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

Diff of /Sprout/ERDB.pm

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

revision 1.38, Fri Mar 17 22:02:03 2006 UTC revision 1.66, Thu Jul 13 04:53:54 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    
15  =head1 Entity-Relationship Database Package  =head1 Entity-Relationship Database Package
# Line 90  Line 91 
91    
92  32-bit signed integer  32-bit signed integer
93    
94    =item counter
95    
96    32-bit unsigned integer
97    
98  =item date  =item date
99    
100  64-bit unsigned integer, representing a PERL date/time value  64-bit unsigned integer, representing a PERL date/time value
# Line 109  Line 114 
114  compatability with certain database packages), but the only values supported are  compatability with certain database packages), but the only values supported are
115  0 and 1.  0 and 1.
116    
117    =item id-string
118    
119    variable-length string, maximum 25 characters
120    
121  =item key-string  =item key-string
122    
123  variable-length string, maximum 40 characters  variable-length string, maximum 40 characters
# Line 125  Line 134 
134    
135  variable-length string, maximum 255 characters  variable-length string, maximum 255 characters
136    
137    =item hash-string
138    
139    variable-length string, maximum 22 characters
140    
141  =back  =back
142    
143    The hash-string data type has a special meaning. The actual key passed into the loader will
144    be a string, but it will be digested into a 22-character MD5 code to save space. Although the
145    MD5 algorithm is not perfect, it is extremely unlikely two strings will have the same
146    digest. Therefore, it is presumed the keys will be unique. When the database is actually
147    in use, the hashed keys will be presented rather than the original values. For this reason,
148    they should not be used for entities where the key is meaningful.
149    
150  =head3 Global Tags  =head3 Global Tags
151    
152  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 302  Line 322 
322  # "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
323  # of the specified type. "dataGen" is PERL string that will be evaluated if no test data generation  # of the specified type. "dataGen" is PERL string that will be evaluated if no test data generation
324  # string is specified in the field definition. "avgLen" is the average byte length for estimating  # string is specified in the field definition. "avgLen" is the average byte length for estimating
325  # record sizes.  # record sizes. "sort" is the key modifier for the sort command.
326  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, dataGen => "StringGen('A')" },  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",  dataGen => "StringGen('A')" },
327                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, dataGen => "IntGen(0, 99999999)" },                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n", dataGen => "IntGen(0, 99999999)" },
328                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, dataGen => "StringGen(IntGen(10,250))" },                    counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n", dataGen => "IntGen(0, 99999999)" },
329                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, dataGen => "StringGen(IntGen(80,1000))" },                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, sort => "",  dataGen => "StringGen(IntGen(10,250))" },
330                    date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, dataGen => "DateGen(-7, 7, IntGen(0,1400))" },                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, sort => "",  dataGen => "StringGen(IntGen(80,1000))" },
331                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, dataGen => "FloatGen(0.0, 100.0)" },                    date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, sort => "n", dataGen => "DateGen(-7, 7, IntGen(0,1400))" },
332                    boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, dataGen => "IntGen(0, 1)" },                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, sort => "g", dataGen => "FloatGen(0.0, 100.0)" },
333                      boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, sort => "n", dataGen => "IntGen(0, 1)" },
334                     'hash-string' =>
335                                 { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, sort => "",  dataGen => "SringGen(22)" },
336                     'id-string' =>
337                                 { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, sort => "",  dataGen => "SringGen(22)" },
338                   'key-string' =>                   'key-string' =>
339                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, dataGen => "StringGen(IntGen(10,40))" },                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, sort => "",  dataGen => "StringGen(IntGen(10,40))" },
340                   'name-string' =>                   'name-string' =>
341                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, dataGen => "StringGen(IntGen(10,80))" },                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, sort => "",  dataGen => "StringGen(IntGen(10,80))" },
342                   'medium-string' =>                   'medium-string' =>
343                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, dataGen => "StringGen(IntGen(10,160))" },                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",  dataGen => "StringGen(IntGen(10,160))" },
344                  );                  );
345    
346  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 402  Line 427 
427      # Write the HTML heading stuff.      # Write the HTML heading stuff.
428      print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";      print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";
429      print HTMLOUT "</head>\n<body>\n";      print HTMLOUT "</head>\n<body>\n";
430        # Write the documentation.
431        print HTMLOUT $self->DisplayMetaData();
432        # Close the document.
433        print HTMLOUT "</body>\n</html>\n";
434        # Close the file.
435        close HTMLOUT;
436    }
437    
438    =head3 DisplayMetaData
439    
440    C<< my $html = $erdb->DisplayMetaData(); >>
441    
442    Return an HTML description of the database. This description can be used to help users create
443    the data to be loaded into the relations and form queries. The output is raw includable HTML
444    without any HEAD or BODY tags.
445    
446    =over 4
447    
448    =item filename
449    
450    The name of the output file.
451    
452    =back
453    
454    =cut
455    
456    sub DisplayMetaData {
457        # Get the parameters.
458        my ($self) = @_;
459        # Get the metadata and the title string.
460        my $metadata = $self->{_metaData};
461        # Get the title string.
462        my $title = $metadata->{Title};
463        # Get the entity and relationship lists.
464        my $entityList = $metadata->{Entities};
465        my $relationshipList = $metadata->{Relationships};
466        # Declare the return variable.
467        my $retVal = "";
468        # Open the output file.
469        Trace("Building MetaData table of contents.") if T(4);
470      # 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
471      # section contains an ordered list of entity or relationship subsections.      # section contains an ordered list of entity or relationship subsections.
472      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";
473      # Loop through the Entities, displaying a list item for each.      # Loop through the Entities, displaying a list item for each.
474      foreach my $key (sort keys %{$entityList}) {      foreach my $key (sort keys %{$entityList}) {
475          # Display this item.          # Display this item.
476          print HTMLOUT "<li><a href=\"#$key\">$key</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$key</a></li>\n";
477      }      }
478      # Close off the entity section and start the relationship section.      # Close off the entity section and start the relationship section.
479      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";
480      # Loop through the Relationships.      # Loop through the Relationships.
481      foreach my $key (sort keys %{$relationshipList}) {      foreach my $key (sort keys %{$relationshipList}) {
482          # Display this item.          # Display this item.
483          my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});          my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});
484          print HTMLOUT "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";
485      }      }
486      # Close off the relationship section and list the join table section.      # Close off the relationship section and list the join table section.
487      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";
488      # Close off the table of contents itself.      # Close off the table of contents itself.
489      print HTMLOUT "</ul>\n";      $retVal .=  "</ul>\n";
490      # 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.
491      print HTMLOUT "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";      $retVal .= "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";
492      # Loop through the entities.      # Loop through the entities.
493      for my $key (sort keys %{$entityList}) {      for my $key (sort keys %{$entityList}) {
494          Trace("Building MetaData entry for $key entity.") if T(4);          Trace("Building MetaData entry for $key entity.") if T(4);
495          # Create the entity header. It contains a bookmark and the entity name.          # Create the entity header. It contains a bookmark and the entity name.
