?, ?)";
2631                        # Execute the command.
2632                        $dbh->SQL($statement, 0, $entityID, $value);
2633                    }
2634                }
2635            }
2636        } else {
2637            Confess("$fieldName is not a valid field name.");
2638        }
2639    }
2640    
2641  =head3 InsertObject  =head3 InsertObject
2642    
2643  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>      $erdb->InsertObject($objectType, \%fieldHash);
2644    
2645  Insert an object into the database. The object is defined by a type name and then a hash  Insert an object into the database. The object is defined by a type name and then a hash
2646  of field names to values. Field values in the primary relation are represented by scalars.  of field names to values. Field values in the primary relation are represented by scalars.
# Line 1515  Line 2649 
2649  example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases  example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases
2650  C<ZP_00210270.1> and C<gi|46206278>.  C<ZP_00210270.1> and C<gi|46206278>.
2651    
2652  C<< $erdb->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>      $erdb->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']});
2653    
2654  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
2655  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
2656    
2657  C<< $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>      $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'});
2658    
2659  =over 4  =over 4
2660    
# Line 1532  Line 2666 
2666    
2667  Hash of field names to values.  Hash of field names to values.
2668    
 =item RETURN  
   
 Returns 1 if successful, 0 if an error occurred.  
   
2669  =back  =back
2670    
2671  =cut  =cut
# Line 1634  Line 2764 
2764                  $retVal = $sth->execute(@parameterList);                  $retVal = $sth->execute(@parameterList);
2765                  if (!$retVal) {                  if (!$retVal) {
2766                      my $errorString = $sth->errstr();                      my $errorString = $sth->errstr();
2767                      Trace("Insert error: $errorString.") if T(0);                      Confess("Error inserting into $relationName: $errorString");
2768                    } else {
2769                        Trace("Insert successful using $parameterList[0].") if T(3);
2770                  }                  }
2771              }              }
2772          }          }
2773      }      }
2774      # Return the success indicator.      # Return a 1 for backward compatability.
2775      return $retVal;      return 1;
2776  }  }
2777    
2778  =head3 LoadTable  =head3 UpdateEntity
2779    
2780  C<< my %results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>      $erdb->UpdateEntity($entityName, $id, \%fields);
2781    
2782  Load data from a tab-delimited file into a specified table, optionally re-creating the table  Update the values of an entity. This is an unprotected update, so it should only be
2783  first.  done if the database resides on a database server.
2784    
2785  =over 4  =over 4
2786    
2787  =item fileName  =item entityName
   
 Name of the file from which the table data should be loaded.  
   
 =item relationName  
2788    
2789  Name of the relation to be loaded. This is the same as the table name.  Name of the entity to update. (This is the entity type.)
2790    
2791  =item truncateFlag  =item id
2792    
2793  TRUE if the table should be dropped and re-created, else FALSE  ID of the entity to update. If no entity exists with this ID, an error will be thrown.
2794    
2795  =item RETURN  =item fields
2796    
2797  Returns a statistical object containing a list of the error messages.  Reference to a hash mapping field names to their new values. All of the fields named
2798    must be in the entity's primary relation, and they cannot any of them be the ID field.
2799    
2800  =back  =back
2801    
2802  =cut  =cut
2803  sub LoadTable {  
2804    sub UpdateEntity {
2805      # Get the parameters.      # Get the parameters.
2806      my ($self, $fileName, $relationName, $truncateFlag) = @_;      my ($self, $entityName, $id, $fields) = @_;
2807        # Get a list of the field names being updated.
2808        my @fieldList = keys %{$fields};
2809        # Verify that the fields exist.
2810        my $checker = $self->GetFieldTable($entityName);
2811        for my $field (@fieldList) {
2812            if ($field eq 'id') {
2813                Confess("Cannot update the ID field for entity $entityName.");
2814            } elsif ($checker->{$field}->{relation} ne $entityName) {
2815                Confess("Cannot find $field in primary relation of $entityName.");
2816            }
2817        }
2818        # Build the SQL statement.
2819        my @sets = ();
2820        my @valueList = ();
2821        for my $field (@fieldList) {
2822            push @sets, _FixName($field) . " = ?";
2823            push @valueList, $fields->{$field};
2824        }
2825        my $command = "UPDATE $entityName SET " . join(", ", @sets) . " WHERE id = ?";
2826        # Add the ID to the list of binding values.
2827        push @valueList, $id;
2828        # Call SQL to do the work.
2829        my $rows = $self->{_dbh}->SQL($command, 0, @valueList);
2830        # Check for errors.
2831        if ($rows == 0) {
2832            Confess("Entity $id of type $entityName not found.");
2833        }
2834    }
2835    
2836    =head3 LoadTable
2837    
2838        my $results = $erdb->LoadTable($fileName, $relationName, %options);
2839    
2840    Load data from a tab-delimited file into a specified table, optionally re-creating the table
2841    first.
2842    
2843    =over 4
2844    
2845    =item fileName
2846    
2847    Name of the file from which the table data should be loaded.
2848    
2849    =item relationName
2850    
2851    Name of the relation to be loaded. This is the same as the table name.
2852    
2853    =item options
2854    
2855    A hash of load options.
2856    
2857    =item RETURN
2858    
2859    Returns a statistical object containing a list of the error messages.
2860    
2861    =back
2862    
2863    The permissible options are as follows.
2864    
2865    =over 4
2866    
2867    =item truncate
2868    
2869    If TRUE, then the table will be erased before loading.
2870    
2871    =item mode
2872    
2873    Mode in which the load should operate, either C<low_priority> or C<concurrent>.
2874    This option is only applicable to a MySQL database.
2875    
2876    =item partial
2877    
2878    If TRUE, then it is assumed that this is a partial load, and the table will not
2879    be analyzed and compacted at the end.
2880    
2881    =back
2882    
2883    =cut
2884    sub LoadTable {
2885        # Get the parameters.
2886        my ($self, $fileName, $relationName, %options) = @_;
2887      # Create the statistical return object.      # Create the statistical return object.
2888      my $retVal = _GetLoadStats();      my $retVal = _GetLoadStats();
2889      # Trace the fact of the load.      # Trace the fact of the load.
# Line 1685  Line 2895 
2895      # Get the relation data.      # Get the relation data.
2896      my $relation = $self->_FindRelation($relationName);      my $relation = $self->_FindRelation($relationName);
2897      # Check the truncation flag.      # Check the truncation flag.
2898      if ($truncateFlag) {      if ($options{truncate}) {
2899          Trace("Creating table $relationName") if T(2);          Trace("Creating table $relationName") if T(2);
2900          # Compute the row count estimate. We take the size of the load file,          # Compute the row count estimate. We take the size of the load file,
2901          # divide it by the estimated row size, and then multiply by 1.5 to          # divide it by the estimated row size, and then multiply by 2 to
2902          # leave extra room. We postulate a minimum row count of 1000 to          # leave extra room. We postulate a minimum row count of 1000 to
2903          # prevent problems with incoming empty load files.          # prevent problems with incoming empty load files.
