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

Diff of /Sprout/ERDB.pm

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

revision 1.28, Thu Oct 20 09:31:02 2005 UTC revision 1.94, Thu Dec 6 14:58:03 2007 UTC
# Line 6  Line 6 
6      use Data::Dumper;      use Data::Dumper;
7      use XML::Simple;      use XML::Simple;
8      use DBQuery;      use DBQuery;
9      use DBObject;      use ERDBObject;
10      use Stats;      use Stats;
11      use Time::HiRes qw(gettimeofday);      use Time::HiRes qw(gettimeofday);
12      use FIG;      use Digest::MD5 qw(md5_base64);
13        use CGI;
14    
15  =head1 Entity-Relationship Database Package  =head1 Entity-Relationship Database Package
16    
# Line 58  Line 59 
59  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
60  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.
61    
62  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
63  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
64  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
65  to generate documentation for the database.  for the database.
66    
67    Special support is provided for text searching. An entity field can be marked as <em>searchable</em>,
68    in which case it will be used to generate a text search index in which the user searches for words
69    in the field instead of a particular field value.
70    
71  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
72  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
73  was inserted by the L</InsertObject> method.  was inserted by the L</InsertObject> method.
74    
 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.  
   
75  =head2 XML Database Description  =head2 XML Database Description
76    
77  =head3 Data Types  =head3 Data Types
# 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 170  Line 190 
190    
191  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<->),
192  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
193  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,
194    the name C<search-relevance> has special meaning for full-text searches and should not be
195    used as a field name.
196    
197  =item type  =item type
198    
# Line 189  Line 211 
211  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
212  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.
213    
214    =item searchable
215    
216    If specified, then the field is a candidate for full-text searching. A single full-text
217    index will be created for each relation with at least one searchable field in it.
218    For best results, this option should only be used for string or text fields.
219    
220    =item special
221    
222    This attribute allows the subclass to assign special meaning for certain fields.
223    The interpretation is up to the subclass itself. Currently, only entity fields
224    can have this attribute.
225    
226  =back  =back
227    
228  =head3 Indexes  =head3 Indexes
229    
230  An entity can have multiple alternate indexes associated with it. The fields must  An entity can have multiple alternate indexes associated with it. The fields in an
231  be from the primary relation. The alternate indexes assist in ordering results  index must all be from the same relation. The alternate indexes assist in searching
232  from a query. A relationship can have up to two indexes-- a I<to-index> and a  on fields other than the entity ID. A relationship has at least two indexes-- a I<to-index> and a
233  I<from-index>. These order the results when crossing the relationship. For  I<from-index> that order the results when crossing the relationship. For
234  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
235  from-index would order the contigs of a ganome, and the to-index would order  from-index would order the contigs of a ganome, and the to-index would order
236  the genomes of a contig. A relationship's index must specify only fields in  the genomes of a contig. In addition, it can have zero or more alternate
237    indexes. A relationship's index must specify only fields in
238  the relationship.  the relationship.
239    
240  The indexes for an entity must be listed inside the B<Indexes> tag. The from-index  The alternate indexes for an entity or relationship must be listed inside the B<Indexes> tag.
241  of a relationship is specified using the B<FromIndex> tag; the to-index is specified  The from-index of a relationship is specified using the B<FromIndex> tag; the to-index is
242  using the B<ToIndex> tag.  specified using the B<ToIndex> tag.
243    
244  Each index can contain a B<Notes> tag. In addition, it will have an B<IndexFields>  Each index can contain a B<Notes> tag. In addition, it will have an B<IndexFields>
245  tag containing the B<IndexField> tags. These specify, in order, the fields used in  tag containing the B<IndexField> tags. These specify, in order, the fields used in
# Line 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 266  Line 303 
303    
304  A relationship is described by the C<Relationship> tag. Within a relationship,  A relationship is described by the C<Relationship> tag. Within a relationship,
305  there can be a C<Notes> tag, a C<Fields> tag containing the intersection data  there can be a C<Notes> tag, a C<Fields> tag containing the intersection data
306  fields, a C<FromIndex> tag containing the from-index, and a C<ToIndex> tag containing  fields, a C<FromIndex> tag containing the from-index, a C<ToIndex> tag containing
307  the to-index.  the to-index, and an C<Indexes> tag containing the alternate indexes.
308    
309  The C<Relationship> tag has the following attributes.  The C<Relationship> tag has the following attributes.
310    
# Line 300  Line 337 
337    
338  # Table of information about our datatypes. "sqlType" is the corresponding SQL datatype string.  # Table of information about our datatypes. "sqlType" is the corresponding SQL datatype string.
339  # "maxLen" is the maximum permissible length of the incoming string data used to populate a field  # "maxLen" is the maximum permissible length of the incoming string data used to populate a field
340  # of the specified type. "dataGen" is PERL string that will be evaluated if no test data generation  # of the specified type. "avgLen" is the average byte length for estimating
341  # string is specified in the field definition. "avgLen" is the average byte length for estimating  # record sizes. "sort" is the key modifier for the sort command, "notes" is a type description,
342  # record sizes.  # and "indexMod", if non-zero, is the number of characters to use when the field is specified in an
343  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, dataGen => "StringGen('A')" },  # index
344                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, dataGen => "IntGen(0, 99999999)" },  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",
345                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, dataGen => "StringGen(IntGen(10,250))" },                                 indexMod =>   0, notes => "single ASCII character"},
346                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, dataGen => "StringGen(IntGen(80,1000))" },                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n",
347                    date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, dataGen => "DateGen(-7, 7, IntGen(0,1400))" },                                 indexMod =>   0, notes => "signed 32-bit integer"},
348                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, dataGen => "FloatGen(0.0, 100.0)" },                    counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n",
349                    boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   2, dataGen => "IntGen(0, 1)" },                                 indexMod =>   0, notes => "unsigned 32-bit integer"},
350                      string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, sort => "",
351                                   indexMod =>   0, notes => "character string, 0 to 255 characters"},
352                      text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, sort => "",
353                                   indexMod => 255, notes => "character string, nearly unlimited length, only first 255 characters are indexed"},
354                      date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, sort => "n",
355                                   indexMod =>   0, notes => "signed, 64-bit integer"},
356                      float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, sort => "g",
357                                   indexMod =>   0, notes => "64-bit double precision floating-point number"},
358                      boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, sort => "n",
359                                   indexMod =>   0, notes => "boolean value: 0 if false, 1 if true"},
360                     'hash-string' =>
361                                 { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, sort => "",
362                                   indexMod =>   0, notes => "string stored in digested form, used for certain types of key fields"},
363                     'id-string' =>
364                                 { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, sort => "",
365                                   indexMod =>   0, notes => "character string, 0 to 25 characters"},
366                   'key-string' =>                   'key-string' =>
367                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, dataGen => "StringGen(IntGen(10,40))" },                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, sort => "",
368                                   indexMod =>   0, notes => "character string, 0 to 40 characters"},
369                   'name-string' =>                   'name-string' =>
370                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, dataGen => "StringGen(IntGen(10,80))" },                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, sort => "",
371                                   indexMod =>   0, notes => "character string, 0 to 80 characters"},
372                   'medium-string' =>                   'medium-string' =>
373                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, dataGen => "StringGen(IntGen(10,160))" },                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",
374                                   indexMod =>   0, notes => "character string, 0 to 160 characters"},
375                     'long-string' =>
376                                 { sqlType => 'VARCHAR(500)',       maxLen => 500,          avglen => 255, sort => "",
377                                   indexMod =>   0, notes => "character string, 0 to 500 characters"},
378                  );                  );
379    
380  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 324  Line 383 
383                     'MM' => 'many-to-many'                     'MM' => 'many-to-many'
384                   );                   );
385    
386  # Table for interpreting string patterns.  # Options for XML input and output.
387    
388    my %XmlOptions = (GroupTags =>  { Relationships => 'Relationship',
389                                      Entities => 'Entity',
390                                      Fields => 'Field',
391                                      Indexes => 'Index',
392                                      IndexFields => 'IndexField'
393                                    },
394                      KeyAttr =>    { Relationship => 'name',
395                                      Entity => 'name',
396                                      Field => 'name'
397                                    },
398                      SuppressEmpty => 1,
399                     );
400    
401  my %PictureTable = ( 'A' => "abcdefghijklmnopqrstuvwxyz",  my %XmlInOpts  = (
402                       '9' => "0123456789",                    ForceArray => ['Field', 'Index', 'IndexField', 'Relationship', 'Entity'],
403                       'X' => "abcdefghijklmnopqrstuvwxyz0123456789",                    ForceContent => 1,
404                       'V' => "aeiou",                    NormalizeSpace => 2,
                      'K' => "bcdfghjklmnoprstvwxyz"  
405                     );                     );
406    my %XmlOutOpts = (
407                      RootName => 'Database',
408                      XMLDecl => 1,
409                     );
410    
411    
412  =head2 Public Methods  =head2 Public Methods
413    
414  =head3 new  =head3 new
415    
416  C<< my $database = ERDB->new($dbh, $metaFileName); >>      my $database = ERDB->new($dbh, $metaFileName);
417    
418  Create a new ERDB object.  Create a new ERDB object.
419    
# Line 371  Line 447 
447    
448  =head3 ShowMetaData  =head3 ShowMetaData
449    
450  C<< $erdb->ShowMetaData($fileName); >>      $erdb->ShowMetaData($fileName);
451    
452  This method outputs a description of the database. This description can be used to help users create  This method outputs a description of the database. This description can be used to help users create
453  the data to be loaded into the relations.  the data to be loaded into the relations.
# Line 402  Line 478 
478      # Write the HTML heading stuff.      # Write the HTML heading stuff.
479      print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";      print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";
480      print HTMLOUT "</head>\n<body>\n";      print HTMLOUT "</head>\n<body>\n";
481        # Write the documentation.
482        print HTMLOUT $self->DisplayMetaData();
483        # Close the document.
484        print HTMLOUT "</body>\n</html>\n";
485        # Close the file.
486        close HTMLOUT;
487    }
488    
489    =head3 DisplayMetaData
490    
491        my $html = $erdb->DisplayMetaData();
492    
493    Return an HTML description of the database. This description can be used to help users create
494    the data to be loaded into the relations and form queries. The output is raw includable HTML
495    without any HEAD or BODY tags.
496    
497    =over 4
498    
499    =item filename
500    
501    The name of the output file.
502    
503    =back
504    
505    =cut
506    
507    sub DisplayMetaData {
508        # Get the parameters.
509        my ($self) = @_;
510        # Get the metadata and the title string.
511        my $metadata = $self->{_metaData};
512        # Get the title string.
513        my $title = $metadata->{Title};
514        # Get the entity and relationship lists.
515        my $entityList = $metadata->{Entities};
516        my $relationshipList = $metadata->{Relationships};
517        # Declare the return variable.
518        my $retVal = "";
519        # Open the output file.
520        Trace("Building MetaData table of contents.") if T(4);
521      # Here we do the table of contents. It starts as an unordered list of section names. Each      # Here we do the table of contents. It starts as an unordered list of section names. Each
522      # section contains an ordered list of entity or relationship subsections.      # section contains an ordered list of entity or relationship subsections.
523      print HTMLOUT "<ul>\n<li><a href=\"#EntitiesSection\">Entities</a>\n<ol>\n";      $retVal .= "<ul>\n<li><a href=\"#EntitiesSection\">Entities</a>\n<ol>\n";
524      # Loop through the Entities, displaying a list item for each.      # Loop through the Entities, displaying a list item for each.
525      foreach my $key (sort keys %{$entityList}) {      foreach my $key (sort keys %{$entityList}) {
526          # Display this item.          # Display this item.
527          print HTMLOUT "<li><a href=\"#$key\">$key</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$key</a></li>\n";
528      }      }
529      # Close off the entity section and start the relationship section.      # Close off the entity section and start the relationship section.
530      print HTMLOUT "</ol></li>\n<li><a href=\"#RelationshipsSection\">Relationships</a>\n<ol>\n";      $retVal .= "</ol></li>\n<li><a href=\"#RelationshipsSection\">Relationships</a>\n<ol>\n";
531      # Loop through the Relationships.      # Loop through the Relationships.
532      foreach my $key (sort keys %{$relationshipList}) {      foreach my $key (sort keys %{$relationshipList}) {
533          # Display this item.          # Display this item.
534          my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});          my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});
535          print HTMLOUT "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";
536      }      }
537      # Close off the relationship section and list the join table section.      # Close off the relationship section and list the join table section.
538      print HTMLOUT "</ol></li>\n<li><a href=\"#JoinTable\">Join Table</a></li>\n";      $retVal .= "</ol></li>\n<li><a href=\"#JoinTable\">Join Table</a></li>\n";
539      # Close off the table of contents itself.      # Close off the table of contents itself.
540      print HTMLOUT "</ul>\n";      $retVal .=  "</ul>\n";
541      # Now we start with the actual data. Denote we're starting the entity section.      # Now we start with the actual data. Denote we're starting the entity section.
542      print HTMLOUT "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";      $retVal .= "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";
543      # Loop through the entities.      # Loop through the entities.
544      for my $key (sort keys %{$entityList}) {      for my $key (sort keys %{$entityList}) {
545          Trace("Building MetaData entry for $key entity.") if T(4);          Trace("Building MetaData entry for $key entity.") if T(4);
546          # Create the entity header. It contains a bookmark and the entity name.          # Create the entity header. It contains a bookmark and the entity name.
547          print HTMLOUT "<a name=\"$key\"></a><h3>$key</h3>\n";          $retVal .= "<a name=\"$key\"></a><h3>$key</h3>\n";
548          # Get the entity data.          # Get the entity data.
549          my $entityData = $entityList->{$key};          my $entityData = $entityList->{$key};
550          # If there's descriptive text, display it.          # If there's descriptive text, display it.
551          if (my $notes = $entityData->{Notes}) {          if (my $notes = $entityData->{Notes}) {
552              print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
553          }          }
554          # Now we want a list of the entity's relationships. First, we set up the relationship subsection.          # See if we need a list of the entity's relationships.
555          print HTMLOUT "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          my $relCount = keys %{$relationshipList};
556            if ($relCount > 0) {
557                # First, we set up the relationship subsection.
558                $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
559          # Loop through the relationships.          # Loop through the relationships.
560          for my $relationship (sort keys %{$relationshipList}) {          for my $relationship (sort keys %{$relationshipList}) {
561              # Get the relationship data.              # Get the relationship data.
# Line 446  Line 565 
565                  # Get the relationship sentence and append the arity.                  # Get the relationship sentence and append the arity.
566                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);
567                  # Display the relationship data.                  # Display the relationship data.
568                  print HTMLOUT "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";                      $retVal .= "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";
569              }              }
570          }          }
571          # Close off the relationship list.          # Close off the relationship list.
572          print HTMLOUT "</ul>\n";              $retVal .= "</ul>\n";
573            }
574          # Get the entity's relations.          # Get the entity's relations.
575          my $relationList = $entityData->{Relations};          my $relationList = $entityData->{Relations};
576          # Create a header for the relation subsection.          # Create a header for the relation subsection.
577          print HTMLOUT "<h4>Relations for <b>$key</b></h4>\n";          $retVal .= "<h4>Relations for <b>$key</b></h4>\n";
578          # Loop through the relations, displaying them.          # Loop through the relations, displaying them.
579          for my $relation (sort keys %{$relationList}) {          for my $relation (sort keys %{$relationList}) {
580              my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});              my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});
581              print HTMLOUT $htmlString;              $retVal .= $htmlString;
582          }          }
583      }      }
584      # Denote we're starting the relationship section.      # Denote we're starting the relationship section.
585      print HTMLOUT "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";      $retVal .= "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";
586      # Loop through the relationships.      # Loop through the relationships.
587      for my $key (sort keys %{$relationshipList}) {      for my $key (sort keys %{$relationshipList}) {
588          Trace("Building MetaData entry for $key relationship.") if T(4);          Trace("Building MetaData entry for $key relationship.") if T(4);
# Line 470  Line 590 
590          my $relationshipStructure = $relationshipList->{$key};          my $relationshipStructure = $relationshipList->{$key};
591          # Create the relationship header.          # Create the relationship header.
592          my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);          my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);
593          print HTMLOUT "<h3><a name=\"$key\"></a>$headerText</h3>\n";          $retVal .= "<h3><a name=\"$key\"></a>$headerText</h3>\n";
594          # Get the entity names.          # Get the entity names.
595          my $fromEntity = $relationshipStructure->{from};          my $fromEntity = $relationshipStructure->{from};
596          my $toEntity = $relationshipStructure->{to};          my $toEntity = $relationshipStructure->{to};
# Line 480  Line 600 
600          # since both sentences will say the same thing.          # since both sentences will say the same thing.
601          my $arity = $relationshipStructure->{arity};          my $arity = $relationshipStructure->{arity};
602          if ($arity eq "11") {          if ($arity eq "11") {
603              print HTMLOUT "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";
604          } else {          } else {
605              print HTMLOUT "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";
606              if ($arity eq "MM" && $fromEntity ne $toEntity) {              if ($arity eq "MM" && $fromEntity ne $toEntity) {
607                  print HTMLOUT "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";                  $retVal .= "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";
608              }              }
609          }          }
610          print HTMLOUT "</p>\n";          $retVal .= "</p>\n";
611          # If there are notes on this relationship, display them.          # If there are notes on this relationship, display them.
612          if (my $notes = $relationshipStructure->{Notes}) {          if (my $notes = $relationshipStructure->{Notes}) {
613              print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
614          }          }
615          # Generate the relationship's relation table.          # Generate the relationship's relation table.
616          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
617          print HTMLOUT $htmlString;          $retVal .= $htmlString;
618      }      }
619      Trace("Building MetaData join table.") if T(4);      Trace("Building MetaData join table.") if T(4);
620      # Denote we're starting the join table.      # Denote we're starting the join table.
621      print HTMLOUT "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";      $retVal .= "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";
622      # Create a table header.      # Create a table header.
623      print HTMLOUT _OpenTable("Join Table", "Source", "Target", "Join Condition");      $retVal .= _OpenTable("Join Table", "Source", "Target", "Join Condition");
624      # Loop through the joins.      # Loop through the joins.
625      my $joinTable = $metadata->{Joins};      my $joinTable = $metadata->{Joins};
626      my @joinKeys = keys %{$joinTable};      my @joinKeys = keys %{$joinTable};
# Line 508  Line 628 
628          # Separate out the source, the target, and the join clause.          # Separate out the source, the target, and the join clause.
