[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 1.89, Thu Apr 12 05:59:41 2007 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 FIG;
14        use CGI;
15    
16  =head1 Entity-Relationship Database Package  =head1 Entity-Relationship Database Package
17    
# Line 59  Line 60 
60  B<start-position>, which indicates where in the contig that the sequence begins. This attribute  B<start-position>, which indicates where in the contig that the sequence begins. This attribute
61  is implemented as the C<start_position> field in the C<IsMadeUpOf> relation.  is implemented as the C<start_position> field in the C<IsMadeUpOf> relation.
62    
63  The database itself is described by an XML file using the F<ERDatabase.xsd> schema. In addition to  The database itself is described by an XML file. In addition to all the data required to define
64  all the data required to define the entities, relationships, and attributes, the schema provides  the entities, relationships, and attributes, the schema provides space for notes describing
65  space for notes describing the data and what it means. These notes are used by L</ShowMetaData>  the data and what it means. These notes are used by L</ShowMetaData> to generate documentation
66  to generate documentation for the database.  for the database.
67    
68    Special support is provided for text searching. An entity field can be marked as <em>searchable</em>,
69    in which case it will be used to generate a text search index in which the user searches for words
70    in the field instead of a particular field value.
71    
72  Finally, every entity and relationship object has a flag indicating if it is new or old. The object  Finally, every entity and relationship object has a flag indicating if it is new or old. The object
73  is considered I<old> if it was loaded by the L</LoadTables> method. It is considered I<new> if it  is considered I<old> if it was loaded by the L</LoadTables> method. It is considered I<new> if it
74  was inserted by the L</InsertObject> method.  was inserted by the L</InsertObject> method.
75    
 To facilitate testing, the ERDB module supports automatic generation of test data. This process  
 is described in the L</GenerateEntity> and L</GenerateConnection> methods, though it is not yet  
 fully implemented.  
   