496          print HTMLOUT "<a name=\"$key\"></a><h3>$key</h3>\n";          $retVal .= "<a name=\"$key\"></a><h3>$key</h3>\n";
497          # Get the entity data.          # Get the entity data.
498          my $entityData = $entityList->{$key};          my $entityData = $entityList->{$key};
499          # If there's descriptive text, display it.          # If there's descriptive text, display it.
500          if (my $notes = $entityData->{Notes}) {          if (my $notes = $entityData->{Notes}) {
501              print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";
502          }          }
503          # 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.
504          print HTMLOUT "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
505          # Loop through the relationships.          # Loop through the relationships.
506          for my $relationship (sort keys %{$relationshipList}) {          for my $relationship (sort keys %{$relationshipList}) {
507              # Get the relationship data.              # Get the relationship data.
# Line 446  Line 511 
511                  # Get the relationship sentence and append the arity.                  # Get the relationship sentence and append the arity.
512                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);
513                  # Display the relationship data.                  # Display the relationship data.
514                  print HTMLOUT "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";                  $retVal .= "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";
515              }              }
516          }          }
517          # Close off the relationship list.          # Close off the relationship list.
518          print HTMLOUT "</ul>\n";          $retVal .= "</ul>\n";
519          # Get the entity's relations.          # Get the entity's relations.
520          my $relationList = $entityData->{Relations};          my $relationList = $entityData->{Relations};
521          # Create a header for the relation subsection.          # Create a header for the relation subsection.
522          print HTMLOUT "<h4>Relations for <b>$key</b></h4>\n";          $retVal .= "<h4>Relations for <b>$key</b></h4>\n";
523          # Loop through the relations, displaying them.          # Loop through the relations, displaying them.
524          for my $relation (sort keys %{$relationList}) {          for my $relation (sort keys %{$relationList}) {
525              my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});              my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});
526              print HTMLOUT $htmlString;              $retVal .= $htmlString;
527          }          }
528      }      }
529      # Denote we're starting the relationship section.      # Denote we're starting the relationship section.
530      print HTMLOUT "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";      $retVal .= "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";
531      # Loop through the relationships.      # Loop through the relationships.
532      for my $key (sort keys %{$relationshipList}) {      for my $key (sort keys %{$relationshipList}) {
533          Trace("Building MetaData entry for $key relationship.") if T(4);          Trace("Building MetaData entry for $key relationship.") if T(4);
# Line 470  Line 535 
535          my $relationshipStructure = $relationshipList->{$key};          my $relationshipStructure = $relationshipList->{$key};
536          # Create the relationship header.          # Create the relationship header.
537          my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);          my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);
538          print HTMLOUT "<h3><a name=\"$key\"></a>$headerText</h3>\n";          $retVal .= "<h3><a name=\"$key\"></a>$headerText</h3>\n";
539          # Get the entity names.          # Get the entity names.
540          my $fromEntity = $relationshipStructure->{from};          my $fromEntity = $relationshipStructure->{from};
541          my $toEntity = $relationshipStructure->{to};          my $toEntity = $relationshipStructure->{to};
# Line 480  Line 545 
545          # since both sentences will say the same thing.          # since both sentences will say the same thing.
546          my $arity = $relationshipStructure->{arity};          my $arity = $relationshipStructure->{arity};
547          if ($arity eq "11") {          if ($arity eq "11") {
548              print HTMLOUT "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";
549          } else {          } else {
550              print HTMLOUT "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";
551              if ($arity eq "MM" && $fromEntity ne $toEntity) {              if ($arity eq "MM" && $fromEntity ne $toEntity) {
552                  print HTMLOUT "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";                  $retVal .= "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";
553              }              }
554          }          }
555          print HTMLOUT "</p>\n";          $retVal .= "</p>\n";
556          # If there are notes on this relationship, display them.          # If there are notes on this relationship, display them.
557          if (my $notes = $relationshipStructure->{Notes}) {          if (my $notes = $relationshipStructure->{Notes}) {
558              print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";
559          }          }
560          # Generate the relationship's relation table.          # Generate the relationship's relation table.
561          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
562          print HTMLOUT $htmlString;          $retVal .= $htmlString;
563      }      }
564      Trace("Building MetaData join table.") if T(4);      Trace("Building MetaData join table.") if T(4);
565      # Denote we're starting the join table.      # Denote we're starting the join table.
566      print HTMLOUT "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";      $retVal .= "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";
567      # Create a table header.      # Create a table header.
568      print HTMLOUT _OpenTable("Join Table", "Source", "Target", "Join Condition");      $retVal .= _OpenTable("Join Table", "Source", "Target", "Join Condition");
569      # Loop through the joins.      # Loop through the joins.
570      my $joinTable = $metadata->{Joins};      my $joinTable = $metadata->{Joins};
571      my @joinKeys = keys %{$joinTable};      my @joinKeys = keys %{$joinTable};
# Line 513  Line 578 
578          my $target = $self->ComputeObjectSentence($targetRelation);          my $target = $self->ComputeObjectSentence($targetRelation);
579          my $clause = $joinTable->{$joinKey};          my $clause = $joinTable->{$joinKey};
580          # Display them in a table row.          # Display them in a table row.
581          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";
582      }      }
583      # Close the table.      # Close the table.
584      print HTMLOUT _CloseTable();      $retVal .= _CloseTable();
585      # Close the document.      Trace("Built MetaData HTML.") if T(3);
586      print HTMLOUT "</body>\n</html>\n";      # Return the HTML.
587      # Close the file.      return $retVal;
     close HTMLOUT;  
     Trace("Built MetaData web page.") if T(3);  
588  }  }
589    
590  =head3 DumpMetaData  =head3 DumpMetaData
# Line 687  Line 750 
750      return $retVal;      return $retVal;
751  }  }
752    
753    =head3 DigestFields
754    
755    C<< $erdb->DigestFields($relName, $fieldList); >>
756    
757    Digest the strings in the field list that correspond to data type C<hash-string> in the
758    specified relation.
759    
760    =over 4
761    
762    =item relName
763    
764    Name of the relation to which the fields belong.
765    
766    =item fieldList
767    
768    List of field contents to be loaded into the relation.
769    
770    =back
771    
772    =cut
773    #: Return Type ;
774    sub DigestFields {
775        # Get the parameters.
776        my ($self, $relName, $fieldList) = @_;
777        # Get the relation definition.
778        my $relData = $self->_FindRelation($relName);
779        # Get the list of field descriptors.
780        my $fieldTypes = $relData->{Fields};
781        my $fieldCount = scalar @{$fieldTypes};
782        # Loop through the two lists.
783        for (my $i = 0; $i < $fieldCount; $i++) {
784            # Get the type of the current field.
785            my $fieldType = $fieldTypes->[$i]->{type};
786            # If it's a hash string, digest it in place.
787            if ($fieldType eq 'hash-string') {
788                $fieldList->[$i] = $self->DigestKey($fieldList->[$i]);
789            }
790        }
791    }
792    
793    =head3 DigestKey
794    
795    C<< my $digested = $erdb->DigestKey($keyValue); >>
796    
797    Return the digested value of a symbolic key. The digested value can then be plugged into a
798    key-based search into a table with key-type hash-string.