629          $joinKey =~ m!^([^/]+)/(.+)$!;          $joinKey =~ m!^([^/]+)/(.+)$!;
630          my ($sourceRelation, $targetRelation) = ($1, $2);          my ($sourceRelation, $targetRelation) = ($1, $2);
631          Trace("Join with key $joinKey is from $sourceRelation to $targetRelation.") if T(4);          Trace("Join with key $joinKey is from $sourceRelation to $targetRelation.") if T(Joins => 4);
632          my $source = $self->ComputeObjectSentence($sourceRelation);          my $source = $self->ComputeObjectSentence($sourceRelation);
633          my $target = $self->ComputeObjectSentence($targetRelation);          my $target = $self->ComputeObjectSentence($targetRelation);
634          my $clause = $joinTable->{$joinKey};          my $clause = $joinTable->{$joinKey};
635          # Display them in a table row.          # Display them in a table row.
636          print HTMLOUT "<tr><td>$source</td><td>$target</td><td>$clause</td></tr>\n";          $retVal .= "<tr><td>$source</td><td>$target</td><td>$clause</td></tr>\n";
637      }      }
638      # Close the table.      # Close the table.
639      print HTMLOUT _CloseTable();      $retVal .= _CloseTable();
640      # Close the document.      Trace("Built MetaData HTML.") if T(3);
641      print HTMLOUT "</body>\n</html>\n";      # Return the HTML.
642      # Close the file.      return $retVal;
     close HTMLOUT;  
     Trace("Built MetaData web page.") if T(3);  
643  }  }
644    
645  =head3 DumpMetaData  =head3 DumpMetaData
646    
647  C<< $erdb->DumpMetaData(); >>      $erdb->DumpMetaData();
648    
649  Return a dump of the metadata structure.  Return a dump of the metadata structure.
650    
# Line 539  Line 657 
657      return Data::Dumper::Dumper($self->{_metaData});      return Data::Dumper::Dumper($self->{_metaData});
658  }  }
659    
660    =head3 CreatePPO
661    
662        ERDB::CreatePPO($erdbXMLFile, $ppoXMLFile);
663    
664    Create a PPO XML file from an ERDB data definition XML file. At the
665    current time, the PPO XML file can be used to create a database with
666    similar functionality. Eventually, the PPO will be able to use the
667    created XML to access the live ERDB database.
668    
669    =over 4
670    
671    =item erdbXMLFile
672    
673    Name of the XML data definition file for the ERDB database. This
674    file must exist.
675    
676    =item ppoXMLFile
677    
678    Output file for the PPO XML definition. If this file exists, it
679    will be overwritten.
680    
681    =back
682    
683    =cut
684    
685    sub CreatePPO {
686        # Get the parameters.
687        my ($erdbXMLFile, $ppoXMLFile) = @_;
688        # First, we want to slurp in the ERDB XML file in its raw form.
689        my $xml = ReadMetaXML($erdbXMLFile);
690        # Create a variable to hold all of the objects in the PPO project.
691        my @objects = ();
692        # Get the relationship hash.
693        my $relationships = $xml->{Relationships};
694        # Loop through the entities.
695        my $entities = $xml->{Entities};
696        for my $entityName (keys %{$entities}) {
697            # Get the entity's data structures.
698            my $entityObject = $entities->{$entityName};
699            # We put the object's fields in here, according to their type.
700            my (@object_refs, @scalars, @indexes, @arrays);
701            # Create the ID field for the entity. We get the key type from the
702            # entity object and compute the corresponding SQL type.
703            my $type = $TypeTable{$entityObject->{keyType}}->{sqlType};
704            push @scalars, { label => 'id', type => $type };
705            # Loop through the entity fields.
706            for my $fieldName ( keys %{$entityObject->{Fields}} ) {
707                # Get the field object.
708                my $fieldObject = $entityObject->{Fields}->{$fieldName};
709                # Convert it to a scalar tag.
710                my $scalar = _CreatePPOField($fieldName, $fieldObject);
711                # If we have a relation, this field is stored in an array.
712                # otherwise, it is a scalar. The array tag has scalars
713                # stored as an XML array. In ERDB, there is only ever one,
714                # but PPO can have more.
715                my $relation = $fieldObject->{relation};
716                if ($relation) {
717                    push @arrays, { scalar => [$scalar] };
718                } else {
719                    push @scalars, $scalar;
720                }
721            }
722            # Loop through the relationships. If this entity is the to-entity
723            # on a relationship of 1M arity, then it is implemented as a PPO
724            # object reference.
725            for my $relationshipName (keys %{$relationships}) {
726                # Get the relationship data.
727                my $relationshipData = $relationships->{$relationshipName};
728                # If we have a from for this entity and an arity of 1M, we
729                # have an object reference.
730                if ($relationshipData->{to} eq $entityName &&
731                    $relationshipData->{arity} eq '1M') {
732                    # Build the object reference tag.
733                    push @object_refs, { label => $relationshipName,
734                                         type => $relationshipData->{from} };
735                }
736            }
737            # Create the indexes.
738            my $indexList = $entityObject->{Indexes};
739            push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
740            # Build the object XML tree.
741            my $object = { label => $entityName,
742                           object_ref => \@object_refs,
743                           scalar => \@scalars,
744                           index => \@indexes,
745                           array => \@arrays
746                          };
747            # Push the object onto the objects list.
748            push @objects, $object;
749        }
750        # Loop through the relationships, searching for MMs. The 1Ms were
751        # already handled by the entity search above.
752        for my $relationshipName (keys %{$relationships}) {
753            # Get this relationship's object.
754            my $relationshipObject = $relationships->{$relationshipName};
755            # Only proceed if it's many-to-many.
756            if ($relationshipObject->{arity} eq 'MM') {
757                # Create the tag lists for the relationship object.
758                my (@object_refs, @scalars, @indexes);
759                # The relationship will be created as an object with object
760                # references for its links to the participating entities.
761                my %links = ( from_link => $relationshipObject->{from},
762                              to_link => $relationshipObject->{to} );
763                for my $link (keys %links) {
764                    # Create an object_ref tag for this piece of the
765                    # relationship (from or to).
766                    my $object_ref = { label => $link,
767                                       type => $links{$link} };
768                    push @object_refs, $object_ref;
769                }
770                # Loop through the intersection data fields, creating scalar tags.
771                # There are no fancy array tags in a relationship.
772                for my $fieldName (keys %{$relationshipObject->{Fields}}) {
773                    my $fieldObject = $relationshipObject->{Fields}->{$fieldName};
774                    push @scalars, _CreatePPOField($fieldName, $fieldObject);
775                }
776                # Finally, the indexes: currently we cannot support the to-index and
777                # from-index in PPO, so we just process the alternate indexes.
778                my $indexList = $relationshipObject->{Indexes};
779                push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
780                # Wrap up all the stuff about this relationship.
781                my $object = { label => $relationshipName,
782                               scalar => \@scalars,
783                               object_ref => \@object_refs,
784                               index => \@indexes
785                             };
786                # Push it into the object list.
787                push @objects, $object;
788            }
789        }
790        # Compute a title.
791        my $title;
792        if ($erdbXMLFile =~ /(\/|^)([^\/]+)DBD\.xml/) {
793            # Here we have a standard file name we can use for a title.
794            $title = $2;
795        } else {
796            # Here the file name is non-standard, so we carve up the
797            # database title.
798            $title = $xml->{Title}->{content};
799            $title =~ s/\s\.,//g;
800        }
801        # Wrap up the XML as a project.
802        my $ppoXML = { project => { label => $title,
803                                    object => \@objects }};
804        # Write out the results.
805        my $ppoString = XML::Simple::XMLout($ppoXML,
806                                            AttrIndent => 1,
807                                            KeepRoot => 1);
808        Tracer::PutFile($ppoXMLFile, [ $ppoString ]);
809    }
810    
811    =head3 FindIndexForEntity
812    
813        my $indexFound = ERDB::FindIndexForEntity($xml, $entityName, $attributeName);
814    
815    This method locates the entry in an entity's index list that begins with the
816    specified attribute name. If the entity has no index list, one will be
817    created. This method works on raw XML, not a live ERDB object.
818    
819    =over 4
820    
821    =item xml
822    
823    The raw XML structure defining the database.
824    
825    =item entityName
826    
827    The name of the relevant entity.
828    
829    =item attributeName
830    
831    The name of the attribute relevant to the search.
832    
833    =item RETURN
834    
835    The numerical index in the index list of the index entry for the specified entity and
836    attribute, or C<undef> if no such index exists.
837    
838    =back
839    
840    =cut
841    
842    sub FindIndexForEntity {
843        # Get the parameters.
844        my ($xml, $entityName, $attributeName) = @_;
845        # Declare the return variable.
846        my $retVal;
847        # Get the named entity.
848        my $entityData = $xml->{Entities}->{$entityName};
849        if (! $entityData) {
850            Confess("Entity $entityName not found in DBD structure.");
851        } else {
852            # Insure it has an index list.
853            if (! exists $entityData->{Indexes}) {
854                $entityData->{Indexes} = [];
855            } else {
856                # Search for the desired index.
857                my $indexList = $entityData->{Indexes};
858                my $n = scalar @{$indexList};
859                Trace("Searching $n indexes in index list for $entityName.") if T(2);
860                # We use an indexed FOR here because we're returning an
861                # index number instead of an object. We do THAT so we can
862                # delete the index from the list if needed.
863                for (my $i = 0; $i < $n && !defined($retVal); $i++) {
864                    my $index = $indexList->[$i];
865                    my $fields = $index->{IndexFields};
866                    # Technically this IF should be safe (that is, we are guaranteed
867                    # the existence of a "$fields->[0]"), because when we load the XML
868                    # we have SuppressEmpty specified.
869                    if ($fields->[0]->{name} eq $attributeName) {
870                        $retVal = $i;
871                    }
872                }
873            }
874        }
875        Trace("Index for $attributeName of $entityName found at position $retVal.") if defined($retVal) && T(3);
876        Trace("Index for $attributeName not found in $entityName.") if !defined($retVal) && T(3);
877        # Return the result.
878        return $retVal;
879    }
880    
881  =head3 CreateTables  =head3 CreateTables
882    
883  C<< $erdb->CreateTables(); >>      $erdb->CreateTables();
884    
885  This method creates the tables for the database from the metadata structure loaded by the  This method creates the tables for the database from the metadata structure loaded by the
886  constructor. It is expected this function will only be used on rare occasions, when the  constructor. It is expected this function will only be used on rare occasions, when the
# Line 558  Line 897 
897      # Loop through the relations.      # Loop through the relations.
898      for my $relationName (@relNames) {      for my $relationName (@relNames) {
899          # Create a table for this relation.          # Create a table for this relation.
900          $self->CreateTable($relationName);          $self->CreateTable($relationName, 1);
901          Trace("Relation $relationName created.") if T(2);          Trace("Relation $relationName created.") if T(2);
902      }      }
903  }  }
904    
905  =head3 CreateTable  =head3 CreateTable
906    
907  C<< $erdb->CreateTable($tableName, $indexFlag, $estimatedRows); >>      $erdb->CreateTable($tableName, $indexFlag, $estimatedRows);
908    
909  Create the table for a relation and optionally create its indexes.  Create the table for a relation and optionally create its indexes.
910    
# Line 621  Line 960 
960      my $estimation = undef;      my $estimation = undef;
961      if ($estimatedRows) {      if ($estimatedRows) {
962          $estimation = [$self->EstimateRowSize($relationName), $estimatedRows];          $estimation = [$self->EstimateRowSize($relationName), $estimatedRows];
963            Trace("$estimation->[1] rows of $estimation->[0] bytes each.") if T(3);
964      }      }
965      # Create the table.      # Create the table.
966      Trace("Creating table $relationName: $fieldThing") if T(2);      Trace("Creating table $relationName: $fieldThing") if T(2);
967      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);
968      Trace("Relation $relationName created in database.") if T(2);      Trace("Relation $relationName created in database.") if T(2);
969      # If we want to build the indexes, we do it here.      # If we want to build the indexes, we do it here. Note that the full-text search
970        # index will not be built until the table has been loaded.
971      if ($indexFlag) {      if ($indexFlag) {
972          $self->CreateIndex($relationName);          $self->CreateIndex($relationName);
973      }      }
974  }  }
975    
976    =head3 VerifyFields
977    
978        my $count = $erdb->VerifyFields($relName, \@fieldList);
979    
980    Run through the list of proposed field values, insuring that all the character fields are
981    below the maximum length. If any fields are too long, they will be truncated in place.
982    
983    =over 4
984    
985    =item relName
986    
987    Name of the relation for which the specified fields are destined.
988    
989    =item fieldList
990    
991    Reference to a list, in order, of the fields to be put into the relation.
992    
993    =item RETURN
994    
995    Returns the number of fields truncated.
996    
997    =back
998    
999    =cut
1000    
1001    sub VerifyFields {
1002        # Get the parameters.
1003        my ($self, $relName, $fieldList) = @_;
1004        # Initialize the return value.
1005        my $retVal = 0;
1006        # Get the relation definition.
1007        my $relData = $self->_FindRelation($relName);
1008        # Get the list of field descriptors.
1009        my $fieldTypes = $relData->{Fields};
1010        my $fieldCount = scalar @{$fieldTypes};
1011        # Loop through the two lists.
1012        for (my $i = 0; $i < $fieldCount; $i++) {
1013            # Get the type of the current field.
1014            my $fieldType = $fieldTypes->[$i]->{type};
1015            # If it's a character field, verify the length.
1016            if ($fieldType =~ /string/) {
1017                my $maxLen = $TypeTable{$fieldType}->{maxLen};
1018                my $oldString = $fieldList->[$i];
1019                if (length($oldString) > $maxLen) {
1020                    # Here it's too big, so we truncate it.
1021                    Trace("Truncating field $i ($fieldTypes->[$i]->{name}) in relation $relName to $maxLen characters from \"$oldString\".") if T(1);
1022                    $fieldList->[$i] = substr $oldString, 0, $maxLen;
1023                    $retVal++;
1024                }
1025            }
1026        }
1027        # Return the truncation count.
1028        return $retVal;
1029    }
1030    
1031    =head3 DigestFields
1032    
1033        $erdb->DigestFields($relName, $fieldList);
1034    
1035    Digest the strings in the field list that correspond to data type C<hash-string> in the
1036    specified relation.
1037    
1038    =over 4
1039    
1040    =item relName
1041    
1042    Name of the relation to which the fields belong.
1043    
1044    =item fieldList
1045    
1046    List of field contents to be loaded into the relation.
1047    
1048    =back
1049    
1050    =cut
1051    #: Return Type ;
1052    sub DigestFields {
1053        # Get the parameters.
1054        my ($self, $relName, $fieldList) = @_;
1055        # Get the relation definition.
1056        my $relData = $self->_FindRelation($relName);
1057        # Get the list of field descriptors.
1058        my $fieldTypes = $relData->{Fields};
1059        my $fieldCount = scalar @{$fieldTypes};
1060        # Loop through the two lists.
1061        for (my $i = 0; $i < $fieldCount; $i++) {
1062            # Get the type of the current field.
1063            my $fieldType = $fieldTypes->[$i]->{type};
1064            # If it's a hash string, digest it in place.
1065            if ($fieldType eq 'hash-string') {
1066                $fieldList->[$i] = $self->DigestKey($fieldList->[$i]);
1067            }
1068        }
1069    }
1070    
1071    =head3 DigestKey
1072    
1073        my $digested = $erdb->DigestKey($keyValue);
1074    
1075    Return the digested value of a symbolic key. The digested value can then be plugged into a
1076    key-based search into a table with key-type hash-string.
1077    
1078    Currently the digesting process is independent of the database structure, but that may not
1079    always be the case, so this is an instance method instead of a static method.
1080    
1081    =over 4
1082    
1083    =item keyValue
1084    
1085    Key value to digest.
1086    
1087    =item RETURN
1088    
1089    Digested value of the key.
1090    
1091    =back
1092    
1093    =cut
1094    
1095    sub DigestKey {
1096        # Get the parameters.
1097        my ($self, $keyValue) = @_;
1098        # Compute the digest.
1099        my $retVal = md5_base64($keyValue);
1100        # Return the result.
1101        return $retVal;
1102    }
1103    
1104  =head3 CreateIndex  =head3 CreateIndex
1105    
1106  C<< $erdb->CreateIndex($relationName); >>      $erdb->CreateIndex($relationName);
1107    
1108  Create the indexes for a relation. If a table is being loaded from a large source file (as  Create the indexes for a relation. If a table is being loaded from a large source file (as
1109  is the case in L</LoadTable>), it is sometimes best to create the indexes after the load.  is the case in L</LoadTable>), it is sometimes best to create the indexes after the load.
# Line 655  Line 1124 
1124      for my $indexName (keys %{$indexHash}) {      for my $indexName (keys %{$indexHash}) {
1125          my $indexData = $indexHash->{$indexName};          my $indexData = $indexHash->{$indexName};
1126          # Get the index's field list.          # Get the index's field list.
1127          my @fieldList = _FixNames(@{$indexData->{IndexFields}});          my @rawFields = @{$indexData->{IndexFields}};
1128            # Get a hash of the relation's field types.
1129            my %types = map { $_->{name} => $_->{type} } @{$relationData->{Fields}};
1130            # We need to check for text fields so we can append a length limitation for them. To do
1131            # that, we need the relation's field list.
1132            my $relFields = $relationData->{Fields};
1133            for (my $i = 0; $i <= $#rawFields; $i++) {
1134                # Get the field type.
1135                my $field = $rawFields[$i];
1136                my $type = $types{$field};
1137                # Ask if it requires using prefix notation for the index.
1138                my $mod = $TypeTable{$type}->{indexMod};
1139                Trace("Field $field ($i) in $relationName has type $type and indexMod $mod.") if T(3);
1140                if ($mod) {
1141                    # Append the prefix length to the field name,
1142                    $rawFields[$i] .= "($mod)";
1143                }
1144            }
1145            my @fieldList = _FixNames(@rawFields);
1146          my $flds = join(', ', @fieldList);          my $flds = join(', ', @fieldList);
1147          # Get the index's uniqueness flag.          # Get the index's uniqueness flag.
1148          my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
1149          # Create the index.          # Create the index.
