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

Diff of /Sprout/ERDB.pm

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

revision 1.33, Sat Jan 28 09:36:47 2006 UTC revision 1.79, Wed Nov 29 20:29:53 2006 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 =>   1, 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 513  Line 626 
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 626  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      }      }
# Line 687  Line 869 
869      return $retVal;      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 710  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          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
992                                      flds => $flds, unique => $unique);                                      flds => $flds, kind => $unique);
993          if ($rv) {          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 {          } else {
# Line 725  Line 998 
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
1167    
1168  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>
# Line 819  Line 1257 
1257      return sort keys %{$entityList};      return sort keys %{$entityList};
1258  }  }
1259    
1260    =head3 GetDataTypes
1261    
1262    C<< my %types = ERDB::GetDataTypes(); >>
1263    
1264    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  =head3 IsEntity
1280    
1281  C<< my $flag = $erdb->IsEntity($entityName); >>  C<< my $flag = $erdb->IsEntity($entityName); >>
# Line 848  Line 1305 
1305    
1306  =head3 Get  =head3 Get
1307    
1308  C<< my $query = $erdb->Get(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  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.  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
# Line 856  Line 1313 
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 873  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 913  Line 1375 
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    C<< "LIMIT 10" >>
1389    
1390    =item params
1391    
1392  Parameter values to be substituted into the filter clause.  Reference to a list of parameter values to be substituted into the filter clause.
1393    
1394  =item RETURN  =item RETURN
1395    
# Line 927  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;  
                 }  
1417              }              }
1418        # Return the statement object.
1419        my $retVal = DBQuery::_new($self, $sth, \@relationMap);
1420        return $retVal;
1421          }          }
1422          # The next step is to join the objects together. We only need to do this if there  
1423          # is more than one object in the object list. We start with the first object and  
1424          # run through the objects after it. Note also that we make a safety copy of the  
1425          # list before running through it.  =head3 Search
1426          my @objectList = @{$objectNames};  
1427          my $lastObject = shift @objectList;  C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>
1428          # Get the join table.  
1429          my $joinTable = $self->{_metaData}->{Joins};  Perform a full text search with filtering. The search will be against a specified object
1430          # Loop through the object list.  in the object name list. That object will get an extra field containing the search
1431          for my $thisObject (@objectList) {  relevance. Note that except for the search expression, the parameters of this method are
1432              # Look for a join.  the same as those for L</Get> and follow the same rules.
1433              my $joinKey = "$lastObject/$thisObject";  
1434              if (!exists $joinTable->{$joinKey}) {  =over 4
1435                  # Here there's no join, so we throw an error.  
1436                  Confess("No join exists to connect from $lastObject to $thisObject.");  =item searchExpression
1437    
1438    Boolean search expression for the text fields of the target object. The default mode for
1439    a Boolean search expression is OR, but we want the default to be AND, so we will
1440    add a C<+> operator to each word with no other operator before it.
1441    
1442    =item idx
1443    
1444    Index in the I<$objectNames> list of the table to be searched in full-text mode.
1445    
1446    =item objectNames
1447    
1448    List containing the names of the entity and relationship objects to be retrieved.
1449    
1450    =item filterClause
1451    
1452    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1453    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
1454    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
1455    in the filter clause should be added to the parameter list as additional parameters. The
1456    fields in a filter clause can come from primary entity relations, relationship relations,
1457    or secondary entity relations; however, all of the entities and relationships involved must
1458    be included in the list of object names.
1459    
1460    =item params
1461    
1462    Reference to a list of parameter values to be substituted into the filter clause.
1463    
1464    =item RETURN
1465    
1466    Returns a query object for the specified search.
1467    
1468    =back
1469    
1470    =cut
1471    
1472    sub Search {
1473        # Get the parameters.
1474        my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1475        # Declare the return variable.
1476        my $retVal;
1477        # Create a safety copy of the parameter list. Note we have to be careful to insure
1478        # a parameter list exists before we copy it.
1479        my @myParams = ();
1480        if (defined $params) {
1481            @myParams = @{$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 {              } else {
1490                  # Get the join clause and add it to the WHERE list.          # Get the field list.
1491                  push @joinWhere, $joinTable->{$joinKey};          my @fields = @{$object1Structure->{searchFields}};
1492                  # Save this object as the last object for the next iteration.          # Clean the search expression.
1493                  $lastObject = $thisObject;          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          # Now we need to handle the whole ORDER BY / LIMIT thing. The important part      return $retVal;
         # here is we want the filter clause to be empty if there's no WHERE filter.  
         # We'll put the ORDER BY / LIMIT clauses in the following variable.  
         my $orderClause = "";  
         # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy  
         # operator so that we find the first occurrence of either verb.  
         if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {  
             # Here we have an ORDER BY or LIMIT verb. Split it off of the filter string.  
             my $pos = pos $filterString;  
             $orderClause = $2 . substr($filterString, $pos);  
             $filterString = $1;  
1520          }          }
1521          # Add the filter and the join clauses (if any) to the SELECT command.  
1522          if ($filterString) {  =head3 GetFlat
1523              push @joinWhere, "($filterString)";  
1524    C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>
1525    
1526    This is a variation of L</GetAll> that asks for only a single field per record and
1527    returns a single flattened list.
1528    
1529    =over 4
1530    
1531    =item objectNames
1532    
1533    List containing the names of the entity and relationship objects to be retrieved.
1534    
1535    =item filterClause
1536    
1537    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1538    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
1539    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
1540    parameter list as additional parameters. The fields in a filter clause can come from primary
1541    entity relations, relationship relations, or secondary entity relations; however, all of the
1542    entities and relationships involved must be included in the list of object names.
1543    
1544    =item parameterList
1545    
1546    List of the parameters to be substituted in for the parameters marks in the filter clause.
1547    
1548    =item field
1549    
1550    Name of the field to be used to get the elements of the list returned.
1551    
1552    =item RETURN
1553    
1554    Returns a list of values.
1555    
1556    =back
1557    
1558    =cut
1559    #: Return Type @;
1560    sub GetFlat {
1561        # Get the parameters.
1562        my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
1563        # Construct the query.
1564        my $query = $self->Get($objectNames, $filterClause, $parameterList);
1565        # Create the result list.
1566        my @retVal = ();
1567        # Loop through the records, adding the field values found to the result list.
1568        while (my $row = $query->Fetch()) {
1569            push @retVal, $row->Value($field);
1570          }          }
1571          if (@joinWhere) {      # Return the list created.
1572              $command .= " WHERE " . join(' AND ', @joinWhere);      return @retVal;
1573          }          }
1574          # Add the sort or limit clause (if any) to the SELECT command.  
1575          if ($orderClause) {  =head3 SpecialFields
1576              $command .= " $orderClause";  
1577    C<< my %specials = $erdb->SpecialFields($entityName); >>
1578    
1579    Return a hash mapping special fields in the specified entity to the value of their
1580    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
1584    
1585    =item entityName
1586    
1587    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
1595    
1596    =cut
1597    
1598    sub SpecialFields {
1599        # Get the parameters.
1600        my ($self, $entityName) = @_;
1601        # Declare the return variable.
1602        my %retVal = ();
1603        # Find the entity's data structure.
1604        my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1605        # Loop through its fields, adding each special field to the return hash.
1606        my $fieldHash = $entityData->{Fields};
1607        for my $fieldName (keys %{$fieldHash}) {
1608            my $fieldData = $fieldHash->{$fieldName};
1609            if (exists $fieldData->{special}) {
1610                $retVal{$fieldName} = $fieldData->{special};
1611          }          }
1612      }      }
1613      Trace("SQL query: $command") if T(SQL => 4);      # Return the result.
1614      Trace("PARMS: '" . (join "', '", @params) . "'") if (T(SQL => 4) && (@params > 0));      return %retVal;
     my $sth = $dbh->prepare_command($command);  
     # Execute it with the parameters bound in.  
     $sth->execute(@params) || Confess("SELECT error" . $sth->errstr());  
     # Return the statement object.  
     my $retVal = DBQuery::_new($self, $sth, @{$objectNames});  
     return $retVal;  
1615  }  }
1616    
1617  =head3 Delete  =head3 Delete
1618    
1619  C<< my $stats = $erdb->Delete($entityName, $objectID); >>  C<< my $stats = $erdb->Delete($entityName, $objectID, %options); >>
1620    
1621  Delete an entity instance from the database. The instance is deleted along with all entity and  Delete an entity instance from the database. The instance is deleted along with all entity and
1622  relationship instances dependent on it. The idea of dependence here is recursive. An object is  relationship instances dependent on it. The definition of I<dependence> is recursive.
1623  always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many  
1624  relationship connected to a dependent entity or the "to" entity connected to a 1-to-many  An object is always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many
1625    relationship connected to a dependent entity or if it is the "to" entity connected to a 1-to-many
1626  dependent relationship.  dependent relationship.
1627    
1628  =over 4  =over 4
# Line 1072  Line 1636 
1636  ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),  ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),
1637  then it is presumed to by a LIKE pattern.  then it is presumed to by a LIKE pattern.
1638    
1639  =item testFlag  =item options
1640    
1641  If TRUE, the delete statements will be traced without being executed.  A hash detailing the options for this delete operation.
1642    
1643  =item RETURN  =item RETURN
1644    
# Line 1083  Line 1647 
1647    
1648  =back  =back
1649    
1650    The permissible options for this method are as follows.
1651    
1652    =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  =cut
1665  #: Return Type $%;  #: Return Type $%;
1666  sub Delete {  sub Delete {
1667      # Get the parameters.      # Get the parameters.
1668      my ($self, $entityName, $objectID, $testFlag) = @_;      my ($self, $entityName, $objectID, %options) = @_;
1669      # Declare the return variable.      # Declare the return variable.
1670      my $retVal = Stats->new();      my $retVal = Stats->new();
1671      # Get the DBKernel object.      # Get the DBKernel object.
# Line 1104  Line 1682 
1682      # FROM-relationships and entities.      # FROM-relationships and entities.
1683      my @fromPathList = ();      my @fromPathList = ();
1684      my @toPathList = ();      my @toPathList = ();
1685      # This final hash is used to remember what work still needs to be done. We push paths      # This final list is used to remember what work still needs to be done. We push paths
1686      # onto the list, then pop them off to extend the paths. We prime it with the starting      # onto the list, then pop them off to extend the paths. We prime it with the starting
1687      # point. Note that we will work hard to insure that the last item on a path in the      # point. Note that we will work hard to insure that the last item on a path in the
1688      # TODO list is always an entity.      # to-do list is always an entity.
1689      my @todoList = ([$entityName]);      my @todoList = ([$entityName]);
1690      while (@todoList) {      while (@todoList) {
1691          # Get the current path.          # Get the current path.
# Line 1115  Line 1693 
1693          # Copy it into a list.          # Copy it into a list.
1694          my @stackedPath = @{$current};          my @stackedPath = @{$current};
1695          # Pull off the last item on the path. It will always be an entity.          # Pull off the last item on the path. It will always be an entity.
1696          my $entityName = pop @stackedPath;          my $myEntityName = pop @stackedPath;
1697          # Add it to the alreadyFound list.          # Add it to the alreadyFound list.
1698          $alreadyFound{$entityName} = 1;          $alreadyFound{$myEntityName} = 1;
1699            # Figure out if we need to delete this entity.
1700            if ($myEntityName ne $entityName || ! $options{keepRoot}) {
1701          # Get the entity data.          # Get the entity data.
1702          my $entityData = $self->_GetStructure($entityName);              my $entityData = $self->_GetStructure($myEntityName);
1703          # The first task is to loop through the entity's relation. A DELETE command will              # Loop through the entity's relations. A DELETE command will be needed for each of them.
         # be needed for each of them.  
1704          my $relations = $entityData->{Relations};          my $relations = $entityData->{Relations};
1705          for my $relation (keys %{$relations}) {          for my $relation (keys %{$relations}) {
1706              my @augmentedList = (@stackedPath, $relation);              my @augmentedList = (@stackedPath, $relation);
1707              push @fromPathList, \@augmentedList;              push @fromPathList, \@augmentedList;
1708          }          }
1709            }
1710          # Now we need to look for relationships connected to this entity.          # Now we need to look for relationships connected to this entity.
1711          my $relationshipList = $self->{_metaData}->{Relationships};          my $relationshipList = $self->{_metaData}->{Relationships};
1712          for my $relationshipName (keys %{$relationshipList}) {          for my $relationshipName (keys %{$relationshipList}) {
1713              my $relationship = $relationshipList->{$relationshipName};              my $relationship = $relationshipList->{$relationshipName};
1714              # Check the FROM field. We're only interested if it's us.              # Check the FROM field. We're only interested if it's us.
1715              if ($relationship->{from} eq $entityName) {              if ($relationship->{from} eq $myEntityName) {
1716                  # Add the path to this relationship.                  # Add the path to this relationship.
1717                  my @augmentedList = (@stackedPath, $entityName, $relationshipName);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1718                  push @fromPathList, \@augmentedList;                  push @fromPathList, \@augmentedList;
1719                  # Check the arity. If it's MM we're done. If it's 1M                  # Check the arity. If it's MM we're done. If it's 1M
1720                  # and the target hasn't been seen yet, we want to                  # and the target hasn't been seen yet, we want to
# Line 1146  Line 1726 
1726                          # the current entity, so we need to stack it.                          # the current entity, so we need to stack it.
1727                          my @stackList = (@augmentedList, $toEntity);                          my @stackList = (@augmentedList, $toEntity);
1728                          push @fromPathList, \@stackList;                          push @fromPathList, \@stackList;
1729                        } else {
1730                            Trace("$toEntity ignored because it occurred previously.") if T(4);
1731                      }                      }
1732                  }                  }
1733              }              }
1734              # Now check the TO field. In this case only the relationship needs              # Now check the TO field. In this case only the relationship needs
1735              # deletion.              # deletion.
1736              if ($relationship->{to} eq $entityName) {              if ($relationship->{to} eq $myEntityName) {
1737                  my @augmentedList = (@stackedPath, $entityName, $relationshipName);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1738                  push @toPathList, \@augmentedList;                  push @toPathList, \@augmentedList;
1739              }              }
1740          }          }
1741      }      }
1742      # Create the first qualifier for the WHERE clause. This selects the      # 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      # keys of the primary entity records to be deleted. When we're deleting
1744      # from a dependent table, we construct a join page from the first qualifier      # from a dependent table, we construct a join path from the first qualifier
1745      # to the table containing the dependent records to delete.      # to the table containing the dependent records to delete.
1746      my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");      my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
1747      # We need to make two passes. The first is through the to-list, and      # We need to make two passes. The first is through the to-list, and
# Line 1171  Line 1753 
1753      for my $keyName ('to_link', 'from_link') {      for my $keyName ('to_link', 'from_link') {
1754          # Get the list for this key.          # Get the list for this key.
1755          my @pathList = @{$stackList{$keyName}};          my @pathList = @{$stackList{$keyName}};
1756            Trace(scalar(@pathList) . " entries in path list for $keyName.") if T(3);
1757          # Loop through this list.          # Loop through this list.
1758          while (my $path = pop @pathList) {          while (my $path = pop @pathList) {
1759              # Get the table whose rows are to be deleted.              # Get the table whose rows are to be deleted.
1760              my @pathTables = @{$path};              my @pathTables = @{$path};
1761              # Start the DELETE statement.              # 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];              my $target = $pathTables[$#pathTables];
1764              my $stmt = "DELETE FROM $target";              my $stmt = $db->SetUsing(@pathTables);
             # If there's more than just the one table, we need a USING clause.  
             if (@pathTables > 1) {  
                 $stmt .= " USING " . join(", ", @pathTables[0 .. ($#pathTables - 1)]);  
             }  
1765              # Now start the WHERE. The first thing is the ID field from the starting table. That              # 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              # starting table will either be the entity relation or one of the entity's
1767              # sub-relations.              # sub-relations.
# Line 1191  Line 1771 
1771                  # Connect the current relationship to the preceding entity.                  # Connect the current relationship to the preceding entity.
1772                  my ($entity, $rel) = @pathTables[$i-1,$i];                  my ($entity, $rel) = @pathTables[$i-1,$i];
1773                  # The style of connection depends on the direction of the relationship.                  # The style of connection depends on the direction of the relationship.
1774                  $stmt .= " AND $entity.id = $rel.from_link";                  $stmt .= " AND $entity.id = $rel.$keyName";
1775                  if ($i + 1 <= $#pathTables) {                  if ($i + 1 <= $#pathTables) {
1776                      # Here there's a next entity, so connect that to the relationship's                      # Here there's a next entity, so connect that to the relationship's
1777                      # to-link.                      # to-link.
1778                      my $entity2 = $pathTables[$i+1];                      my $entity2 = $pathTables[$i+1];
1779                      $stmt .= " AND $rel.$keyName = $entity2.id";                      $stmt .= " AND $rel.to_link = $entity2.id";
1780                  }                  }
1781              }              }
1782              # Now we have our desired DELETE statement.              # Now we have our desired DELETE statement.
1783              if ($testFlag) {              if ($options{testMode}) {
1784                  # Here the user wants to trace without executing.                  # Here the user wants to trace without executing.
1785                  Trace($stmt) if T(0);                  Trace($stmt) if T(0);
1786              } else {              } else {
1787                  # Here we can delete. Note that the SQL method dies with a confessing                  # Here we can delete. Note that the SQL method dies with a confession
1788                  # if an error occurs, so we just go ahead and do it.                  # if an error occurs, so we just go ahead and do it.
1789                  Trace("Executing delete: $stmt") if T(3);                  Trace("Executing delete from $target using '$objectID'.") if T(3);
1790                  my $rv = $db->SQL($stmt, 0, [$objectID]);                  my $rv = $db->SQL($stmt, 0, $objectID);
1791                  # Accumulate the statistics for this delete. The only rows deleted                  # Accumulate the statistics for this delete. The only rows deleted
1792                  # are from the target table, so we use its name to record the                  # are from the target table, so we use its name to record the
1793                  # statistic.                  # statistic.
# Line 1219  Line 1799 
1799      return $retVal;      return $retVal;
1800  }  }
1801    
1802  =head3 GetList  =head3 Disconnect
   