2904          my $rowSize = $self->EstimateRowSize($relationName);          my $rowSize = $self->EstimateRowSize($relationName);
2905          my $estimate = FIG::max($fileSize * 1.5 / $rowSize, 1000);          my $estimate = $fileSize * 8 / $rowSize;
2906            if ($estimate < 1000) {
2907                $estimate = 1000;
2908            }
2909          # Re-create the table without its index.          # Re-create the table without its index.
2910          $self->CreateTable($relationName, 0, $estimate);          $self->CreateTable($relationName, 0, $estimate);
2911          # If this is a pre-index DBMS, create the index here.          # If this is a pre-index DBMS, create the index here.
# Line 1708  Line 2921 
2921      # Load the table.      # Load the table.
2922      my $rv;      my $rv;
2923      eval {      eval {
2924          $rv = $dbh->load_table(file => $fileName, tbl => $relationName);          $rv = $dbh->load_table(file => $fileName, tbl => $relationName, style => $options{mode});
2925      };      };
2926      if (!defined $rv) {      if (!defined $rv) {
2927          $retVal->AddMessage($@) if ($@);          $retVal->AddMessage($@) if ($@);
2928          $retVal->AddMessage("Table load failed for $relationName using $fileName.");          $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2929          Trace("Table load failed for $relationName.") if T(1);          Trace("Table load failed for $relationName.") if T(1);
2930      } else {      } else {
2931          # Here we successfully loaded the table.          # Here we successfully loaded the table.
2932          $retVal->Add("tables");          $retVal->Add("tables");
2933          my $size = -s $fileName;          my $size = -s $fileName;
2934          Trace("$size bytes loaded into $relationName.") if T(2);          Trace("$size bytes loaded into $relationName.") if T(2);
2935            $retVal->Add("bytes", $size);
2936          # If we're rebuilding, we need to create the table indexes.          # If we're rebuilding, we need to create the table indexes.
2937          if ($truncateFlag && ! $dbh->{_preIndex}) {          if ($options{truncate}) {
2938                # Indexes are created here for PostGres. For PostGres, indexes are
2939                # best built at the end. For MySQL, the reverse is true.
2940                if (! $dbh->{_preIndex}) {
2941              eval {              eval {
2942                  $self->CreateIndex($relationName);                  $self->CreateIndex($relationName);
2943              };              };
# Line 1728  Line 2945 
2945                  $retVal->AddMessage($@);                  $retVal->AddMessage($@);
2946              }              }
2947          }          }
2948                # The full-text index (if any) is always built last, even for MySQL.
2949                # First we need to see if this table has a full-text index. Only
2950                # primary relations are allowed that privilege.
2951                Trace("Checking for full-text index on $relationName.") if T(2);
2952                if ($self->_IsPrimary($relationName)) {
2953                    $self->CreateSearchIndex($relationName);
2954                }
2955            }
2956      }      }
2957      # Analyze the table to improve performance.      # Analyze the table to improve performance.
2958        if (! $options{partial}) {
2959            Trace("Analyzing and compacting $relationName.") if T(3);
2960      $dbh->vacuum_it($relationName);      $dbh->vacuum_it($relationName);
2961        }
2962        Trace("$relationName load completed.") if T(3);
2963      # Return the statistics.      # Return the statistics.
2964      return $retVal;      return $retVal;
2965  }  }
2966    
2967  =head3 GenerateEntity  =head3 CreateSearchIndex
2968    
2969  C<< my $fieldHash = $erdb->GenerateEntity($id, $type, \%values); >>      $erdb->CreateSearchIndex($objectName);
2970    
2971  Generate the data for a new entity instance. This method creates a field hash suitable for  Check for a full-text search index on the specified entity or relationship object, and
2972  passing as a parameter to L</InsertObject>. The ID is specified by the callr, but the rest  if one is required, rebuild it.
 of the fields are generated using information in the database schema.  
   
 Each data type has a default algorithm for generating random test data. This can be overridden  
 by including a B<DataGen> element in the field. If this happens, the content of the element is  
 executed as a PERL program in the context of this module. The element may make use of a C<$this>  
 variable which contains the field hash as it has been built up to the current point. If any  
 fields are dependent on other fields, the C<pass> attribute can be used to control the order  
 in which the fields are generated. A field with a high data pass number will be generated after  
 a field with a lower one. If any external values are needed, they should be passed in via the  
 optional third parameter, which will be available to the data generation script under the name  
 C<$value>. Several useful utility methods are provided for generating random values, including  
 L</IntGen>, L</StringGen>, L</FloatGen>, and L</DateGen>. Note that dates are stored and generated  
 in the form of a timestamp number rather than a string.  
2973    
2974  =over 4  =over 4
2975    
2976  =item id  =item objectName
2977    
2978  ID to assign to the new entity.  Name of the entity or relationship to be indexed.
2979    
2980  =item type  =back
2981    
2982  Type name for the new entity.  =cut
2983    
2984  =item values  sub CreateSearchIndex {
2985        # Get the parameters.
2986        my ($self, $objectName) = @_;
2987        # Get the relation's entity/relationship structure.
2988        my $structure = $self->_GetStructure($objectName);
2989        # Get the database handle.
2990        my $dbh = $self->{_dbh};
2991        Trace("Checking for search fields in $objectName.") if T(3);
2992        # Check for a searchable fields list.
2993        if (exists $structure->{searchFields}) {
2994            # Here we know that we need to create a full-text search index.
2995            # Get an SQL-formatted field name list.
2996            my $fields = join(", ", _FixNames(@{$structure->{searchFields}}));
2997            # Create the index. If it already exists, it will be dropped.
2998            $dbh->create_index(tbl => $objectName, idx => "search_idx",
2999                               flds => $fields, kind => 'fulltext');
3000            Trace("Index created for $fields in $objectName.") if T(2);
3001        }
3002    }
3003    
3004    =head3 DropRelation
3005    
3006        $erdb->DropRelation($relationName);
3007    
3008    Physically drop a relation from the database.
3009    
3010    =over 4
3011    
3012    =item relationName
3013    
3014  Hash containing additional values that might be needed by the data generation methods (optional).  Name of the relation to drop. If it does not exist, this method will have
3015    no effect.
3016    
3017  =back  =back
3018    
3019  =cut  =cut
3020    
3021  sub GenerateEntity {  sub DropRelation {
3022      # Get the parameters.      # Get the parameters.
3023      my ($self, $id, $type, $values) = @_;      my ($self, $relationName) = @_;
3024      # Create the return hash.      # Get the database handle.
3025      my $this = { id => $id };      my $dbh = $self->{_dbh};
3026      # Get the metadata structure.      # Drop the relation. The method used here has no effect if the relation
3027      my $metadata = $self->{_metaData};      # does not exist.
