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

Diff of /Sprout/ERDB.pm

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

revision 1.19, Fri Sep 9 14:50:58 2005 UTC revision 1.82, Tue Jan 9 01:49:57 2007 UTC
# Line 9  Line 9 
9      use DBObject;      use DBObject;
10      use Stats;      use Stats;
11      use Time::HiRes qw(gettimeofday);      use Time::HiRes qw(gettimeofday);
12        use Digest::MD5 qw(md5_base64);
13      use FIG;      use FIG;
14        use CGI;
15    
16  =head1 Entity-Relationship Database Package  =head1 Entity-Relationship Database Package
17    
# Line 58  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 90  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 109  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 125  Line 135 
135    
136  variable-length string, maximum 255 characters  variable-length string, maximum 255 characters
137    
138    =item hash-string
139    
140    variable-length string, maximum 22 characters
141    
142  =back  =back
143    
144    The hash-string data type has a special meaning. The actual key passed into the loader will
145    be a string, but it will be digested into a 22-character MD5 code to save space. Although the
146    MD5 algorithm is not perfect, it is extremely unlikely two strings will have the same
147    digest. Therefore, it is presumed the keys will be unique. When the database is actually
148    in use, the hashed keys will be presented rather than the original values. For this reason,
149    they should not be used for entities where the key is meaningful.
150    
151  =head3 Global Tags  =head3 Global Tags
152    
153  The entire database definition must be inside a B<Database> tag. The display name of  The entire database definition must be inside a B<Database> tag. The display name of
# Line 170  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 189  Line 212 
212  entity, the fields without a relation attribute are said to belong to the  entity, the fields without a relation attribute are said to belong to the
213  I<primary relation>. This relation has the same name as the entity itself.  I<primary relation>. This relation has the same name as the entity itself.
214    
215    =item searchable
216    
217    If specified, then the field is a candidate for full-text searching. A single full-text
218    index will be created for each relation with at least one searchable field in it.
219    For best results, this option should only be used for string or text fields.
220    
221    =item special
222    
223    This attribute allows the subclass to assign special meaning for certain fields.
224    The interpretation is up to the subclass itself. Currently, only entity fields
225    can have this attribute.
226    
227  =back  =back
228    
229  =head3 Indexes  =head3 Indexes
230    
231  An entity can have multiple alternate indexes associated with it. The fields must  An entity can have multiple alternate indexes associated with it. The fields must
232  be from the primary relation. The alternate indexes assist in ordering results  all be from the same relation. The alternate indexes assist in ordering results
233  from a query. A relationship can have up to two indexes-- a I<to-index> and a  from a query. A relationship can have up to two indexes-- a I<to-index> and a
234  I<from-index>. These order the results when crossing the relationship. For  I<from-index>. These order the results when crossing the relationship. For
235  example, in the relationship C<HasContig> from C<Genome> to C<Contig>, the  example, in the relationship C<HasContig> from C<Genome> to C<Contig>, the
# Line 222  Line 257 
257    
258  =back  =back
259    
260  The B<Index>, B<FromIndex>, and B<ToIndex> tags themselves have no attributes.  The B<FromIndex>, and B<ToIndex> tags have no attributes. The B<Index> tag can
261    have a B<Unique> attribute. If specified, the index will be generated as a unique
262    index.
263    
264  =head3 Object and Field Names  =head3 Object and Field Names
265    
# Line 300  Line 337 
337    
338  # Table of information about our datatypes. "sqlType" is the corresponding SQL datatype string.  # Table of information about our datatypes. "sqlType" is the corresponding SQL datatype string.
339  # "maxLen" is the maximum permissible length of the incoming string data used to populate a field  # "maxLen" is the maximum permissible length of the incoming string data used to populate a field
340  # of the specified type. "dataGen" is PERL string that will be evaluated if no test data generation  # of the specified type. "avgLen" is the average byte length for estimating
341  # string is specified in the field definition. "avgLen" is the average byte length for estimating  # record sizes. "sort" is the key modifier for the sort command, "notes" is a type description,
342  # record sizes.  # and "indexMod", if non-zero, is the number of characters to use when the field is specified in an
343  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, dataGen => "StringGen('A')" },  # index
344                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, dataGen => "IntGen(0, 99999999)" },  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",
345                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, dataGen => "StringGen(IntGen(10,250))" },                                 indexMod =>   0, notes => "single ASCII character"},
346                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, dataGen => "StringGen(IntGen(80,1000))" },                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n",
347                    date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, dataGen => "DateGen(-7, 7, IntGen(0,1400))" },                                 indexMod =>   0, notes => "signed 32-bit integer"},
348                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, dataGen => "FloatGen(0.0, 100.0)" },                    counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n",
349                    boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   2, dataGen => "IntGen(0, 1)" },                                 indexMod =>   0, notes => "unsigned 32-bit integer"},
350                      string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, sort => "",
351                                   indexMod =>   0, notes => "character string, 0 to 255 characters"},
352                      text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, sort => "",
353                                   indexMod => 255, notes => "character string, nearly unlimited length, only first 255 characters are indexed"},
354                      date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, sort => "n",
355                                   indexMod =>   0, notes => "signed, 64-bit integer"},
356                      float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, sort => "g",
357                                   indexMod =>   0, notes => "64-bit double precision floating-point number"},
358                      boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, sort => "n",
359                                   indexMod =>   0, notes => "boolean value: 0 if false, 1 if true"},
360                     'hash-string' =>
361                                 { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, sort => "",
362                                   indexMod =>   0, notes => "string stored in digested form, used for certain types of key fields"},
363                     'id-string' =>
364                                 { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, sort => "",
365                                   indexMod =>   0, notes => "character string, 0 to 25 characters"},
366                   'key-string' =>                   'key-string' =>
367                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, dataGen => "StringGen(IntGen(10,40))" },                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, sort => "",
368                                   indexMod =>   0, notes => "character string, 0 to 40 characters"},
369                   'name-string' =>                   'name-string' =>
370                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, dataGen => "StringGen(IntGen(10,80))" },                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, sort => "",
371                                   indexMod =>   0, notes => "character string, 0 to 80 characters"},
372                   'medium-string' =>                   'medium-string' =>
373                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, dataGen => "StringGen(IntGen(10,160))" },                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",
374                                   indexMod =>   0, notes => "character string, 0 to 160 characters"},
375                  );                  );
376    
377  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 324  Line 380 
380                     'MM' => 'many-to-many'                     'MM' => 'many-to-many'
381                   );                   );
382    
383  # Table for interpreting string patterns.  # Options for XML input and output.
384    
385    my %XmlOptions = (GroupTags =>  { Relationships => 'Relationship',
386                                      Entities => 'Entity',
387                                      Fields => 'Field',
388                                      Indexes => 'Index',
389                                      IndexFields => 'IndexField'
390                                    },
391                      KeyAttr =>    { Relationship => 'name',
392                                      Entity => 'name',
393                                      Field => 'name'
394                                    },
395                      SuppressEmpty => 1,
396                     );
397    
398  my %PictureTable = ( 'A' => "abcdefghijklmnopqrstuvwxyz",  my %XmlInOpts  = (
399                       '9' => "0123456789",                    ForceArray => ['Field', 'Index', 'IndexField', 'Relationship', 'Entity'],
400                       'X' => "abcdefghijklmnopqrstuvwxyz0123456789",                    ForceContent => 1,
401                       'V' => "aeiou",                    NormalizeSpace => 2,
                      'K' => "bcdfghjklmnoprstvwxyz"  
402                     );                     );
403    my %XmlOutOpts = (
404                      RootName => 'Database',
405                      XMLDecl => 1,
406                     );
407    
408    
409  =head2 Public Methods  =head2 Public Methods
410    
# Line 402  Line 475 
475      # Write the HTML heading stuff.      # Write the HTML heading stuff.
476      print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";      print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";
477      print HTMLOUT "</head>\n<body>\n";      print HTMLOUT "</head>\n<body>\n";
478        # Write the documentation.
479        print HTMLOUT $self->DisplayMetaData();
480        # Close the document.
481        print HTMLOUT "</body>\n</html>\n";
482        # Close the file.
483        close HTMLOUT;
484    }
485    
486    =head3 DisplayMetaData
487    
488    C<< my $html = $erdb->DisplayMetaData(); >>
489    
490    Return an HTML description of the database. This description can be used to help users create
491    the data to be loaded into the relations and form queries. The output is raw includable HTML
492    without any HEAD or BODY tags.
493    
494    =over 4
495    
496    =item filename
497    
498    The name of the output file.
499    
500    =back
501    
502    =cut
503    
504    sub DisplayMetaData {
505        # Get the parameters.
506        my ($self) = @_;
507        # Get the metadata and the title string.
508        my $metadata = $self->{_metaData};
509        # Get the title string.
510        my $title = $metadata->{Title};
511        # Get the entity and relationship lists.
512        my $entityList = $metadata->{Entities};
513        my $relationshipList = $metadata->{Relationships};
514        # Declare the return variable.
515        my $retVal = "";
516        # Open the output file.
517        Trace("Building MetaData table of contents.") if T(4);
518      # Here we do the table of contents. It starts as an unordered list of section names. Each      # Here we do the table of contents. It starts as an unordered list of section names. Each
519      # section contains an ordered list of entity or relationship subsections.      # section contains an ordered list of entity or relationship subsections.
520      print HTMLOUT "<ul>\n<li><a href=\"#EntitiesSection\">Entities</a>\n<ol>\n";      $retVal .= "<ul>\n<li><a href=\"#EntitiesSection\">Entities</a>\n<ol>\n";
521      # Loop through the Entities, displaying a list item for each.      # Loop through the Entities, displaying a list item for each.
522      foreach my $key (sort keys %{$entityList}) {      foreach my $key (sort keys %{$entityList}) {
523          # Display this item.          # Display this item.
524          print HTMLOUT "<li><a href=\"#$key\">$key</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$key</a></li>\n";
525      }      }
526      # Close off the entity section and start the relationship section.      # Close off the entity section and start the relationship section.
527      print HTMLOUT "</ol></li>\n<li><a href=\"#RelationshipsSection\">Relationships</a>\n<ol>\n";      $retVal .= "</ol></li>\n<li><a href=\"#RelationshipsSection\">Relationships</a>\n<ol>\n";
528      # Loop through the Relationships.      # Loop through the Relationships.
529      foreach my $key (sort keys %{$relationshipList}) {      foreach my $key (sort keys %{$relationshipList}) {
530          # Display this item.          # Display this item.
531          my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});          my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});
532          print HTMLOUT "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";
533      }      }
534      # Close off the relationship section and list the join table section.      # Close off the relationship section and list the join table section.
535      print HTMLOUT "</ol></li>\n<li><a href=\"#JoinTable\">Join Table</a></li>\n";      $retVal .= "</ol></li>\n<li><a href=\"#JoinTable\">Join Table</a></li>\n";
536      # Close off the table of contents itself.      # Close off the table of contents itself.
537      print HTMLOUT "</ul>\n";      $retVal .=  "</ul>\n";
538      # Now we start with the actual data. Denote we're starting the entity section.      # Now we start with the actual data. Denote we're starting the entity section.
539      print HTMLOUT "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";      $retVal .= "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";
540      # Loop through the entities.      # Loop through the entities.
541      for my $key (sort keys %{$entityList}) {      for my $key (sort keys %{$entityList}) {
542          Trace("Building MetaData entry for $key entity.") if T(4);          Trace("Building MetaData entry for $key entity.") if T(4);
543          # Create the entity header. It contains a bookmark and the entity name.          # Create the entity header. It contains a bookmark and the entity name.
544          print HTMLOUT "<a name=\"$key\"></a><h3>$key</h3>\n";          $retVal .= "<a name=\"$key\"></a><h3>$key</h3>\n";
545          # Get the entity data.          # Get the entity data.
546          my $entityData = $entityList->{$key};          my $entityData = $entityList->{$key};
547          # If there's descriptive text, display it.          # If there's descriptive text, display it.
548          if (my $notes = $entityData->{Notes}) {          if (my $notes = $entityData->{Notes}) {
549              print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
550          }          }
551          # Now we want a list of the entity's relationships. First, we set up the relationship subsection.          # Now we want a list of the entity's relationships. First, we set up the relationship subsection.
552          print HTMLOUT "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
553          # Loop through the relationships.          # Loop through the relationships.
554          for my $relationship (sort keys %{$relationshipList}) {          for my $relationship (sort keys %{$relationshipList}) {
555              # Get the relationship data.              # Get the relationship data.
# Line 446  Line 559 
559                  # Get the relationship sentence and append the arity.                  # Get the relationship sentence and append the arity.
560                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);
561                  # Display the relationship data.                  # Display the relationship data.
562                  print HTMLOUT "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";                  $retVal .= "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";
563              }              }
564          }          }
565          # Close off the relationship list.          # Close off the relationship list.
566          print HTMLOUT "</ul>\n";          $retVal .= "</ul>\n";
567          # Get the entity's relations.          # Get the entity's relations.
568          my $relationList = $entityData->{Relations};          my $relationList = $entityData->{Relations};
569          # Create a header for the relation subsection.          # Create a header for the relation subsection.
570          print HTMLOUT "<h4>Relations for <b>$key</b></h4>\n";          $retVal .= "<h4>Relations for <b>$key</b></h4>\n";
571          # Loop through the relations, displaying them.          # Loop through the relations, displaying them.
572          for my $relation (sort keys %{$relationList}) {          for my $relation (sort keys %{$relationList}) {
573              my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});              my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});
574              print HTMLOUT $htmlString;              $retVal .= $htmlString;
575          }          }
576      }      }
577      # Denote we're starting the relationship section.      # Denote we're starting the relationship section.
578      print HTMLOUT "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";      $retVal .= "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";
579      # Loop through the relationships.      # Loop through the relationships.
580      for my $key (sort keys %{$relationshipList}) {      for my $key (sort keys %{$relationshipList}) {
581          Trace("Building MetaData entry for $key relationship.") if T(4);          Trace("Building MetaData entry for $key relationship.") if T(4);
# Line 470  Line 583 
583          my $relationshipStructure = $relationshipList->{$key};          my $relationshipStructure = $relationshipList->{$key};
584          # Create the relationship header.          # Create the relationship header.
585          my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);          my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);
586          print HTMLOUT "<h3><a name=\"$key\"></a>$headerText</h3>\n";          $retVal .= "<h3><a name=\"$key\"></a>$headerText</h3>\n";
587          # Get the entity names.          # Get the entity names.
588          my $fromEntity = $relationshipStructure->{from};          my $fromEntity = $relationshipStructure->{from};
589          my $toEntity = $relationshipStructure->{to};          my $toEntity = $relationshipStructure->{to};
# Line 480  Line 593 
593          # since both sentences will say the same thing.          # since both sentences will say the same thing.
594          my $arity = $relationshipStructure->{arity};          my $arity = $relationshipStructure->{arity};
595          if ($arity eq "11") {          if ($arity eq "11") {
596              print HTMLOUT "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";
597          } else {          } else {
598              print HTMLOUT "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";
599              if ($arity eq "MM" && $fromEntity ne $toEntity) {              if ($arity eq "MM" && $fromEntity ne $toEntity) {
600                  print HTMLOUT "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";                  $retVal .= "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";
601              }              }
602          }          }
603          print HTMLOUT "</p>\n";          $retVal .= "</p>\n";
604          # If there are notes on this relationship, display them.          # If there are notes on this relationship, display them.
605          if (my $notes = $relationshipStructure->{Notes}) {          if (my $notes = $relationshipStructure->{Notes}) {
606              print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
607          }          }
608          # Generate the relationship's relation table.          # Generate the relationship's relation table.
609          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
610          print HTMLOUT $htmlString;          $retVal .= $htmlString;
611      }      }
612      Trace("Building MetaData join table.") if T(4);      Trace("Building MetaData join table.") if T(4);
613      # Denote we're starting the join table.      # Denote we're starting the join table.
614      print HTMLOUT "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";      $retVal .= "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";
615      # Create a table header.      # Create a table header.
616      print HTMLOUT _OpenTable("Join Table", "Source", "Target", "Join Condition");      $retVal .= _OpenTable("Join Table", "Source", "Target", "Join Condition");
617      # Loop through the joins.      # Loop through the joins.
618      my $joinTable = $metadata->{Joins};      my $joinTable = $metadata->{Joins};
619      my @joinKeys = keys %{$joinTable};      my @joinKeys = keys %{$joinTable};
# Line 508  Line 621 
621          # Separate out the source, the target, and the join clause.          # Separate out the source, the target, and the join clause.
622          $joinKey =~ m!^([^/]+)/(.+)$!;          $joinKey =~ m!^([^/]+)/(.+)$!;
623          my ($sourceRelation, $targetRelation) = ($1, $2);          my ($sourceRelation, $targetRelation) = ($1, $2);
624          Trace("Join with key $joinKey is from $sourceRelation to $targetRelation.") if T(4);          Trace("Join with key $joinKey is from $sourceRelation to $targetRelation.") if T(Joins => 4);
625          my $source = $self->ComputeObjectSentence($sourceRelation);          my $source = $self->ComputeObjectSentence($sourceRelation);
626          my $target = $self->ComputeObjectSentence($targetRelation);          my $target = $self->ComputeObjectSentence($targetRelation);
627          my $clause = $joinTable->{$joinKey};          my $clause = $joinTable->{$joinKey};
628          # Display them in a table row.          # Display them in a table row.
629          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";
630      }      }
631      # Close the table.      # Close the table.
632      print HTMLOUT _CloseTable();      $retVal .= _CloseTable();
633      # Close the document.      Trace("Built MetaData HTML.") if T(3);
634      print HTMLOUT "</body>\n</html>\n";      # Return the HTML.
635      # Close the file.      return $retVal;
     close HTMLOUT;  
     Trace("Built MetaData web page.") if T(3);  
636  }  }
637    
638  =head3 DumpMetaData  =head3 DumpMetaData
# Line 539  Line 650 
650      return Data::Dumper::Dumper($self->{_metaData});      return Data::Dumper::Dumper($self->{_metaData});
651  }  }
652    
653    =head3 FindIndexForEntity
654    
655    C<< my $indexFound = ERDB::FindIndexForEntity($xml, $entityName, $attributeName); >>
656    
657    This method locates the entry in an entity's index list that begins with the
658    specified attribute name. If the entity has no index list, one will be
659    created. This method works on raw XML, not a live ERDB object.
660    
661    =over 4
662    
663    =item xml
664    
665    The raw XML structure defining the database.
666    
667    =item entityName
668    
669    The name of the relevant entity.
670    
671    =item attributeName
672    
673    The name of the attribute relevant to the search.
674    
675    =item RETURN
676    
677    The numerical index in the index list of the index entry for the specified entity and
678    attribute, or C<undef> if no such index exists.
679    
680    =back
681    
682    =cut
683    
684    sub FindIndexForEntity {
685        # Get the parameters.
686        my ($xml, $entityName, $attributeName) = @_;
687        # Declare the return variable.
688        my $retVal;
689        # Get the named entity.
690        my $entityData = $xml->{Entities}->{$entityName};
691        if (! $entityData) {
692            Confess("Entity $entityName not found in DBD structure.");
693        } else {
694            # Insure it has an index list.
695            if (! exists $entityData->{Indexes}) {
696                $entityData->{Indexes} = [];
697            } else {
698                # Search for the desired index.
699                my $indexList = $entityData->{Indexes};
700                my $n = scalar @{$indexList};
701                Trace("Searching $n indexes in index list for $entityName.") if T(2);
702                # We use an indexed FOR here because we're returning an
703                # index number instead of an object. We do THAT so we can
704                # delete the index from the list if needed.
705                for (my $i = 0; $i < $n && !defined($retVal); $i++) {
706                    my $index = $indexList->[$i];
707                    my $fields = $index->{IndexFields};
708                    # Technically this IF should be safe (that is, we are guaranteed
709                    # the existence of a "$fields->[0]"), because when we load the XML
710                    # we have SuppressEmpty specified.
711                    if ($fields->[0]->{name} eq $attributeName) {
712                        $retVal = $i;
713                    }
714                }
715            }
716        }
717        Trace("Index for $attributeName of $entityName found at position $retVal.") if defined($retVal) && T(3);
718        Trace("Index for $attributeName not found in $entityName.") if !defined($retVal) && T(3);
719        # Return the result.
720        return $retVal;
721    }
722    
723  =head3 CreateTables  =head3 CreateTables
724    
725  C<< $erdb->CreateTables(); >>  C<< $erdb->CreateTables(); >>
# Line 553  Line 734 
734  sub CreateTables {  sub CreateTables {
735      # Get the parameters.      # Get the parameters.
736      my ($self) = @_;      my ($self) = @_;
737      my $metadata = $self->{_metaData};      # Get the relation names.
738      my $dbh = $self->{_dbh};      my @relNames = $self->GetTableNames();
739      # Loop through the entities.      # Loop through the relations.
740      my $entityHash = $metadata->{Entities};      for my $relationName (@relNames) {
     for my $entityName (keys %{$entityHash}) {  
         my $entityData = $entityHash->{$entityName};  
         # Tell the user what we're doing.  
         Trace("Creating relations for entity $entityName.") if T(1);  
         # Loop through the entity's relations.  
         for my $relationName (keys %{$entityData->{Relations}}) {  
741              # Create a table for this relation.              # Create a table for this relation.
742              $self->CreateTable($relationName);              $self->CreateTable($relationName);
743              Trace("Relation $relationName created.") if T(1);          Trace("Relation $relationName created.") if T(2);
         }  
     }  
     # Loop through the relationships.  
     my $relationshipTable = $metadata->{Relationships};  
     for my $relationshipName (keys %{$metadata->{Relationships}}) {  
         # Create a table for this relationship.  
         Trace("Creating relationship $relationshipName.") if T(1);  
         $self->CreateTable($relationshipName);  
744      }      }
745  }  }
746    
# Line 640  Line 807 
807      Trace("Creating table $relationName: $fieldThing") if T(2);      Trace("Creating table $relationName: $fieldThing") if T(2);
808      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);
809      Trace("Relation $relationName created in database.") if T(2);      Trace("Relation $relationName created in database.") if T(2);
810      # If we want to build the indexes, we do it here.      # If we want to build the indexes, we do it here. Note that the full-text search
811        # index will not be built until the table has been loaded.
812      if ($indexFlag) {      if ($indexFlag) {
813          $self->CreateIndex($relationName);          $self->CreateIndex($relationName);
814      }      }
815  }  }
816    
817    =head3 VerifyFields
818    
819    C<< my $count = $erdb->VerifyFields($relName, \@fieldList); >>
820    
821    Run through the list of proposed field values, insuring that all the character fields are
822    below the maximum length. If any fields are too long, they will be truncated in place.
823    
824    =over 4
825    
826    =item relName
827    
828    Name of the relation for which the specified fields are destined.
829    
830    =item fieldList
831    
832    Reference to a list, in order, of the fields to be put into the relation.
833    
834    =item RETURN
835    
836    Returns the number of fields truncated.