 C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  
1803    
1804  Return a list of object descriptors for the specified objects as determined by the  C<< $erdb->Disconnect($relationshipName, $originEntityName, $originEntityID); >>
 specified filter clause.  
1805    
1806  This method is essentially the same as L</Get> except it returns a list of objects rather  Disconnect an entity instance from all the objects to which it is related. This
1807  than a query object that can be used to get the results one record at a time.  will delete each relationship instance that connects to the specified entity.
1808    
1809  =over 4  =over 4
1810    
1811  =item objectNames  =item relationshipName
   
 List containing the names of the entity and relationship objects to be retrieved.  
   
 =item filterClause  
   
 WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  
 be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be  
 specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified  
 in the filter clause should be added to the parameter list as additional parameters. The  
 fields in a filter clause can come from primary entity relations, relationship relations,  
 or secondary entity relations; however, all of the entities and relationships involved must  
 be included in the list of object names.  
   
 The filter clause can also specify a sort order. To do this, simply follow the filter string  
 with an ORDER BY clause. For example, the following filter string gets all genomes for a  
 particular genus and sorts them by species name.  
   
 C<< "Genome(genus) = ? ORDER BY Genome(species)" >>  
1812    
1813  The rules for field references in a sort order are the same as those for field references in the  Name of the relationship whose instances are to be deleted.
 filter clause in general; however, odd things may happen if a sort field is from a secondary  
 relation.  
1814    
1815  =item param1, param2, ..., paramN  =item originEntityName
1816    
1817  Parameter values to be substituted into the filter clause.  Name of the entity that is to be disconnected.
1818    
1819  =item RETURN  =item originEntityID
1820    
1821  Returns a list of B<DBObject>s that satisfy the query conditions.  ID of the entity that is to be disconnected.
1822    
1823  =back  =back
1824    
1825  =cut  =cut
1826  #: Return Type @%  
1827  sub GetList {  sub Disconnect {
1828      # Get the parameters.      # Get the parameters.
1829      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $relationshipName, $originEntityName, $originEntityID) = @_;
1830      # Declare the return variable.      # Get the relationship descriptor.
1831      my @retVal = ();      my $structure = $self->_GetStructure($relationshipName);
1832      # Perform the query.      # Insure we have a relationship.
1833      my $query = $self->Get($objectNames, $filterClause, @params);      if (! exists $structure->{from}) {
1834      # Loop through the results.          Confess("$relationshipName is not a relationship in the database.");
1835      while (my $object = $query->Fetch) {      } else {
1836          push @retVal, $object;          # Get the database handle.
1837            my $dbh = $self->{_dbh};
1838            # We'll set this value to 1 if we find our entity.
1839            my $found = 0;
1840            # Loop through the ends of the relationship.
1841            for my $dir ('from', 'to') {
1842                if ($structure->{$dir} eq $originEntityName) {
1843                    # Delete all relationship instances on this side of the entity instance.
1844                    $dbh->SQL("DELETE FROM $relationshipName WHERE ${dir}_link = ?", 0, $originEntityID);
1845                    $found = 1;
1846                }
1847            }
1848            # Insure we found the entity on at least one end.
1849            if (! $found) {
1850                Confess("Entity \"$originEntityName\" does not use $relationshipName.");
1851            }
1852      }      }
     # Return the result.  
     return @retVal;  
1853  }  }
1854    
1855  =head3 ComputeObjectSentence  =head3 DeleteRow
1856    
1857  C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>  C<< $erdb->DeleteRow($relationshipName, $fromLink, $toLink, \%values); >>
1858    
1859  Check an object name, and if it is a relationship convert it to a relationship sentence.  Delete a row from a relationship. In most cases, only the from-link and to-link are
1860    needed; however, for relationships with intersection data values can be specified
1861    for the other fields using a hash.
1862    
1863  =over 4  =over 4
1864    
1865  =item objectName  =item relationshipName
1866    
1867  Name of the entity or relationship.  Name of the relationship from which the row is to be deleted.
1868    
1869  =item RETURN  =item fromLink
1870    
1871  Returns a string containing the entity name or a relationship sentence.  ID of the entity instance in the From direction.
1872    
1873    =item toLink
1874    
1875    ID of the entity instance in the To direction.
1876    
1877    =item values
1878    
1879    Reference to a hash of other values to be used for filtering the delete.
1880    
1881  =back  =back
1882    
1883  =cut  =cut
1884    
1885  sub ComputeObjectSentence {  sub DeleteRow {
1886      # Get the parameters.      # Get the parameters.
1887      my ($self, $objectName) = @_;      my ($self, $relationshipName, $fromLink, $toLink, $values) = @_;
1888      # Set the default return value.      # Create a hash of all the filter information.
1889      my $retVal = $objectName;      my %filter = ('from-link' => $fromLink, 'to-link' => $toLink);
1890      # Look for the object as a relationship.      if (defined $values) {
1891      my $relTable = $self->{_metaData}->{Relationships};          for my $key (keys %{$values}) {
1892      if (exists $relTable->{$objectName}) {              $filter{$key} = $values->{$key};
         # Get the relationship sentence.  
         $retVal = _ComputeRelationshipSentence($objectName, $relTable->{$objectName});  
1893      }      }
1894      # Return the result.      }
1895      return $retVal;      # Build an SQL statement out of the hash.
1896        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 DumpRelations  =head3 SortNeeded
1911    
1912  C<< $erdb->DumpRelations($outputDirectory); >>  C<< my $parms = $erdb->SortNeeded($relationName); >>
1913    
1914  Write the contents of all the relations to tab-delimited files in the specified directory.  Return the pipe command for the sort that should be applied to the specified
1915  Each file will have the same name as the relation dumped, with an extension of DTX.  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 outputDirectory      sort -k1 -t"\t"
1921    
1922  Name of the directory into which the relation files should be dumped.  If the first field is numeric, the method would return
1923    
1924  =back      sort -k1n -t"\t"
1925    
1926    Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate
1927    keys using a sort.
1928    
1929    =over 4
1930    
1931    =item relationName
1932    
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
1940    
1941    =cut
1942    #: Return Type $;
1943    sub SortNeeded {
1944        # Get the parameters.
1945        my ($self, $relationName) = @_;
1946        # Declare a descriptor to hold the names of the key fields.
1947        my @keyNames = ();
1948        # Get the relation structure.
1949        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.
2005        return $retVal;
2006    }
2007    
2008    =head3 GetList
2009    
2010    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    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
2019    
2020    =item objectNames
2021    
2022    List containing the names of the entity and relationship objects to be retrieved.
2023    
2024    =item filterClause
2025    
2026    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    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    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
2049    
2050    Returns a list of B<DBObject>s that satisfy the query conditions.
2051    
2052    =back
2053    
2054    =cut
2055    #: Return Type @%
2056    sub GetList {
2057        # Get the parameters.
2058        my ($self, $objectNames, $filterClause, $params) = @_;
2059        # Declare the return variable.
2060        my @retVal = ();
2061        # Perform the query.
2062        my $query = $self->Get($objectNames, $filterClause, $params);
2063        # Loop through the results.
2064        while (my $object = $query->Fetch) {
2065            push @retVal, $object;
2066        }
2067        # Return the result.
2068        return @retVal;
2069    }
2070    
2071    =head3 GetCount
2072    
2073    C<< my $count = $erdb->GetCount(\@objectNames, $filter, \@params); >>
2074    
2075    Return the number of rows found by a specified query. This method would
2076    normally be used to count the records in a single table. For example, in a
2077    genetics database
2078    
2079        my $count = $erdb->GetCount(['Genome'], 'Genome(genus-species) LIKE ?', ['homo %']);
2080    
2081    would return the number of genomes for the genus I<homo>. It is conceivable, however,
2082    to use it to return records based on a join. For example,
2083    
2084        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        my $count = $erdb->GetCount(['Genome', 'Feature'], 'Genome(genus-species) LIKE ?',
2091                                    ['homo %']);
2092    
2093    it would return the number of genomes, not the number of genome/feature pairs.
2094    
2095    =over 4
2096    
2097    =item objectNames
2098    
2099    Reference to a list of the objects (entities and relationships) included in the
2100    query.
2101    
2102    =item filter
2103    
2104    A filter clause for restricting the query. The rules are the same as for the L</Get>
2105    method.
2106    
2107    =item params
2108    
2109    Reference to a list of the parameter values to be substituted for the parameter marks
2110    in the filter.
2111    
2112    =item RETURN
2113    
2114    Returns a count of the number of records in the first table that would satisfy
2115    the query.
2116    
2117    =back
2118    
2119    =cut
2120    
2121    sub GetCount {
2122        # Get the parameters.
2123        my ($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  =cut
2215    
# Line 1359  Line 2238 
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  =head3 InsertObject
2305    
2306  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>  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  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.  of field names to values. Field values in the primary relation are represented by scalars.
# Line 1375  Line 2317 
2317  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
2318  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
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'}); >>  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  =over 4
2323    
# Line 1387  Line 2329 
2329    
2330  Hash of field names to values.  Hash of field names to values.
2331    
 =item RETURN  
   