3028      # Get this entity's list of fields.      Trace("Invoking DB Kernel to drop $relationName.") if T(3);
3029      if (!exists $metadata->{Entities}->{$type}) {      $dbh->drop_table(tbl => $relationName);
3030          Confess("Unrecognized entity type $type in GenerateEntity.");  }
3031      } else {  
3032          my $entity = $metadata->{Entities}->{$type};  =head3 MatchSqlPattern
3033          my $fields = $entity->{Fields};  
3034          # Generate data from the fields.      my $matched = ERDB::MatchSqlPattern($value, $pattern);
3035          _GenerateFields($this, $fields, $type, $values);  
3036    Determine whether or not a specified value matches an SQL pattern. An SQL
3037    pattern has two wild card characters: C<%> that matches multiple characters,
3038    and C<_> that matches a single character. These can be escaped using a
3039    backslash (C<\>). We pull this off by converting the SQL pattern to a
3040    PERL regular expression. As per SQL rules, the match is case-insensitive.
3041    
3042    =over 4
3043    
3044    =item value
3045    
3046    Value to be matched against the pattern. Note that an undefined or empty
3047    value will not match anything.
3048    
3049    =item pattern
3050    
3051    SQL pattern against which to match the value. An undefined or empty pattern will
3052    match everything.
3053    
3054    =item RETURN
3055    
3056    Returns TRUE if the value and pattern match, else FALSE.
3057    
3058    =back
3059    
3060    =cut
3061    
3062    sub MatchSqlPattern {
3063        # Get the parameters.
3064        my ($value, $pattern) = @_;
3065        # Declare the return variable.
3066        my $retVal;
3067        # Insure we have a pattern.
3068        if (! defined($pattern) || $pattern eq "") {
3069            $retVal = 1;
3070        } else {
3071            # Break the pattern into pieces around the wildcard characters. Because we
3072            # use parentheses in the split function's delimiter expression, we'll get
3073            # list elements for the delimiters as well as the rest of the string.
3074            my @pieces = split /([_%]|\\[_%])/, $pattern;
3075            # Check some fast special cases.
3076            if ($pattern eq '%') {
3077                # A null pattern matches everything.
3078                $retVal = 1;
3079            } elsif (@pieces == 1) {
3080                # No wildcards, so we have a literal comparison. Note we're case-insensitive.
3081                $retVal = (lc($value) eq lc($pattern));
3082            } elsif (@pieces == 2 && $pieces[1] eq '%') {
3083                # A wildcard at the end, so we have a substring match. This is also case-insensitive.
3084                $retVal = (lc(substr($value, 0, length($pieces[0]))) eq lc($pieces[0]));
3085            } else {
3086                # Okay, we have to do it the hard way. Convert each piece to a PERL pattern.
3087                my $realPattern = "";
3088                for my $piece (@pieces) {
3089                    # Determine the type of piece.
3090                    if ($piece eq "") {
3091                        # Empty pieces are ignored.
3092                    } elsif ($piece eq "%") {
3093                        # Here we have a multi-character wildcard. Note that it can match
3094                        # zero or more characters.
3095                        $realPattern .= ".*"
3096                    } elsif ($piece eq "_") {
3097                        # Here we have a single-character wildcard.
3098                        $realPattern .= ".";
3099                    } elsif ($piece eq "\\%" || $piece eq "\\_") {
3100                        # This is an escape sequence (which is a rare thing, actually).
3101                        $realPattern .= substr($piece, 1, 1);
3102                    } else {
3103                        # Here we have raw text.
3104                        $realPattern .= quotemeta($piece);
3105      }      }
3106      # Return the hash created.              }
3107      return $this;              # Do the match.
3108                $retVal = ($value =~ /^$realPattern$/i ? 1 : 0);
3109            }
3110        }
3111        # Return the result.
3112        return $retVal;
3113  }  }
3114    
3115  =head3 GetEntity  =head3 GetEntity
3116    
3117  C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>      my $entityObject = $erdb->GetEntity($entityType, $ID);
3118    
3119  Return an object describing the entity instance with a specified ID.  Return an object describing the entity instance with a specified ID.
3120    
# Line 1811  Line 3130 
3130    
3131  =item RETURN  =item RETURN
3132    
3133  Returns a B<DBObject> representing the desired entity instance, or an undefined value if no  Returns a B<ERDBObject> representing the desired entity instance, or an undefined value if no
3134  instance is found with the specified key.  instance is found with the specified key.
3135    
3136  =back  =back
# Line 1822  Line 3141 
3141      # Get the parameters.      # Get the parameters.
3142      my ($self, $entityType, $ID) = @_;      my ($self, $entityType, $ID) = @_;
3143      # Create a query.      # Create a query.
3144      my $query = $self->Get([$entityType], "$entityType(id) = ?", $ID);      my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);
3145      # Get the first (and only) object.      # Get the first (and only) object.
3146      my $retVal = $query->Fetch();      my $retVal = $query->Fetch();
3147      # Return the result.      # Return the result.
3148      return $retVal;      return $retVal;
3149  }  }
3150    
3151    =head3 GetChoices
3152    
3153        my @values = $erdb->GetChoices($entityName, $fieldName);
3154    
3155    Return a list of all the values for the specified field that are represented in the
3156    specified entity.
3157    
3158    Note that if the field is not indexed, then this will be a very slow operation.
3159    
3160    =over 4
3161    
3162    =item entityName
3163    
3164    Name of an entity in the database.
3165    
3166    =item fieldName
3167    
3168    Name of a field belonging to the entity. This is a raw field name without
3169    the standard parenthesized notation used in most calls.
3170    
3171    =item RETURN
3172    
3173    Returns a list of the distinct values for the specified field in the database.
3174    
3175    =back
3176    
3177    =cut
3178    
3179    sub GetChoices {
3180        # Get the parameters.
3181        my ($self, $entityName, $fieldName) = @_;
3182        # Declare the return variable.
3183        my @retVal;
3184        # Get the entity data structure.
3185        my $entityData = $self->_GetStructure($entityName);
3186        # Get the field.
3187        my $fieldHash = $entityData->{Fields};
3188        if (! exists $fieldHash->{$fieldName}) {
3189            Confess("$fieldName not found in $entityName.");
3190        } else {
3191            # Get the name of the relation containing the field.
3192            my $relation = $fieldHash->{$fieldName}->{relation};
3193            # Fix up the field name.
3194            my $realName = _FixName($fieldName);
3195            # Get the database handle.
3196            my $dbh = $self->{_dbh};
3197            # Query the database.
3198            my $results = $dbh->SQL("SELECT DISTINCT $realName FROM $relation");
3199            # Clean the results. They are stored as a list of lists, and we just want the one list.
3200            @retVal = sort map { $_->[0] } @{$results};
3201        }
3202        # Return the result.
3203        return @retVal;
3204    }
3205    
3206  =head3 GetEntityValues  =head3 GetEntityValues
3207    
3208  C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>      my @values = $erdb->GetEntityValues($entityType, $ID, \@fields);
3209    
3210  Return a list of values from a specified entity instance.  Return a list of values from a specified entity instance. If the entity instance
3211    does not exist, an empty list is returned.
3212    
3213  =over 4  =over 4
3214    
# Line 1874  Line 3249 
3249    
3250  =head3 GetAll  =head3 GetAll
3251    
3252  C<< my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>      my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count);
3253    
3254  Return a list of values taken from the objects returned by a query. The first three  Return a list of values taken from the objects returned by a query. The first three
3255  parameters correspond to the parameters of the L</Get> method. The final parameter is  parameters correspond to the parameters of the L</Get> method. The final parameter is
# Line 1888  Line 3263 
3263  fields specified returns multiple values, they are flattened in with the rest. For  fields specified returns multiple values, they are flattened in with the rest. For
3264  example, the following call will return a list of the features in a particular  example, the following call will return a list of the features in a particular
3265  spreadsheet cell, and each feature will be represented by a list containing the  spreadsheet cell, and each feature will be represented by a list containing the
3266  feature ID followed by all of its aliases.  feature ID followed by all of its essentiality determinations.