799    
800    Currently the digesting process is independent of the database structure, but that may not
801    always be the case, so this is an instance method instead of a static method.
802    
803    =over 4
804    
805    =item keyValue
806    
807    Key value to digest.
808    
809    =item RETURN
810    
811    Digested value of the key.
812    
813    =back
814    
815    =cut
816    
817    sub DigestKey {
818        # Get the parameters.
819        my ($self, $keyValue) = @_;
820        # Compute the digest.
821        my $retVal = md5_base64($keyValue);
822        # Return the result.
823        return $retVal;
824    }
825    
826  =head3 CreateIndex  =head3 CreateIndex
827    
828  C<< $erdb->CreateIndex($relationName); >>  C<< $erdb->CreateIndex($relationName); >>
# Line 848  Line 984 
984    
985  =head3 Get  =head3 Get
986    
987  C<< my $query = $erdb->Get(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  C<< my $query = $erdb->Get(\@objectNames, $filterClause, \@params); >>
988    
989  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.
990  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 992 
992  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
993  $genus.  $genus.
994    
995  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", [$genus]); >>
996    
997  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
998  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 1009 
1009  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
1010  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,
1011    
1012  C<< $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]); >>
1013    
1014  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
1015  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.
1016  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
1017  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
1018  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  
1019  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,
1020  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.
1021    
1022    If an entity or relationship is mentioned twice, the name for the second occurrence will
1023    be suffixed with C<2>, the third occurrence will be suffixed with C<3>, and so forth. So,
1024    for example, if we have C<['Feature', 'HasContig', 'Contig', 'HasContig']>, then the
1025    B<to-link> field of the first B<HasContig> is specified as C<HasContig(to-link)>, while
1026    the B<to-link> field of the second B<HasContig> is specified as C<HasContig2(to-link)>.
1027    
1028  =over 4  =over 4
1029    
1030  =item objectNames  =item objectNames
# Line 913  Line 1054 
1054  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
1055  relation.  relation.
1056    
1057  =item param1, param2, ..., paramN  Finally, you can limit the number of rows returned by adding a LIMIT clause. The LIMIT must
1058    be the last thing in the filter clause, and it contains only the word "LIMIT" followed by
1059    a positive number. So, for example
1060    
1061    C<< "Genome(genus) = ? ORDER BY Genome(species) LIMIT 10" >>
1062    
1063    will only return the first ten genomes for the specified genus. The ORDER BY clause is not
1064    required. For example, to just get the first 10 genomes in the B<Genome> table, you could
1065    use
1066    
1067    C<< "LIMIT 10" >>
1068    
1069    =item params
1070    
1071  Parameter values to be substituted into the filter clause.  Reference to a list of parameter values to be substituted into the filter clause.
1072    
1073  =item RETURN  =item RETURN
1074    
# Line 927  Line 1080 
1080    
1081  sub Get {  sub Get {
1082      # Get the parameters.      # Get the parameters.
1083      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $objectNames, $filterClause, $params) = @_;
1084      # Construct the SELECT statement. The general pattern is      # Process the SQL stuff.
1085      #      my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1086      # SELECT name1.*, name2.*, ... nameN.* FROM name1, name2, ... nameN          $self->_SetupSQL($objectNames, $filterClause);
1087      #      # Create the query.
1088      my $dbh = $self->{_dbh};      my $command = "SELECT DISTINCT " . join(".*, ", @{$mappedNameListRef}) .
1089      my $command = "SELECT DISTINCT " . join('.*, ', @{$objectNames}) . ".* FROM " .          ".* $suffix";
1090                  join(', ', @{$objectNames});      my $sth = $self->_GetStatementHandle($command, $params);
1091      # Check for a filter clause.      # Now we create the relation map, which enables DBQuery to determine the order, name
1092      if ($filterClause) {      # and mapped name for each object in the query.
1093          # Here we have one, so we convert its field names and add it to the query. First,      my @relationMap = ();
1094          # We create a copy of the filter string we can work with.      for my $mappedName (@{$mappedNameListRef}) {
1095          my $filterString = $filterClause;          push @relationMap, [$mappedName, $mappedNameHashRef->{$mappedName}];
         # Next, we sort the object names by length. This helps protect us from finding  
         # object names inside other object names when we're doing our search and replace.  
         my @sortedNames = sort { length($b) - length($a) } @{$objectNames};  
         # We will also keep a list of conditions to add to the WHERE clause in order to link  
         # entities and relationships as well as primary relations to secondary ones.  
         my @joinWhere = ();  
         # The final preparatory step is to create a hash table of relation names. The  
         # table begins with the relation names already in the SELECT command.  
         my %fromNames = ();  
         for my $objectName (@sortedNames) {  
             $fromNames{$objectName} = 1;  
         }  
         # We are ready to begin. We loop through the object names, replacing each  
         # object name's field references by the corresponding SQL field reference.  
         # Along the way, if we find a secondary relation, we will need to add it  
         # to the FROM clause.  
         for my $objectName (@sortedNames) {  
             # Get the length of the object name plus 2. This is the value we add to the  
             # size of the field name to determine the size of the field reference as a  
             # whole.  
             my $nameLength = 2 + length $objectName;  
             # Get the object's field list.  
             my $fieldList = $self->GetFieldTable($objectName);  
             # Find the field references for this object.  
             while ($filterString =~ m/$objectName\(([^)]*)\)/g) {  
                 # At this point, $1 contains the field name, and the current position  
                 # is set immediately after the final parenthesis. We pull out the name of  
                 # the field and the position and length of the field reference as a whole.  
                 my $fieldName = $1;  
                 my $len = $nameLength + length $fieldName;  
                 my $pos = pos($filterString) - $len;  
                 # Insure the field exists.  
                 if (!exists $fieldList->{$fieldName}) {  
                     Confess("Field $fieldName not found for object $objectName.");  
                 } else {  
                     # Get the field's relation.  
                     my $relationName = $fieldList->{$fieldName}->{relation};  
                     # Insure the relation is in the FROM clause.  
                     if (!exists $fromNames{$relationName}) {  
                         # Add the relation to the FROM clause.  
                         $command .= ", $relationName";  
                         # Create its join sub-clause.  
                         push @joinWhere, "$objectName.id = $relationName.id";  
                         # Denote we have it available for future fields.  
                         $fromNames{$relationName} = 1;  
                     }  
                     # Form an SQL field reference from the relation name and the field name.  
                     my $sqlReference = "$relationName." . _FixName($fieldName);  
                     # Put it into the filter string in place of the old value.  
                     substr($filterString, $pos, $len) = $sqlReference;  
                     # Reposition the search.  
                     pos $filterString = $pos + length $sqlReference;  
                 }  
             }  
         }  
         # The next step is to join the objects together. We only need to do this if there  
         # is more than one object in the object list. We start with the first object and  
         # run through the objects after it. Note also that we make a safety copy of the  
         # list before running through it.  
         my @objectList = @{$objectNames};  
         my $lastObject = shift @objectList;  
         # Get the join table.  
         my $joinTable = $self->{_metaData}->{Joins};  
         # Loop through the object list.  
         for my $thisObject (@objectList) {  
             # Look for a join.  
             my $joinKey = "$lastObject/$thisObject";  