 Returns 1 if successful, 0 if an error occurred.  
   
2332  =back  =back
2333    
2334  =cut  =cut
# Line 1489  Line 2427 
2427                  $retVal = $sth->execute(@parameterList);                  $retVal = $sth->execute(@parameterList);
2428                  if (!$retVal) {                  if (!$retVal) {
2429                      my $errorString = $sth->errstr();                      my $errorString = $sth->errstr();
2430                      Trace("Insert error: $errorString.") if T(0);                      Confess("Error inserting into $relationName: $errorString");
2431                  }                  }
2432              }              }
2433          }          }
2434      }      }
2435      # Return the success indicator.      # Return a 1 for backward compatability.
2436      return $retVal;      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  =head3 LoadTable
2498    
2499  C<< my %results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>  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  Load data from a tab-delimited file into a specified table, optionally re-creating the table
2502  first.  first.
# Line 1567  Line 2563 
2563      };      };
2564      if (!defined $rv) {      if (!defined $rv) {
2565          $retVal->AddMessage($@) if ($@);          $retVal->AddMessage($@) if ($@);
2566          $retVal->AddMessage("Table load failed for $relationName using $fileName.");          $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2567          Trace("Table load failed for $relationName.") if T(1);          Trace("Table load failed for $relationName.") if T(1);
2568      } else {      } else {
2569          # Here we successfully loaded the table.          # Here we successfully loaded the table.
# Line 1575  Line 2571 
2571          my $size = -s $fileName;          my $size = -s $fileName;
2572          Trace("$size bytes loaded into $relationName.") if T(2);          Trace("$size bytes loaded into $relationName.") if T(2);
2573          # If we're rebuilding, we need to create the table indexes.          # If we're rebuilding, we need to create the table indexes.
2574          if ($truncateFlag && ! $dbh->{_preIndex}) {          if ($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 {              eval {
2579                  $self->CreateIndex($relationName);                  $self->CreateIndex($relationName);
2580              };              };
# Line 1583  Line 2582 
2582                  $retVal->AddMessage($@);                  $retVal->AddMessage($@);
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                if ($self->_IsPrimary($relationName)) {
2589                    # Get the relation's entity/relationship structure.
2590                    my $structure = $self->_GetStructure($relationName);
2591                    # Check for a searchable fields list.
2592                    if (exists $structure->{searchFields}) {
2593                        # Here we know that we need to create a full-text search index.
2594                        # Get an SQL-formatted field name list.
2595                        my $fields = join(", ", $self->_FixNames(@{$structure->{searchFields}}));
2596                        # Create the index.
2597                        $dbh->create_index(tbl => $relationName, idx => "search_idx",
2598                                           flds => $fields, kind => 'fulltext');
2599                    }
2600                }
2601            }
2602      }      }
2603      # Analyze the table to improve performance.      # Analyze the table to improve performance.
2604        Trace("Analyzing and compacting $relationName.") if T(3);
2605      $dbh->vacuum_it($relationName);      $dbh->vacuum_it($relationName);
2606        Trace("$relationName load completed.") if T(3);
2607      # Return the statistics.      # Return the statistics.
2608      return $retVal;      return $retVal;
2609  }  }
2610    
2611  =head3 GenerateEntity  =head3 DropRelation
2612    
2613  C<< my $fieldHash = $erdb->GenerateEntity($id, $type, \%values); >>  C<< $erdb->DropRelation($relationName); >>
2614    
2615  Generate the data for a new entity instance. This method creates a field hash suitable for  Physically drop a relation from the database.
 passing as a parameter to L</InsertObject>. The ID is specified by the callr, but the rest  
 of the fields are generated using information in the database schema.  
   
 Each data type has a default algorithm for generating random test data. This can be overridden  
 by including a B<DataGen> element in the field. If this happens, the content of the element is  
 executed as a PERL program in the context of this module. The element may make use of a C<$this>  
 variable which contains the field hash as it has been built up to the current point. If any  
 fields are dependent on other fields, the C<pass> attribute can be used to control the order  
 in which the fields are generated. A field with a high data pass number will be generated after  
 a field with a lower one. If any external values are needed, they should be passed in via the  
 optional third parameter, which will be available to the data generation script under the name  
 C<$value>. Several useful utility methods are provided for generating random values, including  
 L</IntGen>, L</StringGen>, L</FloatGen>, and L</DateGen>. Note that dates are stored and generated  
 in the form of a timestamp number rather than a string.  
2616    
2617  =over 4  =over 4
2618    
2619  =item id  =item relationName
   
 ID to assign to the new entity.  
   
 =item type  
   
 Type name for the new entity.  
   