76  =head2 XML Database Description  =head2 XML Database Description
77    
78  =head3 Data Types  =head3 Data Types
# Line 91  Line 92 
92    
93  32-bit signed integer  32-bit signed integer
94    
95    =item counter
96    
97    32-bit unsigned integer
98    
99  =item date  =item date
100    
101  64-bit unsigned integer, representing a PERL date/time value  64-bit unsigned integer, representing a PERL date/time value
# Line 110  Line 115 
115  compatability with certain database packages), but the only values supported are  compatability with certain database packages), but the only values supported are
116  0 and 1.  0 and 1.
117    
118    =item id-string
119    
120    variable-length string, maximum 25 characters
121    
122  =item key-string  =item key-string
123    
124  variable-length string, maximum 40 characters  variable-length string, maximum 40 characters
# Line 182  Line 191 
191    
192  Name of the field. The field name should contain only letters, digits, and hyphens (C<->),  Name of the field. The field name should contain only letters, digits, and hyphens (C<->),
193  and the first character should be a letter. Most underlying databases are case-insensitive  and the first character should be a letter. Most underlying databases are case-insensitive
194  with the respect to field names, so a best practice is to use lower-case letters only.  with the respect to field names, so a best practice is to use lower-case letters only. Finally,
195    the name C<search-relevance> has special meaning for full-text searches and should not be
196    used as a field name.
197    
198  =item type  =item type
199    
# Line 201  Line 212 
212  entity, the fields without a relation attribute are said to belong to the  entity, the fields without a relation attribute are said to belong to the
213  I<primary relation>. This relation has the same name as the entity itself.  I<primary relation>. This relation has the same name as the entity itself.
214    
215    =item searchable
216    
217    If specified, then the field is a candidate for full-text searching. A single full-text
218    index will be created for each relation with at least one searchable field in it.
219    For best results, this option should only be used for string or text fields.
220    
221    =item special
222    
223    This attribute allows the subclass to assign special meaning for certain fields.
224    The interpretation is up to the subclass itself. Currently, only entity fields
225    can have this attribute.
226    
227  =back  =back
228    
229  =head3 Indexes  =head3 Indexes
230    
231  An entity can have multiple alternate indexes associated with it. The fields must  An entity can have multiple alternate indexes associated with it. The fields 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                  );                  );
377    
378  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 338  Line 381 
381                     'MM' => 'many-to-many'                     'MM' => 'many-to-many'
382                   );                   );
383    
384  # Table for interpreting string patterns.  # Options for XML input and output.
385    
386    my %XmlOptions = (GroupTags =>  { Relationships => 'Relationship',
387                                      Entities => 'Entity',
388                                      Fields => 'Field',
389                                      Indexes => 'Index',
390                                      IndexFields => 'IndexField'
391                                    },
392                      KeyAttr =>    { Relationship => 'name',
393                                      Entity => 'name',
394                                      Field => 'name'
395                                    },
396                      SuppressEmpty => 1,
397                     );
398    
399  my %PictureTable = ( 'A' => "abcdefghijklmnopqrstuvwxyz",  my %XmlInOpts  = (
400                       '9' => "0123456789",                    ForceArray => ['Field', 'Index', 'IndexField', 'Relationship', 'Entity'],
401                       'X' => "abcdefghijklmnopqrstuvwxyz0123456789",                    ForceContent => 1,
402                       'V' => "aeiou",                    NormalizeSpace => 2,
403                       'K' => "bcdfghjklmnoprstvwxyz"                   );
404    my %XmlOutOpts = (
405                      RootName => 'Database',
406                      XMLDecl => 1,
407                     );                     );
408    
409    
410  =head2 Public Methods  =head2 Public Methods
411    
412  =head3 new  =head3 new
# Line 416  Line 476 
476      # Write the HTML heading stuff.      # Write the HTML heading stuff.
477      print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";      print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";
478      print HTMLOUT "</head>\n<body>\n";      print HTMLOUT "</head>\n<body>\n";
479        # Write the documentation.
480        print HTMLOUT $self->DisplayMetaData();
481        # Close the document.
482        print HTMLOUT "</body>\n</html>\n";
483        # Close the file.
484        close HTMLOUT;
485    }
486    
487    =head3 DisplayMetaData
488    
489    C<< my $html = $erdb->DisplayMetaData(); >>
490    
491    Return an HTML description of the database. This description can be used to help users create
492    the data to be loaded into the relations and form queries. The output is raw includable HTML
493    without any HEAD or BODY tags.
494    
495    =over 4
496    
497    =item filename
498    
499    The name of the output file.
500    
501    =back
502    
503    =cut
504    
505    sub DisplayMetaData {
506        # Get the parameters.
507        my ($self) = @_;
508        # Get the metadata and the title string.
509        my $metadata = $self->{_metaData};
510        # Get the title string.
511        my $title = $metadata->{Title};
512        # Get the entity and relationship lists.
513        my $entityList = $metadata->{Entities};
514        my $relationshipList = $metadata->{Relationships};
515        # Declare the return variable.
516        my $retVal = "";
517        # Open the output file.
518        Trace("Building MetaData table of contents.") if T(4);
519      # 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
520      # section contains an ordered list of entity or relationship subsections.      # section contains an ordered list of entity or relationship subsections.
521      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";
522      # Loop through the Entities, displaying a list item for each.      # Loop through the Entities, displaying a list item for each.
523      foreach my $key (sort keys %{$entityList}) {      foreach my $key (sort keys %{$entityList}) {
524          # Display this item.          # Display this item.
525          print HTMLOUT "<li><a href=\"#$key\">$key</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$key</a></li>\n";
526      }      }
527      # Close off the entity section and start the relationship section.      # Close off the entity section and start the relationship section.
528      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";
529      # Loop through the Relationships.      # Loop through the Relationships.
530      foreach my $key (sort keys %{$relationshipList}) {      foreach my $key (sort keys %{$relationshipList}) {
531          # Display this item.          # Display this item.
532          my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});          my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});
533          print HTMLOUT "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";
534      }      }
535      # Close off the relationship section and list the join table section.      # Close off the relationship section and list the join table section.
536      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";
537      # Close off the table of contents itself.      # Close off the table of contents itself.
538      print HTMLOUT "</ul>\n";      $retVal .=  "</ul>\n";
539      # 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.
540      print HTMLOUT "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";      $retVal .= "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";
541      # Loop through the entities.      # Loop through the entities.
542      for my $key (sort keys %{$entityList}) {      for my $key (sort keys %{$entityList}) {
543          Trace("Building MetaData entry for $key entity.") if T(4);          Trace("Building MetaData entry for $key entity.") if T(4);
544          # Create the entity header. It contains a bookmark and the entity name.          # Create the entity header. It contains a bookmark and the entity name.
545          print HTMLOUT "<a name=\"$key\"></a><h3>$key</h3>\n";          $retVal .= "<a name=\"$key\"></a><h3>$key</h3>\n";
546          # Get the entity data.          # Get the entity data.
547          my $entityData = $entityList->{$key};          my $entityData = $entityList->{$key};
548          # If there's descriptive text, display it.          # If there's descriptive text, display it.
549          if (my $notes = $entityData->{Notes}) {          if (my $notes = $entityData->{Notes}) {
550              print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
551          }          }
552          # 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.
553          print HTMLOUT "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          my $relCount = keys %{$relationshipList};
554            if ($relCount > 0) {
555                # First, we set up the relationship subsection.
556                $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
557          # Loop through the relationships.          # Loop through the relationships.
558          for my $relationship (sort keys %{$relationshipList}) {          for my $relationship (sort keys %{$relationshipList}) {
559              # Get the relationship data.              # Get the relationship data.
# Line 460  Line 563 
563                  # Get the relationship sentence and append the arity.                  # Get the relationship sentence and append the arity.
564                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);
565                  # Display the relationship data.                  # Display the relationship data.
566                  print HTMLOUT "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";                      $retVal .= "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";
567              }              }
568          }          }
569          # Close off the relationship list.          # Close off the relationship list.
570          print HTMLOUT "</ul>\n";              $retVal .= "</ul>\n";
571            }
572          # Get the entity's relations.          # Get the entity's relations.
573          my $relationList = $entityData->{Relations};          my $relationList = $entityData->{Relations};
574          # Create a header for the relation subsection.          # Create a header for the relation subsection.
575          print HTMLOUT "<h4>Relations for <b>$key</b></h4>\n";          $retVal .= "<h4>Relations for <b>$key</b></h4>\n";
576          # Loop through the relations, displaying them.          # Loop through the relations, displaying them.
577          for my $relation (sort keys %{$relationList}) {          for my $relation (sort keys %{$relationList}) {
578              my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});              my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});
579              print HTMLOUT $htmlString;              $retVal .= $htmlString;
580          }          }
581      }      }
582      # Denote we're starting the relationship section.      # Denote we're starting the relationship section.
583      print HTMLOUT "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";      $retVal .= "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";
584      # Loop through the relationships.      # Loop through the relationships.
585      for my $key (sort keys %{$relationshipList}) {      for my $key (sort keys %{$relationshipList}) {
586          Trace("Building MetaData entry for $key relationship.") if T(4);          Trace("Building MetaData entry for $key relationship.") if T(4);
# Line 484  Line 588 
588          my $relationshipStructure = $relationshipList->{$key};          my $relationshipStructure = $relationshipList->{$key};
589          # Create the relationship header.          # Create the relationship header.
590          my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);          my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);
591          print HTMLOUT "<h3><a name=\"$key\"></a>$headerText</h3>\n";          $retVal .= "<h3><a name=\"$key\"></a>$headerText</h3>\n";
592          # Get the entity names.          # Get the entity names.
593          my $fromEntity = $relationshipStructure->{from};          my $fromEntity = $relationshipStructure->{from};
594          my $toEntity = $relationshipStructure->{to};          my $toEntity = $relationshipStructure->{to};
# Line 494  Line 598 
598          # since both sentences will say the same thing.          # since both sentences will say the same thing.
599          my $arity = $relationshipStructure->{arity};          my $arity = $relationshipStructure->{arity};
600          if ($arity eq "11") {          if ($arity eq "11") {
601              print HTMLOUT "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";
602          } else {          } else {
603              print HTMLOUT "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";
604              if ($arity eq "MM" && $fromEntity ne $toEntity) {              if ($arity eq "MM" && $fromEntity ne $toEntity) {
605                  print HTMLOUT "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";                  $retVal .= "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";
606              }              }
607          }          }
608          print HTMLOUT "</p>\n";          $retVal .= "</p>\n";
609          # If there are notes on this relationship, display them.          # If there are notes on this relationship, display them.
610          if (my $notes = $relationshipStructure->{Notes}) {          if (my $notes = $relationshipStructure->{Notes}) {
611              print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
612          }          }
613          # Generate the relationship's relation table.          # Generate the relationship's relation table.
614          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
615          print HTMLOUT $htmlString;          $retVal .= $htmlString;
616      }      }
617      Trace("Building MetaData join table.") if T(4);      Trace("Building MetaData join table.") if T(4);
618      # Denote we're starting the join table.      # Denote we're starting the join table.
619      print HTMLOUT "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";      $retVal .= "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";
620      # Create a table header.      # Create a table header.
621      print HTMLOUT _OpenTable("Join Table", "Source", "Target", "Join Condition");      $retVal .= _OpenTable("Join Table", "Source", "Target", "Join Condition");
622      # Loop through the joins.      # Loop through the joins.
623      my $joinTable = $metadata->{Joins};      my $joinTable = $metadata->{Joins};
624      my @joinKeys = keys %{$joinTable};      my @joinKeys = keys %{$joinTable};
# Line 527  Line 631 
631          my $target = $self->ComputeObjectSentence($targetRelation);          my $target = $self->ComputeObjectSentence($targetRelation);
632          my $clause = $joinTable->{$joinKey};          my $clause = $joinTable->{$joinKey};
633          # Display them in a table row.          # Display them in a table row.
634          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";
635      }      }
636      # Close the table.      # Close the table.
637      print HTMLOUT _CloseTable();      $retVal .= _CloseTable();
638      # Close the document.      Trace("Built MetaData HTML.") if T(3);
639      print HTMLOUT "</body>\n</html>\n";      # Return the HTML.
640      # Close the file.      return $retVal;
     close HTMLOUT;  
     Trace("Built MetaData web page.") if T(3);  
641  }  }
642    
643  =head3 DumpMetaData  =head3 DumpMetaData
# Line 553  Line 655 
655      return Data::Dumper::Dumper($self->{_metaData});      return Data::Dumper::Dumper($self->{_metaData});
656  }  }
657    
658    =head3 CreatePPO
659    
660    C<< ERDB::CreatePPO($erdbXMLFile, $ppoXMLFile); >>
661    
662    Create a PPO XML file from an ERDB data definition XML file. At the
663    current time, the PPO XML file can be used to create a database with
664    similar functionality. Eventually, the PPO will be able to use the
665    created XML to access the live ERDB database.
666    
667    =over 4
668    
669    =item erdbXMLFile
670    
671    Name of the XML data definition file for the ERDB database. This
672    file must exist.
673    
674    =item ppoXMLFile
675    
676    Output file for the PPO XML definition. If this file exists, it
677    will be overwritten.
678    
679    =back
680    
681    =cut
682    
683    sub CreatePPO {
684        # Get the parameters.
685        my ($erdbXMLFile, $ppoXMLFile) = @_;
686        # First, we want to slurp in the ERDB XML file in its raw form.
687        my $xml = ReadMetaXML($erdbXMLFile);
688        # Create a variable to hold all of the objects in the PPO project.
689        my @objects = ();
690        # Get the relationship hash.
691        my $relationships = $xml->{Relationships};
692        # Loop through the entities.
693        my $entities = $xml->{Entities};
694        for my $entityName (keys %{$entities}) {
695            # Get the entity's data structures.
696            my $entityObject = $entities->{$entityName};
697            # We put the object's fields in here, according to their type.
698            my (@object_refs, @scalars, @indexes, @arrays);
699            # Create the ID field for the entity. We get the key type from the
700            # entity object and compute the corresponding SQL type.
701            my $type = $TypeTable{$entityObject->{keyType}}->{sqlType};
702            push @scalars, { label => 'id', type => $type };
703            # Loop through the entity fields.
704            for my $fieldName ( keys %{$entityObject->{Fields}} ) {
705                # Get the field object.
706                my $fieldObject = $entityObject->{Fields}->{$fieldName};
707                # Convert it to a scalar tag.
708                my $scalar = _CreatePPOField($fieldName, $fieldObject);
709                # If we have a relation, this field is stored in an array.
710                # otherwise, it is a scalar. The array tag has scalars
711                # stored as an XML array. In ERDB, there is only ever one,
712                # but PPO can have more.
713                my $relation = $fieldObject->{relation};
714                if ($relation) {
715                    push @arrays, { scalar => [$scalar] };
716                } else {
717                    push @scalars, $scalar;
718                }
719            }
720            # Loop through the relationships. If this entity is the to-entity
721            # on a relationship of 1M arity, then it is implemented as a PPO
722            # object reference.
723            for my $relationshipName (keys %{$relationships}) {
724                # Get the relationship data.
725                my $relationshipData = $relationships->{$relationshipName};
726                # If we have a from for this entity and an arity of 1M, we
727                # have an object reference.
728                if ($relationshipData->{to} eq $entityName &&
729                    $relationshipData->{arity} eq '1M') {
730                    # Build the object reference tag.
731                    push @object_refs, { label => $relationshipName,
732                                         type => $relationshipData->{from} };
733                }
734            }
735            # Create the indexes.
736            my $indexList = $entityObject->{Indexes};
737            push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
738            # Build the object XML tree.
739            my $object = { label => $entityName,
740                           object_ref => \@object_refs,
741                           scalar => \@scalars,
742                           index => \@indexes,
743                           array => \@arrays
744                          };
745            # Push the object onto the objects list.
746            push @objects, $object;
747        }
748        # Loop through the relationships, searching for MMs. The 1Ms were
749        # already handled by the entity search above.
750        for my $relationshipName (keys %{$relationships}) {
751            # Get this relationship's object.
752            my $relationshipObject = $relationships->{$relationshipName};
753            # Only proceed if it's many-to-many.
754            if ($relationshipObject->{arity} eq 'MM') {
755                # Create the tag lists for the relationship object.
756                my (@object_refs, @scalars, @indexes);
757                # The relationship will be created as an object with object
758                # references for its links to the participating entities.
759                my %links = ( from => $relationshipObject->{from},
760                              to => $relationshipObject->{to} );
761                for my $link (keys %links) {
762                    # Create an object_ref tag for this piece of the
763                    # relationship (from or to).
764                    my $object_ref = { label => $link,
765                                       type => $links{$link} };
766                    push @object_refs, $object_ref;
767                }
768                # Loop through the intersection data fields, creating scalar tags.
769                # There are no fancy array tags in a relationship.
770                for my $fieldName (keys %{$relationshipObject->{Fields}}) {
771                    my $fieldObject = $relationshipObject->{Fields}->{$fieldName};
772                    push @scalars, _CreatePPOField($fieldName, $fieldObject);
773                }
774                # Finally, the indexes: currently we cannot support the to-index and
775                # from-index in PPO, so we just process the alternate indexes.
776                my $indexList = $relationshipObject->{Indexes};
777                push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
778                # Wrap up all the stuff about this relationship.
779                my $object = { label => $relationshipName,
780                               scalar => \@scalars,
781                               object_ref => \@object_refs,
782                               index => \@indexes
783                             };
784                # Push it into the object list.
785                push @objects, $object;
786            }
787        }
788        # Compute a title.
789        my $title;
790        if ($erdbXMLFile =~ /\/([^\/]+)DBD\.xml/) {
791            # Here we have a standard file name we can use for a title.
792            $title = $1;
793        } else {
794            # Here the file name is non-standard, so we carve up the
795            # database title.
796            $title = $xml->{Title}->{content};
797            $title =~ s/\s\.,//g;
798        }
799        # Wrap up the XML as a project.
800        my $ppoXML = { project => { label => $title,
801                                    object => \@objects }};
802        # Write out the results.
803        my $ppoString = XML::Simple::XMLout($ppoXML,
804                                            AttrIndent => 1,
805                                            KeepRoot => 1);
806        Tracer::PutFile($ppoXMLFile, [ $ppoString ]);
807    }
808    
809    
810    
811    =head3 FindIndexForEntity
812    
813    C<< my $indexFound = ERDB::FindIndexForEntity($xml, $entityName, $attributeName); >>
814    
815    This method locates the entry in an entity's index list that begins with the
816    specified attribute name. If the entity has no index list, one will be
817    created. This method works on raw XML, not a live ERDB object.
818    
819    =over 4
820    
821    =item xml
822    
823    The raw XML structure defining the database.
824    
825    =item entityName
826    
827    The name of the relevant entity.
828    
829    =item attributeName
830    
831    The name of the attribute relevant to the search.
832    
833    =item RETURN
834    
835    The numerical index in the index list of the index entry for the specified entity and
836    attribute, or C<undef> if no such index exists.
837    
838    =back
839    
840    =cut
841    
842    sub FindIndexForEntity {
843        # Get the parameters.
844        my ($xml, $entityName, $attributeName) = @_;
845        # Declare the return variable.
846        my $retVal;
847        # Get the named entity.
848        my $entityData = $xml->{Entities}->{$entityName};
849        if (! $entityData) {
850            Confess("Entity $entityName not found in DBD structure.");
851        } else {
852            # Insure it has an index list.
853            if (! exists $entityData->{Indexes}) {
854                $entityData->{Indexes} = [];
855            } else {
856                # Search for the desired index.
857                my $indexList = $entityData->{Indexes};
858                my $n = scalar @{$indexList};
859                Trace("Searching $n indexes in index list for $entityName.") if T(2);
860                # We use an indexed FOR here because we're returning an
861                # index number instead of an object. We do THAT so we can
862                # delete the index from the list if needed.
863                for (my $i = 0; $i < $n && !defined($retVal); $i++) {
864                    my $index = $indexList->[$i];
865                    my $fields = $index->{IndexFields};
866                    # Technically this IF should be safe (that is, we are guaranteed
867                    # the existence of a "$fields->[0]"), because when we load the XML
868                    # we have SuppressEmpty specified.
869                    if ($fields->[0]->{name} eq $attributeName) {
870                        $retVal = $i;
871                    }
872                }
873            }
874        }
875        Trace("Index for $attributeName of $entityName found at position $retVal.") if defined($retVal) && T(3);
876        Trace("Index for $attributeName not found in $entityName.") if !defined($retVal) && T(3);
877        # Return the result.
878        return $retVal;
879    }
880    
881  =head3 CreateTables  =head3 CreateTables
882    
883  C<< $erdb->CreateTables(); >>  C<< $erdb->CreateTables(); >>
# Line 572  Line 897 
897      # Loop through the relations.      # Loop through the relations.
898      for my $relationName (@relNames) {      for my $relationName (@relNames) {
899          # Create a table for this relation.          # Create a table for this relation.
900          $self->CreateTable($relationName);          $self->CreateTable($relationName, 1);
901          Trace("Relation $relationName created.") if T(2);          Trace("Relation $relationName created.") if T(2);
902      }      }
903  }  }
# Line 640  Line 965 
965      Trace("Creating table $relationName: $fieldThing") if T(2);      Trace("Creating table $relationName: $fieldThing") if T(2);
966      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);
967      Trace("Relation $relationName created in database.") if T(2);      Trace("Relation $relationName created in database.") if T(2);
968      # If we want to build the indexes, we do it here.      # If we want to build the indexes, we do it here. Note that the full-text search
969        # index will not be built until the table has been loaded.
970      if ($indexFlag) {      if ($indexFlag) {
971          $self->CreateIndex($relationName);          $self->CreateIndex($relationName);
972      }      }
# Line 736  Line 1062 
1062          my $fieldType = $fieldTypes->[$i]->{type};          my $fieldType = $fieldTypes->[$i]->{type};
1063          # If it's a hash string, digest it in place.          # If it's a hash string, digest it in place.
1064          if ($fieldType eq 'hash-string') {          if ($fieldType eq 'hash-string') {
1065              $fieldList->[$i] = md5_base64($fieldList->[$i]);              $fieldList->[$i] = $self->DigestKey($fieldList->[$i]);
1066            }
1067          }          }
1068      }      }
1069    
1070    =head3 DigestKey
1071    
1072    C<< my $digested = $erdb->DigestKey($keyValue); >>
1073    
1074    Return the digested value of a symbolic key. The digested value can then be plugged into a
1075    key-based search into a table with key-type hash-string.
1076    
1077    Currently the digesting process is independent of the database structure, but that may not
1078    always be the case, so this is an instance method instead of a static method.
1079    
1080    =over 4
1081    
1082    =item keyValue
1083    
1084    Key value to digest.
1085    
1086    =item RETURN
1087    
1088    Digested value of the key.
1089    
1090    =back
1091    
1092    =cut
1093    
1094    sub DigestKey {
1095        # Get the parameters.
1096        my ($self, $keyValue) = @_;
1097        # Compute the digest.
1098        my $retVal = md5_base64($keyValue);
1099        # Return the result.
1100        return $retVal;
1101  }  }
1102    
1103  =head3 CreateIndex  =head3 CreateIndex
# Line 764  Line 1123 
1123      for my $indexName (keys %{$indexHash}) {      for my $indexName (keys %{$indexHash}) {
1124          my $indexData = $indexHash->{$indexName};          my $indexData = $indexHash->{$indexName};
1125          # Get the index's field list.          # Get the index's field list.
1126          my @fieldList = _FixNames(@{$indexData->{IndexFields}});          my @rawFields = @{$indexData->{IndexFields}};
1127            # Get a hash of the relation's field types.
1128            my %types = map { $_->{name} => $_->{type} } @{$relationData->{Fields}};
1129            # We need to check for text fields so we can append a length limitation for them. To do
1130            # that, we need the relation's field list.
1131            my $relFields = $relationData->{Fields};
1132            for (my $i = 0; $i <= $#rawFields; $i++) {
1133                # Get the field type.
1134                my $field = $rawFields[$i];
1135                my $type = $types{$field};
1136                # Ask if it requires using prefix notation for the index.
1137                my $mod = $TypeTable{$type}->{indexMod};
1138                Trace("Field $field ($i) in $relationName has type $type and indexMod $mod.") if T(3);
1139                if ($mod) {
1140                    # Append the prefix length to the field name,
1141                    $rawFields[$i] .= "($mod)";
1142                }
1143            }
1144            my @fieldList = _FixNames(@rawFields);
1145          my $flds = join(', ', @fieldList);          my $flds = join(', ', @fieldList);
1146          # Get the index's uniqueness flag.          # Get the index's uniqueness flag.
1147          my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
1148          # Create the index.          # Create the index.
1149          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
1150                                      flds => $flds, unique => $unique);                                      flds => $flds, kind => $unique);
1151          if ($rv) {          if ($rv) {
1152              Trace("Index created: $indexName for $relationName ($flds)") if T(1);              Trace("Index created: $indexName for $relationName ($flds)") if T(1);
1153          } else {          } else {
# Line 779  Line 1156 
1156      }      }
1157  }  }
1158    
1159    =head3 GetSecondaryFields
1160    
1161    C<< my %fieldTuples = $erdb->GetSecondaryFields($entityName); >>
1162    
1163    This method will return a list of the name and type of each of the secondary
1164    fields for a specified entity. Secondary fields are stored in two-column tables
1165    in addition to the primary entity table. This enables the field to have no value
1166    or to have multiple values.
1167    
1168    =over 4
1169    
1170    =item entityName
1171    
1172    Name of the entity whose secondary fields are desired.
1173    
1174    =item RETURN
1175    
1176    Returns a hash mapping the field names to their field types.
1177    
1178    =back
1179    
1180    =cut
1181    
1182    sub GetSecondaryFields {
1183        # Get the parameters.
1184        my ($self, $entityName) = @_;
1185        # Declare the return variable.
1186        my %retVal = ();
1187        # Look for the entity.
1188        my $table = $self->GetFieldTable($entityName);
1189        # Loop through the fields, pulling out the secondaries.
1190        for my $field (sort keys %{$table}) {
1191            if ($table->{$field}->{relation} ne $entityName) {
1192                # Here we have a secondary field.
1193                $retVal{$field} = $table->{$field}->{type};
1194            }
1195        }
1196        # Return the result.
1197        return %retVal;
1198    }
1199    
1200    =head3 GetFieldRelationName
1201    
1202    C<< my $name = $erdb->GetFieldRelationName($objectName, $fieldName); >>
1203    
1204    Return the name of the relation containing a specified field.
1205    
1206    =over 4
1207    
1208    =item objectName
1209    
1210    Name of the entity or relationship containing the field.
1211    
1212    =item fieldName
1213    
1214    Name of the relevant field in that entity or relationship.
1215    
1216    =item RETURN
1217    
1218    Returns the name of the database relation containing the field, or C<undef> if
1219    the field does not exist.
1220    
1221    =back
1222    
1223    =cut
1224    
1225    sub GetFieldRelationName {
1226        # Get the parameters.
1227        my ($self, $objectName, $fieldName) = @_;
1228        # Declare the return variable.
1229        my $retVal;
1230        # Get the object field table.
1231        my $table = $self->GetFieldTable($objectName);
1232        # Only proceed if the field exists.
1233        if (exists $table->{$fieldName}) {
1234            # Determine the name of the relation that contains this field.
1235            $retVal = $table->{$fieldName}->{relation};
1236        }
1237        # Return the result.
1238        return $retVal;
1239    }
1240    
1241    =head3 DeleteValue
1242    
1243    C<< my $numDeleted = $erdb->DeleteValue($entityName, $id, $fieldName, $fieldValue); >>
1244    
1245    Delete secondary field values from the database. This method can be used to delete all
1246    values of a specified field for a particular entity instance, or only a single value.
1247    
1248    Secondary fields are stored in two-column relations separate from an entity's primary
1249    table, and as a result a secondary field can legitimately have no value or multiple
1250    values. Therefore, it makes sense to talk about deleting secondary fields where it
1251    would not make sense for primary fields.
1252    
1253    =over 4
1254    
1255    =item entityName
1256    
1257    Name of the entity from which the fields are to be deleted.
1258    
1259    =item id
1260    
1261    ID of the entity instance to be processed. If the instance is not found, this
1262    method will have no effect. If C<undef> is specified, all values for all of
1263    the entity instances will be deleted.
1264    
1265    =item fieldName
1266    
1267    Name of the field whose values are to be deleted.
1268    
1269    =item fieldValue (optional)
1270    
1271    Value to be deleted. If not specified, then all values of the specified field
1272    will be deleted for the entity instance. If specified, then only the values which
1273    match this parameter will be deleted.
1274    
1275    =item RETURN
1276    
1277    Returns the number of rows deleted.
1278    
1279    =back
1280    
1281    =cut
1282    
1283    sub DeleteValue {
1284        # Get the parameters.
1285        my ($self, $entityName, $id, $fieldName, $fieldValue) = @_;
1286        # Declare the return value.
1287        my $retVal = 0;
1288        # We need to set up an SQL command to do the deletion. First, we
1289        # find the name of the field's relation.
1290        my $table = $self->GetFieldTable($entityName);
1291        my $field = $table->{$fieldName};
1292        my $relation = $field->{relation};
1293        # Make sure this is a secondary field.
1294        if ($relation eq $entityName) {
1295            Confess("Cannot delete values of $fieldName for $entityName.");
1296        } else {
1297            # Set up the SQL command to delete all values.
1298            my $sql = "DELETE FROM $relation";
1299            # Build the filter.
1300            my @filters = ();
1301            my @parms = ();
1302            # Check for a filter by ID.
1303            if (defined $id) {
1304                push @filters, "id = ?";
1305                push @parms, $id;
1306            }
1307            # Check for a filter by value.
1308            if (defined $fieldValue) {
1309                push @filters, "$fieldName = ?";
1310                push @parms, $fieldValue;
1311            }
1312            # Append the filters to the command.
1313            if (@filters) {
1314                $sql .= " WHERE " . join(" AND ", @filters);
1315            }
1316            # Execute the command.
1317            my $dbh = $self->{_dbh};
1318            $retVal = $dbh->SQL($sql, 0, @parms);
1319        }
1320        # Return the result.
1321        return $retVal;
1322    }
1323    
1324  =head3 LoadTables  =head3 LoadTables
1325    
1326  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>
# Line 873  Line 1415 
1415      return sort keys %{$entityList};      return sort keys %{$entityList};
1416  }  }
1417    
1418    =head3 GetDataTypes
1419    
1420    C<< my %types = ERDB::GetDataTypes(); >>
1421    
1422    Return a table of ERDB data types. The table returned is a hash of hashes.
1423    The keys of the big hash are the datatypes. Each smaller hash has several
1424    values used to manage the data. The most interesting is the SQL type (key
1425    C<sqlType>) and the descriptive node (key C<notes>).
1426    
1427    Note that changing the values in the smaller hashes will seriously break
1428    things, so this data should be treated as read-only.
1429    
1430    =cut
1431    
1432    sub GetDataTypes {
1433        return %TypeTable;
1434    }
1435    
1436    
1437  =head3 IsEntity  =head3 IsEntity
1438    
1439  C<< my $flag = $erdb->IsEntity($entityName); >>  C<< my $flag = $erdb->IsEntity($entityName); >>
# Line 902  Line 1463 
1463    
1464  =head3 Get  =head3 Get
1465    
1466  C<< my $query = $erdb->Get(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  C<< my $query = $erdb->Get(\@objectNames, $filterClause, \@params); >>
1467    
1468  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.
1469  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 1471 
1471  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
1472  $genus.  $genus.
1473    
1474  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", [$genus]); >>
1475    
1476  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
1477  parameter representing the parameter value. It would also be possible to code  parameter representing the parameter value. It would also be possible to code
# Line 927  Line 1488 
1488  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
1489  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,
1490    
1491  C<< $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]); >>
1492    
1493  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
1494  join path between the entities and relationships. The algorithm used is very simplistic.  join path between the entities and relationships. The algorithm used is very simplistic.
# Line 984  Line 1545 
1545    
1546  C<< "LIMIT 10" >>  C<< "LIMIT 10" >>
1547    
1548  =item param1, param2, ..., paramN  =item params
1549    
1550  Parameter values to be substituted into the filter clause.  Reference to a list of parameter values to be substituted into the filter clause.
1551    
1552  =item RETURN  =item RETURN
1553    
# Line 998  Line 1559 
1559    
1560  sub Get {  sub Get {
1561      # Get the parameters.      # Get the parameters.
1562      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $objectNames, $filterClause, $params) = @_;
1563      # Adjust the list of object names to account for multiple occurrences of the      # Process the SQL stuff.
1564      # same object. We start with a hash table keyed on object name that will      my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1565      # return the object suffix. The first time an object is encountered it will          $self->_SetupSQL($objectNames, $filterClause);
1566      # not be found in the hash. The next time the hash will map the object name      # Create the query.
1567      # to 2, then 3, and so forth.      my $command = "SELECT DISTINCT " . join(".*, ", @{$mappedNameListRef}) .
1568      my %objectHash = ();          ".* $suffix";
1569      # This list will contain the object names as they are to appear in the      my $sth = $self->_GetStatementHandle($command, $params);
1570      # FROM list.      # Now we create the relation map, which enables DBQuery to determine the order, name
1571      my @fromList = ();      # and mapped name for each object in the query.
1572      # This list contains the suffixed object name for each object. It is exactly      my @relationMap = ();
1573      # parallel to the list in the $objectNames parameter.      for my $mappedName (@{$mappedNameListRef}) {
1574      my @mappedNameList = ();          push @relationMap, [$mappedName, $mappedNameHashRef->{$mappedName}];