             if (!exists $joinTable->{$joinKey}) {  
                 # Here there's no join, so we throw an error.  
                 Confess("No join exists to connect from $lastObject to $thisObject.");  
             } else {  
                 # Get the join clause and add it to the WHERE list.  
                 push @joinWhere, $joinTable->{$joinKey};  
                 # Save this object as the last object for the next iteration.  
                 $lastObject = $thisObject;  
             }  
         }  
         # Now we need to handle the whole ORDER BY / LIMIT thing. The important part  
         # here is we want the filter clause to be empty if there's no WHERE filter.  
         # We'll put the ORDER BY / LIMIT clauses in the following variable.  
         my $orderClause = "";  
         # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy  
         # operator so that we find the first occurrence of either verb.  
         if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {  
             # Here we have an ORDER BY or LIMIT verb. Split it off of the filter string.  
             my $pos = pos $filterString;  
             $orderClause = $2 . substr($filterString, $pos);  
             $filterString = $1;  
         }  
         # Add the filter and the join clauses (if any) to the SELECT command.  
         if ($filterString) {  
             push @joinWhere, "($filterString)";  
         }  
         if (@joinWhere) {  
             $command .= " WHERE " . join(' AND ', @joinWhere);  
         }  
         # Add the sort or limit clause (if any) to the SELECT command.  
         if ($orderClause) {  
             $command .= " $orderClause";  
         }  
1096      }      }
     Trace("SQL query: $command") if T(SQL => 4);  
     Trace("PARMS: '" . (join "', '", @params) . "'") if (T(SQL => 4) && (@params > 0));  
     my $sth = $dbh->prepare_command($command);  
     # Execute it with the parameters bound in.  
     $sth->execute(@params) || Confess("SELECT error" . $sth->errstr());  
1097      # Return the statement object.      # Return the statement object.
1098      my $retVal = DBQuery::_new($self, $sth, @{$objectNames});      my $retVal = DBQuery::_new($self, $sth, \@relationMap);
1099      return $retVal;      return $retVal;
1100  }  }
1101    
1102    =head3 GetFlat
1103    
1104    C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>
1105    
1106    This is a variation of L</GetAll> that asks for only a single field per record and
1107    returns a single flattened list.
1108    
1109    =over 4
1110    
1111    =item objectNames
1112    
1113    List containing the names of the entity and relationship objects to be retrieved.
1114    
1115    =item filterClause
1116    
1117    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1118    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
1119    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
1120    parameter list as additional parameters. The fields in a filter clause can come from primary
1121    entity relations, relationship relations, or secondary entity relations; however, all of the
1122    entities and relationships involved must be included in the list of object names.
1123    
1124    =item parameterList
1125    
1126    List of the parameters to be substituted in for the parameters marks in the filter clause.
1127    
1128    =item field
1129    
1130    Name of the field to be used to get the elements of the list returned.
1131    
1132    =item RETURN
1133    
1134    Returns a list of values.
1135    
1136    =back
1137    
1138    =cut
1139    #: Return Type @;
1140    sub GetFlat {
1141        # Get the parameters.
1142        my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
1143        # Construct the query.
1144        my $query = $self->Get($objectNames, $filterClause, $parameterList);
1145        # Create the result list.
1146        my @retVal = ();
1147        # Loop through the records, adding the field values found to the result list.
1148        while (my $row = $query->Fetch()) {
1149            push @retVal, $row->Value($field);
1150        }
1151        # Return the list created.
1152        return @retVal;
1153    }
1154    
1155  =head3 Delete  =head3 Delete
1156    
1157  C<< my $stats = $erdb->Delete($entityName, $objectID); >>  C<< my $stats = $erdb->Delete($entityName, $objectID); >>
# Line 1221  Line 1322 
1322    
1323  =head3 GetList  =head3 GetList
1324    
1325  C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>
1326    
1327  Return a list of object descriptors for the specified objects as determined by the  Return a list of object descriptors for the specified objects as determined by the
1328  specified filter clause.  specified filter clause.
# Line 1255  Line 1356 
1356  filter clause in general; however, odd things may happen if a sort field is from a secondary  filter clause in general; however, odd things may happen if a sort field is from a secondary
1357  relation.  relation.
1358    
1359  =item param1, param2, ..., paramN  =item params
1360    
1361  Parameter values to be substituted into the filter clause.  Reference to a list of parameter values to be substituted into the filter clause.
1362    
1363  =item RETURN  =item RETURN
1364    
# Line 1269  Line 1370 
1370  #: Return Type @%  #: Return Type @%
1371  sub GetList {  sub GetList {
1372      # Get the parameters.      # Get the parameters.
1373      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $objectNames, $filterClause, $params) = @_;
1374      # Declare the return variable.      # Declare the return variable.
1375      my @retVal = ();      my @retVal = ();
1376      # Perform the query.      # Perform the query.
1377      my $query = $self->Get($objectNames, $filterClause, @params);      my $query = $self->Get($objectNames, $filterClause, $params);
1378      # Loop through the results.      # Loop through the results.
1379      while (my $object = $query->Fetch) {      while (my $object = $query->Fetch) {
1380          push @retVal, $object;          push @retVal, $object;
# Line 1282  Line 1383 
1383      return @retVal;      return @retVal;
1384  }  }
1385    
1386    =head3 GetCount
1387    
1388    C<< my $count = $erdb->GetCount(\@objectNames, $filter, \@params); >>
1389    
1390    Return the number of rows found by a specified query. This method would
1391    normally be used to count the records in a single table. For example, in a
1392    genetics database
1393    
1394        my $count = $erdb->GetCount(['Genome'], 'Genome(genus-species) LIKE ?', ['homo %']);
1395    
1396    would return the number of genomes for the genus I<homo>. It is conceivable, however,
1397    to use it to return records based on a join. For example,
1398    
1399        my $count = $erdb->GetCount(['HasFeature', 'Genome'], 'Genome(genus-species) LIKE ?',
1400                                    ['homo %']);
1401    
1402    would return the number of features for genomes in the genus I<homo>. Note that
1403    only the rows from the first table are counted. If the above command were
1404    
1405        my $count = $erdb->GetCount(['Genome', 'Feature'], 'Genome(genus-species) LIKE ?',
1406                                    ['homo %']);
1407    
1408    it would return the number of genomes, not the number of genome/feature pairs.
1409    
1410    =over 4
1411    
1412    =item objectNames
1413    
1414    Reference to a list of the objects (entities and relationships) included in the
1415    query.
1416    
1417    =item filter
1418    
1419    A filter clause for restricting the query. The rules are the same as for the L</Get>
1420    method.
1421    
1422    =item params
1423    
1424    Reference to a list of the parameter values to be substituted for the parameter marks
1425    in the filter.
1426    
1427    =item RETURN
1428    
1429    Returns a count of the number of records in the first table that would satisfy
1430    the query.
1431    
1432    =back
1433    
1434    =cut
1435    
1436    sub GetCount {
1437        # Get the parameters.
1438        my ($self, $objectNames, $filter, $params) = @_;
1439        # Insure the params argument is an array reference if the caller left it off.
