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

Diff of /Sprout/ERDB.pm

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

revision 1.11, Thu Jun 23 21:24:49 2005 UTC revision 1.90, Fri Apr 27 22:19:49 2007 UTC
# Line 2  Line 2 
2    
3      use strict;      use strict;
4      use Tracer;      use Tracer;
5      use DBKernel;      use DBrtns;
6      use Data::Dumper;      use Data::Dumper;
7      use XML::Simple;      use XML::Simple;
8      use DBQuery;      use DBQuery;
9      use DBObject;      use ERDBObject;
10      use Stats;      use Stats;
11      use Time::HiRes qw(gettimeofday);      use Time::HiRes qw(gettimeofday);
12        use Digest::MD5 qw(md5_base64);
13        use CGI;
14    
15  =head1 Entity-Relationship Database Package  =head1 Entity-Relationship Database Package
16    
# Line 57  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 89  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 108  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 124  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 169  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 188  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 221  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 265  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 299  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.  # record sizes. "sort" is the key modifier for the sort command, "notes" is a type description,
342  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            dataGen => "StringGen('A')" },  # and "indexMod", if non-zero, is the number of characters to use when the field is specified in an
343                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           dataGen => "IntGen(0, 99999999)" },  # index
344                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          dataGen => "StringGen(IntGen(10,250))" },  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",
345                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   dataGen => "StringGen(IntGen(80,1000))" },                                 indexMod =>   0, notes => "single ASCII character"},
346                    date =>    { sqlType => 'BIGINT',             maxLen => 80,           dataGen => "DateGen(-7, 7, IntGen(0,1400))" },                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n",
347                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           dataGen => "FloatGen(0.0, 100.0)" },                                 indexMod =>   0, notes => "signed 32-bit integer"},
348                    boolean => { sqlType => 'SMALLINT',           maxLen => 1,            dataGen => "IntGen(0, 1)" },                    counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n",
349                                   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,           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,           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,          dataGen => "StringGen(IntGen(10,160))" },                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",
374                                   indexMod =>   0, notes => "character string, 0 to 160 characters"},
375                  );                  );
376    
377  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 322  Line 380 
380                     'MM' => 'many-to-many'                     'MM' => 'many-to-many'
381                   );                   );
382    
383  # Table for interpreting string patterns.  # Options for XML input and output.
384    
385    my %XmlOptions = (GroupTags =>  { Relationships => 'Relationship',
386                                      Entities => 'Entity',
387                                      Fields => 'Field',
388                                      Indexes => 'Index',
389                                      IndexFields => 'IndexField'
390                                    },
391                      KeyAttr =>    { Relationship => 'name',
392                                      Entity => 'name',
393                                      Field => 'name'
394                                    },
395                      SuppressEmpty => 1,
396                     );
397    
398  my %PictureTable = ( 'A' => "abcdefghijklmnopqrstuvwxyz",  my %XmlInOpts  = (
399                       '9' => "0123456789",                    ForceArray => ['Field', 'Index', 'IndexField', 'Relationship', 'Entity'],
400                       'X' => "abcdefghijklmnopqrstuvwxyz0123456789",                    ForceContent => 1,
401                       'V' => "aeiou",                    NormalizeSpace => 2,
                      'K' => "bcdfghjklmnoprstvwxyz"  
402                     );                     );
403    my %XmlOutOpts = (
404                      RootName => 'Database',
405                      XMLDecl => 1,
406                     );
407    
408    
409  =head2 Public Methods  =head2 Public Methods
410    
# Line 369  Line 444 
444    
445  =head3 ShowMetaData  =head3 ShowMetaData
446    
447  C<< $database->ShowMetaData($fileName); >>  C<< $erdb->ShowMetaData($fileName); >>
448    
449  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
450  the data to be loaded into the relations.  the data to be loaded into the relations.
# Line 400  Line 475 
475      # Write the HTML heading stuff.      # Write the HTML heading stuff.
476      print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";      print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";
477      print HTMLOUT "</head>\n<body>\n";      print HTMLOUT "</head>\n<body>\n";
478        # Write the documentation.
479        print HTMLOUT $self->DisplayMetaData();
480        # Close the document.
481        print HTMLOUT "</body>\n</html>\n";
482        # Close the file.
483        close HTMLOUT;
484    }
485    
486    =head3 DisplayMetaData
487    
488    C<< my $html = $erdb->DisplayMetaData(); >>
489    
490    Return an HTML description of the database. This description can be used to help users create
491    the data to be loaded into the relations and form queries. The output is raw includable HTML
492    without any HEAD or BODY tags.
493    
494    =over 4
495    
496    =item filename
497    
498    The name of the output file.
499    
500    =back
501    
502    =cut
503    
504    sub DisplayMetaData {
505        # Get the parameters.
506        my ($self) = @_;
507        # Get the metadata and the title string.
508        my $metadata = $self->{_metaData};
509        # Get the title string.
510        my $title = $metadata->{Title};
511        # Get the entity and relationship lists.
512        my $entityList = $metadata->{Entities};
513        my $relationshipList = $metadata->{Relationships};
514        # Declare the return variable.
515        my $retVal = "";
516        # Open the output file.
517        Trace("Building MetaData table of contents.") if T(4);
518      # Here we do the table of contents. It starts as an unordered list of section names. Each      # Here we do the table of contents. It starts as an unordered list of section names. Each
519      # section contains an ordered list of entity or relationship subsections.      # section contains an ordered list of entity or relationship subsections.
520      print HTMLOUT "<ul>\n<li><a href=\"#EntitiesSection\">Entities</a>\n<ol>\n";      $retVal .= "<ul>\n<li><a href=\"#EntitiesSection\">Entities</a>\n<ol>\n";
521      # Loop through the Entities, displaying a list item for each.      # Loop through the Entities, displaying a list item for each.
522      foreach my $key (sort keys %{$entityList}) {      foreach my $key (sort keys %{$entityList}) {
523          # Display this item.          # Display this item.
524          print HTMLOUT "<li><a href=\"#$key\">$key</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$key</a></li>\n";
525      }      }
526      # Close off the entity section and start the relationship section.      # Close off the entity section and start the relationship section.
527      print HTMLOUT "</ol></li>\n<li><a href=\"#RelationshipsSection\">Relationships</a>\n<ol>\n";      $retVal .= "</ol></li>\n<li><a href=\"#RelationshipsSection\">Relationships</a>\n<ol>\n";
528      # Loop through the Relationships.      # Loop through the Relationships.
529      foreach my $key (sort keys %{$relationshipList}) {      foreach my $key (sort keys %{$relationshipList}) {
530          # Display this item.          # Display this item.
531          my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});          my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});
532          print HTMLOUT "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";
533      }      }
534      # Close off the relationship section and list the join table section.      # Close off the relationship section and list the join table section.
535      print HTMLOUT "</ol></li>\n<li><a href=\"#JoinTable\">Join Table</a></li>\n";      $retVal .= "</ol></li>\n<li><a href=\"#JoinTable\">Join Table</a></li>\n";
536      # Close off the table of contents itself.      # Close off the table of contents itself.
537      print HTMLOUT "</ul>\n";      $retVal .=  "</ul>\n";
538      # Now we start with the actual data. Denote we're starting the entity section.      # Now we start with the actual data. Denote we're starting the entity section.
539      print HTMLOUT "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";      $retVal .= "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";
540      # Loop through the entities.      # Loop through the entities.
541      for my $key (sort keys %{$entityList}) {      for my $key (sort keys %{$entityList}) {
542          Trace("Building MetaData entry for $key entity.") if T(4);          Trace("Building MetaData entry for $key entity.") if T(4);
543          # Create the entity header. It contains a bookmark and the entity name.          # Create the entity header. It contains a bookmark and the entity name.
544          print HTMLOUT "<a name=\"$key\"></a><h3>$key</h3>\n";          $retVal .= "<a name=\"$key\"></a><h3>$key</h3>\n";
545          # Get the entity data.          # Get the entity data.
546          my $entityData = $entityList->{$key};          my $entityData = $entityList->{$key};
547          # If there's descriptive text, display it.          # If there's descriptive text, display it.
548          if (my $notes = $entityData->{Notes}) {          if (my $notes = $entityData->{Notes}) {
549              print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
550          }          }
551          # Now we want a list of the entity's relationships. First, we set up the relationship subsection.          # See if we need a list of the entity's relationships.
552          print HTMLOUT "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          my $relCount = keys %{$relationshipList};
553            if ($relCount > 0) {
554                # First, we set up the relationship subsection.
555                $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
556          # Loop through the relationships.          # Loop through the relationships.
557          for my $relationship (sort keys %{$relationshipList}) {          for my $relationship (sort keys %{$relationshipList}) {
558              # Get the relationship data.              # Get the relationship data.
# Line 444  Line 562 
562                  # Get the relationship sentence and append the arity.                  # Get the relationship sentence and append the arity.
563                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);
564                  # Display the relationship data.                  # Display the relationship data.
565                  print HTMLOUT "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";                      $retVal .= "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";
566              }              }
567          }          }
568          # Close off the relationship list.          # Close off the relationship list.
569          print HTMLOUT "</ul>\n";              $retVal .= "</ul>\n";
570            }
571          # Get the entity's relations.          # Get the entity's relations.
572          my $relationList = $entityData->{Relations};          my $relationList = $entityData->{Relations};
573          # Create a header for the relation subsection.          # Create a header for the relation subsection.
574          print HTMLOUT "<h4>Relations for <b>$key</b></h4>\n";          $retVal .= "<h4>Relations for <b>$key</b></h4>\n";
575          # Loop through the relations, displaying them.          # Loop through the relations, displaying them.
576          for my $relation (sort keys %{$relationList}) {          for my $relation (sort keys %{$relationList}) {
577              my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});              my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});
578              print HTMLOUT $htmlString;              $retVal .= $htmlString;
579          }          }
580      }      }
581      # Denote we're starting the relationship section.      # Denote we're starting the relationship section.
582      print HTMLOUT "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";      $retVal .= "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";
583      # Loop through the relationships.      # Loop through the relationships.