1150          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
1151                                      flds => $flds, unique => $unique);                                      flds => $flds, kind => $unique);
1152          if ($rv) {          if ($rv) {
1153              Trace("Index created: $indexName for $relationName ($flds)") if T(1);              Trace("Index created: $indexName for $relationName ($flds)") if T(1);
1154          } else {          } else {
# Line 670  Line 1157 
1157      }      }
1158  }  }
1159    
1160  =head3 LoadTables  =head3 GetSecondaryFields
   
 C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>  
1161    
1162  This method will load the database tables from a directory. The tables must already have been created      my %fieldTuples = $erdb->GetSecondaryFields($entityName);
 in the database. (This can be done by calling L</CreateTables>.) The caller passes in a directory name;  
 all of the relations to be loaded must have a file in the directory with the same name as the relation  
 (optionally with a suffix of C<.dtx>). Each file must be a tab-delimited table of field values. Each  
 line of the file will be loaded as a row of the target relation table. The field values should be in  
 the same order as the fields in the relation tables generated by L</ShowMetaData>. The old data is  
 erased before the new data is loaded in.  
1163    
1164  A certain amount of translation automatically takes place. Ctrl-M characters are deleted, and  This method will return a list of the name and type of each of the secondary
1165  tab and new-line characters inside a field are escaped as C<\t> and C<\n>, respectively. Dates must  fields for a specified entity. Secondary fields are stored in two-column tables
1166  be entered as a Unix timestamp, that is, as an integer number of seconds since the base epoch.  in addition to the primary entity table. This enables the field to have no value
1167    or to have multiple values.
1168    
1169  =over 4  =over 4
1170    
1171  =item directoryName  =item entityName
   
 Name of the directory containing the relation files to be loaded.  
   
 =item rebuild  
1172    
1173  TRUE if the tables should be dropped and rebuilt, else FALSE. This is, unfortunately, the  Name of the entity whose secondary fields are desired.
 only way to erase existing data in the tables, since the TRUNCATE command is not supported  
 by all of the DB engines we use.  
1174    
1175  =item RETURN  =item RETURN
1176    
1177  Returns a statistical object describing the number of records read and a list of the error messages.  Returns a hash mapping the field names to their field types.
1178    
1179  =back  =back
1180    
1181  =cut  =cut
1182    
1183  sub LoadTables {  sub GetSecondaryFields {
1184      # Get the parameters.      # Get the parameters.
1185      my ($self, $directoryName, $rebuild) = @_;      my ($self, $entityName) = @_;
     # Start the timer.  
     my $startTime = gettimeofday;  
     # Clean any trailing slash from the directory name.  
     $directoryName =~ s!/\\$!!;  
1186      # Declare the return variable.      # Declare the return variable.
1187      my $retVal = Stats->new();      my %retVal = ();
1188      # Get the relation names.      # Look for the entity.
1189      my @relNames = $self->GetTableNames();      my $table = $self->GetFieldTable($entityName);
1190      for my $relationName (@relNames) {      # Loop through the fields, pulling out the secondaries.
1191          # Try to load this relation.      for my $field (sort keys %{$table}) {
1192          my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);          if ($table->{$field}->{relation} ne $entityName) {
1193          # Accumulate the statistics.              # Here we have a secondary field.
1194          $retVal->Accumulate($result);              $retVal{$field} = $table->{$field}->{type};
1195      }      }
1196      # Add the duration of the load to the statistical object.      }
1197      $retVal->Add('duration', gettimeofday - $startTime);      # Return the result.
1198      # Return the accumulated statistics.      return %retVal;
     return $retVal;  
1199  }  }
1200    
1201    =head3 GetFieldRelationName
1202    
1203  =head3 GetTableNames      my $name = $erdb->GetFieldRelationName($objectName, $fieldName);
1204    
1205  C<< my @names = $erdb->GetTableNames; >>  Return the name of the relation containing a specified field.
1206    
1207  Return a list of the relations required to implement this database.  =over 4
1208    
1209  =cut  =item objectName
1210    
1211  sub GetTableNames {  Name of the entity or relationship containing the field.
     # Get the parameters.  
     my ($self) = @_;  
     # Get the relation list from the metadata.  
     my $relationTable = $self->{_metaData}->{RelationTable};  
     # Return the relation names.  
     return keys %{$relationTable};  
 }  
1212    
1213  =head3 GetEntityTypes  =item fieldName
1214    
1215  C<< my @names = $erdb->GetEntityTypes; >>  Name of the relevant field in that entity or relationship.
1216    
1217  Return a list of the entity type names.  =item RETURN
1218    
1219    Returns the name of the database relation containing the field, or C<undef> if
1220    the field does not exist.
1221    
1222    =back
1223    
1224  =cut  =cut
1225    
1226  sub GetEntityTypes {  sub GetFieldRelationName {
1227      # Get the database object.      # Get the parameters.
1228      my ($self) = @_;      my ($self, $objectName, $fieldName) = @_;
1229        # Declare the return variable.
1230        my $retVal;
1231        # Get the object field table.
1232        my $table = $self->GetFieldTable($objectName);
1233        # Only proceed if the field exists.
1234        if (exists $table->{$fieldName}) {
1235            # Determine the name of the relation that contains this field.
1236            $retVal = $table->{$fieldName}->{relation};
1237        }
1238        # Return the result.
1239        return $retVal;
1240    }
1241    
1242    =head3 DeleteValue
1243    
1244        my $numDeleted = $erdb->DeleteValue($entityName, $id, $fieldName, $fieldValue);
1245    
1246    Delete secondary field values from the database. This method can be used to delete all
1247    values of a specified field for a particular entity instance, or only a single value.
1248    
1249    Secondary fields are stored in two-column relations separate from an entity's primary
1250    table, and as a result a secondary field can legitimately have no value or multiple
1251    values. Therefore, it makes sense to talk about deleting secondary fields where it
1252    would not make sense for primary fields.
1253    
1254    =over 4
1255    
1256    =item entityName
1257    
1258    Name of the entity from which the fields are to be deleted.
1259    
1260    =item id
1261    
1262    ID of the entity instance to be processed. If the instance is not found, this
1263    method will have no effect. If C<undef> is specified, all values for all of
1264    the entity instances will be deleted.
1265    
1266    =item fieldName
1267    
1268    Name of the field whose values are to be deleted.
1269    
1270    =item fieldValue (optional)
1271    
1272    Value to be deleted. If not specified, then all values of the specified field
1273    will be deleted for the entity instance. If specified, then only the values which
1274    match this parameter will be deleted.
1275    
1276    =item RETURN
1277    
1278    Returns the number of rows deleted.
1279    
1280    =back
1281    
1282    =cut
1283    
1284    sub DeleteValue {
1285        # Get the parameters.
1286        my ($self, $entityName, $id, $fieldName, $fieldValue) = @_;
1287        # Declare the return value.
1288        my $retVal = 0;
1289        # We need to set up an SQL command to do the deletion. First, we
1290        # find the name of the field's relation.
1291        my $table = $self->GetFieldTable($entityName);
1292        my $field = $table->{$fieldName};
1293        my $relation = $field->{relation};
1294        # Make sure this is a secondary field.
1295        if ($relation eq $entityName) {
1296            Confess("Cannot delete values of $fieldName for $entityName.");
1297        } else {
1298            # Set up the SQL command to delete all values.
1299            my $sql = "DELETE FROM $relation";
1300            # Build the filter.
1301            my @filters = ();
1302            my @parms = ();
1303            # Check for a filter by ID.
1304            if (defined $id) {
1305                push @filters, "id = ?";
1306                push @parms, $id;
1307            }
1308            # Check for a filter by value.
1309            if (defined $fieldValue) {
1310                push @filters, "$fieldName = ?";
1311                push @parms, $fieldValue;
1312            }
1313            # Append the filters to the command.
1314            if (@filters) {
1315                $sql .= " WHERE " . join(" AND ", @filters);
1316            }
1317            # Execute the command.
1318            my $dbh = $self->{_dbh};
1319            $retVal = $dbh->SQL($sql, 0, @parms);
1320        }
1321        # Return the result.
1322        return $retVal;
1323    }
1324    
1325    =head3 LoadTables
1326    
1327        my $stats = $erdb->LoadTables($directoryName, $rebuild);
1328    
1329    This method will load the database tables from a directory. The tables must already have been created
1330    in the database. (This can be done by calling L</CreateTables>.) The caller passes in a directory name;
1331    all of the relations to be loaded must have a file in the directory with the same name as the relation
1332    (optionally with a suffix of C<.dtx>). Each file must be a tab-delimited table of field values. Each
1333    line of the file will be loaded as a row of the target relation table. The field values should be in
1334    the same order as the fields in the relation tables generated by L</ShowMetaData>. The old data is
1335    erased before the new data is loaded in.
1336    
1337    A certain amount of translation automatically takes place. Ctrl-M characters are deleted, and
1338    tab and new-line characters inside a field are escaped as C<\t> and C<\n>, respectively. Dates must
1339    be entered as a Unix timestamp, that is, as an integer number of seconds since the base epoch.
1340    
1341    =over 4
1342    
1343    =item directoryName
1344    
1345    Name of the directory containing the relation files to be loaded.
1346    
1347    =item rebuild
1348    
1349    TRUE if the tables should be dropped and rebuilt, else FALSE. This is, unfortunately, the
1350    only way to erase existing data in the tables, since the TRUNCATE command is not supported
1351    by all of the DB engines we use.
1352    
1353    =item RETURN
1354    
1355    Returns a statistical object describing the number of records read and a list of the error messages.
1356    
1357    =back
1358    
1359    =cut
1360    
1361    sub LoadTables {
1362        # Get the parameters.
1363        my ($self, $directoryName, $rebuild) = @_;
1364        # Start the timer.
1365        my $startTime = gettimeofday;
1366        # Clean any trailing slash from the directory name.
1367        $directoryName =~ s!/\\$!!;
1368        # Declare the return variable.
1369        my $retVal = Stats->new();
1370        # Get the relation names.
1371        my @relNames = $self->GetTableNames();
1372        for my $relationName (@relNames) {
1373            # Try to load this relation.
1374            my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);
1375            # Accumulate the statistics.
1376            $retVal->Accumulate($result);
1377        }
1378        # Add the duration of the load to the statistical object.
1379        $retVal->Add('duration', gettimeofday - $startTime);
1380        # Return the accumulated statistics.
1381        return $retVal;
1382    }
1383    
1384    
1385    =head3 GetTableNames
1386    
1387        my @names = $erdb->GetTableNames;
1388    
1389    Return a list of the relations required to implement this database.
1390    
1391    =cut
1392    
1393    sub GetTableNames {
1394        # Get the parameters.
1395        my ($self) = @_;
1396        # Get the relation list from the metadata.
1397        my $relationTable = $self->{_metaData}->{RelationTable};
1398        # Return the relation names.
1399        return keys %{$relationTable};
1400    }
1401    
1402    =head3 GetEntityTypes
1403    
1404        my @names = $erdb->GetEntityTypes;
1405    
1406    Return a list of the entity type names.
1407    
1408    =cut
1409    
1410    sub GetEntityTypes {
1411        # Get the database object.
1412        my ($self) = @_;
1413      # Get the entity list from the metadata object.      # Get the entity list from the metadata object.
1414      my $entityList = $self->{_metaData}->{Entities};      my $entityList = $self->{_metaData}->{Entities};
1415      # Return the list of entity names in alphabetical order.      # Return the list of entity names in alphabetical order.
1416      return sort keys %{$entityList};      return sort keys %{$entityList};
1417  }  }
1418    
1419    =head3 GetDataTypes
1420    
1421        my %types = ERDB::GetDataTypes();
1422    
1423    Return a table of ERDB data types. The table returned is a hash of hashes.
1424    The keys of the big hash are the datatypes. Each smaller hash has several
1425    values used to manage the data. The most interesting is the SQL type (key
1426    C<sqlType>) and the descriptive node (key C<notes>).
1427    
1428    Note that changing the values in the smaller hashes will seriously break
1429    things, so this data should be treated as read-only.
1430    
1431    =cut
1432    
1433    sub GetDataTypes {
1434        return %TypeTable;
1435    }
1436    
1437    
1438  =head3 IsEntity  =head3 IsEntity
1439    
1440  C<< my $flag = $erdb->IsEntity($entityName); >>      my $flag = $erdb->IsEntity($entityName);
1441    
1442  Return TRUE if the parameter is an entity name, else FALSE.  Return TRUE if the parameter is an entity name, else FALSE.
1443    
# Line 793  Line 1464 
1464    
1465  =head3 Get  =head3 Get
1466    
1467  C<< my $query = $erdb->Get(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>      my $query = $erdb->Get(\@objectNames, $filterClause, \@params);
1468    
1469  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.
1470  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 801  Line 1472 
1472  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
1473  $genus.  $genus.
1474    
1475  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", $genus); >>      $query = $erdb->Get(['Genome'], "Genome(genus) = ?", [$genus]);
1476    
1477  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
1478  parameter representing the parameter value. It would also be possible to code  parameter representing the parameter value. It would also be possible to code
1479    
1480  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>      $query = $erdb->Get(['Genome'], "Genome(genus) = \'$genus\'");
1481    
1482  however, this version of the call would generate a syntax error if there were any quote  however, this version of the call would generate a syntax error if there were any quote
1483  characters inside the variable C<$genus>.  characters inside the variable C<$genus>.
# Line 818  Line 1489 
1489  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
1490  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,
1491    
1492  C<< $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", $genus); >>      $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]);
1493    
1494  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
1495  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.
1496  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
1497  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
1498  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  
1499  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,
1500  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.
1501    
1502    If an entity or relationship is mentioned twice, the name for the second occurrence will
1503    be suffixed with C<2>, the third occurrence will be suffixed with C<3>, and so forth. So,
1504    for example, if we have C<['Feature', 'HasContig', 'Contig', 'HasContig']>, then the
1505    B<to-link> field of the first B<HasContig> is specified as C<HasContig(to-link)>, while
1506    the B<to-link> field of the second B<HasContig> is specified as C<HasContig2(to-link)>.
1507    
1508  =over 4  =over 4
1509    
1510  =item objectNames  =item objectNames
# Line 849  Line 1525 
1525  with an ORDER BY clause. For example, the following filter string gets all genomes for a  with an ORDER BY clause. For example, the following filter string gets all genomes for a
1526  particular genus and sorts them by species name.  particular genus and sorts them by species name.
1527    
1528  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>      "Genome(genus) = ? ORDER BY Genome(species)"
1529    
1530    Note that the case is important. Only an uppercase "ORDER BY" with a single space will
1531    be processed. The idea is to make it less likely to find the verb by accident.
1532    
1533  The rules for field references in a sort order are the same as those for field references in the  The rules for field references in a sort order are the same as those for field references in the
1534  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
1535  relation.  relation.
1536    
1537  =item param1, param2, ..., paramN  Finally, you can limit the number of rows returned by adding a LIMIT clause. The LIMIT must
1538    be the last thing in the filter clause, and it contains only the word "LIMIT" followed by
1539    a positive number. So, for example
1540    
1541        "Genome(genus) = ? ORDER BY Genome(species) LIMIT 10"
1542    
1543    will only return the first ten genomes for the specified genus. The ORDER BY clause is not
1544    required. For example, to just get the first 10 genomes in the B<Genome> table, you could
1545    use
1546    
1547  Parameter values to be substituted into the filter clause.      "LIMIT 10"
1548    
1549    =item params
1550    
1551    Reference to a list of parameter values to be substituted into the filter clause.
1552    
1553  =item RETURN  =item RETURN
1554    
# Line 869  Line 1560 
1560    
1561  sub Get {  sub Get {
1562      # Get the parameters.      # Get the parameters.
1563      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $objectNames, $filterClause, $params) = @_;
1564      # Construct the SELECT statement. The general pattern is      # Process the SQL stuff.
1565      #      my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1566      # SELECT name1.*, name2.*, ... nameN.* FROM name1, name2, ... nameN          $self->_SetupSQL($objectNames, $filterClause);
1567      #      # Create the query.
1568      my $dbh = $self->{_dbh};      my $command = "SELECT " . join(".*, ", @{$mappedNameListRef}) .
1569      my $command = "SELECT DISTINCT " . join('.*, ', @{$objectNames}) . ".* FROM " .          ".* $suffix";
1570                  join(', ', @{$objectNames});      my $sth = $self->_GetStatementHandle($command, $params);
1571      # Check for a filter clause.      # Now we create the relation map, which enables DBQuery to determine the order, name
1572      if ($filterClause) {      # and mapped name for each object in the query.
1573          # Here we have one, so we convert its field names and add it to the query. First,      my @relationMap = ();
1574          # We create a copy of the filter string we can work with.      for my $mappedName (@{$mappedNameListRef}) {
1575          my $filterString = $filterClause;          push @relationMap, [$mappedName, $mappedNameHashRef->{$mappedName}];
         # Next, we sort the object names by length. This helps protect us from finding  
         # object names inside other object names when we're doing our search and replace.  
         my @sortedNames = sort { length($b) - length($a) } @{$objectNames};  
         # We will also keep a list of conditions to add to the WHERE clause in order to link  
         # entities and relationships as well as primary relations to secondary ones.  
         my @joinWhere = ();  
         # The final preparatory step is to create a hash table of relation names. The  
         # table begins with the relation names already in the SELECT command.  
         my %fromNames = ();  
         for my $objectName (@sortedNames) {  
             $fromNames{$objectName} = 1;  
         }  
         # We are ready to begin. We loop through the object names, replacing each  
         # object name's field references by the corresponding SQL field reference.  
         # Along the way, if we find a secondary relation, we will need to add it  
         # to the FROM clause.  
         for my $objectName (@sortedNames) {  
             # Get the length of the object name plus 2. This is the value we add to the  
             # size of the field name to determine the size of the field reference as a  
             # whole.  
             my $nameLength = 2 + length $objectName;  
             # Get the object's field list.  
             my $fieldList = $self->_GetFieldTable($objectName);  
             # Find the field references for this object.  
             while ($filterString =~ m/$objectName\(([^)]*)\)/g) {  
                 # At this point, $1 contains the field name, and the current position  
                 # is set immediately after the final parenthesis. We pull out the name of  
                 # the field and the position and length of the field reference as a whole.  
                 my $fieldName = $1;  
                 my $len = $nameLength + length $fieldName;  
                 my $pos = pos($filterString) - $len;  
                 # Insure the field exists.  
                 if (!exists $fieldList->{$fieldName}) {  
                     Confess("Field $fieldName not found for object $objectName.");  
                 } else {  
                     # Get the field's relation.  
                     my $relationName = $fieldList->{$fieldName}->{relation};  
                     # Insure the relation is in the FROM clause.  
                     if (!exists $fromNames{$relationName}) {  
                         # Add the relation to the FROM clause.  
                         $command .= ", $relationName";  
                         # Create its join sub-clause.  
                         push @joinWhere, "$objectName.id = $relationName.id";  
                         # Denote we have it available for future fields.  
                         $fromNames{$relationName} = 1;  
                     }  
                     # Form an SQL field reference from the relation name and the field name.  
                     my $sqlReference = "$relationName." . _FixName($fieldName);  
                     # Put it into the filter string in place of the old value.  
                     substr($filterString, $pos, $len) = $sqlReference;  
                     # Reposition the search.  
                     pos $filterString = $pos + length $sqlReference;  
                 }  
             }  
         }  
         # The next step is to join the objects together. We only need to do this if there  
         # is more than one object in the object list. We start with the first object and  
         # run through the objects after it. Note also that we make a safety copy of the  
         # list before running through it.  
         my @objectList = @{$objectNames};  
         my $lastObject = shift @objectList;  
         # Get the join table.  
         my $joinTable = $self->{_metaData}->{Joins};  
         # Loop through the object list.  
         for my $thisObject (@objectList) {  
             # Look for a join.  
             my $joinKey = "$lastObject/$thisObject";  
             if (!exists $joinTable->{$joinKey}) {  
                 # Here there's no join, so we throw an error.  
                 Confess("No join exists to connect from $lastObject to $thisObject.");  
             } else {  
                 # Get the join clause and add it to the WHERE list.  
                 push @joinWhere, $joinTable->{$joinKey};  
                 # Save this object as the last object for the next iteration.  
                 $lastObject = $thisObject;  
             }  
         }  
         # Now we need to handle the whole ORDER BY thing. We'll put the order by clause  
         # in the following variable.  
         my $orderClause = "";  
         # Locate the ORDER BY verb (if any).  
         if ($filterString =~ m/^(.*)ORDER BY/g) {  
             # Here we have an ORDER BY verb. Split it off of the filter string.  
             my $pos = pos $filterString;  
             $orderClause = substr($filterString, $pos);  
             $filterString = $1;  
         }  
         # Add the filter and the join clauses (if any) to the SELECT command.  
         if ($filterString) {  
             push @joinWhere, "($filterString)";  
         }  
         if (@joinWhere) {  
             $command .= " WHERE " . join(' AND ', @joinWhere);  
         }  
         # Add the sort clause (if any) to the SELECT command.  
         if ($orderClause) {  
             $command .= " ORDER BY $orderClause";  
         }  
1576      }      }
     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());  
1577      # Return the statement object.      # Return the statement object.