1575      # Finally, this hash translates from a mapped name to its original object name.      }
1576      my %mappedNameHash = ();      # Return the statement object.
1577      # Now we create the lists. Note that for every single name we push something into      my $retVal = DBQuery::_new($self, $sth, \@relationMap);
1578      # @fromList and @mappedNameList. This insures that those two arrays are exactly      return $retVal;
1579      # parallel to $objectNames.  }
1580      for my $objectName (@{$objectNames}) {  
1581          # Get the next suffix for this object.  
1582          my $suffix = $objectHash{$objectName};  
1583          if (! $suffix) {  =head3 Search
1584              # Here we are seeing the object for the first time. The object name  
1585              # is used as is.  C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>
1586              push @mappedNameList, $objectName;  
1587              push @fromList, $objectName;  Perform a full text search with filtering. The search will be against a specified object
1588              $mappedNameHash{$objectName} = $objectName;  in the object name list. That object will get an extra field containing the search
1589              # Denote the next suffix will be 2.  relevance. Note that except for the search expression, the parameters of this method are
1590              $objectHash{$objectName} = 2;  the same as those for L</Get> and follow the same rules.
1591    
1592    =over 4
1593    
1594    =item searchExpression
1595    
1596    Boolean search expression for the text fields of the target object. The default mode for
1597    a Boolean search expression is OR, but we want the default to be AND, so we will
1598    add a C<+> operator to each word with no other operator before it.
1599    
1600    =item idx
1601    
1602    Index in the I<$objectNames> list of the table to be searched in full-text mode.
1603    
1604    =item objectNames
1605    
1606    List containing the names of the entity and relationship objects to be retrieved.
1607    
1608    =item filterClause
1609    
1610    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1611    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
1612    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
1613    in the filter clause should be added to the parameter list as additional parameters. The
1614    fields in a filter clause can come from primary entity relations, relationship relations,
1615    or secondary entity relations; however, all of the entities and relationships involved must
1616    be included in the list of object names.
1617    
1618    =item params
1619    
1620    Reference to a list of parameter values to be substituted into the filter clause.
1621    
1622    =item RETURN
1623    
1624    Returns a query object for the specified search.
1625    
1626    =back
1627    
1628    =cut
1629    
1630    sub Search {
1631        # Get the parameters.
1632        my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1633        # Declare the return variable.
1634        my $retVal;
1635        # Create a safety copy of the parameter list. Note we have to be careful to insure
1636        # a parameter list exists before we copy it.
1637        my @myParams = ();
1638        if (defined $params) {
1639            @myParams = @{$params};
1640        }
1641        # Get the first object's structure so we have access to the searchable fields.
1642        my $object1Name = $objectNames->[$idx];
1643        my $object1Structure = $self->_GetStructure($object1Name);
1644        # Get the field list.
1645        if (! exists $object1Structure->{searchFields}) {
1646            Confess("No searchable index for $object1Name.");
1647        } else {
1648            # Get the field list.
1649            my @fields = @{$object1Structure->{searchFields}};
1650            # Clean the search expression.
1651            my $actualKeywords = $self->CleanKeywords($searchExpression);
1652            # Prefix a "+" to each uncontrolled word. This converts the default
1653            # search mode from OR to AND.
1654            $actualKeywords =~ s/(^|\s)(\w|")/$1\+$2/g;
1655            Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1656            # We need two match expressions, one for the filter clause and one in the
1657            # query itself. Both will use a parameter mark, so we need to push the
1658            # search expression onto the front of the parameter list twice.
1659            unshift @myParams, $actualKeywords, $actualKeywords;
1660            # Build the match expression.
1661            my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
1662            my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
1663            # Process the SQL stuff.
1664            my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1665                $self->_SetupSQL($objectNames, $filterClause, $matchClause);
1666            # Create the query. Note that the match clause is inserted at the front of
1667            # the select fields.
1668            my $command = "SELECT DISTINCT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .
1669                ".* $suffix";
1670            my $sth = $self->_GetStatementHandle($command, \@myParams);
1671            # Now we create the relation map, which enables DBQuery to determine the order, name
1672            # and mapped name for each object in the query.
1673            my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
1674            # Return the statement object.
1675            $retVal = DBQuery::_new($self, $sth, \@relationMap, $object1Name);
1676        }
1677        return $retVal;
1678    }
1679    
1680    =head3 GetFlat
1681    
1682    C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>
1683    
1684    This is a variation of L</GetAll> that asks for only a single field per record and
1685    returns a single flattened list.
1686    
1687    =over 4
1688    
1689    =item objectNames
1690    
1691    List containing the names of the entity and relationship objects to be retrieved.
1692    
1693    =item filterClause
1694    
1695    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1696    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
1697    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
1698    parameter list as additional parameters. The fields in a filter clause can come from primary
1699    entity relations, relationship relations, or secondary entity relations; however, all of the
1700    entities and relationships involved must be included in the list of object names.
1701    
1702    =item parameterList
1703    
1704    List of the parameters to be substituted in for the parameters marks in the filter clause.
1705    
1706    =item field
1707    
1708    Name of the field to be used to get the elements of the list returned.
1709    
1710    =item RETURN
1711    
1712    Returns a list of values.
1713    
1714    =back
1715    
1716    =cut
1717    #: Return Type @;
1718    sub GetFlat {
1719        # Get the parameters.
1720        my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
1721        # Construct the query.
1722        my $query = $self->Get($objectNames, $filterClause, $parameterList);
1723        # Create the result list.
1724        my @retVal = ();
1725        # Loop through the records, adding the field values found to the result list.
1726        while (my $row = $query->Fetch()) {
1727            push @retVal, $row->Value($field);
1728        }
1729        # Return the list created.
1730        return @retVal;
1731    }
1732    
1733    =head3 SpecialFields
1734    
1735    C<< my %specials = $erdb->SpecialFields($entityName); >>
1736    
1737    Return a hash mapping special fields in the specified entity to the value of their
1738    C<special> attribute. This enables the subclass to get access to the special field
1739    attributes without needed to plumb the internal ERDB data structures.
1740    
1741    =over 4
1742    
1743    =item entityName
1744    
1745    Name of the entity whose special fields are desired.
1746    
1747    =item RETURN
1748    
1749    Returns a hash. The keys of the hash are the special field names, and the values
1750    are the values from each special field's C<special> attribute.
1751    
1752    =back
1753    
1754    =cut
1755    
1756    sub SpecialFields {
1757        # Get the parameters.
1758        my ($self, $entityName) = @_;
1759        # Declare the return variable.
1760        my %retVal = ();
1761        # Find the entity's data structure.
1762        my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1763        # Loop through its fields, adding each special field to the return hash.
1764        my $fieldHash = $entityData->{Fields};
1765        for my $fieldName (keys %{$fieldHash}) {
1766            my $fieldData = $fieldHash->{$fieldName};
1767            if (exists $fieldData->{special}) {
1768                $retVal{$fieldName} = $fieldData->{special};
1769            }
1770        }
1771        # Return the result.
1772        return %retVal;
1773    }
1774    
1775    =head3 Delete
1776    
1777    C<< my $stats = $erdb->Delete($entityName, $objectID, %options); >>
1778    
1779    Delete an entity instance from the database. The instance is deleted along with all entity and
1780    relationship instances dependent on it. The definition of I<dependence> is recursive.
1781    
1782    An object is always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many
1783    relationship connected to a dependent entity or if it is the "to" entity connected to a 1-to-many
1784    dependent relationship.
1785    
1786    =over 4
1787    
1788    =item entityName
1789    
1790    Name of the entity type for the instance being deleted.
1791    
1792    =item objectID
1793    
1794    ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),
1795    then it is presumed to by a LIKE pattern.
1796    
1797    =item options
1798    
1799    A hash detailing the options for this delete operation.
1800    
1801    =item RETURN
1802    
1803    Returns a statistics object indicating how many records of each particular table were
1804    deleted.
1805    
1806    =back
1807    
1808    The permissible options for this method are as follows.
1809    
1810    =over 4
1811    
1812    =item testMode
1813    
1814    If TRUE, then the delete statements will be traced, but no changes will be made to the database.
1815    
1816    =item keepRoot
1817    
1818    If TRUE, then the entity instances will not be deleted, only the dependent records.
1819    
1820    =back
1821    
1822    =cut
1823    #: Return Type $%;
1824    sub Delete {
1825        # Get the parameters.
1826        my ($self, $entityName, $objectID, %options) = @_;
1827        # Declare the return variable.
1828        my $retVal = Stats->new();
1829        # Get the DBKernel object.
1830        my $db = $self->{_dbh};
1831        # We're going to generate all the paths branching out from the starting entity. One of
1832        # the things we have to be careful about is preventing loops. We'll use a hash to
1833        # determine if we've hit a loop.
1834        my %alreadyFound = ();
1835        # These next lists will serve as our result stack. We start by pushing object lists onto
1836        # the stack, and then popping them off to do the deletes. This means the deletes will
1837        # start with the longer paths before getting to the shorter ones. That, in turn, makes
1838        # sure we don't delete records that might be needed to forge relationships back to the
1839        # original item. We have two lists-- one for TO-relationships, and one for
1840        # FROM-relationships and entities.
1841        my @fromPathList = ();
1842        my @toPathList = ();
1843        # This final list is used to remember what work still needs to be done. We push paths
1844        # onto the list, then pop them off to extend the paths. We prime it with the starting
1845        # point. Note that we will work hard to insure that the last item on a path in the
1846        # to-do list is always an entity.
1847        my @todoList = ([$entityName]);
1848        while (@todoList) {
1849            # Get the current path.
1850            my $current = pop @todoList;
1851            # Copy it into a list.
1852            my @stackedPath = @{$current};
1853            # Pull off the last item on the path. It will always be an entity.
1854            my $myEntityName = pop @stackedPath;
1855            # Add it to the alreadyFound list.
1856            $alreadyFound{$myEntityName} = 1;
1857            # Figure out if we need to delete this entity.
1858            if ($myEntityName ne $entityName || ! $options{keepRoot}) {
1859                # Get the entity data.
1860                my $entityData = $self->_GetStructure($myEntityName);
1861                # Loop through the entity's relations. A DELETE command will be needed for each of them.
1862                my $relations = $entityData->{Relations};
1863                for my $relation (keys %{$relations}) {
1864                    my @augmentedList = (@stackedPath, $relation);
1865                    push @fromPathList, \@augmentedList;
1866                }
1867            }
1868            # Now we need to look for relationships connected to this entity.
1869            my $relationshipList = $self->{_metaData}->{Relationships};
1870            for my $relationshipName (keys %{$relationshipList}) {
1871                my $relationship = $relationshipList->{$relationshipName};
1872                # Check the FROM field. We're only interested if it's us.
1873                if ($relationship->{from} eq $myEntityName) {
1874                    # Add the path to this relationship.
1875                    my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1876                    push @fromPathList, \@augmentedList;
1877                    # Check the arity. If it's MM we're done. If it's 1M
1878                    # and the target hasn't been seen yet, we want to
1879                    # stack the entity for future processing.
1880                    if ($relationship->{arity} eq '1M') {
1881                        my $toEntity = $relationship->{to};
1882                        if (! exists $alreadyFound{$toEntity}) {
1883                            # Here we have a new entity that's dependent on
1884                            # the current entity, so we need to stack it.
1885                            my @stackList = (@augmentedList, $toEntity);
1886                            push @fromPathList, \@stackList;
1887                        } else {
1888                            Trace("$toEntity ignored because it occurred previously.") if T(4);
1889                        }
1890                    }
1891                }
1892                # Now check the TO field. In this case only the relationship needs
1893                # deletion.
1894                if ($relationship->{to} eq $myEntityName) {
1895                    my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1896                    push @toPathList, \@augmentedList;
1897                }
1898            }
1899        }
1900        # Create the first qualifier for the WHERE clause. This selects the
1901        # keys of the primary entity records to be deleted. When we're deleting
1902        # from a dependent table, we construct a join path from the first qualifier
1903        # to the table containing the dependent records to delete.
1904        my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
1905        # We need to make two passes. The first is through the to-list, and
1906        # the second through the from-list. The from-list is second because
1907        # the to-list may need to pass through some of the entities the
1908        # from-list would delete.
1909        my %stackList = ( from_link => \@fromPathList, to_link => \@toPathList );
1910        # Now it's time to do the deletes. We do it in two passes.
1911        for my $keyName ('to_link', 'from_link') {
1912            # Get the list for this key.
1913            my @pathList = @{$stackList{$keyName}};
1914            Trace(scalar(@pathList) . " entries in path list for $keyName.") if T(3);
1915            # Loop through this list.
1916            while (my $path = pop @pathList) {
1917                # Get the table whose rows are to be deleted.
1918                my @pathTables = @{$path};
1919                # Start the DELETE statement. We need to call DBKernel because the
1920                # syntax of a DELETE-USING varies among DBMSs.
1921                my $target = $pathTables[$#pathTables];
1922                my $stmt = $db->SetUsing(@pathTables);
1923                # Now start the WHERE. The first thing is the ID field from the starting table. That
1924                # starting table will either be the entity relation or one of the entity's
1925                # sub-relations.
1926                $stmt .= " WHERE $pathTables[0].id $qualifier";
1927                # Now we run through the remaining entities in the path, connecting them up.
1928                for (my $i = 1; $i <= $#pathTables; $i += 2) {
1929                    # Connect the current relationship to the preceding entity.
1930                    my ($entity, $rel) = @pathTables[$i-1,$i];
1931                    # The style of connection depends on the direction of the relationship.
1932                    $stmt .= " AND $entity.id = $rel.$keyName";
1933                    if ($i + 1 <= $#pathTables) {
1934                        # Here there's a next entity, so connect that to the relationship's
1935                        # to-link.
1936                        my $entity2 = $pathTables[$i+1];
1937                        $stmt .= " AND $rel.to_link = $entity2.id";
1938                    }
1939                }
1940                # Now we have our desired DELETE statement.
1941                if ($options{testMode}) {
1942                    # Here the user wants to trace without executing.
1943                    Trace($stmt) if T(0);
1944                } else {
1945                    # Here we can delete. Note that the SQL method dies with a confession
1946                    # if an error occurs, so we just go ahead and do it.
1947                    Trace("Executing delete from $target using '$objectID'.") if T(3);
1948                    my $rv = $db->SQL($stmt, 0, $objectID);
1949                    # Accumulate the statistics for this delete. The only rows deleted
1950                    # are from the target table, so we use its name to record the
1951                    # statistic.
1952                    $retVal->Add($target, $rv);
1953                }
1954            }
1955        }
1956        # Return the result.
1957        return $retVal;
1958    }
1959    
1960    =head3 Disconnect
1961    
1962    C<< $erdb->Disconnect($relationshipName, $originEntityName, $originEntityID); >>
1963    
1964    Disconnect an entity instance from all the objects to which it is related. This
1965    will delete each relationship instance that connects to the specified entity.
1966    
1967    =over 4
1968    
1969    =item relationshipName
1970    
1971    Name of the relationship whose instances are to be deleted.
1972    
1973    =item originEntityName
1974    
1975    Name of the entity that is to be disconnected.
1976    
1977    =item originEntityID
1978    
1979    ID of the entity that is to be disconnected.
1980    
1981    =back
1982    
1983    =cut
1984    
1985    sub Disconnect {
1986        # Get the parameters.
1987        my ($self, $relationshipName, $originEntityName, $originEntityID) = @_;
1988        # Get the relationship descriptor.
1989        my $structure = $self->_GetStructure($relationshipName);
1990        # Insure we have a relationship.
1991        if (! exists $structure->{from}) {
1992            Confess("$relationshipName is not a relationship in the database.");
1993        } else {
1994            # Get the database handle.
1995            my $dbh = $self->{_dbh};
1996            # We'll set this value to 1 if we find our entity.
1997            my $found = 0;
1998            # Loop through the ends of the relationship.
1999            for my $dir ('from', 'to') {
2000                if ($structure->{$dir} eq $originEntityName) {
2001                    # Delete all relationship instances on this side of the entity instance.
2002                    Trace("Disconnecting in $dir direction with ID \"$originEntityID\".");
2003                    $dbh->SQL("DELETE FROM $relationshipName WHERE ${dir}_link = ?", 0, $originEntityID);
2004                    $found = 1;
2005                }
2006            }
2007            # Insure we found the entity on at least one end.
2008            if (! $found) {
2009                Confess("Entity \"$originEntityName\" does not use $relationshipName.");
2010            }
2011        }
2012    }
2013    
2014    =head3 DeleteRow
2015    
2016    C<< $erdb->DeleteRow($relationshipName, $fromLink, $toLink, \%values); >>
2017    
2018    Delete a row from a relationship. In most cases, only the from-link and to-link are
2019    needed; however, for relationships with intersection data values can be specified
2020    for the other fields using a hash.
2021    
2022    =over 4
2023    
2024    =item relationshipName
2025    
2026    Name of the relationship from which the row is to be deleted.
2027    
2028    =item fromLink
2029    
2030    ID of the entity instance in the From direction.
2031    
2032    =item toLink
2033    
2034    ID of the entity instance in the To direction.
2035    
2036    =item values
2037    
2038    Reference to a hash of other values to be used for filtering the delete.
2039    
2040    =back
2041    
2042    =cut
2043    
2044    sub DeleteRow {
2045        # Get the parameters.
2046        my ($self, $relationshipName, $fromLink, $toLink, $values) = @_;
2047        # Create a hash of all the filter information.
2048        my %filter = ('from-link' => $fromLink, 'to-link' => $toLink);
2049        if (defined $values) {
2050            for my $key (keys %{$values}) {
2051                $filter{$key} = $values->{$key};
2052            }
2053        }
2054        # Build an SQL statement out of the hash.
2055        my @filters = ();
2056        my @parms = ();
2057        for my $key (keys %filter) {
2058            push @filters, _FixName($key) . " = ?";
2059            push @parms, $filter{$key};
2060        }
2061        Trace("Parms for delete row are " . join(", ", map { "\"$_\"" } @parms) . ".") if T(SQL => 4);
2062        my $command = "DELETE FROM $relationshipName WHERE " .
2063                      join(" AND ", @filters);
2064        # Execute it.
2065        my $dbh = $self->{_dbh};
2066        $dbh->SQL($command, undef, @parms);
2067    }
2068    
2069    =head3 SortNeeded
2070    
2071    C<< my $parms = $erdb->SortNeeded($relationName); >>
2072    
2073    Return the pipe command for the sort that should be applied to the specified
2074    relation when creating the load file.
2075    
2076    For example, if the load file should be sorted ascending by the first
2077    field, this method would return
2078    
2079        sort -k1 -t"\t"
2080    
2081    If the first field is numeric, the method would return
2082    
2083        sort -k1n -t"\t"
2084    
2085    Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate
2086    keys using a sort.
2087    
2088    =over 4
2089    
2090    =item relationName
2091    
2092    Name of the relation to be examined.
2093    
2094    =item
2095    
2096    Returns the sort command to use for sorting the relation, suitable for piping.
2097    
2098    =back
2099    
2100    =cut
2101    #: Return Type $;
2102    sub SortNeeded {
2103        # Get the parameters.
2104        my ($self, $relationName) = @_;
2105        # Declare a descriptor to hold the names of the key fields.
2106        my @keyNames = ();
2107        # Get the relation structure.
2108        my $relationData = $self->_FindRelation($relationName);
2109        # Find out if the relation is a primary entity relation,
2110        # a relationship relation, or a secondary entity relation.
2111        my $entityTable = $self->{_metaData}->{Entities};
2112        my $relationshipTable = $self->{_metaData}->{Relationships};
2113        if (exists $entityTable->{$relationName}) {
2114            # Here we have a primary entity relation.
2115            push @keyNames, "id";
2116        } elsif (exists $relationshipTable->{$relationName}) {
2117            # Here we have a relationship. We sort using the FROM index.
2118            my $relationshipData = $relationshipTable->{$relationName};
2119            my $index = $relationData->{Indexes}->{idxFrom};
2120            push @keyNames, @{$index->{IndexFields}};
2121        } else {
2122            # Here we have a secondary entity relation, so we have a sort on the ID field.
2123            push @keyNames, "id";
2124        }
2125        # Now we parse the key names into sort parameters. First, we prime the return
2126        # string.
2127        my $retVal = "sort -t\"\t\" ";
2128        # Get the relation's field list.
2129        my @fields = @{$relationData->{Fields}};
2130        # Loop through the keys.
2131        for my $keyData (@keyNames) {
2132            # Get the key and the ordering.
2133            my ($keyName, $ordering);
2134            if ($keyData =~ /^([^ ]+) DESC/) {
2135                ($keyName, $ordering) = ($1, "descending");
2136            } else {
2137                ($keyName, $ordering) = ($keyData, "ascending");
2138            }
2139            # Find the key's position and type.
2140            my $fieldSpec;
2141            for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {
2142                my $thisField = $fields[$i];
2143                if ($thisField->{name} eq $keyName) {
2144                    # Get the sort modifier for this field type. The modifier
2145                    # decides whether we're using a character, numeric, or
2146                    # floating-point sort.
2147                    my $modifier = $TypeTable{$thisField->{type}}->{sort};
2148                    # If the index is descending for this field, denote we want
2149                    # to reverse the sort order on this field.
2150                    if ($ordering eq 'descending') {
2151                        $modifier .= "r";
2152                    }
2153                    # Store the position and modifier into the field spec, which
2154                    # will stop the inner loop. Note that the field number is
2155                    # 1-based in the sort command, so we have to increment the
2156                    # index.
2157                    $fieldSpec = ($i + 1) . $modifier;
2158                }
2159            }
2160            # Add this field to the sort command.
2161            $retVal .= " -k$fieldSpec";
2162        }
2163        # Return the result.
2164        return $retVal;
2165    }
2166    
2167    =head3 GetList
2168    
2169    C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>
2170    
2171    Return a list of object descriptors for the specified objects as determined by the
2172    specified filter clause.
2173    
2174    This method is essentially the same as L</Get> except it returns a list of objects rather
2175    than a query object that can be used to get the results one record at a time.
2176    
2177    =over 4
2178    
2179    =item objectNames
2180    
2181    List containing the names of the entity and relationship objects to be retrieved.
2182    
2183    =item filterClause
2184    
2185    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
2186    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
2187    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
2188    in the filter clause should be added to the parameter list as additional parameters. The
2189    fields in a filter clause can come from primary entity relations, relationship relations,
2190    or secondary entity relations; however, all of the entities and relationships involved must
2191    be included in the list of object names.
2192    
2193    The filter clause can also specify a sort order. To do this, simply follow the filter string
2194    with an ORDER BY clause. For example, the following filter string gets all genomes for a
2195    particular genus and sorts them by species name.
2196    
2197    C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
2198    
2199    The rules for field references in a sort order are the same as those for field references in the
2200    filter clause in general; however, odd things may happen if a sort field is from a secondary
2201    relation.
2202    
2203    =item params
2204    
2205    Reference to a list of parameter values to be substituted into the filter clause.
2206    
2207    =item RETURN
2208    
2209    Returns a list of B<ERDBObject>s that satisfy the query conditions.
2210    
2211    =back
2212    
2213    =cut
2214    #: Return Type @%
2215    sub GetList {
2216        # Get the parameters.
2217        my ($self, $objectNames, $filterClause, $params) = @_;
2218        # Declare the return variable.
2219        my @retVal = ();
2220        # Perform the query.
2221        my $query = $self->Get($objectNames, $filterClause, $params);
2222        # Loop through the results.
2223        while (my $object = $query->Fetch) {
2224            push @retVal, $object;
2225        }
2226        # Return the result.
2227        return @retVal;
2228    }
2229    
2230    =head3 GetCount
2231    
2232    C<< my $count = $erdb->GetCount(\@objectNames, $filter, \@params); >>
2233    
2234    Return the number of rows found by a specified query. This method would
2235    normally be used to count the records in a single table. For example, in a
2236    genetics database
2237    
2238        my $count = $erdb->GetCount(['Genome'], 'Genome(genus-species) LIKE ?', ['homo %']);
2239    
2240    would return the number of genomes for the genus I<homo>. It is conceivable, however,
2241    to use it to return records based on a join. For example,
2242    
2243        my $count = $erdb->GetCount(['HasFeature', 'Genome'], 'Genome(genus-species) LIKE ?',
2244                                    ['homo %']);
2245    
2246    would return the number of features for genomes in the genus I<homo>. Note that
2247    only the rows from the first table are counted. If the above command were
2248    
2249        my $count = $erdb->GetCount(['Genome', 'Feature'], 'Genome(genus-species) LIKE ?',
2250                                    ['homo %']);
2251    
2252    it would return the number of genomes, not the number of genome/feature pairs.
2253    
2254    =over 4
2255    
2256    =item objectNames
2257    
2258    Reference to a list of the objects (entities and relationships) included in the
2259    query.
2260    
2261    =item filter
2262    
2263    A filter clause for restricting the query. The rules are the same as for the L</Get>
2264    method.
2265    
2266    =item params
2267    
2268    Reference to a list of the parameter values to be substituted for the parameter marks
2269    in the filter.
2270    
2271    =item RETURN
2272    
2273    Returns a count of the number of records in the first table that would satisfy
2274    the query.
2275    
2276    =back
2277    
2278    =cut
2279    
2280    sub GetCount {
2281        # Get the parameters.
2282        my ($self, $objectNames, $filter, $params) = @_;
2283        # Insure the params argument is an array reference if the caller left it off.
2284        if (! defined($params)) {
2285            $params = [];
2286        }
2287        # Declare the return variable.
2288        my $retVal;
2289        # Find out if we're counting an entity or a relationship.
2290        my $countedField;
2291        if ($self->IsEntity($objectNames->[0])) {
2292            $countedField = "id";
2293        } else {
2294            # For a relationship we count the to-link because it's usually more
2295            # numerous. Note we're automatically converting to the SQL form
2296            # of the field name (to_link vs. to-link).
2297            $countedField = "to_link";
2298        }
2299        # Create the SQL command suffix to get the desired records.
2300        my ($suffix, $mappedNameListRef, $mappedNameHashRef) = $self->_SetupSQL($objectNames,
2301                                                                                $filter);
2302        # Prefix it with text telling it we want a record count.
2303        my $firstObject = $mappedNameListRef->[0];
2304        my $command = "SELECT COUNT($firstObject.$countedField) $suffix";
2305        # Prepare and execute the command.
2306        my $sth = $self->_GetStatementHandle($command, $params);
2307        # Get the count value.
2308        ($retVal) = $sth->fetchrow_array();
2309        # Check for a problem.
2310        if (! defined($retVal)) {
2311            if ($sth->err) {
2312                # Here we had an SQL error.
2313                Confess("Error retrieving row count: " . $sth->errstr());
2314            } else {
2315                # Here we have no result.
2316                Confess("No result attempting to retrieve row count.");
2317            }
2318        }
2319        # Return the result.
2320        return $retVal;
2321    }
2322    
2323    =head3 ComputeObjectSentence
2324    
2325    C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>
2326    
2327    Check an object name, and if it is a relationship convert it to a relationship sentence.
2328    
2329    =over 4
2330    
2331    =item objectName
2332    
2333    Name of the entity or relationship.
2334    
2335    =item RETURN
2336    
2337    Returns a string containing the entity name or a relationship sentence.
2338    
2339    =back
2340    
2341    =cut
2342    
2343    sub ComputeObjectSentence {
2344        # Get the parameters.
2345        my ($self, $objectName) = @_;
2346        # Set the default return value.
2347        my $retVal = $objectName;
2348        # Look for the object as a relationship.
2349        my $relTable = $self->{_metaData}->{Relationships};
2350        if (exists $relTable->{$objectName}) {
2351            # Get the relationship sentence.
2352            $retVal = _ComputeRelationshipSentence($objectName, $relTable->{$objectName});
2353        }
2354        # Return the result.
2355        return $retVal;
2356    }
2357    
2358    =head3 DumpRelations
2359    
2360    C<< $erdb->DumpRelations($outputDirectory); >>
2361    
2362    Write the contents of all the relations to tab-delimited files in the specified directory.
2363    Each file will have the same name as the relation dumped, with an extension of DTX.
2364    
2365    =over 4
2366    
2367    =item outputDirectory
2368    
2369    Name of the directory into which the relation files should be dumped.
2370    
2371    =back
2372    
2373    =cut
2374    
2375    sub DumpRelations {
2376        # Get the parameters.
2377        my ($self, $outputDirectory) = @_;
2378        # Now we need to run through all the relations. First, we loop through the entities.
2379        my $metaData = $self->{_metaData};
2380        my $entities = $metaData->{Entities};
2381        for my $entityName (keys %{$entities}) {
2382            my $entityStructure = $entities->{$entityName};
2383            # Get the entity's relations.
2384            my $relationList = $entityStructure->{Relations};
2385            # Loop through the relations, dumping them.
2386            for my $relationName (keys %{$relationList}) {
2387                my $relation = $relationList->{$relationName};
2388                $self->_DumpRelation($outputDirectory, $relationName, $relation);
2389            }
2390        }
2391        # Next, we loop through the relationships.
2392        my $relationships = $metaData->{Relationships};
2393        for my $relationshipName (keys %{$relationships}) {
2394            my $relationshipStructure = $relationships->{$relationshipName};
2395            # Dump this relationship's relation.
2396            $self->_DumpRelation($outputDirectory, $relationshipName, $relationshipStructure->{Relations}->{$relationshipName});
2397        }
2398    }
2399    
2400    =head3 InsertValue
2401    
2402    C<< $erdb->InsertValue($entityID, $fieldName, $value); >>
2403    
2404    This method will insert a new value into the database. The value must be one
2405    associated with a secondary relation, since primary values cannot be inserted:
2406    they occur exactly once. Secondary values, on the other hand, can be missing
2407    or multiply-occurring.
2408    
2409    =over 4
2410    
2411    =item entityID
2412    
2413    ID of the object that is to receive the new value.
2414    
2415    =item fieldName
2416    
2417    Field name for the new value-- this includes the entity name, since
2418    field names are of the format I<objectName>C<(>I<fieldName>C<)>.
2419    
2420    =item value
2421    
2422    New value to be put in the field.
2423    
2424    =back
2425    
2426    =cut
2427    
2428    sub InsertValue {
2429        # Get the parameters.
2430        my ($self, $entityID, $fieldName, $value) = @_;
2431        # Parse the entity name and the real field name.
2432        if ($fieldName =~ /^([^(]+)\(([^)]+)\)/) {
2433            my $entityName = $1;
2434            my $fieldTitle = $2;
2435            # Get its descriptor.
2436            if (!$self->IsEntity($entityName)) {
2437                Confess("$entityName is not a valid entity.");
2438            } else {
2439                my $entityData = $self->{_metaData}->{Entities}->{$entityName};
2440                # Find the relation containing this field.
2441                my $fieldHash = $entityData->{Fields};
2442                if (! exists $fieldHash->{$fieldTitle}) {
2443                    Confess("$fieldTitle not found in $entityName.");
2444                } else {
2445                    my $relation = $fieldHash->{$fieldTitle}->{relation};
2446                    if ($relation eq $entityName) {
2447                        Confess("Cannot do InsertValue on primary field $fieldTitle of $entityName.");
2448                    } else {
2449                        # Now we can create an INSERT statement.
2450                        my $dbh = $self->{_dbh};
2451                        my $fixedName = _FixName($fieldTitle);
2452                        my $statement = "INSERT INTO $relation (id, $fixedName) VALUES(?, ?)";
2453                        # Execute the command.
2454                        $dbh->SQL($statement, 0, $entityID, $value);
2455                    }
2456                }
2457            }
2458        } else {
2459            Confess("$fieldName is not a valid field name.");
2460        }
2461    }
2462    
2463    =head3 InsertObject
2464    
2465    C<< $erdb->InsertObject($objectType, \%fieldHash); >>
2466    
2467    Insert an object into the database. The object is defined by a type name and then a hash
2468    of field names to values. Field values in the primary relation are represented by scalars.
2469    (Note that for relationships, the primary relation is the B<only> relation.)
2470    Field values for the other relations comprising the entity are always list references. For
2471    example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases
2472    C<ZP_00210270.1> and C<gi|46206278>.
2473    
2474    C<< $erdb->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>
2475    
2476    The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
2477    property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
2478    
2479    C<< $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>
2480    
2481    =over 4
2482    
2483    =item newObjectType
2484    
2485    Type name of the object to insert.
2486    
2487    =item fieldHash
2488    
2489    Hash of field names to values.
2490    
2491    =back
2492    
2493    =cut
2494    
2495    sub InsertObject {
2496        # Get the parameters.
2497        my ($self, $newObjectType, $fieldHash) = @_;
2498        # Denote that so far we appear successful.
2499        my $retVal = 1;
2500        # Get the database handle.
2501        my $dbh = $self->{_dbh};
2502        # Get the relation list.
2503        my $relationTable = $self->_GetRelationTable($newObjectType);
2504        # Loop through the relations. We'll build insert statements for each one. If a relation is
2505        # secondary, we may end up generating multiple insert statements. If an error occurs, we
2506        # stop the loop.
2507        my @relationList = keys %{$relationTable};
2508        for (my $i = 0; $retVal && $i <= $#relationList; $i++) {
2509            my $relationName = $relationList[$i];
2510            my $relationDefinition = $relationTable->{$relationName};
2511            # Get the relation's fields. For each field we will collect a value in the corresponding
2512            # position of the @valueList array. If one of the fields is missing, we will add it to the
2513            # @missing list.
2514            my @fieldList = @{$relationDefinition->{Fields}};
2515            my @fieldNameList = ();
2516            my @valueList = ();
2517            my @missing = ();
2518            my $recordCount = 1;
2519            for my $fieldDescriptor (@fieldList) {
2520                # Get the field name and save it. Note we need to fix it up so the hyphens
2521                # are converted to underscores.
2522                my $fieldName = $fieldDescriptor->{name};
2523                push @fieldNameList, _FixName($fieldName);
2524                # Look for the named field in the incoming structure. Note that we are looking
2525                # for the real field name, not the fixed-up one!
2526                if (exists $fieldHash->{$fieldName}) {
2527                    # Here we found the field. Stash it in the value list.
2528                    my $value = $fieldHash->{$fieldName};
2529                    push @valueList, $value;