584      for my $key (sort keys %{$relationshipList}) {      for my $key (sort keys %{$relationshipList}) {
585          Trace("Building MetaData entry for $key relationship.") if T(4);          Trace("Building MetaData entry for $key relationship.") if T(4);
# Line 468  Line 587 
587          my $relationshipStructure = $relationshipList->{$key};          my $relationshipStructure = $relationshipList->{$key};
588          # Create the relationship header.          # Create the relationship header.
589          my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);          my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);
590          print HTMLOUT "<h3><a name=\"$key\"></a>$headerText</h3>\n";          $retVal .= "<h3><a name=\"$key\"></a>$headerText</h3>\n";
591          # Get the entity names.          # Get the entity names.
592          my $fromEntity = $relationshipStructure->{from};          my $fromEntity = $relationshipStructure->{from};
593          my $toEntity = $relationshipStructure->{to};          my $toEntity = $relationshipStructure->{to};
# Line 478  Line 597 
597          # since both sentences will say the same thing.          # since both sentences will say the same thing.
598          my $arity = $relationshipStructure->{arity};          my $arity = $relationshipStructure->{arity};
599          if ($arity eq "11") {          if ($arity eq "11") {
600              print HTMLOUT "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";
601          } else {          } else {
602              print HTMLOUT "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";
603              if ($arity eq "MM" && $fromEntity ne $toEntity) {              if ($arity eq "MM" && $fromEntity ne $toEntity) {
604                  print HTMLOUT "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";                  $retVal .= "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";
605              }              }
606          }          }
607          print HTMLOUT "</p>\n";          $retVal .= "</p>\n";
608          # If there are notes on this relationship, display them.          # If there are notes on this relationship, display them.
609          if (my $notes = $relationshipStructure->{Notes}) {          if (my $notes = $relationshipStructure->{Notes}) {
610              print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
611          }          }
612          # Generate the relationship's relation table.          # Generate the relationship's relation table.
613          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
614          print HTMLOUT $htmlString;          $retVal .= $htmlString;
615      }      }
616      Trace("Building MetaData join table.") if T(4);      Trace("Building MetaData join table.") if T(4);
617      # Denote we're starting the join table.      # Denote we're starting the join table.
618      print HTMLOUT "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";      $retVal .= "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";
619      # Create a table header.      # Create a table header.
620      print HTMLOUT _OpenTable("Join Table", "Source", "Target", "Join Condition");      $retVal .= _OpenTable("Join Table", "Source", "Target", "Join Condition");
621      # Loop through the joins.      # Loop through the joins.
622      my $joinTable = $metadata->{Joins};      my $joinTable = $metadata->{Joins};
623      my @joinKeys = keys %{$joinTable};      my @joinKeys = keys %{$joinTable};
# Line 506  Line 625 
625          # Separate out the source, the target, and the join clause.          # Separate out the source, the target, and the join clause.
626          $joinKey =~ m!^([^/]+)/(.+)$!;          $joinKey =~ m!^([^/]+)/(.+)$!;
627          my ($sourceRelation, $targetRelation) = ($1, $2);          my ($sourceRelation, $targetRelation) = ($1, $2);
628          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);
629          my $source = $self->ComputeObjectSentence($sourceRelation);          my $source = $self->ComputeObjectSentence($sourceRelation);
630          my $target = $self->ComputeObjectSentence($targetRelation);          my $target = $self->ComputeObjectSentence($targetRelation);
631          my $clause = $joinTable->{$joinKey};          my $clause = $joinTable->{$joinKey};
632          # Display them in a table row.          # Display them in a table row.
633          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";
634      }      }
635      # Close the table.      # Close the table.
636      print HTMLOUT _CloseTable();      $retVal .= _CloseTable();
637      # Close the document.      Trace("Built MetaData HTML.") if T(3);
638      print HTMLOUT "</body>\n</html>\n";      # Return the HTML.
639      # Close the file.      return $retVal;
     close HTMLOUT;  
     Trace("Built MetaData web page.") if T(3);  
640  }  }
641    
642  =head3 DumpMetaData  =head3 DumpMetaData
643    
644  C<< $database->DumpMetaData(); >>  C<< $erdb->DumpMetaData(); >>
645    
646  Return a dump of the metadata structure.  Return a dump of the metadata structure.
647    
# Line 537  Line 654 
654      return Data::Dumper::Dumper($self->{_metaData});      return Data::Dumper::Dumper($self->{_metaData});
655  }  }
656    
657    =head3 CreatePPO
658    
659    C<< ERDB::CreatePPO($erdbXMLFile, $ppoXMLFile); >>
660    
661    Create a PPO XML file from an ERDB data definition XML file. At the
662    current time, the PPO XML file can be used to create a database with
663    similar functionality. Eventually, the PPO will be able to use the
664    created XML to access the live ERDB database.
665    
666    =over 4
667    
668    =item erdbXMLFile
669    
670    Name of the XML data definition file for the ERDB database. This
671    file must exist.
672    
673    =item ppoXMLFile
674    
675    Output file for the PPO XML definition. If this file exists, it
676    will be overwritten.
677    
678    =back
679    
680    =cut
681    
682    sub CreatePPO {
683        # Get the parameters.
684        my ($erdbXMLFile, $ppoXMLFile) = @_;
685        # First, we want to slurp in the ERDB XML file in its raw form.
686        my $xml = ReadMetaXML($erdbXMLFile);
687        # Create a variable to hold all of the objects in the PPO project.
688        my @objects = ();
689        # Get the relationship hash.
690        my $relationships = $xml->{Relationships};
691        # Loop through the entities.
692        my $entities = $xml->{Entities};
693        for my $entityName (keys %{$entities}) {
694            # Get the entity's data structures.
695            my $entityObject = $entities->{$entityName};
696            # We put the object's fields in here, according to their type.
697            my (@object_refs, @scalars, @indexes, @arrays);
698            # Create the ID field for the entity. We get the key type from the
699            # entity object and compute the corresponding SQL type.
700            my $type = $TypeTable{$entityObject->{keyType}}->{sqlType};
701            push @scalars, { label => 'id', type => $type };
702            # Loop through the entity fields.
703            for my $fieldName ( keys %{$entityObject->{Fields}} ) {
704                # Get the field object.
705                my $fieldObject = $entityObject->{Fields}->{$fieldName};
706                # Convert it to a scalar tag.
707                my $scalar = _CreatePPOField($fieldName, $fieldObject);
708                # If we have a relation, this field is stored in an array.
709                # otherwise, it is a scalar. The array tag has scalars
710                # stored as an XML array. In ERDB, there is only ever one,
711                # but PPO can have more.
712                my $relation = $fieldObject->{relation};
713                if ($relation) {
714                    push @arrays, { scalar => [$scalar] };
715                } else {
716                    push @scalars, $scalar;
717                }
718            }
719            # Loop through the relationships. If this entity is the to-entity
720            # on a relationship of 1M arity, then it is implemented as a PPO
721            # object reference.
722            for my $relationshipName (keys %{$relationships}) {
723                # Get the relationship data.
724                my $relationshipData = $relationships->{$relationshipName};
725                # If we have a from for this entity and an arity of 1M, we
726                # have an object reference.
727                if ($relationshipData->{to} eq $entityName &&
728                    $relationshipData->{arity} eq '1M') {
729                    # Build the object reference tag.
730                    push @object_refs, { label => $relationshipName,
731                                         type => $relationshipData->{from} };
732                }
733            }
734            # Create the indexes.
735            my $indexList = $entityObject->{Indexes};
736            push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
737            # Build the object XML tree.
738            my $object = { label => $entityName,
739                           object_ref => \@object_refs,
740                           scalar => \@scalars,
741                           index => \@indexes,
742                           array => \@arrays
743                          };
744            # Push the object onto the objects list.
745            push @objects, $object;
746        }
747        # Loop through the relationships, searching for MMs. The 1Ms were
748        # already handled by the entity search above.
749        for my $relationshipName (keys %{$relationships}) {
750            # Get this relationship's object.
751            my $relationshipObject = $relationships->{$relationshipName};
752            # Only proceed if it's many-to-many.
753            if ($relationshipObject->{arity} eq 'MM') {
754                # Create the tag lists for the relationship object.
755                my (@object_refs, @scalars, @indexes);
756                # The relationship will be created as an object with object
757                # references for its links to the participating entities.
758                my %links = ( from_link => $relationshipObject->{from},
759                              to_link => $relationshipObject->{to} );
760                for my $link (keys %links) {
761                    # Create an object_ref tag for this piece of the
762                    # relationship (from or to).
763                    my $object_ref = { label => $link,
764                                       type => $links{$link} };
765                    push @object_refs, $object_ref;
766                }
767                # Loop through the intersection data fields, creating scalar tags.
768                # There are no fancy array tags in a relationship.
769                for my $fieldName (keys %{$relationshipObject->{Fields}}) {
770                    my $fieldObject = $relationshipObject->{Fields}->{$fieldName};
771                    push @scalars, _CreatePPOField($fieldName, $fieldObject);
772                }
773                # Finally, the indexes: currently we cannot support the to-index and
774                # from-index in PPO, so we just process the alternate indexes.
775                my $indexList = $relationshipObject->{Indexes};
776                push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
777                # Wrap up all the stuff about this relationship.
778                my $object = { label => $relationshipName,
779                               scalar => \@scalars,
780                               object_ref => \@object_refs,
781                               index => \@indexes
782                             };
783                # Push it into the object list.
784                push @objects, $object;
785            }
786        }
787        # Compute a title.
788        my $title;
789        if ($erdbXMLFile =~ /(\/|^)([^\/]+)DBD\.xml/) {
790            # Here we have a standard file name we can use for a title.
791            $title = $2;
792        } else {
793            # Here the file name is non-standard, so we carve up the
794            # database title.
795            $title = $xml->{Title}->{content};
796            $title =~ s/\s\.,//g;
797        }
798        # Wrap up the XML as a project.
799        my $ppoXML = { project => { label => $title,
800                                    object => \@objects }};
801        # Write out the results.