1440        if (! defined($params)) {
1441            $params = [];
1442        }
1443        # Declare the return variable.
1444        my $retVal;
1445        # Find out if we're counting an entity or a relationship.
1446        my $countedField;
1447        if ($self->IsEntity($objectNames->[0])) {
1448            $countedField = "id";
1449        } else {
1450            # For a relationship we count the to-link because it's usually more
1451            # numerous. Note we're automatically converting to the SQL form
1452            # of the field name (to_link vs. to-link).
1453            $countedField = "to_link";
1454        }
1455        # Create the SQL command suffix to get the desired records.
1456        my ($suffix, $mappedNameListRef, $mappedNameHashRef) = $self->_SetupSQL($objectNames,
1457                                                                                $filter);
1458        # Prefix it with text telling it we want a record count.
1459        my $firstObject = $mappedNameListRef->[0];
1460        my $command = "SELECT COUNT($firstObject.$countedField) $suffix";
1461        # Prepare and execute the command.
1462        my $sth = $self->_GetStatementHandle($command, $params);
1463        # Get the count value.
1464        ($retVal) = $sth->fetchrow_array();
1465        # Check for a problem.
1466        if (! defined($retVal)) {
1467            if ($sth->err) {
1468                # Here we had an SQL error.
1469                Confess("Error retrieving row count: " . $sth->errstr());
1470            } else {
1471                # Here we have no result.
1472                Confess("No result attempting to retrieve row count.");
1473            }
1474        }
1475        # Return the result.
1476        return $retVal;
1477    }
1478    
1479  =head3 ComputeObjectSentence  =head3 ComputeObjectSentence
1480    
1481  C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>  C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>
# Line 1350  Line 1544 
1544              $self->_DumpRelation($outputDirectory, $relationName, $relation);              $self->_DumpRelation($outputDirectory, $relationName, $relation);
1545          }          }
1546      }      }
1547      # Next, we loop through the relationships.      # Next, we loop through the relationships.
1548      my $relationships = $metaData->{Relationships};      my $relationships = $metaData->{Relationships};
1549      for my $relationshipName (keys %{$relationships}) {      for my $relationshipName (keys %{$relationships}) {
1550          my $relationshipStructure = $relationships->{$relationshipName};          my $relationshipStructure = $relationships->{$relationshipName};
1551          # Dump this relationship's relation.          # Dump this relationship's relation.
1552          $self->_DumpRelation($outputDirectory, $relationshipName, $relationshipStructure->{Relations}->{$relationshipName});          $self->_DumpRelation($outputDirectory, $relationshipName, $relationshipStructure->{Relations}->{$relationshipName});
1553        }
1554    }
1555    
1556    =head3 InsertValue
1557    
1558    C<< $erdb->InsertValue($entityID, $fieldName, $value); >>
1559    
1560    This method will insert a new value into the database. The value must be one
1561    associated with a secondary relation, since primary values cannot be inserted:
1562    they occur exactly once. Secondary values, on the other hand, can be missing
1563    or multiply-occurring.
1564    
1565    =over 4
1566    
1567    =item entityID
1568    
1569    ID of the object that is to receive the new value.
1570    
1571    =item fieldName
1572    
1573    Field name for the new value-- this includes the entity name, since
1574    field names are of the format I<objectName>C<(>I<fieldName>C<)>.
1575    
1576    =item value
1577    
1578    New value to be put in the field.
1579    
1580    =back
1581    
1582    =cut
1583    
1584    sub InsertValue {
1585        # Get the parameters.
1586        my ($self, $entityID, $fieldName, $value) = @_;
1587        # Parse the entity name and the real field name.
1588        if ($fieldName =~ /^([^(]+)\(([^)]+)\)/) {
1589            my $entityName = $1;
1590            my $fieldTitle = $2;
1591            # Get its descriptor.
1592            if (!$self->IsEntity($entityName)) {
1593                Confess("$entityName is not a valid entity.");
1594            } else {
1595                my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1596                # Find the relation containing this field.
1597                my $fieldHash = $entityData->{Fields};
1598                if (! exists $fieldHash->{$fieldTitle}) {
1599                    Confess("$fieldTitle not found in $entityName.");
1600                } else {
1601                    my $relation = $fieldHash->{$fieldTitle}->{relation};
1602                    if ($relation eq $entityName) {
1603                        Confess("Cannot do InsertValue on primary field $fieldTitle of $entityName.");
1604                    } else {
1605                        # Now we can create an INSERT statement.
1606                        my $dbh = $self->{_dbh};
1607                        my $fixedName = _FixName($fieldTitle);
1608                        my $statement = "INSERT INTO $relation (id, $fixedName) VALUES(?, ?)";
1609                        # Execute the command.
1610                        $dbh->SQL($statement, 0, $entityID, $value);
1611                    }
1612                }
1613            }
1614        } else {
1615            Confess("$fieldName is not a valid field name.");
1616      }      }
1617  }  }
1618    
# Line 1375  Line 1632 
1632  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
1633  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>.
1634    
1635  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'}); >>
1636    
1637  =over 4  =over 4
1638    
# Line 1585  Line 1842 
1842          }          }
1843      }      }
1844      # Analyze the table to improve performance.      # Analyze the table to improve performance.
1845        Trace("Analyzing and compacting $relationName.") if T(3);
1846      $dbh->vacuum_it($relationName);      $dbh->vacuum_it($relationName);
1847        Trace("$relationName load completed.") if T(3);
1848      # Return the statistics.      # Return the statistics.
1849      return $retVal;      return $retVal;
1850  }  }
# Line 1677  Line 1936 
1936      # Get the parameters.      # Get the parameters.
1937      my ($self, $entityType, $ID) = @_;      my ($self, $entityType, $ID) = @_;
1938      # Create a query.      # Create a query.
1939      my $query = $self->Get([$entityType], "$entityType(id) = ?", $ID);      my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);
1940      # Get the first (and only) object.      # Get the first (and only) object.
1941      my $retVal = $query->Fetch();      my $retVal = $query->Fetch();
1942      # Return the result.      # Return the result.
# Line 1790  Line 2049 
2049      # list is a scalar we convert it into a singleton list.      # list is a scalar we convert it into a singleton list.
2050      my @parmList = ();      my @parmList = ();
2051      if (ref $parameterList eq "ARRAY") {      if (ref $parameterList eq "ARRAY") {
2052            Trace("GetAll parm list is an array.") if T(4);
2053          @parmList = @{$parameterList};          @parmList = @{$parameterList};
2054      } else {      } else {
2055            Trace("GetAll parm list is a scalar: $parameterList.") if T(4);
2056          push @parmList, $parameterList;          push @parmList, $parameterList;
2057      }      }
2058      # Insure the counter has a value.      # Insure the counter has a value.
# Line 1803  Line 2064 
2064          $filterClause .= " LIMIT $count";          $filterClause .= " LIMIT $count";
2065      }      }
2066      # Create the query.      # Create the query.
2067      my $query = $self->Get($objectNames, $filterClause, @parmList);      my $query = $self->Get($objectNames, $filterClause, \@parmList);
2068      # Set up a counter of the number of records read.      # Set up a counter of the number of records read.