 =item values  
2620    
2621  Hash containing additional values that might be needed by the data generation methods (optional).  Name of the relation to drop. If it does not exist, this method will have
2622    no effect.
2623    
2624  =back  =back
2625    
2626  =cut  =cut
2627    
2628  sub GenerateEntity {  sub DropRelation {
2629      # Get the parameters.      # Get the parameters.
2630      my ($self, $id, $type, $values) = @_;      my ($self, $relationName) = @_;
2631      # Create the return hash.      # Get the database handle.
2632      my $this = { id => $id };      my $dbh = $self->{_dbh};
2633      # Get the metadata structure.      # Drop the relation. The method used here has no effect if the relation
2634      my $metadata = $self->{_metaData};      # does not exist.
2635      # Get this entity's list of fields.      Trace("Invoking DB Kernel to drop $relationName.") if T(3);
2636      if (!exists $metadata->{Entities}->{$type}) {      $dbh->drop_table(tbl => $relationName);
         Confess("Unrecognized entity type $type in GenerateEntity.");  
     } else {  
         my $entity = $metadata->{Entities}->{$type};  
         my $fields = $entity->{Fields};  
         # Generate data from the fields.  
         _GenerateFields($this, $fields, $type, $values);  
     }  
     # Return the hash created.  
     return $this;  
2637  }  }
2638    
2639  =head3 GetEntity  =head3 MatchSqlPattern
2640    
2641  C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>  C<< my $matched = ERDB::MatchSqlPattern($value, $pattern); >>
2642    
2643  Return an object describing the entity instance with a specified ID.  Determine whether or not a specified value matches an SQL pattern. An SQL
2644    pattern has two wild card characters: C<%> that matches multiple characters,
2645    and C<_> that matches a single character. These can be escaped using a
2646    backslash (C<\>). We pull this off by converting the SQL pattern to a
2647    PERL regular expression. As per SQL rules, the match is case-insensitive.
2648    
2649  =over 4  =over 4
2650    
2651  =item entityType  =item value
2652    
2653  Entity type name.  Value to be matched against the pattern. Note that an undefined or empty
2654    value will not match anything.
2655    
2656    =item pattern
2657    
2658    SQL pattern against which to match the value. An undefined or empty pattern will
2659    match everything.
2660    
2661    =item RETURN
2662    
2663    Returns TRUE if the value and pattern match, else FALSE.
2664    
2665    =back
2666    
2667    =cut
2668    
2669    sub MatchSqlPattern {
2670        # Get the parameters.
2671        my ($value, $pattern) = @_;
2672        # Declare the return variable.
2673        my $retVal;
2674        # Insure we have a pattern.
2675        if (! defined($pattern) || $pattern eq "") {
2676            $retVal = 1;
2677        } else {
2678            # Break the pattern into pieces around the wildcard characters. Because we
2679            # use parentheses in the split function's delimiter expression, we'll get
2680            # list elements for the delimiters as well as the rest of the string.
2681            my @pieces = split /([_%]|\\[_%])/, $pattern;
2682            # Check some fast special cases.
2683            if ($pattern eq '%') {
2684                # A null pattern matches everything.
2685                $retVal = 1;
2686            } elsif (@pieces == 1) {
2687                # No wildcards, so we have a literal comparison. Note we're case-insensitive.
2688                $retVal = (lc($value) eq lc($pattern));
2689            } elsif (@pieces == 2 && $pieces[1] eq '%') {
2690                # A wildcard at the end, so we have a substring match. This is also case-insensitive.
2691                $retVal = (lc(substr($value, 0, length($pieces[0]))) eq lc($pieces[0]));
2692            } else {
2693                # Okay, we have to do it the hard way. Convert each piece to a PERL pattern.
2694                my $realPattern = "";
2695                for my $piece (@pieces) {
2696                    # Determine the type of piece.
2697                    if ($piece eq "") {
2698                        # Empty pieces are ignored.
2699                    } elsif ($piece eq "%") {
2700                        # Here we have a multi-character wildcard. Note that it can match
2701                        # zero or more characters.
2702                        $realPattern .= ".*"
2703                    } elsif ($piece eq "_") {
2704                        # Here we have a single-character wildcard.
2705                        $realPattern .= ".";
2706                    } elsif ($piece eq "\\%" || $piece eq "\\_") {
2707                        # This is an escape sequence (which is a rare thing, actually).
2708                        $realPattern .= substr($piece, 1, 1);
2709                    } else {
2710                        # Here we have raw text.
2711                        $realPattern .= quotemeta($piece);
2712                    }
2713                }
2714                # Do the match.
2715                $retVal = ($value =~ /^$realPattern$/i ? 1 : 0);
2716            }
2717        }
2718        # Return the result.
2719        return $retVal;
2720    }
2721    
2722    =head3 GetEntity
2723    
2724    C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>
2725    
2726    Return an object describing the entity instance with a specified ID.
2727    
2728    =over 4
2729    
2730    =item entityType
2731    
2732    Entity type name.
2733    
2734  =item ID  =item ID
2735    
# Line 1677  Line 2748 
2748      # Get the parameters.      # Get the parameters.
2749      my ($self, $entityType, $ID) = @_;      my ($self, $entityType, $ID) = @_;
2750      # Create a query.      # Create a query.
2751      my $query = $self->Get([$entityType], "$entityType(id) = ?", $ID);      my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);
2752      # Get the first (and only) object.      # Get the first (and only) object.
2753      my $retVal = $query->Fetch();      my $retVal = $query->Fetch();
2754      # Return the result.      # Return the result.
2755      return $retVal;      return $retVal;
2756  }  }
2757    
2758    =head3 GetChoices
2759    
2760    C<< my @values = $erdb->GetChoices($entityName, $fieldName); >>
2761    
2762    Return a list of all the values for the specified field that are represented in the
2763    specified entity.
2764    
2765    Note that if the field is not indexed, then this will be a very slow operation.
2766    
2767    =over 4
2768    
2769    =item entityName
2770    
2771    Name of an entity in the database.
2772    
2773    =item fieldName
2774    
2775    Name of a field belonging to the entity. This is a raw field name without
2776    the standard parenthesized notation used in most calls.
2777    
2778    =item RETURN
2779    
2780    Returns a list of the distinct values for the specified field in the database.
2781    
2782    =back
2783    
2784    =cut
2785    
2786    sub GetChoices {
2787        # Get the parameters.
2788        my ($self, $entityName, $fieldName) = @_;
2789        # Declare the return variable.
2790        my @retVal;
2791        # Get the entity data structure.
2792        my $entityData = $self->_GetStructure($entityName);
2793        # Get the field.
2794        my $fieldHash = $entityData->{Fields};
2795        if (! exists $fieldHash->{$fieldName}) {
2796            Confess("$fieldName not found in $entityName.");
2797        } else {
2798            # Get the name of the relation containing the field.
2799            my $relation = $fieldHash->{$fieldName}->{relation};
2800            # Fix up the field name.
2801            my $realName = _FixName($fieldName);
2802            # Get the database handle.
2803            my $dbh = $self->{_dbh};
2804            # Query the database.
2805            my $results = $dbh->SQL("SELECT DISTINCT $realName FROM $relation");
2806            # Clean the results. They are stored as a list of lists, and we just want the one list.
2807            @retVal = sort map { $_->[0] } @{$results};
2808        }
2809        # Return the result.
2810        return @retVal;
2811    }
2812    
2813  =head3 GetEntityValues  =head3 GetEntityValues
2814    
2815  C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>  C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>
2816    
2817  Return a list of values from a specified entity instance.  Return a list of values from a specified entity instance. If the entity instance
2818    does not exist, an empty list is returned.
2819    
2820  =over 4  =over 4
2821    
# Line 1745  Line 2872 
2872  spreadsheet cell, and each feature will be represented by a list containing the  spreadsheet cell, and each feature will be represented by a list containing the
2873  feature ID followed by all of its aliases.  feature ID followed by all of its aliases.
2874    
2875  C<< $query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>  C<< @query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>
2876    
2877  =over 4  =over 4
2878    
# Line 1790  Line 2917 
2917      # list is a scalar we convert it into a singleton list.      # list is a scalar we convert it into a singleton list.
2918      my @parmList = ();      my @parmList = ();
2919      if (ref $parameterList eq "ARRAY") {      if (ref $parameterList eq "ARRAY") {
2920            Trace("GetAll parm list is an array.") if T(4);
2921          @parmList = @{$parameterList};          @parmList = @{$parameterList};
2922      } else {      } else {
2923            Trace("GetAll parm list is a scalar: $parameterList.") if T(4);
2924          push @parmList, $parameterList;          push @parmList, $parameterList;
2925      }      }
2926      # Insure the counter has a value.      # Insure the counter has a value.
# Line 1803  Line 2932 
2932          $filterClause .= " LIMIT $count";          $filterClause .= " LIMIT $count";
2933      }      }
2934      # Create the query.      # Create the query.
2935      my $query = $self->Get($objectNames, $filterClause, @parmList);      my $query = $self->Get($objectNames, $filterClause, \@parmList);
2936      # Set up a counter of the number of records read.      # Set up a counter of the number of records read.
2937      my $fetched = 0;      my $fetched = 0;
2938      # Loop through the records returned, extracting the fields. Note that if the      # Loop through the records returned, extracting the fields. Note that if the
# Line 1814  Line 2943 
2943          push @retVal, \@rowData;          push @retVal, \@rowData;
2944          $fetched++;          $fetched++;
2945      }      }
2946        Trace("$fetched rows returned in GetAll.") if T(SQL => 4);
2947      # Return the resulting list.      # Return the resulting list.
2948      return @retVal;      return @retVal;
2949  }  }
2950    
2951    =head3 Exists
2952    
2953    C<< my $found = $sprout->Exists($entityName, $entityID); >>
2954    
2955    Return TRUE if an entity exists, else FALSE.
2956    
2957    =over 4
2958    
2959    =item entityName
2960    
2961    Name of the entity type (e.g. C<Feature>) relevant to the existence check.
2962    
2963    =item entityID
2964    
2965    ID of the entity instance whose existence is to be checked.
2966    
2967    =item RETURN
2968    
2969    Returns TRUE if the entity instance exists, else FALSE.
2970    
2971    =back
2972    
2973    =cut
2974    #: Return Type $;
2975    sub Exists {
2976        # Get the parameters.
2977        my ($self, $entityName, $entityID) = @_;
2978        # Check for the entity instance.
2979        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
2980        my $testInstance = $self->GetEntity($entityName, $entityID);
2981        # Return an existence indicator.
2982        my $retVal = ($testInstance ? 1 : 0);
2983        return $retVal;
2984    }
2985    
2986  =head3 EstimateRowSize  =head3 EstimateRowSize
2987    
2988  C<< my $rowSize = $erdb->EstimateRowSize($relName); >>  C<< my $rowSize = $erdb->EstimateRowSize($relName); >>
# Line 1856  Line 3021 
3021      return $retVal;      return $retVal;
3022  }  }
3023    
3024  =head2 Internal Utility Methods  =head3 GetFieldTable
3025    
3026  =head3 GetLoadStats  C<< my $fieldHash = $self->GetFieldTable($objectnName); >>
3027    
3028  Return a blank statistics object for use by the load methods.  Get the field structure for a specified entity or relationship.
3029    
3030  This is a static method.  =over 4
3031    
3032    =item objectName
3033    
3034    Name of the desired entity or relationship.
3035    
3036    =item RETURN
3037    
3038    The table containing the field descriptors for the specified object.
3039    
3040    =back
3041    
3042  =cut  =cut
3043    
3044  sub _GetLoadStats{  sub GetFieldTable {
3045      return Stats->new();      # Get the parameters.
3046        my ($self, $objectName) = @_;
3047        # Get the descriptor from the metadata.
3048        my $objectData = $self->_GetStructure($objectName);
3049        # Return the object's field table.
3050        return $objectData->{Fields};
3051  }  }
3052    
3053  =head3 GenerateFields  =head3 SplitKeywords
3054    
3055  Generate field values from a field structure and store in a specified table. The field names  C<< my @keywords = ERDB::SplitKeywords($keywordString); >>
 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.  
3056    
3057  This is a static method.  This method returns a list of the positive keywords in the specified
3058    keyword string. All of the operators will have been stripped off,
3059    and if the keyword is preceded by a minus operator (C<->), it will
3060    not be in the list returned. The idea here is to get a list of the
3061    keywords the user wants to see. The list will be processed to remove
3062    duplicates.
3063    
3064    It is possible to create a string that confuses this method. For example
3065    
3066        frog toad -frog
3067    
3068    would return both C<frog> and C<toad>. If this is a problem we can deal
3069    with it later.
3070    
3071  =over 4  =over 4
3072    
3073  =item this  =item keywordString
3074    
3075  Hash table into which the field values should be placed.  The keyword string to be parsed.
3076    
3077  =item fields  =item RETURN
3078    
3079  Field structure from which the field descriptors should be taken.  Returns a list of the words in the keyword string the user wants to
3080    see.
3081    
3082  =item type  =back
3083    
3084    =cut
3085    
3086    sub SplitKeywords {
3087        # Get the parameters.
3088        my ($keywordString) = @_;
3089        # Make a safety copy of the string. (This helps during debugging.)
3090        my $workString = $keywordString;
3091        # Convert operators we don't care about to spaces.
3092        $workString =~ tr/+"()<>/ /;
3093        # Split the rest of the string along space boundaries. Note that we
3094        # eliminate any words that are zero length or begin with a minus sign.
3095        my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
3096        # Use a hash to remove duplicates.
3097        my %words = map { $_ => 1 } @wordList;
3098        # Return the result.
3099        return sort keys %words;
3100    }
3101    
3102    =head3 ValidateFieldName
3103    
3104    C<< my $okFlag = ERDB::ValidateFieldName($fieldName); >>
3105    
3106    Return TRUE if the specified field name is valid, else FALSE. Valid field names must
3107    be hyphenated words subject to certain restrictions.
3108    
3109    =over 4
3110    
3111    =item fieldName
3112    
3113    Field name to be validated.
3114    
3115    =item RETURN
3116    
3117    Returns TRUE if the field name is valid, else FALSE.
3118    
3119    =back
3120    
3121    =cut
3122    
3123    sub ValidateFieldName {
3124        # Get the parameters.
3125        my ($fieldName) = @_;
3126        # Declare the return variable. The field name is valid until we hear
3127        # differently.
3128        my $retVal = 1;
3129        # Compute the maximum name length.
3130        my $maxLen = $TypeTable{'name-string'}->{maxLen};
3131        # Look for bad stuff in the name.
3132        if ($fieldName =~ /--/) {
3133            # Here we have a doubled minus sign.
3134            Trace("Field name $fieldName has a doubled hyphen.") if T(1);