3267    
3268  C<< $query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>      @query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(essential)']);
3269    
3270  =over 4  =over 4
3271    
# Line 1935  Line 3310 
3310      # list is a scalar we convert it into a singleton list.      # list is a scalar we convert it into a singleton list.
3311      my @parmList = ();      my @parmList = ();
3312      if (ref $parameterList eq "ARRAY") {      if (ref $parameterList eq "ARRAY") {
3313            Trace("GetAll parm list is an array.") if T(4);
3314          @parmList = @{$parameterList};          @parmList = @{$parameterList};
3315      } else {      } else {
3316            Trace("GetAll parm list is a scalar: $parameterList.") if T(4);
3317          push @parmList, $parameterList;          push @parmList, $parameterList;
3318      }      }
3319      # Insure the counter has a value.      # Insure the counter has a value.
3320      if (!defined $count) {      if (!defined $count) {
3321          $count = 0;          $count = 0;
3322      }      }
3323      # Add the row limit to the filter clause.      # Add the row limit to the filter clause.
3324      if ($count > 0) {      if ($count > 0) {
3325          $filterClause .= " LIMIT $count";          $filterClause .= " LIMIT $count";
3326        }
3327        # Create the query.
3328        my $query = $self->Get($objectNames, $filterClause, \@parmList);
3329        # Set up a counter of the number of records read.
3330        my $fetched = 0;
3331        # Loop through the records returned, extracting the fields. Note that if the
3332        # counter is non-zero, we stop when the number of records read hits the count.
3333        my @retVal = ();
3334        while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {
3335            my @rowData = $row->Values($fields);
3336            push @retVal, \@rowData;
3337            $fetched++;
3338        }
3339        Trace("$fetched rows returned in GetAll.") if T(SQL => 4);
3340        # Return the resulting list.
3341        return @retVal;
3342    }
3343    
3344    =head3 Exists
3345    
3346        my $found = $sprout->Exists($entityName, $entityID);
3347    
3348    Return TRUE if an entity exists, else FALSE.
3349    
3350    =over 4
3351    
3352    =item entityName
3353    
3354    Name of the entity type (e.g. C<Feature>) relevant to the existence check.
3355    
3356    =item entityID
3357    
3358    ID of the entity instance whose existence is to be checked.
3359    
3360    =item RETURN
3361    
3362    Returns TRUE if the entity instance exists, else FALSE.
3363    
3364    =back
3365    
3366    =cut
3367    #: Return Type $;
3368    sub Exists {
3369        # Get the parameters.
3370        my ($self, $entityName, $entityID) = @_;
3371        # Check for the entity instance.
3372        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
3373        my $testInstance = $self->GetEntity($entityName, $entityID);
3374        # Return an existence indicator.
3375        my $retVal = ($testInstance ? 1 : 0);
3376        return $retVal;
3377    }
3378    
3379    =head3 EstimateRowSize
3380    
3381        my $rowSize = $erdb->EstimateRowSize($relName);
3382    
3383    Estimate the row size of the specified relation. The estimated row size is computed by adding
3384    up the average length for each data type.
3385    
3386    =over 4
3387    
3388    =item relName
3389    
3390    Name of the relation whose estimated row size is desired.
3391    
3392    =item RETURN
3393    
3394    Returns an estimate of the row size for the specified relation.
3395    
3396    =back
3397    
3398    =cut
3399    #: Return Type $;
3400    sub EstimateRowSize {
3401        # Get the parameters.
3402        my ($self, $relName) = @_;
3403        # Declare the return variable.
3404        my $retVal = 0;
3405        # Find the relation descriptor.
3406        my $relation = $self->_FindRelation($relName);
3407        # Get the list of fields.
3408        for my $fieldData (@{$relation->{Fields}}) {
3409            # Get the field type and add its length.
3410            my $fieldLen = $TypeTable{$fieldData->{type}}->{avgLen};
3411            $retVal += $fieldLen;
3412        }
3413        # Return the result.
3414        return $retVal;
3415    }
3416    
3417    =head3 GetFieldTable
3418    
3419        my $fieldHash = $self->GetFieldTable($objectnName);
3420    
3421    Get the field structure for a specified entity or relationship.
3422    
3423    =over 4
3424    
3425    =item objectName
3426    
3427    Name of the desired entity or relationship.
3428    
3429    =item RETURN
3430    
3431    The table containing the field descriptors for the specified object.
3432    
3433    =back
3434    
3435    =cut
3436    
3437    sub GetFieldTable {
3438        # Get the parameters.
3439        my ($self, $objectName) = @_;
3440        # Get the descriptor from the metadata.
3441        my $objectData = $self->_GetStructure($objectName);
3442        # Return the object's field table.
3443        return $objectData->{Fields};
3444    }
3445    
3446    =head3 SplitKeywords
3447    
3448        my @keywords = ERDB::SplitKeywords($keywordString);
3449    
3450    This method returns a list of the positive keywords in the specified
3451    keyword string. All of the operators will have been stripped off,
3452    and if the keyword is preceded by a minus operator (C<->), it will
3453    not be in the list returned. The idea here is to get a list of the
3454    keywords the user wants to see. The list will be processed to remove
3455    duplicates.
3456    
3457    It is possible to create a string that confuses this method. For example
3458    
3459        frog toad -frog
3460    
3461    would return both C<frog> and C<toad>. If this is a problem we can deal
3462    with it later.
3463    
3464    =over 4
3465    
3466    =item keywordString
3467    
3468    The keyword string to be parsed.
3469    
3470    =item RETURN
3471    
3472    Returns a list of the words in the keyword string the user wants to
3473    see.
3474    
3475    =back
3476    
3477    =cut
3478    
3479    sub SplitKeywords {
3480        # Get the parameters.
3481        my ($keywordString) = @_;
3482        # Make a safety copy of the string. (This helps during debugging.)
3483        my $workString = $keywordString;
3484        # Convert operators we don't care about to spaces.
3485        $workString =~ tr/+"()<>/ /;
3486        # Split the rest of the string along space boundaries. Note that we
3487        # eliminate any words that are zero length or begin with a minus sign.
3488        my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
3489        # Use a hash to remove duplicates.
3490        my %words = map { $_ => 1 } @wordList;
3491        # Return the result.
3492        return sort keys %words;
3493    }
3494    
3495    =head3 ValidateFieldName
3496    
3497        my $okFlag = ERDB::ValidateFieldName($fieldName);
3498    
3499    Return TRUE if the specified field name is valid, else FALSE. Valid field names must
3500    be hyphenated words subject to certain restrictions.
3501    
3502    =over 4
3503    
3504    =item fieldName
3505    
3506    Field name to be validated.
3507    
3508    =item RETURN
3509    
3510    Returns TRUE if the field name is valid, else FALSE.
3511    
3512    =back
3513    
3514    =cut
3515    
3516    sub ValidateFieldName {
3517        # Get the parameters.