837    
838    =back
839    
840    =cut
841    
842    sub VerifyFields {
843        # Get the parameters.
844        my ($self, $relName, $fieldList) = @_;
845        # Initialize the return value.
846        my $retVal = 0;
847        # Get the relation definition.
848        my $relData = $self->_FindRelation($relName);
849        # Get the list of field descriptors.
850        my $fieldTypes = $relData->{Fields};
851        my $fieldCount = scalar @{$fieldTypes};
852        # Loop through the two lists.
853        for (my $i = 0; $i < $fieldCount; $i++) {
854            # Get the type of the current field.
855            my $fieldType = $fieldTypes->[$i]->{type};
856            # If it's a character field, verify the length.
857            if ($fieldType =~ /string/) {
858                my $maxLen = $TypeTable{$fieldType}->{maxLen};
859                my $oldString = $fieldList->[$i];
860                if (length($oldString) > $maxLen) {
861                    # Here it's too big, so we truncate it.
862                    Trace("Truncating field $i in relation $relName to $maxLen characters from \"$oldString\".") if T(1);
863                    $fieldList->[$i] = substr $oldString, 0, $maxLen;
864                    $retVal++;
865                }
866            }
867        }
868        # Return the truncation count.
869        return $retVal;
870    }
871    
872    =head3 DigestFields
873    
874    C<< $erdb->DigestFields($relName, $fieldList); >>
875    
876    Digest the strings in the field list that correspond to data type C<hash-string> in the
877    specified relation.
878    
879    =over 4
880    
881    =item relName
882    
883    Name of the relation to which the fields belong.
884    
885    =item fieldList
886    
887    List of field contents to be loaded into the relation.
888    
889    =back
890    
891    =cut
892    #: Return Type ;
893    sub DigestFields {
894        # Get the parameters.
895        my ($self, $relName, $fieldList) = @_;
896        # Get the relation definition.
897        my $relData = $self->_FindRelation($relName);
898        # Get the list of field descriptors.
899        my $fieldTypes = $relData->{Fields};
900        my $fieldCount = scalar @{$fieldTypes};
901        # Loop through the two lists.
902        for (my $i = 0; $i < $fieldCount; $i++) {
903            # Get the type of the current field.
904            my $fieldType = $fieldTypes->[$i]->{type};
905            # If it's a hash string, digest it in place.
906            if ($fieldType eq 'hash-string') {
907                $fieldList->[$i] = $self->DigestKey($fieldList->[$i]);
908            }
909        }
910    }
911    
912    =head3 DigestKey
913    
914    C<< my $digested = $erdb->DigestKey($keyValue); >>
915    
916    Return the digested value of a symbolic key. The digested value can then be plugged into a
917    key-based search into a table with key-type hash-string.
918    
919    Currently the digesting process is independent of the database structure, but that may not
920    always be the case, so this is an instance method instead of a static method.
921    
922    =over 4
923    
924    =item keyValue
925    
926    Key value to digest.
927    
928    =item RETURN
929    
930    Digested value of the key.
931    
932    =back
933    
934    =cut
935    
936    sub DigestKey {
937        # Get the parameters.
938        my ($self, $keyValue) = @_;
939        # Compute the digest.
940        my $retVal = md5_base64($keyValue);
941        # Return the result.
942        return $retVal;
943    }
944    
945  =head3 CreateIndex  =head3 CreateIndex
946    
947  C<< $erdb->CreateIndex($relationName); >>  C<< $erdb->CreateIndex($relationName); >>
# Line 669  Line 965 
965      for my $indexName (keys %{$indexHash}) {      for my $indexName (keys %{$indexHash}) {
966          my $indexData = $indexHash->{$indexName};          my $indexData = $indexHash->{$indexName};
967          # Get the index's field list.          # Get the index's field list.
968          my @fieldList = _FixNames(@{$indexData->{IndexFields}});          my @rawFields = @{$indexData->{IndexFields}};
969            # Get a hash of the relation's field types.
970            my %types = map { $_->{name} => $_->{type} } @{$relationData->{Fields}};
971            # We need to check for text fields so we can append a length limitation for them. To do
972            # that, we need the relation's field list.
973            my $relFields = $relationData->{Fields};
974            for (my $i = 0; $i <= $#rawFields; $i++) {
975                # Get the field type.
976                my $field = $rawFields[$i];
977                my $type = $types{$field};
978                # Ask if it requires using prefix notation for the index.
979                my $mod = $TypeTable{$type}->{indexMod};
980                Trace("Field $field ($i) in $relationName has type $type and indexMod $mod.") if T(3);
981                if ($mod) {
982                    # Append the prefix length to the field name,
983                    $rawFields[$i] .= "($mod)";
984                }
985            }
986            my @fieldList = _FixNames(@rawFields);
987          my $flds = join(', ', @fieldList);          my $flds = join(', ', @fieldList);
988          # Get the index's uniqueness flag.          # Get the index's uniqueness flag.
989          my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
990          # Create the index.          # Create the index.
991          $dbh->create_index(idx => $indexName, tbl => $relationName, flds => $flds, unique => $unique);          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
992                                        flds => $flds, kind => $unique);
993            if ($rv) {
994          Trace("Index created: $indexName for $relationName ($flds)") if T(1);          Trace("Index created: $indexName for $relationName ($flds)") if T(1);
995            } else {
996                Confess("Error creating index $indexName for $relationName using ($flds): " . $dbh->error_message());
997            }
998        }
999    }
1000    
1001    =head3 GetSecondaryFields
1002    
1003    C<< my %fieldTuples = $erdb->GetSecondaryFields($entityName); >>
1004    
1005    This method will return a list of the name and type of each of the secondary
1006    fields for a specified entity. Secondary fields are stored in two-column tables
1007    in addition to the primary entity table. This enables the field to have no value
1008    or to have multiple values.
1009    
1010    =over 4
1011    
1012    =item entityName
1013    
1014    Name of the entity whose secondary fields are desired.
1015    
1016    =item RETURN
1017    
1018    Returns a hash mapping the field names to their field types.
1019    
1020    =back
1021    
1022    =cut
1023    
1024    sub GetSecondaryFields {
1025        # Get the parameters.
1026        my ($self, $entityName) = @_;
1027        # Declare the return variable.
1028        my %retVal = ();
1029        # Look for the entity.
1030        my $table = $self->GetFieldTable($entityName);
1031        # Loop through the fields, pulling out the secondaries.
1032        for my $field (sort keys %{$table}) {
1033            if ($table->{$field}->{relation} ne $entityName) {
1034                # Here we have a secondary field.
1035                $retVal{$field} = $table->{$field}->{type};
1036            }
1037        }
1038        # Return the result.
1039        return %retVal;
1040    }
1041    
1042    =head3 GetFieldRelationName
1043    
1044    C<< my $name = $erdb->GetFieldRelationName($objectName, $fieldName); >>
1045    
1046    Return the name of the relation containing a specified field.
1047    
1048    =over 4
1049    
1050    =item objectName
1051    
1052    Name of the entity or relationship containing the field.
1053    
1054    =item fieldName
1055    
1056    Name of the relevant field in that entity or relationship.
1057    
1058    =item RETURN
1059    
1060    Returns the name of the database relation containing the field, or C<undef> if
1061    the field does not exist.
1062    
1063    =back
1064    
1065    =cut
1066    
1067    sub GetFieldRelationName {
1068        # Get the parameters.
1069        my ($self, $objectName, $fieldName) = @_;
1070        # Declare the return variable.
1071        my $retVal;
1072        # Get the object field table.
1073        my $table = $self->GetFieldTable($objectName);
1074        # Only proceed if the field exists.
1075        if (exists $table->{$fieldName}) {
1076            # Determine the name of the relation that contains this field.
1077            $retVal = $table->{$fieldName}->{relation};
1078        }
1079        # Return the result.
1080        return $retVal;
1081    }
1082    
1083    =head3 DeleteValue
1084    
1085    C<< my $numDeleted = $erdb->DeleteValue($entityName, $id, $fieldName, $fieldValue); >>
1086    
1087    Delete secondary field values from the database. This method can be used to delete all
1088    values of a specified field for a particular entity instance, or only a single value.
1089    
1090    Secondary fields are stored in two-column relations separate from an entity's primary
1091    table, and as a result a secondary field can legitimately have no value or multiple
1092    values. Therefore, it makes sense to talk about deleting secondary fields where it
1093    would not make sense for primary fields.
1094    
1095    =over 4
1096    
1097    =item entityName
1098    
1099    Name of the entity from which the fields are to be deleted.
1100    
1101    =item id
1102    
1103    ID of the entity instance to be processed. If the instance is not found, this
1104    method will have no effect. If C<undef> is specified, all values for all of
1105    the entity instances will be deleted.
1106    
1107    =item fieldName
1108    
1109    Name of the field whose values are to be deleted.
1110    
1111    =item fieldValue (optional)
1112    
1113    Value to be deleted. If not specified, then all values of the specified field
1114    will be deleted for the entity instance. If specified, then only the values which
1115    match this parameter will be deleted.
1116    
1117    =item RETURN
1118    
1119    Returns the number of rows deleted.
1120    
1121    =back
1122    
1123    =cut
1124    
1125    sub DeleteValue {
1126        # Get the parameters.
1127        my ($self, $entityName, $id, $fieldName, $fieldValue) = @_;
1128        # Declare the return value.
1129        my $retVal = 0;
1130        # We need to set up an SQL command to do the deletion. First, we
1131        # find the name of the field's relation.
1132        my $table = $self->GetFieldTable($entityName);
1133        my $field = $table->{$fieldName};
1134        my $relation = $field->{relation};
1135        # Make sure this is a secondary field.
1136        if ($relation eq $entityName) {
1137            Confess("Cannot delete values of $fieldName for $entityName.");
1138        } else {
1139            # Set up the SQL command to delete all values.
1140            my $sql = "DELETE FROM $relation";
1141            # Build the filter.
1142            my @filters = ();
1143            my @parms = ();
1144            # Check for a filter by ID.
1145            if (defined $id) {
1146                push @filters, "id = ?";
1147                push @parms, $id;
1148            }
1149            # Check for a filter by value.
1150            if (defined $fieldValue) {
1151                push @filters, "$fieldName = ?";
1152                push @parms, $fieldValue;
1153            }
1154            # Append the filters to the command.
1155            if (@filters) {
1156                $sql .= " WHERE " . join(" AND ", @filters);
1157            }
1158            # Execute the command.
1159            my $dbh = $self->{_dbh};
1160            $retVal = $dbh->SQL($sql, 0, @parms);
1161      }      }
1162        # Return the result.
1163        return $retVal;
1164  }  }
1165    
1166  =head3 LoadTables  =head3 LoadTables
# Line 724  Line 1208 
1208      $directoryName =~ s!/\\$!!;      $directoryName =~ s!/\\$!!;
1209      # Declare the return variable.      # Declare the return variable.
1210      my $retVal = Stats->new();      my $retVal = Stats->new();
1211      # Get the metadata structure.      # Get the relation names.
1212      my $metaData = $self->{_metaData};      my @relNames = $self->GetTableNames();
1213      # Loop through the entities.      for my $relationName (@relNames) {
     for my $entity (values %{$metaData->{Entities}}) {  
         # Loop through the entity's relations.  
         for my $relationName (keys %{$entity->{Relations}}) {  
1214              # Try to load this relation.              # Try to load this relation.
1215              my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);              my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);
1216              # Accumulate the statistics.              # Accumulate the statistics.
1217              $retVal->Accumulate($result);              $retVal->Accumulate($result);
1218          }          }
     }  
     # Loop through the relationships.  
     for my $relationshipName (keys %{$metaData->{Relationships}}) {  
         # Try to load this relationship's relation.  
         my $result = $self->_LoadRelation($directoryName, $relationshipName, $rebuild);  
         # Accumulate the statistics.  
         $retVal->Accumulate($result);  
     }  
1219      # Add the duration of the load to the statistical object.      # Add the duration of the load to the statistical object.
1220      $retVal->Add('duration', gettimeofday - $startTime);      $retVal->Add('duration', gettimeofday - $startTime);
1221      # Return the accumulated statistics.      # Return the accumulated statistics.
1222      return $retVal;      return $retVal;
1223  }  }
1224    
1225    
1226  =head3 GetTableNames  =head3 GetTableNames
1227    
1228  C<< my @names = $erdb->GetTableNames; >>  C<< my @names = $erdb->GetTableNames; >>
# Line 783  Line 1257 
1257      return sort keys %{$entityList};      return sort keys %{$entityList};
1258  }  }
1259    
1260  =head3 Get  =head3 GetDataTypes
1261    
1262  C<< my $query = $erdb->Get(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  C<< my %types = ERDB::GetDataTypes(); >>
1263    
1264  This method returns a query object for entities of a specified type using a specified filter.  Return a table of ERDB data types. The table returned is a hash of hashes.
1265    The keys of the big hash are the datatypes. Each smaller hash has several
1266    values used to manage the data. The most interesting is the SQL type (key
1267    C<sqlType>) and the descriptive node (key C<notes>).
1268    
1269    Note that changing the values in the smaller hashes will seriously break
1270    things, so this data should be treated as read-only.
1271    
1272    =cut
1273    
1274    sub GetDataTypes {
1275        return %TypeTable;
1276    }
1277    
1278    
1279    =head3 IsEntity
1280    
1281    C<< my $flag = $erdb->IsEntity($entityName); >>
1282    
1283    Return TRUE if the parameter is an entity name, else FALSE.
1284    
1285    =over 4
1286    
1287    =item entityName
1288    
1289    Object name to be tested.
1290    
1291    =item RETURN
1292    
1293    Returns TRUE if the specified string is an entity name, else FALSE.
1294    
1295    =back
1296    
1297    =cut
1298    
1299    sub IsEntity {
1300        # Get the parameters.
1301        my ($self, $entityName) = @_;
1302        # Test to see if it's an entity.
1303        return exists $self->{_metaData}->{Entities}->{$entityName};
1304    }
1305    
1306    =head3 Get
1307    
1308    C<< my $query = $erdb->Get(\@objectNames, $filterClause, \@params); >>
1309    
1310    This method returns a query object for entities of a specified type using a specified filter.
1311  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
1312  field name represented in the form B<I<objectName>(I<fieldName>)>. For example, the  field name represented in the form B<I<objectName>(I<fieldName>)>. For example, the
1313  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
1314  $genus.  $genus.
1315    
1316  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", [$genus]); >>
1317    
1318  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
1319  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 810  Line 1330 
1330  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
1331  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,
1332    
1333  C<< $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]); >>
1334    
1335  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
1336  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.
1337  In particular, you can't specify any entity or relationship more than once, and if a  In particular, if a relationship is recursive, the path is determined by the order in which
1338  relationship is recursive, the path is determined by the order in which the entity  the entity and the relationship appear. For example, consider a recursive relationship
1339  and the relationship appear. For example, consider a recursive relationship B<IsParentOf>  B<IsParentOf> which relates B<People> objects to other B<People> objects. If the join path is
 which relates B<People> objects to other B<People> objects. If the join path is  
1340  coded as C<['People', 'IsParentOf']>, then the people returned will be parents. If, however,  coded as C<['People', 'IsParentOf']>, then the people returned will be parents. If, however,
1341  the join path is C<['IsParentOf', 'People']>, then the people returned will be children.  the join path is C<['IsParentOf', 'People']>, then the people returned will be children.
1342    
1343    If an entity or relationship is mentioned twice, the name for the second occurrence will
1344    be suffixed with C<2>, the third occurrence will be suffixed with C<3>, and so forth. So,
1345    for example, if we have C<['Feature', 'HasContig', 'Contig', 'HasContig']>, then the
1346    B<to-link> field of the first B<HasContig> is specified as C<HasContig(to-link)>, while
1347    the B<to-link> field of the second B<HasContig> is specified as C<HasContig2(to-link)>.
1348    
1349  =over 4  =over 4
1350    
1351  =item objectNames  =item objectNames
# Line 843  Line 1368 
1368    
1369  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
1370    
1371    Note that the case is important. Only an uppercase "ORDER BY" with a single space will
1372    be processed. The idea is to make it less likely to find the verb by accident.
1373    
1374  The rules for field references in a sort order are the same as those for field references in the  The rules for field references in a sort order are the same as those for field references in the
1375  filter clause in general; however, odd things may happen if a sort field is from a secondary  filter clause in general; however, odd things may happen if a sort field is from a secondary
1376  relation.  relation.
1377    
1378  =item param1, param2, ..., paramN  Finally, you can limit the number of rows returned by adding a LIMIT clause. The LIMIT must
1379    be the last thing in the filter clause, and it contains only the word "LIMIT" followed by
1380    a positive number. So, for example
1381    
1382    C<< "Genome(genus) = ? ORDER BY Genome(species) LIMIT 10" >>
1383    
1384    will only return the first ten genomes for the specified genus. The ORDER BY clause is not
1385    required. For example, to just get the first 10 genomes in the B<Genome> table, you could
1386    use
1387    
1388  Parameter values to be substituted into the filter clause.  C<< "LIMIT 10" >>
1389    
1390    =item params
1391    
1392    Reference to a list of parameter values to be substituted into the filter clause.
1393    
1394  =item RETURN  =item RETURN
1395    
# Line 861  Line 1401 
1401    
1402  sub Get {  sub Get {
1403      # Get the parameters.      # Get the parameters.
1404      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $objectNames, $filterClause, $params) = @_;
1405      # Construct the SELECT statement. The general pattern is      # Process the SQL stuff.
1406      #      my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1407      # SELECT name1.*, name2.*, ... nameN.* FROM name1, name2, ... nameN          $self->_SetupSQL($objectNames, $filterClause);
1408      #      # Create the query.
1409      my $dbh = $self->{_dbh};      my $command = "SELECT DISTINCT " . join(".*, ", @{$mappedNameListRef}) .
1410      my $command = "SELECT DISTINCT " . join('.*, ', @{$objectNames}) . ".* FROM " .          ".* $suffix";
1411                  join(', ', @{$objectNames});      my $sth = $self->_GetStatementHandle($command, $params);
1412      # Check for a filter clause.      # Now we create the relation map, which enables DBQuery to determine the order, name
1413      if ($filterClause) {      # and mapped name for each object in the query.
1414          # Here we have one, so we convert its field names and add it to the query. First,      my @relationMap = ();
1415          # We create a copy of the filter string we can work with.      for my $mappedName (@{$mappedNameListRef}) {
1416          my $filterString = $filterClause;          push @relationMap, [$mappedName, $mappedNameHashRef->{$mappedName}];
         # Next, we sort the object names by length. This helps protect us from finding  
         # object names inside other object names when we're doing our search and replace.  
         my @sortedNames = sort { length($b) - length($a) } @{$objectNames};  
         # We will also keep a list of conditions to add to the WHERE clause in order to link  
         # entities and relationships as well as primary relations to secondary ones.  
         my @joinWhere = ();  
         # The final preparatory step is to create a hash table of relation names. The  
         # table begins with the relation names already in the SELECT command.  
         my %fromNames = ();  
         for my $objectName (@sortedNames) {  
             $fromNames{$objectName} = 1;  
         }  
         # We are ready to begin. We loop through the object names, replacing each  
         # object name's field references by the corresponding SQL field reference.  
         # Along the way, if we find a secondary relation, we will need to add it  
         # to the FROM clause.  
         for my $objectName (@sortedNames) {  
             # Get the length of the object name plus 2. This is the value we add to the  
             # size of the field name to determine the size of the field reference as a  
             # whole.  
             my $nameLength = 2 + length $objectName;  
             # Get the object's field list.  
             my $fieldList = $self->_GetFieldTable($objectName);  
             # Find the field references for this object.  
             while ($filterString =~ m/$objectName\(([^)]*)\)/g) {  
                 # At this point, $1 contains the field name, and the current position  
                 # is set immediately after the final parenthesis. We pull out the name of  
                 # the field and the position and length of the field reference as a whole.  
                 my $fieldName = $1;  
                 my $len = $nameLength + length $fieldName;  
                 my $pos = pos($filterString) - $len;  
                 # Insure the field exists.  
                 if (!exists $fieldList->{$fieldName}) {  
                     Confess("Field $fieldName not found for object $objectName.");  
                 } else {  
                     # Get the field's relation.  
                     my $relationName = $fieldList->{$fieldName}->{relation};  
                     # Insure the relation is in the FROM clause.  
                     if (!exists $fromNames{$relationName}) {  
                         # Add the relation to the FROM clause.  
                         $command .= ", $relationName";  
                         # Create its join sub-clause.  
                         push @joinWhere, "$objectName.id = $relationName.id";  
                         # Denote we have it available for future fields.  
                         $fromNames{$relationName} = 1;  
                     }  
                     # Form an SQL field reference from the relation name and the field name.  
                     my $sqlReference = "$relationName." . _FixName($fieldName);  
                     # Put it into the filter string in place of the old value.  
                     substr($filterString, $pos, $len) = $sqlReference;  
                     # Reposition the search.  
                     pos $filterString = $pos + length $sqlReference;  
                 }  
             }  
         }  
         # The next step is to join the objects together. We only need to do this if there  
         # is more than one object in the object list. We start with the first object and  
         # run through the objects after it. Note also that we make a safety copy of the  
         # list before running through it.  
         my @objectList = @{$objectNames};  
         my $lastObject = shift @objectList;  
         # Get the join table.  
         my $joinTable = $self->{_metaData}->{Joins};  
         # Loop through the object list.  
         for my $thisObject (@objectList) {  
             # Look for a join.  
             my $joinKey = "$lastObject/$thisObject";  
             if (!exists $joinTable->{$joinKey}) {  
                 # Here there's no join, so we throw an error.  
                 Confess("No join exists to connect from $lastObject to $thisObject.");  
             } else {  
                 # Get the join clause and add it to the WHERE list.  
                 push @joinWhere, $joinTable->{$joinKey};  
                 # Save this object as the last object for the next iteration.  
                 $lastObject = $thisObject;  
             }  
         }  
         # Now we need to handle the whole ORDER BY thing. We'll put the order by clause  
         # in the following variable.  
         my $orderClause = "";  
         # Locate the ORDER BY verb (if any).  
         if ($filterString =~ m/^(.*)ORDER BY/g) {  
             # Here we have an ORDER BY verb. Split it off of the filter string.  
             my $pos = pos $filterString;  
             $orderClause = substr($filterString, $pos);  
             $filterString = $1;  
         }  
         # Add the filter and the join clauses (if any) to the SELECT command.  
         if ($filterString) {  
             push @joinWhere, "($filterString)";  
         }  
         if (@joinWhere) {  
             $command .= " WHERE " . join(' AND ', @joinWhere);  
         }  
         # Add the sort clause (if any) to the SELECT command.  
         if ($orderClause) {  
             $command .= " ORDER BY $orderClause";  
         }  
1417      }      }
     Trace("SQL query: $command") if T(3);  
     Trace("PARMS: '" . (join "', '", @params) . "'") if (T(4) && (@params > 0));  
     my $sth = $dbh->prepare_command($command);  
     # Execute it with the parameters bound in.  
     $sth->execute(@params) || Confess("SELECT error" . $sth->errstr());  
1418      # Return the statement object.      # Return the statement object.
1419      my $retVal = DBQuery::_new($self, $sth, @{$objectNames});      my $retVal = DBQuery::_new($self, $sth, \@relationMap);
1420      return $retVal;      return $retVal;
1421  }  }
1422    
 =head3 GetList  
1423    
 C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  
1424    
1425  Return a list of object descriptors for the specified objects as determined by the  =head3 Search
 specified filter clause.  
1426    
1427  This method is essentially the same as L</Get> except it returns a list of objects rather  C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>
1428  than a query object that can be used to get the results one record at a time.  
1429    Perform a full text search with filtering. The search will be against a specified object
1430    in the object name list. That object will get an extra field containing the search
1431    relevance. Note that except for the search expression, the parameters of this method are
1432    the same as those for L</Get> and follow the same rules.
1433    
1434  =over 4  =over 4
1435    
1436    =item searchExpression
1437    
1438    Boolean search expression for the text fields of the target object. The default mode for
1439    a Boolean search expression is OR, but we want the default to be AND, so we will
1440    add a C<+> operator to each word with no other operator before it.
1441    
1442    =item idx
1443    
1444    Index in the I<$objectNames> list of the table to be searched in full-text mode.
1445    
1446  =item objectNames  =item objectNames
1447    
1448  List containing the names of the entity and relationship objects to be retrieved.  List containing the names of the entity and relationship objects to be retrieved.
# Line 1009  Line 1457 
1457  or secondary entity relations; however, all of the entities and relationships involved must  or secondary entity relations; however, all of the entities and relationships involved must
1458  be included in the list of object names.  be included in the list of object names.
1459    
1460  The filter clause can also specify a sort order. To do this, simply follow the filter string  =item params
 with an ORDER BY clause. For example, the following filter string gets all genomes for a  
 particular genus and sorts them by species name.  
   