2069      my $fetched = 0;      my $fetched = 0;
2070      # 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 2075 
2075          push @retVal, \@rowData;          push @retVal, \@rowData;
2076          $fetched++;          $fetched++;
2077      }      }
2078        Trace("$fetched rows returned in GetAll.") if T(SQL => 4);
2079      # Return the resulting list.      # Return the resulting list.
2080      return @retVal;      return @retVal;
2081  }  }
2082    
2083    =head3 Exists
2084    
2085    C<< my $found = $sprout->Exists($entityName, $entityID); >>
2086    
2087    Return TRUE if an entity exists, else FALSE.
2088    
2089    =over 4
2090    
2091    =item entityName
2092    
2093    Name of the entity type (e.g. C<Feature>) relevant to the existence check.
2094    
2095    =item entityID
2096    
2097    ID of the entity instance whose existence is to be checked.
2098    
2099    =item RETURN
2100    
2101    Returns TRUE if the entity instance exists, else FALSE.
2102    
2103    =back
2104    
2105    =cut
2106    #: Return Type $;
2107    sub Exists {
2108        # Get the parameters.
2109        my ($self, $entityName, $entityID) = @_;
2110        # Check for the entity instance.
2111        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
2112        my $testInstance = $self->GetEntity($entityName, $entityID);
2113        # Return an existence indicator.
2114        my $retVal = ($testInstance ? 1 : 0);
2115        return $retVal;
2116    }
2117    
2118  =head3 EstimateRowSize  =head3 EstimateRowSize
2119    
2120  C<< my $rowSize = $erdb->EstimateRowSize($relName); >>  C<< my $rowSize = $erdb->EstimateRowSize($relName); >>
# Line 1885  Line 2182 
2182      return $objectData->{Fields};      return $objectData->{Fields};
2183  }  }
2184    
2185    =head2 Data Mining Methods
2186    
2187  =head3 GetUsefulCrossValues  =head3 GetUsefulCrossValues
2188    
2189  C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>  C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>
# Line 1946  Line 2245 
2245      return @retVal;      return @retVal;
2246  }  }
2247    
2248    =head3 FindColumn
2249    
2250    C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>
2251    
2252    Return the location a desired column in a data mining header line. The data
2253    mining header line is a tab-separated list of column names. The column
2254    identifier is either the numerical index of a column or the actual column
2255    name.
2256    
2257    =over 4
2258    
2259    =item headerLine
2260    
2261    The header line from a data mining command, which consists of a tab-separated
2262    list of column names.
2263    
2264    =item columnIdentifier
2265    
2266    Either the ordinal number of the desired column (1-based), or the name of the
2267    desired column.
2268    
2269    =item RETURN
2270    
2271    Returns the array index (0-based) of the desired column.
2272    
2273    =back
2274    
2275    =cut
2276    
2277    sub FindColumn {
2278        # Get the parameters.
2279        my ($headerLine, $columnIdentifier) = @_;
2280        # Declare the return variable.
2281        my $retVal;
2282        # Split the header line into column names.
2283        my @headers = ParseColumns($headerLine);
2284        # Determine whether we have a number or a name.
2285        if ($columnIdentifier =~ /^\d+$/) {
2286            # Here we have a number. Subtract 1 and validate the result.
2287            $retVal = $columnIdentifier - 1;
2288            if ($retVal < 0 || $retVal > $#headers) {
2289                Confess("Invalid column identifer \"$columnIdentifier\": value out of range.");
2290            }
2291        } else {
2292            # Here we have a name. We need to find it in the list.
2293            for (my $i = 0; $i <= $#headers && ! defined($retVal); $i++) {
2294                if ($headers[$i] eq $columnIdentifier) {
2295                    $retVal = $i;
2296                }
2297            }
2298            if (! defined($retVal)) {
2299                Confess("Invalid column identifier \"$columnIdentifier\": value not found.");
2300            }
2301        }
2302        # Return the result.
2303        return $retVal;
2304    }
2305    
2306    =head3 ParseColumns
2307    
2308    C<< my @columns = ERDB::ParseColumns($line); >>
2309    
2310    Convert the specified data line to a list of columns.
2311    
2312    =over 4
2313    
2314    =item line
2315    
2316    A data mining input, consisting of a tab-separated list of columns terminated by a
2317    new-line.
2318    
2319    =item RETURN
2320    
2321    Returns a list consisting of the column values.
2322    
2323    =back
2324    
2325    =cut
2326    
2327    sub ParseColumns {
2328        # Get the parameters.
2329        my ($line) = @_;
2330        # Chop off the line-end.
2331        chomp $line;
2332        # Split it into a list.
2333        my @retVal = split(/\t/, $line);
2334        # Return the result.
2335        return @retVal;
2336    }
2337    
2338  =head2 Internal Utility Methods  =head2 Internal Utility Methods
2339    
2340    =head3 SetupSQL
2341    
2342    Process a list of object names and a filter clause so that they can be used to
2343    build an SQL statement. This method takes in a reference to a list of object names
2344    and a filter clause. It will return a corrected filter clause, a list of mapped
2345    names and the mapped name hash.
2346    
2347    This is an instance method.
2348    
2349    =over 4
2350    
2351    =item objectNames
2352    
2353    Reference to a list of the object names to be included in the query.
2354    
2355    =item filterClause
2356    
2357    A string containing the WHERE clause for the query (without the C<WHERE>) and also
2358    optionally the C<ORDER BY> and C<LIMIT> clauses.
2359    
2360    =item RETURN
2361    
2362    Returns a three-element list. The first element is the SQL statement suffix, beginning
2363    with the FROM clause. The second element is a reference to a list of the names to be
2364    used in retrieving the fields. The third element is a hash mapping the names to the
2365    objects they represent.
2366    
2367    =back
2368    
2369    =cut
2370    
2371    sub _SetupSQL {
2372        my ($self, $objectNames, $filterClause) = @_;
2373        # Adjust the list of object names to account for multiple occurrences of the
2374        # same object. We start with a hash table keyed on object name that will
2375        # return the object suffix. The first time an object is encountered it will
2376        # not be found in the hash. The next time the hash will map the object name
2377        # to 2, then 3, and so forth.
2378        my %objectHash = ();
2379        # This list will contain the object names as they are to appear in the
2380        # FROM list.
2381        my @fromList = ();
2382        # This list contains the suffixed object name for each object. It is exactly
2383        # parallel to the list in the $objectNames parameter.
2384        my @mappedNameList = ();
2385        # Finally, this hash translates from a mapped name to its original object name.
2386        my %mappedNameHash = ();
2387        # Now we create the lists. Note that for every single name we push something into
2388        # @fromList and @mappedNameList. This insures that those two arrays are exactly
2389        # parallel to $objectNames.
2390        for my $objectName (@{$objectNames}) {
2391            # Get the next suffix for this object.
2392            my $suffix = $objectHash{$objectName};
2393            if (! $suffix) {
2394                # Here we are seeing the object for the first time. The object name
2395                # is used as is.