3518        my ($fieldName) = @_;
3519        # Declare the return variable. The field name is valid until we hear
3520        # differently.
3521        my $retVal = 1;
3522        # Compute the maximum name length.
3523        my $maxLen = $TypeTable{'name-string'}->{maxLen};
3524        # Look for bad stuff in the name.
3525        if ($fieldName =~ /--/) {
3526            # Here we have a doubled minus sign.
3527            Trace("Field name $fieldName has a doubled hyphen.") if T(1);
3528            $retVal = 0;
3529        } elsif ($fieldName !~ /^[A-Za-z]/) {
3530            # Here the field name is missing the initial letter.
3531            Trace("Field name $fieldName does not begin with a letter.") if T(1);
3532            $retVal = 0;
3533        } elsif (length($fieldName) > $maxLen) {
3534            # Here the field name is too long.
3535            Trace("Maximum field name length is $maxLen. Field name must be truncated to " . substr($fieldName,0, $maxLen) . ".");
3536        } else {
3537            # Strip out the minus signs. Everything remaining must be a letter,
3538            # underscore, or digit.
3539            my $strippedName = $fieldName;
3540            $strippedName =~ s/-//g;
3541            if ($strippedName !~ /^(\w|\d)+$/) {
3542                Trace("Field name $fieldName contains illegal characters.") if T(1);
3543                $retVal = 0;
3544            }
3545        }
3546        # Return the result.
3547        return $retVal;
3548    }
3549    
3550    =head3 ReadMetaXML
3551    
3552        my $rawMetaData = ERDB::ReadDBD($fileName);
3553    
3554    This method reads a raw database definition XML file and returns it.
3555    Normally, the metadata used by the ERDB system has been processed and
3556    modified to make it easier to load and retrieve the data; however,
3557    this method can be used to get the data in its raw form.
3558    
3559    =over 4
3560    
3561    =item fileName
3562    
3563    Name of the XML file to read.
3564    
3565    =item RETURN
3566    
3567    Returns a hash reference containing the raw XML data from the specified file.
3568    
3569    =back
3570    
3571    =cut
3572    
3573    sub ReadMetaXML {
3574        # Get the parameters.
3575        my ($fileName) = @_;
3576        # Read the XML.
3577        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
3578        Trace("XML metadata loaded from file $fileName.") if T(1);
3579        # Return the result.
3580        return $retVal;
3581    }
3582    
3583    =head3 GetEntityFieldHash
3584    
3585        my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName);
3586    
3587    Get the field hash of the named entity in the specified raw XML structure.
3588    The field hash may not exist, in which case we need to create it.
3589    
3590    =over 4
3591    
3592    =item structure
3593    
3594    Raw XML structure defininng the database. This is not the run-time XML used by
3595    an ERDB object, since that has all sorts of optimizations built-in.
3596    
3597    =item entityName
3598    
3599    Name of the entity whose field structure is desired.
3600    
3601    =item RETURN
3602    
3603    Returns the field hash used to define the entity's fields.
3604    
3605    =back
3606    
3607    =cut
3608    
3609    sub GetEntityFieldHash {
3610        # Get the parameters.
3611        my ($structure, $entityName) = @_;
3612        # Get the entity structure.
3613        my $entityData = $structure->{Entities}->{$entityName};
3614        # Look for a field structure.
3615        my $retVal = $entityData->{Fields};
3616        # If it doesn't exist, create it.
3617        if (! defined($retVal)) {
3618            $entityData->{Fields} = {};
3619            $retVal = $entityData->{Fields};
3620        }
3621        # Return the result.
3622        return $retVal;
3623    }
3624    
3625    =head3 WriteMetaXML
3626    
3627        ERDB::WriteMetaXML($structure, $fileName);
3628    
3629    Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
3630    used to update the database definition. It must be used with care, however, since it
3631    will only work on a raw structure, not on the processed structure created by an ERDB
3632    constructor.
3633    
3634    =over 4
3635    
3636    =item structure
3637    
3638    XML structure to be written to the file.
3639    
3640    =item fileName
3641    
3642    Name of the output file to which the updated XML should be stored.
3643    
3644    =back
3645    
3646    =cut
3647    
3648    sub WriteMetaXML {
3649        # Get the parameters.
3650        my ($structure, $fileName) = @_;
3651        # Compute the output.
3652        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
3653        # Write it to the file.
3654        my $xmlOut = Open(undef, ">$fileName");
3655        print $xmlOut $fileString;
3656    }
3657    
3658    
3659    =head3 HTMLNote
3660    
3661    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
3662    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
3663    Except for C<[p]>, all the codes are closed by slash-codes. So, for
3664    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
3665    
3666        my $realHtml = ERDB::HTMLNote($dataString);
3667    
3668    =over 4
3669    
3670    =item dataString
3671    
3672    String to convert to HTML.
3673    
3674    =item RETURN
3675    
3676    An HTML string derived from the input string.
3677    
3678    =back
3679    
3680    =cut
3681    
3682    sub HTMLNote {
3683        # Get the parameter.
3684        my ($dataString) = @_;
3685        # HTML-escape the text.
3686        my $retVal = CGI::escapeHTML($dataString);
3687        # Substitute the bulletin board codes.
3688        $retVal =~ s!\[(/?[bi])\]!<$1>!g;
3689        $retVal =~ s!\[p\]!</p><p>!g;
3690        $retVal =~ s!\[link\s+([^\]]+)\]!<a href="$1">!g;
3691        $retVal =~ s!\[/link\]!</a>!g;
3692        # Return the result.
3693        return $retVal;
3694    }
3695    
3696    =head3 WikiNote
3697    
3698    Convert a note or comment to Wiki text by replacing some bulletin-board codes with HTML. The codes
3699    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
3700    Except for C<[p]>, all the codes are closed by slash-codes. So, for
3701    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
3702    
3703        my $wikiText = ERDB::WikiNote($dataString);
3704    
3705    =over 4
3706    
3707    =item dataString
3708    
3709    String to convert to Wiki text.
3710    
3711    =item RETURN
3712    
3713    An Wiki text string derived from the input string.
3714    
3715    =back
3716    
3717    =cut
3718    
3719    sub WikiNote {
3720        # Get the parameter.
3721        my ($dataString) = @_;
3722        # HTML-escape the text.
3723        my $retVal = CGI::escapeHTML($dataString);
3724        # Substitute the bulletin board codes.
3725        my $italic = WikiTools::ItalicCode();
3726        $retVal =~ s/\[\/?i\]/$italic/g;
3727        my $bold = WikiTools::BoldCode();
3728        $retVal =~ s/\[\/?b\]/$bold/g;
3729        # Paragraph breaks are the same no matter which Wiki you're using.
3730        $retVal =~ s!\[p\]!\n\n!g;
3731        # Now we do the links, which are complicated by the need to know two
3732        # things: the target URL and the text.
3733        while ($retVal =~ /\[link\s+([^\]]+)\]([^\[]+)\[\/link\]/g) {
3734            # Replace the matched string with the Wiki markup for links. Note that
3735            # $-[0] is the starting position of the match for the entire expression,
3736            # and $+[0] is past the ending position.