 C<< "Genome(genus) = ? ORDER BY Genome(species)" >>  
   
 The rules for field references in a sort order are the same as those for field references in the  
 filter clause in general; however, odd things may happen if a sort field is from a secondary  
 relation.  
   
 =item param1, param2, ..., paramN  
1461    
1462  Parameter values to be substituted into the filter clause.  Reference to a list of parameter values to be substituted into the filter clause.
1463    
1464  =item RETURN  =item RETURN
1465    
1466  Returns a list of B<DBObject>s that satisfy the query conditions.  Returns a query object for the specified search.
1467    
1468  =back  =back
1469    
1470  =cut  =cut
1471  #: Return Type @%  
1472  sub GetList {  sub Search {
1473      # Get the parameters.      # Get the parameters.
1474      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1475      # Declare the return variable.      # Declare the return variable.
1476      my @retVal = ();      my $retVal;
1477      # Perform the query.      # Create a safety copy of the parameter list. Note we have to be careful to insure
1478      my $query = $self->Get($objectNames, $filterClause, @params);      # a parameter list exists before we copy it.
1479      # Loop through the results.      my @myParams = ();
1480      while (my $object = $query->Fetch) {      if (defined $params) {
1481          push @retVal, $object;          @myParams = @{$params};
1482        }
1483        # Get the first object's structure so we have access to the searchable fields.
1484        my $object1Name = $objectNames->[$idx];
1485        my $object1Structure = $self->_GetStructure($object1Name);
1486        # Get the field list.
1487        if (! exists $object1Structure->{searchFields}) {
1488            Confess("No searchable index for $object1Name.");
1489        } else {
1490            # Get the field list.
1491            my @fields = @{$object1Structure->{searchFields}};
1492            # Clean the search expression.
1493            my $actualKeywords = $self->CleanKeywords($searchExpression);
1494            # Prefix a "+" to each uncontrolled word. This converts the default
1495            # search mode from OR to AND.
1496            $actualKeywords =~ s/(^|\s)(\w|")/$1\+$2/g;
1497            Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1498            # We need two match expressions, one for the filter clause and one in the
1499            # query itself. Both will use a parameter mark, so we need to push the
1500            # search expression onto the front of the parameter list twice.
1501            unshift @myParams, $actualKeywords, $actualKeywords;
1502            # Build the match expression.
1503            my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
1504            my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
1505            # Process the SQL stuff.
1506            my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1507                $self->_SetupSQL($objectNames, $filterClause, $matchClause);
1508            # Create the query. Note that the match clause is inserted at the front of
1509            # the select fields.
1510            my $command = "SELECT DISTINCT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .
1511                ".* $suffix";
1512            my $sth = $self->_GetStatementHandle($command, \@myParams);
1513            # Now we create the relation map, which enables DBQuery to determine the order, name
1514            # and mapped name for each object in the query.
1515            my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
1516            # Return the statement object.
1517            $retVal = DBQuery::_new($self, $sth, \@relationMap, $object1Name);
1518      }      }
1519      # Return the result.      return $retVal;
     return @retVal;  
1520  }  }
1521    
1522  =head3 ComputeObjectSentence  =head3 GetFlat
1523    
1524  C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>  C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>
1525    
1526  Check an object name, and if it is a relationship convert it to a relationship sentence.  This is a variation of L</GetAll> that asks for only a single field per record and
1527    returns a single flattened list.
1528    
1529  =over 4  =over 4
1530    
1531  =item objectName  =item objectNames
1532    
1533  Name of the entity or relationship.  List containing the names of the entity and relationship objects to be retrieved.
1534    
1535    =item filterClause
1536    
1537    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1538    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
1539    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
1540    parameter list as additional parameters. The fields in a filter clause can come from primary
1541    entity relations, relationship relations, or secondary entity relations; however, all of the
1542    entities and relationships involved must be included in the list of object names.
1543    
1544    =item parameterList
1545    
1546    List of the parameters to be substituted in for the parameters marks in the filter clause.
1547    
1548    =item field
1549    
1550    Name of the field to be used to get the elements of the list returned.
1551    
1552  =item RETURN  =item RETURN
1553    
1554  Returns a string containing the entity name or a relationship sentence.  Returns a list of values.
1555    
1556  =back  =back
1557    
1558  =cut  =cut
1559    #: Return Type @;
1560  sub ComputeObjectSentence {  sub GetFlat {
1561      # Get the parameters.      # Get the parameters.
1562      my ($self, $objectName) = @_;      my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
1563      # Set the default return value.      # Construct the query.
1564      my $retVal = $objectName;      my $query = $self->Get($objectNames, $filterClause, $parameterList);
1565      # Look for the object as a relationship.      # Create the result list.
1566      my $relTable = $self->{_metaData}->{Relationships};      my @retVal = ();
1567      if (exists $relTable->{$objectName}) {      # Loop through the records, adding the field values found to the result list.
1568          # Get the relationship sentence.      while (my $row = $query->Fetch()) {
1569          $retVal = _ComputeRelationshipSentence($objectName, $relTable->{$objectName});          push @retVal, $row->Value($field);
1570      }      }
1571      # Return the result.      # Return the list created.
1572      return $retVal;      return @retVal;
1573  }  }
1574    
1575  =head3 DumpRelations  =head3 SpecialFields
1576    
1577  C<< $erdb->DumpRelations($outputDirectory); >>  C<< my %specials = $erdb->SpecialFields($entityName); >>
1578    
1579  Write the contents of all the relations to tab-delimited files in the specified directory.  Return a hash mapping special fields in the specified entity to the value of their
1580  Each file will have the same name as the relation dumped, with an extension of DTX.  C<special> attribute. This enables the subclass to get access to the special field
1581    attributes without needed to plumb the internal ERDB data structures.
1582    
1583  =over 4  =over 4
1584    
1585  =item outputDirectory  =item entityName
1586    
1587  Name of the directory into which the relation files should be dumped.  Name of the entity whose special fields are desired.
1588    
1589    =item RETURN
1590    
1591    Returns a hash. The keys of the hash are the special field names, and the values
1592    are the values from each special field's C<special> attribute.
1593    
1594  =back  =back
1595    
1596  =cut  =cut
1597    
1598  sub DumpRelations {  sub SpecialFields {
1599      # Get the parameters.      # Get the parameters.
1600      my ($self, $outputDirectory) = @_;      my ($self, $entityName) = @_;
1601      # Now we need to run through all the relations. First, we loop through the entities.      # Declare the return variable.
1602      my $metaData = $self->{_metaData};      my %retVal = ();
1603      my $entities = $metaData->{Entities};      # Find the entity's data structure.
1604      for my $entityName (keys %{$entities}) {      my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1605          my $entityStructure = $entities->{$entityName};      # Loop through its fields, adding each special field to the return hash.
1606          # Get the entity's relations.      my $fieldHash = $entityData->{Fields};
1607          my $relationList = $entityStructure->{Relations};      for my $fieldName (keys %{$fieldHash}) {
1608          # Loop through the relations, dumping them.          my $fieldData = $fieldHash->{$fieldName};
1609          for my $relationName (keys %{$relationList}) {          if (exists $fieldData->{special}) {
1610              my $relation = $relationList->{$relationName};              $retVal{$fieldName} = $fieldData->{special};
             $self->_DumpRelation($outputDirectory, $relationName, $relation);  
         }  
1611      }      }
     # Next, we loop through the relationships.  
     my $relationships = $metaData->{Relationships};  
     for my $relationshipName (keys %{$relationships}) {  
         my $relationshipStructure = $relationships->{$relationshipName};  
         # Dump this relationship's relation.  
         $self->_DumpRelation($outputDirectory, $relationshipName, $relationshipStructure->{Relations}->{$relationshipName});  
1612      }      }
1613        # Return the result.
1614        return %retVal;
1615  }  }
1616    
1617  =head3 InsertObject  =head3 Delete
1618    
1619  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>  C<< my $stats = $erdb->Delete($entityName, $objectID, %options); >>
1620    
1621  Insert an object into the database. The object is defined by a type name and then a hash  Delete an entity instance from the database. The instance is deleted along with all entity and
1622  of field names to values. Field values in the primary relation are represented by scalars.  relationship instances dependent on it. The definition of I<dependence> is recursive.
 (Note that for relationships, the primary relation is the B<only> relation.)  
 Field values for the other relations comprising the entity are always list references. For  
 example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases  
 C<ZP_00210270.1> and C<gi|46206278>.  
1623    
1624  C<< $erdb->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>  An object is always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many
1625    relationship connected to a dependent entity or if it is the "to" entity connected to a 1-to-many
1626    dependent relationship.
1627    
1628  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and  =over 4
 property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.  
1629    
1630  C<< $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>  =item entityName
1631    
1632  =over 4  Name of the entity type for the instance being deleted.
1633    
1634  =item newObjectType  =item objectID
1635    
1636  Type name of the object to insert.  ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),
1637    then it is presumed to by a LIKE pattern.
1638    
1639  =item fieldHash  =item options
1640    
1641  Hash of field names to values.  A hash detailing the options for this delete operation.
1642    
1643  =item RETURN  =item RETURN
1644    
1645  Returns 1 if successful, 0 if an error occurred.  Returns a statistics object indicating how many records of each particular table were
1646    deleted.
1647    
1648  =back  =back
1649    
1650  =cut  The permissible options for this method are as follows.
1651    
1652  sub InsertObject {  =over 4
1653    
1654    =item testMode
1655    
1656    If TRUE, then the delete statements will be traced, but no changes will be made to the database.
1657    
1658    =item keepRoot
1659    
1660    If TRUE, then the entity instances will not be deleted, only the dependent records.
1661    
1662    =back
1663    
1664    =cut
1665    #: Return Type $%;
1666    sub Delete {
1667      # Get the parameters.      # Get the parameters.
1668      my ($self, $newObjectType, $fieldHash) = @_;      my ($self, $entityName, $objectID, %options) = @_;
1669      # Denote that so far we appear successful.      # Declare the return variable.
1670      my $retVal = 1;      my $retVal = Stats->new();
1671      # Get the database handle.      # Get the DBKernel object.
1672      my $dbh = $self->{_dbh};      my $db = $self->{_dbh};
1673      # Get the relation list.      # We're going to generate all the paths branching out from the starting entity. One of
1674      my $relationTable = $self->_GetRelationTable($newObjectType);      # the things we have to be careful about is preventing loops. We'll use a hash to
1675      # Loop through the relations. We'll build insert statements for each one. If a relation is      # determine if we've hit a loop.
1676      # secondary, we may end up generating multiple insert statements. If an error occurs, we      my %alreadyFound = ();
1677      # stop the loop.      # These next lists will serve as our result stack. We start by pushing object lists onto
1678      my @relationList = keys %{$relationTable};      # the stack, and then popping them off to do the deletes. This means the deletes will
1679      for (my $i = 0; $retVal && $i <= $#relationList; $i++) {      # start with the longer paths before getting to the shorter ones. That, in turn, makes
1680          my $relationName = $relationList[$i];      # sure we don't delete records that might be needed to forge relationships back to the
1681          my $relationDefinition = $relationTable->{$relationName};      # original item. We have two lists-- one for TO-relationships, and one for
1682          # Get the relation's fields. For each field we will collect a value in the corresponding      # FROM-relationships and entities.
1683          # position of the @valueList array. If one of the fields is missing, we will add it to the      my @fromPathList = ();
1684          # @missing list.      my @toPathList = ();
1685          my @fieldList = @{$relationDefinition->{Fields}};      # This final list is used to remember what work still needs to be done. We push paths
1686          my @fieldNameList = ();      # onto the list, then pop them off to extend the paths. We prime it with the starting
1687          my @valueList = ();      # point. Note that we will work hard to insure that the last item on a path in the
1688          my @missing = ();      # to-do list is always an entity.
1689          my $recordCount = 1;      my @todoList = ([$entityName]);
1690          for my $fieldDescriptor (@fieldList) {      while (@todoList) {
1691              # Get the field name and save it. Note we need to fix it up so the hyphens          # Get the current path.
1692              # are converted to underscores.          my $current = pop @todoList;
1693              my $fieldName = $fieldDescriptor->{name};          # Copy it into a list.
1694              push @fieldNameList, _FixName($fieldName);          my @stackedPath = @{$current};
1695              # Look for the named field in the incoming structure. Note that we are looking          # Pull off the last item on the path. It will always be an entity.
1696              # for the real field name, not the fixed-up one!          my $myEntityName = pop @stackedPath;
1697              if (exists $fieldHash->{$fieldName}) {          # Add it to the alreadyFound list.
1698                  # Here we found the field. Stash it in the value list.          $alreadyFound{$myEntityName} = 1;
1699                  my $value = $fieldHash->{$fieldName};          # Figure out if we need to delete this entity.
1700                  push @valueList, $value;          if ($myEntityName ne $entityName || ! $options{keepRoot}) {
1701                  # If the value is a list, we may need to increment the record count.              # Get the entity data.
1702                  if (ref $value eq "ARRAY") {              my $entityData = $self->_GetStructure($myEntityName);
1703                      my $thisCount = @{$value};              # Loop through the entity's relations. A DELETE command will be needed for each of them.
1704                      if ($recordCount == 1) {              my $relations = $entityData->{Relations};
1705                          # Here we have our first list, so we save its count.              for my $relation (keys %{$relations}) {
1706                          $recordCount = $thisCount;                  my @augmentedList = (@stackedPath, $relation);
1707                      } elsif ($recordCount != $thisCount) {                  push @fromPathList, \@augmentedList;
                         # Here we have a second list, so its length has to match the  
                         # previous lists.  
                         Trace("Field $value in new $newObjectType object has an invalid list length $thisCount. Expected $recordCount.") if T(0);  
                         $retVal = 0;  
1708                      }                      }
1709                  }                  }
1710            # Now we need to look for relationships connected to this entity.
1711            my $relationshipList = $self->{_metaData}->{Relationships};
1712            for my $relationshipName (keys %{$relationshipList}) {
1713                my $relationship = $relationshipList->{$relationshipName};
1714                # Check the FROM field. We're only interested if it's us.
1715                if ($relationship->{from} eq $myEntityName) {
1716                    # Add the path to this relationship.
1717                    my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1718                    push @fromPathList, \@augmentedList;
1719                    # Check the arity. If it's MM we're done. If it's 1M
1720                    # and the target hasn't been seen yet, we want to
1721                    # stack the entity for future processing.
1722                    if ($relationship->{arity} eq '1M') {
1723                        my $toEntity = $relationship->{to};
1724                        if (! exists $alreadyFound{$toEntity}) {
1725                            # Here we have a new entity that's dependent on
1726                            # the current entity, so we need to stack it.
1727                            my @stackList = (@augmentedList, $toEntity);
1728                            push @fromPathList, \@stackList;
1729              } else {              } else {
1730                  # Here the field is not present. Flag it as missing.                          Trace("$toEntity ignored because it occurred previously.") if T(4);
                 push @missing, $fieldName;  
1731              }              }
1732          }          }
         # If we are the primary relation, add the new-record flag.  
         if ($relationName eq $newObjectType) {  
             push @valueList, 1;  
             push @fieldNameList, "new_record";  
1733          }          }
1734          # Only proceed if there are no missing fields.              # Now check the TO field. In this case only the relationship needs
1735          if (@missing > 0) {              # deletion.
1736              Trace("Relation $relationName for $newObjectType skipped due to missing fields: " .              if ($relationship->{to} eq $myEntityName) {
1737                  join(' ', @missing)) if T(1);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1738          } else {                  push @toPathList, \@augmentedList;
             # Build the INSERT statement.  
             my $statement = "INSERT INTO $relationName (" . join (', ', @fieldNameList) .  
                 ") VALUES (";  
             # Create a marker list of the proper size and put it in the statement.  
             my @markers = ();  
             while (@markers < @fieldNameList) { push @markers, '?'; }  
             $statement .= join(', ', @markers) . ")";  
             # We have the insert statement, so prepare it.  
             my $sth = $dbh->prepare_command($statement);  
             Trace("Insert statement prepared: $statement") if T(3);  
             # Now we loop through the values. If a value is scalar, we use it unmodified. If it's  
             # a list, we use the current element. The values are stored in the @parameterList array.  
             my $done = 0;  
             for (my $i = 0; $i < $recordCount; $i++) {  
                 # Clear the parameter list array.  
                 my @parameterList = ();  
                 # Loop through the values.  
                 for my $value (@valueList) {  
                     # Check to see if this is a scalar value.  
                     if (ref $value eq "ARRAY") {  
                         # Here we have a list value. Pull the current entry.  
                         push @parameterList, $value->[$i];  
                     } else {  
                         # Here we have a scalar value. Use it unmodified.  
                         push @parameterList, $value;  
1739                      }                      }
1740                  }                  }
                 # 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);  
1741                  }                  }
1742        # Create the first qualifier for the WHERE clause. This selects the
1743        # keys of the primary entity records to be deleted. When we're deleting
1744        # from a dependent table, we construct a join path from the first qualifier
1745        # to the table containing the dependent records to delete.
1746        my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
1747        # We need to make two passes. The first is through the to-list, and
1748        # the second through the from-list. The from-list is second because
1749        # the to-list may need to pass through some of the entities the
1750        # from-list would delete.
1751        my %stackList = ( from_link => \@fromPathList, to_link => \@toPathList );
1752        # Now it's time to do the deletes. We do it in two passes.
1753        for my $keyName ('to_link', 'from_link') {
1754            # Get the list for this key.
1755            my @pathList = @{$stackList{$keyName}};
1756            Trace(scalar(@pathList) . " entries in path list for $keyName.") if T(3);
1757            # Loop through this list.
1758            while (my $path = pop @pathList) {
1759                # Get the table whose rows are to be deleted.
1760                my @pathTables = @{$path};
1761                # Start the DELETE statement. We need to call DBKernel because the
1762                # syntax of a DELETE-USING varies among DBMSs.
1763                my $target = $pathTables[$#pathTables];
1764                my $stmt = $db->SetUsing(@pathTables);
1765                # Now start the WHERE. The first thing is the ID field from the starting table. That
1766                # starting table will either be the entity relation or one of the entity's
1767                # sub-relations.
1768                $stmt .= " WHERE $pathTables[0].id $qualifier";
1769                # Now we run through the remaining entities in the path, connecting them up.
1770                for (my $i = 1; $i <= $#pathTables; $i += 2) {
1771                    # Connect the current relationship to the preceding entity.
1772                    my ($entity, $rel) = @pathTables[$i-1,$i];
1773                    # The style of connection depends on the direction of the relationship.
1774                    $stmt .= " AND $entity.id = $rel.$keyName";
1775                    if ($i + 1 <= $#pathTables) {
1776                        # Here there's a next entity, so connect that to the relationship's
1777                        # to-link.
1778                        my $entity2 = $pathTables[$i+1];
1779                        $stmt .= " AND $rel.to_link = $entity2.id";
1780                    }
1781                }
1782                # Now we have our desired DELETE statement.
1783                if ($options{testMode}) {
1784                    # Here the user wants to trace without executing.
1785                    Trace($stmt) if T(0);
1786                } else {
1787                    # Here we can delete. Note that the SQL method dies with a confession
1788                    # if an error occurs, so we just go ahead and do it.
1789                    Trace("Executing delete from $target using '$objectID'.") if T(3);
1790                    my $rv = $db->SQL($stmt, 0, $objectID);
1791                    # Accumulate the statistics for this delete. The only rows deleted
1792                    # are from the target table, so we use its name to record the
1793                    # statistic.
1794                    $retVal->Add($target, $rv);
1795              }              }
1796          }          }
1797      }      }
1798      # Return the success indicator.      # Return the result.
1799      return $retVal;      return $retVal;
1800  }  }
1801    
1802  =head3 LoadTable  =head3 Disconnect
1803    
1804  C<< my %results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>  C<< $erdb->Disconnect($relationshipName, $originEntityName, $originEntityID); >>
1805    
1806  Load data from a tab-delimited file into a specified table, optionally re-creating the table  Disconnect an entity instance from all the objects to which it is related. This
1807  first.  will delete each relationship instance that connects to the specified entity.
1808    
1809  =over 4  =over 4
1810    
1811  =item fileName  =item relationshipName
   