3135            $retVal = 0;
3136        } elsif ($fieldName !~ /^[A-Za-z]/) {
3137            # Here the field name is missing the initial letter.
3138            Trace("Field name $fieldName does not begin with a letter.") if T(1);
3139            $retVal = 0;
3140        } elsif (length($fieldName) > $maxLen) {
3141            # Here the field name is too long.
3142            Trace("Maximum field name length is $maxLen. Field name must be truncated to " . substr($fieldName,0, $maxLen) . ".");
3143        } else {
3144            # Strip out the minus signs. Everything remaining must be a letter,
3145            # underscore, or digit.
3146            my $strippedName = $fieldName;
3147            $strippedName =~ s/-//g;
3148            if ($strippedName !~ /^(\w|\d)+$/) {
3149                Trace("Field name $fieldName contains illegal characters.") if T(1);
3150                $retVal = 0;
3151            }
3152        }
3153        # Return the result.
3154        return $retVal;
3155    }
3156    
3157    =head3 ReadMetaXML
3158    
3159    C<< my $rawMetaData = ERDB::ReadDBD($fileName); >>
3160    
3161    This method reads a raw database definition XML file and returns it.
3162    Normally, the metadata used by the ERDB system has been processed and
3163    modified to make it easier to load and retrieve the data; however,
3164    this method can be used to get the data in its raw form.
3165    
3166    =over 4
3167    
3168    =item fileName
3169    
3170    Name of the XML file to read.
3171    
3172    =item RETURN
3173    
3174    Returns a hash reference containing the raw XML data from the specified file.
3175    
3176    =back
3177    
3178    =cut
3179    
3180    sub ReadMetaXML {
3181        # Get the parameters.
3182        my ($fileName) = @_;
3183        # Read the XML.
3184        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
3185        Trace("XML metadata loaded from file $fileName.") if T(1);
3186        # Return the result.
3187        return $retVal;
3188    }
3189    
3190    =head3 GetEntityFieldHash
3191    
3192    C<< my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName); >>
3193    
3194    Get the field hash of the named entity in the specified raw XML structure.
3195    The field hash may not exist, in which case we need to create it.
3196    
3197    =over 4
3198    
3199    =item structure
3200    
3201    Raw XML structure defininng the database. This is not the run-time XML used by
3202    an ERDB object, since that has all sorts of optimizations built-in.
3203    
3204    =item entityName
3205    
3206    Name of the entity whose field structure is desired.
3207    
3208    =item RETURN
3209    
3210    Returns the field hash used to define the entity's fields.
3211    
3212    =back
3213    
3214    =cut
3215    
3216    sub GetEntityFieldHash {
3217        # Get the parameters.
3218        my ($structure, $entityName) = @_;
3219        # Get the entity structure.
3220        my $entityData = $structure->{Entities}->{$entityName};
3221        # Look for a field structure.
3222        my $retVal = $entityData->{Fields};
3223        # If it doesn't exist, create it.
3224        if (! defined($retVal)) {
3225            $entityData->{Fields} = {};
3226            $retVal = $entityData->{Fields};
3227        }
3228        # Return the result.
3229        return $retVal;
3230    }
3231    
3232    =head3 WriteMetaXML
3233    
3234    C<< ERDB::WriteMetaXML($structure, $fileName); >>
3235    
3236    Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
3237    used to update the database definition. It must be used with care, however, since it
3238    will only work on a raw structure, not on the processed structure created by an ERDB
3239    constructor.
3240    
3241    =over 4
3242    
3243    =item structure
3244    
3245    XML structure to be written to the file.
3246    
3247    =item fileName
3248    
3249    Name of the output file to which the updated XML should be stored.
3250    
3251    =back
3252    
3253    =cut
3254    
3255    sub WriteMetaXML {
3256        # Get the parameters.
3257        my ($structure, $fileName) = @_;
3258        # Compute the output.
3259        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
3260        # Write it to the file.
3261        my $xmlOut = Open(undef, ">$fileName");
3262        print $xmlOut $fileString;
3263    }
3264    
3265    
3266    =head3 HTMLNote
3267    
3268    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
3269    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
3270    Except for C<[p]>, all the codes are closed by slash-codes. So, for
3271    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
3272    
3273    C<< my $realHtml = ERDB::HTMLNote($dataString); >>
3274    
3275    =over 4
3276    
3277    =item dataString
3278    
3279    String to convert to HTML.
3280    
3281    =item RETURN
3282    
3283    An HTML string derived from the input string.
3284    
3285    =back
3286    
3287    =cut
3288    
3289    sub HTMLNote {
3290        # Get the parameter.
3291        my ($dataString) = @_;
3292        # HTML-escape the text.
3293        my $retVal = CGI::escapeHTML($dataString);
3294        # Substitute the bulletin board codes.
3295        $retVal =~ s!\[(/?[bi])\]!<$1>!g;
3296        $retVal =~ s!\[p\]!</p><p>!g;
3297        # Return the result.
3298        return $retVal;
3299    }
3300    
3301    
3302    =head2 Data Mining Methods
3303    
3304    =head3 GetUsefulCrossValues
3305    
3306    C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>
3307    
3308    Return a list of the useful attributes that would be returned by a B<Cross> call
3309    from an entity of the source entity type through the specified relationship. This
3310    means it will return the fields of the target entity type and the intersection data
3311    fields in the relationship. Only primary table fields are returned. In other words,
3312    the field names returned will be for fields where there is always one and only one
3313    value.
3314    
3315    =over 4
3316    
3317    =item sourceEntity
3318    
3319    Name of the entity from which the relationship crossing will start.
3320    
3321    =item relationship
3322    
3323    Name of the relationship being crossed.
3324    
3325    =item RETURN
3326    
3327    Returns a list of field names in Sprout field format (I<objectName>C<(>I<fieldName>C<)>.
3328    
3329    =back
3330    
3331    =cut
3332    #: Return Type @;
3333    sub GetUsefulCrossValues {
3334        # Get the parameters.
3335        my ($self, $sourceEntity, $relationship) = @_;
3336        # Declare the return variable.
3337        my @retVal = ();
3338        # Determine the target entity for the relationship. This is whichever entity is not
3339        # the source entity. So, if the source entity is the FROM, we'll get the name of
3340        # the TO, and vice versa.
3341        my $relStructure = $self->_GetStructure($relationship);
3342        my $targetEntityType = ($relStructure->{from} eq $sourceEntity ? "to" : "from");
3343        my $targetEntity = $relStructure->{$targetEntityType};
3344        # Get the field table for the entity.
3345        my $entityFields = $self->GetFieldTable($targetEntity);
3346        # The field table is a hash. The hash key is the field name. The hash value is a structure.
3347        # For the entity fields, the key aspect of the target structure is that the {relation} value
3348        # must match the entity name.
3349        my @fieldList = map { "$targetEntity($_)" } grep { $entityFields->{$_}->{relation} eq $targetEntity }
3350                            keys %{$entityFields};
3351        # Push the fields found onto the return variable.
3352        push @retVal, sort @fieldList;
3353        # Get the field table for the relationship.
3354        my $relationshipFields = $self->GetFieldTable($relationship);
3355        # Here we have a different rule. We want all the fields other than "from-link" and "to-link".
3356        # This may end up being an empty set.
3357        my @fieldList2 = map { "$relationship($_)" } grep { $_ ne "from-link" && $_ ne "to-link" }
3358                            keys %{$relationshipFields};
3359        # Push these onto the return list.
3360        push @retVal, sort @fieldList2;
3361        # Return the result.
3362        return @retVal;
3363    }
3364    
3365    =head3 FindColumn
3366    
3367    C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>
3368    
3369    Return the location a desired column in a data mining header line. The data
3370    mining header line is a tab-separated list of column names. The column
3371    identifier is either the numerical index of a column or the actual column
3372    name.
3373    
3374    =over 4
3375    
3376    =item headerLine
3377    
3378    The header line from a data mining command, which consists of a tab-separated
3379    list of column names.
3380    
3381    =item columnIdentifier
3382    
3383    Either the ordinal number of the desired column (1-based), or the name of the
3384    desired column.
3385    
3386    =item RETURN
3387    
3388    Returns the array index (0-based) of the desired column.
3389    
3390    =back
3391    
3392    =cut
3393    
3394    sub FindColumn {
3395        # Get the parameters.
3396        my ($headerLine, $columnIdentifier) = @_;
3397        # Declare the return variable.
3398        my $retVal;
3399        # Split the header line into column names.
3400        my @headers = ParseColumns($headerLine);
3401        # Determine whether we have a number or a name.
3402        if ($columnIdentifier =~ /^\d+$/) {
3403            # Here we have a number. Subtract 1 and validate the result.
3404            $retVal = $columnIdentifier - 1;
3405            if ($retVal < 0 || $retVal > $#headers) {
3406                Confess("Invalid column identifer \"$columnIdentifier\": value out of range.");
3407            }
3408        } else {
3409            # Here we have a name. We need to find it in the list.
3410            for (my $i = 0; $i <= $#headers && ! defined($retVal); $i++) {
3411                if ($headers[$i] eq $columnIdentifier) {
3412                    $retVal = $i;
3413                }
3414            }
3415            if (! defined($retVal)) {
3416                Confess("Invalid column identifier \"$columnIdentifier\": value not found.");
3417            }
3418        }
3419        # Return the result.
3420        return $retVal;
3421    }
3422    
3423    =head3 ParseColumns
3424    
3425    C<< my @columns = ERDB::ParseColumns($line); >>
3426    
3427    Convert the specified data line to a list of columns.
3428    
3429    =over 4
3430    
3431    =item line
3432    
3433    A data mining input, consisting of a tab-separated list of columns terminated by a
3434    new-line.
3435    
3436  Type name of the object whose fields are being generated.  =item RETURN
3437    
3438    Returns a list consisting of the column values.
3439    
3440    =back
3441    
3442    =cut
3443    
3444    sub ParseColumns {
3445        # Get the parameters.
3446        my ($line) = @_;
3447        # Chop off the line-end.
3448        chomp $line;
3449        # Split it into a list.
3450        my @retVal = split(/\t/, $line);
3451        # Return the result.
3452        return @retVal;
3453    }
3454    
3455    =head2 Virtual Methods
3456    
3457    =head3 CleanKeywords
3458    
3459    C<< my $cleanedString = $erdb->CleanKeywords($searchExpression); >>
3460    
3461    Clean up a search expression or keyword list. This is a virtual method that may
3462    be overridden by the subclass. The base-class method removes extra spaces
3463    and converts everything to lower case.
3464    
3465    =over 4
3466    
3467    =item searchExpression
3468    
3469    Search expression or keyword list to clean. Note that a search expression may
3470    contain boolean operators which need to be preserved. This includes leading
3471    minus signs.
3472    
3473    =item RETURN
3474    
3475    Cleaned expression or keyword list.
3476    
3477    =back
3478    
3479    =cut
3480    
3481    sub CleanKeywords {
3482        # Get the parameters.
3483        my ($self, $searchExpression) = @_;
3484        # Lower-case the expression and copy it into the return variable. Note that we insure we
3485        # don't accidentally end up with an undefined value.
3486        my $retVal = lc($searchExpression || "");
3487        # Remove extra spaces.
3488        $retVal =~ s/\s+/ /g;
3489        $retVal =~ s/(^\s+)|(\s+$)//g;
3490        # Return the result.
3491        return $retVal;
3492    }
3493    
3494  =item values (optional)  =head3 GetSourceObject
3495    
3496  Reference to a value structure from which additional values can be taken.  C<< my $source = $erdb->GetSourceObject($entityName); >>
3497    
3498  =item from (optiona)  Return the object to be used in loading special attributes of the specified entity. The
3499    algorithm for loading special attributes is stored in the C<DataGen> elements of the
3500    XML
3501    
3502  Reference to the source entity instance if relationship data is being generated.  =head2 Internal Utility Methods
3503    
3504    =head3 _RelationMap
3505    
3506    C<< my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef); >>
3507    
3508    Create the relation map for an SQL query. The relation map is used by B<DBObject>
3509    to determine how to interpret the results of the query.
3510    
3511    =over 4
3512    
3513    =item mappedNameHashRef
3514    
3515    Reference to a hash that maps modified object names to real object names.
3516    
3517  =item to (optional)  =item mappedNameListRef
3518    
3519  Reference to the target entity instance if relationship data is being generated.  Reference to a list of modified object names in the order they appear in the
3520    SELECT list.
3521    
3522    =item RETURN
3523    
3524    Returns a list of 2-tuples. Each tuple consists of an object name as used in the
3525    query followed by the actual name of that object. This enables the B<DBObject> to
3526    determine the order of the tables in the query and which object name belongs to each
3527    mapped object name. Most of the time these two values are the same; however, if a
3528    relation occurs twice in the query, the relation name in the field list and WHERE
3529    clause will use a mapped name (generally the actual relation name with a numeric
3530    suffix) that does not match the actual relation name.
3531    
3532  =back  =back
3533    
3534  =cut  =cut
3535    
3536  sub _GenerateFields {  sub _RelationMap {
3537      # Get the parameters.      # Get the parameters.
3538      my ($this, $fields, $type, $values, $from, $to) = @_;      my ($mappedNameHashRef, $mappedNameListRef) = @_;
3539      # Sort the field names by pass number.      # Declare the return variable.
3540      my @fieldNames = sort { $fields->{$a}->{DataGen}->{pass} <=> $fields->{$b}->{DataGen}->{pass} } keys %{$fields};      my @retVal = ();
3541      # Loop through the field names, generating data.      # Build the map.
3542      for my $name (@fieldNames) {      for my $mappedName (@{$mappedNameListRef}) {
3543          # Only proceed if this field needs to be generated.          push @retVal, [$mappedName, $mappedNameHashRef->{$mappedName}];
3544          if (!exists $this->{$name}) {      }
3545              # Get this field's data generation descriptor.      # Return it.
3546              my $fieldDescriptor = $fields->{$name};      return @retVal;
3547              my $data = $fieldDescriptor->{DataGen};  }
3548              # Get the code to generate the field value.  
3549              my $codeString = $data->{content};  
3550              # Determine whether or not this field is in the primary relation.  =head3 _SetupSQL
3551              if ($fieldDescriptor->{relation} eq $type) {  
3552                  # 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
3553                  # a scalar.  build an SQL statement. This method takes in a reference to a list of object names
3554                  $this->{$name} = eval($codeString);  and a filter clause. It will return a corrected filter clause, a list of mapped
3555    names and the mapped name hash.
3556    
3557    This is an instance method.
3558    
3559    =over 4