3737            substr $retVal, $-[0], $+[0] - $-[0], WikiTools::LinkMarkup($1, $2);
3738        }
3739        # Return the result.
3740        return $retVal;
3741    }
3742    
3743    =head3 BeginTran
3744    
3745        $erdb->BeginTran();
3746    
3747    Start a database transaction.
3748    
3749    =cut
3750    
3751    sub BeginTran {
3752        my ($self) = @_;
3753        $self->{_dbh}->begin_tran();
3754    
3755    }
3756    
3757    =head3 CommitTran
3758    
3759        $erdb->CommitTran();
3760    
3761    Commit an active database transaction.
3762    
3763    =cut
3764    
3765    sub CommitTran {
3766        my ($self) = @_;
3767        $self->{_dbh}->commit_tran();
3768    }
3769    
3770    =head3 RollbackTran
3771    
3772        $erdb->RollbackTran();
3773    
3774    Roll back an active database transaction.
3775    
3776    =cut
3777    
3778    sub RollbackTran {
3779        my ($self) = @_;
3780        $self->{_dbh}->roll_tran();
3781    }
3782    
3783    =head3 UpdateField
3784    
3785        my $count = $erdb->UpdateField($objectNames, $fieldName, $oldValue, $newValue, $filter, $parms);
3786    
3787    Update all occurrences of a specific field value to a new value. The number of rows changed will be
3788    returned.
3789    
3790    =over 4
3791    
3792    =item fieldName
3793    
3794    Name of the field in standard I<objectName>C<(>I<fieldName>C<)> format.
3795    
3796    =item oldValue
3797    
3798    Value to be modified. All occurrences of this value in the named field will be replaced by the
3799    new value.
3800    
3801    =item newValue
3802    
3803    New value to be substituted for the old value when it's found.
3804    
3805    =item filter
3806    
3807    A standard ERDB filter clause (see L</Get>). The filter will be applied before any substitutions take place.
3808    
3809    =item parms
3810    
3811    Reference to a list of parameter values in the filter.
3812    
3813    =item RETURN
3814    
3815    Returns the number of rows modified.
3816    
3817    =back
3818    
3819    =cut
3820    
3821    sub UpdateField {
3822        # Get the parameters.
3823        my ($self, $fieldName, $oldValue, $newValue, $filter, $parms) = @_;
3824        # Get the object and field names from the field name parameter.
3825        $fieldName =~ /^([^(]+)\(([^)]+)\)/;
3826        my $objectName = $1;
3827        my $realFieldName = _FixName($2);
3828        # Add the old value to the filter. Note we allow the possibility that no
3829        # filter was specified.
3830        my $realFilter = "$fieldName = ?";
3831        if ($filter) {
3832            $realFilter .= " AND $filter";
3833        }
3834        # Format the query filter.
3835        my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
3836            $self->_SetupSQL([$objectName], $realFilter);
3837        # Create the query. Since there is only one object name, the mapped-name data is not
3838        # necessary. Neither is the FROM clause.
3839        $suffix =~ s/^FROM.+WHERE\s+//;
3840        # Create the update statement.
3841        my $command = "UPDATE $objectName SET $realFieldName = ? WHERE $suffix";
3842        # Get the database handle.
3843        my $dbh = $self->{_dbh};
3844        # Add the old and new values to the parameter list. Note we allow the possibility that
3845        # there are no user-supplied parameters.
3846        my @params = ($newValue, $oldValue);
3847        if (defined $parms) {
3848            push @params, @{$parms};
3849        }
3850        # Execute the update.
3851        my $retVal = $dbh->SQL($command, 0, @params);
3852        # Make the funky zero a real zero.
3853        if ($retVal == 0) {
3854            $retVal = 0;
3855        }
3856        # Return the result.
3857        return $retVal;
3858    }
3859    
3860    
3861    =head2 Data Mining Methods
3862    
3863    =head3 GetUsefulCrossValues
3864    
3865        my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship);
3866    
3867    Return a list of the useful attributes that would be returned by a B<Cross> call
3868    from an entity of the source entity type through the specified relationship. This
3869    means it will return the fields of the target entity type and the intersection data
3870    fields in the relationship. Only primary table fields are returned. In other words,
3871    the field names returned will be for fields where there is always one and only one
3872    value.
3873    
3874    =over 4
3875    
3876    =item sourceEntity
3877    
3878    Name of the entity from which the relationship crossing will start.
3879    
3880    =item relationship
3881    
3882    Name of the relationship being crossed.
3883    
3884    =item RETURN
3885    
3886    Returns a list of field names in Sprout field format (I<objectName>C<(>I<fieldName>C<)>.
3887    
3888    =back
3889    
3890    =cut
3891    #: Return Type @;
3892    sub GetUsefulCrossValues {
3893        # Get the parameters.
3894        my ($self, $sourceEntity, $relationship) = @_;
3895        # Declare the return variable.
3896        my @retVal = ();
3897        # Determine the target entity for the relationship. This is whichever entity is not
3898        # the source entity. So, if the source entity is the FROM, we'll get the name of
3899        # the TO, and vice versa.
3900        my $relStructure = $self->_GetStructure($relationship);
3901        my $targetEntityType = ($relStructure->{from} eq $sourceEntity ? "to" : "from");
3902        my $targetEntity = $relStructure->{$targetEntityType};
3903        # Get the field table for the entity.
3904        my $entityFields = $self->GetFieldTable($targetEntity);
3905        # The field table is a hash. The hash key is the field name. The hash value is a structure.
3906        # For the entity fields, the key aspect of the target structure is that the {relation} value
3907        # must match the entity name.
3908        my @fieldList = map { "$targetEntity($_)" } grep { $entityFields->{$_}->{relation} eq $targetEntity }
3909                            keys %{$entityFields};
3910        # Push the fields found onto the return variable.
3911        push @retVal, sort @fieldList;
3912        # Get the field table for the relationship.
3913        my $relationshipFields = $self->GetFieldTable($relationship);
3914        # Here we have a different rule. We want all the fields other than "from-link" and "to-link".
3915        # This may end up being an empty set.
3916        my @fieldList2 = map { "$relationship($_)" } grep { $_ ne "from-link" && $_ ne "to-link" }
3917                            keys %{$relationshipFields};
3918        # Push these onto the return list.
3919        push @retVal, sort @fieldList2;
3920        # Return the result.
3921        return @retVal;
3922    }
3923    
3924    =head3 FindColumn
3925    
3926        my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier);
3927    
3928    Return the location a desired column in a data mining header line. The data
3929    mining header line is a tab-separated list of column names. The column
3930    identifier is either the numerical index of a column or the actual column
3931    name.
3932    
3933    =over 4
3934    
3935    =item headerLine
3936    
3937    The header line from a data mining command, which consists of a tab-separated
3938    list of column names.
3939    
3940    =item columnIdentifier
3941    
3942    Either the ordinal number of the desired column (1-based), or the name of the
3943    desired column.
3944    
3945    =item RETURN
3946    
3947    Returns the array index (0-based) of the desired column.
3948    
3949    =back
3950    
3951    =cut
3952    
3953    sub FindColumn {
3954        # Get the parameters.