 Name of the file from which the table data should be loaded.  
   
 =item relationName  
1812    
1813  Name of the relation to be loaded. This is the same as the table name.  Name of the relationship whose instances are to be deleted.
1814    
1815  =item truncateFlag  =item originEntityName
1816    
1817  TRUE if the table should be dropped and re-created, else FALSE  Name of the entity that is to be disconnected.
1818    
1819  =item RETURN  =item originEntityID
1820    
1821  Returns a statistical object containing the number of records read and a list of  ID of the entity that is to be disconnected.
 the error messages.  
1822    
1823  =back  =back
1824    
1825  =cut  =cut
1826  sub LoadTable {  
1827    sub Disconnect {
1828      # Get the parameters.      # Get the parameters.
1829      my ($self, $fileName, $relationName, $truncateFlag) = @_;      my ($self, $relationshipName, $originEntityName, $originEntityID) = @_;
1830      # Create the statistical return object.      # Get the relationship descriptor.
1831      my $retVal = _GetLoadStats();      my $structure = $self->_GetStructure($relationshipName);
1832      # Trace the fact of the load.      # Insure we have a relationship.
1833      Trace("Loading table $relationName from $fileName") if T(2);      if (! exists $structure->{from}) {
1834            Confess("$relationshipName is not a relationship in the database.");
1835        } else {
1836      # Get the database handle.      # Get the database handle.
1837      my $dbh = $self->{_dbh};      my $dbh = $self->{_dbh};
1838      # Get the relation data.          # We'll set this value to 1 if we find our entity.
1839      my $relation = $self->_FindRelation($relationName);          my $found = 0;
1840      # Check the truncation flag.          # Loop through the ends of the relationship.
1841      if ($truncateFlag) {          for my $dir ('from', 'to') {
1842          Trace("Creating table $relationName") if T(2);              if ($structure->{$dir} eq $originEntityName) {
1843          # Compute the row count estimate. We take the size of the load file,                  # Delete all relationship instances on this side of the entity instance.
1844          # divide it by the estimated row size, and then multiply by 1.5 to                  $dbh->SQL("DELETE FROM $relationshipName WHERE ${dir}_link = ?", 0, $originEntityID);
1845          # leave extra room. We postulate a minimum row count of 1000 to                  $found = 1;
         # prevent problems with incoming empty load files.  
         my $rowSize = $self->EstimateRowSize($relationName);  
         my $fileSize = -s $fileName;  
         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 ($@) {  
                 $retVal->AddMessage($@);  
             }  
         }  
1846      }      }
     # Determine whether or not this is a primary relation. Primary relations have an extra  
     # field indicating whether or not a given object is new or was loaded from the flat files.  
     my $primary = $self->_IsPrimary($relationName);  
     # Get the number of fields in this relation.  
     my @fieldList = @{$relation->{Fields}};  
     my $fieldCount = @fieldList;  
     # Start a database transaction.  
     $dbh->begin_tran;  
     # Open the relation file. We need to create a cleaned-up copy before loading.  
     open TABLEIN, '<', $fileName;  
     my $tempName = "$fileName.tbl";  
     open TABLEOUT, '>', $tempName;  
     my $inputCount = 0;  
     # Loop through the file.  
     while (<TABLEIN>) {  
         $inputCount++;  
         # Chop off the new-line character.  
         my $record = Tracer::Strip($_);  
         # Only proceed if the record is non-blank.  
         if ($record) {  
             # Escape all the backslashes found in the line.  
             $record =~ s/\\/\\\\/g;  
             # Insure the number of fields is correct.  
             my @fields = split /\t/, $record;  
             while (@fields > $fieldCount) {  
                 my $extraField = $fields[$#fields];  
                 delete $fields[$#fields];  
                 if ($extraField) {  
                     Trace("Nonblank extra field value \"$extraField\" deleted from record $inputCount of $fileName.") if T(1);  
                 }  
             }  
             while (@fields < $fieldCount) {  
                 push @fields, "";  
             }  
             # If this is a primary relation, add a 0 for the new-record flag (indicating that  
             # this record is not new, but part of the original load).  
             if ($primary) {  
                 push @fields, "0";  
             }  
             # Write the record.  
             $record = join "\t", @fields;  
             print TABLEOUT "$record\n";  
             # Count the record written.  
             my $count = $retVal->Add('records');  
             my $len = length $record;  
             Trace("Record $count written with $len characters.") if T(4);  
         } else {  
             # Here we have a blank record.  
             $retVal->Add('skipped');  
         }  
     }  
     # Close the files.  
     close TABLEIN;  
     close TABLEOUT;  
     Trace("Temporary file $tempName created.") if T(2);  
     # Load the table.  
     my $rv;  
     eval {  
         $rv = $dbh->load_table(file => $tempName, tbl => $relationName);  
     };  
     if (!defined $rv) {  
         $retVal->AddMessage($@) if ($@);  
         $retVal->AddMessage("Table load failed for $relationName using $tempName.");  
         Trace("Table load failed for $relationName.") if T(1);  
     } else {  
         # Here we successfully loaded the table. Trace the number of records loaded.  
         Trace("$retVal->{records} records read for $relationName.") if T(2);  
         # If we're rebuilding, we need to create the table indexes.  
         if ($truncateFlag && ! $dbh->{_preIndex}) {  
             eval {  
                 $self->CreateIndex($relationName);  
             };  
             if ($@) {  
                 $retVal->AddMessage($@);  
1847              }              }
1848            # Insure we found the entity on at least one end.
1849            if (! $found) {
1850                Confess("Entity \"$originEntityName\" does not use $relationshipName.");
1851          }          }
         # Analyze the table to help optimize tables.  
1852      }      }
     # Commit the database changes.  
     $dbh->commit_tran;  
     $dbh->vacuum_it($relationName);  
     # Delete the temporary file.  
     unlink $tempName;  
     # Return the statistics.  
     return $retVal;  
1853  }  }
1854    
1855  =head3 GenerateEntity  =head3 DeleteRow
1856    
1857  C<< my $fieldHash = $erdb->GenerateEntity($id, $type, \%values); >>  C<< $erdb->DeleteRow($relationshipName, $fromLink, $toLink, \%values); >>
1858    
1859  Generate the data for a new entity instance. This method creates a field hash suitable for  Delete a row from a relationship. In most cases, only the from-link and to-link are
1860  passing as a parameter to L</InsertObject>. The ID is specified by the callr, but the rest  needed; however, for relationships with intersection data values can be specified
1861  of the fields are generated using information in the database schema.  for the other fields using a hash.
   