802        my $ppoString = XML::Simple::XMLout($ppoXML,
803                                            AttrIndent => 1,
804                                            KeepRoot => 1);
805        Tracer::PutFile($ppoXMLFile, [ $ppoString ]);
806    }
807    
808    =head3 FindIndexForEntity
809    
810    C<< my $indexFound = ERDB::FindIndexForEntity($xml, $entityName, $attributeName); >>
811    
812    This method locates the entry in an entity's index list that begins with the
813    specified attribute name. If the entity has no index list, one will be
814    created. This method works on raw XML, not a live ERDB object.
815    
816    =over 4
817    
818    =item xml
819    
820    The raw XML structure defining the database.
821    
822    =item entityName
823    
824    The name of the relevant entity.
825    
826    =item attributeName
827    
828    The name of the attribute relevant to the search.
829    
830    =item RETURN
831    
832    The numerical index in the index list of the index entry for the specified entity and
833    attribute, or C<undef> if no such index exists.
834    
835    =back
836    
837    =cut
838    
839    sub FindIndexForEntity {
840        # Get the parameters.
841        my ($xml, $entityName, $attributeName) = @_;
842        # Declare the return variable.
843        my $retVal;
844        # Get the named entity.
845        my $entityData = $xml->{Entities}->{$entityName};
846        if (! $entityData) {
847            Confess("Entity $entityName not found in DBD structure.");
848        } else {
849            # Insure it has an index list.
850            if (! exists $entityData->{Indexes}) {
851                $entityData->{Indexes} = [];
852            } else {
853                # Search for the desired index.
854                my $indexList = $entityData->{Indexes};
855                my $n = scalar @{$indexList};
856                Trace("Searching $n indexes in index list for $entityName.") if T(2);
857                # We use an indexed FOR here because we're returning an
858                # index number instead of an object. We do THAT so we can
859                # delete the index from the list if needed.
860                for (my $i = 0; $i < $n && !defined($retVal); $i++) {
861                    my $index = $indexList->[$i];
862                    my $fields = $index->{IndexFields};
863                    # Technically this IF should be safe (that is, we are guaranteed
864                    # the existence of a "$fields->[0]"), because when we load the XML
865                    # we have SuppressEmpty specified.
866                    if ($fields->[0]->{name} eq $attributeName) {
867                        $retVal = $i;
868                    }
869                }
870            }
871        }
872        Trace("Index for $attributeName of $entityName found at position $retVal.") if defined($retVal) && T(3);
873        Trace("Index for $attributeName not found in $entityName.") if !defined($retVal) && T(3);
874        # Return the result.
875        return $retVal;
876    }
877    
878  =head3 CreateTables  =head3 CreateTables
879    
880  C<< $datanase->CreateTables(); >>  C<< $erdb->CreateTables(); >>
881    
882  This method creates the tables for the database from the metadata structure loaded by the  This method creates the tables for the database from the metadata structure loaded by the
883  constructor. It is expected this function will only be used on rare occasions, when the  constructor. It is expected this function will only be used on rare occasions, when the
# Line 551  Line 889 
889  sub CreateTables {  sub CreateTables {
890      # Get the parameters.      # Get the parameters.
891      my ($self) = @_;      my ($self) = @_;
892      my $metadata = $self->{_metaData};      # Get the relation names.
893      my $dbh = $self->{_dbh};      my @relNames = $self->GetTableNames();
894      # Loop through the entities.      # Loop through the relations.
895      my $entityHash = $metadata->{Entities};      for my $relationName (@relNames) {
     for my $entityName (keys %{$entityHash}) {  
         my $entityData = $entityHash->{$entityName};  
         # Tell the user what we're doing.  
         Trace("Creating relations for entity $entityName.") if T(1);  
         # Loop through the entity's relations.  
         for my $relationName (keys %{$entityData->{Relations}}) {  
896              # Create a table for this relation.              # Create a table for this relation.
897              $self->CreateTable($relationName);          $self->CreateTable($relationName, 1);
898              Trace("Relation $relationName created.") if T(1);          Trace("Relation $relationName created.") if T(2);
         }  
     }  
     # Loop through the relationships.  
     my $relationshipTable = $metadata->{Relationships};  
     for my $relationshipName (keys %{$metadata->{Relationships}}) {  
         # Create a table for this relationship.  
         Trace("Creating relationship $relationshipName.") if T(1);  
         $self->CreateTable($relationshipName);  
899      }      }
900  }  }
901    
902  =head3 CreateTable  =head3 CreateTable
903    
904  C<< $database->CreateTable($tableName, $indexFlag); >>  C<< $erdb->CreateTable($tableName, $indexFlag, $estimatedRows); >>
905    
906  Create the table for a relation and optionally create its indexes.  Create the table for a relation and optionally create its indexes.
907    
# Line 587  Line 911 
911    
912  Name of the relation (which will also be the table name).  Name of the relation (which will also be the table name).
913    
914  =item $indexFlag  =item indexFlag
915    
916  TRUE if the indexes for the relation should be created, else FALSE. If FALSE,  TRUE if the indexes for the relation should be created, else FALSE. If FALSE,
917  L</CreateIndexes> must be called later to bring the indexes into existence.  L</CreateIndexes> must be called later to bring the indexes into existence.
918    
919    =item estimatedRows (optional)
920    
921    If specified, the estimated maximum number of rows for the relation. This
922    information allows the creation of tables using storage engines that are
923    faster but require size estimates, such as MyISAM.
924    
925  =back  =back
926    
927  =cut  =cut
928    
929  sub CreateTable {  sub CreateTable {
930      # Get the parameters.      # Get the parameters.
931      my ($self, $relationName, $indexFlag) = @_;      my ($self, $relationName, $indexFlag, $estimatedRows) = @_;
932      # Get the database handle.      # Get the database handle.
933      my $dbh = $self->{_dbh};      my $dbh = $self->{_dbh};
934      # Get the relation data and determine whether or not the relation is primary.      # Get the relation data and determine whether or not the relation is primary.
# Line 622  Line 952 
952      # Insure the table is not already there.      # Insure the table is not already there.
953      $dbh->drop_table(tbl => $relationName);      $dbh->drop_table(tbl => $relationName);
954      Trace("Table $relationName dropped.") if T(2);      Trace("Table $relationName dropped.") if T(2);
955        # If there are estimated rows, create an estimate so we can take advantage of
956        # faster DB technologies.
957        my $estimation = undef;
958        if ($estimatedRows) {
959            $estimation = [$self->EstimateRowSize($relationName), $estimatedRows];
960        }
961      # Create the table.      # Create the table.
962      Trace("Creating table $relationName: $fieldThing") if T(2);      Trace("Creating table $relationName: $fieldThing") if T(2);
963      $dbh->create_table(tbl => $relationName, flds => $fieldThing);      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);
964      Trace("Relation $relationName created in database.") if T(2);      Trace("Relation $relationName created in database.") if T(2);
965      # If we want to build the indexes, we do it here.      # If we want to build the indexes, we do it here. Note that the full-text search
966        # index will not be built until the table has been loaded.
967      if ($indexFlag) {      if ($indexFlag) {
968          $self->CreateIndex($relationName);          $self->CreateIndex($relationName);
969      }      }
970  }  }
971    
972    =head3 VerifyFields
973    
974    C<< my $count = $erdb->VerifyFields($relName, \@fieldList); >>
975    
976    Run through the list of proposed field values, insuring that all the character fields are
977    below the maximum length. If any fields are too long, they will be truncated in place.
978    
979    =over 4
980    
981    =item relName
982    
983    Name of the relation for which the specified fields are destined.
984    
985    =item fieldList
986    
987    Reference to a list, in order, of the fields to be put into the relation.
988    
989    =item RETURN
990    
991    Returns the number of fields truncated.
992    
993    =back
994    
995    =cut
996    
997    sub VerifyFields {
998        # Get the parameters.
999        my ($self, $relName, $fieldList) = @_;
1000        # Initialize the return value.
1001        my $retVal = 0;
1002        # Get the relation definition.
1003        my $relData = $self->_FindRelation($relName);
1004        # Get the list of field descriptors.
1005        my $fieldTypes = $relData->{Fields};
1006        my $fieldCount = scalar @{$fieldTypes};
1007        # Loop through the two lists.
1008        for (my $i = 0; $i < $fieldCount; $i++) {
1009            # Get the type of the current field.
1010            my $fieldType = $fieldTypes->[$i]->{type};
1011            # If it's a character field, verify the length.
1012            if ($fieldType =~ /string/) {
1013                my $maxLen = $TypeTable{$fieldType}->{maxLen};
1014                my $oldString = $fieldList->[$i];
1015                if (length($oldString) > $maxLen) {
1016                    # Here it's too big, so we truncate it.
1017                    Trace("Truncating field $i in relation $relName to $maxLen characters from \"$oldString\".") if T(1);
1018                    $fieldList->[$i] = substr $oldString, 0, $maxLen;
1019                    $retVal++;
1020                }
1021            }
1022        }
1023        # Return the truncation count.
1024        return $retVal;
1025    }
1026    
1027    =head3 DigestFields
1028    
1029    C<< $erdb->DigestFields($relName, $fieldList); >>
1030    
1031    Digest the strings in the field list that correspond to data type C<hash-string> in the
1032    specified relation.
1033    
1034    =over 4
1035    
1036    =item relName
1037    
1038    Name of the relation to which the fields belong.
1039    
1040    =item fieldList
1041    
1042    List of field contents to be loaded into the relation.
1043    
1044    =back
1045    
1046    =cut
1047    #: Return Type ;
1048    sub DigestFields {
1049        # Get the parameters.
1050        my ($self, $relName, $fieldList) = @_;
1051        # Get the relation definition.
1052        my $relData = $self->_FindRelation($relName);
1053        # Get the list of field descriptors.
1054        my $fieldTypes = $relData->{Fields};
1055        my $fieldCount = scalar @{$fieldTypes};
1056        # Loop through the two lists.
1057        for (my $i = 0; $i < $fieldCount; $i++) {
1058            # Get the type of the current field.