3955        my ($headerLine, $columnIdentifier) = @_;
3956        # Declare the return variable.
3957        my $retVal;
3958        # Split the header line into column names.
3959        my @headers = ParseColumns($headerLine);
3960        # Determine whether we have a number or a name.
3961        if ($columnIdentifier =~ /^\d+$/) {
3962            # Here we have a number. Subtract 1 and validate the result.
3963            $retVal = $columnIdentifier - 1;
3964            if ($retVal < 0 || $retVal > $#headers) {
3965                Confess("Invalid column identifer \"$columnIdentifier\": value out of range.");
3966            }
3967        } else {
3968            # Here we have a name. We need to find it in the list.
3969            for (my $i = 0; $i <= $#headers && ! defined($retVal); $i++) {
3970                if ($headers[$i] eq $columnIdentifier) {
3971                    $retVal = $i;
3972                }
3973            }
3974            if (! defined($retVal)) {
3975                Confess("Invalid column identifier \"$columnIdentifier\": value not found.");
3976            }
3977        }
3978        # Return the result.
3979        return $retVal;
3980    }
3981    
3982    =head3 ParseColumns
3983    
3984        my @columns = ERDB::ParseColumns($line);
3985    
3986    Convert the specified data line to a list of columns.
3987    
3988    =over 4
3989    
3990    =item line
3991    
3992    A data mining input, consisting of a tab-separated list of columns terminated by a
3993    new-line.
3994    
3995    =item RETURN
3996    
3997    Returns a list consisting of the column values.
3998    
3999    =back
4000    
4001    =cut
4002    
4003    sub ParseColumns {
4004        # Get the parameters.
4005        my ($line) = @_;
4006        # Chop off the line-end.
4007        chomp $line;
4008        # Split it into a list.
4009        my @retVal = split(/\t/, $line);
4010        # Return the result.
4011        return @retVal;
4012    }
4013    
4014    =head2 Virtual Methods
4015    
4016    =head3 _CreatePPOIndex
4017    
4018        my $index = ERDB::_CreatePPOIndex($indexObject);
4019    
4020    Convert the XML for an ERDB index to the XML structure for a PPO
4021    index.
4022    
4023    =over 4
4024    
4025    =item indexObject
4026    
4027    ERDB XML structure for an index.
4028    
4029    =item RETURN
4030    
4031    PPO XML structure for the same index.
4032    
4033    =back
4034    
4035    =cut
4036    
4037    sub _CreatePPOIndex {
4038        # Get the parameters.
4039        my ($indexObject) = @_;
4040        # The incoming index contains a list of the index fields in the IndexFields
4041        # member. We loop through it to create the index tags.
4042        my @fields = map { { label => _FixName($_->{name}) } } @{$indexObject->{IndexFields}};
4043        # Wrap the fields in attribute tags.
4044        my $retVal = { attribute => \@fields };
4045        # Return the result.
4046        return $retVal;
4047    }
4048    
4049    =head3 _CreatePPOField
4050    
4051        my $fieldXML = ERDB::_CreatePPOField($fieldName, $fieldObject);
4052    
4053    Convert the ERDB XML structure for a field to a PPO scalar XML structure.
4054    
4055    =over 4
4056    
4057    =item fieldName
4058    
4059    Name of the scalar field.
4060    
4061    =item fieldObject
4062    
4063    ERDB XML structure describing the field.
4064    
4065    =item RETURN
4066    
4067    Returns a PPO XML structure for the same field.
4068    
4069    =back
4070    
4071    =cut
4072    
4073    sub _CreatePPOField {
4074        # Get the parameters.
4075        my ($fieldName, $fieldObject) = @_;
4076        # Get the field type.
4077        my $type = $TypeTable{$fieldObject->{type}}->{sqlType};
4078        # Fix up the field name.
4079        $fieldName = _FixName($fieldName);
4080        # Build the scalar tag.
4081        my $retVal = { label => $fieldName, type => $type };
4082        # Return the result.
4083        return $retVal;
4084    }
4085    
4086    =head3 CleanKeywords
4087    
4088        my $cleanedString = $erdb->CleanKeywords($searchExpression);
4089    
4090    Clean up a search expression or keyword list. This is a virtual method that may
4091    be overridden by the subclass. The base-class method removes extra spaces
4092    and converts everything to lower case.
4093    
4094    =over 4
4095    
4096    =item searchExpression
4097    
4098    Search expression or keyword list to clean. Note that a search expression may
4099    contain boolean operators which need to be preserved. This includes leading
4100    minus signs.
4101    
4102    =item RETURN
4103    
4104    Cleaned expression or keyword list.
4105    
4106    =back
4107    
4108    =cut
4109    
4110    sub CleanKeywords {
4111        # Get the parameters.
4112        my ($self, $searchExpression) = @_;
4113        # Lower-case the expression and copy it into the return variable. Note that we insure we
4114        # don't accidentally end up with an undefined value.
4115        my $retVal = lc($searchExpression || "");
4116        # Remove extra spaces.
4117        $retVal =~ s/\s+/ /g;
4118        $retVal =~ s/(^\s+)|(\s+$)//g;
4119        # Return the result.
4120        return $retVal;
4121    }
4122    
4123    =head3 GetSourceObject
4124    
4125        my $source = $erdb->GetSourceObject($entityName);
4126    
4127    Return the object to be used in loading special attributes of the specified entity. The
4128    algorithm for loading special attributes is stored in the C<DataGen> elements of the
4129    XML
4130    
4131    =head2 Internal Utility Methods
4132    
4133    =head3 _RelationMap
4134    
4135        my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
4136    
4137    Create the relation map for an SQL query. The relation map is used by B<ERDBObject>
4138    to determine how to interpret the results of the query.
4139    
4140    =over 4
4141    
4142    =item mappedNameHashRef
4143    
4144    Reference to a hash that maps modified object names to real object names.
4145    
4146    =item mappedNameListRef
4147    
4148    Reference to a list of modified object names in the order they appear in the
4149    SELECT list.
4150    
4151    =item RETURN
4152    
4153    Returns a list of 2-tuples. Each tuple consists of an object name as used in the
4154    query followed by the actual name of that object. This enables the B<ERDBObject> to
4155    determine the order of the tables in the query and which object name belongs to each
4156    mapped object name. Most of the time these two values are the same; however, if a
4157    relation occurs twice in the query, the relation name in the field list and WHERE
4158    clause will use a mapped name (generally the actual relation name with a numeric
4159    suffix) that does not match the actual relation name.
4160    
4161    =back
4162    
4163    =cut
4164    
4165    sub _RelationMap {
4166        # Get the parameters.
4167        my ($mappedNameHashRef, $mappedNameListRef) = @_;
4168        # Declare the return variable.
4169        my @retVal = ();
4170        # Build the map.
4171        for my $mappedName (@{$mappedNameListRef}) {
4172            push @retVal, [$mappedName, $mappedNameHashRef->{$mappedName}];
4173        }
4174        # Return it.