 Each data type has a default algorithm for generating random test data. This can be overridden  
 by including a B<DataGen> element in the field. If this happens, the content of the element is  
 executed as a PERL program in the context of this module. The element may make use of a C<$this>  
 variable which contains the field hash as it has been built up to the current point. If any  
 fields are dependent on other fields, the C<pass> attribute can be used to control the order  
 in which the fields are generated. A field with a high data pass number will be generated after  
 a field with a lower one. If any external values are needed, they should be passed in via the  
 optional third parameter, which will be available to the data generation script under the name  
 C<$value>. Several useful utility methods are provided for generating random values, including  
 L</IntGen>, L</StringGen>, L</FloatGen>, and L</DateGen>. Note that dates are stored and generated  
 in the form of a timestamp number rather than a string.  
1862    
1863  =over 4  =over 4
1864    
1865  =item id  =item relationshipName
1866    
1867  ID to assign to the new entity.  Name of the relationship from which the row is to be deleted.
1868    
1869  =item type  =item fromLink
1870    
1871    ID of the entity instance in the From direction.
1872    
1873  Type name for the new entity.  =item toLink
1874    
1875    ID of the entity instance in the To direction.
1876    
1877  =item values  =item values
1878    
1879  Hash containing additional values that might be needed by the data generation methods (optional).  Reference to a hash of other values to be used for filtering the delete.
1880    
1881  =back  =back
1882    
1883  =cut  =cut
1884    
1885  sub GenerateEntity {  sub DeleteRow {
1886      # Get the parameters.      # Get the parameters.
1887      my ($self, $id, $type, $values) = @_;      my ($self, $relationshipName, $fromLink, $toLink, $values) = @_;
1888      # Create the return hash.      # Create a hash of all the filter information.
1889      my $this = { id => $id };      my %filter = ('from-link' => $fromLink, 'to-link' => $toLink);
1890      # Get the metadata structure.      if (defined $values) {
1891      my $metadata = $self->{_metaData};          for my $key (keys %{$values}) {
1892      # Get this entity's list of fields.              $filter{$key} = $values->{$key};
1893      if (!exists $metadata->{Entities}->{$type}) {          }
         Confess("Unrecognized entity type $type in GenerateEntity.");  
     } else {  
         my $entity = $metadata->{Entities}->{$type};  
         my $fields = $entity->{Fields};  
         # Generate data from the fields.  
         _GenerateFields($this, $fields, $type, $values);  
1894      }      }
1895      # Return the hash created.      # Build an SQL statement out of the hash.
1896      return $this;      my @filters = ();
1897        my @parms = ();
1898        for my $key (keys %filter) {
1899            push @filters, _FixName($key) . " = ?";
1900            push @parms, $filter{$key};
1901        }
1902        Trace("Parms for delete row are " . join(", ", map { "\"$_\"" } @parms) . ".") if T(SQL => 4);
1903        my $command = "DELETE FROM $relationshipName WHERE " .
1904                      join(" AND ", @filters);
1905        # Execute it.
1906        my $dbh = $self->{_dbh};
1907        $dbh->SQL($command, undef, @parms);
1908  }  }
1909    
1910  =head3 GetEntity  =head3 SortNeeded
1911    
1912  C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>  C<< my $parms = $erdb->SortNeeded($relationName); >>
1913    
1914  Return an object describing the entity instance with a specified ID.  Return the pipe command for the sort that should be applied to the specified
1915    relation when creating the load file.
1916    
1917  =over 4  For example, if the load file should be sorted ascending by the first
1918    field, this method would return
1919    
1920  =item entityType      sort -k1 -t"\t"
1921    
1922  Entity type name.  If the first field is numeric, the method would return
1923    
1924  =item ID      sort -k1n -t"\t"
1925    
1926  ID of the desired entity.  Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate
1927    keys using a sort.
1928    
1929  =item RETURN  =over 4
1930    
1931  Returns a B<DBObject> representing the desired entity instance, or an undefined value if no  =item relationName
1932  instance is found with the specified key.  
1933    Name of the relation to be examined.
1934    
1935    =item
1936    
1937    Returns the sort command to use for sorting the relation, suitable for piping.
1938    
1939  =back  =back
1940    
1941  =cut  =cut
1942    #: Return Type $;
1943  sub GetEntity {  sub SortNeeded {
1944      # Get the parameters.      # Get the parameters.
1945      my ($self, $entityType, $ID) = @_;      my ($self, $relationName) = @_;
1946      # Create a query.      # Declare a descriptor to hold the names of the key fields.
1947      my $query = $self->Get([$entityType], "$entityType(id) = ?", $ID);      my @keyNames = ();
1948      # Get the first (and only) object.      # Get the relation structure.
1949      my $retVal = $query->Fetch();      my $relationData = $self->_FindRelation($relationName);
1950        # Find out if the relation is a primary entity relation,
1951        # a relationship relation, or a secondary entity relation.
1952        my $entityTable = $self->{_metaData}->{Entities};
1953        my $relationshipTable = $self->{_metaData}->{Relationships};
1954        if (exists $entityTable->{$relationName}) {
1955            # Here we have a primary entity relation.
1956            push @keyNames, "id";
1957        } elsif (exists $relationshipTable->{$relationName}) {
1958            # Here we have a relationship. We sort using the FROM index.
1959            my $relationshipData = $relationshipTable->{$relationName};
1960            my $index = $relationData->{Indexes}->{idxFrom};
1961            push @keyNames, @{$index->{IndexFields}};
1962        } else {
1963            # Here we have a secondary entity relation, so we have a sort on the ID field.
1964            push @keyNames, "id";
1965        }
1966        # Now we parse the key names into sort parameters. First, we prime the return
1967        # string.
1968        my $retVal = "sort -t\"\t\" ";
1969        # Get the relation's field list.
1970        my @fields = @{$relationData->{Fields}};
1971        # Loop through the keys.
1972        for my $keyData (@keyNames) {
1973            # Get the key and the ordering.
1974            my ($keyName, $ordering);
1975            if ($keyData =~ /^([^ ]+) DESC/) {
1976                ($keyName, $ordering) = ($1, "descending");
1977            } else {
1978                ($keyName, $ordering) = ($keyData, "ascending");
1979            }
1980            # Find the key's position and type.
1981            my $fieldSpec;
1982            for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {
1983                my $thisField = $fields[$i];
1984                if ($thisField->{name} eq $keyName) {
1985                    # Get the sort modifier for this field type. The modifier
1986                    # decides whether we're using a character, numeric, or
1987                    # floating-point sort.
1988                    my $modifier = $TypeTable{$thisField->{type}}->{sort};
1989                    # If the index is descending for this field, denote we want
1990                    # to reverse the sort order on this field.
1991                    if ($ordering eq 'descending') {
1992                        $modifier .= "r";
1993                    }
1994                    # Store the position and modifier into the field spec, which
1995                    # will stop the inner loop. Note that the field number is
1996                    # 1-based in the sort command, so we have to increment the
1997                    # index.
1998                    $fieldSpec = ($i + 1) . $modifier;
1999                }
2000            }
2001            # Add this field to the sort command.
2002            $retVal .= " -k$fieldSpec";
2003        }
2004      # Return the result.      # Return the result.
2005      return $retVal;      return $retVal;
2006  }  }
2007    
2008  =head3 GetEntityValues  =head3 GetList
2009    
2010  C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>  C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>
2011    
2012    Return a list of object descriptors for the specified objects as determined by the
2013    specified filter clause.
2014    
2015  Return a list of values from a specified entity instance.  This method is essentially the same as L</Get> except it returns a list of objects rather
2016    than a query object that can be used to get the results one record at a time.
2017    
2018  =over 4  =over 4
2019    
2020  =item entityType  =item objectNames
2021    
2022  Entity type name.  List containing the names of the entity and relationship objects to be retrieved.
2023    
2024  =item ID  =item filterClause
2025    
2026  ID of the desired entity.  WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
2027    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
2028    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
2029    in the filter clause should be added to the parameter list as additional parameters. The
2030    fields in a filter clause can come from primary entity relations, relationship relations,
2031    or secondary entity relations; however, all of the entities and relationships involved must
2032    be included in the list of object names.
2033    
2034  =item fields  The filter clause can also specify a sort order. To do this, simply follow the filter string
2035    with an ORDER BY clause. For example, the following filter string gets all genomes for a
2036    particular genus and sorts them by species name.
2037    
2038  List of field names, each of the form I<objectName>C<(>I<fieldName>C<)>.  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
2039    
2040    The rules for field references in a sort order are the same as those for field references in the
2041    filter clause in general; however, odd things may happen if a sort field is from a secondary
2042    relation.
2043    
2044    =item params
2045    
2046    Reference to a list of parameter values to be substituted into the filter clause.
2047    
2048  =item RETURN  =item RETURN
2049    
2050  Returns a flattened list of the values of the specified fields for the specified entity.  Returns a list of B<DBObject>s that satisfy the query conditions.
2051    
2052  =back  =back
2053    
2054  =cut  =cut
2055    #: Return Type @%
2056  sub GetEntityValues {  sub GetList {
2057      # Get the parameters.      # Get the parameters.
2058      my ($self, $entityType, $ID, $fields) = @_;      my ($self, $objectNames, $filterClause, $params) = @_;
2059      # Get the specified entity.      # Declare the return variable.
     my $entity = $self->GetEntity($entityType, $ID);  
     # Declare the return list.  
2060      my @retVal = ();      my @retVal = ();
2061      # If we found the entity, push the values into the return list.      # Perform the query.
2062      if ($entity) {      my $query = $self->Get($objectNames, $filterClause, $params);
2063          push @retVal, $entity->Values($fields);      # Loop through the results.
2064        while (my $object = $query->Fetch) {
2065            push @retVal, $object;
2066      }      }
2067      # Return the result.      # Return the result.
2068      return @retVal;      return @retVal;
2069  }  }
2070    
2071  =head3 GetAll  =head3 GetCount
2072    
2073  C<< my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>  C<< my $count = $erdb->GetCount(\@objectNames, $filter, \@params); >>
2074    
2075  Return a list of values taken from the objects returned by a query. The first three  Return the number of rows found by a specified query. This method would
2076  parameters correspond to the parameters of the L</Get> method. The final parameter is  normally be used to count the records in a single table. For example, in a
2077  a list of the fields desired from each record found by the query. The field name  genetics database
 syntax is the standard syntax used for fields in the B<ERDB> system--  
 B<I<objectName>(I<fieldName>)>-- where I<objectName> is the name of the relevant entity  
 or relationship and I<fieldName> is the name of the field.  
2078    
2079  The list returned will be a list of lists. Each element of the list will contain      my $count = $erdb->GetCount(['Genome'], 'Genome(genus-species) LIKE ?', ['homo %']);
2080  the values returned for the fields specified in the fourth parameter. If one of the  
2081  fields specified returns multiple values, they are flattened in with the rest. For  would return the number of genomes for the genus I<homo>. It is conceivable, however,
2082  example, the following call will return a list of the features in a particular  to use it to return records based on a join. For example,
2083  spreadsheet cell, and each feature will be represented by a list containing the  
2084  feature ID followed by all of its aliases.      my $count = $erdb->GetCount(['HasFeature', 'Genome'], 'Genome(genus-species) LIKE ?',
2085                                    ['homo %']);
2086    
2087    would return the number of features for genomes in the genus I<homo>. Note that
2088    only the rows from the first table are counted. If the above command were
2089    
2090  C<< $query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>      my $count = $erdb->GetCount(['Genome', 'Feature'], 'Genome(genus-species) LIKE ?',
2091                                    ['homo %']);
2092    
2093    it would return the number of genomes, not the number of genome/feature pairs.
2094    
2095  =over 4  =over 4
2096    
2097  =item objectNames  =item objectNames
2098    
2099  List containing the names of the entity and relationship objects to be retrieved.  Reference to a list of the objects (entities and relationships) included in the
2100    query.
2101    
2102  =item filterClause  =item filter
2103    
2104  WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  A filter clause for restricting the query. The rules are the same as for the L</Get>
2105    method.
2106    
2107    =item params
2108    
2109    Reference to a list of the parameter values to be substituted for the parameter marks
2110    in the filter.
2111    
2112    =item RETURN
2113    
2114    Returns a count of the number of records in the first table that would satisfy
2115    the query.
2116    
2117    =back
2118    
2119    =cut
2120    
2121    sub GetCount {
2122        # Get the parameters.
2123        my ($self, $objectNames, $filter, $params) = @_;
2124        # Insure the params argument is an array reference if the caller left it off.
2125        if (! defined($params)) {
2126            $params = [];
2127        }
2128        # Declare the return variable.
2129        my $retVal;
2130        # Find out if we're counting an entity or a relationship.
2131        my $countedField;
2132        if ($self->IsEntity($objectNames->[0])) {
2133            $countedField = "id";
2134        } else {
2135            # For a relationship we count the to-link because it's usually more
2136            # numerous. Note we're automatically converting to the SQL form
2137            # of the field name (to_link vs. to-link).
2138            $countedField = "to_link";
2139        }
2140        # Create the SQL command suffix to get the desired records.
2141        my ($suffix, $mappedNameListRef, $mappedNameHashRef) = $self->_SetupSQL($objectNames,
2142                                                                                $filter);
2143        # Prefix it with text telling it we want a record count.
2144        my $firstObject = $mappedNameListRef->[0];
2145        my $command = "SELECT COUNT($firstObject.$countedField) $suffix";
2146        # Prepare and execute the command.
2147        my $sth = $self->_GetStatementHandle($command, $params);
2148        # Get the count value.
2149        ($retVal) = $sth->fetchrow_array();
2150        # Check for a problem.
2151        if (! defined($retVal)) {
2152            if ($sth->err) {
2153                # Here we had an SQL error.
2154                Confess("Error retrieving row count: " . $sth->errstr());
2155            } else {
2156                # Here we have no result.
2157                Confess("No result attempting to retrieve row count.");
2158            }
2159        }
2160        # Return the result.
2161        return $retVal;
2162    }
2163    
2164    =head3 ComputeObjectSentence
2165    
2166    C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>
2167    
2168    Check an object name, and if it is a relationship convert it to a relationship sentence.
2169    
2170    =over 4
2171    
2172    =item objectName
2173    
2174    Name of the entity or relationship.
2175    
2176    =item RETURN
2177    
2178    Returns a string containing the entity name or a relationship sentence.
2179    
2180    =back
2181    
2182    =cut
2183    
2184    sub ComputeObjectSentence {
2185        # Get the parameters.
2186        my ($self, $objectName) = @_;
2187        # Set the default return value.
2188        my $retVal = $objectName;
2189        # Look for the object as a relationship.
2190        my $relTable = $self->{_metaData}->{Relationships};
2191        if (exists $relTable->{$objectName}) {
2192            # Get the relationship sentence.
2193            $retVal = _ComputeRelationshipSentence($objectName, $relTable->{$objectName});
2194        }
2195        # Return the result.
2196        return $retVal;
2197    }
2198    
2199    =head3 DumpRelations
2200    
2201    C<< $erdb->DumpRelations($outputDirectory); >>
2202    
2203    Write the contents of all the relations to tab-delimited files in the specified directory.
2204    Each file will have the same name as the relation dumped, with an extension of DTX.
2205    
2206    =over 4
2207    
2208    =item outputDirectory
2209    
2210    Name of the directory into which the relation files should be dumped.
2211    
2212    =back
2213    
2214    =cut
2215    
2216    sub DumpRelations {
2217        # Get the parameters.
2218        my ($self, $outputDirectory) = @_;
2219        # Now we need to run through all the relations. First, we loop through the entities.
2220        my $metaData = $self->{_metaData};
2221        my $entities = $metaData->{Entities};
2222        for my $entityName (keys %{$entities}) {
2223            my $entityStructure = $entities->{$entityName};
2224            # Get the entity's relations.
2225            my $relationList = $entityStructure->{Relations};
2226            # Loop through the relations, dumping them.
2227            for my $relationName (keys %{$relationList}) {
2228                my $relation = $relationList->{$relationName};
2229                $self->_DumpRelation($outputDirectory, $relationName, $relation);
2230            }
2231        }
2232        # Next, we loop through the relationships.
2233        my $relationships = $metaData->{Relationships};
2234        for my $relationshipName (keys %{$relationships}) {
2235            my $relationshipStructure = $relationships->{$relationshipName};
2236            # Dump this relationship's relation.
2237            $self->_DumpRelation($outputDirectory, $relationshipName, $relationshipStructure->{Relations}->{$relationshipName});
2238        }
2239    }
2240    
2241    =head3 InsertValue
2242    
2243    C<< $erdb->InsertValue($entityID, $fieldName, $value); >>
2244    
2245    This method will insert a new value into the database. The value must be one
2246    associated with a secondary relation, since primary values cannot be inserted:
2247    they occur exactly once. Secondary values, on the other hand, can be missing
2248    or multiply-occurring.
2249    
2250    =over 4
2251    
2252    =item entityID
2253    
2254    ID of the object that is to receive the new value.
2255    
2256    =item fieldName
2257    
2258    Field name for the new value-- this includes the entity name, since
2259    field names are of the format I<objectName>C<(>I<fieldName>C<)>.
2260    
2261    =item value
2262    
2263    New value to be put in the field.
2264    
2265    =back
2266    
2267    =cut
2268    
2269    sub InsertValue {
2270        # Get the parameters.
2271        my ($self, $entityID, $fieldName, $value) = @_;
2272        # Parse the entity name and the real field name.
2273        if ($fieldName =~ /^([^(]+)\(([^)]+)\)/) {
2274            my $entityName = $1;
2275            my $fieldTitle = $2;
2276            # Get its descriptor.
2277            if (!$self->IsEntity($entityName)) {
2278                Confess("$entityName is not a valid entity.");
2279            } else {
2280                my $entityData = $self->{_metaData}->{Entities}->{$entityName};
2281                # Find the relation containing this field.
2282                my $fieldHash = $entityData->{Fields};
2283                if (! exists $fieldHash->{$fieldTitle}) {
2284                    Confess("$fieldTitle not found in $entityName.");
2285                } else {
2286                    my $relation = $fieldHash->{$fieldTitle}->{relation};
2287                    if ($relation eq $entityName) {
2288                        Confess("Cannot do InsertValue on primary field $fieldTitle of $entityName.");
2289                    } else {
2290                        # Now we can create an INSERT statement.
2291                        my $dbh = $self->{_dbh};
2292                        my $fixedName = _FixName($fieldTitle);
2293                        my $statement = "INSERT INTO $relation (id, $fixedName) VALUES(?, ?)";
2294                        # Execute the command.
2295                        $dbh->SQL($statement, 0, $entityID, $value);
2296                    }
2297                }
2298            }
2299        } else {
2300            Confess("$fieldName is not a valid field name.");
2301        }
2302    }
2303    
2304    =head3 InsertObject
2305    
2306    C<< $erdb->InsertObject($objectType, \%fieldHash); >>
2307    
2308    Insert an object into the database. The object is defined by a type name and then a hash
2309    of field names to values. Field values in the primary relation are represented by scalars.
2310    (Note that for relationships, the primary relation is the B<only> relation.)
2311    Field values for the other relations comprising the entity are always list references. For
2312    example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases
2313    C<ZP_00210270.1> and C<gi|46206278>.
2314    
2315    C<< $erdb->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>
2316    
2317    The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
2318    property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
2319    
2320    C<< $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>
2321    
2322    =over 4
2323    
2324    =item newObjectType
2325    
2326    Type name of the object to insert.
2327    
2328    =item fieldHash
2329    
2330    Hash of field names to values.
2331    
2332    =back
2333    
2334    =cut
2335    
2336    sub InsertObject {
2337        # Get the parameters.
2338        my ($self, $newObjectType, $fieldHash) = @_;
2339        # Denote that so far we appear successful.
2340        my $retVal = 1;
2341        # Get the database handle.
2342        my $dbh = $self->{_dbh};
2343        # Get the relation list.
2344        my $relationTable = $self->_GetRelationTable($newObjectType);
2345        # Loop through the relations. We'll build insert statements for each one. If a relation is
2346        # secondary, we may end up generating multiple insert statements. If an error occurs, we
2347        # stop the loop.
2348        my @relationList = keys %{$relationTable};
2349        for (my $i = 0; $retVal && $i <= $#relationList; $i++) {
2350            my $relationName = $relationList[$i];
2351            my $relationDefinition = $relationTable->{$relationName};
2352            # Get the relation's fields. For each field we will collect a value in the corresponding
2353            # position of the @valueList array. If one of the fields is missing, we will add it to the
2354            # @missing list.
2355            my @fieldList = @{$relationDefinition->{Fields}};
2356            my @fieldNameList = ();
2357            my @valueList = ();
2358            my @missing = ();
2359            my $recordCount = 1;
2360            for my $fieldDescriptor (@fieldList) {
2361                # Get the field name and save it. Note we need to fix it up so the hyphens
2362                # are converted to underscores.
2363                my $fieldName = $fieldDescriptor->{name};
2364                push @fieldNameList, _FixName($fieldName);
2365                # Look for the named field in the incoming structure. Note that we are looking
2366                # for the real field name, not the fixed-up one!
2367                if (exists $fieldHash->{$fieldName}) {
2368                    # Here we found the field. Stash it in the value list.
2369                    my $value = $fieldHash->{$fieldName};
2370                    push @valueList, $value;
2371                    # If the value is a list, we may need to increment the record count.
2372                    if (ref $value eq "ARRAY") {
2373                        my $thisCount = @{$value};
2374                        if ($recordCount == 1) {
2375                            # Here we have our first list, so we save its count.
2376                            $recordCount = $thisCount;
2377                        } elsif ($recordCount != $thisCount) {
2378                            # Here we have a second list, so its length has to match the
2379                            # previous lists.
2380                            Trace("Field $value in new $newObjectType object has an invalid list length $thisCount. Expected $recordCount.") if T(0);
2381                            $retVal = 0;
2382                        }
2383                    }
2384                } else {
2385                    # Here the field is not present. Flag it as missing.
2386                    push @missing, $fieldName;
2387                }
2388            }
2389            # If we are the primary relation, add the new-record flag.
2390            if ($relationName eq $newObjectType) {
2391                push @valueList, 1;
2392                push @fieldNameList, "new_record";
2393            }
2394            # Only proceed if there are no missing fields.
2395            if (@missing > 0) {
2396                Trace("Relation $relationName for $newObjectType skipped due to missing fields: " .
2397                    join(' ', @missing)) if T(1);
2398            } else {
2399                # Build the INSERT statement.
2400                my $statement = "INSERT INTO $relationName (" . join (', ', @fieldNameList) .
2401                    ") VALUES (";
2402                # Create a marker list of the proper size and put it in the statement.
2403                my @markers = ();
2404                while (@markers < @fieldNameList) { push @markers, '?'; }
2405                $statement .= join(', ', @markers) . ")";
2406                # We have the insert statement, so prepare it.
2407                my $sth = $dbh->prepare_command($statement);
2408                Trace("Insert statement prepared: $statement") if T(3);
2409                # Now we loop through the values. If a value is scalar, we use it unmodified. If it's
2410                # a list, we use the current element. The values are stored in the @parameterList array.
2411                my $done = 0;
2412                for (my $i = 0; $i < $recordCount; $i++) {
2413                    # Clear the parameter list array.
2414                    my @parameterList = ();
2415                    # Loop through the values.
2416                    for my $value (@valueList) {
2417                        # Check to see if this is a scalar value.
2418                        if (ref $value eq "ARRAY") {
2419                            # Here we have a list value. Pull the current entry.
2420                            push @parameterList, $value->[$i];
2421                        } else {
2422                            # Here we have a scalar value. Use it unmodified.
2423                            push @parameterList, $value;
2424                        }
2425                    }
2426                    # Execute the INSERT statement with the specified parameter list.
2427                    $retVal = $sth->execute(@parameterList);
2428                    if (!$retVal) {
2429                        my $errorString = $sth->errstr();
2430                        Confess("Error inserting into $relationName: $errorString");
2431                    }
2432                }
2433            }
2434        }
2435        # Return a 1 for backward compatability.
2436        return 1;
2437    }
2438    
2439    =head3 UpdateEntity
2440    
2441    C<< $erdb->UpdateEntity($entityName, $id, \%fields); >>
2442    
2443    Update the values of an entity. This is an unprotected update, so it should only be
2444    done if the database resides on a database server.
2445    
2446    =over 4
2447    
2448    =item entityName
2449    
2450    Name of the entity to update. (This is the entity type.)
2451    
2452    =item id
2453    
2454    ID of the entity to update. If no entity exists with this ID, an error will be thrown.
2455    
2456    =item fields
2457    
2458    Reference to a hash mapping field names to their new values. All of the fields named
2459    must be in the entity's primary relation, and they cannot any of them be the ID field.
2460    
2461    =back
2462    
2463    =cut
2464    
2465    sub UpdateEntity {
2466        # Get the parameters.
2467        my ($self, $entityName, $id, $fields) = @_;
2468        # Get a list of the field names being updated.
2469        my @fieldList = keys %{$fields};
2470        # Verify that the fields exist.
2471        my $checker = $self->GetFieldTable($entityName);
2472        for my $field (@fieldList) {
2473            if ($field eq 'id') {
2474                Confess("Cannot update the ID field for entity $entityName.");
2475            } elsif ($checker->{$field}->{relation} ne $entityName) {
2476                Confess("Cannot find $field in primary relation of $entityName.");
2477            }
2478        }
2479        # Build the SQL statement.
2480        my @sets = ();
2481        my @valueList = ();
2482        for my $field (@fieldList) {
2483            push @sets, _FixName($field) . " = ?";
2484            push @valueList, $fields->{$field};
2485        }
2486        my $command = "UPDATE $entityName SET " . join(", ", @sets) . " WHERE id = ?";