1059            my $fieldType = $fieldTypes->[$i]->{type};
1060            # If it's a hash string, digest it in place.
1061            if ($fieldType eq 'hash-string') {
1062                $fieldList->[$i] = $self->DigestKey($fieldList->[$i]);
1063            }
1064        }
1065    }
1066    
1067    =head3 DigestKey
1068    
1069    C<< my $digested = $erdb->DigestKey($keyValue); >>
1070    
1071    Return the digested value of a symbolic key. The digested value can then be plugged into a
1072    key-based search into a table with key-type hash-string.
1073    
1074    Currently the digesting process is independent of the database structure, but that may not
1075    always be the case, so this is an instance method instead of a static method.
1076    
1077    =over 4
1078    
1079    =item keyValue
1080    
1081    Key value to digest.
1082    
1083    =item RETURN
1084    
1085    Digested value of the key.
1086    
1087    =back
1088    
1089    =cut
1090    
1091    sub DigestKey {
1092        # Get the parameters.
1093        my ($self, $keyValue) = @_;
1094        # Compute the digest.
1095        my $retVal = md5_base64($keyValue);
1096        # Return the result.
1097        return $retVal;
1098    }
1099    
1100  =head3 CreateIndex  =head3 CreateIndex
1101    
1102  C<< $database->CreateIndex($relationName); >>  C<< $erdb->CreateIndex($relationName); >>
1103    
1104  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
1105  is the case in L</LoadTable>), it is best to create the indexes after the load. If that is  is the case in L</LoadTable>), it is sometimes best to create the indexes after the load.
1106  the case, then L</CreateTable> should be called with the index flag set to FALSE, and this  If that is the case, then L</CreateTable> should be called with the index flag set to
1107  method used after the load to create the indexes for the table.  FALSE, and this method used after the load to create the indexes for the table.
1108    
1109  =cut  =cut
1110    
# Line 655  Line 1120 
1120      for my $indexName (keys %{$indexHash}) {      for my $indexName (keys %{$indexHash}) {
1121          my $indexData = $indexHash->{$indexName};          my $indexData = $indexHash->{$indexName};
1122          # Get the index's field list.          # Get the index's field list.
1123          my @fieldList = _FixNames(@{$indexData->{IndexFields}});          my @rawFields = @{$indexData->{IndexFields}};
1124            # Get a hash of the relation's field types.
1125            my %types = map { $_->{name} => $_->{type} } @{$relationData->{Fields}};
1126            # We need to check for text fields so we can append a length limitation for them. To do
1127            # that, we need the relation's field list.
1128            my $relFields = $relationData->{Fields};
1129            for (my $i = 0; $i <= $#rawFields; $i++) {
1130                # Get the field type.
1131                my $field = $rawFields[$i];
1132                my $type = $types{$field};
1133                # Ask if it requires using prefix notation for the index.
1134                my $mod = $TypeTable{$type}->{indexMod};
1135                Trace("Field $field ($i) in $relationName has type $type and indexMod $mod.") if T(3);
1136                if ($mod) {
1137                    # Append the prefix length to the field name,
1138                    $rawFields[$i] .= "($mod)";
1139                }
1140            }
1141            my @fieldList = _FixNames(@rawFields);
1142          my $flds = join(', ', @fieldList);          my $flds = join(', ', @fieldList);
1143          # Get the index's uniqueness flag.          # Get the index's uniqueness flag.
1144          my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
1145          # Create the index.          # Create the index.
1146          $dbh->create_index(idx => $indexName, tbl => $relationName, flds => $flds, unique => $unique);          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
1147                                        flds => $flds, kind => $unique);
1148            if ($rv) {
1149          Trace("Index created: $indexName for $relationName ($flds)") if T(1);          Trace("Index created: $indexName for $relationName ($flds)") if T(1);
1150            } else {
1151                Confess("Error creating index $indexName for $relationName using ($flds): " . $dbh->error_message());
1152            }
1153      }      }
1154  }  }
1155    
1156  =head3 LoadTables  =head3 GetSecondaryFields
   
 C<< my $stats = $database->LoadTables($directoryName, $rebuild); >>  
1157    
1158  This method will load the database tables from a directory. The tables must already have been created  C<< 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.  
1159    
1160  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
1161  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
1162  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
1163    or to have multiple values.
1164    
1165  =over 4  =over 4
1166    
1167  =item directoryName  =item entityName
   
 Name of the directory containing the relation files to be loaded.  
   
 =item rebuild  
1168    
1169  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.  
1170    
1171  =item RETURN  =item RETURN
1172    
1173  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.
1174    
1175  =back  =back
1176    
1177  =cut  =cut
1178    
1179  sub LoadTables {  sub GetSecondaryFields {
1180      # Get the parameters.      # Get the parameters.
1181      my ($self, $directoryName, $rebuild) = @_;      my ($self, $entityName) = @_;
     # Start the timer.  
     my $startTime = gettimeofday;  
     # Clean any trailing slash from the directory name.  
     $directoryName =~ s!/\\$!!;  
1182      # Declare the return variable.      # Declare the return variable.
1183      my $retVal = Stats->new();      my %retVal = ();
1184      # Get the metadata structure.      # Look for the entity.
1185      my $metaData = $self->{_metaData};      my $table = $self->GetFieldTable($entityName);
1186      # Loop through the entities.      # Loop through the fields, pulling out the secondaries.
1187      for my $entity (values %{$metaData->{Entities}}) {      for my $field (sort keys %{$table}) {
1188          # Loop through the entity's relations.          if ($table->{$field}->{relation} ne $entityName) {
1189          for my $relationName (keys %{$entity->{Relations}}) {              # Here we have a secondary field.
1190              # Try to load this relation.              $retVal{$field} = $table->{$field}->{type};
             my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);  
             # Accumulate the statistics.  
             $retVal->Accumulate($result);  
         }  
1191      }      }
     # Loop through the relationships.  
     for my $relationshipName (keys %{$metaData->{Relationships}}) {  
         # Try to load this relationship's relation.  
         my $result = $self->_LoadRelation($directoryName, $relationshipName, $rebuild);  
         # Accumulate the statistics.  
         $retVal->Accumulate($result);  
1192      }      }
1193      # Add the duration of the load to the statistical object.      # Return the result.
1194      $retVal->Add('duration', gettimeofday - $startTime);      return %retVal;
     # Return the accumulated statistics.  
     return $retVal;  
1195  }  }
1196    
1197  =head3 GetTableNames  =head3 GetFieldRelationName
1198    
1199  C<< my @names = $database->GetTableNames; >>  C<< my $name = $erdb->GetFieldRelationName($objectName, $fieldName); >>
1200    
1201  Return a list of the relations required to implement this database.  Return the name of the relation containing a specified field.
1202    
1203  =cut  =over 4
1204    
1205  sub GetTableNames {  =item objectName
     # Get the parameters.  
     my ($self) = @_;  
     # Get the relation list from the metadata.  
     my $relationTable = $self->{_metaData}->{RelationTable};  
     # Return the relation names.  
     return keys %{$relationTable};  
 }  
1206    
1207  =head3 GetEntityTypes  Name of the entity or relationship containing the field.
1208    
1209  C<< my @names = $database->GetEntityTypes; >>  =item fieldName
1210    
1211    Name of the relevant field in that entity or relationship.
1212    
1213    =item RETURN
1214    
1215    Returns the name of the database relation containing the field, or C<undef> if
1216    the field does not exist.
1217    
1218    =back
1219    
1220    =cut
1221    
1222    sub GetFieldRelationName {
1223        # Get the parameters.
1224        my ($self, $objectName, $fieldName) = @_;
1225        # Declare the return variable.
1226        my $retVal;
1227        # Get the object field table.
1228        my $table = $self->GetFieldTable($objectName);
1229        # Only proceed if the field exists.
1230        if (exists $table->{$fieldName}) {
1231            # Determine the name of the relation that contains this field.
1232            $retVal = $table->{$fieldName}->{relation};
1233        }
1234        # Return the result.
1235        return $retVal;
1236    }
1237    
1238    =head3 DeleteValue
1239    
1240    C<< my $numDeleted = $erdb->DeleteValue($entityName, $id, $fieldName, $fieldValue); >>
1241    
1242    Delete secondary field values from the database. This method can be used to delete all
1243    values of a specified field for a particular entity instance, or only a single value.
1244    
1245    Secondary fields are stored in two-column relations separate from an entity's primary
1246    table, and as a result a secondary field can legitimately have no value or multiple
1247    values. Therefore, it makes sense to talk about deleting secondary fields where it
1248    would not make sense for primary fields.
1249    
1250    =over 4
1251    
1252    =item entityName
1253    
1254    Name of the entity from which the fields are to be deleted.
1255    
1256    =item id
1257    
1258    ID of the entity instance to be processed. If the instance is not found, this
1259    method will have no effect. If C<undef> is specified, all values for all of
1260    the entity instances will be deleted.
1261    
1262    =item fieldName
1263    
1264    Name of the field whose values are to be deleted.
1265    
1266    =item fieldValue (optional)
1267    
1268    Value to be deleted. If not specified, then all values of the specified field
1269    will be deleted for the entity instance. If specified, then only the values which
1270    match this parameter will be deleted.
1271    
1272    =item RETURN
1273    
1274    Returns the number of rows deleted.
1275    
1276    =back
1277    
1278    =cut
1279    
1280    sub DeleteValue {
1281        # Get the parameters.
1282        my ($self, $entityName, $id, $fieldName, $fieldValue) = @_;
1283        # Declare the return value.
1284        my $retVal = 0;
1285        # We need to set up an SQL command to do the deletion. First, we
1286        # find the name of the field's relation.
1287        my $table = $self->GetFieldTable($entityName);
1288        my $field = $table->{$fieldName};
1289        my $relation = $field->{relation};
1290        # Make sure this is a secondary field.
1291        if ($relation eq $entityName) {
1292            Confess("Cannot delete values of $fieldName for $entityName.");
1293        } else {
1294            # Set up the SQL command to delete all values.
1295            my $sql = "DELETE FROM $relation";
1296            # Build the filter.