2530                    # If the value is a list, we may need to increment the record count.
2531                    if (ref $value eq "ARRAY") {
2532                        my $thisCount = @{$value};
2533                        if ($recordCount == 1) {
2534                            # Here we have our first list, so we save its count.
2535                            $recordCount = $thisCount;
2536                        } elsif ($recordCount != $thisCount) {
2537                            # Here we have a second list, so its length has to match the
2538                            # previous lists.
2539                            Trace("Field $value in new $newObjectType object has an invalid list length $thisCount. Expected $recordCount.") if T(0);
2540                            $retVal = 0;
2541                        }
2542                    }
2543          } else {          } else {
2544              # Here we've seen the object before. We construct a new name using                  # Here the field is not present. Flag it as missing.
2545              # the suffix from the hash and update the hash.                  push @missing, $fieldName;
2546              my $mappedName = "$objectName$suffix";              }
2547              $objectHash{$objectName} = $suffix + 1;          }
2548              # The FROM list has the object name followed by the mapped name. This          # If we are the primary relation, add the new-record flag.
2549              # tells SQL it's still the same table, but we're using a different name          if ($relationName eq $newObjectType) {
2550              # for it to avoid confusion.              push @valueList, 1;
2551              push @fromList, "$objectName $mappedName";              push @fieldNameList, "new_record";
2552              # The mapped-name list contains the real mapped name.          }
2553              push @mappedNameList, $mappedName;          # Only proceed if there are no missing fields.
2554              # Finally, enable us to get back from the mapped name to the object name.          if (@missing > 0) {
2555              $mappedNameHash{$mappedName} = $objectName;              Trace("Relation $relationName for $newObjectType skipped due to missing fields: " .
2556                    join(' ', @missing)) if T(1);
2557            } else {
2558                # Build the INSERT statement.
2559                my $statement = "INSERT INTO $relationName (" . join (', ', @fieldNameList) .
2560                    ") VALUES (";
2561                # Create a marker list of the proper size and put it in the statement.
2562                my @markers = ();
2563                while (@markers < @fieldNameList) { push @markers, '?'; }
2564                $statement .= join(', ', @markers) . ")";
2565                # We have the insert statement, so prepare it.
2566                my $sth = $dbh->prepare_command($statement);
2567                Trace("Insert statement prepared: $statement") if T(3);
2568                # Now we loop through the values. If a value is scalar, we use it unmodified. If it's
2569                # a list, we use the current element. The values are stored in the @parameterList array.
2570                my $done = 0;
2571                for (my $i = 0; $i < $recordCount; $i++) {
2572                    # Clear the parameter list array.
2573                    my @parameterList = ();
2574                    # Loop through the values.
2575                    for my $value (@valueList) {
2576                        # Check to see if this is a scalar value.
2577                        if (ref $value eq "ARRAY") {
2578                            # Here we have a list value. Pull the current entry.
2579                            push @parameterList, $value->[$i];
2580                        } else {
2581                            # Here we have a scalar value. Use it unmodified.
2582                            push @parameterList, $value;
2583                        }
2584                    }
2585                    # Execute the INSERT statement with the specified parameter list.
2586                    $retVal = $sth->execute(@parameterList);
2587                    if (!$retVal) {
2588                        my $errorString = $sth->errstr();
2589                        Confess("Error inserting into $relationName: $errorString");
2590                    } else {
2591                        Trace("Insert successful using $parameterList[0].") if T(3);
2592                    }
2593                }
2594            }
2595        }
2596        # Return a 1 for backward compatability.
2597        return 1;
2598    }
2599    
2600    =head3 UpdateEntity
2601    
2602    C<< $erdb->UpdateEntity($entityName, $id, \%fields); >>
2603    
2604    Update the values of an entity. This is an unprotected update, so it should only be
2605    done if the database resides on a database server.
2606    
2607    =over 4
2608    
2609    =item entityName
2610    
2611    Name of the entity to update. (This is the entity type.)
2612    
2613    =item id
2614    
2615    ID of the entity to update. If no entity exists with this ID, an error will be thrown.
2616    
2617    =item fields
2618    
2619    Reference to a hash mapping field names to their new values. All of the fields named
2620    must be in the entity's primary relation, and they cannot any of them be the ID field.
2621    
2622    =back
2623    
2624    =cut
2625    
2626    sub UpdateEntity {
2627        # Get the parameters.
2628        my ($self, $entityName, $id, $fields) = @_;
2629        # Get a list of the field names being updated.
2630        my @fieldList = keys %{$fields};
2631        # Verify that the fields exist.
2632        my $checker = $self->GetFieldTable($entityName);
2633        for my $field (@fieldList) {
2634            if ($field eq 'id') {
2635                Confess("Cannot update the ID field for entity $entityName.");
2636            } elsif ($checker->{$field}->{relation} ne $entityName) {
2637                Confess("Cannot find $field in primary relation of $entityName.");
2638            }
2639        }
2640        # Build the SQL statement.
2641        my @sets = ();
2642        my @valueList = ();
2643        for my $field (@fieldList) {
2644            push @sets, _FixName($field) . " = ?";
2645            push @valueList, $fields->{$field};
2646        }
2647        my $command = "UPDATE $entityName SET " . join(", ", @sets) . " WHERE id = ?";
2648        # Add the ID to the list of binding values.
2649        push @valueList, $id;
2650        # Call SQL to do the work.
2651        my $rows = $self->{_dbh}->SQL($command, 0, @valueList);
2652        # Check for errors.
2653        if ($rows == 0) {
2654            Confess("Entity $id of type $entityName not found.");
2655        }
2656    }
2657    
2658    =head3 LoadTable
2659    
2660    C<< my $results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>
2661    
2662    Load data from a tab-delimited file into a specified table, optionally re-creating the table
2663    first.
2664    
2665    =over 4
2666    
2667    =item fileName
2668    
2669    Name of the file from which the table data should be loaded.
2670    
2671    =item relationName
2672    
2673    Name of the relation to be loaded. This is the same as the table name.
2674    
2675    =item truncateFlag
2676    
2677    TRUE if the table should be dropped and re-created, else FALSE
2678    
2679    =item RETURN
2680    
2681    Returns a statistical object containing a list of the error messages.
2682    
2683    =back
2684    
2685    =cut
2686    sub LoadTable {
2687        # Get the parameters.
2688        my ($self, $fileName, $relationName, $truncateFlag) = @_;
2689        # Create the statistical return object.
2690        my $retVal = _GetLoadStats();
2691        # Trace the fact of the load.
2692        Trace("Loading table $relationName from $fileName") if T(2);
2693        # Get the database handle.
2694        my $dbh = $self->{_dbh};
2695        # Get the input file size.
2696        my $fileSize = -s $fileName;
2697        # Get the relation data.
2698        my $relation = $self->_FindRelation($relationName);
2699        # Check the truncation flag.
2700        if ($truncateFlag) {
2701            Trace("Creating table $relationName") if T(2);
2702            # Compute the row count estimate. We take the size of the load file,
2703            # divide it by the estimated row size, and then multiply by 1.5 to
2704            # leave extra room. We postulate a minimum row count of 1000 to
2705            # prevent problems with incoming empty load files.
2706            my $rowSize = $self->EstimateRowSize($relationName);
2707            my $estimate = FIG::max($fileSize * 1.5 / $rowSize, 1000);
2708            # Re-create the table without its index.
2709            $self->CreateTable($relationName, 0, $estimate);
2710            # If this is a pre-index DBMS, create the index here.
2711            if ($dbh->{_preIndex}) {
2712                eval {
2713                    $self->CreateIndex($relationName);
2714                };
2715                if ($@) {
2716                    $retVal->AddMessage($@);
2717                }
2718            }
2719        }
2720        # Load the table.
2721        my $rv;
2722        eval {
2723            $rv = $dbh->load_table(file => $fileName, tbl => $relationName);
2724        };
2725        if (!defined $rv) {
2726            $retVal->AddMessage($@) if ($@);
2727            $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2728            Trace("Table load failed for $relationName.") if T(1);
2729        } else {
2730            # Here we successfully loaded the table.
2731            $retVal->Add("tables");
2732            my $size = -s $fileName;
2733            Trace("$size bytes loaded into $relationName.") if T(2);
2734            # If we're rebuilding, we need to create the table indexes.
2735            if ($truncateFlag) {
2736                # Indexes are created here for PostGres. For PostGres, indexes are
2737                # best built at the end. For MySQL, the reverse is true.
2738                if (! $dbh->{_preIndex}) {
2739                    eval {
2740                        $self->CreateIndex($relationName);
2741                    };
2742                    if ($@) {
2743                        $retVal->AddMessage($@);
2744                    }
2745                }
2746                # The full-text index (if any) is always built last, even for MySQL.
2747                # First we need to see if this table has a full-text index. Only
2748                # primary relations are allowed that privilege.
2749                Trace("Checking for full-text index on $relationName.") if T(2);
2750                if ($self->_IsPrimary($relationName)) {
2751                    $self->CreateSearchIndex($relationName);
2752                }
2753            }
2754        }
2755        # Analyze the table to improve performance.
2756        Trace("Analyzing and compacting $relationName.") if T(3);
2757        $dbh->vacuum_it($relationName);
2758        Trace("$relationName load completed.") if T(3);
2759        # Return the statistics.
2760        return $retVal;
2761    }
2762    
2763    =head3 CreateSearchIndex
2764    
2765    C<< $erdb->CreateSearchIndex($objectName); >>
2766    
2767    Check for a full-text search index on the specified entity or relationship object, and
2768    if one is required, rebuild it.
2769    
2770    =over 4
2771    
2772    =item objectName
2773    
2774    Name of the entity or relationship to be indexed.
2775    
2776    =back
2777    
2778    =cut
2779    
2780    sub CreateSearchIndex {
2781        # Get the parameters.
2782        my ($self, $objectName) = @_;
2783        # Get the relation's entity/relationship structure.
2784        my $structure = $self->_GetStructure($objectName);
2785        # Get the database handle.
2786        my $dbh = $self->{_dbh};
2787        Trace("Checking for search fields in $objectName.") if T(3);
2788        # Check for a searchable fields list.
2789        if (exists $structure->{searchFields}) {
2790            # Here we know that we need to create a full-text search index.
2791            # Get an SQL-formatted field name list.
2792            my $fields = join(", ", _FixNames(@{$structure->{searchFields}}));
2793            # Create the index. If it already exists, it will be dropped.
2794            $dbh->create_index(tbl => $objectName, idx => "search_idx",
2795                               flds => $fields, kind => 'fulltext');
2796            Trace("Index created for $fields in $objectName.") if T(2);
2797          }          }
2798      }      }
2799      # Construct the SELECT statement. The general pattern is  
2800      #  =head3 DropRelation
2801      # SELECT name1.*, name2.*, ... nameN.* FROM name1, name2, ... nameN  
2802      #  C<< $erdb->DropRelation($relationName); >>
2803    
2804    Physically drop a relation from the database.
2805    
2806    =over 4
2807    
2808    =item relationName
2809    
2810    Name of the relation to drop. If it does not exist, this method will have
2811    no effect.
2812    
2813    =back
2814    
2815    =cut
2816    
2817    sub DropRelation {
2818        # Get the parameters.
2819        my ($self, $relationName) = @_;
2820        # Get the database handle.
2821      my $dbh = $self->{_dbh};      my $dbh = $self->{_dbh};
2822      my $command = "SELECT DISTINCT " . join('.*, ', @mappedNameList) . ".* FROM " .      # Drop the relation. The method used here has no effect if the relation
2823                  join(', ', @fromList);      # does not exist.
2824      # Check for a filter clause.      Trace("Invoking DB Kernel to drop $relationName.") if T(3);
2825      if ($filterClause) {      $dbh->drop_table(tbl => $relationName);
2826          # Here we have one, so we convert its field names and add it to the query. First,  }
2827          # We create a copy of the filter string we can work with.  
2828          my $filterString = $filterClause;  =head3 MatchSqlPattern
2829          # Next, we sort the object names by length. This helps protect us from finding  
2830          # object names inside other object names when we're doing our search and replace.  C<< my $matched = ERDB::MatchSqlPattern($value, $pattern); >>
2831          my @sortedNames = sort { length($b) - length($a) } @mappedNameList;  
2832          # We will also keep a list of conditions to add to the WHERE clause in order to link  Determine whether or not a specified value matches an SQL pattern. An SQL
2833          # entities and relationships as well as primary relations to secondary ones.  pattern has two wild card characters: C<%> that matches multiple characters,
2834          my @joinWhere = ();  and C<_> that matches a single character. These can be escaped using a
2835          # The final preparatory step is to create a hash table of relation names. The  backslash (C<\>). We pull this off by converting the SQL pattern to a
2836          # table begins with the relation names already in the SELECT command. We may  PERL regular expression. As per SQL rules, the match is case-insensitive.
2837          # need to add relations later if there is filtering on a field in a secondary  
2838          # relation. The secondary relations are the ones that contain multiply-  =over 4
2839          # occurring or optional fields.  
2840          my %fromNames = map { $_ => 1 } @sortedNames;  =item value
2841          # We are ready to begin. We loop through the object names, replacing each  
2842          # object name's field references by the corresponding SQL field reference.  Value to be matched against the pattern. Note that an undefined or empty
2843          # Along the way, if we find a secondary relation, we will need to add it  value will not match anything.
2844          # to the FROM clause.  
2845          for my $mappedName (@sortedNames) {  =item pattern
2846              # Get the length of the object name plus 2. This is the value we add to the  
2847              # size of the field name to determine the size of the field reference as a  SQL pattern against which to match the value. An undefined or empty pattern will
2848              # whole.  match everything.
2849              my $nameLength = 2 + length $mappedName;  
2850              # Get the real object name for this mapped name.  =item RETURN
2851              my $objectName = $mappedNameHash{$mappedName};  
2852              Trace("Processing $mappedName for object $objectName.") if T(4);  Returns TRUE if the value and pattern match, else FALSE.
2853              # Get the object's field list.  
2854              my $fieldList = $self->GetFieldTable($objectName);  =back
2855              # Find the field references for this object.  
2856              while ($filterString =~ m/$mappedName\(([^)]*)\)/g) {  =cut
2857                  # At this point, $1 contains the field name, and the current position  
2858                  # is set immediately after the final parenthesis. We pull out the name of  sub MatchSqlPattern {
2859                  # the field and the position and length of the field reference as a whole.      # Get the parameters.
2860                  my $fieldName = $1;      my ($value, $pattern) = @_;
2861                  my $len = $nameLength + length $fieldName;      # Declare the return variable.
2862                  my $pos = pos($filterString) - $len;      my $retVal;
2863                  # Insure the field exists.      # Insure we have a pattern.
2864                  if (!exists $fieldList->{$fieldName}) {      if (! defined($pattern) || $pattern eq "") {
2865                      Confess("Field $fieldName not found for object $objectName.");          $retVal = 1;
2866                  } else {                  } else {
2867                      Trace("Processing $fieldName at position $pos.") if T(4);          # Break the pattern into pieces around the wildcard characters. Because we
2868                      # Get the field's relation.          # use parentheses in the split function's delimiter expression, we'll get
2869                      my $relationName = $fieldList->{$fieldName}->{relation};          # list elements for the delimiters as well as the rest of the string.
2870                      # Now we have a secondary relation. We need to insure it matches the          my @pieces = split /([_%]|\\[_%])/, $pattern;
2871                      # mapped name of the primary relation. First we peel off the suffix          # Check some fast special cases.
2872                      # from the mapped name.          if ($pattern eq '%') {
2873                      my $mappingSuffix = substr $mappedName, length($objectName);              # A null pattern matches everything.
2874                      # Put the mapping suffix onto the relation name to get the              $retVal = 1;
2875                      # mapped relation name.          } elsif (@pieces == 1) {
2876                      my $mappedRelationName = "$relationName$mappingSuffix";              # No wildcards, so we have a literal comparison. Note we're case-insensitive.
2877                      # Insure the relation is in the FROM clause.              $retVal = (lc($value) eq lc($pattern));
2878                      if (!exists $fromNames{$mappedRelationName}) {          } elsif (@pieces == 2 && $pieces[1] eq '%') {
2879                          # Add the relation to the FROM clause.              # A wildcard at the end, so we have a substring match. This is also case-insensitive.
2880                          if ($mappedRelationName eq $relationName) {              $retVal = (lc(substr($value, 0, length($pieces[0]))) eq lc($pieces[0]));
2881                              # The name is un-mapped, so we add it without          } else {
2882                              # any frills.              # Okay, we have to do it the hard way. Convert each piece to a PERL pattern.
2883                              $command .= ", $relationName";              my $realPattern = "";
2884                              push @joinWhere, "$objectName.id = $relationName.id";              for my $piece (@pieces) {
2885                    # Determine the type of piece.
2886                    if ($piece eq "") {
2887                        # Empty pieces are ignored.
2888                    } elsif ($piece eq "%") {
2889                        # Here we have a multi-character wildcard. Note that it can match
2890                        # zero or more characters.
2891                        $realPattern .= ".*"
2892                    } elsif ($piece eq "_") {
2893                        # Here we have a single-character wildcard.
2894                        $realPattern .= ".";
2895                    } elsif ($piece eq "\\%" || $piece eq "\\_") {
2896                        # This is an escape sequence (which is a rare thing, actually).
2897                        $realPattern .= substr($piece, 1, 1);
2898                    } else {
2899                        # Here we have raw text.
2900                        $realPattern .= quotemeta($piece);
2901                    }
2902                }
2903                # Do the match.
2904                $retVal = ($value =~ /^$realPattern$/i ? 1 : 0);
2905            }
2906        }
2907        # Return the result.
2908        return $retVal;
2909    }
2910    
2911    =head3 GetEntity
2912    
2913    C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>
2914    
2915    Return an object describing the entity instance with a specified ID.
2916    
2917    =over 4
2918    
2919    =item entityType
2920    
2921    Entity type name.
2922    
2923    =item ID
2924    
2925    ID of the desired entity.
2926    
2927    =item RETURN
2928    
2929    Returns a B<ERDBObject> representing the desired entity instance, or an undefined value if no
2930    instance is found with the specified key.
2931    
2932    =back
2933    
2934    =cut
2935    
2936    sub GetEntity {
2937        # Get the parameters.
2938        my ($self, $entityType, $ID) = @_;
2939        # Create a query.
2940        my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);
2941        # Get the first (and only) object.
2942        my $retVal = $query->Fetch();
2943        # Return the result.
2944        return $retVal;
2945    }
2946    
2947    =head3 GetChoices
2948    
2949    C<< my @values = $erdb->GetChoices($entityName, $fieldName); >>
2950    
2951    Return a list of all the values for the specified field that are represented in the
2952    specified entity.
2953    
2954    Note that if the field is not indexed, then this will be a very slow operation.
2955    
2956    =over 4
2957    
2958    =item entityName
2959    
2960    Name of an entity in the database.
2961    
2962    =item fieldName
2963    
2964    Name of a field belonging to the entity. This is a raw field name without
2965    the standard parenthesized notation used in most calls.
2966    
2967    =item RETURN
2968    
2969    Returns a list of the distinct values for the specified field in the database.
2970    
2971    =back
2972    
2973    =cut
2974    
2975    sub GetChoices {
2976        # Get the parameters.
2977        my ($self, $entityName, $fieldName) = @_;
2978        # Declare the return variable.
2979        my @retVal;
2980        # Get the entity data structure.
2981        my $entityData = $self->_GetStructure($entityName);
2982        # Get the field.
2983        my $fieldHash = $entityData->{Fields};
2984        if (! exists $fieldHash->{$fieldName}) {
2985            Confess("$fieldName not found in $entityName.");
2986        } else {
2987            # Get the name of the relation containing the field.
2988            my $relation = $fieldHash->{$fieldName}->{relation};
2989            # Fix up the field name.
2990            my $realName = _FixName($fieldName);
2991            # Get the database handle.
2992            my $dbh = $self->{_dbh};
2993            # Query the database.
2994            my $results = $dbh->SQL("SELECT DISTINCT $realName FROM $relation");
2995            # Clean the results. They are stored as a list of lists, and we just want the one list.
2996            @retVal = sort map { $_->[0] } @{$results};
2997        }
2998        # Return the result.
2999        return @retVal;
3000    }
3001    
3002    =head3 GetEntityValues
3003    
3004    C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>
3005    
3006    Return a list of values from a specified entity instance. If the entity instance
3007    does not exist, an empty list is returned.
3008    
3009    =over 4
3010    
3011    =item entityType
3012    
3013    Entity type name.
3014    
3015    =item ID
3016    
3017    ID of the desired entity.
3018    
3019    =item fields
3020    
3021    List of field names, each of the form I<objectName>C<(>I<fieldName>C<)>.
3022    
3023    =item RETURN
3024    
3025    Returns a flattened list of the values of the specified fields for the specified entity.
3026    
3027    =back
3028    
3029    =cut
3030    
3031    sub GetEntityValues {
3032        # Get the parameters.
3033        my ($self, $entityType, $ID, $fields) = @_;
3034        # Get the specified entity.
3035        my $entity = $self->GetEntity($entityType, $ID);
3036        # Declare the return list.
3037        my @retVal = ();
3038        # If we found the entity, push the values into the return list.
3039        if ($entity) {
3040            push @retVal, $entity->Values($fields);
3041        }
3042        # Return the result.
3043        return @retVal;
3044    }
3045    
3046    =head3 GetAll
3047    
3048    C<< my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>
3049    
3050    Return a list of values taken from the objects returned by a query. The first three
3051    parameters correspond to the parameters of the L</Get> method. The final parameter is
3052    a list of the fields desired from each record found by the query. The field name
3053    syntax is the standard syntax used for fields in the B<ERDB> system--
3054    B<I<objectName>(I<fieldName>)>-- where I<objectName> is the name of the relevant entity
3055    or relationship and I<fieldName> is the name of the field.
3056    
3057    The list returned will be a list of lists. Each element of the list will contain
3058    the values returned for the fields specified in the fourth parameter. If one of the
3059    fields specified returns multiple values, they are flattened in with the rest. For
3060    example, the following call will return a list of the features in a particular
3061    spreadsheet cell, and each feature will be represented by a list containing the
3062    feature ID followed by all of its aliases.
3063    
3064    C<< @query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>
3065    
3066    =over 4
3067    
3068    =item objectNames
3069    
3070    List containing the names of the entity and relationship objects to be retrieved.
3071    
3072    =item filterClause
3073    
3074    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
3075    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
3076    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
3077    parameter list as additional parameters. The fields in a filter clause can come from primary
3078    entity relations, relationship relations, or secondary entity relations; however, all of the
3079    entities and relationships involved must be included in the list of object names.
3080    
3081    =item parameterList
3082    
3083    List of the parameters to be substituted in for the parameters marks in the filter clause.
3084    
3085    =item fields
3086    
3087    List of the fields to be returned in each element of the list returned.
3088    
3089    =item count
3090    
3091    Maximum number of records to return. If omitted or 0, all available records will be returned.
3092    
3093    =item RETURN
3094    
3095    Returns a list of list references. Each element of the return list contains the values for the
3096    fields specified in the B<fields> parameter.
3097    
3098    =back
3099    
3100    =cut
3101    #: Return Type @@;
3102    sub GetAll {
3103        # Get the parameters.
3104        my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
3105        # Translate the parameters from a list reference to a list. If the parameter
3106        # list is a scalar we convert it into a singleton list.
3107        my @parmList = ();
3108        if (ref $parameterList eq "ARRAY") {
3109            Trace("GetAll parm list is an array.") if T(4);
3110            @parmList = @{$parameterList};
3111                          } else {                          } else {
3112                              # Here we have a mapping situation.          Trace("GetAll parm list is a scalar: $parameterList.") if T(4);
3113                              $command .= ", $relationName $mappedRelationName";          push @parmList, $parameterList;
                             push @joinWhere, "$mappedRelationName.id = $mappedName.id";  
3114                          }                          }
3115                          # Denote we have this relation available for future fields.      # Insure the counter has a value.
3116                          $fromNames{$mappedRelationName} = 1;      if (!defined $count) {
3117            $count = 0;
3118                      }                      }
3119                      # Form an SQL field reference from the relation name and the field name.      # Add the row limit to the filter clause.
3120                      my $sqlReference = "$mappedRelationName." . _FixName($fieldName);      if ($count > 0) {
3121                      # Put it into the filter string in place of the old value.          $filterClause .= " LIMIT $count";
                     substr($filterString, $pos, $len) = $sqlReference;  
                     # Reposition the search.  
                     pos $filterString = $pos + length $sqlReference;  
3122                  }                  }
3123        # Create the query.
3124        my $query = $self->Get($objectNames, $filterClause, \@parmList);
3125        # Set up a counter of the number of records read.
3126        my $fetched = 0;
3127        # Loop through the records returned, extracting the fields. Note that if the
3128        # counter is non-zero, we stop when the number of records read hits the count.
3129        my @retVal = ();
3130        while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {
3131            my @rowData = $row->Values($fields);
3132            push @retVal, \@rowData;
3133            $fetched++;
3134              }              }
3135        Trace("$fetched rows returned in GetAll.") if T(SQL => 4);
3136        # Return the resulting list.
3137        return @retVal;
3138          }          }
3139          # The next step is to join the objects together. We only need to do this if there  
3140          # is more than one object in the object list. We start with the first object and  =head3 Exists
3141          # run through the objects after it. Note also that we make a safety copy of the  
3142          # list before running through it.  C<< my $found = $sprout->Exists($entityName, $entityID); >>
3143          my @mappedObjectList = @mappedNameList;  
3144          my $lastMappedObject = shift @mappedObjectList;  Return TRUE if an entity exists, else FALSE.
3145          # Get the join table.  
3146          my $joinTable = $self->{_metaData}->{Joins};  =over 4
3147          # Loop through the object list.  
3148          for my $thisMappedObject (@mappedObjectList) {  =item entityName
3149              # Look for a join using the real object names.  
3150              my $lastObject = $mappedNameHash{$lastMappedObject};  Name of the entity type (e.g. C<Feature>) relevant to the existence check.
3151              my $thisObject = $mappedNameHash{$thisMappedObject};  
3152              my $joinKey = "$lastObject/$thisObject";  =item entityID
3153              if (!exists $joinTable->{$joinKey}) {  
3154                  # Here there's no join, so we throw an error.  ID of the entity instance whose existence is to be checked.
3155                  Confess("No join exists to connect from $lastMappedObject to $thisMappedObject.");  
3156              } else {  =item RETURN
3157                  # Get the join clause.  
3158                  my $unMappedJoin = $joinTable->{$joinKey};  Returns TRUE if the entity instance exists, else FALSE.
3159                  # Fix the names.  
3160                  $unMappedJoin =~ s/$lastObject/$lastMappedObject/;  =back
3161                  $unMappedJoin =~ s/$thisObject/$thisMappedObject/;  
3162                  push @joinWhere, $unMappedJoin;  =cut
3163                  # Save this object as the last object for the next iteration.  #: Return Type $;
3164                  $lastMappedObject = $thisMappedObject;  sub Exists {
3165        # Get the parameters.
3166        my ($self, $entityName, $entityID) = @_;
3167        # Check for the entity instance.
3168        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
3169        my $testInstance = $self->GetEntity($entityName, $entityID);
3170        # Return an existence indicator.
3171        my $retVal = ($testInstance ? 1 : 0);
3172        return $retVal;
3173              }              }
3174    
3175    =head3 EstimateRowSize
3176    
3177    C<< my $rowSize = $erdb->EstimateRowSize($relName); >>
3178    
3179    Estimate the row size of the specified relation. The estimated row size is computed by adding
3180    up the average length for each data type.
3181    
3182    =over 4
3183    
3184    =item relName
3185    
3186    Name of the relation whose estimated row size is desired.
3187    
3188    =item RETURN
3189    
3190    Returns an estimate of the row size for the specified relation.
3191    
3192    =back
3193    
3194    =cut
3195    #: Return Type $;
3196    sub EstimateRowSize {
3197        # Get the parameters.
3198        my ($self, $relName) = @_;
3199        # Declare the return variable.
3200        my $retVal = 0;
3201        # Find the relation descriptor.
3202        my $relation = $self->_FindRelation($relName);
3203        # Get the list of fields.
3204        for my $fieldData (@{$relation->{Fields}}) {
3205            # Get the field type and add its length.
3206            my $fieldLen = $TypeTable{$fieldData->{type}}->{avgLen};
3207            $retVal += $fieldLen;
3208          }          }
3209          # Now we need to handle the whole ORDER BY / LIMIT thing. The important part      # Return the result.
3210          # here is we want the filter clause to be empty if there's no WHERE filter.      return $retVal;
         # 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 = $1;  
3211          }          }
3212          # Add the filter and the join clauses (if any) to the SELECT command.  
3213          if ($filterString) {  =head3 GetFieldTable
3214              Trace("Filter string is \"$filterString\".") if T(4);  
3215              push @joinWhere, "($filterString)";  C<< my $fieldHash = $self->GetFieldTable($objectnName); >>
3216    
3217    Get the field structure for a specified entity or relationship.
3218    
3219    =over 4
3220    
3221    =item objectName
3222    
3223    Name of the desired entity or relationship.
3224    
3225    =item RETURN
3226    
3227    The table containing the field descriptors for the specified object.
3228    
3229    =back
3230    
3231    =cut
3232    
3233    sub GetFieldTable {
3234        # Get the parameters.
3235        my ($self, $objectName) = @_;
3236        # Get the descriptor from the metadata.
3237        my $objectData = $self->_GetStructure($objectName);
3238        # Return the object's field table.
3239        return $objectData->{Fields};
3240          }          }
3241          if (@joinWhere) {  
3242              $command .= " WHERE " . join(' AND ', @joinWhere);  =head3 SplitKeywords
3243    
3244    C<< my @keywords = ERDB::SplitKeywords($keywordString); >>
3245    
3246    This method returns a list of the positive keywords in the specified
3247    keyword string. All of the operators will have been stripped off,
3248    and if the keyword is preceded by a minus operator (C<->), it will
3249    not be in the list returned. The idea here is to get a list of the
3250    keywords the user wants to see. The list will be processed to remove
3251    duplicates.
3252    
3253    It is possible to create a string that confuses this method. For example
3254    
3255        frog toad -frog
3256    
3257    would return both C<frog> and C<toad>. If this is a problem we can deal
3258    with it later.
3259    
3260    =over 4
3261    
3262    =item keywordString
3263    
3264    The keyword string to be parsed.
3265    
3266    =item RETURN
3267    
3268    Returns a list of the words in the keyword string the user wants to
3269    see.
3270    
3271    =back
3272    
3273    =cut
3274    
3275    sub SplitKeywords {
3276        # Get the parameters.
3277        my ($keywordString) = @_;
3278        # Make a safety copy of the string. (This helps during debugging.)
3279        my $workString = $keywordString;
3280        # Convert operators we don't care about to spaces.
3281        $workString =~ tr/+"()<>/ /;
3282        # Split the rest of the string along space boundaries. Note that we
3283        # eliminate any words that are zero length or begin with a minus sign.
3284        my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
3285        # Use a hash to remove duplicates.
3286        my %words = map { $_ => 1 } @wordList;
3287        # Return the result.
3288        return sort keys %words;
3289          }          }
3290          # Add the sort or limit clause (if any) to the SELECT command.  
3291          if ($orderClause) {  =head3 ValidateFieldName
3292              $command .= " $orderClause";  
3293    C<< my $okFlag = ERDB::ValidateFieldName($fieldName); >>
3294    
3295    Return TRUE if the specified field name is valid, else FALSE. Valid field names must
3296    be hyphenated words subject to certain restrictions.
3297    
3298    =over 4
3299    
3300    =item fieldName
3301    
3302    Field name to be validated.
3303    
3304    =item RETURN
3305    
3306    Returns TRUE if the field name is valid, else FALSE.
3307    
3308    =back
3309    
3310    =cut
3311    
3312    sub ValidateFieldName {
3313        # Get the parameters.
3314        my ($fieldName) = @_;
3315        # Declare the return variable. The field name is valid until we hear
3316        # differently.
3317        my $retVal = 1;
3318        # Compute the maximum name length.
3319        my $maxLen = $TypeTable{'name-string'}->{maxLen};
3320        # Look for bad stuff in the name.
3321        if ($fieldName =~ /--/) {
3322            # Here we have a doubled minus sign.
3323            Trace("Field name $fieldName has a doubled hyphen.") if T(1);
3324            $retVal = 0;
3325        } elsif ($fieldName !~ /^[A-Za-z]/) {
3326            # Here the field name is missing the initial letter.
3327            Trace("Field name $fieldName does not begin with a letter.") if T(1);
3328            $retVal = 0;
3329        } elsif (length($fieldName) > $maxLen) {
3330            # Here the field name is too long.
3331            Trace("Maximum field name length is $maxLen. Field name must be truncated to " . substr($fieldName,0, $maxLen) . ".");
3332        } else {
3333            # Strip out the minus signs. Everything remaining must be a letter,
3334            # underscore, or digit.
3335            my $strippedName = $fieldName;
3336            $strippedName =~ s/-//g;
3337            if ($strippedName !~ /^(\w|\d)+$/) {
3338                Trace("Field name $fieldName contains illegal characters.") if T(1);
3339                $retVal = 0;
3340          }          }
3341      }      }
3342      Trace("SQL query: $command") if T(SQL => 3);      # Return the result.
3343      Trace("PARMS: '" . (join "', '", @params) . "'") if (T(SQL => 4) && (@params > 0));      return $retVal;
     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}];  
3344      }      }
3345      # Return the statement object.  
3346      my $retVal = DBQuery::_new($self, $sth, \@relationMap);  =head3 ReadMetaXML
3347    
3348    C<< my $rawMetaData = ERDB::ReadDBD($fileName); >>
3349    
3350    This method reads a raw database definition XML file and returns it.
3351    Normally, the metadata used by the ERDB system has been processed and
3352    modified to make it easier to load and retrieve the data; however,
3353    this method can be used to get the data in its raw form.
3354    
3355    =over 4
3356    
3357    =item fileName
3358    
3359    Name of the XML file to read.
3360    
3361    =item RETURN
3362    
3363    Returns a hash reference containing the raw XML data from the specified file.
3364    
3365    =back
3366    
3367    =cut
3368    
3369    sub ReadMetaXML {
3370        # Get the parameters.
3371        my ($fileName) = @_;
3372        # Read the XML.
3373        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
3374        Trace("XML metadata loaded from file $fileName.") if T(1);
3375        # Return the result.
3376      return $retVal;      return $retVal;
3377  }  }
3378    
3379  =head3 Delete  =head3 GetEntityFieldHash
3380    
3381  C<< my $stats = $erdb->Delete($entityName, $objectID); >>  C<< my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName); >>
3382    
3383  Delete an entity instance from the database. The instance is deleted along with all entity and  Get the field hash of the named entity in the specified raw XML structure.
3384  relationship instances dependent on it. The idea of dependence here is recursive. An object is  The field hash may not exist, in which case we need to create it.
 always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many  
 relationship connected to a dependent entity or the "to" entity connected to a 1-to-many  
 dependent relationship.  
3385    
3386  =over 4  =over 4
3387    
3388  =item entityName  =item structure
   