1578      my $retVal = DBQuery::_new($self, $sth, @{$objectNames});      my $retVal = DBQuery::_new($self, $sth, \@relationMap);
1579      return $retVal;      return $retVal;
1580  }  }
1581    
 =head3 GetList  
1582    
 C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  
1583    
1584  Return a list of object descriptors for the specified objects as determined by the  =head3 Search
 specified filter clause.  
1585    
1586  This method is essentially the same as L</Get> except it returns a list of objects rather      my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params);
1587  than a query object that can be used to get the results one record at a time.  
1588    Perform a full text search with filtering. The search will be against a specified object
1589    in the object name list. That object will get an extra field containing the search
1590    relevance. Note that except for the search expression, the parameters of this method are
1591    the same as those for L</Get> and follow the same rules.
1592    
1593  =over 4  =over 4
1594    
1595    =item searchExpression
1596    
1597    Boolean search expression for the text fields of the target object. The default mode for
1598    a Boolean search expression is OR, but we want the default to be AND, so we will
1599    add a C<+> operator to each word with no other operator before it.
1600    
1601    =item idx
1602    
1603    Index in the I<$objectNames> list of the table to be searched in full-text mode.
1604    
1605  =item objectNames  =item objectNames
1606    
1607  List containing the names of the entity and relationship objects to be retrieved.  List containing the names of the entity and relationship objects to be retrieved.
# Line 1017  Line 1616 
1616  or secondary entity relations; however, all of the entities and relationships involved must  or secondary entity relations; however, all of the entities and relationships involved must
1617  be included in the list of object names.  be included in the list of object names.
1618    
1619  The filter clause can also specify a sort order. To do this, simply follow the filter string  =item params
 with an ORDER BY clause. For example, the following filter string gets all genomes for a  
 particular genus and sorts them by species name.  
   
 C<< "Genome(genus) = ? ORDER BY Genome(species)" >>  
   
 The rules for field references in a sort order are the same as those for field references in the  
 filter clause in general; however, odd things may happen if a sort field is from a secondary  
 relation.  
   
 =item param1, param2, ..., paramN  
1620    
1621  Parameter values to be substituted into the filter clause.  Reference to a list of parameter values to be substituted into the filter clause.
1622    
1623  =item RETURN  =item RETURN
1624    
1625  Returns a list of B<DBObject>s that satisfy the query conditions.  Returns a query object for the specified search.
1626    
1627  =back  =back
1628    
1629  =cut  =cut
1630  #: Return Type @%  
1631  sub GetList {  sub Search {
1632      # Get the parameters.      # Get the parameters.
1633      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1634      # Declare the return variable.      # Declare the return variable.
1635      my @retVal = ();      my $retVal;
1636      # Perform the query.      # Create a safety copy of the parameter list. Note we have to be careful to insure
1637      my $query = $self->Get($objectNames, $filterClause, @params);      # a parameter list exists before we copy it.
1638      # Loop through the results.      my @myParams = ();
1639      while (my $object = $query->Fetch) {      if (defined $params) {
1640          push @retVal, $object;          @myParams = @{$params};
1641        }
1642        # Get the first object's structure so we have access to the searchable fields.
1643        my $object1Name = $objectNames->[$idx];
1644        my $object1Structure = $self->_GetStructure($object1Name);
1645        # Get the field list.
1646        if (! exists $object1Structure->{searchFields}) {
1647            Confess("No searchable index for $object1Name.");
1648        } else {
1649            # Get the field list.
1650            my @fields = @{$object1Structure->{searchFields}};
1651            # Clean the search expression.
1652            my $actualKeywords = $self->CleanKeywords($searchExpression);
1653            # Prefix a "+" to each uncontrolled word. This converts the default
1654            # search mode from OR to AND.
1655            $actualKeywords =~ s/(^|\s)(\w|")/$1\+$2/g;
1656            Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1657            # We need two match expressions, one for the filter clause and one in the
1658            # query itself. Both will use a parameter mark, so we need to push the
1659            # search expression onto the front of the parameter list twice.
1660            unshift @myParams, $actualKeywords, $actualKeywords;
1661            # Build the match expression.
1662            my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
1663            my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
1664            # Process the SQL stuff.
1665            my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1666                $self->_SetupSQL($objectNames, $filterClause, $matchClause);
1667            # Create the query. Note that the match clause is inserted at the front of
1668            # the select fields.
1669            my $command = "SELECT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .
1670                ".* $suffix";
1671            my $sth = $self->_GetStatementHandle($command, \@myParams);
1672            # Now we create the relation map, which enables DBQuery to determine the order, name
1673            # and mapped name for each object in the query.
1674            my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
1675            # Return the statement object.
1676            $retVal = DBQuery::_new($self, $sth, \@relationMap, $object1Name);
1677      }      }
1678      # Return the result.      return $retVal;
     return @retVal;  
1679  }  }
1680    
1681  =head3 ComputeObjectSentence  =head3 GetFlat
1682    
1683  C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>      my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field);
1684    
1685  Check an object name, and if it is a relationship convert it to a relationship sentence.  This is a variation of L</GetAll> that asks for only a single field per record and
1686    returns a single flattened list.
1687    
1688  =over 4  =over 4
1689    
1690  =item objectName  =item objectNames
1691    
1692  Name of the entity or relationship.  List containing the names of the entity and relationship objects to be retrieved.
1693    
1694  =item RETURN  =item filterClause
1695    
1696    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1697    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
1698    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
1699    parameter list as additional parameters. The fields in a filter clause can come from primary
1700    entity relations, relationship relations, or secondary entity relations; however, all of the
1701    entities and relationships involved must be included in the list of object names.
1702    
1703    =item parameterList
1704    
1705    List of the parameters to be substituted in for the parameters marks in the filter clause.
1706    
1707    =item field
1708    
1709    Name of the field to be used to get the elements of the list returned.
1710    
1711    =item RETURN
1712    
1713    Returns a list of values.
1714    
1715    =back
1716    
1717    =cut
1718    #: Return Type @;
1719    sub GetFlat {
1720        # Get the parameters.
1721        my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
1722        # Construct the query.
1723        my $query = $self->Get($objectNames, $filterClause, $parameterList);
1724        # Create the result list.
1725        my @retVal = ();
1726        # Loop through the records, adding the field values found to the result list.
1727        while (my $row = $query->Fetch()) {
1728            push @retVal, $row->Value($field);
1729        }
1730        # Return the list created.
1731        return @retVal;
1732    }
1733    
1734    =head3 SpecialFields
1735    
1736        my %specials = $erdb->SpecialFields($entityName);
1737    
1738    Return a hash mapping special fields in the specified entity to the value of their
1739    C<special> attribute. This enables the subclass to get access to the special field
1740    attributes without needed to plumb the internal ERDB data structures.
1741    
1742    =over 4
1743    
1744    =item entityName
1745    
1746    Name of the entity whose special fields are desired.
1747    
1748    =item RETURN
1749    
1750    Returns a hash. The keys of the hash are the special field names, and the values
1751    are the values from each special field's C<special> attribute.
1752    
1753    =back
1754    
1755    =cut
1756    
1757    sub SpecialFields {
1758        # Get the parameters.
1759        my ($self, $entityName) = @_;
1760        # Declare the return variable.
1761        my %retVal = ();
1762        # Find the entity's data structure.
1763        my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1764        # Loop through its fields, adding each special field to the return hash.
1765        my $fieldHash = $entityData->{Fields};
1766        for my $fieldName (keys %{$fieldHash}) {
1767            my $fieldData = $fieldHash->{$fieldName};
1768            if (exists $fieldData->{special}) {
1769                $retVal{$fieldName} = $fieldData->{special};
1770            }
1771        }
1772        # Return the result.
1773        return %retVal;
1774    }
1775    
1776    =head3 Delete
1777    
1778        my $stats = $erdb->Delete($entityName, $objectID, %options);
1779    
1780    Delete an entity instance from the database. The instance is deleted along with all entity and
1781    relationship instances dependent on it. The definition of I<dependence> is recursive.
1782    
1783    An object is always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many
1784    relationship connected to a dependent entity or if it is the "to" entity connected to a 1-to-many
1785    dependent relationship.
1786    
1787    =over 4
1788    
1789    =item entityName
1790    
1791    Name of the entity type for the instance being deleted.
1792    
1793    =item objectID
1794    
1795    ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),
1796    then it is presumed to by a LIKE pattern.
1797    
1798    =item options
1799    
1800    A hash detailing the options for this delete operation.
1801    
1802    =item RETURN
1803    
1804    Returns a statistics object indicating how many records of each particular table were
1805    deleted.
1806    
1807    =back
1808    
1809    The permissible options for this method are as follows.
1810    
1811    =over 4
1812    
1813    =item testMode
1814    
1815    If TRUE, then the delete statements will be traced, but no changes will be made to the database.
1816    
1817    =item keepRoot
1818    
1819    If TRUE, then the entity instances will not be deleted, only the dependent records.
1820    
1821    =back
1822    
1823    =cut
1824    #: Return Type $%;
1825    sub Delete {
1826        # Get the parameters.
1827        my ($self, $entityName, $objectID, %options) = @_;
1828        # Declare the return variable.
1829        my $retVal = Stats->new();
1830        # Get the DBKernel object.
1831        my $db = $self->{_dbh};
1832        # We're going to generate all the paths branching out from the starting entity. One of
1833        # the things we have to be careful about is preventing loops. We'll use a hash to
1834        # determine if we've hit a loop.
1835        my %alreadyFound = ();
1836        # These next lists will serve as our result stack. We start by pushing object lists onto
1837        # the stack, and then popping them off to do the deletes. This means the deletes will
1838        # start with the longer paths before getting to the shorter ones. That, in turn, makes
1839        # sure we don't delete records that might be needed to forge relationships back to the
1840        # original item. We have two lists-- one for TO-relationships, and one for
1841        # FROM-relationships and entities.
1842        my @fromPathList = ();
1843        my @toPathList = ();
1844        # This final list is used to remember what work still needs to be done. We push paths
1845        # onto the list, then pop them off to extend the paths. We prime it with the starting
1846        # point. Note that we will work hard to insure that the last item on a path in the
1847        # to-do list is always an entity.
1848        my @todoList = ([$entityName]);
1849        while (@todoList) {
1850            # Get the current path.
1851            my $current = pop @todoList;
1852            # Copy it into a list.
1853            my @stackedPath = @{$current};
1854            # Pull off the last item on the path. It will always be an entity.
1855            my $myEntityName = pop @stackedPath;
1856            # Add it to the alreadyFound list.
1857            $alreadyFound{$myEntityName} = 1;
1858            # Figure out if we need to delete this entity.
1859            if ($myEntityName ne $entityName || ! $options{keepRoot}) {
1860                # Get the entity data.
1861                my $entityData = $self->_GetStructure($myEntityName);
1862                # Loop through the entity's relations. A DELETE command will be needed for each of them.
1863                my $relations = $entityData->{Relations};
1864                for my $relation (keys %{$relations}) {
1865                    my @augmentedList = (@stackedPath, $relation);
1866                    push @fromPathList, \@augmentedList;
1867                }
1868            }
1869            # Now we need to look for relationships connected to this entity.
1870            my $relationshipList = $self->{_metaData}->{Relationships};
1871            for my $relationshipName (keys %{$relationshipList}) {
1872                my $relationship = $relationshipList->{$relationshipName};
1873                # Check the FROM field. We're only interested if it's us.
1874                if ($relationship->{from} eq $myEntityName) {
1875                    # Add the path to this relationship.
1876                    my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1877                    push @fromPathList, \@augmentedList;
1878                    # Check the arity. If it's MM we're done. If it's 1M
1879                    # and the target hasn't been seen yet, we want to
1880                    # stack the entity for future processing.
1881                    if ($relationship->{arity} eq '1M') {
1882                        my $toEntity = $relationship->{to};
1883                        if (! exists $alreadyFound{$toEntity}) {
1884                            # Here we have a new entity that's dependent on
1885                            # the current entity, so we need to stack it.
1886                            my @stackList = (@augmentedList, $toEntity);
1887                            push @fromPathList, \@stackList;
1888                        } else {
1889                            Trace("$toEntity ignored because it occurred previously.") if T(4);
1890                        }
1891                    }
1892                }
1893                # Now check the TO field. In this case only the relationship needs
1894                # deletion.
1895                if ($relationship->{to} eq $myEntityName) {
1896                    my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1897                    push @toPathList, \@augmentedList;
1898                }
1899            }
1900        }
1901        # Create the first qualifier for the WHERE clause. This selects the
1902        # keys of the primary entity records to be deleted. When we're deleting
1903        # from a dependent table, we construct a join path from the first qualifier
1904        # to the table containing the dependent records to delete.
1905        my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
1906        # We need to make two passes. The first is through the to-list, and
1907        # the second through the from-list. The from-list is second because
1908        # the to-list may need to pass through some of the entities the
1909        # from-list would delete.
1910        my %stackList = ( from_link => \@fromPathList, to_link => \@toPathList );
1911        # Now it's time to do the deletes. We do it in two passes.
1912        for my $keyName ('to_link', 'from_link') {
1913            # Get the list for this key.
1914            my @pathList = @{$stackList{$keyName}};
1915            Trace(scalar(@pathList) . " entries in path list for $keyName.") if T(3);
1916            # Loop through this list.
1917            while (my $path = pop @pathList) {
1918                # Get the table whose rows are to be deleted.
1919                my @pathTables = @{$path};
1920                # Start the DELETE statement. We need to call DBKernel because the
1921                # syntax of a DELETE-USING varies among DBMSs.
1922                my $target = $pathTables[$#pathTables];
1923                my $stmt = $db->SetUsing(@pathTables);
1924                # Now start the WHERE. The first thing is the ID field from the starting table. That
1925                # starting table will either be the entity relation or one of the entity's
1926                # sub-relations.
1927                $stmt .= " WHERE $pathTables[0].id $qualifier";
1928                # Now we run through the remaining entities in the path, connecting them up.
1929                for (my $i = 1; $i <= $#pathTables; $i += 2) {
1930                    # Connect the current relationship to the preceding entity.
1931                    my ($entity, $rel) = @pathTables[$i-1,$i];
1932                    # The style of connection depends on the direction of the relationship.
1933                    $stmt .= " AND $entity.id = $rel.$keyName";
1934                    if ($i + 1 <= $#pathTables) {
1935                        # Here there's a next entity, so connect that to the relationship's
1936                        # to-link.
1937                        my $entity2 = $pathTables[$i+1];
1938                        $stmt .= " AND $rel.to_link = $entity2.id";
1939                    }
1940                }
1941                # Now we have our desired DELETE statement.
1942                if ($options{testMode}) {
1943                    # Here the user wants to trace without executing.
1944                    Trace($stmt) if T(0);
1945                } else {
1946                    # Here we can delete. Note that the SQL method dies with a confession
1947                    # if an error occurs, so we just go ahead and do it.
1948                    Trace("Executing delete from $target using '$objectID'.") if T(3);
1949                    my $rv = $db->SQL($stmt, 0, $objectID);
1950                    # Accumulate the statistics for this delete. The only rows deleted
1951                    # are from the target table, so we use its name to record the
1952                    # statistic.
1953                    $retVal->Add($target, $rv);
1954                }
1955            }
1956        }
1957        # Return the result.
1958        return $retVal;
1959    }
1960    
1961    =head3 Disconnect
1962    
1963        $erdb->Disconnect($relationshipName, $originEntityName, $originEntityID);
1964    
1965    Disconnect an entity instance from all the objects to which it is related. This
1966    will delete each relationship instance that connects to the specified entity.
1967    
1968    =over 4
1969    
1970    =item relationshipName
1971    
1972    Name of the relationship whose instances are to be deleted.
1973    
1974    =item originEntityName
1975    
1976    Name of the entity that is to be disconnected.
1977    
1978    =item originEntityID
1979    
1980    ID of the entity that is to be disconnected.
1981    
1982    =back
1983    
1984    =cut
1985    
1986    sub Disconnect {
1987        # Get the parameters.
1988        my ($self, $relationshipName, $originEntityName, $originEntityID) = @_;
1989        # Get the relationship descriptor.
1990        my $structure = $self->_GetStructure($relationshipName);
1991        # Insure we have a relationship.
1992        if (! exists $structure->{from}) {
1993            Confess("$relationshipName is not a relationship in the database.");
1994        } else {
1995            # Get the database handle.
1996            my $dbh = $self->{_dbh};
1997            # We'll set this value to 1 if we find our entity.