4175        return @retVal;
4176    }
4177    
4178    
4179    =head3 _SetupSQL
4180    
4181    Process a list of object names and a filter clause so that they can be used to
4182    build an SQL statement. This method takes in a reference to a list of object names
4183    and a filter clause. It will return a corrected filter clause, a list of mapped
4184    names and the mapped name hash.
4185    
4186    This is an instance method.
4187    
4188    =over 4
4189    
4190    =item objectNames
4191    
4192    Reference to a list of the object names to be included in the query.
4193    
4194    =item filterClause
4195    
4196    A string containing the WHERE clause for the query (without the C<WHERE>) and also
4197    optionally the C<ORDER BY> and C<LIMIT> clauses.
4198    
4199    =item matchClause
4200    
4201    An optional full-text search clause. If specified, it will be inserted at the
4202    front of the WHERE clause. It should already be SQL-formatted; that is, the
4203    field names should be in the form I<table>C<.>I<fieldName>.
4204    
4205    =item RETURN
4206    
4207    Returns a three-element list. The first element is the SQL statement suffix, beginning
4208    with the FROM clause. The second element is a reference to a list of the names to be
4209    used in retrieving the fields. The third element is a hash mapping the names to the
4210    objects they represent.
4211    
4212    =back
4213    
4214    =cut
4215    
4216    sub _SetupSQL {
4217        my ($self, $objectNames, $filterClause, $matchClause) = @_;
4218        # Adjust the list of object names to account for multiple occurrences of the
4219        # same object. We start with a hash table keyed on object name that will
4220        # return the object suffix. The first time an object is encountered it will
4221        # not be found in the hash. The next time the hash will map the object name
4222        # to 2, then 3, and so forth.
4223        my %objectHash = ();
4224        # This list will contain the object names as they are to appear in the
4225        # FROM list.
4226        my @fromList = ();
4227        # This list contains the suffixed object name for each object. It is exactly
4228        # parallel to the list in the $objectNames parameter.
4229        my @mappedNameList = ();
4230        # Finally, this hash translates from a mapped name to its original object name.
4231        my %mappedNameHash = ();
4232        # Now we create the lists. Note that for every single name we push something into
4233        # @fromList and @mappedNameList. This insures that those two arrays are exactly
4234        # parallel to $objectNames.
4235        for my $objectName (@{$objectNames}) {
4236            # Get the next suffix for this object.
4237            my $suffix = $objectHash{$objectName};
4238            if (! $suffix) {
4239                # Here we are seeing the object for the first time. The object name
4240                # is used as is.
4241                push @mappedNameList, $objectName;
4242                push @fromList, $objectName;
4243                $mappedNameHash{$objectName} = $objectName;
4244                # Denote the next suffix will be 2.
4245                $objectHash{$objectName} = 2;
4246            } else {
4247                # Here we've seen the object before. We construct a new name using
4248                # the suffix from the hash and update the hash.
4249                my $mappedName = "$objectName$suffix";
4250                $objectHash{$objectName} = $suffix + 1;
4251                # The FROM list has the object name followed by the mapped name. This
4252                # tells SQL it's still the same table, but we're using a different name
4253                # for it to avoid confusion.
4254                push @fromList, "$objectName $mappedName";
4255                # The mapped-name list contains the real mapped name.
4256                push @mappedNameList, $mappedName;
4257                # Finally, enable us to get back from the mapped name to the object name.
4258                $mappedNameHash{$mappedName} = $objectName;
4259            }
4260        }
4261        # Begin the SELECT suffix. It starts with
4262        #
4263        # FROM name1, name2, ... nameN
4264        #
4265        my $suffix = "FROM " . join(', ', @fromList);
4266        # Now for the WHERE. First, we need a place for the filter string.
4267        my $filterString = "";
4268        # We will also keep a list of conditions to add to the WHERE clause in order to link
4269        # entities and relationships as well as primary relations to secondary ones.
4270        my @joinWhere = ();
4271        # Check for a filter clause.
4272        if ($filterClause) {
4273            # Here we have one, so we convert its field names and add it to the query. First,
4274            # We create a copy of the filter string we can work with.
4275            $filterString = $filterClause;
4276            # Next, we sort the object names by length. This helps protect us from finding
4277            # object names inside other object names when we're doing our search and replace.
4278            my @sortedNames = sort { length($b) - length($a) } @mappedNameList;
4279            # The final preparatory step is to create a hash table of relation names. The
4280            # table begins with the relation names already in the SELECT command. We may
4281            # need to add relations later if there is filtering on a field in a secondary
4282            # relation. The secondary relations are the ones that contain multiply-
4283            # occurring or optional fields.
4284            my %fromNames = map { $_ => 1 } @sortedNames;
4285            # We are ready to begin. We loop through the object names, replacing each
4286            # object name's field references by the corresponding SQL field reference.
4287            # Along the way, if we find a secondary relation, we will need to add it
4288            # to the FROM clause.
4289            for my $mappedName (@sortedNames) {
4290                # Get the length of the object name plus 2. This is the value we add to the
4291                # size of the field name to determine the size of the field reference as a
4292                # whole.
4293                my $nameLength = 2 + length $mappedName;
4294                # Get the real object name for this mapped name.
4295                my $objectName = $mappedNameHash{$mappedName};
4296                Trace("Processing $mappedName for object $objectName.") if T(4);
4297                # Get the object's field list.
4298                my $fieldList = $self->GetFieldTable($objectName);
4299                # Find the field references for this object.
4300                while ($filterString =~ m/$mappedName\(([^)]*)\)/g) {
4301                    # At this point, $1 contains the field name, and the current position
4302                    # is set immediately after the final parenthesis. We pull out the name of
4303                    # the field and the position and length of the field reference as a whole.
4304                    my $fieldName = $1;
4305                    my $len = $nameLength + length $fieldName;
4306                    my $pos = pos($filterString) - $len;
4307                    # Insure the field exists.
4308                    if (!exists $fieldList->{$fieldName}) {
4309                        Confess("Field $fieldName not found for object $objectName.");
4310                    } else {
4311                        Trace("Processing $fieldName at position $pos.") if T(4);
4312                        # Get the field's relation.
4313                        my $relationName = $fieldList->{$fieldName}->{relation};
4314                        # Now we have a secondary relation. We need to insure it matches the
4315                        # mapped name of the primary relation. First we peel off the suffix
4316                        # from the mapped name.
4317                        my $mappingSuffix = substr $mappedName, length($objectName);
4318                        # Put the mapping suffix onto the relation name to get the
4319                        # mapped relation name.
4320                        my $mappedRelationName = "$relationName$mappingSuffix";
4321                        # Insure the relation is in the FROM clause.
4322                        if (!exists $fromNames{$mappedRelationName}) {
4323                            # Add the relation to the FROM clause.
4324                            if ($mappedRelationName eq $relationName) {
4325                                # The name is un-mapped, so we add it without
4326                                # any frills.
4327                                $suffix .= ", $relationName";
4328                                push @joinWhere, "$objectName.id = $relationName.id";
4329                            } else {
4330                                # Here we have a mapping situation.
4331                                $suffix .= ", $relationName $mappedRelationName";
4332                                push @joinWhere, "$mappedRelationName.id = $mappedName.id";
4333                            }
4334                            # Denote we have this relation available for future fields.
4335                         &nbs