 Name of the entity type for the instance being deleted.  
   
 =item objectID  
3389    
3390  ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),  Raw XML structure defininng the database. This is not the run-time XML used by
3391  then it is presumed to by a LIKE pattern.  an ERDB object, since that has all sorts of optimizations built-in.
3392    
3393  =item testFlag  =item entityName
3394    
3395  If TRUE, the delete statements will be traced without being executed.  Name of the entity whose field structure is desired.
3396    
3397  =item RETURN  =item RETURN
3398    
3399  Returns a statistics object indicating how many records of each particular table were  Returns the field hash used to define the entity's fields.
 deleted.  
3400    
3401  =back  =back
3402    
3403  =cut  =cut
3404  #: Return Type $%;  
3405  sub Delete {  sub GetEntityFieldHash {
3406      # Get the parameters.      # Get the parameters.
3407      my ($self, $entityName, $objectID, $testFlag) = @_;      my ($structure, $entityName) = @_;
3408      # Declare the return variable.      # Get the entity structure.
3409      my $retVal = Stats->new();      my $entityData = $structure->{Entities}->{$entityName};
3410      # Get the DBKernel object.      # Look for a field structure.
3411      my $db = $self->{_dbh};      my $retVal = $entityData->{Fields};
3412      # We're going to generate all the paths branching out from the starting entity. One of      # If it doesn't exist, create it.
3413      # the things we have to be careful about is preventing loops. We'll use a hash to      if (! defined($retVal)) {
3414      # determine if we've hit a loop.          $entityData->{Fields} = {};
3415      my %alreadyFound = ();          $retVal = $entityData->{Fields};
     # These next lists will serve as our result stack. We start by pushing object lists onto  
     # the stack, and then popping them off to do the deletes. This means the deletes will  
     # start with the longer paths before getting to the shorter ones. That, in turn, makes  
     # sure we don't delete records that might be needed to forge relationships back to the  
     # original item. We have two lists-- one for TO-relationships, and one for  
     # FROM-relationships and entities.  
     my @fromPathList = ();  
     my @toPathList = ();  
     # This final hash is used to remember what work still needs to be done. We push paths  
     # onto the list, then pop them off to extend the paths. We prime it with the starting  
     # point. Note that we will work hard to insure that the last item on a path in the  
     # TODO list is always an entity.  
     my @todoList = ([$entityName]);  
     while (@todoList) {  
         # Get the current path.  
         my $current = pop @todoList;  
         # Copy it into a list.  
         my @stackedPath = @{$current};  
         # Pull off the last item on the path. It will always be an entity.  
         my $entityName = pop @stackedPath;  
         # Add it to the alreadyFound list.  
         $alreadyFound{$entityName} = 1;  
         # Get the entity data.  
         my $entityData = $self->_GetStructure($entityName);  
         # The first task is to loop through the entity's relation. A DELETE command will  
         # be needed for each of them.  
         my $relations = $entityData->{Relations};  
         for my $relation (keys %{$relations}) {  
             my @augmentedList = (@stackedPath, $relation);  
             push @fromPathList, \@augmentedList;  
         }  
         # Now we need to look for relationships connected to this entity.  
         my $relationshipList = $self->{_metaData}->{Relationships};  
         for my $relationshipName (keys %{$relationshipList}) {  
             my $relationship = $relationshipList->{$relationshipName};  
             # Check the FROM field. We're only interested if it's us.  
             if ($relationship->{from} eq $entityName) {  
                 # Add the path to this relationship.  
                 my @augmentedList = (@stackedPath, $entityName, $relationshipName);  
                 push @fromPathList, \@augmentedList;  
                 # Check the arity. If it's MM we're done. If it's 1M  
                 # and the target hasn't been seen yet, we want to  
                 # stack the entity for future processing.  
                 if ($relationship->{arity} eq '1M') {  
                     my $toEntity = $relationship->{to};  
                     if (! exists $alreadyFound{$toEntity}) {  
                         # Here we have a new entity that's dependent on  
                         # the current entity, so we need to stack it.  
                         my @stackList = (@augmentedList, $toEntity);  
                         push @fromPathList, \@stackList;  
                     } else {  
                         Trace("$toEntity ignored because it occurred previously.") if T(4);  
                     }  
                 }  
             }  
             # Now check the TO field. In this case only the relationship needs  
             # deletion.  
             if ($relationship->{to} eq $entityName) {  
                 my @augmentedList = (@stackedPath, $entityName, $relationshipName);  
                 push @toPathList, \@augmentedList;  
             }  
         }  
     }  
     # Create the first qualifier for the WHERE clause. This selects the  
     # keys of the primary entity records to be deleted. When we're deleting  
     # from a dependent table, we construct a join page from the first qualifier  
     # to the table containing the dependent records to delete.  
     my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");  
     # We need to make two passes. The first is through the to-list, and  
     # the second through the from-list. The from-list is second because  
     # the to-list may need to pass through some of the entities the  
     # from-list would delete.  
     my %stackList = ( from_link => \@fromPathList, to_link => \@toPathList );  
     # Now it's time to do the deletes. We do it in two passes.  
     for my $keyName ('to_link', 'from_link') {  
         # Get the list for this key.  
         my @pathList = @{$stackList{$keyName}};  
         Trace(scalar(@pathList) . " entries in path list for $keyName.") if T(3);  
         # Loop through this list.  
         while (my $path = pop @pathList) {  
             # Get the table whose rows are to be deleted.  
             my @pathTables = @{$path};  
             # Start the DELETE statement. We need to call DBKernel because the  
             # syntax of a DELETE-USING varies among DBMSs.  
             my $target = $pathTables[$#pathTables];  
             my $stmt = $db->SetUsing(@pathTables);  
             # Now start the WHERE. The first thing is the ID field from the starting table. That  
             # starting table will either be the entity relation or one of the entity's  
             # sub-relations.  
             $stmt .= " WHERE $pathTables[0].id $qualifier";  
             # Now we run through the remaining entities in the path, connecting them up.  
             for (my $i = 1; $i <= $#pathTables; $i += 2) {  
                 # Connect the current relationship to the preceding entity.  
                 my ($entity, $rel) = @pathTables[$i-1,$i];  
                 # The style of connection depends on the direction of the relationship.  
                 $stmt .= " AND $entity.id = $rel.$keyName";  
                 if ($i + 1 <= $#pathTables) {  
                     # Here there's a next entity, so connect that to the relationship's  
                     # to-link.  
                     my $entity2 = $pathTables[$i+1];  
                     $stmt .= " AND $rel.to_link = $entity2.id";  
                 }  
             }  
             # Now we have our desired DELETE statement.  
             if ($testFlag) {  
                 # Here the user wants to trace without executing.  
                 Trace($stmt) if T(0);  
             } else {  
                 # Here we can delete. Note that the SQL method dies with a confessing  
                 # if an error occurs, so we just go ahead and do it.  
                 Trace("Executing delete from $target using '$objectID'.") if T(3);  
                 my $rv = $db->SQL($stmt, 0, $objectID);  
                 # Accumulate the statistics for this delete. The only rows deleted  
                 # are from the target table, so we use its name to record the  
                 # statistic.  
                 $retVal->Add($target, $rv);  
             }  
         }  
3416      }      }
3417      # Return the result.      # Return the result.
3418      return $retVal;      return $retVal;
3419  }  }
3420    
3421  =head3 GetList  =head3 WriteMetaXML
   