2396                push @mappedNameList, $objectName;
2397                push @fromList, $objectName;
2398                $mappedNameHash{$objectName} = $objectName;
2399                # Denote the next suffix will be 2.
2400                $objectHash{$objectName} = 2;
2401            } else {
2402                # Here we've seen the object before. We construct a new name using
2403                # the suffix from the hash and update the hash.
2404                my $mappedName = "$objectName$suffix";
2405                $objectHash{$objectName} = $suffix + 1;
2406                # The FROM list has the object name followed by the mapped name. This
2407                # tells SQL it's still the same table, but we're using a different name
2408                # for it to avoid confusion.
2409                push @fromList, "$objectName $mappedName";
2410                # The mapped-name list contains the real mapped name.
2411                push @mappedNameList, $mappedName;
2412                # Finally, enable us to get back from the mapped name to the object name.
2413                $mappedNameHash{$mappedName} = $objectName;
2414            }
2415        }
2416        # Begin the SELECT suffix. It starts with
2417        #
2418        # FROM name1, name2, ... nameN
2419        #
2420        my $suffix = "FROM " . join(', ', @fromList);
2421        # Check for a filter clause.
2422        if ($filterClause) {
2423            # Here we have one, so we convert its field names and add it to the query. First,
2424            # We create a copy of the filter string we can work with.
2425            my $filterString = $filterClause;
2426            # Next, we sort the object names by length. This helps protect us from finding
2427            # object names inside other object names when we're doing our search and replace.
2428            my @sortedNames = sort { length($b) - length($a) } @mappedNameList;
2429            # We will also keep a list of conditions to add to the WHERE clause in order to link
2430            # entities and relationships as well as primary relations to secondary ones.
2431            my @joinWhere = ();
2432            # The final preparatory step is to create a hash table of relation names. The
2433            # table begins with the relation names already in the SELECT command. We may
2434            # need to add relations later if there is filtering on a field in a secondary
2435            # relation. The secondary relations are the ones that contain multiply-
2436            # occurring or optional fields.
2437            my %fromNames = map { $_ => 1 } @sortedNames;
2438            # We are ready to begin. We loop through the object names, replacing each
2439            # object name's field references by the corresponding SQL field reference.
2440            # Along the way, if we find a secondary relation, we will need to add it
2441            # to the FROM clause.
2442            for my $mappedName (@sortedNames) {
2443                # Get the length of the object name plus 2. This is the value we add to the
2444                # size of the field name to determine the size of the field reference as a
2445                # whole.
2446                my $nameLength = 2 + length $mappedName;
2447                # Get the real object name for this mapped name.
2448                my $objectName = $mappedNameHash{$mappedName};
2449                Trace("Processing $mappedName for object $objectName.") if T(4);
2450                # Get the object's field list.
2451                my $fieldList = $self->GetFieldTable($objectName);
2452                # Find the field references for this object.
2453                while ($filterString =~ m/$mappedName\(([^)]*)\)/g) {
2454                    # At this point, $1 contains the field name, and the current position
2455                    # is set immediately after the final parenthesis. We pull out the name of
2456                    # the field and the position and length of the field reference as a whole.
2457                    my $fieldName = $1;
2458                    my $len = $nameLength + length $fieldName;
2459                    my $pos = pos($filterString) - $len;
2460                    # Insure the field exists.
2461                    if (!exists $fieldList->{$fieldName}) {
2462                        Confess("Field $fieldName not found for object $objectName.");
2463                    } else {
2464                        Trace("Processing $fieldName at position $pos.") if T(4);
2465                        # Get the field's relation.
2466                        my $relationName = $fieldList->{$fieldName}->{relation};
2467                        # Now we have a secondary relation. We need to insure it matches the
2468                        # mapped name of the primary relation. First we peel off the suffix
2469                        # from the mapped name.
2470                        my $mappingSuffix = substr $mappedName, length($objectName);
2471                        # Put the mapping suffix onto the relation name to get the
2472                        # mapped relation name.
2473                        my $mappedRelationName = "$relationName$mappingSuffix";
2474                        # Insure the relation is in the FROM clause.
2475                        if (!exists $fromNames{$mappedRelationName}) {
2476                            # Add the relation to the FROM clause.
2477                            if ($mappedRelationName eq $relationName) {
2478                                # The name is un-mapped, so we add it without
2479                                # any frills.
2480                                $suffix .= ", $relationName";
2481                                push @joinWhere, "$objectName.id = $relationName.id";
2482                            } else {
2483                                # Here we have a mapping situation.
2484                                $suffix .= ", $relationName $mappedRelationName";
2485                                push @joinWhere, "$mappedRelationName.id = $mappedName.id";
2486                            }
2487                            # Denote we have this relation available for future fields.
2488                            $fromNames{$mappedRelationName} = 1;
2489                        }
2490                        # Form an SQL field reference from the relation name and the field name.
2491                        my $sqlReference = "$mappedRelationName." . _FixName($fieldName);
2492                        # Put it into the filter string in place of the old value.
2493                        substr($filterString, $pos, $len) = $sqlReference;
2494                        # Reposition the search.
2495                        pos $filterString = $pos + length $sqlReference;
2496                    }
2497                }
2498            }
2499            # The next step is to join the objects together. We only need to do this if there
2500            # is more than one object in the object list. We start with the first object and
2501            # run through the objects after it. Note also that we make a safety copy of the
2502            # list before running through it.
2503            my @mappedObjectList = @mappedNameList;
2504            my $lastMappedObject = shift @mappedObjectList;
2505            # Get the join table.
2506            my $joinTable = $self->{_metaData}->{Joins};
2507            # Loop through the object list.
2508            for my $thisMappedObject (@mappedObjectList) {
2509                # Look for a join using the real object names.
2510                my $lastObject = $mappedNameHash{$lastMappedObject};
2511                my $thisObject = $mappedNameHash{$thisMappedObject};
2512                my $joinKey = "$lastObject/$thisObject";
2513                if (!exists $joinTable->{$joinKey}) {
2514                    # Here there's no join, so we throw an error.
2515                    Confess("No join exists to connect from $lastMappedObject to $thisMappedObject.");
2516                } else {
2517                    # Get the join clause.
2518                    my $unMappedJoin = $joinTable->{$joinKey};
2519                    # Fix the names.
2520                    $unMappedJoin =~ s/$lastObject/$lastMappedObject/;
2521                    $unMappedJoin =~ s/$thisObject/$thisMappedObject/;
2522                    push @joinWhere, $unMappedJoin;
2523                    # Save this object as the last object for the next iteration.
2524                    $lastMappedObject = $thisMappedObject;
2525                }
2526            }
2527            # Now we need to handle the whole ORDER BY / LIMIT thing. The important part
2528            # here is we want the filter clause to be empty if there's no WHERE filter.
2529            # We'll put the ORDER BY / LIMIT clauses in the following variable.
2530            my $orderClause = "";
2531            # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy
2532            # operator so that we find the first occurrence of either verb.
2533            if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {
2534                # Here we have an ORDER BY or LIMIT verb. Split it off of the filter string.
2535                my $pos = pos $filterString;
2536                $orderClause = $2 . substr($filterString, $pos);
2537                $filterString = $1;
2538            }
2539            # Add the filter and the join clauses (if any) to the SELECT command.