1998            my $found = 0;
1999            # Loop through the ends of the relationship.
2000            for my $dir ('from', 'to') {
2001                if ($structure->{$dir} eq $originEntityName) {
2002                    # Delete all relationship instances on this side of the entity instance.
2003                    Trace("Disconnecting in $dir direction with ID \"$originEntityID\".");
2004                    $dbh->SQL("DELETE FROM $relationshipName WHERE ${dir}_link = ?", 0, $originEntityID);
2005                    $found = 1;
2006                }
2007            }
2008            # Insure we found the entity on at least one end.
2009            if (! $found) {
2010                Confess("Entity \"$originEntityName\" does not use $relationshipName.");
2011            }
2012        }
2013    }
2014    
2015    =head3 DeleteRow
2016    
2017        $erdb->DeleteRow($relationshipName, $fromLink, $toLink, \%values);
2018    
2019    Delete a row from a relationship. In most cases, only the from-link and to-link are
2020    needed; however, for relationships with intersection data values can be specified
2021    for the other fields using a hash.
2022    
2023    =over 4
2024    
2025    =item relationshipName
2026    
2027    Name of the relationship from which the row is to be deleted.
2028    
2029    =item fromLink
2030    
2031    ID of the entity instance in the From direction.
2032    
2033    =item toLink
2034    
2035    ID of the entity instance in the To direction.
2036    
2037    =item values
2038    
2039    Reference to a hash of other values to be used for filtering the delete.
2040    
2041    =back
2042    
2043    =cut
2044    
2045    sub DeleteRow {
2046        # Get the parameters.
2047        my ($self, $relationshipName, $fromLink, $toLink, $values) = @_;
2048        # Create a hash of all the filter information.
2049        my %filter = ('from-link' => $fromLink, 'to-link' => $toLink);
2050        if (defined $values) {
2051            for my $key (keys %{$values}) {
2052                $filter{$key} = $values->{$key};
2053            }
2054        }
2055        # Build an SQL statement out of the hash.
2056        my @filters = ();
2057        my @parms = ();
2058        for my $key (keys %filter) {
2059            push @filters, _FixName($key) . " = ?";
2060            push @parms, $filter{$key};
2061        }
2062        Trace("Parms for delete row are " . join(", ", map { "\"$_\"" } @parms) . ".") if T(SQL => 4);
2063        my $command = "DELETE FROM $relationshipName WHERE " .
2064                      join(" AND ", @filters);
2065        # Execute it.
2066        my $dbh = $self->{_dbh};
2067        $dbh->SQL($command, undef, @parms);
2068    }
2069    
2070    =head3 DeleteLike
2071    
2072        my $deleteCount = $erdb->DeleteLike($relName, $filter, \@parms);
2073    
2074    Delete all the relationship rows that satisfy a particular filter condition. Unlike a normal
2075    filter, only fields from the relationship itself can be used.
2076    
2077    =over 4
2078    
2079    =item relName
2080    
2081    Name of the relationship whose records are to be deleted.
2082    
2083    =item filter
2084    
2085    A filter clause (L</Get>-style) for the delete query.
2086    
2087    =item parms
2088    
2089    Reference to a list of parameters for the filter clause.
2090    
2091    =item RETURN
2092    
2093    Returns a count of the number of rows deleted.
2094    
2095    =back
2096    
2097    =cut
2098    
2099    sub DeleteLike {
2100        # Get the parameters.
2101        my ($self, $objectName, $filter, $parms) = @_;
2102        # Declare the return variable.
2103        my $retVal;
2104        # Insure the parms argument is an array reference if the caller left it off.
2105        if (! defined($parms)) {
2106            $parms = [];
2107        }
2108        # Insure we have a relationship. The main reason for this is if we delete an entity
2109        # instance we have to yank out a bunch of other stuff with it.
2110        if ($self->IsEntity($objectName)) {
2111            Confess("Cannot use DeleteLike on $objectName, because it is not a relationship.");
2112        } else {
2113            # Create the SQL command suffix to get the desierd records.
2114            my ($suffix) = $self->_SetupSQL([$objectName], $filter);
2115            # Convert it to a DELETE command.
2116            my $command = "DELETE $suffix";
2117            # Execute the command.
2118            my $dbh = $self->{_dbh};
2119            my $result = $dbh->SQL($command, 0, @{$parms});
2120            # Check the results. Note we convert the "0D0" result to a real zero.
2121            # A failure causes an abnormal termination, so the caller isn't going to
2122            # worry about it.
2123            if (! defined $result) {
2124                Confess("Error deleting from $objectName: " . $dbh->errstr());
2125            } elsif ($result == 0) {
2126                $retVal = 0;
2127            } else {
2128                $retVal = $result;
2129            }
2130        }
2131        # Return the result count.
2132        return $retVal;
2133    }
2134    
2135    =head3 SortNeeded
2136    
2137        my $parms = $erdb->SortNeeded($relationName);
2138    
2139    Return the pipe command for the sort that should be applied to the specified
2140    relation when creating the load file.
2141    
2142    For example, if the load file should be sorted ascending by the first
2143    field, this method would return
2144    
2145        sort -k1 -t"\t"
2146    
2147    If the first field is numeric, the method would return
2148    
2149        sort -k1n -t"\t"
2150    
2151    Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate
2152    keys using a sort.
2153    
2154    =over 4
2155    
2156    =item relationName
2157    
2158    Name of the relation to be examined.
2159    
2160    =item
2161    
2162    Returns the sort command to use for sorting the relation, suitable for piping.
2163    
2164    =back
2165    
2166    =cut
2167    #: Return Type $;
2168    sub SortNeeded {
2169        # Get the parameters.
2170        my ($self, $relationName) = @_;
2171        # Declare a descriptor to hold the names of the key fields.
2172        my @keyNames = ();
2173        # Get the relation structure.
2174        my $relationData = $self->_FindRelation($relationName);
2175        # Find out if the relation is a primary entity relation,
2176        # a relationship relation, or a secondary entity relation.
2177        my $entityTable = $self->{_metaData}->{Entities};
2178        my $relationshipTable = $self->{_metaData}->{Relationships};
2179        if (exists $entityTable->{$relationName}) {
2180            # Here we have a primary entity relation.
2181            push @keyNames, "id";
2182        } elsif (exists $relationshipTable->{$relationName}) {
2183            # Here we have a relationship. We sort using the FROM index.
2184            my $relationshipData = $relationshipTable->{$relationName};
2185            my $index = $relationData->{Indexes}->{idxFrom};
2186            push @keyNames, @{$index->{IndexFields}};
2187        } else {
2188            # Here we have a secondary entity relation, so we have a sort on the ID field.
2189            push @keyNames, "id";
2190        }
2191        # Now we parse the key names into sort parameters. First, we prime the return
2192        # string.
2193        my $retVal = "sort -t\"\t\" ";
2194        # Get the relation's field list.
2195        my @fields = @{$relationData->{Fields}};
2196        # Loop through the keys.
2197        for my $keyData (@keyNames) {
2198            # Get the key and the ordering.
2199            my ($keyName, $ordering);
2200            if ($keyData =~ /^([^ ]+) DESC/) {
2201                ($keyName, $ordering) = ($1, "descending");
2202            } else {
2203                ($keyName, $ordering) = ($keyData, "ascending");
2204            }
2205            # Find the key's position and type.
2206            my $fieldSpec;
2207            for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {
2208                my $thisField = $fields[$i];
2209                if ($thisField->{name} eq $keyName) {
2210                    # Get the sort modifier for this field type. The modifier
2211                    # decides whether we're using a character, numeric, or
2212                    # floating-point sort.
2213                    my $modifier = $TypeTable{$thisField->{type}}->{sort};
2214                    # If the index is descending for this field, denote we want
2215                    # to reverse the sort order on this field.
2216                    if ($ordering eq 'descending') {
2217                        $modifier .= "r";
2218                    }
2219                    # Store the position and modifier into the field spec, which
2220                    # will stop the inner loop. Note that the field number is
2221                    # 1-based in the sort command, so we have to increment the
2222                    # index.
2223                    $fieldSpec = ($i + 1) . $modifier;
2224                }
2225            }
2226            # Add this field to the sort command.
2227            $retVal .= " -k$fieldSpec";
2228        }
2229        # Return the result.
2230        return $retVal;
2231    }
2232    
2233    =head3 GetList
2234    
2235        my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params);
2236    
2237    Return a list of object descriptors for the specified objects as determined by the
2238    specified filter clause.
2239    
2240    This method is essentially the same as L</Get> except it returns a list of objects rather
2241    than a query object that can be used to get the results one record at a time.
2242    
2243    =over 4
2244    
2245    =item objectNames
2246    
2247    List containing the names of the entity and relationship objects to be retrieved.
2248    
2249    =item filterClause
2250    
2251    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
2252    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
2253    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
2254    in the filter clause should be added to the parameter list as additional parameters. The
2255    fields in a filter clause can come from primary entity relations, relationship relations,
2256    or secondary entity relations; however, all of the entities and relationships involved must
2257    be included in the list of object names.
2258    
2259    The filter clause can also specify a sort order. To do this, simply follow the filter string
2260    with an ORDER BY clause. For example, the following filter string gets all genomes for a
2261    particular genus and sorts them by species name.
2262    
2263        "Genome(genus) = ? ORDER BY Genome(species)"
2264    
2265    The rules for field references in a sort order are the same as those for field references in the
2266    filter clause in general; however, odd things may happen if a sort field is from a secondary
2267    relation.
2268    
2269    =item params
2270    
2271    Reference to a list of parameter values to be substituted into the filter clause.
2272    
2273    =item RETURN
2274    
2275    Returns a list of B<ERDBObject>s that satisfy the query conditions.
2276    
2277    =back
2278    
2279    =cut
2280    #: Return Type @%
2281    sub GetList {
2282        # Get the parameters.
2283        my ($self, $objectNames, $filterClause, $params) = @_;
2284        # Declare the return variable.
2285        my @retVal = ();
2286        # Perform the query.
2287        my $query = $self->Get($objectNames, $filterClause, $params);
2288        # Loop through the results.
2289        while (my $object = $query->Fetch) {
2290            push @retVal, $object;
2291        }
2292        # Return the result.
2293        return @retVal;
2294    }
2295    
2296    =head3 GetCount
2297    
2298        my $count = $erdb->GetCount(\@objectNames, $filter, \@params);
2299    
2300    Return the number of rows found by a specified query. This method would
2301    normally be used to count the records in a single table. For example, in a
2302    genetics database
2303    
2304        my $count = $erdb->GetCount(['Genome'], 'Genome(genus-species) LIKE ?', ['homo %']);
2305    
2306    would return the number of genomes for the genus I<homo>. It is conceivable, however,
2307    to use it to return records based on a join. For example,
2308    
2309        my $count = $erdb->GetCount(['HasFeature', 'Genome'], 'Genome(genus-species) LIKE ?',
2310                                    ['homo %']);
2311    
2312    would return the number of features for genomes in the genus I<homo>. Note that
2313    only the rows from the first table are counted. If the above command were
2314    
2315        my $count = $erdb->GetCount(['Genome', 'Feature'], 'Genome(genus-species) LIKE ?',
2316                                    ['homo %']);
2317    
2318    it would return the number of genomes, not the number of genome/feature pairs.
2319    
2320    =over 4
2321    
2322    =item objectNames
2323    
2324    Reference to a list of the objects (entities and relationships) included in the
2325    query.
2326    
2327    =item filter
2328    
2329    A filter clause for restricting the query. The rules are the same as for the L</Get>
2330    method.
2331    
2332    =item params
2333    
2334    Reference to a list of the parameter values to be substituted for the parameter marks
2335    in the filter.
2336    
2337    =item RETURN
2338    
2339    Returns a count of the number of records in the first table that would satisfy
2340    the query.
2341    
2342    =back
2343    
2344    =cut
2345    
2346    sub GetCount {
2347        # Get the parameters.
2348        my ($self, $objectNames, $filter, $params) = @_;
2349        # Insure the params argument is an array reference if the caller left it off.
2350        if (! defined($params)) {
2351            $params = [];
2352        }
2353        # Declare the return variable.
2354        my $retVal;
2355        # Find out if we're counting an entity or a relationship.
2356        my $countedField;
2357        if ($self->IsEntity($objectNames->[0])) {
2358            $countedField = "id";
2359        } else {
2360            # For a relationship we count the to-link because it's usually more
2361            # numerous. Note we're automatically converting to the SQL form
2362            # of the field name (to_link vs. to-link).
2363            $countedField = "to_link";
2364        }
2365        # Create the SQL command suffix to get the desired records.
2366        my ($suffix, $mappedNameListRef, $mappedNameHashRef) = $self->_SetupSQL($objectNames,
2367                                                                                $filter);
2368        # Prefix it with text telling it we want a record count.
2369        my $firstObject = $mappedNameListRef->[0];
2370        my $command = "SELECT COUNT($firstObject.$countedField) $suffix";
2371        # Prepare and execute the command.
2372        my $sth = $self->_GetStatementHandle($command, $params);
2373        # Get the count value.
2374        ($retVal) = $sth->fetchrow_array();
2375        # Check for a problem.
2376        if (! defined($retVal)) {
2377            if ($sth->err) {
2378                # Here we had an SQL error.
2379                Confess("Error retrieving row count: " . $sth->errstr());
2380            } else {
2381                # Here we have no result.
2382                Confess("No result attempting to retrieve row count.");
2383            }
2384        }
2385        # Return the result.
2386        return $retVal;
2387    }
2388    
2389    =head3 ComputeObjectSentence
2390    
2391        my $sentence = $erdb->ComputeObjectSentence($objectName);
2392    
2393    Check an object name, and if it is a relationship convert it to a relationship sentence.
2394    
2395    =over 4
2396    
2397    =item objectName
2398    
2399    Name of the entity or relationship.
2400    
2401    =item RETURN
2402    
2403    Returns a string containing the entity name or a relationship sentence.
2404    
2405    =back
2406    
2407    =cut
2408    
2409    sub ComputeObjectSentence {
2410        # Get the parameters.
2411        my ($self, $objectName) = @_;
2412        # Set the default return value.
2413        my $retVal = $objectName;
2414        # Look for the object as a relationship.
2415        my $relTable = $self->{_metaData}->{Relationships};
2416        if (exists $relTable->{$objectName}) {
2417            # Get the relationship sentence.
2418            $retVal = _ComputeRelationshipSentence($objectName, $relTable->{$objectName});
2419        }
2420        # Return the result.
2421        return $retVal;
2422    }
2423    
2424    =head3 DumpRelations
2425    
2426        $erdb->DumpRelations($outputDirectory);
2427    
2428    Write the contents of all the relations to tab-delimited files in the specified directory.
2429    Each file will have the same name as the relation dumped, with an extension of DTX.
2430    
2431    =over 4
2432    
2433    =item outputDirectory
2434    
2435    Name of the directory into which the relation files should be dumped.
2436    
2437    =back
2438    
2439    =cut
2440    
2441    sub DumpRelations {
2442        # Get the parameters.
2443        my ($self, $outputDirectory) = @_;
2444        # Now we need to run through all the relations. First, we loop through the entities.
2445        my $metaData = $self->{_metaData};
2446        my $entities = $metaData->{Entities};
2447        for my $entityName (keys %{$entities}) {
2448            my $entityStructure = $entities->{$entityName};
2449            # Get the entity's relations.
2450            my $relationList = $entityStructure->{Relations};
2451            # Loop through the relations, dumping them.
2452            for my $relationName (keys %{$relationList}) {
2453                my $relation = $relationList->{$relationName};
2454                $self->_DumpRelation($outputDirectory, $relationName, $relation);
2455            }
2456        }
2457        # Next, we loop through the relationships.
2458        my $relationships = $metaData->{Relationships};
2459        for my $relationshipName (keys %{$relationships}) {
2460            my $relationshipStructure = $relationships->{$relationshipName};
2461            # Dump this relationship's relation.
2462            $self->_DumpRelation($outputDirectory, $relationshipName, $relationshipStructure->{Relations}->{$relationshipName});
2463        }
2464    }
2465    
2466    =head3 InsertValue
2467    
2468        $erdb->InsertValue($entityID, $fieldName, $value);
2469    
2470    This method will insert a new value into the database. The value must be one
2471    associated with a secondary relation, since primary values cannot be inserted:
2472    they occur exactly once. Secondary values, on the other hand, can be missing
2473    or multiply-occurring.
2474    
2475    =over 4
2476    
2477    =item entityID
2478    
2479    ID of the object that is to receive the new value.
2480    
2481    =item fieldName
2482    
2483    Field name for the new value-- this includes the entity name, since
2484    field names are of the format I<objectName>C<(>I<fieldName>C<)>.
2485    
2486    =item value
2487    
2488    New value to be put in the field.
2489    
2490    =back
2491    
2492    =cut
2493    
2494    sub InsertValue {
2495        # Get the parameters.
2496        my ($self, $entityID, $fieldName, $value) = @_;
2497        # Parse the entity name and the real field name.
2498        if ($fieldName =~ /^([^(]+)\(([^)]+)\)/) {
2499            my $entityName = $1;
2500            my $fieldTitle = $2;
2501            # Get its descriptor.
2502            if (!$self->IsEntity($entityName)) {
2503                Confess("$entityName is not a valid entity.");
2504            } else {
2505                my $entityData = $self->{_metaData}->{Entities}->{$entityName};
2506                # Find the relation containing this field.
2507                my $fieldHash = $entityData->{Fields};
2508                if (! exists $fieldHash->{$fieldTitle}) {
2509                    Confess("$fieldTitle not found in $entityName.");
2510                } else {
2511                    my $relation = $fieldHash->{$fieldTitle}->{relation};
2512                    if ($relation eq $entityName) {
2513                        Confess("Cannot do InsertValue on primary field $fieldTitle of $entityName.");
2514                    } else {
2515                        # Now we can create an INSERT statement.
2516                        my $dbh = $self->{_dbh};
2517                        my $fixedName = _FixName($fieldTitle);
2518                        my $statement = "INSERT INTO $relation (id, $fixedName) VALUES(?, ?)";
2519                        # Execute the command.
2520                        $dbh->SQL($statement, 0, $entityID, $value);
2521                    }
2522                }
2523            }
2524        } else {
2525            Confess("$fieldName is not a valid field name.");
2526        }
2527    }
2528    
2529    =head3 InsertObject
2530    
2531        $erdb->InsertObject($objectType, \%fieldHash);
2532    
2533    Insert an object into the database. The object is defined by a type name and then a hash
2534    of field names to values. Field values in the primary relation are represented by scalars.
2535    (Note that for relationships, the primary relation is the B<only> relation.)