3560    
3561    =item objectNames
3562    
3563    Reference to a list of the object names to be included in the query.
3564    
3565    =item filterClause
3566    
3567    A string containing the WHERE clause for the query (without the C<WHERE>) and also
3568    optionally the C<ORDER BY> and C<LIMIT> clauses.
3569    
3570    =item matchClause
3571    
3572    An optional full-text search clause. If specified, it will be inserted at the
3573    front of the WHERE clause. It should already be SQL-formatted; that is, the
3574    field names should be in the form I<table>C<.>I<fieldName>.
3575    
3576    =item RETURN
3577    
3578    Returns a three-element list. The first element is the SQL statement suffix, beginning
3579    with the FROM clause. The second element is a reference to a list of the names to be
3580    used in retrieving the fields. The third element is a hash mapping the names to the
3581    objects they represent.
3582    
3583    =back
3584    
3585    =cut
3586    
3587    sub _SetupSQL {
3588        my ($self, $objectNames, $filterClause, $matchClause) = @_;
3589        # Adjust the list of object names to account for multiple occurrences of the
3590        # same object. We start with a hash table keyed on object name that will
3591        # return the object suffix. The first time an object is encountered it will
3592        # not be found in the hash. The next time the hash will map the object name
3593        # to 2, then 3, and so forth.
3594        my %objectHash = ();
3595        # This list will contain the object names as they are to appear in the
3596        # FROM list.
3597        my @fromList = ();
3598        # This list contains the suffixed object name for each object. It is exactly
3599        # parallel to the list in the $objectNames parameter.
3600        my @mappedNameList = ();
3601        # Finally, this hash translates from a mapped name to its original object name.
3602        my %mappedNameHash = ();
3603        # Now we create the lists. Note that for every single name we push something into
3604        # @fromList and @mappedNameList. This insures that those two arrays are exactly
3605        # parallel to $objectNames.
3606        for my $objectName (@{$objectNames}) {
3607            # Get the next suffix for this object.
3608            my $suffix = $objectHash{$objectName};
3609            if (! $suffix) {
3610                # Here we are seeing the object for the first time. The object name
3611                # is used as is.
3612                push @mappedNameList, $objectName;
3613                push @fromList, $objectName;
3614                $mappedNameHash{$objectName} = $objectName;
3615                # Denote the next suffix will be 2.
3616                $objectHash{$objectName} = 2;
3617            } else {
3618                # Here we've seen the object before. We construct a new name using
3619                # the suffix from the hash and update the hash.
3620                my $mappedName = "$objectName$suffix";
3621                $objectHash{$objectName} = $suffix + 1;
3622                # The FROM list has the object name followed by the mapped name. This
3623                # tells SQL it's still the same table, but we're using a different name
3624                # for it to avoid confusion.
3625                push @fromList, "$objectName $mappedName";
3626                # The mapped-name list contains the real mapped name.
3627                push @mappedNameList, $mappedName;
3628                # Finally, enable us to get back from the mapped name to the object name.
3629                $mappedNameHash{$mappedName} = $objectName;
3630            }
3631        }
3632        # Begin the SELECT suffix. It starts with
3633        #
3634        # FROM name1, name2, ... nameN
3635        #
3636        my $suffix = "FROM " . join(', ', @fromList);
3637        # Now for the WHERE. First, we need a place for the filter string.
3638        my $filterString = "";
3639        # We will also keep a list of conditions to add to the WHERE clause in order to link
3640        # entities and relationships as well as primary relations to secondary ones.
3641        my @joinWhere = ();
3642        # Check for a filter clause.
3643        if ($filterClause) {
3644            # Here we have one, so we convert its field names and add it to the query. First,
3645            # We create a copy of the filter string we can work with.
3646            $filterString = $filterClause;
3647            # Next, we sort the object names by length. This helps protect us from finding
3648            # object names inside other object names when we're doing our search and replace.
3649            my @sortedNames = sort { length($b) - length($a) } @mappedNameList;
3650            # The final preparatory step is to create a hash table of relation names. The
3651            # table begins with the relation names already in the SELECT command. We may
3652            # need to add relations later if there is filtering on a field in a secondary
3653            # relation. The secondary relations are the ones that contain multiply-
3654            # occurring or optional fields.
3655            my %fromNames = map { $_ => 1 } @sortedNames;
3656            # We are ready to begin. We loop through the object names, replacing each
3657            # object name's field references by the corresponding SQL field reference.
3658            # Along the way, if we find a secondary relation, we will need to add it
3659            # to the FROM clause.
3660            for my $mappedName (@sortedNames) {
3661                # Get the length of the object name plus 2. This is the value we add to the
3662                # size of the field name to determine the size of the field reference as a
3663                # whole.
3664                my $nameLength = 2 + length $mappedName;
3665                # Get the real object name for this mapped name.
3666                my $objectName = $mappedNameHash{$mappedName};
3667                Trace("Processing $mappedName for object $objectName.") if T(4);
3668                # Get the object's field list.
3669                my $fieldList = $self->GetFieldTable($objectName);
3670                # Find the field references for this object.
3671                while ($filterString =~ m/$mappedName\(([^)]*)\)/g) {
3672                    # At this point, $1 contains the field name, and the current position
3673                    # is set immediately after the final parenthesis. We pull out the name of
3674                    # the field and the position and length of the field reference as a whole.
3675                    my $fieldName = $1;
3676                    my $len = $nameLength + length $fieldName;
3677                    my $pos = pos($filterString) - $len;
3678                    # Insure the field exists.
3679                    if (!exists $fieldList->{$fieldName}) {
3680                        Confess("Field $fieldName not found for object $objectName.");
3681                    } else {
3682                        Trace("Processing $fieldName at position $pos.") if T(4);
3683                        # Get the field's relation.
3684                        my $relationName = $fieldList->{$fieldName}->{relation};
3685                        # Now we have a secondary relation. We need to insure it matches the
3686                        # mapped name of the primary relation. First we peel off the suffix
3687                        # from the mapped name.
3688                        my $mappingSuffix = substr $mappedName, length($objectName);
3689                        # Put the mapping suffix onto the relation name to get the
3690                        # mapped relation name.
3691                        my $mappedRelationName = "$relationName$mappingSuffix";
3692                        # Insure the relation is in the FROM clause.
3693                        if (!exists $fromNames{$mappedRelationName}) {
3694                            # Add the relation to the FROM clause.
3695                            if ($mappedRelationName eq $relationName) {
3696                                # The name is un-mapped, so we add it without
3697                                # any frills.
3698                                $suffix .= ", $relationName";
3699                                push @joinWhere, "$objectName.id = $relationName.id";
3700                            } else {
3701                                # Here we have a mapping situation.
3702                                $suffix .= ", $relationName $mappedRelationName";
3703                                push @joinWhere, "$mappedRelationName.id = $mappedName.id";
3704                            }
3705                            # Denote we have this relation available for future fields.
3706                            $fromNames{$mappedRelationName} = 1;
3707                        }
3708                        # Form an SQL field reference from the relation name and the field name.
3709                        my $sqlReference = "$mappedRelationName." . _FixName($fieldName);
3710                        # Put it into the filter string in place of the old value.
3711                        substr($filterString, $pos, $len) = $sqlReference;
3712                        # Reposition the search.
3713                        pos $filterString = $pos + length $sqlReference;
3714                    }
3715                }
3716            }
3717        }
3718        # The next step is to join the objects together. We only need to do this if there
3719        # is more than one object in the object list. We start with the first object and
3720        # run through the objects after it. Note also that we make a safety copy of the
3721        # list before running through it, because we shift off the first object before
3722        # processing the rest.
3723        my @mappedObjectList = @mappedNameList;
3724        my $lastMappedObject = shift @mappedObjectList;
3725        # Get the join table.
3726        my $joinTable = $self->{_metaData}->{Joins};
3727        # Loop through the object list.
3728        for my $thisMappedObject (@mappedObjectList) {
3729            # Look for a join using the real object names.
3730            my $lastObject = $mappedNameHash{$lastMappedObject};
3731            my $thisObject = $mappedNameHash{$thisMappedObject};
3732            my $joinKey = "$lastObject/$thisObject";
3733            if (!exists $joinTable->{$joinKey}) {
3734                # Here there's no join, so we throw an error.
3735                Confess("No join exists to connect from $lastMappedObject to $thisMappedObject.");
3736              } else {              } else {
3737                  # Here we have a secondary relation field. Create a null list              # Get the join clause.
3738                  # and push the desired number of field values onto it.              my $unMappedJoin = $joinTable->{$joinKey};
3739                  my @fieldValues = ();              # Fix the names.
3740                  my $count = IntGen(0,$data->{testCount});              $unMappedJoin =~ s/$lastObject/$lastMappedObject/;
3741                  for (my $i = 0; $i < $count; $i++) {              $unMappedJoin =~ s/$thisObject/$thisMappedObject/;
3742                      my $newValue = eval($codeString);              push @joinWhere, $unMappedJoin;
3743                      push @fieldValues, $newValue;              # Save this object as the last object for the next iteration.
3744                $lastMappedObject = $thisMappedObject;
3745            }
3746                  }                  }
3747                  # Store the value list in the main hash.      # Now we need to handle the whole ORDER BY / LIMIT thing. The important part
3748                  $this->{$name} = \@fieldValues;      # here is we want the filter clause to be empty if there's no WHERE filter.
3749        # We'll put the ORDER BY / LIMIT clauses in the following variable.
3750        my $orderClause = "";
3751        # This is only necessary if we have a filter string in which the ORDER BY
3752        # and LIMIT clauses can live.
3753        if ($filterString) {
3754            # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy
3755            # operator so that we find the first occurrence of either verb.
3756            if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {
3757                # Here we have an ORDER BY or LIMIT verb. Split it off of the filter string.
3758                my $pos = pos $filterString;
3759                $orderClause = $2 . substr($filterString, $pos);
3760                $filterString = $1;
3761            }
3762        }
3763        # All the things that are supposed to be in the WHERE clause of the
3764        # SELECT command need to be put into @joinWhere so we can string them
3765        # together. We begin with the match clause. This is important,
3766        # because the match clause's parameter mark must precede any parameter
3767        # marks in the filter string.
3768        if ($matchClause) {
3769            push @joinWhere, $matchClause;
3770        }
3771        # Add the filter string. We put it in parentheses to avoid operator
3772        # precedence problems with the match clause or the joins.
3773        if ($filterString) {
3774            Trace("Filter string is \"$filterString\".") if T(4);
3775            push @joinWhere, "($filterString)";
3776        }
3777        # String it all together into a big filter clause.
3778        if (@joinWhere) {
3779            $suffix .= " WHERE " . join(' AND ', @joinWhere);
3780        }
3781        # Add the sort or limit clause (if any).
3782        if ($orderClause) {
3783            $suffix .= " $orderClause";
3784              }              }
3785        # Return the suffix, the mapped name list, and the mapped name hash.
3786        return ($suffix, \@mappedNameList, \%mappedNameHash);
3787          }          }
3788    
3789    =head3 _GetStatementHandle
3790    
3791    This method will prepare and execute an SQL query, returning the statement handle.
3792    The main reason for doing this here is so that everybody who does SQL queries gets
3793    the benefit of tracing.
3794    
3795    This is an instance method.
3796    
3797    =over 4
3798    
3799    =item command
3800    
3801    Command to prepare and execute.
3802    
3803    =item params
3804    
3805    Reference to a list of the values to be substituted in for the parameter marks.
3806    
3807    =item RETURN
3808    
3809    Returns a prepared and executed statement handle from which the caller can extract
3810    results.
3811    
3812    =back
3813    
3814    =cut
3815    
3816    sub _GetStatementHandle {
3817        # Get the parameters.
3818        my ($self, $command, $params) = @_;
3819        # Trace the query.
3820        Trace("SQL query: $command") if T(SQL => 3);
3821        Trace("PARMS: '" . (join "', '", @{$params}) . "'") if (T(SQL => 4) && (@{$params} > 0));
3822        # Get the database handle.
3823        my $dbh = $self->{_dbh};
3824        # Prepare the command.
3825        my $sth = $dbh->prepare_command($command);
3826        # Execute it with the parameters bound in.
3827        $sth->execute(@{$params}) || Confess("SELECT error:  " . $sth->errstr());
3828        # Return the statement handle.
3829        return $sth;
3830      }      }
3831    
3832    =head3 _GetLoadStats
3833    
3834    Return a blank statistics object for use by the load methods.
3835    
3836    This is a static method.
3837    
3838    =cut
3839    
3840    sub _GetLoadStats{
3841        return Stats->new();
3842  }  }
3843    
3844  =head3 DumpRelation  =head3 _DumpRelation
3845    
3846  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.
3847    
3848  This is an instance method.  This is an instance method.
3849    
# Line 1994  Line 3891 
3891      close DTXOUT;      close DTXOUT;
3892  }  }
3893    
3894  =head3 GetStructure  =head3 _GetStructure
3895    
3896  Get the data structure for a specified entity or relationship.  Get the data structure for a specified entity or relationship.
3897    
# Line 2033  Line 3930 
3930      return $retVal;      return $retVal;
3931  }  }
3932    
3933  =head3 GetRelationTable  
3934    
3935    =head3 _GetRelationTable
3936    