 C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  
3422    
3423  Return a list of object descriptors for the specified objects as determined by the  C<< ERDB::WriteMetaXML($structure, $fileName); >>
 specified filter clause.  
3424    
3425  This method is essentially the same as L</Get> except it returns a list of objects rather  Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
3426  than a query object that can be used to get the results one record at a time.  used to update the database definition. It must be used with care, however, since it
3427    will only work on a raw structure, not on the processed structure created by an ERDB
3428    constructor.
3429    
3430  =over 4  =over 4
3431    
3432  =item objectNames  =item structure
3433    
3434  List containing the names of the entity and relationship objects to be retrieved.  XML structure to be written to the file.
3435    
3436  =item filterClause  =item fileName
3437    
3438  WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  Name of the output file to which the updated XML should be stored.
 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.  
3439    
3440  The filter clause can also specify a sort order. To do this, simply follow the filter string  =back
 with an ORDER BY clause. For example, the following filter string gets all genomes for a  
 particular genus and sorts them by species name.  
3441    
3442  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>  =cut
3443    
3444  The rules for field references in a sort order are the same as those for field references in the  sub WriteMetaXML {
3445  filter clause in general; however, odd things may happen if a sort field is from a secondary      # Get the parameters.
3446  relation.      my ($structure, $fileName) = @_;
3447        # Compute the output.
3448        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
3449        # Write it to the file.
3450        my $xmlOut = Open(undef, ">$fileName");
3451        print $xmlOut $fileString;
3452    }
3453    
3454    
3455    =head3 HTMLNote
3456    
3457    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
3458    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
3459    Except for C<[p]>, all the codes are closed by slash-codes. So, for
3460    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
3461    
3462    C<< my $realHtml = ERDB::HTMLNote($dataString); >>
3463    
3464    =over 4
3465    
3466  =item param1, param2, ..., paramN  =item dataString
3467    
3468  Parameter values to be substituted into the filter clause.  String to convert to HTML.
3469    
3470  =item RETURN  =item RETURN
3471    
3472  Returns a list of B<DBObject>s that satisfy the query conditions.  An HTML string derived from the input string.
3473    
3474  =back  =back
3475    
3476  =cut  =cut
3477  #: Return Type @%  
3478  sub GetList {  sub HTMLNote {
3479      # Get the parameters.      # Get the parameter.
3480      my ($self, $objectNames, $filterClause, @params) = @_;      my ($dataString) = @_;
3481      # Declare the return variable.      # HTML-escape the text.
3482      my @retVal = ();      my $retVal = CGI::escapeHTML($dataString);
3483      # Perform the query.      # Substitute the bulletin board codes.
3484      my $query = $self->Get($objectNames, $filterClause, @params);      $retVal =~ s!\[(/?[bi])\]!<$1>!g;
3485      # Loop through the results.      $retVal =~ s!\[p\]!</p><p>!g;
3486      while (my $object = $query->Fetch) {      $retVal =~ s!\[link\s+([^\]]+)\]!<a href="$1">!g;
3487          push @retVal, $object;      $retVal =~ s!\[/link\]!</a>!g;
     }  
3488      # Return the result.      # Return the result.
3489      return @retVal;      return $retVal;
3490  }  }
3491    
3492  =head3 ComputeObjectSentence  =head3 BeginTran
3493    
3494  C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>  C<< $erdb->BeginTran(); >>
3495    
3496  Check an object name, and if it is a relationship convert it to a relationship sentence.  Start a database transaction.
3497    
3498  =over 4  =cut
3499    
3500  =item objectName  sub BeginTran {
3501        my ($self) = @_;
3502        $self->{_dbh}->begin_tran();
3503    
3504  Name of the entity or relationship.  }
3505    
3506  =item RETURN  =head3 CommitTran
3507    
3508  Returns a string containing the entity name or a relationship sentence.  C<< $erdb->CommitTran(); >>
3509    
3510  =back  Commit an active database transaction.
3511    
3512  =cut  =cut
3513    
3514  sub ComputeObjectSentence {  sub CommitTran {
3515      # Get the parameters.      my ($self) = @_;
3516      my ($self, $objectName) = @_;      $self->{_dbh}->commit_tran();
     # Set the default return value.  
     my $retVal = $objectName;  
     # Look for the object as a relationship.  
     my $relTable = $self->{_metaData}->{Relationships};  
     if (exists $relTable->{$objectName}) {  
         # Get the relationship sentence.  
         $retVal = _ComputeRelationshipSentence($objectName, $relTable->{$objectName});  
3517      }      }
3518      # Return the result.  
3519      return $retVal;  =head3 RollbackTran
3520    
3521    C<< $erdb->RollbackTran(); >>
3522    
3523    Roll back an active database transaction.
3524    
3525    =cut
3526    
3527    sub RollbackTran {
3528        my ($self) = @_;
3529        $self->{_dbh}->roll_tran();
3530  }  }
3531    
 =head3 DumpRelations  
3532    
3533  C<< $erdb->DumpRelations($outputDirectory); >>  =head2 Data Mining Methods
3534    
3535  Write the contents of all the relations to tab-delimited files in the specified directory.  =head3 GetUsefulCrossValues
3536  Each file will have the same name as the relation dumped, with an extension of DTX.  
3537    C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>
3538    
3539    Return a list of the useful attributes that would be returned by a B<Cross> call
3540    from an entity of the source entity type through the specified relationship. This
3541    means it will return the fields of the target entity type and the intersection data
3542    fields in the relationship. Only primary table fields are returned. In other words,
3543    the field names returned will be for fields where there is always one and only one
3544    value.
3545    
3546    =over 4
3547    
3548    =item sourceEntity
3549    
3550    Name of the entity from which the relationship crossing will start.
3551    
3552    =item relationship
3553    
3554  =over 4  Name of the relationship being crossed.
3555    
3556  =item outputDirectory  =item RETURN
3557    
3558  Name of the directory into which the relation files should be dumped.  Returns a list of field names in Sprout field format (I<objectName>C<(>I<fieldName>C<)>.
3559    
3560  =back  =back
3561    
3562  =cut  =cut
3563    #: Return Type @;
3564  sub DumpRelations {  sub GetUsefulCrossValues {
3565      # Get the parameters.      # Get the parameters.
3566      my ($self, $outputDirectory) = @_;      my ($self, $sourceEntity, $relationship) = @_;
3567      # Now we need to run through all the relations. First, we loop through the entities.      # Declare the return variable.
3568      my $metaData = $self->{_metaData};      my @retVal = ();
3569      my $entities = $metaData->{Entities};      # Determine the target entity for the relationship. This is whichever entity is not
3570      for my $entityName (keys %{$entities}) {      # the source entity. So, if the source entity is the FROM, we'll get the name of
3571          my $entityStructure = $entities->{$entityName};      # the TO, and vice versa.
3572          # Get the entity's relations.      my $relStructure = $self->_GetStructure($relationship);
3573          my $relationList = $entityStructure->{Relations};      my $targetEntityType = ($relStructure->{from} eq $sourceEntity ? "to" : "from");
3574          # Loop through the relations, dumping them.      my $targetEntity = $relStructure->{$targetEntityType};
3575          for my $relationName (keys %{$relationList}) {      # Get the field table for the entity.
3576              my $relation = $relationList->{$relationName};      my $entityFields = $self->GetFieldTable($targetEntity);
3577              $self->_DumpRelation($outputDirectory, $relationName, $relation);      # The field table is a hash. The hash key is the field name. The hash value is a structure.
3578          }      # For the entity fields, the key aspect of the target structure is that the {relation} value
3579      }      # must match the entity name.
3580      # Next, we loop through the relationships.      my @fieldList = map { "$targetEntity($_)" } grep { $entityFields->{$_}->{relation} eq $targetEntity }
3581      my $relationships = $metaData->{Relationships};                          keys %{$entityFields};
3582      for my $relationshipName (keys %{$relationships}) {      # Push the fields found onto the return variable.
3583          my $relationshipStructure = $relationships->{$relationshipName};      push @retVal, sort @fieldList;
3584          # Dump this relationship's relation.      # Get the field table for the relationship.
3585          $self->_DumpRelation($outputDirectory, $relationshipName, $relationshipStructure->{Relations}->{$relationshipName});      my $relationshipFields = $self->GetFieldTable($relationship);
3586      }      # Here we have a different rule. We want all the fields other than "from-link" and "to-link".
3587        # This may end up being an empty set.
3588        my @fieldList2 = map { "$relationship($_)" } grep { $_ ne "from-link" && $_ ne "to-link" }
3589                            keys %{$relationshipFields};
3590        # Push these onto the return list.
3591        push @retVal, sort @fieldList2;
3592        # Return the result.
3593        return @retVal;
3594  }  }
3595    
3596  =head3 InsertObject  =head3 FindColumn
   