2540            if ($filterString) {
2541                Trace("Filter string is \"$filterString\".") if T(4);
2542                push @joinWhere, "($filterString)";
2543            }
2544            if (@joinWhere) {
2545                $suffix .= " WHERE " . join(' AND ', @joinWhere);
2546            }
2547            # Add the sort or limit clause (if any) to the SELECT command.
2548            if ($orderClause) {
2549                $suffix .= " $orderClause";
2550            }
2551        }
2552        # Return the suffix, the mapped name list, and the mapped name hash.
2553        return ($suffix, \@mappedNameList, \%mappedNameHash);
2554    }
2555    
2556    =head3 GetStatementHandle
2557    
2558    This method will prepare and execute an SQL query, returning the statement handle.
2559    The main reason for doing this here is so that everybody who does SQL queries gets
2560    the benefit of tracing.
2561    
2562    This is an instance method.
2563    
2564    =over 4
2565    
2566    =item command
2567    
2568    Command to prepare and execute.
2569    
2570    =item params
2571    
2572    Reference to a list of the values to be substituted in for the parameter marks.
2573    
2574    =item RETURN
2575    
2576    Returns a prepared and executed statement handle from which the caller can extract
2577    results.
2578    
2579    =back
2580    
2581    =cut
2582    
2583    sub _GetStatementHandle {
2584        # Get the parameters.
2585        my ($self, $command, $params) = @_;
2586        # Trace the query.
2587        Trace("SQL query: $command") if T(SQL => 3);
2588        Trace("PARMS: '" . (join "', '", @{$params}) . "'") if (T(SQL => 4) && (@{$params} > 0));
2589        # Get the database handle.
2590        my $dbh = $self->{_dbh};
2591        # Prepare the command.
2592        my $sth = $dbh->prepare_command($command);
2593        # Execute it with the parameters bound in.
2594        $sth->execute(@{$params}) || Confess("SELECT error" . $sth->errstr());
2595        # Return the statement handle.
2596        return $sth;
2597    }
2598    
2599  =head3 GetLoadStats  =head3 GetLoadStats
2600    
2601  Return a blank statistics object for use by the load methods.  Return a blank statistics object for use by the load methods.
# Line 2505  Line 3153 
3153              # 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.
3154              my $fromEntity = $relationship->{from};              my $fromEntity = $relationship->{from};
3155              my $toEntity = $relationship->{to};              my $toEntity = $relationship->{to};
3156              Trace("Join check for relationship $relationshipName from $fromEntity to $toEntity.") if T(4);              Trace("Join check for relationship $relationshipName from $fromEntity to $toEntity.") if T(Joins => 4);
3157              if ($fromEntity eq $entityName) {              if ($fromEntity eq $entityName) {
3158                  if ($toEntity eq $entityName) {                  if ($toEntity eq $entityName) {
3159                      # Here the relationship is recursive.                      # Here the relationship is recursive.
# Line 2594  Line 3242 
3242      return $metadata;      return $metadata;
3243  }  }
3244    
3245    =head3 SortNeeded
3246    
3247    C<< my $parms = $erdb->SortNeeded($relationName); >>
3248    
3249    Return the pipe command for the sort that should be applied to the specified
3250    relation when creating the load file.
3251    
3252    For example, if the load file should be sorted ascending by the first
3253    field with duplicates removed, this method would return
3254    
3255        sort -k 1 -u -t "\t"
3256    
3257    If the first field is numeric and duplicates are okay, the method would
3258    return
3259    
3260        sort -k 1n -t "\t"
3261    
3262    =over 4
3263    
3264    =item relationName
3265    
3266    Name of the relation to be examined.
3267    
3268    =item
3269    
3270    Returns the sort command to use for sorting the relation, suitable for piping.
3271    
3272    =back
3273    
3274    =cut
3275    #: Return Type $;
3276    sub SortNeeded {
3277        # Get the parameters.
3278        my ($self, $relationName) = @_;
3279        # Declare a descriptor to hold the names of the key fields.
3280        my @keyNames = ();
3281        # Declare a flag for indicating uniqueness.
3282        my $unique;
3283        # Get the relation structure.
3284        my $relationData = $self->_FindRelation($relationName);
3285        # Find out if the relation is a primary entity relation,
3286        # a relationship relation, or a secondary entity relation.
3287        my $entityTable = $self->{_metaData}->{Entities};
3288        my $relationshipTable = $self->{_metaData}->{Relationships};
3289        if (exists $entityTable->{$relationName}) {
3290            # Here we have a primary entity relation, so we have a unique sort on the
3291            # ID field.
3292            $unique = "-u ";
3293            push @keyNames, "id";
3294        } elsif (exists $relationshipTable->{$relationName}) {
3295            # Here we have a relationship. We sort using the FROM index.
3296            $unique = "";
3297            my $relationshipData = $relationshipTable->{$relationName};
3298            my $index = $relationData->{Indexes}->{"idx${relationName}From"};
3299            push @keyNames, @{$index->{IndexFields}};
3300        } else {
3301            # Here we have a secondary entity relation, so we have a non-unique sort on
3302            # the ID field.
3303            $unique = "";
3304            push @keyNames, "id";
3305        }
3306        # Now we parse the key names into sort parameters. First, we prime the return
3307        # string.
3308        my $retVal = "sort -t \"\t\" $unique";
3309        # Get the relation's field list.
3310        my @fields = @{$relationData->{Fields}};
3311        # Loop through the keys.
3312        for my $keyData (@keyNames) {
3313            # Get the key and the ordering.
3314            my ($keyName, $ordering);
3315            if ($keyData =~ /^([^ ]+) DESC/) {
3316                ($keyName, $ordering) = ($1, "descending");
3317            } else {
3318                ($keyName, $ordering) = ($keyData, "ascending");
3319            }
3320            # Find the key's position and type.
3321            my $fieldSpec;
3322            for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {
3323                my $thisField = $fields[$i];
3324                if ($thisField->{name} eq $keyName) {
3325                    # Get the sort modifier for this field type. The modifier
3326                    # decides whether we're using a character, numeric, or
3327                    # floating-point sort.
3328                    my $modifier = $TypeTable{$thisField->{type}}->{sort};
3329                    # If the index is descending for this field, denote we want
3330                    # to reverse the sort order on this field.
3331                    if ($ordering eq 'descending') {
3332                        $modifier .= "r";
3333                    }
3334                    # Store the position and modifier into the field spec, which
3335                    # will stop the inner loop. Note that the field number is
3336                    # 1-based in the sort command, so we have to increment the
3337                    # index.
3338                    $fieldSpec = ($i + 1) . $modifier;
3339                }
3340            }
3341            # Add this field to the sort command.
3342            $retVal .= " -k $fieldSpec";
3343        }
3344        # Return the result.
3345        return $retVal;
3346    }
3347    
3348  =head3 CreateRelationshipIndex  =head3 CreateRelationshipIndex
3349    
3350  Create an index for a relationship's relation.  Create an index for a relationship's relation.

Legend:
Removed from v.1.38  
changed lines
  Added in v.1.66

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3