2536    Field values for the other relations comprising the entity are always list references. For
2537    example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases
2538    C<ZP_00210270.1> and C<gi|46206278>.
2539    
2540        $erdb->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']});
2541    
2542    The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
2543    property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
2544    
2545        $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'});
2546    
2547    =over 4
2548    
2549    =item newObjectType
2550    
2551    Type name of the object to insert.
2552    
2553    =item fieldHash
2554    
2555    Hash of field names to values.
2556    
2557    =back
2558    
2559    =cut
2560    
2561    sub InsertObject {
2562        # Get the parameters.
2563        my ($self, $newObjectType, $fieldHash) = @_;
2564        # Denote that so far we appear successful.
2565        my $retVal = 1;
2566        # Get the database handle.
2567        my $dbh = $self->{_dbh};
2568        # Get the relation list.
2569        my $relationTable = $self->_GetRelationTable($newObjectType);
2570        # Loop through the relations. We'll build insert statements for each one. If a relation is
2571        # secondary, we may end up generating multiple insert statements. If an error occurs, we
2572        # stop the loop.
2573        my @relationList = keys %{$relationTable};
2574        for (my $i = 0; $retVal && $i <= $#relationList; $i++) {
2575            my $relationName = $relationList[$i];
2576            my $relationDefinition = $relationTable->{$relationName};
2577            # Get the relation's fields. For each field we will collect a value in the corresponding
2578            # position of the @valueList array. If one of the fields is missing, we will add it to the
2579            # @missing list.
2580            my @fieldList = @{$relationDefinition->{Fields}};
2581            my @fieldNameList = ();
2582            my @valueList = ();
2583            my @missing = ();
2584            my $recordCount = 1;
2585            for my $fieldDescriptor (@fieldList) {
2586                # Get the field name and save it. Note we need to fix it up so the hyphens
2587                # are converted to underscores.
2588                my $fieldName = $fieldDescriptor->{name};
2589                push @fieldNameList, _FixName($fieldName);
2590                # Look for the named field in the incoming structure. Note that we are looking
2591                # for the real field name, not the fixed-up one!
2592                if (exists $fieldHash->{$fieldName}) {
2593                    # Here we found the field. Stash it in the value list.
2594                    my $value = $fieldHash->{$fieldName};
2595                    push @valueList, $value;
2596                    # If the value is a list, we may need to increment the record count.
2597                    if (ref $value eq "ARRAY") {
2598                        my $thisCount = @{$value};
2599                        if ($recordCount == 1) {
2600                            # Here we have our first list, so we save its count.
2601                            $recordCount = $thisCount;
2602                        } elsif ($recordCount != $thisCount) {
2603                            # Here we have a second list, so its length has to match the
2604                            # previous lists.
2605                            Trace("Field $value in new $newObjectType object has an invalid list length $thisCount. Expected $recordCount.") if T(0);
2606                            $retVal = 0;
2607                        }
2608                    }
2609                } else {
2610                    # Here the field is not present. Flag it as missing.
2611                    push @missing, $fieldName;
2612                }
2613            }
2614            # If we are the primary relation, add the new-record flag.
2615            if ($relationName eq $newObjectType) {
2616                push @valueList, 1;
2617                push @fieldNameList, "new_record";
2618            }
2619            # Only proceed if there are no missing fields.
2620            if (@missing > 0) {
2621                Trace("Relation $relationName for $newObjectType skipped due to missing fields: " .
2622                    join(' ', @missing)) if T(1);
2623            } else {
2624                # Build the INSERT statement.
2625                my $statement = "INSERT INTO $relationName (" . join (', ', @fieldNameList) .
2626                    ") VALUES (";
2627                # Create a marker list of the proper size and put it in the statement.
2628                my @markers = ();
2629                while (@markers < @fieldNameList) { push @markers, '?'; }
2630                $statement .= join(', ', @markers) . ")";
2631                # We have the insert statement, so prepare it.
2632                my $sth = $dbh->prepare_command($statement);
2633                Trace("Insert statement prepared: $statement") if T(3);
2634                # Now we loop through the values. If a value is scalar, we use it unmodified. If it's
2635                # a list, we use the current element. The values are stored in the @parameterList array.
2636                my $done = 0;
2637                for (my $i = 0; $i < $recordCount; $i++) {
2638                    # Clear the parameter list array.
2639                    my @parameterList = ();
2640                    # Loop through the values.
2641                    for my $value (@valueList) {
2642                        # Check to see if this is a scalar value.
2643                        if (ref $value eq "ARRAY") {
2644                            # Here we have a list value. Pull the current entry.
2645                            push @parameterList, $value->[$i];
2646                        } else {
2647                            # Here we have a scalar value. Use it unmodified.
2648                            push @parameterList, $value;
2649                        }
2650                    }
2651                    # Execute the INSERT statement with the specified parameter list.
2652                    $retVal = $sth->execute(@parameterList);
2653                    if (!$retVal) {
2654                        my $errorString = $sth->errstr();
2655                        Confess("Error inserting into $relationName: $errorString");
2656                    } else {
2657                        Trace("Insert successful using $parameterList[0].") if T(3);
2658                    }
2659                }
2660            }
2661        }
2662        # Return a 1 for backward compatability.
2663        return 1;
2664    }
2665    
2666    =head3 UpdateEntity
2667    
2668        $erdb->UpdateEntity($entityName, $id, \%fields);
2669    
2670    Update the values of an entity. This is an unprotected update, so it should only be
2671    done if the database resides on a database server.
2672    
2673    =over 4
2674    
2675    =item entityName
2676    
2677    Name of the entity to update. (This is the entity type.)
2678    
2679    =item id
2680    
2681    ID of the entity to update. If no entity exists with this ID, an error will be thrown.
2682    
2683    =item fields
2684    
2685    Reference to a hash mapping field names to their new values. All of the fields named
2686    must be in the entity's primary relation, and they cannot any of them be the ID field.
2687    
2688    =back
2689    
2690    =cut
2691    
2692    sub UpdateEntity {
2693        # Get the parameters.
2694        my ($self, $entityName, $id, $fields) = @_;
2695        # Get a list of the field names being updated.
2696        my @fieldList = keys %{$fields};
2697        # Verify that the fields exist.
2698        my $checker = $self->GetFieldTable($entityName);
2699        for my $field (@fieldList) {
2700            if ($field eq 'id') {
2701                Confess("Cannot update the ID field for entity $entityName.");
2702            } elsif ($checker->{$field}->{relation} ne $entityName) {
2703                Confess("Cannot find $field in primary relation of $entityName.");
2704            }
2705        }
2706        # Build the SQL statement.
2707        my @sets = ();
2708        my @valueList = ();
2709        for my $field (@fieldList) {
2710            push @sets, _FixName($field) . " = ?";
2711            push @valueList, $fields->{$field};
2712        }
2713        my $command = "UPDATE $entityName SET " . join(", ", @sets) . " WHERE id = ?";
2714        # Add the ID to the list of binding values.
2715        push @valueList, $id;
2716        # Call SQL to do the work.
2717        my $rows = $self->{_dbh}->SQL($command, 0, @valueList);
2718        # Check for errors.
2719        if ($rows == 0) {
2720            Confess("Entity $id of type $entityName not found.");
2721        }
2722    }
2723    
2724    =head3 LoadTable
2725    
2726        my $results = $erdb->LoadTable($fileName, $relationName, $truncateFlag);
2727    
2728    Load data from a tab-delimited file into a specified table, optionally re-creating the table
2729    first.
2730    
2731    =over 4
2732    
2733    =item fileName
2734    
2735    Name of the file from which the table data should be loaded.
2736    
2737    =item relationName
2738    
2739    Name of the relation to be loaded. This is the same as the table name.
2740    
2741    =item truncateFlag
2742    
2743    TRUE if the table should be dropped and re-created, else FALSE
2744    
2745    =item RETURN
2746    
2747    Returns a statistical object containing a list of the error messages.
2748    
2749    =back
2750    
2751    =cut
2752    sub LoadTable {
2753        # Get the parameters.
2754        my ($self, $fileName, $relationName, $truncateFlag) = @_;
2755        # Create the statistical return object.
2756        my $retVal = _GetLoadStats();
2757        # Trace the fact of the load.
2758        Trace("Loading table $relationName from $fileName") if T(2);
2759        # Get the database handle.
2760        my $dbh = $self->{_dbh};
2761        # Get the input file size.
2762        my $fileSize = -s $fileName;
2763        # Get the relation data.
2764        my $relation = $self->_FindRelation($relationName);
2765        # Check the truncation flag.
2766        if ($truncateFlag) {
2767            Trace("Creating table $relationName") if T(2);
2768            # Compute the row count estimate. We take the size of the load file,
2769            # divide it by the estimated row size, and then multiply by 2 to
2770            # leave extra room. We postulate a minimum row count of 1000 to
2771            # prevent problems with incoming empty load files.
2772            my $rowSize = $self->EstimateRowSize($relationName);
2773            my $estimate = $fileSize * 8 / $rowSize;
2774            if ($estimate < 1000) {
2775                $estimate = 1000;
2776            }
2777            # Re-create the table without its index.
2778            $self->CreateTable($relationName, 0, $estimate);
2779            # If this is a pre-index DBMS, create the index here.
2780            if ($dbh->{_preIndex}) {
2781                eval {
2782                    $self->CreateIndex($relationName);
2783                };
2784                if ($@) {
2785                    $retVal->AddMessage($@);
2786                }
2787            }
2788        }
2789        # Load the table.
2790        my $rv;
2791        eval {
2792            $rv = $dbh->load_table(file => $fileName, tbl => $relationName);
2793        };
2794        if (!defined $rv) {
2795            $retVal->AddMessage($@) if ($@);
2796            $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2797            Trace("Table load failed for $relationName.") if T(1);
2798        } else {
2799            # Here we successfully loaded the table.
2800            $retVal->Add("tables");
2801            my $size = -s $fileName;
2802            Trace("$size bytes loaded into $relationName.") if T(2);
2803            # If we're rebuilding, we need to create the table indexes.
2804            if ($truncateFlag) {
2805                # Indexes are created here for PostGres. For PostGres, indexes are
2806                # best built at the end. For MySQL, the reverse is true.
2807                if (! $dbh->{_preIndex}) {
2808                    eval {
2809                        $self->CreateIndex($relationName);
2810                    };
2811                    if ($@) {
2812                        $retVal->AddMessage($@);
2813                    }
2814                }
2815                # The full-text index (if any) is always built last, even for MySQL.
2816                # First we need to see if this table has a full-text index. Only
2817                # primary relations are allowed that privilege.
2818                Trace("Checking for full-text index on $relationName.") if T(2);
2819                if ($self->_IsPrimary($relationName)) {
2820                    $self->CreateSearchIndex($relationName);
2821                }
2822            }
2823        }
2824        # Analyze the table to improve performance.
2825        Trace("Analyzing and compacting $relationName.") if T(3);
2826        $dbh->vacuum_it($relationName);
2827        Trace("$relationName load completed.") if T(3);
2828        # Return the statistics.
2829        return $retVal;
2830    }
2831    
2832    =head3 CreateSearchIndex
2833    
2834        $erdb->CreateSearchIndex($objectName);
2835    
2836    Check for a full-text search index on the specified entity or relationship object, and
2837    if one is required, rebuild it.
2838    
2839    =over 4
2840    
2841    =item objectName
2842    
2843    Name of the entity or relationship to be indexed.
2844    
2845    =back
2846    
2847    =cut
2848    
2849    sub CreateSearchIndex {
2850        # Get the parameters.
2851        my ($self, $objectName) = @_;
2852        # Get the relation's entity/relationship structure.
2853        my $structure = $self->_GetStructure($objectName);
2854        # Get the database handle.
2855        my $dbh = $self->{_dbh};
2856        Trace("Checking for search fields in $objectName.") if T(3);
2857        # Check for a searchable fields list.
2858        if (exists $structure->{searchFields}) {
2859            # Here we know that we need to create a full-text search index.
2860            # Get an SQL-formatted field name list.
2861            my $fields = join(", ", _FixNames(@{$structure->{searchFields}}));
2862            # Create the index. If it already exists, it will be dropped.
2863            $dbh->create_index(tbl => $objectName, idx => "search_idx",
2864                               flds => $fields, kind => 'fulltext');
2865            Trace("Index created for $fields in $objectName.") if T(2);
2866        }
2867    }
2868    
2869    =head3 DropRelation
2870    
2871        $erdb->DropRelation($relationName);
2872    
2873    Physically drop a relation from the database.
2874    
2875    =over 4
2876    
2877    =item relationName
2878    
2879    Name of the relation to drop. If it does not exist, this method will have
2880    no effect.
2881    
2882    =back
2883    
2884    =cut
2885    
2886    sub DropRelation {
2887        # Get the parameters.
2888        my ($self, $relationName) = @_;
2889        # Get the database handle.
2890        my $dbh = $self->{_dbh};
2891        # Drop the relation. The method used here has no effect if the relation
2892        # does not exist.
2893        Trace("Invoking DB Kernel to drop $relationName.") if T(3);
2894        $dbh->drop_table(tbl => $relationName);
2895    }
2896    
2897    =head3 MatchSqlPattern
2898    
2899        my $matched = ERDB::MatchSqlPattern($value, $pattern);
2900    
2901    Determine whether or not a specified value matches an SQL pattern. An SQL
2902    pattern has two wild card characters: C<%> that matches multiple characters,
2903    and C<_> that matches a single character. These can be escaped using a
2904    backslash (C<\>). We pull this off by converting the SQL pattern to a
2905    PERL regular expression. As per SQL rules, the match is case-insensitive.
2906    
2907    =over 4
2908    
2909    =item value
2910    
2911    Value to be matched against the pattern. Note that an undefined or empty
2912    value will not match anything.
2913    
2914    =item pattern
2915    
2916    SQL pattern against which to match the value. An undefined or empty pattern will
2917    match everything.
2918    
2919    =item RETURN
2920    
2921    Returns TRUE if the value and pattern match, else FALSE.
2922    
2923    =back
2924    
2925    =cut
2926    
2927    sub MatchSqlPattern {
2928        # Get the parameters.
2929        my ($value, $pattern) = @_;
2930        # Declare the return variable.
2931        my $retVal;
2932        # Insure we have a pattern.
2933        if (! defined($pattern) || $pattern eq "") {
2934            $retVal = 1;
2935        } else {
2936            # Break the pattern into pieces around the wildcard characters. Because we
2937            # use parentheses in the split function's delimiter expression, we'll get
2938            # list elements for the delimiters as well as the rest of the string.
2939            my @pieces = split /([_%]|\\[_%])/, $pattern;
2940            # Check some fast special cases.
2941            if ($pattern eq '%') {
2942                # A null pattern matches everything.
2943                $retVal = 1;
2944            } elsif (@pieces == 1) {
2945                # No wildcards, so we have a literal comparison. Note we're case-insensitive.
2946                $retVal = (lc($value) eq lc($pattern));
2947            } elsif (@pieces == 2 && $pieces[1] eq '%') {
2948                # A wildcard at the end, so we have a substring match. This is also case-insensitive.
2949                $retVal = (lc(substr($value, 0, length($pieces[0]))) eq lc($pieces[0]));
2950            } else {
2951                # Okay, we have to do it the hard way. Convert each piece to a PERL pattern.
2952                my $realPattern = "";
2953                for my $piece (@pieces) {
2954                    # Determine the type of piece.
2955                    if ($piece eq "") {
2956                        # Empty pieces are ignored.
2957                    } elsif ($piece eq "%") {
2958                        # Here we have a multi-character wildcard. Note that it can match
2959                        # zero or more characters.
2960                        $realPattern .= ".*"
2961                    } elsif ($piece eq "_") {
2962                        # Here we have a single-character wildcard.
2963                        $realPattern .= ".";
2964                    } elsif ($piece eq "\\%" || $piece eq "\\_") {
2965                        # This is an escape sequence (which is a rare thing, actually).
2966                        $realPattern .= substr($piece, 1, 1);
2967                    } else {
2968                        # Here we have raw text.
2969                        $realPattern .= quotemeta($piece);
2970                    }
2971                }
2972                # Do the match.
2973                $retVal = ($value =~ /^$realPattern$/i ? 1 : 0);
2974            }
2975        }
2976        # Return the result.
2977        return $retVal;
2978    }
2979    
2980    =head3 GetEntity
2981    
2982        my $entityObject = $erdb->GetEntity($entityType, $ID);
2983    
2984    Return an object describing the entity instance with a specified ID.
2985    
2986    =over 4
2987    
2988    =item entityType
2989    
2990    Entity type name.
2991    
2992    =item ID
2993    
2994    ID of the desired entity.
2995    
2996    =item RETURN
2997    
2998    Returns a B<ERDBObject> representing the desired entity instance, or an undefined value if no
2999    instance is found with the specified key.
3000    
3001    =back
3002    
3003    =cut
3004    
3005    sub GetEntity {
3006        # Get the parameters.
3007        my ($self, $entityType, $ID) = @_;
3008        # Create a query.
3009        my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);
3010        # Get the first (and only) object.
3011        my $retVal = $query->Fetch();
3012        # Return the result.
3013        return $retVal;
3014    }
3015    
3016    =head3 GetChoices
3017    
3018        my @values = $erdb->GetChoices($entityName, $fieldName);
3019    
3020    Return a list of all the values for the specified field that are represented in the
3021    specified entity.
3022    
3023    Note that if the field is not indexed, then this will be a very slow operation.
3024    
3025    =over 4
3026    
3027    =item entityName
3028    
3029    Name of an entity in the database.
3030    
3031    =item fieldName
3032    
3033    Name of a field belonging to the entity. This is a raw field name without
3034    the standard parenthesized notation used in most calls.
3035    
3036    =item RETURN
3037    
3038    Returns a list of the distinct values for the specified field in the database.
3039    
3040    =back
3041    
3042    =cut
3043    
3044    sub GetChoices {
3045        # Get the parameters.
3046        my ($self, $entityName, $fieldName) = @_;
3047        # Declare the return variable.
3048        my @retVal;
3049        # Get the entity data structure.
3050        my $entityData = $self->_GetStructure($entityName);
3051        # Get the field.
3052        my $fieldHash = $entityData->{Fields};
3053        if (! exists $fieldHash->{$fieldName}) {
3054            Confess("$fieldName not found in $entityName.");
3055        } else {
3056            # Get the name of the relation containing the field.
3057            my $relation = $fieldHash->{$fieldName}->{relation};
3058            # Fix up the field name.
3059            my $realName = _FixName($fieldName);
3060            # Get the database handle.
3061            my $dbh = $self->{_dbh};
3062            # Query the database.