 C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>  
   
 Insert an object into the database. The object is defined by a type name and then a hash  
 of field names to values. Field values in the primary relation are represented by scalars.  
 (Note that for relationships, the primary relation is the B<only> relation.)  
 Field values for the other relations comprising the entity are always list references. For  
 example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases  
 C<ZP_00210270.1> and C<gi|46206278>.  
   
 C<< $erdb->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>  
3597    
3598  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and  C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>
 property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.  
3599    
3600  C<< $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>  Return the location a desired column in a data mining header line. The data
3601    mining header line is a tab-separated list of column names. The column
3602    identifier is either the numerical index of a column or the actual column
3603    name.
3604    
3605  =over 4  =over 4
3606    
3607  =item newObjectType  =item headerLine
3608    
3609  Type name of the object to insert.  The header line from a data mining command, which consists of a tab-separated
3610    list of column names.
3611    
3612  =item fieldHash  =item columnIdentifier
3613    
3614  Hash of field names to values.  Either the ordinal number of the desired column (1-based), or the name of the
3615    desired column.
3616    
3617  =item RETURN  =item RETURN
3618    
3619  Returns 1 if successful, 0 if an error occurred.  Returns the array index (0-based) of the desired column.
3620    
3621  =back  =back
3622    
3623  =cut  =cut
3624    
3625  sub InsertObject {  sub FindColumn {
3626      # Get the parameters.      # Get the parameters.
3627      my ($self, $newObjectType, $fieldHash) = @_;      my ($headerLine, $columnIdentifier) = @_;
3628      # Denote that so far we appear successful.      # Declare the return variable.
3629      my $retVal = 1;      my $retVal;
3630      # Get the database handle.      # Split the header line into column names.
3631      my $dbh = $self->{_dbh};      my @headers = ParseColumns($headerLine);
3632      # Get the relation list.      # Determine whether we have a number or a name.
3633      my $relationTable = $self->_GetRelationTable($newObjectType);      if ($columnIdentifier =~ /^\d+$/) {
3634      # Loop through the relations. We'll build insert statements for each one. If a relation is          # Here we have a number. Subtract 1 and validate the result.
3635      # secondary, we may end up generating multiple insert statements. If an error occurs, we          $retVal = $columnIdentifier - 1;
3636      # stop the loop.          if ($retVal < 0 || $retVal > $#headers) {
3637      my @relationList = keys %{$relationTable};              Confess("Invalid column identifer \"$columnIdentifier\": value out of range.");
     for (my $i = 0; $retVal && $i <= $#relationList; $i++) {  
         my $relationName = $relationList[$i];  
         my $relationDefinition = $relationTable->{$relationName};  
         # Get the relation's fields. For each field we will collect a value in the corresponding  
         # position of the @valueList array. If one of the fields is missing, we will add it to the  
         # @missing list.  
         my @fieldList = @{$relationDefinition->{Fields}};  
         my @fieldNameList = ();  
         my @valueList = ();  
         my @missing = ();  
         my $recordCount = 1;  
         for my $fieldDescriptor (@fieldList) {  
             # Get the field name and save it. Note we need to fix it up so the hyphens  
             # are converted to underscores.  
             my $fieldName = $fieldDescriptor->{name};  
             push @fieldNameList, _FixName($fieldName);  
             # Look for the named field in the incoming structure. Note that we are looking  
             # for the real field name, not the fixed-up one!  
             if (exists $fieldHash->{$fieldName}) {  
                 # Here we found the field. Stash it in the value list.  
                 my $value = $fieldHash->{$fieldName};  
                 push @valueList, $value;  
                 # If the value is a list, we may need to increment the record count.  
                 if (ref $value eq "ARRAY") {  
                     my $thisCount = @{$value};  
                     if ($recordCount == 1) {  
                         # Here we have our first list, so we save its count.  
                         $recordCount = $thisCount;  
                     } elsif ($recordCount != $thisCount) {  
                         # Here we have a second list, so its length has to match the  
                         # previous lists.  
                         Trace("Field $value in new $newObjectType object has an invalid list length $thisCount. Expected $recordCount.") if T(0);  
                         $retVal = 0;  
                     }  
                 }  
             } else {  
                 # Here the field is not present. Flag it as missing.  
                 push @missing, $fieldName;  
             }  
         }  
         # If we are the primary relation, add the new-record flag.  
         if ($relationName eq $newObjectType) {  
             push @valueList, 1;  
             push @fieldNameList, "new_record";  
3638          }          }
         # Only proceed if there are no missing fields.  
         if (@missing > 0) {  
             Trace("Relation $relationName for $newObjectType skipped due to missing fields: " .  
                 join(' ', @missing)) if T(1);  
         } else {  
             # Build the INSERT statement.  
             my $statement = "INSERT INTO $relationName (" . join (', ', @fieldNameList) .  
                 ") VALUES (";  
             # Create a marker list of the proper size and put it in the statement.  
             my @markers = ();  
             while (@markers < @fieldNameList) { push @markers, '?'; }  
             $statement .= join(', ', @markers) . ")";  
             # We have the insert statement, so prepare it.  
             my $sth = $dbh->prepare_command($statement);  
             Trace("Insert statement prepared: $statement") if T(3);  
             # Now we loop through the values. If a value is scalar, we use it unmodified. If it's  
             # a list, we use the current element. The values are stored in the @parameterList array.  
             my $done = 0;  
             for (my $i = 0; $i < $recordCount; $i++) {  
                 # Clear the parameter list array.  
                 my @parameterList = ();  
                 # Loop through the values.  
                 for my $value (@valueList) {  
                     # Check to see if this is a scalar value.  
                     if (ref $value eq "ARRAY") {  
                         # Here we have a list value. Pull the current entry.  
                         push @parameterList, $value->[$i];  
3639                      } else {                      } else {
3640                          # Here we have a scalar value. Use it unmodified.          # Here we have a name. We need to find it in the list.
3641                          push @parameterList, $value;          for (my $i = 0; $i <= $#headers && ! defined($retVal); $i++) {
3642                      }              if ($headers[$i] eq $columnIdentifier) {
3643                  }                  $retVal = $i;
                 # Execute the INSERT statement with the specified parameter list.  
                 $retVal = $sth->execute(@parameterList);  
                 if (!$retVal) {  
                     my $errorString = $sth->errstr();  
                     Trace("Insert error: $errorString.") if T(0);  
3644                  }                  }
3645              }              }
3646            if (! defined($retVal)) {
3647                Confess("Invalid column identifier \"$columnIdentifier\": value not found.");
3648          }          }
3649      }      }
3650      # Return the success indicator.      # Return the result.
3651      return $retVal;      return $retVal;
3652  }  }
3653    
3654  =head3 LoadTable  =head3 ParseColumns
3655    
3656  C<< my %results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>  C<< my @columns = ERDB::ParseColumns($line); >>
3657    
3658  Load data from a tab-delimited file into a specified table, optionally re-creating the table  Convert the specified data line to a list of columns.
 first.  
3659    
3660  =over 4  =over 4
3661    
3662  =item fileName  =item line
3663    
3664  Name of the file from which the table data should be loaded.  A data mining input, consisting of a tab-separated list of columns terminated by a
3665    new-line.
3666    
3667  =item relationName  =item RETURN
3668    
3669  Name of the relation to be loaded. This is the same as the table name.  Returns a list consisting of the column values.
3670    
3671  =item truncateFlag  =back
3672    
3673  TRUE if the table should be dropped and re-created, else FALSE  =cut
3674    
3675    sub ParseColumns {
3676        # Get the parameters.
3677        my ($line) = @_;
3678        # Chop off the line-end.
3679        chomp $line;
3680        # Split it into a list.
3681        my @retVal = split(/\t/, $line);
3682        # Return the result.
3683        return @retVal;
3684    }
3685    
3686    =head2 Virtual Methods
3687    
3688    =head3 _CreatePPOIndex
3689    
3690    C<< my $index = ERDB::_CreatePPOIndex($indexObject); >>
3691    
3692    Convert the XML for an ERDB index to the XML structure for a PPO
3693    index.
3694    
3695    =over 4
3696    
3697    ERDB XML structure for an index.
3698    
3699  =item RETURN  =item RETURN
3700    
3701  Returns a statistical object containing a list of the error messages.  PPO XML structure for the same index.
3702    
3703  =back  =back
3704    
3705  =cut  =cut
3706  sub LoadTable {  
3707      # Get the parameters.  sub _CreatePPOIndex {
3708      my ($self, $fileName, $relationName, $truncateFlag) = @_;      # Get the parameters.
3709      # Create the statistical return object.      my ($indexObject) = @_;
3710      my $retVal = _GetLoadStats();      # The incoming index contains a list of the index fields in the IndexFields
3711      # Trace the fact of the load.      # member. We loop through it to create the index tags.
3712      Trace("Loading table $relationName from $fileName") if T(2);      my @fields = map { { label => _FixName($_->{name}) } } @{$indexObject->{IndexFields}};
3713      # Get the database handle.      # Wrap the fields in attribute tags.
3714      my $dbh = $self->{_dbh};      my $retVal = { attribute => \@fields };
3715      # Get the input file size.      # Return the result.
     my $fileSize = -s $fileName;  
     # Get the relation data.  
     my $relation = $self->_FindRelation($relationName);  
     # Check the truncation flag.  
     if ($truncateFlag) {  
         Trace("Creating table $relationName") if T(2);  
         # Compute the row count estimate. We take the size of the load file,  
         # divide it by the estimated row size, and then multiply by 1.5 to  
         # leave extra room. We postulate a minimum row count of 1000 to  
         # prevent problems with incoming empty load files.  
         my $rowSize = $self->EstimateRowSize($relationName);  
         my $estimate = FIG::max($fileSize * 1.5 / $rowSize, 1000);  
         # Re-create the table without its index.  
         $self->CreateTable($relationName, 0, $estimate);  
         # If this is a pre-index DBMS, create the index here.  
         if ($dbh->{_preIndex}) {  
             eval {  
                 $self->CreateIndex($relationName);  
             };  
             if ($@) {  
                 $retVal->AddMessage($@);  
             }  
         }  
     }  
     # Load the table.  
     my $rv;  
     eval {  
         $rv = $dbh->load_table(file => $fileName, tbl => $relationName);  
     };  
     if (!defined $rv) {  
         $retVal->AddMessage($@) if ($@);  
         $retVal->AddMessage("Table load failed for $relationName using $fileName.");  
         Trace("Table load failed for $relationName.") if T(1);  
     } else {  
         # Here we successfully loaded the table.  
         $retVal->Add("tables");  
         my $size = -s $fileName;  
         Trace("$size bytes loaded into $relationName.") if T(2);  
         # If we're rebuilding, we need to create the table indexes.  
         if ($truncateFlag && ! $dbh->{_preIndex}) {  
             eval {  
                 $self->CreateIndex($relationName);  
             };  
             if ($@) {  
                 $retVal->AddMessage($@);  
             }  
         }  
     }  
     # Analyze the table to improve performance.  
     $dbh->vacuum_it($relationName);  
     # Return the statistics.  
3716      return $retVal;      return $retVal;
3717  }  }
3718    
3719  =head3 GenerateEntity  =head3 _CreatePPOField
3720    
3721  C<< my $fieldHash = $erdb->GenerateEntity($id, $type, \%values); >>  C<< my $fieldXML = ERDB::_CreatePPOField($fieldName, $fieldObject); >>
3722    
3723  Generate the data for a new entity instance. This method creates a field hash suitable for  Convert the ERDB XML structure for a field to a PPO scalar XML structure.
 passing as a parameter to L</InsertObject>. The ID is specified by the callr, but the rest  
 of the fields are generated using information in the database schema.  
   