1297            my @filters = ();
1298            my @parms = ();
1299            # Check for a filter by ID.
1300            if (defined $id) {
1301                push @filters, "id = ?";
1302                push @parms, $id;
1303            }
1304            # Check for a filter by value.
1305            if (defined $fieldValue) {
1306                push @filters, "$fieldName = ?";
1307                push @parms, $fieldValue;
1308            }
1309            # Append the filters to the command.
1310            if (@filters) {
1311                $sql .= " WHERE " . join(" AND ", @filters);
1312            }
1313            # Execute the command.
1314            my $dbh = $self->{_dbh};
1315            $retVal = $dbh->SQL($sql, 0, @parms);
1316        }
1317        # Return the result.
1318        return $retVal;
1319    }
1320    
1321    =head3 LoadTables
1322    
1323    C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>
1324    
1325    This method will load the database tables from a directory. The tables must already have been created
1326    in the database. (This can be done by calling L</CreateTables>.) The caller passes in a directory name;
1327    all of the relations to be loaded must have a file in the directory with the same name as the relation
1328    (optionally with a suffix of C<.dtx>). Each file must be a tab-delimited table of field values. Each
1329    line of the file will be loaded as a row of the target relation table. The field values should be in
1330    the same order as the fields in the relation tables generated by L</ShowMetaData>. The old data is
1331    erased before the new data is loaded in.
1332    
1333    A certain amount of translation automatically takes place. Ctrl-M characters are deleted, and
1334    tab and new-line characters inside a field are escaped as C<\t> and C<\n>, respectively. Dates must
1335    be entered as a Unix timestamp, that is, as an integer number of seconds since the base epoch.
1336    
1337    =over 4
1338    
1339    =item directoryName
1340    
1341    Name of the directory containing the relation files to be loaded.
1342    
1343    =item rebuild
1344    
1345    TRUE if the tables should be dropped and rebuilt, else FALSE. This is, unfortunately, the
1346    only way to erase existing data in the tables, since the TRUNCATE command is not supported
1347    by all of the DB engines we use.
1348    
1349    =item RETURN
1350    
1351    Returns a statistical object describing the number of records read and a list of the error messages.
1352    
1353    =back
1354    
1355    =cut
1356    
1357    sub LoadTables {
1358        # Get the parameters.
1359        my ($self, $directoryName, $rebuild) = @_;
1360        # Start the timer.
1361        my $startTime = gettimeofday;
1362        # Clean any trailing slash from the directory name.
1363        $directoryName =~ s!/\\$!!;
1364        # Declare the return variable.
1365        my $retVal = Stats->new();
1366        # Get the relation names.
1367        my @relNames = $self->GetTableNames();
1368        for my $relationName (@relNames) {
1369            # Try to load this relation.
1370            my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);
1371            # Accumulate the statistics.
1372            $retVal->Accumulate($result);
1373        }
1374        # Add the duration of the load to the statistical object.
1375        $retVal->Add('duration', gettimeofday - $startTime);
1376        # Return the accumulated statistics.
1377        return $retVal;
1378    }
1379    
1380    
1381    =head3 GetTableNames
1382    
1383    C<< my @names = $erdb->GetTableNames; >>
1384    
1385    Return a list of the relations required to implement this database.
1386    
1387    =cut
1388    
1389    sub GetTableNames {
1390        # Get the parameters.
1391        my ($self) = @_;
1392        # Get the relation list from the metadata.
1393        my $relationTable = $self->{_metaData}->{RelationTable};
1394        # Return the relation names.
1395        return keys %{$relationTable};
1396    }
1397    
1398    =head3 GetEntityTypes
1399    
1400    C<< my @names = $erdb->GetEntityTypes; >>
1401    
1402  Return a list of the entity type names.  Return a list of the entity type names.
1403    
# Line 769  Line 1412 
1412      return sort keys %{$entityList};      return sort keys %{$entityList};
1413  }  }
1414    
1415    =head3 GetDataTypes
1416    
1417    C<< my %types = ERDB::GetDataTypes(); >>
1418    
1419    Return a table of ERDB data types. The table returned is a hash of hashes.
1420    The keys of the big hash are the datatypes. Each smaller hash has several
1421    values used to manage the data. The most interesting is the SQL type (key
1422    C<sqlType>) and the descriptive node (key C<notes>).
1423    
1424    Note that changing the values in the smaller hashes will seriously break
1425    things, so this data should be treated as read-only.
1426    
1427    =cut
1428    
1429    sub GetDataTypes {
1430        return %TypeTable;
1431    }
1432    
1433    
1434    =head3 IsEntity
1435    
1436    C<< my $flag = $erdb->IsEntity($entityName); >>
1437    
1438    Return TRUE if the parameter is an entity name, else FALSE.
1439    
1440    =over 4
1441    
1442    =item entityName
1443    
1444    Object name to be tested.
1445    
1446    =item RETURN
1447    
1448    Returns TRUE if the specified string is an entity name, else FALSE.
1449    
1450    =back
1451    
1452    =cut
1453    
1454    sub IsEntity {
1455        # Get the parameters.
1456        my ($self, $entityName) = @_;
1457        # Test to see if it's an entity.
1458        return exists $self->{_metaData}->{Entities}->{$entityName};
1459    }
1460    
1461  =head3 Get  =head3 Get
1462    
1463  C<< my $query = $database->Get(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  C<< my $query = $erdb->Get(\@objectNames, $filterClause, \@params); >>
1464    
1465  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.
1466  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 779  Line 1468 
1468  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
1469  $genus.  $genus.
1470    
1471  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", [$genus]); >>
1472    
1473  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
1474  parameter representing the parameter value. It would also be possible to code  parameter representing the parameter value. It would also be possible to code
1475    
1476  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>
1477    
1478  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
1479  characters inside the variable C<$genus>.  characters inside the variable C<$genus>.
# Line 796  Line 1485 
1485  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
1486  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,
1487    
1488  C<< $query = $sprout->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]); >>
1489    
1490  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
1491  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.
1492  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
1493  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
1494  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  
1495  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,
1496  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.
1497    
1498    If an entity or relationship is mentioned twice, the name for the second occurrence will
1499    be suffixed with C<2>, the third occurrence will be suffixed with C<3>, and so forth. So,
1500    for example, if we have C<['Feature', 'HasContig', 'Contig', 'HasContig']>, then the
1501    B<to-link> field of the first B<HasContig> is specified as C<HasContig(to-link)>, while
1502    the B<to-link> field of the second B<HasContig> is specified as C<HasContig2(to-link)>.
1503    
1504  =over 4  =over 4
1505    
1506  =item objectNames  =item objectNames
# Line 829  Line 1523 
1523    
1524  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
1525    
1526    Note that the case is important. Only an uppercase "ORDER BY" with a single space will
1527    be processed. The idea is to make it less likely to find the verb by accident.
1528    
1529  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
1530  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
1531  relation.  relation.
1532    
1533  =item param1, param2, ..., paramN  Finally, you can limit the number of rows returned by adding a LIMIT clause. The LIMIT must
1534    be the last thing in the filter clause, and it contains only the word "LIMIT" followed by
1535    a positive number. So, for example
1536    
1537  Parameter values to be substituted into the filter clause.  C<< "Genome(genus) = ? ORDER BY Genome(species) LIMIT 10" >>
1538    
1539    will only return the first ten genomes for the specified genus. The ORDER BY clause is not
1540    required. For example, to just get the first 10 genomes in the B<Genome> table, you could
1541    use
1542    
1543    C<< "LIMIT 10" >>
1544    
1545    =item params
1546    
1547    Reference to a list of parameter values to be substituted into the filter clause.
1548    
1549  =item RETURN  =item RETURN
1550    
# Line 847  Line 1556 
1556    
1557  sub Get {  sub Get {
1558      # Get the parameters.      # Get the parameters.
1559      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $objectNames, $filterClause, $params) = @_;
1560      # Construct the SELECT statement. The general pattern is      # Process the SQL stuff.
1561      #      my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1562      # SELECT name1.*, name2.*, ... nameN.* FROM name1, name2, ... nameN          $self->_SetupSQL($objectNames, $filterClause);
1563      #      # Create the query.
1564      my $dbh = $self->{_dbh};      my $command = "SELECT DISTINCT " . join(".*, ", @{$mappedNameListRef}) .
1565      my $command = "SELECT DISTINCT " . join('.*, ', @{$objectNames}) . ".* FROM " .          ".* $suffix";
1566                  join(', ', @{$objectNames});      my $sth = $self->_GetStatementHandle($command, $params);
1567      # Check for a filter clause.      # Now we create the relation map, which enables DBQuery to determine the order, name
1568      if ($filterClause) {      # and mapped name for each object in the query.
1569          # Here we have one, so we convert its field names and add it to the query. First,      my @relationMap = ();
1570          # We create a copy of the filter string we can work with.      for my $mappedName (@{$mappedNameListRef}) {
1571          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";  
         }  
1572      }      }
     Trace("SQL query: $command") if T(2);  
     Trace("PARMS: '" . (join "', '", @params) . "'") if (T(3) && (@params > 0));  
     my $sth = $dbh->prepare_command($command);  
     # Execute it with the parameters bound in.  
     $sth->execute(@params) || Confess("SELECT error" . $sth->errstr());  
1573      # Return the statement object.      # Return the statement object.
1574      my $retVal = DBQuery::_new($self, $sth, @{$objectNames});      my $retVal = DBQuery::_new($self, $sth, \@relationMap);
1575      return $retVal;      return $retVal;
1576  }  }
1577    
 =head3 GetList  
1578    
 C<< my @dbObjects = $database->GetList(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  
1579    
1580  Return a list of object descriptors for the specified objects as determined by the  =head3 Search
 specified filter clause.  
1581    
1582  This method is essentially the same as L</Get> except it returns a list of objects rather  C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>
1583  than a query object that can be used to get the results one record at a time.  
1584    Perform a full text search with filtering. The search will be against a specified object
1585    in the object name list. That object will get an extra field containing the search
1586    relevance. Note that except for the search expression, the parameters of this method are
1587    the same as those for L</Get> and follow the same rules.