2487        # Add the ID to the list of binding values.
2488        push @valueList, $id;
2489        # Call SQL to do the work.
2490        my $rows = $self->{_dbh}->SQL($command, 0, @valueList);
2491        # Check for errors.
2492        if ($rows == 0) {
2493            Confess("Entity $id of type $entityName not found.");
2494        }
2495    }
2496    
2497    =head3 LoadTable
2498    
2499    C<< my $results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>
2500    
2501    Load data from a tab-delimited file into a specified table, optionally re-creating the table
2502    first.
2503    
2504    =over 4
2505    
2506    =item fileName
2507    
2508    Name of the file from which the table data should be loaded.
2509    
2510    =item relationName
2511    
2512    Name of the relation to be loaded. This is the same as the table name.
2513    
2514    =item truncateFlag
2515    
2516    TRUE if the table should be dropped and re-created, else FALSE
2517    
2518    =item RETURN
2519    
2520    Returns a statistical object containing a list of the error messages.
2521    
2522    =back
2523    
2524    =cut
2525    sub LoadTable {
2526        # Get the parameters.
2527        my ($self, $fileName, $relationName, $truncateFlag) = @_;
2528        # Create the statistical return object.
2529        my $retVal = _GetLoadStats();
2530        # Trace the fact of the load.
2531        Trace("Loading table $relationName from $fileName") if T(2);
2532        # Get the database handle.
2533        my $dbh = $self->{_dbh};
2534        # Get the input file size.
2535        my $fileSize = -s $fileName;
2536        # Get the relation data.
2537        my $relation = $self->_FindRelation($relationName);
2538        # Check the truncation flag.
2539        if ($truncateFlag) {
2540            Trace("Creating table $relationName") if T(2);
2541            # Compute the row count estimate. We take the size of the load file,
2542            # divide it by the estimated row size, and then multiply by 1.5 to
2543            # leave extra room. We postulate a minimum row count of 1000 to
2544            # prevent problems with incoming empty load files.
2545            my $rowSize = $self->EstimateRowSize($relationName);
2546            my $estimate = FIG::max($fileSize * 1.5 / $rowSize, 1000);
2547            # Re-create the table without its index.
2548            $self->CreateTable($relationName, 0, $estimate);
2549            # If this is a pre-index DBMS, create the index here.
2550            if ($dbh->{_preIndex}) {
2551                eval {
2552                    $self->CreateIndex($relationName);
2553                };
2554                if ($@) {
2555                    $retVal->AddMessage($@);
2556                }
2557            }
2558        }
2559        # Load the table.
2560        my $rv;
2561        eval {
2562            $rv = $dbh->load_table(file => $fileName, tbl => $relationName);
2563        };
2564        if (!defined $rv) {
2565            $retVal->AddMessage($@) if ($@);
2566            $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2567            Trace("Table load failed for $relationName.") if T(1);
2568        } else {
2569            # Here we successfully loaded the table.
2570            $retVal->Add("tables");
2571            my $size = -s $fileName;
2572            Trace("$size bytes loaded into $relationName.") if T(2);
2573            # If we're rebuilding, we need to create the table indexes.
2574            if ($truncateFlag) {
2575                # Indexes are created here for PostGres. For PostGres, indexes are
2576                # best built at the end. For MySQL, the reverse is true.
2577                if (! $dbh->{_preIndex}) {
2578                    eval {
2579                        $self->CreateIndex($relationName);
2580                    };
2581                    if ($@) {
2582                        $retVal->AddMessage($@);
2583                    }
2584                }
2585                # The full-text index (if any) is always built last, even for MySQL.
2586                # First we need to see if this table has a full-text index. Only
2587                # primary relations are allowed that privilege.
2588                Trace("Checking for full-text index on $relationName.") if T(2);
2589                if ($self->_IsPrimary($relationName)) {
2590                    $self->CreateSearchIndex($relationName);
2591                }
2592            }
2593        }
2594        # Analyze the table to improve performance.
2595        Trace("Analyzing and compacting $relationName.") if T(3);
2596        $dbh->vacuum_it($relationName);
2597        Trace("$relationName load completed.") if T(3);
2598        # Return the statistics.
2599        return $retVal;
2600    }
2601    
2602    =head3 CreateSearchIndex
2603    
2604    C<< $erdb->CreateSearchIndex($objectName); >>
2605    
2606    Check for a full-text search index on the specified entity or relationship object, and
2607    if one is required, rebuild it.
2608    
2609    =over 4
2610    
2611    =item objectName
2612    
2613    Name of the entity or relationship to be indexed.
2614    
2615    =back
2616    
2617    =cut
2618    
2619    sub CreateSearchIndex {
2620        # Get the parameters.
2621        my ($self, $objectName) = @_;
2622        # Get the relation's entity/relationship structure.
2623        my $structure = $self->_GetStructure($objectName);
2624        # Get the database handle.
2625        my $dbh = $self->{_dbh};
2626        Trace("Checking for search fields in $objectName.") if T(3);
2627        # Check for a searchable fields list.
2628        if (exists $structure->{searchFields}) {
2629            # Here we know that we need to create a full-text search index.
2630            # Get an SQL-formatted field name list.
2631            my $fields = join(", ", _FixNames(@{$structure->{searchFields}}));
2632            # Create the index. If it already exists, it will be dropped.
2633            $dbh->create_index(tbl => $objectName, idx => "search_idx",
2634                               flds => $fields, kind => 'fulltext');
2635            Trace("Index created for $fields in $objectName.") if T(2);
2636        }
2637    }
2638    
2639    =head3 DropRelation
2640    
2641    C<< $erdb->DropRelation($relationName); >>
2642    
2643    Physically drop a relation from the database.
2644    
2645    =over 4
2646    
2647    =item relationName
2648    
2649    Name of the relation to drop. If it does not exist, this method will have
2650    no effect.
2651    
2652    =back
2653    
2654    =cut
2655    
2656    sub DropRelation {
2657        # Get the parameters.
2658        my ($self, $relationName) = @_;
2659        # Get the database handle.
2660        my $dbh = $self->{_dbh};
2661        # Drop the relation. The method used here has no effect if the relation
2662        # does not exist.
2663        Trace("Invoking DB Kernel to drop $relationName.") if T(3);
2664        $dbh->drop_table(tbl => $relationName);
2665    }
2666    
2667    =head3 MatchSqlPattern
2668    
2669    C<< my $matched = ERDB::MatchSqlPattern($value, $pattern); >>
2670    
2671    Determine whether or not a specified value matches an SQL pattern. An SQL
2672    pattern has two wild card characters: C<%> that matches multiple characters,
2673    and C<_> that matches a single character. These can be escaped using a
2674    backslash (C<\>). We pull this off by converting the SQL pattern to a
2675    PERL regular expression. As per SQL rules, the match is case-insensitive.
2676    
2677    =over 4
2678    
2679    =item value
2680    
2681    Value to be matched against the pattern. Note that an undefined or empty
2682    value will not match anything.
2683    
2684    =item pattern
2685    
2686    SQL pattern against which to match the value. An undefined or empty pattern will
2687    match everything.
2688    
2689    =item RETURN
2690    
2691    Returns TRUE if the value and pattern match, else FALSE.
2692    
2693    =back
2694    
2695    =cut
2696    
2697    sub MatchSqlPattern {
2698        # Get the parameters.
2699        my ($value, $pattern) = @_;
2700        # Declare the return variable.
2701        my $retVal;
2702        # Insure we have a pattern.
2703        if (! defined($pattern) || $pattern eq "") {
2704            $retVal = 1;
2705        } else {
2706            # Break the pattern into pieces around the wildcard characters. Because we
2707            # use parentheses in the split function's delimiter expression, we'll get
2708            # list elements for the delimiters as well as the rest of the string.
2709            my @pieces = split /([_%]|\\[_%])/, $pattern;
2710            # Check some fast special cases.
2711            if ($pattern eq '%') {
2712                # A null pattern matches everything.
2713                $retVal = 1;
2714            } elsif (@pieces == 1) {
2715                # No wildcards, so we have a literal comparison. Note we're case-insensitive.
2716                $retVal = (lc($value) eq lc($pattern));
2717            } elsif (@pieces == 2 && $pieces[1] eq '%') {
2718                # A wildcard at the end, so we have a substring match. This is also case-insensitive.
2719                $retVal = (lc(substr($value, 0, length($pieces[0]))) eq lc($pieces[0]));
2720            } else {
2721                # Okay, we have to do it the hard way. Convert each piece to a PERL pattern.
2722                my $realPattern = "";
2723                for my $piece (@pieces) {
2724                    # Determine the type of piece.
2725                    if ($piece eq "") {
2726                        # Empty pieces are ignored.
2727                    } elsif ($piece eq "%") {
2728                        # Here we have a multi-character wildcard. Note that it can match
2729                        # zero or more characters.
2730                        $realPattern .= ".*"
2731                    } elsif ($piece eq "_") {
2732                        # Here we have a single-character wildcard.
2733                        $realPattern .= ".";
2734                    } elsif ($piece eq "\\%" || $piece eq "\\_") {
2735                        # This is an escape sequence (which is a rare thing, actually).
2736                        $realPattern .= substr($piece, 1, 1);
2737                    } else {
2738                        # Here we have raw text.
2739                        $realPattern .= quotemeta($piece);
2740                    }
2741                }
2742                # Do the match.
2743                $retVal = ($value =~ /^$realPattern$/i ? 1 : 0);
2744            }
2745        }
2746        # Return the result.
2747        return $retVal;
2748    }
2749    
2750    =head3 GetEntity
2751    
2752    C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>
2753    
2754    Return an object describing the entity instance with a specified ID.
2755    
2756    =over 4
2757    
2758    =item entityType
2759    
2760    Entity type name.
2761    
2762    =item ID
2763    
2764    ID of the desired entity.
2765    
2766    =item RETURN
2767    
2768    Returns a B<DBObject> representing the desired entity instance, or an undefined value if no
2769    instance is found with the specified key.
2770    
2771    =back
2772    
2773    =cut
2774    
2775    sub GetEntity {
2776        # Get the parameters.
2777        my ($self, $entityType, $ID) = @_;
2778        # Create a query.
2779        my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);
2780        # Get the first (and only) object.
2781        my $retVal = $query->Fetch();
2782        # Return the result.
2783        return $retVal;
2784    }
2785    
2786    =head3 GetChoices
2787    
2788    C<< my @values = $erdb->GetChoices($entityName, $fieldName); >>
2789    
2790    Return a list of all the values for the specified field that are represented in the
2791    specified entity.
2792    
2793    Note that if the field is not indexed, then this will be a very slow operation.
2794    
2795    =over 4
2796    
2797    =item entityName
2798    
2799    Name of an entity in the database.
2800    
2801    =item fieldName
2802    
2803    Name of a field belonging to the entity. This is a raw field name without
2804    the standard parenthesized notation used in most calls.
2805    
2806    =item RETURN
2807    
2808    Returns a list of the distinct values for the specified field in the database.
2809    
2810    =back
2811    
2812    =cut
2813    
2814    sub GetChoices {
2815        # Get the parameters.
2816        my ($self, $entityName, $fieldName) = @_;
2817        # Declare the return variable.
2818        my @retVal;
2819        # Get the entity data structure.
2820        my $entityData = $self->_GetStructure($entityName);
2821        # Get the field.
2822        my $fieldHash = $entityData->{Fields};
2823        if (! exists $fieldHash->{$fieldName}) {
2824            Confess("$fieldName not found in $entityName.");
2825        } else {
2826            # Get the name of the relation containing the field.
2827            my $relation = $fieldHash->{$fieldName}->{relation};
2828            # Fix up the field name.
2829            my $realName = _FixName($fieldName);
2830            # Get the database handle.
2831            my $dbh = $self->{_dbh};
2832            # Query the database.
2833            my $results = $dbh->SQL("SELECT DISTINCT $realName FROM $relation");
2834            # Clean the results. They are stored as a list of lists, and we just want the one list.
2835            @retVal = sort map { $_->[0] } @{$results};
2836        }
2837        # Return the result.
2838        return @retVal;
2839    }
2840    
2841    =head3 GetEntityValues
2842    
2843    C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>
2844    
2845    Return a list of values from a specified entity instance. If the entity instance
2846    does not exist, an empty list is returned.
2847    
2848    =over 4
2849    
2850    =item entityType
2851    
2852    Entity type name.
2853    
2854    =item ID
2855    
2856    ID of the desired entity.
2857    
2858    =item fields
2859    
2860    List of field names, each of the form I<objectName>C<(>I<fieldName>C<)>.
2861    
2862    =item RETURN
2863    
2864    Returns a flattened list of the values of the specified fields for the specified entity.
2865    
2866    =back
2867    
2868    =cut
2869    
2870    sub GetEntityValues {
2871        # Get the parameters.
2872        my ($self, $entityType, $ID, $fields) = @_;
2873        # Get the specified entity.
2874        my $entity = $self->GetEntity($entityType, $ID);
2875        # Declare the return list.
2876        my @retVal = ();
2877        # If we found the entity, push the values into the return list.
2878        if ($entity) {
2879            push @retVal, $entity->Values($fields);
2880        }
2881        # Return the result.
2882        return @retVal;
2883    }
2884    
2885    =head3 GetAll
2886    
2887    C<< my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>
2888    
2889    Return a list of values taken from the objects returned by a query. The first three
2890    parameters correspond to the parameters of the L</Get> method. The final parameter is
2891    a list of the fields desired from each record found by the query. The field name
2892    syntax is the standard syntax used for fields in the B<ERDB> system--
2893    B<I<objectName>(I<fieldName>)>-- where I<objectName> is the name of the relevant entity
2894    or relationship and I<fieldName> is the name of the field.
2895    
2896    The list returned will be a list of lists. Each element of the list will contain
2897    the values returned for the fields specified in the fourth parameter. If one of the
2898    fields specified returns multiple values, they are flattened in with the rest. For
2899    example, the following call will return a list of the features in a particular
2900    spreadsheet cell, and each feature will be represented by a list containing the
2901    feature ID followed by all of its aliases.
2902    
2903    C<< @query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>
2904    
2905    =over 4
2906    
2907    =item objectNames
2908    
2909    List containing the names of the entity and relationship objects to be retrieved.
2910    
2911    =item filterClause
2912    
2913    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
2914  be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form  be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
2915  B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the  B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
2916  parameter list as additional parameters. The fields in a filter clause can come from primary  parameter list as additional parameters. The fields in a filter clause can come from primary
2917  entity relations, relationship relations, or secondary entity relations; however, all of the  entity relations, relationship relations, or secondary entity relations; however, all of the
2918  entities and relationships involved must be included in the list of object names.  entities and relationships involved must be included in the list of object names.
2919    
2920  =item parameterList  =item parameterList
2921    
2922    List of the parameters to be substituted in for the parameters marks in the filter clause.
2923    
2924    =item fields
2925    
2926    List of the fields to be returned in each element of the list returned.
2927    
2928    =item count
2929    
2930    Maximum number of records to return. If omitted or 0, all available records will be returned.
2931    
2932    =item RETURN
2933    
2934    Returns a list of list references. Each element of the return list contains the values for the
2935    fields specified in the B<fields> parameter.
2936    
2937    =back
2938    
2939    =cut
2940    #: Return Type @@;
2941    sub GetAll {
2942        # Get the parameters.
2943        my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
2944        # Translate the parameters from a list reference to a list. If the parameter
2945        # list is a scalar we convert it into a singleton list.
2946        my @parmList = ();
2947        if (ref $parameterList eq "ARRAY") {
2948            Trace("GetAll parm list is an array.") if T(4);
2949            @parmList = @{$parameterList};
2950        } else {
2951            Trace("GetAll parm list is a scalar: $parameterList.") if T(4);
2952            push @parmList, $parameterList;
2953        }
2954        # Insure the counter has a value.
2955        if (!defined $count) {
2956            $count = 0;
2957        }
2958        # Add the row limit to the filter clause.
2959        if ($count > 0) {
2960            $filterClause .= " LIMIT $count";
2961        }
2962        # Create the query.
2963        my $query = $self->Get($objectNames, $filterClause, \@parmList);
2964        # Set up a counter of the number of records read.
2965        my $fetched = 0;
2966        # Loop through the records returned, extracting the fields. Note that if the
2967        # counter is non-zero, we stop when the number of records read hits the count.
2968        my @retVal = ();
2969        while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {
2970            my @rowData = $row->Values($fields);
2971            push @retVal, \@rowData;
2972            $fetched++;
2973        }
2974        Trace("$fetched rows returned in GetAll.") if T(SQL => 4);
2975        # Return the resulting list.
2976        return @retVal;
2977    }
2978    
2979    =head3 Exists
2980    
2981    C<< my $found = $sprout->Exists($entityName, $entityID); >>
2982    
2983    Return TRUE if an entity exists, else FALSE.
2984    
2985    =over 4
2986    
2987    =item entityName
2988    
2989    Name of the entity type (e.g. C<Feature>) relevant to the existence check.
2990    
2991    =item entityID
2992    
2993    ID of the entity instance whose existence is to be checked.
2994    
2995    =item RETURN
2996    
2997    Returns TRUE if the entity instance exists, else FALSE.
2998    
2999    =back
3000    
3001    =cut
3002    #: Return Type $;
3003    sub Exists {
3004        # Get the parameters.
3005        my ($self, $entityName, $entityID) = @_;
3006        # Check for the entity instance.
3007        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
3008        my $testInstance = $self->GetEntity($entityName, $entityID);
3009        # Return an existence indicator.
3010        my $retVal = ($testInstance ? 1 : 0);
3011        return $retVal;
3012    }
3013    
3014    =head3 EstimateRowSize
3015    
3016    C<< my $rowSize = $erdb->EstimateRowSize($relName); >>
3017    
3018    Estimate the row size of the specified relation. The estimated row size is computed by adding
3019    up the average length for each data type.
3020    
3021    =over 4
3022    
3023    =item relName
3024    
3025    Name of the relation whose estimated row size is desired.
3026    
3027    =item RETURN
3028    
3029    Returns an estimate of the row size for the specified relation.
3030    
3031    =back
3032    
3033    =cut
3034    #: Return Type $;
3035    sub EstimateRowSize {
3036        # Get the parameters.
3037        my ($self, $relName) = @_;
3038        # Declare the return variable.
3039        my $retVal = 0;
3040        # Find the relation descriptor.
3041        my $relation = $self->_FindRelation($relName);
3042        # Get the list of fields.
3043        for my $fieldData (@{$relation->{Fields}}) {
3044            # Get the field type and add its length.
3045            my $fieldLen = $TypeTable{$fieldData->{type}}->{avgLen};
3046            $retVal += $fieldLen;
3047        }
3048        # Return the result.
3049        return $retVal;
3050    }
3051    
3052    =head3 GetFieldTable
3053    
3054    C<< my $fieldHash = $self->GetFieldTable($objectnName); >>
3055    
3056    Get the field structure for a specified entity or relationship.
3057    
3058    =over 4
3059    
3060    =item objectName
3061    
3062    Name of the desired entity or relationship.
3063    
3064    =item RETURN
3065    
3066    The table containing the field descriptors for the specified object.
3067    
3068    =back
3069    
3070    =cut
3071    
3072    sub GetFieldTable {
3073        # Get the parameters.
3074        my ($self, $objectName) = @_;
3075        # Get the descriptor from the metadata.
3076        my $objectData = $self->_GetStructure($objectName);
3077        # Return the object's field table.
3078        return $objectData->{Fields};
3079    }
3080    
3081    =head3 SplitKeywords
3082    
3083    C<< my @keywords = ERDB::SplitKeywords($keywordString); >>
3084    
3085    This method returns a list of the positive keywords in the specified
3086    keyword string. All of the operators will have been stripped off,
3087    and if the keyword is preceded by a minus operator (C<->), it will
3088    not be in the list returned. The idea here is to get a list of the
3089    keywords the user wants to see. The list will be processed to remove
3090    duplicates.
3091    
3092    It is possible to create a string that confuses this method. For example
3093    
3094        frog toad -frog
3095    
3096    would return both C<frog> and C<toad>. If this is a problem we can deal
3097    with it later.
3098    
3099    =over 4
3100    
3101    =item keywordString
3102    
3103    The keyword string to be parsed.
3104    
3105    =item RETURN
3106    
3107    Returns a list of the words in the keyword string the user wants to
3108    see.
3109    
3110    =back
3111    
3112    =cut
3113    
3114    sub SplitKeywords {
3115        # Get the parameters.
3116        my ($keywordString) = @_;
3117        # Make a safety copy of the string. (This helps during debugging.)
3118        my $workString = $keywordString;
3119        # Convert operators we don't care about to spaces.
3120        $workString =~ tr/+"()<>/ /;
3121        # Split the rest of the string along space boundaries. Note that we
3122        # eliminate any words that are zero length or begin with a minus sign.
3123        my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
3124        # Use a hash to remove duplicates.
3125        my %words = map { $_ => 1 } @wordList;
3126        # Return the result.
3127        return sort keys %words;
3128    }
3129    
3130    =head3 ValidateFieldName
3131    
3132    C<< my $okFlag = ERDB::ValidateFieldName($fieldName); >>
3133    
3134    Return TRUE if the specified field name is valid, else FALSE. Valid field names must
3135    be hyphenated words subject to certain restrictions.
3136    
3137    =over 4
3138    
3139    =item fieldName
3140    
3141    Field name to be validated.
3142    
3143    =item RETURN
3144    
3145    Returns TRUE if the field name is valid, else FALSE.
3146    
3147    =back
3148    
3149    =cut
3150    
3151    sub ValidateFieldName {
3152        # Get the parameters.
3153        my ($fieldName) = @_;
3154        # Declare the return variable. The field name is valid until we hear
3155        # differently.
3156        my $retVal = 1;
3157        # Compute the maximum name length.
3158        my $maxLen = $TypeTable{'name-string'}->{maxLen};
3159        # Look for bad stuff in the name.
3160        if ($fieldName =~ /--/) {
3161            # Here we have a doubled minus sign.
3162            Trace("Field name $fieldName has a doubled hyphen.") if T(1);
3163            $retVal = 0;
3164        } elsif ($fieldName !~ /^[A-Za-z]/) {
3165            # Here the field name is missing the initial letter.
3166            Trace("Field name $fieldName does not begin with a letter.") if T(1);
3167            $retVal = 0;
3168        } elsif (length($fieldName) > $maxLen) {
3169            # Here the field name is too long.
3170            Trace("Maximum field name length is $maxLen. Field name must be truncated to " . substr($fieldName,0, $maxLen) . ".");
3171        } else {
3172            # Strip out the minus signs. Everything remaining must be a letter,
3173            # underscore, or digit.
3174            my $strippedName = $fieldName;
3175            $strippedName =~ s/-//g;
3176            if ($strippedName !~ /^(\w|\d)+$/) {
3177                Trace("Field name $fieldName contains illegal characters.") if T(1);
3178                $retVal = 0;
3179            }
3180        }
3181        # Return the result.
3182        return $retVal;
3183    }
3184    
3185    =head3 ReadMetaXML
3186    
3187    C<< my $rawMetaData = ERDB::ReadDBD($fileName); >>
3188    
3189    This method reads a raw database definition XML file and returns it.
3190    Normally, the metadata used by the ERDB system has been processed and
3191    modified to make it easier to load and retrieve the data; however,
3192    this method can be used to get the data in its raw form.
3193    
3194    =over 4
3195    
3196    =item fileName
3197    
3198    Name of the XML file to read.
3199    
3200    =item RETURN
3201    
3202    Returns a hash reference containing the raw XML data from the specified file.
3203    
3204    =back
3205    
3206    =cut
3207    
3208    sub ReadMetaXML {
3209        # Get the parameters.
3210        my ($fileName) = @_;
3211        # Read the XML.
3212        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
3213        Trace("XML metadata loaded from file $fileName.") if T(1);
3214        # Return the result.
3215        return $retVal;
3216    }
3217    
3218    =head3 GetEntityFieldHash
3219    
3220    C<< my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName); >>
3221    
3222    Get the field hash of the named entity in the specified raw XML structure.
3223    The field hash may not exist, in which case we need to create it.
3224    
3225    =over 4
3226    
3227    =item structure
3228    
3229    Raw XML structure defininng the database. This is not the run-time XML used by
3230    an ERDB object, since that has all sorts of optimizations built-in.
3231    
3232    =item entityName
3233    
3234    Name of the entity whose field structure is desired.
3235    
3236    =item RETURN
3237    
3238    Returns the field hash used to define the entity's fields.
3239    
3240    =back
3241    
3242    =cut
3243    
3244    sub GetEntityFieldHash {
3245        # Get the parameters.
3246        my ($structure, $entityName) = @_;
3247        # Get the entity structure.
3248        my $entityData = $structure->{Entities}->{$entityName};
3249        # Look for a field structure.
3250        my $retVal = $entityData->{Fields};
3251        # If it doesn't exist, create it.
3252        if (! defined($retVal)) {
3253            $entityData->{Fields} = {};
3254            $retVal = $entityData->{Fields};
3255        }
3256        # Return the result.
3257        return $retVal;
3258    }
3259    
3260    =head3 WriteMetaXML
3261    
3262    C<< ERDB::WriteMetaXML($structure, $fileName); >>
3263    
3264    Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
3265    used to update the database definition. It must be used with care, however, since it
3266    will only work on a raw structure, not on the processed structure created by an ERDB
3267    constructor.
3268    
3269    =over 4
3270    
3271    =item structure
3272    
3273    XML structure to be written to the file.
3274    
3275    =item fileName
3276    
3277    Name of the output file to which the updated XML should be stored.
3278    
3279    =back
3280    
3281    =cut
3282    
3283    sub WriteMetaXML {
3284        # Get the parameters.
3285        my ($structure, $fileName) = @_;
3286        # Compute the output.
3287        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
3288        # Write it to the file.
3289        my $xmlOut = Open(undef, ">$fileName");
3290        print $xmlOut $fileString;
3291    }
3292    
3293    
3294    =head3 HTMLNote
3295    
3296    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
3297    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
3298    Except for C<[p]>, all the codes are closed by slash-codes. So, for
3299    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
3300    
3301    C<< my $realHtml = ERDB::HTMLNote($dataString); >>
3302    
3303    =over 4
3304    
3305    =item dataString
3306    
3307    String to convert to HTML.
3308    
3309    =item RETURN
3310    
3311  List of the parameters to be substituted in for the parameters marks in the filter clause.  An HTML string derived from the input string.
3312    
3313  =item fields  =back
3314    
3315  List of the fields to be returned in each element of the list returned.  =cut
3316    
3317  =item count  sub HTMLNote {
3318        # Get the parameter.
3319        my ($dataString) = @_;
3320        # HTML-escape the text.
3321        my $retVal = CGI::escapeHTML($dataString);
3322        # Substitute the bulletin board codes.
3323        $retVal =~ s!\[(/?[bi])\]!<$1>!g;