3063            my $results = $dbh->SQL("SELECT DISTINCT $realName FROM $relation");
3064            # Clean the results. They are stored as a list of lists, and we just want the one list.
3065            @retVal = sort map { $_->[0] } @{$results};
3066        }
3067        # Return the result.
3068        return @retVal;
3069    }
3070    
3071    =head3 GetEntityValues
3072    
3073        my @values = $erdb->GetEntityValues($entityType, $ID, \@fields);
3074    
3075    Return a list of values from a specified entity instance. If the entity instance
3076    does not exist, an empty list is returned.
3077    
3078    =over 4
3079    
3080    =item entityType
3081    
3082    Entity type name.
3083    
3084    =item ID
3085    
3086    ID of the desired entity.
3087    
3088    =item fields
3089    
3090    List of field names, each of the form I<objectName>C<(>I<fieldName>C<)>.
3091    
3092    =item RETURN
3093    
3094    Returns a flattened list of the values of the specified fields for the specified entity.
3095    
3096    =back
3097    
3098    =cut
3099    
3100    sub GetEntityValues {
3101        # Get the parameters.
3102        my ($self, $entityType, $ID, $fields) = @_;
3103        # Get the specified entity.
3104        my $entity = $self->GetEntity($entityType, $ID);
3105        # Declare the return list.
3106        my @retVal = ();
3107        # If we found the entity, push the values into the return list.
3108        if ($entity) {
3109            push @retVal, $entity->Values($fields);
3110        }
3111        # Return the result.
3112        return @retVal;
3113    }
3114    
3115    =head3 GetAll
3116    
3117        my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count);
3118    
3119    Return a list of values taken from the objects returned by a query. The first three
3120    parameters correspond to the parameters of the L</Get> method. The final parameter is
3121    a list of the fields desired from each record found by the query. The field name
3122    syntax is the standard syntax used for fields in the B<ERDB> system--
3123    B<I<objectName>(I<fieldName>)>-- where I<objectName> is the name of the relevant entity
3124    or relationship and I<fieldName> is the name of the field.
3125    
3126    The list returned will be a list of lists. Each element of the list will contain
3127    the values returned for the fields specified in the fourth parameter. If one of the
3128    fields specified returns multiple values, they are flattened in with the rest. For
3129    example, the following call will return a list of the features in a particular
3130    spreadsheet cell, and each feature will be represented by a list containing the
3131    feature ID followed by all of its essentiality determinations.
3132    
3133        @query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(essential)']);
3134    
3135    =over 4
3136    
3137    =item objectNames
3138    
3139    List containing the names of the entity and relationship objects to be retrieved.
3140    
3141    =item filterClause
3142    
3143    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
3144    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
3145    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
3146    parameter list as additional parameters. The fields in a filter clause can come from primary
3147    entity relations, relationship relations, or secondary entity relations; however, all of the
3148    entities and relationships involved must be included in the list of object names.
3149    
3150    =item parameterList
3151    
3152    List of the parameters to be substituted in for the parameters marks in the filter clause.
3153    
3154    =item fields
3155    
3156    List of the fields to be returned in each element of the list returned.
3157    
3158    =item count
3159    
3160    Maximum number of records to return. If omitted or 0, all available records will be returned.
3161    
3162    =item RETURN
3163    
3164    Returns a list of list references. Each element of the return list contains the values for the
3165    fields specified in the B<fields> parameter.
3166    
3167    =back
3168    
3169    =cut
3170    #: Return Type @@;
3171    sub GetAll {
3172        # Get the parameters.
3173        my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
3174        # Translate the parameters from a list reference to a list. If the parameter
3175        # list is a scalar we convert it into a singleton list.
3176        my @parmList = ();
3177        if (ref $parameterList eq "ARRAY") {
3178            Trace("GetAll parm list is an array.") if T(4);
3179            @parmList = @{$parameterList};
3180        } else {
3181            Trace("GetAll parm list is a scalar: $parameterList.") if T(4);
3182            push @parmList, $parameterList;
3183        }
3184        # Insure the counter has a value.
3185        if (!defined $count) {
3186            $count = 0;
3187        }
3188        # Add the row limit to the filter clause.
3189        if ($count > 0) {
3190            $filterClause .= " LIMIT $count";
3191        }
3192        # Create the query.
3193        my $query = $self->Get($objectNames, $filterClause, \@parmList);
3194        # Set up a counter of the number of records read.
3195        my $fetched = 0;
3196        # Loop through the records returned, extracting the fields. Note that if the
3197        # counter is non-zero, we stop when the number of records read hits the count.
3198        my @retVal = ();
3199        while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {
3200            my @rowData = $row->Values($fields);
3201            push @retVal, \@rowData;
3202            $fetched++;
3203        }
3204        Trace("$fetched rows returned in GetAll.") if T(SQL => 4);
3205        # Return the resulting list.
3206        return @retVal;
3207    }
3208    
3209    =head3 Exists
3210    
3211        my $found = $sprout->Exists($entityName, $entityID);
3212    
3213    Return TRUE if an entity exists, else FALSE.
3214    
3215    =over 4
3216    
3217    =item entityName
3218    
3219    Name of the entity type (e.g. C<Feature>) relevant to the existence check.
3220    
3221    =item entityID
3222    
3223    ID of the entity instance whose existence is to be checked.
3224    
3225    =item RETURN
3226    
3227    Returns TRUE if the entity instance exists, else FALSE.
3228    
3229    =back
3230    
3231    =cut
3232    #: Return Type $;
3233    sub Exists {
3234        # Get the parameters.
3235        my ($self, $entityName, $entityID) = @_;
3236        # Check for the entity instance.
3237        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
3238        my $testInstance = $self->GetEntity($entityName, $entityID);
3239        # Return an existence indicator.
3240        my $retVal = ($testInstance ? 1 : 0);
3241        return $retVal;
3242    }
3243    
3244    =head3 EstimateRowSize
3245    
3246        my $rowSize = $erdb->EstimateRowSize($relName);
3247    
3248    Estimate the row size of the specified relation. The estimated row size is computed by adding
3249    up the average length for each data type.
3250    
3251    =over 4
3252    
3253    =item relName
3254    
3255    Name of the relation whose estimated row size is desired.
3256    
3257    =item RETURN
3258    
3259    Returns an estimate of the row size for the specified relation.
3260    
3261    =back
3262    
3263  Returns a string containing the entity name or a relationship sentence.  =cut
3264    #: Return Type $;
3265    sub EstimateRowSize {
3266        # Get the parameters.
3267        my ($self, $relName) = @_;
3268        # Declare the return variable.
3269        my $retVal = 0;
3270        # Find the relation descriptor.
3271        my $relation = $self->_FindRelation($relName);
3272        # Get the list of fields.
3273        for my $fieldData (@{$relation->{Fields}}) {
3274            # Get the field type and add its length.
3275            my $fieldLen = $TypeTable{$fieldData->{type}}->{avgLen};
3276            $retVal += $fieldLen;
3277        }
3278        # Return the result.
3279        return $retVal;
3280    }
3281    
3282    =head3 GetFieldTable
3283    
3284        my $fieldHash = $self->GetFieldTable($objectnName);
3285    
3286    Get the field structure for a specified entity or relationship.
3287    
3288    =over 4
3289    
3290    =item objectName
3291    
3292    Name of the desired entity or relationship.
3293    
3294    =item RETURN
3295    
3296    The table containing the field descriptors for the specified object.
3297    
3298  =back  =back
3299    
3300  =cut  =cut
3301    
3302  sub ComputeObjectSentence {  sub GetFieldTable {
3303      # Get the parameters.      # Get the parameters.
3304      my ($self, $objectName) = @_;      my ($self, $objectName) = @_;
3305      # Set the default return value.      # Get the descriptor from the metadata.
3306      my $retVal = $objectName;      my $objectData = $self->_GetStructure($objectName);
3307      # Look for the object as a relationship.      # Return the object's field table.
3308      my $relTable = $self->{_metaData}->{Relationships};      return $objectData->{Fields};
3309      if (exists $relTable->{$objectName}) {  }
3310          # Get the relationship sentence.  
3311          $retVal = _ComputeRelationshipSentence($objectName, $relTable->{$objectName});  =head3 SplitKeywords
3312    
3313        my @keywords = ERDB::SplitKeywords($keywordString);
3314    
3315    This method returns a list of the positive keywords in the specified
3316    keyword string. All of the operators will have been stripped off,
3317    and if the keyword is preceded by a minus operator (C<->), it will
3318    not be in the list returned. The idea here is to get a list of the
3319    keywords the user wants to see. The list will be processed to remove
3320    duplicates.
3321    
3322    It is possible to create a string that confuses this method. For example
3323    
3324        frog toad -frog
3325    
3326    would return both C<frog> and C<toad>. If this is a problem we can deal
3327    with it later.
3328    
3329    =over 4
3330    
3331    =item keywordString
3332    
3333    The keyword string to be parsed.
3334    
3335    =item RETURN
3336    
3337    Returns a list of the words in the keyword string the user wants to
3338    see.
3339    
3340    =back
3341    
3342    =cut
3343    
3344    sub SplitKeywords {
3345        # Get the parameters.
3346        my ($keywordString) = @_;
3347        # Make a safety copy of the string. (This helps during debugging.)
3348        my $workString = $keywordString;
3349        # Convert operators we don't care about to spaces.
3350        $workString =~ tr/+"()<>/ /;
3351        # Split the rest of the string along space boundaries. Note that we
3352        # eliminate any words that are zero length or begin with a minus sign.
3353        my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
3354        # Use a hash to remove duplicates.
3355        my %words = map { $_ => 1 } @wordList;
3356        # Return the result.
3357        return sort keys %words;
3358    }
3359    
3360    =head3 ValidateFieldName
3361    
3362        my $okFlag = ERDB::ValidateFieldName($fieldName);
3363    
3364    Return TRUE if the specified field name is valid, else FALSE. Valid field names must
3365    be hyphenated words subject to certain restrictions.
3366    
3367    =over 4
3368    
3369    =item fieldName
3370    
3371    Field name to be validated.
3372    
3373    =item RETURN
3374    
3375    Returns TRUE if the field name is valid, else FALSE.
3376    
3377    =back
3378    
3379    =cut
3380    
3381    sub ValidateFieldName {
3382        # Get the parameters.
3383        my ($fieldName) = @_;
3384        # Declare the return variable. The field name is valid until we hear
3385        # differently.
3386        my $retVal = 1;
3387        # Compute the maximum name length.
3388        my $maxLen = $TypeTable{'name-string'}->{maxLen};
3389        # Look for bad stuff in the name.
3390        if ($fieldName =~ /--/) {
3391            # Here we have a doubled minus sign.
3392            Trace("Field name $fieldName has a doubled hyphen.") if T(1);
3393            $retVal = 0;
3394        } elsif ($fieldName !~ /^[A-Za-z]/) {
3395            # Here the field name is missing the initial letter.
3396            Trace("Field name $fieldName does not begin with a letter.") if T(1);
3397            $retVal = 0;
3398        } elsif (length($fieldName) > $maxLen) {
3399            # Here the field name is too long.
3400            Trace("Maximum field name length is $maxLen. Field name must be truncated to " . substr($fieldName,0, $maxLen) . ".");
3401        } else {
3402            # Strip out the minus signs. Everything remaining must be a letter,
3403            # underscore, or digit.
3404            my $strippedName = $fieldName;
3405            $strippedName =~ s/-//g;
3406            if ($strippedName !~ /^(\w|\d)+$/) {
3407                Trace("Field name $fieldName contains illegal characters.") if T(1);
3408                $retVal = 0;
3409            }
3410      }      }
3411      # Return the result.      # Return the result.
3412      return $retVal;      return $retVal;
3413  }  }
3414    
3415  =head3 DumpRelations  =head3 ReadMetaXML
3416    
3417        my $rawMetaData = ERDB::ReadDBD($fileName);
3418    
3419    This method reads a raw database definition XML file and returns it.
3420    Normally, the metadata used by the ERDB system has been processed and
3421    modified to make it easier to load and retrieve the data; however,
3422    this method can be used to get the data in its raw form.
3423    
3424    =over 4
3425    
3426    =item fileName
3427    
3428    Name of the XML file to read.
3429    
3430    =item RETURN
3431    
3432    Returns a hash reference containing the raw XML data from the specified file.
3433    
3434    =back
3435    
3436    =cut
3437    
3438    sub ReadMetaXML {
3439        # Get the parameters.
3440        my ($fileName) = @_;
3441        # Read the XML.
3442        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
3443        Trace("XML metadata loaded from file $fileName.") if T(1);
3444        # Return the result.
3445        return $retVal;
3446    }
3447    
3448    =head3 GetEntityFieldHash
3449    
3450        my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName);
3451    
3452    Get the field hash of the named entity in the specified raw XML structure.
3453    The field hash may not exist, in which case we need to create it.
3454    
3455    =over 4
3456    
3457    =item structure
3458    
3459    Raw XML structure defininng the database. This is not the run-time XML used by
3460    an ERDB object, since that has all sorts of optimizations built-in.
3461    
3462    =item entityName
3463    
3464    Name of the entity whose field structure is desired.
3465    
3466    =item RETURN
3467    
3468    Returns the field hash used to define the entity's fields.
3469    
3470    =back
3471    
3472    =cut
3473    
3474    sub GetEntityFieldHash {
3475        # Get the parameters.
3476        my ($structure, $entityName) = @_;
3477        # Get the entity structure.
3478        my $entityData = $structure->{Entities}->{$entityName};
3479        # Look for a field structure.
3480        my $retVal = $entityData->{Fields};
3481        # If it doesn't exist, create it.
3482        if (! defined($retVal)) {
3483            $entityData->{Fields} = {};
3484            $retVal = $entityData->{Fields};
3485        }
3486        # Return the result.
3487        return $retVal;
3488    }
3489    
3490    =head3 WriteMetaXML
3491    
3492        ERDB::WriteMetaXML($structure, $fileName);
3493    
3494    Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
3495    used to update the database definition. It must be used with care, however, since it
3496    will only work on a raw structure, not on the processed structure created by an ERDB
3497    constructor.
3498    
3499    =over 4
3500    
3501    =item structure
3502    
3503    XML structure to be written to the file.
3504    
3505    =item fileName
3506    
3507    Name of the output file to which the updated XML should be stored.
3508    
3509    =back
3510    
3511    =cut
3512    
3513    sub WriteMetaXML {
3514        # Get the parameters.
3515        my ($structure, $fileName) = @_;
3516        # Compute the output.
3517        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
3518        # Write it to the file.
3519        my $xmlOut = Open(undef, ">$fileName");
3520        print $xmlOut $fileString;
3521    }
3522    
3523    
3524    =head3 HTMLNote
3525    
3526    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
3527    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
3528    Except for C<[p]>, all the codes are closed by slash-codes. So, for
3529    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
3530    
3531        my $realHtml = ERDB::HTMLNote($dataString);
3532    
3533    =over 4
3534    
3535    =item dataString
3536    
3537    String to convert to HTML.
3538    
3539    =item RETURN
3540    
3541    An HTML string derived from the input string.
3542    
3543    =back
3544    
3545    =cut
3546    
3547    sub HTMLNote {
3548        # Get the parameter.
3549        my ($dataString) = @_;
3550        # HTML-escape the text.
3551        my $retVal = CGI::escapeHTML($dataString);
3552        # Substitute the bulletin board codes.
3553        $retVal =~ s!\[(/?[bi])\]!<$1>!g;
3554        $retVal =~ s!\[p\]!</p><p>!g;
3555        $retVal =~ s!\[link\s+([^\]]+)\]!<a href="$1">!g;
3556        $retVal =~ s!\[/link\]!</a>!g;
3557        # Return the result.
3558        return $retVal;
3559    }
3560    
3561    =head3 BeginTran
3562    
3563        $erdb->BeginTran();
3564    
3565    Start a database transaction.
3566    
3567    =cut
3568    
3569    sub BeginTran {
3570        my ($self) = @_;
3571        $self->{_dbh}->begin_tran();
3572    
3573    }
3574    
3575    =head3 CommitTran
3576    
3577        $erdb->CommitTran();
3578    
3579    Commit an active database transaction.
3580    
3581    =cut
3582    
3583    sub CommitTran {
3584        my ($self) = @_;
3585        $self->{_dbh}->commit_tran();
3586    }
3587    
3588    =head3 RollbackTran
3589    
3590        $erdb->RollbackTran();
3591    
3592    Roll back an active database transaction.
3593    
3594    =cut
3595    
3596    sub RollbackTran {
3597        my ($self) = @_;
3598        $self->{_dbh}->roll_tran();
3599    }
3600    
3601    =head3 UpdateField
3602    
3603        my $count = $erdb->UpdateField($objectNames, $fieldName, $oldValue, $newValue, $filter, $parms);
3604    
3605    Update all occurrences of a specific field value to a new value. The number of rows changed will be
3606    returned.
3607    
3608    =over 4
3609    
3610    =item fieldName
3611    
3612    Name of the field in standard I<objectName>C<(>I<fieldName>C<)> format.
3613    
3614    =item oldValue
3615    
3616    Value to be modified. All occurrences of this value in the named field will be replaced by the
3617    new value.
3618    
3619    =item newValue
3620    
3621    New value to be substituted for the old value when it's found.
3622    
3623    =item filter
3624    
3625    A standard ERDB filter clause (see L</Get>). The filter will be applied before any substitutions take place.
3626    
3627    =item parms
3628    
3629    Reference to a list of parameter values in the filter.
3630    
3631    =item RETURN
3632    
3633    Returns the number of rows modified.
3634    
3635    =back
3636    
3637    =cut
3638    
3639    sub UpdateField {
3640        # Get the parameters.
3641        my ($self, $fieldName, $oldValue, $newValue, $filter, $parms) = @_;
3642        # Get the object and field names from the field name parameter.
3643        $fieldName =~ /^([^(]+)\(([^)]+)\)/;
3644        my $objectName = $1;
3645        my $realFieldName = _FixName($2);
3646        # Add the old value to the filter. Note we allow the possibility that no
3647        # filter was specified.
3648        my $realFilter = "$fieldName = ?";
3649        if ($filter) {
3650            $realFilter .= " AND $filter";
3651        }
3652        # Format the query filter.
3653        my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
3654            $self->_SetupSQL([$objectName], $realFilter);
3655        # Create the query. Since there is only one object name, the mapped-name data is not
3656        # necessary. Neither is the FROM clause.
3657        $suffix =~ s/^FROM.+WHERE\s+//;
3658        # Create the update statement.