1588    
1589  =over 4  =over 4
1590    
1591    =item searchExpression
1592    
1593    Boolean search expression for the text fields of the target object. The default mode for
1594    a Boolean search expression is OR, but we want the default to be AND, so we will
1595    add a C<+> operator to each word with no other operator before it.
1596    
1597    =item idx
1598    
1599    Index in the I<$objectNames> list of the table to be searched in full-text mode.
1600    
1601  =item objectNames  =item objectNames
1602    
1603  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 995  Line 1612 
1612  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
1613  be included in the list of object names.  be included in the list of object names.
1614    
1615  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  
1616    
1617  Parameter values to be substituted into the filter clause.  Reference to a list of parameter values to be substituted into the filter clause.
1618    
1619  =item RETURN  =item RETURN
1620    
1621  Returns a list of B<DBObject>s that satisfy the query conditions.  Returns a query object for the specified search.
1622    
1623  =back  =back
1624    
1625  =cut  =cut
1626  #: Return Type @%  
1627  sub GetList {  sub Search {
1628      # Get the parameters.      # Get the parameters.
1629      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1630      # Declare the return variable.      # Declare the return variable.
1631      my @retVal = ();      my $retVal;
1632      # Perform the query.      # Create a safety copy of the parameter list. Note we have to be careful to insure
1633      my $query = $self->Get($objectNames, $filterClause, @params);      # a parameter list exists before we copy it.
1634      # Loop through the results.      my @myParams = ();
1635      while (my $object = $query->Fetch) {      if (defined $params) {
1636          push @retVal, $object;          @myParams = @{$params};
1637        }
1638        # Get the first object's structure so we have access to the searchable fields.
1639        my $object1Name = $objectNames->[$idx];
1640        my $object1Structure = $self->_GetStructure($object1Name);
1641        # Get the field list.
1642        if (! exists $object1Structure->{searchFields}) {
1643            Confess("No searchable index for $object1Name.");
1644        } else {
1645            # Get the field list.
1646            my @fields = @{$object1Structure->{searchFields}};
1647            # Clean the search expression.
1648            my $actualKeywords = $self->CleanKeywords($searchExpression);
1649            # Prefix a "+" to each uncontrolled word. This converts the default
1650            # search mode from OR to AND.
1651            $actualKeywords =~ s/(^|\s)(\w|")/$1\+$2/g;
1652            Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1653            # We need two match expressions, one for the filter clause and one in the
1654            # query itself. Both will use a parameter mark, so we need to push the
1655            # search expression onto the front of the parameter list twice.
1656            unshift @myParams, $actualKeywords, $actualKeywords;
1657            # Build the match expression.
1658            my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
1659            my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
1660            # Process the SQL stuff.
1661            my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1662                $self->_SetupSQL($objectNames, $filterClause, $matchClause);
1663            # Create the query. Note that the match clause is inserted at the front of
1664            # the select fields.
1665            my $command = "SELECT DISTINCT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .
1666                ".* $suffix";
1667            my $sth = $self->_GetStatementHandle($command, \@myParams);
1668            # Now we create the relation map, which enables DBQuery to determine the order, name
1669            # and mapped name for each object in the query.
1670            my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
1671            # Return the statement object.
1672            $retVal = DBQuery::_new($self, $sth, \@relationMap, $object1Name);
1673      }      }
1674      # Return the result.      return $retVal;
     return @retVal;  
1675  }  }
1676    
1677  =head3 ComputeObjectSentence  =head3 GetFlat
1678    
1679  C<< my $sentence = $database->ComputeObjectSentence($objectName); >>  C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>
1680    
1681  Check an object name, and if it is a relationship convert it to a relationship sentence.  This is a variation of L</GetAll> that asks for only a single field per record and
1682    returns a single flattened list.
1683    
1684  =over 4  =over 4
1685    
1686  =item objectName  =item objectNames
1687    
1688  Name of the entity or relationship.  List containing the names of the entity and relationship objects to be retrieved.
1689    
1690    =item filterClause
1691    
1692    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1693    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
1694    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
1695    parameter list as additional parameters. The fields in a filter clause can come from primary
1696    entity relations, relationship relations, or secondary entity relations; however, all of the
1697    entities and relationships involved must be included in the list of object names.
1698    
1699    =item parameterList
1700    
1701    List of the parameters to be substituted in for the parameters marks in the filter clause.
1702    
1703    =item field
1704    
1705    Name of the field to be used to get the elements of the list returned.
1706    
1707  =item RETURN  =item RETURN
1708    
1709  Returns a string containing the entity name or a relationship sentence.  Returns a list of values.
1710    
1711  =back  =back
1712    
1713  =cut  =cut
1714    #: Return Type @;
1715  sub ComputeObjectSentence {  sub GetFlat {
1716      # Get the parameters.      # Get the parameters.
1717      my ($self, $objectName) = @_;      my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
1718      # Set the default return value.      # Construct the query.
1719      my $retVal = $objectName;      my $query = $self->Get($objectNames, $filterClause, $parameterList);
1720      # Look for the object as a relationship.      # Create the result list.
1721      my $relTable = $self->{_metaData}->{Relationships};      my @retVal = ();
1722      if (exists $relTable->{$objectName}) {      # Loop through the records, adding the field values found to the result list.
1723          # Get the relationship sentence.      while (my $row = $query->Fetch()) {
1724          $retVal = _ComputeRelationshipSentence($objectName, $relTable->{$objectName});          push @retVal, $row->Value($field);
1725      }      }
1726      # Return the result.      # Return the list created.
1727      return $retVal;      return @retVal;
1728  }  }
1729    
1730  =head3 DumpRelations  =head3 SpecialFields
1731    
1732  C<< $database->DumpRelations($outputDirectory); >>  C<< my %specials = $erdb->SpecialFields($entityName); >>
1733    
1734  Write the contents of all the relations to tab-delimited files in the specified directory.  Return a hash mapping special fields in the specified entity to the value of their
1735  Each file will have the same name as the relation dumped, with an extension of DTX.  C<special> attribute. This enables the subclass to get access to the special field
1736    attributes without needed to plumb the internal ERDB data structures.
1737    
1738  =over 4  =over 4
1739    
1740  =item outputDirectory  =item entityName
1741    
1742  Name of the directory into which the relation files should be dumped.  Name of the entity whose special fields are desired.
1743    
1744    =item RETURN
1745    
1746    Returns a hash. The keys of the hash are the special field names, and the values
1747    are the values from each special field's C<special> attribute.
1748    
1749  =back  =back
1750    
1751  =cut  =cut
1752    
1753  sub DumpRelations {  sub SpecialFields {
1754      # Get the parameters.      # Get the parameters.
1755      my ($self, $outputDirectory) = @_;      my ($self, $entityName) = @_;
1756      # Now we need to run through all the relations. First, we loop through the entities.      # Declare the return variable.
1757      my $metaData = $self->{_metaData};      my %retVal = ();
1758      my $entities = $metaData->{Entities};      # Find the entity's data structure.
1759      for my $entityName (keys %{$entities}) {      my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1760          my $entityStructure = $entities->{$entityName};      # Loop through its fields, adding each special field to the return hash.
1761          # Get the entity's relations.      my $fieldHash = $entityData->{Fields};
1762          my $relationList = $entityStructure->{Relations};      for my $fieldName (keys %{$fieldHash}) {
1763          # Loop through the relations, dumping them.          my $fieldData = $fieldHash->{$fieldName};
1764          for my $relationName (keys %{$relationList}) {          if (exists $fieldData->{special}) {
1765              my $relation = $relationList->{$relationName};              $retVal{$fieldName} = $fieldData->{special};
             $self->_DumpRelation($outputDirectory, $relationName, $relation);  
         }  
1766      }      }
     # Next, we loop through the relationships.  
     my $relationships = $metaData->{Relationships};  
     for my $relationshipName (keys %{$relationships}) {  
         my $relationshipStructure = $relationships->{$relationshipName};  
         # Dump this relationship's relation.  
         $self->_DumpRelation($outputDirectory, $relationshipName, $relationshipStructure->{Relations}->{$relationshipName});  
1767      }      }
1768        # Return the result.
1769        return %retVal;
1770  }  }
1771    
1772  =head3 InsertObject  =head3 Delete
1773    
1774  C<< my $ok = $database->InsertObject($objectType, \%fieldHash); >>  C<< my $stats = $erdb->Delete($entityName, $objectID, %options); >>
1775    
1776  Insert an object into the database. The object is defined by a type name and then a hash  Delete an entity instance from the database. The instance is deleted along with all entity and
1777  of field names to values. Field values in the primary relation are represented by scalars.  relationship instances dependent on it. The definition of I<dependence> is recursive.
 (Note that for relationships, the primary relation is the B<only> relation.)  
 Field values for the other relations comprising the entity are always list references. For  
 example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases  
 C<ZP_00210270.1> and C<gi|46206278>.  
1778    
1779  C<< $database->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>  An object is always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many
1780    relationship connected to a dependent entity or if it is the "to" entity connected to a 1-to-many
1781    dependent relationship.
1782    
1783  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and  =over 4
 property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.  
1784    
1785  C<< $database->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>  =item entityName
1786    
1787  =over 4  Name of the entity type for the instance being deleted.
1788    
1789  =item newObjectType  =item objectID
1790    
1791  Type name of the object to insert.  ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),
1792    then it is presumed to by a LIKE pattern.
1793    
1794  =item fieldHash  =item options
1795    
1796  Hash of field names to values.  A hash detailing the options for this delete operation.
1797    
1798  =item RETURN  =item RETURN
1799    
1800  Returns 1 if successful, 0 if an error occurred.  Returns a statistics object indicating how many records of each particular table were
1801    deleted.
1802    
1803  =back  =back
1804    
1805  =cut  The permissible options for this method are as follows.
1806    
1807  sub InsertObject {  =over 4
1808    
1809    =item testMode
1810    
1811    If TRUE, then the delete statements will be traced, but no changes will be made to the database.
1812    
1813    =item keepRoot
1814    
1815    If TRUE, then the entity instances will not be deleted, only the dependent records.
1816    
1817    =back
1818    
1819    =cut
1820    #: Return Type $%;
1821    sub Delete {
1822      # Get the parameters.      # Get the parameters.