3324        $retVal =~ s!\[p\]!</p><p>!g;
3325        # Return the result.
3326        return $retVal;
3327    }
3328    
3329  Maximum number of records to return. If omitted or 0, all available records will be returned.  
3330    =head2 Data Mining Methods
3331    
3332    =head3 GetUsefulCrossValues
3333    
3334    C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>
3335    
3336    Return a list of the useful attributes that would be returned by a B<Cross> call
3337    from an entity of the source entity type through the specified relationship. This
3338    means it will return the fields of the target entity type and the intersection data
3339    fields in the relationship. Only primary table fields are returned. In other words,
3340    the field names returned will be for fields where there is always one and only one
3341    value.
3342    
3343    =over 4
3344    
3345    =item sourceEntity
3346    
3347    Name of the entity from which the relationship crossing will start.
3348    
3349    =item relationship
3350    
3351    Name of the relationship being crossed.
3352    
3353  =item RETURN  =item RETURN
3354    
3355  Returns a list of list references. Each element of the return list contains the values for the  Returns a list of field names in Sprout field format (I<objectName>C<(>I<fieldName>C<)>.
 fields specified in the B<fields> parameter.  
3356    
3357  =back  =back
3358    
3359  =cut  =cut
3360  #: Return Type @@;  #: Return Type @;
3361  sub GetAll {  sub GetUsefulCrossValues {
3362      # Get the parameters.      # Get the parameters.
3363      my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;      my ($self, $sourceEntity, $relationship) = @_;
3364      # Translate the parameters from a list reference to a list. If the parameter      # Declare the return variable.
     # list is a scalar we convert it into a singleton list.  
     my @parmList = ();  
     if (ref $parameterList eq "ARRAY") {  
         @parmList = @{$parameterList};  
     } else {  
         push @parmList, $parameterList;  
     }  
     # Create the query.  
     my $query = $self->Get($objectNames, $filterClause, @parmList);  
     # Set up a counter of the number of records read.  
     my $fetched = 0;  
     # Insure the counter has a value.  
     if (!defined $count) {  
         $count = 0;  
     }  
     # Loop through the records returned, extracting the fields. Note that if the  
     # counter is non-zero, we stop when the number of records read hits the count.  
3365      my @retVal = ();      my @retVal = ();
3366      while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {      # Determine the target entity for the relationship. This is whichever entity is not
3367          my @rowData = $row->Values($fields);      # the source entity. So, if the source entity is the FROM, we'll get the name of
3368          push @retVal, \@rowData;      # the TO, and vice versa.
3369          $fetched++;      my $relStructure = $self->_GetStructure($relationship);
3370      }      my $targetEntityType = ($relStructure->{from} eq $sourceEntity ? "to" : "from");
3371      # Return the resulting list.      my $targetEntity = $relStructure->{$targetEntityType};
3372        # Get the field table for the entity.
3373        my $entityFields = $self->GetFieldTable($targetEntity);
3374        # The field table is a hash. The hash key is the field name. The hash value is a structure.
3375        # For the entity fields, the key aspect of the target structure is that the {relation} value
3376        # must match the entity name.
3377        my @fieldList = map { "$targetEntity($_)" } grep { $entityFields->{$_}->{relation} eq $targetEntity }
3378                            keys %{$entityFields};
3379        # Push the fields found onto the return variable.
3380        push @retVal, sort @fieldList;
3381        # Get the field table for the relationship.
3382        my $relationshipFields = $self->GetFieldTable($relationship);
3383        # Here we have a different rule. We want all the fields other than "from-link" and "to-link".
3384        # This may end up being an empty set.
3385        my @fieldList2 = map { "$relationship($_)" } grep { $_ ne "from-link" && $_ ne "to-link" }
3386                            keys %{$relationshipFields};
3387        # Push these onto the return list.
3388        push @retVal, sort @fieldList2;
3389        # Return the result.
3390      return @retVal;      return @retVal;
3391  }  }
3392    
3393  =head3 EstimateRowSize  =head3 FindColumn
3394    
3395  C<< my $rowSize = $erdb->EstimateRowSize($relName); >>  C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>
3396    
3397  Estimate the row size of the specified relation. The estimated row size is computed by adding  Return the location a desired column in a data mining header line. The data
3398  up the average length for each data type.  mining header line is a tab-separated list of column names. The column
3399    identifier is either the numerical index of a column or the actual column
3400    name.
3401    
3402  =over 4  =over 4
3403    
3404  =item relName  =item headerLine
3405    
3406  Name of the relation whose estimated row size is desired.  The header line from a data mining command, which consists of a tab-separated
3407    list of column names.
3408    
3409    =item columnIdentifier
3410    
3411    Either the ordinal number of the desired column (1-based), or the name of the
3412    desired column.
3413    
3414  =item RETURN  =item RETURN
3415    
3416  Returns an estimate of the row size for the specified relation.  Returns the array index (0-based) of the desired column.
3417    
3418  =back  =back
3419    
3420  =cut  =cut
3421  #: Return Type $;  
3422  sub EstimateRowSize {  sub FindColumn {
3423      # Get the parameters.      # Get the parameters.
3424      my ($self, $relName) = @_;      my ($headerLine, $columnIdentifier) = @_;
3425      # Declare the return variable.      # Declare the return variable.
3426      my $retVal = 0;      my $retVal;
3427      # Find the relation descriptor.      # Split the header line into column names.
3428      my $relation = $self->_FindRelation($relName);      my @headers = ParseColumns($headerLine);
3429      # Get the list of fields.      # Determine whether we have a number or a name.
3430      for my $fieldData (@{$relation->{Fields}}) {      if ($columnIdentifier =~ /^\d+$/) {
3431          # Get the field type and add its length.          # Here we have a number. Subtract 1 and validate the result.
3432          my $fieldLen = $TypeTable{$fieldData->{type}}->{avgLen};          $retVal = $columnIdentifier - 1;
3433          $retVal += $fieldLen;          if ($retVal < 0 || $retVal > $#headers) {
3434                Confess("Invalid column identifer \"$columnIdentifier\": value out of range.");
3435            }
3436        } else {
3437            # Here we have a name. We need to find it in the list.
3438            for (my $i = 0; $i <= $#headers && ! defined($retVal); $i++) {
3439                if ($headers[$i] eq $columnIdentifier) {
3440                    $retVal = $i;
3441                }
3442            }
3443            if (! defined($retVal)) {
3444                Confess("Invalid column identifier \"$columnIdentifier\": value not found.");
3445            }
3446      }      }
3447      # Return the result.      # Return the result.
3448      return $retVal;      return $retVal;
3449  }  }
3450    
3451  =head2 Internal Utility Methods  =head3 ParseColumns
3452    
3453  =head3 GetLoadStats  C<< my @columns = ERDB::ParseColumns($line); >>
3454    
3455  Return a blank statistics object for use by the load methods.  Convert the specified data line to a list of columns.
3456    
3457  This is a static method.  =over 4
3458    
3459    =item line
3460    
3461    A data mining input, consisting of a tab-separated list of columns terminated by a
3462    new-line.
3463    
3464    =item RETURN
3465    
3466    Returns a list consisting of the column values.
3467    
3468    =back
3469    
3470  =cut  =cut
3471    
3472  sub _GetLoadStats {  sub ParseColumns {
3473      return Stats->new('records');      # Get the parameters.
3474        my ($line) = @_;
3475        # Chop off the line-end.
3476        chomp $line;
3477        # Split it into a list.
3478        my @retVal = split(/\t/, $line);
3479        # Return the result.
3480        return @retVal;
3481  }  }
3482    
3483  =head3 GenerateFields  =head2 Virtual Methods
3484    
3485  Generate field values from a field structure and store in a specified table. The field names  =head3 CleanKeywords
 are first sorted by pass count, certain pre-defined fields are removed from the list, and  
 then we rip through them evaluation the data generation string. Fields in the primary relation  
 are stored as scalars; fields in secondary relations are stored as value lists.  
3486    
3487  This is a static method.  C<< my $cleanedString = $erdb->CleanKeywords($searchExpression); >>
3488    
3489    Clean up a search expression or keyword list. This is a virtual method that may
3490    be overridden by the subclass. The base-class method removes extra spaces
3491    and converts everything to lower case.
3492    
3493  =over 4  =over 4
3494    
3495  =item this  =item searchExpression
3496    
3497  Hash table into which the field values should be placed.  Search expression or keyword list to clean. Note that a search expression may
3498    contain boolean operators which need to be preserved. This includes leading
3499    minus signs.
3500    
3501  =item fields  =item RETURN
3502    
3503  Field structure from which the field descriptors should be taken.  Cleaned expression or keyword list.
3504    
3505  =item type  =back
3506    
3507    =cut
3508    
3509    sub CleanKeywords {
3510        # Get the parameters.
3511        my ($self, $searchExpression) = @_;
3512        # Lower-case the expression and copy it into the return variable. Note that we insure we
3513        # don't accidentally end up with an undefined value.
3514        my $retVal = lc($searchExpression || "");
3515        # Remove extra spaces.
3516        $retVal =~ s/\s+/ /g;
3517        $retVal =~ s/(^\s+)|(\s+$)//g;
3518        # Return the result.
3519        return $retVal;
3520    }
3521    
3522    =head3 GetSourceObject
3523    
3524  Type name of the object whose fields are being generated.  C<< my $source = $erdb->GetSourceObject($entityName); >>
3525    
3526  =item values (optional)  Return the object to be used in loading special attributes of the specified entity. The
3527    algorithm for loading special attributes is stored in the C<DataGen> elements of the
3528    XML
3529    
3530  Reference to a value structure from which additional values can be taken.  =head2 Internal Utility Methods
3531    
3532    =head3 _RelationMap
3533    
3534    C<< my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef); >>
3535    
3536    Create the relation map for an SQL query. The relation map is used by B<DBObject>
3537    to determine how to interpret the results of the query.
3538    
3539    =over 4
3540    
3541    =item mappedNameHashRef
3542    
3543    Reference to a hash that maps modified object names to real object names.
3544    
3545  =item from (optiona)  =item mappedNameListRef
3546    
3547  Reference to the source entity instance if relationship data is being generated.  Reference to a list of modified object names in the order they appear in the
3548    SELECT list.
3549    
3550  =item to (optional)  =item RETURN
3551    
3552  Reference to the target entity instance if relationship data is being generated.  Returns a list of 2-tuples. Each tuple consists of an object name as used in the
3553    query followed by the actual name of that object. This enables the B<DBObject> to
3554    determine the order of the tables in the query and which object name belongs to each
3555    mapped object name. Most of the time these two values are the same; however, if a
3556    relation occurs twice in the query, the relation name in the field list and WHERE
3557    clause will use a mapped name (generally the actual relation name with a numeric
3558    suffix) that does not match the actual relation name.
3559    
3560  =back  =back
3561    
3562  =cut  =cut
3563    
3564  sub _GenerateFields {  sub _RelationMap {
3565      # Get the parameters.      # Get the parameters.
3566      my ($this, $fields, $type, $values, $from, $to) = @_;      my ($mappedNameHashRef, $mappedNameListRef) = @_;
3567      # Sort the field names by pass number.      # Declare the return variable.
3568      my @fieldNames = sort { $fields->{$a}->{DataGen}->{pass} <=> $fields->{$b}->{DataGen}->{pass} } keys %{$fields};      my @retVal = ();
3569      # Loop through the field names, generating data.      # Build the map.
3570      for my $name (@fieldNames) {      for my $mappedName (@{$mappedNameListRef}) {
3571          # Only proceed if this field needs to be generated.          push @retVal, [$mappedName, $mappedNameHashRef->{$mappedName}];
3572          if (!exists $this->{$name}) {      }
3573              # Get this field's data generation descriptor.      # Return it.
3574              my $fieldDescriptor = $fields->{$name};      return @retVal;
3575              my $data = $fieldDescriptor->{DataGen};  }
3576              # Get the code to generate the field value.  
3577              my $codeString = $data->{content};  
3578              # Determine whether or not this field is in the primary relation.  =head3 _SetupSQL
3579              if ($fieldDescriptor->{relation} eq $type) {  
3580                  # Here we have a primary relation field. Store the field value as  Process a list of object names and a filter clause so that they can be used to
3581                  # a scalar.  build an SQL statement. This method takes in a reference to a list of object names
3582                  $this->{$name} = eval($codeString);  and a filter clause. It will return a corrected filter clause, a list of mapped
3583    names and the mapped name hash.
3584    
3585    This is an instance method.
3586    
3587    =over 4
3588    
3589    =item objectNames
3590    
3591    Reference to a list of the object names to be included in the query.
3592    
3593    =item filterClause
3594    
3595    A string containing the WHERE clause for the query (without the C<WHERE>) and also
3596    optionally the C<ORDER BY> and C<LIMIT> clauses.
3597    
3598    =item matchClause
3599    
3600    An optional full-text search clause. If specified, it will be inserted at the
3601    front of the WHERE clause. It should already be SQL-formatted; that is, the
3602    field names should be in the form I<table>C<.>I<fieldName>.
3603    
3604    =item RETURN
3605    
3606    Returns a three-element list. The first element is the SQL statement suffix, beginning
3607    with the FROM clause. The second element is a reference to a list of the names to be
3608    used in retrieving the fields. The third element is a hash mapping the names to the
3609    objects they represent.
3610    
3611    =back
3612    
3613    =cut
3614    
3615    sub _SetupSQL {
3616        my ($self, $objectNames, $filterClause, $matchClause) = @_;
3617        # Adjust the list of object names to account for multiple occurrences of the
3618        # same object. We start with a hash table keyed on object name that will
3619        # return the object suffix. The first time an object is encountered it will
3620        # not be found in the hash. The next time the hash will map the object name
3621        # to 2, then 3, and so forth.
3622        my %objectHash = ();
3623        # This list will contain the object names as they are to appear in the
3624        # FROM list.
3625        my @fromList = ();
3626        # This list contains the suffixed object name for each object. It is exactly
3627        # parallel to the list in the $objectNames parameter.
3628        my @mappedNameList = ();
3629        # Finally, this hash translates from a mapped name to its original object name.
3630        my %mappedNameHash = ();
3631        # Now we create the lists. Note that for every single name we push something into
3632        # @fromList and @mappedNameList. This insures that those two arrays are exactly
3633        # parallel to $objectNames.
3634        for my $objectName (@{$objectNames}) {
3635            # Get the next suffix for this object.
3636            my $suffix = $objectHash{$objectName};
3637            if (! $suffix) {
3638                # Here we are seeing the object for the first time. The object name
3639                # is used as is.
3640                push @mappedNameList, $objectName;
3641                push @fromList, $objectName;
3642                $mappedNameHash{$objectName} = $objectName;
3643                # Denote the next suffix will be 2.
3644                $objectHash{$objectName} = 2;
3645            } else {
3646                # Here we've seen the object before. We construct a new name using
3647                # the suffix from the hash and update the hash.
3648                my $mappedName = "$objectName$suffix";
3649                $objectHash{$objectName} = $suffix + 1;
3650                # The FROM list has the object name followed by the mapped name. This
3651                # tells SQL it's still the same table, but we're using a different name
3652                # for it to avoid confusion.
3653                push @fromList, "$objectName $mappedName";
3654                # The mapped-name list contains the real mapped name.
3655                push @mappedNameList, $mappedName;
3656                # Finally, enable us to get back from the mapped name to the object name.
3657                $mappedNameHash{$mappedName} = $objectName;
3658            }
3659        }
3660        # Begin the SELECT suffix. It starts with
3661        #
3662        # FROM name1, name2, ... nameN
3663        #
3664        my $suffix = "FROM " . join(', ', @fromList);
3665        # Now for the WHERE. First, we need a place for the filter string.
3666        my $filterString = "";
3667        # We will also keep a list of conditions to add to the WHERE clause in order to link
3668        # entities and relationships as well as primary relations to secondary ones.
3669        my @joinWhere = ();
3670        # Check for a filter clause.
3671        if ($filterClause) {
3672            # Here we have one, so we convert its field names and add it to the query. First,
3673            # We create a copy of the filter string we can work with.
3674            $filterString = $filterClause;
3675            # Next, we sort the object names by length. This helps protect us from finding
3676            # object names inside other object names when we're doing our search and replace.
3677            my @sortedNames = sort { length($b) - length($a) } @mappedNameList;
3678            # The final preparatory step is to create a hash table of relation names. The
3679            # table begins with the relation names already in the SELECT command. We may
3680            # need to add relations later if there is filtering on a field in a secondary
3681            # relation. The secondary relations are the ones that contain multiply-
3682            # occurring or optional fields.
3683            my %fromNames = map { $_ => 1 } @sortedNames;
3684            # We are ready to begin. We loop through the object names, replacing each
3685            # object name's field references by the corresponding SQL field reference.
3686            # Along the way, if we find a secondary relation, we will need to add it
3687            # to the FROM clause.
3688            for my $mappedName (@sortedNames) {
3689                # Get the length of the object name plus 2. This is the value we add to the
3690                # size of the field name to determine the size of the field reference as a
3691                # whole.
3692                my $nameLength = 2 + length $mappedName;
3693                # Get the real object name for this mapped name.
3694                my $objectName = $mappedNameHash{$mappedName};
3695                Trace("Processing $mappedName for object $objectName.") if T(4);
3696                # Get the object's field list.
3697                my $fieldList = $self->GetFieldTable($objectName);
3698                # Find the field references for this object.
3699                while ($filterString =~ m/$mappedName\(([^)]*)\)/g) {
3700                    # At this point, $1 contains the field name, and the current position
3701                    # is set immediately after the final parenthesis. We pull out the name of
3702                    # the field and the position and length of the field reference as a whole.
3703                    my $fieldName = $1;
3704                    my $len = $nameLength + length $fieldName;
3705                    my $pos = pos($filterString) - $len;
3706                    # Insure the field exists.
3707                    if (!exists $fieldList->{$fieldName}) {
3708                        Confess("Field $fieldName not found for object $objectName.");
3709                    } else {
3710                        Trace("Processing $fieldName at position $pos.") if T(4);
3711                        # Get the field's relation.
3712                        my $relationName = $fieldList->{$fieldName}->{relation};
3713                        # Now we have a secondary relation. We need to insure it matches the
3714                        # mapped name of the primary relation. First we peel off the suffix
3715                        # from the mapped name.
3716                        my $mappingSuffix = substr $mappedName, length($objectName);
3717                        # Put the mapping suffix onto the relation name to get the
3718                        # mapped relation name.
3719                        my $mappedRelationName = "$relationName$mappingSuffix";
3720                        # Insure the relation is in the FROM clause.
3721                        if (!exists $fromNames{$mappedRelationName}) {
3722                            # Add the relation to the FROM clause.
3723                            if ($mappedRelationName eq $relationName) {
3724                                # The name is un-mapped, so we add it without
3725                                # any frills.
3726                                $suffix .= ", $relationName";
3727                                push @joinWhere, "$objectName.id = $relationName.id";
3728                            } else {
3729                                # Here we have a mapping situation.
3730                                $suffix .= ", $relationName $mappedRelationName";
3731                                push @joinWhere, "$mappedRelationName.id = $mappedName.id";
3732                            }
3733                            # Denote we have this relation available for future fields.
3734                            $fromNames{$mappedRelationName} = 1;
3735                        }
3736                        # Form an SQL field reference from the relation name and the field name.
3737                        my $sqlReference = "$mappedRelationName." . _FixName($fieldName);
3738                        # Put it into the filter string in place of the old value.
3739                        substr($filterString, $pos, $len) = $sqlReference;
3740                        # Reposition the search.
3741                        pos $filterString = $pos + length $sqlReference;
3742                    }
3743                }
3744            }
3745        }
3746        # The next step is to join the objects together. We only need to do this if there
3747        # is more than one object in the object list. We start with the first object and
3748        # run through the objects after it. Note also that we make a safety copy of the
3749        # list before running through it, because we shift off the first object before
3750        # processing the rest.
3751        my @mappedObjectList = @mappedNameList;
3752        my $lastMappedObject = shift @mappedObjectList;
3753        # Get the join table.
3754        my $joinTable = $self->{_metaData}->{Joins};
3755        # Loop through the object list.
3756        for my $thisMappedObject (@mappedObjectList) {
3757            # Look for a join using the real object names.
3758            my $lastObject = $mappedNameHash{$lastMappedObject};
3759            my $thisObject = $mappedNameHash{$thisMappedObject};
3760            my $joinKey = "$lastObject/$thisObject";
3761            if (!exists $joinTable->{$joinKey}) {
3762                # Here there's no join, so we throw an error.
3763                Confess("No join exists to connect from $lastMappedObject to $thisMappedObject.");
3764              } else {              } else {
3765                  # Here we have a secondary relation field. Create a null list              # Get the join clause.
3766                  # and push the desired number of field values onto it.              my $unMappedJoin = $joinTable->{$joinKey};
3767                  my @fieldValues = ();              # Fix the names.
3768                  my $count = IntGen(0,$data->{testCount});              $unMappedJoin =~ s/$lastObject/$lastMappedObject/;
3769                  for (my $i = 0; $i < $count; $i++) {              $unMappedJoin =~ s/$thisObject/$thisMappedObject/;
3770                      my $newValue = eval($codeString);              push @joinWhere, $unMappedJoin;
3771                      push @fieldValues, $newValue;              # Save this object as the last object for the next iteration.
3772                $lastMappedObject = $thisMappedObject;
3773            }
3774        }
3775        # Now we need to handle the whole ORDER BY / LIMIT thing. The important part
3776        # here is we want the filter clause to be empty if there's no WHERE filter.
3777        # We'll put the ORDER BY / LIMIT clauses in the following variable.
3778        my $orderClause = "";
3779        # This is only necessary if we have a filter string in which the ORDER BY
3780        # and LIMIT clauses can live.
3781        if ($filterString) {
3782            # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy
3783            # operator so that we find the first occurrence of either verb.
3784            if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {
3785                # Here we have an ORDER BY or LIMIT verb. Split it off of the filter string.
3786                my $pos = pos $filterString;
3787                $orderClause = $2 . substr($filterString, $pos);
3788                $filterString = $1;
3789            }
3790        }
3791        # All the things that are supposed to be in the WHERE clause of the
3792        # SELECT command need to be put into @joinWhere so we can string them
3793        # together. We begin with the match clause. This is important,
3794        # because the match clause's parameter mark must precede any parameter
3795        # marks in the filter string.
3796        if ($matchClause) {
3797            push @joinWhere, $matchClause;
3798        }
3799        # Add the filter string. We put it in parentheses to avoid operator
3800        # precedence problems with the match clause or the joins.
3801        if ($filterString) {
3802            Trace("Filter string is \"$filterString\".") if T(4);
3803            push @joinWhere, "($filterString)";
3804        }
3805        # String it all together into a big filter clause.
3806        if (@joinWhere) {
3807            $suffix .= " WHERE " . join(' AND ', @joinWhere);
3808                  }                  }
3809                  # Store the value list in the main hash.      # Add the sort or limit clause (if any).
3810                  $this->{$name} = \@fieldValues;      if ($orderClause) {
3811            $suffix .= " $orderClause";
3812              }              }
3813        # Return the suffix, the mapped name list, and the mapped name hash.
3814        return ($suffix, \@mappedNameList, \%mappedNameHash);
3815          }          }
3816    
3817    =head3 _GetStatementHandle
3818    
3819    This method will prepare and execute an SQL query, returning the statement handle.
3820    The main reason for doing this here is so that everybody who does SQL queries gets
3821    the benefit of tracing.
3822    
3823    This is an instance method.
3824    
3825    =over 4
3826    
3827    =item command
3828    
3829    Command to prepare and execute.
3830    
3831    =item params
3832    
3833    Reference to a list of the values to be substituted in for the parameter marks.
3834    
3835    =item RETURN
3836    
3837    Returns a prepared and executed statement handle from which the caller can extract
3838    results.
3839    
3840    =back
3841    
3842    =cut
3843    
3844    sub _GetStatementHandle {
3845        # Get the parameters.
3846        my ($self, $command, $params) = @_;
3847        # Trace the query.
3848        Trace("SQL query: $command") if T(SQL => 3);
3849        Trace("PARMS: '" . (join "', '", @{$params}) . "'") if (T(SQL => 4) && (@{$params} > 0));
3850        # Get the database handle.
3851        my $dbh = $self->{_dbh};
3852        # Prepare the command.
3853        my $sth = $dbh->prepare_command($command);
3854        # Execute it with the parameters bound in.
3855        $sth->execute(@{$params}) || Confess("SELECT error:  " . $sth->errstr());
3856        # Return the statement handle.
3857        return $sth;
3858      }      }
3859    
3860    =head3 _GetLoadStats
3861    
3862    Return a blank statistics object for use by the load methods.
3863    
3864    This is a static method.
3865    
3866    =cut
3867    
3868    sub _GetLoadStats{
3869        return Stats->new();
3870  }  }
3871    
3872  =head3 DumpRelation  =head3 _DumpRelation
3873    
3874  Dump the specified relation's to the specified output file in tab-delimited format.  Dump the specified relation to the specified output file in tab-delimited format.
3875    
3876  This is an instance method.  This is an instance method.
3877    
# Line 1811  Line 3919 
3919      close DTXOUT;      close DTXOUT;
3920  }  }
3921    
3922  =head3 GetStructure  =head3 _GetStructure
3923    
3924  Get the data structure for a specified entity or relationship.  Get the data structure for a specified entity or relationship.
3925    
# Line 1850  Line 3958 
3958      return $retVal;      return $retVal;
3959  }  }
3960    
3961  =head3 GetRelationTable  
3962    
3963    =head3 _GetRelationTable
3964    
3965  Get the list of relations for a specified entity or relationship.  Get the list of relations for a specified entity or relationship.
3966    
# Line 1879  Line 3989 
3989      return $objectData->{Relations};      return $objectData->{Relations};
3990  }  }
3991    
3992  =head3 GetFieldTable  =head3 _ValidateFieldNames
   