 Each data type has a default algorithm for generating random test data. This can be overridden  
 by including a B<DataGen> element in the field. If this happens, the content of the element is  
 executed as a PERL program in the context of this module. The element may make use of a C<$this>  
 variable which contains the field hash as it has been built up to the current point. If any  
 fields are dependent on other fields, the C<pass> attribute can be used to control the order  
 in which the fields are generated. A field with a high data pass number will be generated after  
 a field with a lower one. If any external values are needed, they should be passed in via the  
 optional third parameter, which will be available to the data generation script under the name  
 C<$value>. Several useful utility methods are provided for generating random values, including  
 L</IntGen>, L</StringGen>, L</FloatGen>, and L</DateGen>. Note that dates are stored and generated  
 in the form of a timestamp number rather than a string.  
3724    
3725  =over 4  =over 4
3726    
3727  =item id  =item fieldName
3728    
3729  ID to assign to the new entity.  Name of the scalar field.
3730    
3731  =item type  =item fieldObject
3732    
3733  Type name for the new entity.  ERDB XML structure describing the field.
3734    
3735  =item values  =item RETURN
3736    
3737  Hash containing additional values that might be needed by the data generation methods (optional).  Returns a PPO XML structure for the same field.
3738    
3739  =back  =back
3740    
3741  =cut  =cut
3742    
3743  sub GenerateEntity {  sub _CreatePPOField {
3744      # Get the parameters.      # Get the parameters.
3745      my ($self, $id, $type, $values) = @_;      my ($fieldName, $fieldObject) = @_;
3746      # Create the return hash.      # Get the field type.
3747      my $this = { id => $id };      my $type = $TypeTable{$fieldObject->{type}}->{sqlType};
3748      # Get the metadata structure.      # Fix up the field name.
3749      my $metadata = $self->{_metaData};      $fieldName = _FixName($fieldName);
3750      # Get this entity's list of fields.      # Build the scalar tag.
3751      if (!exists $metadata->{Entities}->{$type}) {      my $retVal = { label => $fieldName, type => $type };
3752          Confess("Unrecognized entity type $type in GenerateEntity.");      # Return the result.
3753      } else {      return $retVal;
         my $entity = $metadata->{Entities}->{$type};  
         my $fields = $entity->{Fields};  
         # Generate data from the fields.  
         _GenerateFields($this, $fields, $type, $values);  
     }  
     # Return the hash created.  
     return $this;  
3754  }  }
3755    
3756  =head3 GetEntity  =head3 CleanKeywords
3757    
3758  C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>  C<< my $cleanedString = $erdb->CleanKeywords($searchExpression); >>
3759    
3760  Return an object describing the entity instance with a specified ID.  Clean up a search expression or keyword list. This is a virtual method that may
3761    be overridden by the subclass. The base-class method removes extra spaces
3762    and converts everything to lower case.
3763    
3764  =over 4  =over 4
3765    
3766  =item entityType  =item searchExpression
   
 Entity type name.  
   
 =item ID  
3767    
3768  ID of the desired entity.  Search expression or keyword list to clean. Note that a search expression may
3769    contain boolean operators which need to be preserved. This includes leading
3770    minus signs.
3771    
3772  =item RETURN  =item RETURN
3773    
3774  Returns a B<DBObject> representing the desired entity instance, or an undefined value if no  Cleaned expression or keyword list.
 instance is found with the specified key.  
3775    
3776  =back  =back
3777    
3778  =cut  =cut
3779    
3780  sub GetEntity {  sub CleanKeywords {
3781      # Get the parameters.      # Get the parameters.
3782      my ($self, $entityType, $ID) = @_;      my ($self, $searchExpression) = @_;
3783      # Create a query.      # Lower-case the expression and copy it into the return variable. Note that we insure we
3784      my $query = $self->Get([$entityType], "$entityType(id) = ?", $ID);      # don't accidentally end up with an undefined value.
3785      # Get the first (and only) object.      my $retVal = lc($searchExpression || "");
3786      my $retVal = $query->Fetch();      # Remove extra spaces.
3787        $retVal =~ s/\s+/ /g;
3788        $retVal =~ s/(^\s+)|(\s+$)//g;
3789      # Return the result.      # Return the result.
3790      return $retVal;      return $retVal;
3791  }  }
3792    
3793  =head3 GetEntityValues  =head3 GetSourceObject
3794    
3795  C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>  C<< my $source = $erdb->GetSourceObject($entityName); >>
3796    
3797  Return a list of values from a specified entity instance.  Return the object to be used in loading special attributes of the specified entity. The
3798    algorithm for loading special attributes is stored in the C<DataGen> elements of the
3799    XML
3800    
3801  =over 4  =head2 Internal Utility Methods
3802    
3803  =item entityType  =head3 _RelationMap
3804    
3805  Entity type name.  C<< my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef); >>
3806    
3807  =item ID  Create the relation map for an SQL query. The relation map is used by B<ERDBObject>
3808    to determine how to interpret the results of the query.
3809    
3810  ID of the desired entity.  =over 4
3811    
3812  =item fields  =item mappedNameHashRef
3813    
3814  List of field names, each of the form I<objectName>C<(>I<fieldName>C<)>.  Reference to a hash that maps modified object names to real object names.
3815    
3816    =item mappedNameListRef
3817    
3818    Reference to a list of modified object names in the order they appear in the
3819    SELECT list.
3820    
3821  =item RETURN  =item RETURN
3822    
3823  Returns a flattened list of the values of the specified fields for the specified entity.  Returns a list of 2-tuples. Each tuple consists of an object name as used in the
3824    query followed by the actual name of that object. This enables the B<ERDBObject> to
3825    determine the order of the tables in the query and which object name belongs to each
3826    mapped object name. Most of the time these two values are the same; however, if a
3827    relation occurs twice in the query, the relation name in the field list and WHERE
3828    clause will use a mapped name (generally the actual relation name with a numeric
3829    suffix) that does not match the actual relation name.
3830    
3831  =back  =back
3832    
3833  =cut  =cut
3834    
3835  sub GetEntityValues {  sub _RelationMap {
3836      # Get the parameters.      # Get the parameters.
3837      my ($self, $entityType, $ID, $fields) = @_;      my ($mappedNameHashRef, $mappedNameListRef) = @_;
3838      # Get the specified entity.      # Declare the return variable.
     my $entity = $self->GetEntity($entityType, $ID);  
     # Declare the return list.  
3839      my @retVal = ();      my @retVal = ();
3840      # If we found the entity, push the values into the return list.      # Build the map.
3841      if ($entity) {      for my $mappedName (@{$mappedNameListRef}) {
3842          push @retVal, $entity->Values($fields);          push @retVal, [$mappedName, $mappedNameHashRef->{$mappedName}];
3843      }      }
3844      # Return the result.      # Return it.
3845      return @retVal;      return @retVal;
3846  }  }
3847    
 =head3 GetAll  
   
 C<< my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>  
3848    
3849  Return a list of values taken from the objects returned by a query. The first three  =head3 _SetupSQL
 parameters correspond to the parameters of the L</Get> method. The final parameter is  
 a list of the fields desired from each record found by the query. The field name  
 syntax is the standard syntax used for fields in the B<ERDB> system--  
 B<I<objectName>(I<fieldName>)>-- where I<objectName> is the name of the relevant entity  
 or relationship and I<fieldName> is the name of the field.  
3850    
3851  The list returned will be a list of lists. Each element of the list will contain  Process a list of object names and a filter clause so that they can be used to
3852  the values returned for the fields specified in the fourth parameter. If one of the  build an SQL statement. This method takes in a reference to a list of object names
3853  fields specified returns multiple values, they are flattened in with the rest. For  and a filter clause. It will return a corrected filter clause, a list of mapped
3854  example, the following call will return a list of the features in a particular  names and the mapped name hash.
 spreadsheet cell, and each feature will be represented by a list containing the  
 feature ID followed by all of its aliases.  
3855    
3856  C<< $query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>  This is an instance method.
3857    
3858  =over 4  =over 4
3859    
3860  =item objectNames  =item objectNames
3861    
3862  List containing the names of the entity and relationship objects to be retrieved.  Reference to a list of the object names to be included in the query.
3863    
3864  =item filterClause  =item filterClause
3865    
3866  WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  A string containing the WHERE clause for the query (without the C<WHERE>) and also
3867  be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form  optionally the C<ORDER BY> and C<LIMIT> clauses.
 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.  
   
 =item parameterList  
   
 List of the parameters to be substituted in for the parameters marks in the filter clause.  
   
 =item fields  
   
 List of the fields to be returned in each element of the list returned.  
3868    
3869  =item count  =item matchClause
3870    
3871  Maximum number of records to return. If omitted or 0, all available records will be returned.  An optional full-text search clause. If specified, it will be inserted at the
3872    front of the WHERE clause. It should already be SQL-formatted; that is, the
3873    field names should be in the form I<table>C<.>I<fieldName>.
3874    
3875  =item RETURN  =item RETURN
3876    
3877  Returns a list of list references. Each element of the return list contains the values for the  Returns a three-element list. The first element is the SQL statement suffix, beginning
3878  fields specified in the B<fields> parameter.  with the FROM clause. The second element is a reference to a list of the names to be
3879    used in retrieving the fields. The third element is a hash mapping the names to the
3880    objects they represent.
3881    
3882  =back  =back
3883    
3884  =cut  =cut
3885  #: Return Type @@;  
3886  sub GetAll {  sub _SetupSQL {
3887      # Get the parameters.      my ($self, $objectNames, $filterClause, $matchClause) = @_;
3888      my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;      # Adjust the list of object names to account for multiple occurrences of the
3889      # Translate the parameters from a list reference to a list. If the parameter      # same object. We start with a hash table keyed on object name that will
3890      # list is a scalar we convert it into a singleton list.      # return the object suffix. The first time an object is encountered it will
3891      my @parmList = ();      # not be found in the hash. The next time the hash will map the object name
3892      if (ref $parameterList eq "ARRAY") {      # to 2, then 3, and so forth.
3893          @parmList = @{$parameterList};      my %objectHash = ();
3894        # This list will contain the object names as they are to appear in the
3895        # FROM list.
3896        my @fromList = ();
3897        # This list contains the suffixed object name for each object. It is exactly
3898        # parallel to the list in the $objectNames parameter.
3899        my @mappedNameList = ();
3900        # Finally, this hash translates from a mapped name to its original object name.
3901        my %mappedNameHash = ();
3902        # Now we create the lists. Note that for every single name we push something into
3903        # @fromList and @mappedNameList. This insures that those two arrays are exactly
3904        # parallel to $objectNames.
3905        for my $objectName (@{$objectNames}) {
3906            # Get the next suffix for this object.
3907            my $suffix = $objectHash{$objectName};
3908            if (! $suffix) {
3909                # Here we are seeing the object for the first time. The object name
3910                # is used as is.
3911                push @mappedNameList, $objectName;
3912                push @fromList, $objectName;
3913                $mappedNameHash{$objectName} = $objectName;
3914                # Denote the next suffix will be 2.
3915                $objectHash{$objectName} = 2;
3916      } else {      } else {
3917          push @parmList, $parameterList;              # Here we've seen the object before. We construct a new name using
3918                # the suffix from the hash and update the hash.
3919                my $mappedName = "$objectName$suffix";
3920                $objectHash{$objectName} = $suffix + 1;
3921                # The FROM list has the object name followed by the mapped name. This
3922                # tells SQL it's still the same table, but we're using a different name
3923                # for it to avoid confusion.
3924                push @fromList, "$objectName $mappedName";
3925                # The mapped-name list contains the real mapped name.
3926                push @mappedNameList, $mappedName;
3927                # Finally, enable us to get back from the mapped name to the object name.
3928                $mappedNameHash{$mappedName} = $objectName;
3929      }      }
     # Insure the counter has a value.  
     if (!defined $count) {  
         $count = 0;  
3930      }      }
3931      # Add the row limit to the filter clause.      # Begin the SELECT suffix. It starts with
3932      if ($count > 0) {      #
3933          $filterClause .= " LIMIT $count";      # FROM name1, name2, ... nameN
3934        #
3935        my $suffix = "FROM " . join(', ', @fromList);
3936        # Now for the WHERE. First, we need a place for the filter string.
3937        my $filterString = "";
3938        # We will also keep a list of conditions to add to the WHERE clause in order to link
3939        # entities and relationships as well as primary relations to secondary ones.
3940        my @joinWhere = ();
3941        # Check for a filter clause.
3942        if ($filterClause) {
3943            # Here we have one, so we convert its field names and add it to the query. First,
3944            # We create a copy of the filter string we can work with.
3945            $filterString = $filterClause;
3946            # Next, we sort the object names by length. This helps protect us from finding
3947            # object names inside other object names when we're doing our search and replace.
3948            my @sortedNames = sort { length($b) - length($a) } @mappedNameList;
3949            # The final preparatory step is to create a hash table of relation names. The
3950            # table begins with the relation names already in the SELECT command. We may
3951            # need to add relations later if there is filtering on a field in a secondary
3952            # relation. The secondary relations are the ones that contain multiply-
3953            # occurring or optional fields.
3954            my %fromNames = map { $_ => 1 } @sortedNames;
3955            # We are ready to begin. We loop through the object names, replacing each
3956            # object name's field references by the corresponding SQL field reference.
3957            # Along the way, if we find a secondary relation, we will need to add it
3958            # to the FROM clause.
3959            for my $mappedName (@sortedNames) {
3960                # Get the length of the object name plus 2. This is the value we add to the
3961                # size of the field name to determine the size of the field reference as a
3962                # whole.
3963                my $nameLength = 2 + length $mappedName;
3964                # Get the real object name for this mapped name.
3965                my $objectName = $mappedNameHash{$mappedName};
3966                Trace("Processing $mappedName for object $objectName.") if T(4);
3967                # Get the object's field list.
3968                my $fieldList = $self->GetFieldTable($objectName);
3969                # Find the field references for this object.
3970                while ($filterString =~ m/$mappedName\(([^)]*)\)/g) {
3971                    # At this point, $1 contains the field name, and the current position
3972                    # is set immediately after the final parenthesis. We pull out the name of
3973                    # the field and the position and length of the field reference as a whole.
3974                    my $fieldName = $1;
3975                    my $len = $nameLength + length $fieldName;
3976                    my $pos = pos($filterString) - $len;
3977                    # Insure the field exists.
3978                    if (!exists $fieldList->{$fieldName}) {
3979                        Confess("Field $fieldName not found for object $objectName.");
3980                    } else {
3981                        Trace("Processing $fieldName at position $pos.") if T(4);
3982                        # Get the field's relation.
3983                        my $relationName = $fieldList->{$fieldName}->{relation};
3984                        # Now we have a secondary relation. We need to insure it matches the
3985                        # mapped name of the primary relation. First we peel off the suffix
3986                        # from the mapped name.
3987                        my $mappingSuffix = substr $mappedName, length($objectName);
3988                        # Put the mapping suffix onto the relation name to get the
3989                        # mapped relation name.
3990                        my $mappedRelationName = "$relationName$mappingSuffix";
3991                        # Insure the relation is in the FROM clause.
3992                        if (!exists $fromNames{$mappedRelationName}) {
3993                            # Add the relation to the FROM clause.
3994                            if ($mappedRelationName eq $relationName) {
3995                                # The name is un-mapped, so we add it without
3996                                # any frills.
3997                                $suffix .= ", $relationName";
3998                                push @joinWhere, "$objectName.id = $relationName.id";
3999                            } else {
4000                                # Here we have a mapping situation.
4001                                $suffix .= ", $relationName $mappedRelationName";
4002                                push @joinWhere, "$mappedRelationName.id = $mappedName.id";
4003                            }
4004                            # Denote we have this relation available for future fields.
4005                            $fromNames{$mappedRelationName} = 1;
4006                        }
4007                        # Form an SQL field reference from the relation name and the field name.
4008                        my $sqlReference = "$mappedRelationName." . _FixName($fieldName);
4009                        # Put it into the filter string in place of the old value.
4010                        substr($filterString, $pos, $len) = $sqlReference;
4011                        # Reposition the search.
4012                        pos $filterString = $pos + length $sqlReference;
4013                    }
4014                }
4015            }
4016        }
4017        # The next step is to join the objects together. We only need to do this if there
4018        # is more than one object in the object list. We start with the first object and
4019        # run through the objects after it. Note also that we make a safety copy of the
4020        # list before running through it, because we shift off the first object before
4021        # processing the rest.
4022        my @mappedObjectList = @mappedNameList;
4023        my $lastMappedObject = shift @mappedObjectList;
4024        # Get the join table.
4025        my $joinTable = $self->{_metaData}->{Joins};
4026        # Loop through the object list.
4027        for my $thisMappedObject (@mappedObjectList) {
4028            # Look for a join using the real object names.
4029            my $lastObject = $mappedNameHash{$lastMappedObject};
4030            my $thisObject = $mappedNameHash{$thisMappedObject};
4031            my $joinKey = "$lastObject/$thisObject";
4032            if (!exists $joinTable->{$joinKey}) {
4033                # Here there's no join, so we throw an error.
4034                Confess("No join exists to connect from $lastMappedObject to $thisMappedObject.");
4035            } else {
4036                # Get the join clause.
4037                my $unMappedJoin = $joinTable->{$joinKey};
4038                # Fix the names.
4039                $unMappedJoin =~ s/$lastObject/$lastMappedObject/;
4040                $unMappedJoin =~ s/$thisObject/$thisMappedObject/;
4041                push @joinWhere, $unMappedJoin;
4042                # Save this object as the last object for the next iteration.
4043                $lastMappedObject = $thisMappedObject;
4044            }
4045        }
4046        # Now we need to handle the whole ORDER BY / LIMIT thing. The important part
4047        # here is we want the filter clause to be empty if there's no WHERE filter.
4048        # We'll put the ORDER BY / LIMIT clauses in the following variable.
4049        my $orderClause = "";
4050        # This is only necessary if we have a filter string in which the ORDER BY
4051        # and LIMIT clauses can live.
4052        if ($filterString) {
4053            # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy
4054            # operator so that we find the first occurrence of either verb.
4055            if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {
4056                # Here we have an ORDER BY or LIMIT verb. Split it off of the filter string.
4057                my $pos = pos $filterString;
4058                $orderClause = $2 . substr($filterString, $pos);
4059                $filterString = $1;
4060            }
4061      }      }
4062      # Create the query.      # All the things that are supposed to be in the WHERE clause of the
4063      my $query = $self->Get($objectNames, $filterClause, @parmList);      # SELECT command need to be put into @joinWhere so we can string them
4064      # Set up a counter of the number of records read.      # together. We begin with the match clause. This is important,
4065      my $fetched = 0;      # because the match clause's parameter mark must precede any parameter
4066      # Loop through the records returned, extracting the fields. Note that if the      # marks in the filter string.
4067      # counter is non-zero, we stop when the number of records read hits the count.      if ($matchClause) {
4068      my @retVal = ();          push @joinWhere, $matchClause;
     while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {  
         my @rowData = $row->Values($fields);  
      &nb