1823      my ($self, $newObjectType, $fieldHash) = @_;      my ($self, $entityName, $objectID, %options) = @_;
1824      # Denote that so far we appear successful.      # Declare the return variable.
1825      my $retVal = 1;      my $retVal = Stats->new();
1826      # Get the database handle.      # Get the DBKernel object.
1827      my $dbh = $self->{_dbh};      my $db = $self->{_dbh};
1828      # Get the relation list.      # We're going to generate all the paths branching out from the starting entity. One of
1829      my $relationTable = $self->_GetRelationTable($newObjectType);      # the things we have to be careful about is preventing loops. We'll use a hash to
1830      # Loop through the relations. We'll build insert statements for each one. If a relation is      # determine if we've hit a loop.
1831      # secondary, we may end up generating multiple insert statements. If an error occurs, we      my %alreadyFound = ();
1832      # stop the loop.      # These next lists will serve as our result stack. We start by pushing object lists onto
1833      my @relationList = keys %{$relationTable};      # the stack, and then popping them off to do the deletes. This means the deletes will
1834      for (my $i = 0; $retVal && $i <= $#relationList; $i++) {      # start with the longer paths before getting to the shorter ones. That, in turn, makes
1835          my $relationName = $relationList[$i];      # sure we don't delete records that might be needed to forge relationships back to the
1836          my $relationDefinition = $relationTable->{$relationName};      # original item. We have two lists-- one for TO-relationships, and one for
1837          # Get the relation's fields. For each field we will collect a value in the corresponding      # FROM-relationships and entities.
1838          # position of the @valueList array. If one of the fields is missing, we will add it to the      my @fromPathList = ();
1839          # @missing list.      my @toPathList = ();
1840          my @fieldList = @{$relationDefinition->{Fields}};      # This final list is used to remember what work still needs to be done. We push paths
1841          my @fieldNameList = ();      # onto the list, then pop them off to extend the paths. We prime it with the starting
1842          my @valueList = ();      # point. Note that we will work hard to insure that the last item on a path in the
1843          my @missing = ();      # to-do list is always an entity.
1844          my $recordCount = 1;      my @todoList = ([$entityName]);
1845          for my $fieldDescriptor (@fieldList) {      while (@todoList) {
1846              # Get the field name and save it. Note we need to fix it up so the hyphens          # Get the current path.
1847              # are converted to underscores.          my $current = pop @todoList;
1848              my $fieldName = $fieldDescriptor->{name};          # Copy it into a list.
1849              push @fieldNameList, _FixName($fieldName);          my @stackedPath = @{$current};
1850              # Look for the named field in the incoming structure. Note that we are looking          # Pull off the last item on the path. It will always be an entity.
1851              # for the real field name, not the fixed-up one!          my $myEntityName = pop @stackedPath;
1852              if (exists $fieldHash->{$fieldName}) {          # Add it to the alreadyFound list.
1853                  # Here we found the field. Stash it in the value list.          $alreadyFound{$myEntityName} = 1;
1854                  my $value = $fieldHash->{$fieldName};          # Figure out if we need to delete this entity.
1855                  push @valueList, $value;          if ($myEntityName ne $entityName || ! $options{keepRoot}) {
1856                  # If the value is a list, we may need to increment the record count.              # Get the entity data.
1857                  if (ref $value eq "ARRAY") {              my $entityData = $self->_GetStructure($myEntityName);
1858                      my $thisCount = @{$value};              # Loop through the entity's relations. A DELETE command will be needed for each of them.
1859                      if ($recordCount == 1) {              my $relations = $entityData->{Relations};
1860                          # Here we have our first list, so we save its count.              for my $relation (keys %{$relations}) {
1861                          $recordCount = $thisCount;                  my @augmentedList = (@stackedPath, $relation);
1862                      } elsif ($recordCount != $thisCount) {                  push @fromPathList, \@augmentedList;
                         # Here we have a second list, so its length has to match the  
                         # previous lists.  
                         Trace("Field $value in new $newObjectType object has an invalid list length $thisCount. Expected $recordCount.") if T(0);  
                         $retVal = 0;  
1863                      }                      }
1864                  }                  }
1865            # Now we need to look for relationships connected to this entity.
1866            my $relationshipList = $self->{_metaData}->{Relationships};
1867            for my $relationshipName (keys %{$relationshipList}) {
1868                my $relationship = $relationshipList->{$relationshipName};
1869                # Check the FROM field. We're only interested if it's us.
1870                if ($relationship->{from} eq $myEntityName) {
1871                    # Add the path to this relationship.
1872                    my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1873                    push @fromPathList, \@augmentedList;
1874                    # Check the arity. If it's MM we're done. If it's 1M
1875                    # and the target hasn't been seen yet, we want to
1876                    # stack the entity for future processing.
1877                    if ($relationship->{arity} eq '1M') {
1878                        my $toEntity = $relationship->{to};
1879                        if (! exists $alreadyFound{$toEntity}) {
1880                            # Here we have a new entity that's dependent on
1881                            # the current entity, so we need to stack it.
1882                            my @stackList = (@augmentedList, $toEntity);
1883                            push @fromPathList, \@stackList;
1884              } else {              } else {
1885                  # Here the field is not present. Flag it as missing.                          Trace("$toEntity ignored because it occurred previously.") if T(4);
                 push @missing, $fieldName;  
1886              }              }
1887          }          }
         # If we are the primary relation, add the new-record flag.  
         if ($relationName eq $newObjectType) {  
             push @valueList, 1;  
             push @fieldNameList, "new_record";  
1888          }          }
1889          # Only proceed if there are no missing fields.              # Now check the TO field. In this case only the relationship needs
1890          if (@missing > 0) {              # deletion.
1891              Trace("Relation $relationName for $newObjectType skipped due to missing fields: " .              if ($relationship->{to} eq $myEntityName) {
1892                  join(' ', @missing)) if T(1);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1893          } else {                  push @toPathList, \@augmentedList;
             # Build the INSERT statement.  
             my $statement = "INSERT INTO $relationName (" . join (', ', @fieldNameList) .  
                 ") VALUES (";  
             # Create a marker list of the proper size and put it in the statement.  
             my @markers = ();  
             while (@markers < @fieldNameList) { push @markers, '?'; }  
             $statement .= join(', ', @markers) . ")";  
             # We have the insert statement, so prepare it.  
             my $sth = $dbh->prepare_command($statement);  
             Trace("Insert statement prepared: $statement") if T(3);  
             # Now we loop through the values. If a value is scalar, we use it unmodified. If it's  
             # a list, we use the current element. The values are stored in the @parameterList array.  
             my $done = 0;  
             for (my $i = 0; $i < $recordCount; $i++) {  
                 # Clear the parameter list array.  
                 my @parameterList = ();  
                 # Loop through the values.  
                 for my $value (@valueList) {  
                     # Check to see if this is a scalar value.  
                     if (ref $value eq "ARRAY") {  
                         # Here we have a list value. Pull the current entry.  
                         push @parameterList, $value->[$i];  
                     } else {  
                         # Here we have a scalar value. Use it unmodified.  
                         push @parameterList, $value;  
1894                      }                      }
1895                  }                  }
                 # Execute the INSERT statement with the specified parameter list.  
                 $retVal = $sth->execute(@parameterList);  
                 if (!$retVal) {  
                     my $errorString = $sth->errstr();  
                     Trace("Insert error: $errorString.") if T(0);  
1896                  }                  }
1897        # Create the first qualifier for the WHERE clause. This selects the
1898        # keys of the primary entity records to be deleted. When we're deleting
1899        # from a dependent table, we construct a join path from the first qualifier
1900        # to the table containing the dependent records to delete.
1901        my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
1902        # We need to make two passes. The first is through the to-list, and
1903        # the second through the from-list. The from-list is second because
1904        # the to-list may need to pass through some of the entities the
1905        # from-list would delete.
1906        my %stackList = ( from_link => \@fromPathList, to_link => \@toPathList );
1907        # Now it's time to do the deletes. We do it in two passes.
1908        for my $keyName ('to_link', 'from_link') {
1909            # Get the list for this key.
1910            my @pathList = @{$stackList{$keyName}};
1911            Trace(scalar(@pathList) . " entries in path list for $keyName.") if T(3);
1912            # Loop through this list.
1913            while (my $path = pop @pathList) {
1914                # Get the table whose rows are to be deleted.
1915                my @pathTables = @{$path};
1916                # Start the DELETE statement. We need to call DBKernel because the
1917                # syntax of a DELETE-USING varies among DBMSs.
1918                my $target = $pathTables[$#pathTables];
1919                my $stmt = $db->SetUsing(@pathTables);
1920                # Now start the WHERE. The first thing is the ID field from the starting table. That
1921                # starting table will either be the entity relation or one of the entity's
1922                # sub-relations.
1923                $stmt .= " WHERE $pathTables[0].id $qualifier";
1924                # Now we run through the remaining entities in the path, connecting them up.
1925                for (my $i = 1; $i <= $#pathTables; $i += 2) {
1926                    # Connect the current relationship to the preceding entity.
1927                    my ($entity, $rel) = @pathTables[$i-1,$i];
1928                    # The style of connection depends on the direction of the relationship.
1929                    $stmt .= " AND $entity.id = $rel.$keyName";
1930                    if ($i + 1 <= $#pathTables) {
1931                        # Here there's a next entity, so connect that to the relationship's
1932                        # to-link.
1933                        my $entity2 = $pathTables[$i+1];
1934                        $stmt .= " AND $rel.to_link = $entity2.id";
1935                    }
1936                }
1937                # Now we have our desired DELETE statement.
1938                if ($options{testMode}) {
1939                    # Here the user wants to trace without executing.
1940                    Trace($stmt) if T(0);
1941                } else {
1942                    # Here we can delete. Note that the SQL method dies with a confession
1943                    # if an error occurs, so we just go ahead and do it.