 Get the field structure for a specified entity or relationship.  
   
 This is an instance method.  
   
 =over 4  
   
 =item objectName  
   
 Name of the desired entity or relationship.  
   
 =item RETURN  
   
 The table containing the field descriptors for the specified object.  
   
 =back  
   
 =cut  
   
 sub _GetFieldTable {  
     # Get the parameters.  
     my ($self, $objectName) = @_;  
     # Get the descriptor from the metadata.  
     my $objectData = $self->_GetStructure($objectName);  
     # Return the object's field table.  
     return $objectData->{Fields};  
 }  
   
 =head3 ValidateFieldNames  
3993    
3994  Determine whether or not the field names are valid. A description of the problems with the names  Determine whether or not the field names are valid. A description of the problems with the names
3995  will be written to the standard error output. If there is an error, this method will abort. This is  will be written to the standard error output. If there is an error, this method will abort. This is
# Line 1935  Line 4016 
4016          for my $object (values %{$metadata->{$section}}) {          for my $object (values %{$metadata->{$section}}) {
4017              # Loop through the object's fields.              # Loop through the object's fields.
4018              for my $fieldName (keys %{$object->{Fields}}) {              for my $fieldName (keys %{$object->{Fields}}) {
4019                  # Now we make some initial validations.                  # If this field name is invalid, set the return value to zero
4020                  if ($fieldName =~ /--/) {                  # so we know we encountered an error.
4021                      # Here we have a doubled minus sign.                  if (! ValidateFieldName($fieldName)) {
                     print STDERR "Field name $fieldName has a doubled hyphen.\n";  
                     $retVal = 0;  
                 } elsif ($fieldName !~ /^[A-Za-z]/) {  
                     # Here the field name is missing the initial letter.  
                     print STDERR "Field name $fieldName does not begin with a letter.\n";  
                     $retVal = 0;  
                 } else {  
                     # Strip out the minus signs. Everything remaining must be a letter  
                     # or digit.  
                     my $strippedName = $fieldName;  
                     $strippedName =~ s/-//g;  
                     if ($strippedName !~ /^[A-Za-z0-9]+$/) {  
                         print STDERR "Field name $fieldName contains illegal characters.\n";  
4022                          $retVal = 0;                          $retVal = 0;
4023                      }                      }
4024                  }                  }
4025              }              }
4026          }          }
     }  
4027      # If an error was found, fail.      # If an error was found, fail.
4028      if ($retVal  == 0) {      if ($retVal  == 0) {
4029          Confess("Errors found in field names.");          Confess("Errors found in field names.");
4030      }      }
4031  }  }
4032    
4033  =head3 LoadRelation  =head3 _LoadRelation
4034    
4035  Load a relation from the data in a tab-delimited disk file. The load will only take place if a disk  Load a relation from the data in a tab-delimited disk file. The load will only take place if a disk
4036  file with the same name as the relation exists in the specified directory.  file with the same name as the relation exists in the specified directory.
# Line 2023  Line 4090 
4090      return $retVal;      return $retVal;
4091  }