3659        my $command = "UPDATE $objectName SET $realFieldName = ? WHERE $suffix";
3660        # Get the database handle.
3661        my $dbh = $self->{_dbh};
3662        # Add the old and new values to the parameter list. Note we allow the possibility that
3663        # there are no user-supplied parameters.
3664        my @params = ($newValue, $oldValue);
3665        if (defined $parms) {
3666            push @params, @{$parms};
3667        }
3668        # Execute the update.
3669        my $retVal = $dbh->SQL($command, 0, @params);
3670        # Make the funky zero a real zero.
3671        if ($retVal == 0) {
3672            $retVal = 0;
3673        }
3674        # Return the result.
3675        return $retVal;
3676    }
3677    
3678    
3679    =head2 Data Mining Methods
3680    
3681    =head3 GetUsefulCrossValues
3682    
3683        my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship);
3684    
3685    Return a list of the useful attributes that would be returned by a B<Cross> call
3686    from an entity of the source entity type through the specified relationship. This
3687    means it will return the fields of the target entity type and the intersection data
3688    fields in the relationship. Only primary table fields are returned. In other words,
3689    the field names returned will be for fields where there is always one and only one
3690    value.
3691    
3692    =over 4
3693    
3694    =item sourceEntity
3695    
3696  C<< $erdb->DumpRelations($outputDirectory); >>  Name of the entity from which the relationship crossing will start.
3697    
3698  Write the contents of all the relations to tab-delimited files in the specified directory.  =item relationship
 Each file will have the same name as the relation dumped, with an extension of DTX.  
3699    
3700  =over 4  Name of the relationship being crossed.
3701    
3702  =item outputDirectory  =item RETURN
3703    
3704  Name of the directory into which the relation files should be dumped.  Returns a list of field names in Sprout field format (I<objectName>C<(>I<fieldName>C<)>.
3705    
3706  =back  =back
3707    
3708  =cut  =cut
3709    #: Return Type @;
3710  sub DumpRelations {  sub GetUsefulCrossValues {
3711      # Get the parameters.      # Get the parameters.
3712      my ($self, $outputDirectory) = @_;      my ($self, $sourceEntity, $relationship) = @_;
3713      # Now we need to run through all the relations. First, we loop through the entities.      # Declare the return variable.
3714      my $metaData = $self->{_metaData};      my @retVal = ();
3715      my $entities = $metaData->{Entities};      # Determine the target entity for the relationship. This is whichever entity is not
3716      for my $entityName (keys %{$entities}) {      # the source entity. So, if the source entity is the FROM, we'll get the name of
3717          my $entityStructure = $entities->{$entityName};      # the TO, and vice versa.
3718          # Get the entity's relations.      my $relStructure = $self->_GetStructure($relationship);
3719          my $relationList = $entityStructure->{Relations};      my $targetEntityType = ($relStructure->{from} eq $sourceEntity ? "to" : "from");
3720          # Loop through the relations, dumping them.      my $targetEntity = $relStructure->{$targetEntityType};
3721          for my $relationName (keys %{$relationList}) {      # Get the field table for the entity.
3722              my $relation = $relationList->{$relationName};      my $entityFields = $self->GetFieldTable($targetEntity);
3723              $self->_DumpRelation($outputDirectory, $relationName, $relation);      # The field table is a hash. The hash key is the field name. The hash value is a structure.
3724          }      # For the entity fields, the key aspect of the target structure is that the {relation} value
3725      }      # must match the entity name.
3726      # Next, we loop through the relationships.      my @fieldList = map { "$targetEntity($_)" } grep { $entityFields->{$_}->{relation} eq $targetEntity }
3727      my $relationships = $metaData->{Relationships};                          keys %{$entityFields};
3728      for my $relationshipName (keys %{$relationships}) {      # Push the fields found onto the return variable.
3729          my $relationshipStructure = $relationships->{$relationshipName};      push @retVal, sort @fieldList;
3730          # Dump this relationship's relation.      # Get the field table for the relationship.
3731          $self->_DumpRelation($outputDirectory, $relationshipName, $relationshipStructure->{Relations}->{$relationshipName});      my $relationshipFields = $self->GetFieldTable($relationship);
3732      }      # Here we have a different rule. We want all the fields other than "from-link" and "to-link".
3733        # This may end up being an empty set.
3734        my @fieldList2 = map { "$relationship($_)" } grep { $_ ne "from-link" && $_ ne "to-link" }
3735                            keys %{$relationshipFields};
3736        # Push these onto the return list.
3737        push @retVal, sort @fieldList2;
3738        # Return the result.
3739        return @retVal;
3740  }  }
3741    
3742  =head3 InsertObject  =head3 FindColumn
   
 C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>  
   
 Insert an object into the database. The object is defined by a type name and then a hash  
 of field names to values. Field values in the primary relation are represented by scalars.  
 (Note that for relationships, the primary relation is the B<only> relation.)  
 Field values for the other relations comprising the entity are always list references. For  
 example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases  
 C<ZP_00210270.1> and C<gi|46206278>.  
   
 C<< $erdb->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>  
3743    
3744  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and      my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier);
 property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.  
3745    
3746  C<< $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>  Return the location a desired column in a data mining header line. The data
3747    mining header line is a tab-separated list of column names. The column
3748    identifier is either the numerical index of a column or the actual column
3749    name.
3750    
3751  =over 4  =over 4
3752    
3753  =item newObjectType  =item headerLine
3754    
3755  Type name of the object to insert.  The header line from a data mining command, which consists of a tab-separated
3756    list of column names.
3757    
3758  =item fieldHash  =item columnIdentifier
3759    
3760  Hash of field names to values.  Either the ordinal number of the desired column (1-based), or the name of the
3761    desired column.
3762    
3763  =item RETURN  =item RETURN
3764    
3765  Returns 1 if successful, 0 if an error occurred.  Returns the array index (0-based) of the desired column.
3766    
3767  =back  =back
3768    
3769  =cut  =cut
3770    
3771  sub InsertObject {  sub FindColumn {
3772      # Get the parameters.      # Get the parameters.
3773      my ($self, $newObjectType, $fieldHash) = @_;      my ($headerLine, $columnIdentifier) = @_;
3774      # Denote that so far we appear successful.      # Declare the return variable.
3775      my $retVal = 1;      my $retVal;
3776      # Get the database handle.      # Split the header line into column names.
3777      my $dbh = $self->{_dbh};      my @headers = ParseColumns($headerLine);
3778      # Get the relation list.      # Determine whether we have a number or a name.
3779      my $relationTable = $self->_GetRelationTable($newObjectType);      if ($columnIdentifier =~ /^\d+$/) {
3780      # Loop through the relations. We'll build insert statements for each one. If a relation is          # Here we have a number. Subtract 1 and validate the result.
3781      # secondary, we may end up generating multiple insert statements. If an error occurs, we          $retVal = $columnIdentifier - 1;
3782      # stop the loop.          if ($retVal < 0 || $retVal > $#headers) {
3783      my @relationList = keys %{$relationTable};              Confess("Invalid column identifer \"$columnIdentifier\": value out of range.");
     for (my $i = 0; $retVal && $i <= $#relationList; $i++) {  
         my $relationName = $relationList[$i];  
         my $relationDefinition = $relationTable->{$relationName};  
         # Get the relation's fields. For each field we will collect a value in the corresponding  
         # position of the @valueList array. If one of the fields is missing, we will add it to the  
         # @missing list.  
         my @fieldList = @{$relationDefinition->{Fields}};  
         my @fieldNameList = ();  
         my @valueList = ();  
         my @missing = ();  
         my $recordCount = 1;  
         for my $fieldDescriptor (@fieldList) {  
             # Get the field name and save it. Note we need to fix it up so the hyphens  
             # are converted to underscores.  
             my $fieldName = $fieldDescriptor->{name};  
             push @fieldNameList, _FixName($fieldName);  
             # Look for the named field in the incoming structure. Note that we are looking  
             # for the real field name, not the fixed-up one!  
             if (exists $fieldHash->{$fieldName}) {  
                 # Here we found the field. Stash it in the value list.  
                 my $value = $fieldHash->{$fieldName};  
                 push @valueList, $value;  
                 # If the value is a list, we may need to increment the record count.  
                 if (ref $value eq "ARRAY") {  
                     my $thisCount = @{$value};  
                     if ($recordCount == 1) {  
                         # Here we have our first list, so we save its count.  
                         $recordCount = $thisCount;  
                     } elsif ($recordCount != $thisCount) {  
                         # Here we have a second list, so its length has to match the  
                         # previous lists.  
                         Trace("Field $value in new $newObjectType object has an invalid list length $thisCount. Expected $recordCount.") if T(0);  
                         $retVal = 0;  
                     }  
                 }  
             } else {  
                 # Here the field is not present. Flag it as missing.  
                 push @missing, $fieldName;  
             }  
         }  
         # If we are the primary relation, add the new-record flag.  
         if ($relationName eq $newObjectType) {  
             push @valueList, 1;  
             push @fieldNameList, "new_record";  
3784          }          }
         # Only proceed if there are no missing fields.  
         if (@missing > 0) {  
             Trace("Relation $relationName for $newObjectType skipped due to missing fields: " .  
                 join(' ', @missing)) if T(1);  
         } else {  
             # Build the INSERT statement.  
             my $statement = "INSERT INTO $relationName (" . join (', ', @fieldNameList) .  
                 ") VALUES (";  
             # Create a marker list of the proper size and put it in the statement.  
             my @markers = ();  
             while (@markers < @fieldNameList) { push @markers, '?'; }  
             $statement .= join(', ', @markers) . ")";  
             # We have the insert statement, so prepare it.  
             my $sth = $dbh->prepare_command($statement);  
             Trace("Insert statement prepared: $statement") if T(3);  
             # Now we loop through the values. If a value is scalar, we use it unmodified. If it's  
             # a list, we use the current element. The values are stored in the @parameterList array.  
             my $done = 0;  
             for (my $i = 0; $i < $recordCount; $i++) {  
                 # Clear the parameter list array.  
                 my @parameterList = ();  
                 # Loop through the values.  
                 for my $value (@valueList) {  
                     # Check to see if this is a scalar value.  
                     if (ref $value eq "ARRAY") {  
                         # Here we have a list value. Pull the current entry.  
                         push @parameterList, $value->[$i];  
3785                      } else {                      } else {
3786                          # Here we have a scalar value. Use it unmodified.          # Here we have a name. We need to find it in the list.
3787                          push @parameterList, $value;          for (my $i = 0; $i <= $#headers && ! defined($retVal); $i++) {
3788                if ($headers[$i] eq $columnIdentifier) {
3789                    $retVal = $i;
3790                      }                      }
3791                  }                  }
3792                  # Execute the INSERT statement with the specified parameter list.          if (! defined($retVal)) {
3793                  $retVal = $sth->execute(@parameterList);              Confess("Invalid column identifier \"$columnIdentifier\": value not found.");
                 if (!$retVal) {  
                     my $errorString = $sth->errstr();  
                     Trace("Insert error: $errorString.") if T(0);  
3794                  }                  }
3795              }              }
3796          }      # Return the result.
     }  
     # Return the success indicator.  
3797      return $retVal;      return $retVal;
3798  }  }
3799    
3800  =head3 LoadTable  =head3 ParseColumns
3801    
3802  C<< my %results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>      my @columns = ERDB::ParseColumns($line);
3803    
3804  Load data from a tab-delimited file into a specified table, optionally re-creating the table  Convert the specified data line to a list of columns.
 first.  
3805    
3806  =over 4  =over 4
3807    
3808  =item fileName  =item line
3809    
3810  Name of the file from which the table data should be loaded.  A data mining input, consisting of a tab-separated list of columns terminated by a
3811    new-line.
3812    
3813  =item relationName  =item RETURN
3814    
3815  Name of the relation to be loaded. This is the same as the table name.  Returns a list consisting of the column values.
3816    
3817  =item truncateFlag  =back
3818    
3819  TRUE if the table should be dropped and re-created, else FALSE  =cut
3820    
3821    sub ParseColumns {
3822        # Get the parameters.
3823        my ($line) = @_;
3824        # Chop off the line-end.
3825        chomp $line;
3826        # Split it into a list.
3827        my @retVal = split(/\t/, $line);
3828        # Return the result.
3829        return @retVal;
3830    }
3831    
3832    =head2 Virtual Methods
3833    
3834    =head3 _CreatePPOIndex
3835    
3836        my $index = ERDB::_CreatePPOIndex($indexObject);
3837    
3838    Convert the XML for an ERDB index to the XML structure for a PPO
3839    index.
3840    
3841    =over 4
3842    
3843    ERDB XML structure for an index.
3844    
3845  =item RETURN  =item RETURN
3846    
3847  Returns a statistical object containing a list of the error messages.  PPO XML structure for the same index.
3848    
3849  =back  =back
3850    
3851  =cut  =cut
3852  sub LoadTable {  
3853    sub _CreatePPOIndex {
3854      # Get the parameters.      # Get the parameters.
3855      my ($self, $fileName, $relationName, $truncateFlag) = @_;      my ($indexObject) = @_;
3856      # Create the statistical return object.      # The incoming index contains a list of the index fields in the IndexFields
3857      my $retVal = _GetLoadStats();      # member. We loop through it to create the index tags.
3858      # Trace the fact of the load.      my @fields = map { { label => _FixName($_->{name}) } } @{$indexObject->{IndexFields}};
3859      Trace("Loading table $relationName from $fileName") if T(2);      # Wrap the fields in attribute tags.
3860      # Get the database handle.      my $retVal = { attribute => \@fields };
3861      my $dbh = $self->{_dbh};      # Return the result.
     # Get the input file size.  
     my $fileSize = -s $fileName;  
     # Get the relation data.  
     my $relation = $self->_FindRelation($relationName);  
     # Check the truncation flag.  
     if ($truncateFlag) {  
         Trace("Creating table $relationName") if T(2);  
         # Compute the row count estimate. We take the size of the load file,  
         # divide it by the estimated row size, and then multiply by 1.5 to  
         # leave extra room. We postulate a minimum row count of 1000 to  
         # prevent problems with incoming empty load files.  
         my $rowSize = $self->EstimateRowSize($relationName);  
         my $estimate = FIG::max($fileSize * 1.5 / $rowSize, 1000);  
         # Re-create the table without its index.  
         $self->CreateTable($relationName, 0, $estimate);  
         # If this is a pre-index DBMS, create the index here.  
         if ($dbh->{_preIndex}) {  
             eval {  
                 $self->CreateIndex($relationName);  
             };  
             if ($@) {  
                 $retVal->AddMessage($@);  
             }  
         }  
     }  
     # Load the table.  
     my $rv;  
     eval {  
         $rv = $dbh->load_table(file => $fileName, tbl => $relationName);  
     };  
     if (!defined $rv) {  
         $retVal->AddMessage($@) if ($@);  
         $retVal->AddMessage("Table load failed for $relationName using $fileName.");  
         Trace("Table load failed for $relationName.") if T(1);  
     } else {  
         # Here we successfully loaded the table.  
         $retVal->Add("tables");  
         my $size = -s $fileName;  
         Trace("$size bytes loaded into $relationName.") if T(2);  
         # If we're rebuilding, we need to create the table indexes.  
         if ($truncateFlag && ! $dbh->{_preIndex}) {  
             eval {  
                 $self->CreateIndex($relationName);  
             };  
             if ($@) {  
                 $retVal->AddMessage($@);  
             }  
         }  
     }  
     # Analyze the table to improve performance.  
     $dbh->vacuum_it($relationName);  
     # Return the statistics.  
3862      return $retVal;      return $retVal;
3863  }  }
3864    
3865  =head3 GenerateEntity  =head3 _CreatePPOField
3866    
3867  C<< my $fieldHash = $erdb->GenerateEntity($id, $type, \%values); >>      my $fieldXML = ERDB::_CreatePPOField($fieldName, $fieldObject);
3868    
3869  Generate the data for a new entity instance. This method creates a field hash suitable for  Convert the ERDB XML structure for a field to a PPO scalar XML structure.
 passing as a parameter to L</InsertObject>. The ID is specified by the callr, but the rest  
 of the fields are generated using information in the database schema.  
   
 Each data type has a default algorithm for generating random test data. This can be overridden  
 by including a B<DataGen> element in the field. If this happens, the content of the element is  
 executed as a PERL program in the context of this module. The element may make use of a C<$this>  
 variable which contains the field hash as it has been built up to the current point. If any  
 fields are dependent on other fields, the C<pass> attribute can be used to control the order  
 in which the fields are generated. A field with a high data pass number will be generated after  
 a field with a lower one. If any external values are needed, they should be passed in via the  
 optional third parameter, which will be available to the data generation script under the name  
 C<$value>. Several useful utility methods are provided for generating random values, including  
 L</IntGen>, L</StringGen>, L</FloatGen>, and L</DateGen>. Note that dates are stored and generated  
 in the form of a timestamp number rather than a string.  
3870    
3871  =over 4  =over 4
3872    
3873  =item id  =item fieldName
3874    
3875  ID to assign to the new entity.  Name of the scalar field.
3876    
3877  =item type  =item fieldObject
3878    
3879  Type name for the new entity.  ERDB XML structure describing the field.
3880    
3881  =item values  =item RETURN
3882    
3883  Hash containing additional values that might be needed by the data generation methods (optional).  Returns a PPO XML structure for the same field.
3884    
3885  =back  =back
3886    
3887  =cut  =cut
3888    
3889  sub GenerateEntity {  sub _CreatePPOField {
3890      # Get the parameters.      # Get the parameters.
3891      my ($self, $id, $type, $values) = @_;      my ($fieldName, $fieldObject) = @_;
3892      # Create the return hash.      # Get the field type.
3893      my $this = { id => $id };      my $type = $TypeTable{$fieldObject->{type}}->{sqlType};
3894      # Get the metadata structure.      # Fix up the field name.
3895      my $metadata = $self->{_metaData};      $fieldName = _FixName($fieldName);
3896      # Get this entity's list of fields.      # Build the scalar tag.
3897      if (!exists $metadata->{Entities}->{$type}) {      my $retVal = { label => $fieldName, type => $type };
3898          Confess("Unrecognized entity type $type in GenerateEntity.");      # Return the result.
3899      } else {      return $retVal;
         my $entity = $metadata->{Entities}->{$type};  
         my $fields = $entity->{Fields};  
         # Generate data from the fields.  
         _GenerateFields($this, $fields, $type, $values);  
     }  
     # Return the hash created.  
     return $this;  
3900  }  }
3901    
3902  =head3 GetEntity  =head3 CleanKeywords
3903    
3904  C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>      my $cleanedString = $erdb->CleanKeywords($searchExpression);
3905