3937  Get the list of relations for a specified entity or relationship.  Get the list of relations for a specified entity or relationship.
3938    
# Line 2062  Line 3961 
3961      return $objectData->{Relations};      return $objectData->{Relations};
3962  }  }
3963    
3964  =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  
3965    
3966  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
3967  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 2118  Line 3988 
3988          for my $object (values %{$metadata->{$section}}) {          for my $object (values %{$metadata->{$section}}) {
3989              # Loop through the object's fields.              # Loop through the object's fields.
3990              for my $fieldName (keys %{$object->{Fields}}) {              for my $fieldName (keys %{$object->{Fields}}) {
3991                  # Now we make some initial validations.                  # If this field name is invalid, set the return value to zero
3992                  if ($fieldName =~ /--/) {                  # so we know we encountered an error.
3993                      # Here we have a doubled minus sign.                  if (! ValidateFieldName($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";  
3994                          $retVal = 0;                          $retVal = 0;
3995                      }                      }
3996                  }                  }
3997              }              }
3998          }          }
     }  
3999      # If an error was found, fail.      # If an error was found, fail.
4000      if ($retVal  == 0) {      if ($retVal  == 0) {
4001          Confess("Errors found in field names.");          Confess("Errors found in field names.");
4002      }      }
4003  }  }
4004    
4005  =head3 LoadRelation  =head3 _LoadRelation
4006    
4007  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
4008  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 2206  Line 4062 
4062      return $retVal;      return $retVal;
4063  }  }
4064    
4065  =head3 LoadMetaData  
4066    =head3 _LoadMetaData
4067    
4068  This method loads the data describing this database from an XML file into a metadata structure.  This method loads the data describing this database from an XML file into a metadata structure.
4069  The resulting structure is a set of nested hash tables containing all the information needed to  The resulting structure is a set of nested hash tables containing all the information needed to
# Line 2231  Line 4088 
4088  sub _LoadMetaData {  sub _LoadMetaData {
4089      # Get the parameters.      # Get the parameters.
4090      my ($filename) = @_;      my ($filename) = @_;
4091      Trace("Reading Sprout DBD from $filename.") if T(2);      Trace("Reading DBD from $filename.") if T(2);
4092      # Slurp the XML file into a variable. Extensive use of options is used to insure we      # Slurp the XML file into a variable. Extensive use of options is used to insure we
4093      # get the exact structure we want.      # get the exact structure we want.
4094      my $metadata = XML::Simple::XMLin($filename,      my $metadata = ReadMetaXML($filename);
                                       GroupTags => { Relationships => 'Relationship',  
                                                      Entities => 'Entity',  
                                                      Fields => 'Field',  
                                                      Indexes => 'Index',  
                                                      IndexFields => 'IndexField'},  
                                       KeyAttr => { Relationship => 'name',  
                                                    Entity => 'name',  
                                                    Field => 'name'},  
                                       ForceArray => ['Field', 'Index', 'IndexField'],  
                                       ForceContent => 1,  
                                       NormalizeSpace => 2  
                                       );  
     Trace("XML metadata loaded from file $filename.") if T(1);  
4095      # Before we go any farther, we need to validate the field and object names. If an error is found,      # Before we go any farther, we need to validate the field and object names. If an error is found,
4096      # the method below will fail.      # the method below will fail.
4097      _ValidateFieldNames($metadata);      _ValidateFieldNames($metadata);
# Line 2377  Line 4221 
4221              my $count = 0;              my $count = 0;
4222              for my $index (@{$indexList}) {              for my $index (@{$indexList}) {
4223                  # Add this index to the index table.                  # Add this index to the index table.
4224                  _AddIndex("idx$relationName$count", $relation, $index);                  _AddIndex("idx$count", $relation, $index);
4225                  # Increment the counter so that the next index has a different name.                  # Increment the counter so that the next index has a different name.
4226                  $count++;                  $count++;
4227              }              }
# Line 2444  Line 4288 
4288              # Determine if this relationship has our entity in one of its link fields.              # Determine if this relationship has our entity in one of its link fields.
4289              my $fromEntity = $relationship->{from};              my $fromEntity = $relationship->{from};
4290              my $toEntity = $relationship->{to};              my $toEntity = $relationship->{to};
4291              Trace("Join check for relationship $relationshipName from $fromEntity to $toEntity.") if T(4);              Trace("Join check for relationship $relationshipName from $fromEntity to $toEntity.") if T(Joins => 4);
4292              if ($fromEntity eq $entityName) {              if ($fromEntity eq $entityName) {
4293                  if ($toEntity eq $entityName) {                  if ($toEntity eq $entityName) {
4294                      # Here the relationship is recursive.                      # Here the relationship is recursive.
# Line 2533  Line 4377 
4377      return $metadata;      return $metadata;
4378  }  }
4379    
4380  =head3 CreateRelationshipIndex  =head3 _CreateRelationshipIndex
4381    
4382  Create an index for a relationship's relation.  Create an index for a relationship's relation.
4383    
# Line 2575  Line 4419 
4419          $newIndex->{Unique} = 'true';          $newIndex->{Unique} = 'true';
4420      }      }
4421      # Add the index to the relation.      # Add the index to the relation.
4422      _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);      _AddIndex("idx$indexKey", $relationStructure, $newIndex);
4423  }  }
4424    
4425  =head3 AddIndex  =head3 _AddIndex
4426    
4427  Add an index to a relation structure.  Add an index to a relation structure.
4428    
# Line 2624  Line 4468 
4468      $relationStructure->{Indexes}->{$indexName} = $newIndex;      $relationStructure->{Indexes}->{$indexName} = $newIndex;
4469  }  }
4470    
4471  =head3 FixupFields  =head3 _FixupFields
4472    
4473  This method fixes the field list for an entity or relationship. It will add the caller-specified  This method fixes the field list for an entity or relationship. It will add the caller-specified
4474  relation name to fields that do not have a name and set the C<PrettySort> value as specified.  relation name to fields that do not have a name and set the C<PrettySort> value as specified.
# Line 2662  Line 4506 
4506          # Here it doesn't, so we create a new one.          # Here it doesn't, so we create a new one.
4507          $structure->{Fields} = { };          $structure->{Fields} = { };
4508      } else {      } else {
4509          # Here we have a field list. Loop through its fields.          # Here we have a field list. We need to track the searchable fields, so we
4510            # create a list for stashing them.
4511            my @textFields = ();
4512            # Loop through the fields.
4513          my $fieldStructures = $structure->{Fields};          my $fieldStructures = $structure->{Fields};
4514          for my $fieldName (keys %{$fieldStructures}) {          for my $fieldName (keys %{$fieldStructures}) {
4515              Trace("Processing field $fieldName of $defaultRelationName.") if T(4);              Trace("Processing field $fieldName of $defaultRelationName.") if T(4);
# Line 2671  Line 4518 
4518              my $type = $fieldData->{type};              my $type = $fieldData->{type};
4519              # Plug in a relation name if it is needed.              # Plug in a relation name if it is needed.
4520              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });
4521              # Plug in a data generator if we need one.              # Check for searchability.
4522              if (!exists $fieldData->{DataGen}) {              if ($fieldData->{searchable}) {
4523                  # The data generator will use the default for the field's type.                  # Only allow this for a primary relation.
4524                  $fieldData->{DataGen} = { content => $TypeTable{$type}->{dataGen} };                  if ($fieldData->{relation} ne $defaultRelationName) {
4525                        Confess("Field $fieldName of $defaultRelationName is in secondary relations and cannot be searchable.");
4526                    } else {
4527                        push @textFields, $fieldName;
4528                    }
4529              }              }
             # Plug in the defaults for the optional data generation parameters.  
             Tracer::MergeOptions($fieldData->{DataGen}, { testCount => 1, pass => 0 });  
4530              # Add the PrettySortValue.              # Add the PrettySortValue.
4531              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);
4532          }          }
4533            # If there are searchable fields, remember the fact.
4534            if (@textFields) {
4535                $structure->{searchFields} = \@textFields;
4536            }
4537      }      }
4538  }  }
4539    
4540  =head3 FixName  =head3 _FixName
4541    
4542  Fix the incoming field name so that it is a legal SQL column name.  Fix the incoming field name so that it is a legal SQL column name.
4543    
# Line 2713  Line 4566 
4566      return $fieldName;      return $fieldName;
4567  }  }
4568    
4569  =head3 FixNames  =head3 _FixNames
4570    
4571  Fix all the field names in a list.  Fix all the field names in a list.
4572    
# Line 2744  Line 4597 
4597      return @result;      return @result;
4598  }  }
4599    
4600  =head3 AddField  =head3 _AddField
4601    
4602  Add a field to a field list.  Add a field to a field list.
4603    
# Line 2779  Line 4632 
4632      $fieldList->{$fieldName} = $fieldStructure;      $fieldList->{$fieldName} = $fieldStructure;
4633  }  }
4634    
4635  =head3 ReOrderRelationTable  =head3 _ReOrderRelationTable
4636    
4637  This method will take a relation table and re-sort it according to the implicit ordering of the  This method will take a relation table and re-sort it according to the implicit ordering of the
4638  C<PrettySort> property. Instead of a hash based on field names, it will return a list of fields.  C<PrettySort> property. Instead of a hash based on field names, it will return a list of fields.
# Line 2840  Line 4693 
4693    
4694  }  }
4695    
4696  =head3 IsPrimary  =head3 _IsPrimary
4697    
4698  Return TRUE if a specified relation is a primary relation, else FALSE. A relation is primary  Return TRUE if a specified relation is a primary relation, else FALSE. A relation is primary
4699  if it has the same name as an entity or relationship.  if it has the same name as an entity or relationship.
# Line 2876  Line 4729 
4729      return $retVal;      return $retVal;
4730  }  }
4731    
4732  =head3 FindRelation  =head3 _FindRelation
4733    
4734  Return the descriptor for the specified relation.  Return the descriptor for the specified relation.
4735    
# Line 2907  Line 4760 
4760    
4761  =head2 HTML Documentation Utility Methods  =head2 HTML Documentation Utility Methods
4762    
4763  =head3 ComputeRelationshipSentence  =head3 _ComputeRelationshipSentence
4764    
4765  The relationship sentence consists of the relationship name between the names of the  The relationship sentence consists of the relationship name between the names of the
4766  two related entities and an arity indicator.  two related entities and an arity indicator.
# Line 2945  Line 4798 
4798      return $result;      return $result;
4799  }  }
4800    
4801  =head3 ComputeRelationshipHeading  =head3 _ComputeRelationshipHeading
4802    
4803  The relationship heading is the L<relationship sentence|/ComputeRelationshipSentence> with the entity  The relationship heading is the L<relationship sentence|/ComputeRelationshipSentence> with the entity
4804  names hyperlinked to the appropriate entity sections of the document.  names hyperlinked to the appropriate entity sections of the document.
# Line 2982  Line 4835 
4835      return $result;      return $result;
4836  }  }
4837    
4838  =head3 ShowRelationTable  =head3 _ShowRelationTable
4839    
4840  Generate the HTML string for a particular relation. The relation's data will be formatted as an HTML  Generate the HTML string for a particular relation. The relation's data will be formatted as an HTML
4841  table with three columns-- the field name, the field type, and the field description.  table with three columns-- the field name, the field type, and the field description.
# Line 3032  Line 4885 
4885          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";
4886          # Add any note text.          # Add any note text.
4887          if (my $note = $indexData->{Notes}) {          if (my $note = $indexData->{Notes}) {
4888              $htmlString .= "<li>" . _HTMLNote($note->{content}) . "</li>\n";              $htmlString .= "<li>" . HTMLNote($note->{content}) . "</li>\n";
4889          }          }
4890          # Add the fiield list.          # Add the fiield list.
4891          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";
# Line 3043  Line 4896 
4896      $htmlString .= "</ul>\n";      $htmlString .= "</ul>\n";
4897  }  }
4898    
4899  =head3 OpenFieldTable  =head3 _OpenFieldTable
4900    
4901  This method creates the header string for the field table generated by L</ShowMetaData>.  This method creates the header string for the field table generated by L</ShowMetaData>.
4902    
# Line 3068  Line 4921 
4921      return _OpenTable($tablename, 'Field', 'Type', 'Description');      return _OpenTable($tablename, 'Field', 'Type', 'Description');
4922  }  }
4923    
4924  =head3 OpenTable  =head3 _OpenTable
4925    
4926  This method creates the header string for an HTML table.  This method creates the header string for an HTML table.
4927    
# Line 3108  Line 4961 
4961      return $htmlString;      return $htmlString;
4962  }  }
4963    
4964  =head3 CloseTable  =head3 _CloseTable
4965    
4966  This method returns the HTML for closing a table.  This method returns the HTML for closing a table.
4967    
# Line 3120  Line 4973 
4973      return "</table></p>\n";      return "</table></p>\n";
4974  }  }
4975    
4976  =head3 ShowField  =head3 _ShowField
4977    
4978  This method returns the HTML for displaying a row of field information in a field table.  This method returns the HTML for displaying a row of field information in a field table.
4979    
# Line 3147  Line 5000 
5000      my $htmlString = "<tr><th align=\"left\">$fieldData->{name}</th><td>$fieldData->{type}</td>";      my $htmlString = "<tr><th align=\"left\">$fieldData->{name}</th><td>$fieldData->{type}</td>";
5001      # If we have content, add it as a third column.      # If we have content, add it as a third column.
5002      if (exists $fieldData->{Notes}) {      if (exists $fieldData->{Notes}) {
5003          $htmlString .= "<td>" . _HTMLNote($fieldData->{Notes}->{content}) . "</td>";          $htmlString .= "<td>" . HTMLNote($fieldData->{Notes}->{content}) . "</td>";
5004      }      }
5005      # Close off the row.      # Close off the row.
5006      $htmlString .= "</tr>\n";      $htmlString .= "</tr>\n";
# Line 3155  Line 5008 
5008      return $htmlString;      return $htmlString;
5009  }  }
5010    
 =head3 HTMLNote  
   
 Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes  
 supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.  
 Except for C<[p]>, all the codes are closed by slash-codes. So, for  
 example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.  
   
 This is a static method.  
   
 =over 4  
   
 =item dataString  
   
 String to convert to HTML.  
   
 =item RETURN  
   
 An HTML string derived from the input string.  
   
 =back  
   
 =cut  
   
 sub _HTMLNote {  
     # Get the parameter.  
     my ($dataString) = @_;  
     # Substitute the codes.  
     $dataString =~ s!\[(/?[bi])\]!<$1>!g;  
     $dataString =~ s!\[p\]!</p><p>!g;  
     # Return the result.  
     return $dataString;  
 }  
   
 =head2 Data Generation Utilities  
   
 =head3 IntGen  
   
 C<< my $integer = IntGen($min, $max); >>  
   
 Returns a random number between the specified minimum and maximum (inclusive).  
   
 =over 4  
   
 =item min  
   
 Minimum permissible return value.  
   
 =item max  
   
 Maximum permissible return value.  
   
 =item RETURN  
   
 Returns a value no lower than the minimum and no greater than the maximum.  
   
 =back  
   
 =cut  
   
 sub IntGen {  
     # Get the parameters.  
     my ($min, $max) = @_;  
     # Determine the range of possible values. Note we put some space well above the  
     # maximum value to give it a fighting chance of apppearing in the list.  
     my $span = $max + 0.99 - $min;  
     # Create an integer in the range.  
     my $retVal = $min + int(rand($span));  
     # Return the result.  
     return $retVal;  
 }  
   
 =head3 RandChar  
   
 C<< my $char = RandChar($sourceString); >>  
   
 Select a random character from a string.  
   
 =over 4  
   
 =item sourceString  
   
 String from which the random character should be selected.  
   
 =item RETURN  
   
 Returns a single character from the incoming string.  
   
 =back  
   
 =cut  
   
 sub RandChar {  
     # Get the parameter.  
     my ($sourceString) = @_;  
     # Select a random character.  
     my $retVal = IntGen(0, (length $sourceString) - 1);  
     # Return it.  
     return substr($sourceString, $retVal, 1);  
 }  
   
 =head3 RandChars  
   
 C<< my $string = RandChars($sourceString, $length); >>  
   
 Create a string from characters taken from a source string.  
   
 =over 4  
   
 =item sourceString  
   
 String from which the random characters should be selected.  
   
 =item length  
   
 Number of characters to put in the output string.  
   
 =item RETURN  
   
 Returns a string of the specified length consisting of characters taken from the  
 source string.  
   
 =back  
   
 =cut  
   
 sub RandChars {  
     # Get the parameters.  
     my ($sourceString, $length) = @_;  
     # Call RandChar repeatedly to generate the string.  
     my $retVal = "";  
     for (my $i = 0; $i < $length; $i++) {  
         $retVal .= RandChar($sourceString);  
     }  
     # Return the result.  
     return $retVal;  
 }  
   
 =head3 RandParam  
   
 C<< my $value = RandParam($parm1, $parm2, ... $parmN); >>  
   
 Return a randomly-selected value from the parameter list.  
   
 =over 4  
   
 =item parm1, parm2, ... parmN  
   
 List of values of which one will be selected.  
   
 =item RETURN  
   
 Returns a randomly-chosen value from the specified list.  
   
 =back  
   
 =cut  
   
 sub RandParam {  
     # Get the parameter.  
     my @parms = @_;  
     # Choose a random parameter from the list.  
     my $chosenIndex = IntGen(0, $#parms);  
     return $parms[$chosenIndex];  
 }  
   
 =head3 StringGen  
   
 C<< my $string = StringGen($pattern1, $pattern2, ... $patternN); >>  
   
 Returns a random string derived from a randomly-chosen format pattern. The pattern  
 can either be a number (indicating the number of characters desired, or the letter  
 C<P> followed by a picture. The picture should contain C<A> when a letter is desired,  
 C<9> when a digit is desired, C<V> when a vowel is desired, C<K> when a consonant is  
 desired, and C<X> when a letter or a digit is desired. Any other character will be  
 translated as a literal.  
   
 =over 4  
   
 =item pattern1, pattern2, ... patternN  
   
 List of patterns to be used to generate string values.  
   
 =item RETURN  
   
 A single string generated from a pattern.  
   
 =back  
   
 =cut  
   
 sub StringGen {  
     # Get the parameters.  
     my @patterns = @_;  
     # Choose the appropriate pattern.  
     my $chosenPattern = RandParam(@patterns);  
     # Declare the return variable.  
     my $retVal = "";  
     # Determine whether this is a count or a picture pattern.  
     if ($chosenPattern =~ m/^\d+/) {  
         # Here we have a count. Get the string of source characters.  
         my $letterString = $PictureTable{'X'};  
         my $stringLen = length $letterString;  
         # Save the number of characters we have to generate.  
         my $charsLeft = $chosenPattern;  
         # Loop until the return variable is full.  
         while ($charsLeft > 0) {  
             # Generate a random position in the soruce string.  
             my $stringIndex = IntGen(0, $stringLen - 1);  
             # Compute the number of characters to pull out of the source string.  
             my $chunkSize = $stringLen - $stringIndex;  
             if ($chunkSize > $charsLeft) { $chunkSize = $charsLeft; }  
             # Stuff this chunk into the return value.  
             $retVal .= substr($letterString, $stringIndex, $chunkSize);  
             # Record the data moved.  
             $charsLeft -= $chunkSize;  
         }  
     } elsif ($chosenPattern =~ m/^P/) {  
         # Here we have a picture string. We will move through the picture one  
         # character at a time generating data.  
         for (my $i = 1; $i < length $chosenPattern; $i++) {  
             # Get this picture character.  
             my $chr = substr($chosenPattern, $i, 1);  
             # Check to see if the picture char is one we recognize.  
             if (exists $PictureTable{$chr}) {  
                 # Choose a random character from the available values for this  
                 # picture character.  
                 $retVal .= RandChar($PictureTable{$chr});  
             } else {  
                 # Copy in the picture character as a literal.  
                 $retVal .= $chr;  
             }  
         }  
     } else {  
         # Here we have neither a picture string or a letter count, so we treat  
         # the string as a literal.  
         $retVal = $chosenPattern;  
     }  
     # Return the string formed.  
     return $retVal;  
 }  
   
 =head3 DateGen  
   
 C<< my $date = DateGen($startDayOffset, $endDayOffset, $minutes); >>  
   
 Return a numeric timestamp within the specified range of days with the specified minute  
 value. The range of days is specified relevant to the current day. Thus, the call  
   
 C<< my $date = DateGen(-1, 5, 720); >>  
   
 will return a timestamp at noon (72 minutes past midnight) sometime during the week that  
 began on the preceding day. If you want a random minute of the day, simply combine with  
 a call to L</IntGen>, as follows.  
   
 C<< my $date = DateGen(-1, 5, IntGen(0, 1439)); >>  
   
 =over 4  
   
 =item startDayOffset  
   
 The earliest day that can be returned, relative to the current day.  
   
 =item endDayOffset  
   
 The latest day that can be returned, related to the current day.  
   
 =item minutes  
   
 Number of minutes into the selected day that should be used.  
   
 =back  
   
 =cut  
   
 sub DateGen {  
     # Get the parameters.  
     my ($startDayOffset, $endDayOffset, $minutes) = @_;  
     # Get midnight of the current day.  
     my $now = time();  
     my ($sec, $min, $hour) = localtime($now);  
     my $today = $now - (($hour * 60 + $min) * 60 + $sec);  
     # Compute the day we want.  
     my $newDay = IntGen($startDayOffset, $endDayOffset) * 86400 + $today;  
     # Add the minutes.  
     my $retVal = $newDay + $minutes * 60;  
     # Return the result.  
     return $retVal;  
 }  
   
 =head3 FloatGen  
   
 C<< my $number = FloatGen($min, $max); >>  
   
 Return a random floating-point number greater than or equal to the specified minimum and  
 less than the specified maximum.  
   
 =over 4  
   
 =item min  
   
 Minimum permissible value for the number returned.  
   
 =item max  
   
 Maximum permissible value for the number returned.  
   
 =item RETURN  
   
 Returns a floating-point number anywhere in the specified range.  
   
 =back  
   
 =cut  
   
 sub FloatGen {  
     # Get the parameters.  
     my ($min, $max) = @_;  
     # Generate the result.  
     my $retVal = rand($max - $min) + $min;  
     return $retVal;  
 }  
   
 =head3 ListGen  
   
 C<< my @list = ListGen($pattern, $count); >>  
   
 Return a list containing a fixed number of randomly-generated strings.  
   
 =over 4  
   
 =item pattern  
   
 A pattern (in the form expected by L</StringGen>) that should be used to generate the  
 strings in the list.  
   
 =item count  
   
 The number of list entries to generate.  
   
 =item RETURN  
   
 Returns a list consisting of the specified number of strings.  
   
 =back  
   
 =cut  
   
 sub ListGen {  
     # Get the parameters.  
     my ($pattern, $count) = @_;  
     # Generate the list.  
     my @retVal = ();  
     for (my $i = 0; $i < $count; $i++) {  
         push @retVal, StringGen($pattern);  
     }  
     # Return it.  
     return @retVal;  
 }  
   
5011  1;  1;

Legend:
Removed from v.1.33  
changed lines
  Added in v.1.79

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3