1944                    Trace("Executing delete from $target using '$objectID'.") if T(3);
1945                    my $rv = $db->SQL($stmt, 0, $objectID);
1946                    # Accumulate the statistics for this delete. The only rows deleted
1947                    # are from the target table, so we use its name to record the
1948                    # statistic.
1949                    $retVal->Add($target, $rv);
1950              }              }
1951          }          }
1952      }      }
1953      # Return the success indicator.      # Return the result.
1954      return $retVal;      return $retVal;
1955  }  }
1956    
1957  =head3 LoadTable  =head3 Disconnect
1958    
1959  C<< my %results = $database->LoadTable($fileName, $relationName, $truncateFlag); >>  C<< $erdb->Disconnect($relationshipName, $originEntityName, $originEntityID); >>
1960    
1961  Load data from a tab-delimited file into a specified table, optionally re-creating the table  Disconnect an entity instance from all the objects to which it is related. This
1962  first.  will delete each relationship instance that connects to the specified entity.
1963    
1964  =over 4  =over 4
1965    
1966  =item fileName  =item relationshipName
   
 Name of the file from which the table data should be loaded.  
   
 =item relationName  
1967    
1968  Name of the relation to be loaded. This is the same as the table name.  Name of the relationship whose instances are to be deleted.
1969    
1970  =item truncateFlag  =item originEntityName
1971    
1972  TRUE if the table should be dropped and re-created, else FALSE  Name of the entity that is to be disconnected.
1973    
1974  =item RETURN  =item originEntityID
1975    
1976  Returns a statistical object containing the number of records read and a list of  ID of the entity that is to be disconnected.
 the error messages.  
1977    
1978  =back  =back
1979    
1980  =cut  =cut
1981  sub LoadTable {  
1982    sub Disconnect {
1983      # Get the parameters.      # Get the parameters.
1984      my ($self, $fileName, $relationName, $truncateFlag) = @_;      my ($self, $relationshipName, $originEntityName, $originEntityID) = @_;
1985      # Create the statistical return object.      # Get the relationship descriptor.
1986      my $retVal = _GetLoadStats();      my $structure = $self->_GetStructure($relationshipName);
1987      # Trace the fact of the load.      # Insure we have a relationship.
1988      Trace("Loading table $relationName from $fileName") if T(2);      if (! exists $structure->{from}) {
1989            Confess("$relationshipName is not a relationship in the database.");
1990        } else {
1991      # Get the database handle.      # Get the database handle.
1992      my $dbh = $self->{_dbh};      my $dbh = $self->{_dbh};
1993      # Get the relation data.          # We'll set this value to 1 if we find our entity.
1994      my $relation = $self->_FindRelation($relationName);          my $found = 0;
1995      # Check the truncation flag.          # Loop through the ends of the relationship.
1996      if ($truncateFlag) {          for my $dir ('from', 'to') {
1997          Trace("Creating table $relationName") if T(2);              if ($structure->{$dir} eq $originEntityName) {
1998          # Re-create the table without its index.                  # Delete all relationship instances on this side of the entity instance.
1999          $self->CreateTable($relationName, 0);                  Trace("Disconnecting in $dir direction with ID \"$originEntityID\".");
2000          # If this is a pre-index DBMS, create the index here.                  $dbh->SQL("DELETE FROM $relationshipName WHERE ${dir}_link = ?", 0, $originEntityID);
2001          if ($dbh->{_preIndex}) {                  $found = 1;
             eval {  
                 $self->CreateIndex($relationName);  
             };  
             if ($@) {  
                 $retVal->AddMessage($@);  
             }  
         }  
2002      }      }
     # Determine whether or not this is a primary relation. Primary relations have an extra  
     # field indicating whether or not a given object is new or was loaded from the flat files.  
     my $primary = $self->_IsPrimary($relationName);  
     # Get the number of fields in this relation.  
     my @fieldList = @{$relation->{Fields}};  
     my $fieldCount = @fieldList;  
     # Start a database transaction.  
     $dbh->begin_tran;  
     # Open the relation file. We need to create a cleaned-up copy before loading.  
     open TABLEIN, '<', $fileName;  
     my $tempName = "$fileName.tbl";  
     open TABLEOUT, '>', $tempName;  
     my $inputCount = 0;  
     # Loop through the file.  
     while (<TABLEIN>) {  
         $inputCount++;  
         # Chop off the new-line character.  
         my $record = Tracer::Strip($_);  
         # Only proceed if the record is non-blank.  
         if ($record) {  
             # Escape all the backslashes found in the line.  
             $record =~ s/\\/\\\\/g;  
             # Insure the number of fields is correct.  
             my @fields = split /\t/, $record;  
             while (@fields > $fieldCount) {  
                 my $extraField = $fields[$#fields];  
                 delete $fields[$#fields];  
                 if ($extraField) {  
                     Trace("Nonblank extra field value \"$extraField\" deleted from record $inputCount of $fileName.") if T(1);  
                 }  
             }  
             while (@fields < $fieldCount) {  
                 push @fields, "";  
             }  
             # If this is a primary relation, add a 0 for the new-record flag (indicating that  
             # this record is not new, but part of the original load).  
             if ($primary) {  
                 push @fields, "0";  
             }  
             # Write the record.  
             $record = join "\t", @fields;  
             print TABLEOUT "$record\n";  
             # Count the record written.  
             my $count = $retVal->Add('records');  
             my $len = length $record;  
             Trace("Record $count written with $len characters.") if T(4);  
         } else {  
             # Here we have a blank record.  
             $retVal->Add('skipped');  
         }  
     }  
     # Close the files.  
     close TABLEIN;  
     close TABLEOUT;  
     Trace("Temporary file $tempName created.") if T(2);  
     # Load the table.  
     my $rv;  
     eval {  
         $rv = $dbh->load_table(file => $tempName, tbl => $relationName);  
     };  
     if (!defined $rv) {  
         $retVal->AddMessage($@) if ($@);  
         $retVal->AddMessage("Table load failed for $relationName using $tempName.");  
         Trace("Table load failed for $relationName.") if T(1);  
     } else {  
         # Here we successfully loaded the table. Trace the number of records loaded.  
         Trace("$retVal->{records} records read for $relationName.") if T(2);  
         # If we're rebuilding, we need to create the table indexes.  
         if ($truncateFlag && ! $dbh->{_preIndex}) {  
             eval {  
                 $self->CreateIndex($relationName);  
             };  
             if ($@) {  
                 $retVal->AddMessage($@);  
2003              }              }
2004            # Insure we found the entity on at least one end.
2005            if (! $found) {
2006                Confess("Entity \"$originEntityName\" does not use $relationshipName.");
2007          }          }
2008      }      }
     # Commit the database changes.  
     $dbh->commit_tran;  
     # Delete the temporary file.  
     unlink $tempName;  
     # Return the statistics.  
     return $retVal;  
2009  }  }
2010    
2011  =head3 GenerateEntity  =head3 DeleteRow
2012    
2013  C<< my $fieldHash = $database->GenerateEntity($id, $type, \%values); >>  C<< $erdb->DeleteRow($relationshipName, $fromLink, $toLink, \%values); >>
2014    
2015  Generate the data for a new entity instance. This method creates a field hash suitable for  Delete a row from a relationship. In most cases, only the from-link and to-link are
2016  passing as a parameter to L</InsertObject>. The ID is specified by the callr, but the rest  needed; however, for relationships with intersection data values can be specified
2017  of the fields are generated using information in the database schema.  for the other fields using a hash.
   
 Each data type has a default algorithm for generating random test data. This can be overridden  
 by including a B<DataGen> element in the field. If this happens, the content of the element is  
 executed as a PERL program in the context of this module. The element may make use of a C<$this>  
 variable which contains the field hash as it has been built up to the current point. If any  
 fields are dependent on other fields, the C<pass> attribute can be used to control the order  
 in which the fields are generated. A field with a high data pass number will be generated after  
 a field with a lower one. If any external values are needed, they should be passed in via the  
 optional third parameter, which will be available to the data generation script under the name  
 C<$value>. Several useful utility methods are provided for generating random values, including  
 L</IntGen>, L</StringGen>, L</FloatGen>, and L</DateGen>. Note that dates are stored and generated  
 in the form of a timestamp number rather than a string.  
2018    
2019  =over 4  =over 4
2020    
2021  =item id  =item relationshipName
2022    
2023  ID to assign to the new entity.  Name of the relationship from which the row is to be deleted.
2024    
2025  =item type  =item fromLink
2026    
2027    ID of the entity instance in the From direction.
2028    
2029    =item toLink
2030    
2031    ID of the entity instance in the To direction.
2032    
2033    =item values
2034    
2035    Reference to a hash of other values to be used for filtering the delete.
2036    
2037    =back
2038    
2039    =cut
2040    
2041    sub DeleteRow {
2042        # Get the parameters.
2043        my ($self, $relationshipName, $fromLink, $toLink, $values) = @_;
2044        # Create a hash of all the filter information.
2045        my %filter = ('from-link' => $fromLink, 'to-link' => $toLink);
2046        if (defined $values) {
2047            for my $key (keys %{$values}) {
2048                $filter{$key} = $values->{$key};
2049            }
2050        }
2051        # Build an SQL statement out of the hash.
2052        my @filters = ();
2053        my @parms = ();
2054        for my $key (keys %filter) {
2055            push @filters, _FixName($key) . " = ?";
2056            push @parms, $filter{$key};
2057        }
2058        Trace("Parms for delete row are " . join(", ", map { "\"$_\"" } @parms) . ".") if T(SQL => 4);
2059        my $command = "DELETE FROM $relationshipName WHERE " .
2060                      join(" AND ", @filters);
2061        # Execute it.
2062        my $dbh = $self->{_dbh};
2063        $dbh->SQL($command, undef, @parms);
2064    }
2065    
2066    =head3 SortNeeded
2067    
2068    C<< my $parms = $erdb->SortNeeded($relationName); >>
2069    
2070    Return the pipe command for the sort that should be applied to the specified
2071    relation when creating the load file.
2072    
2073    For example, if the load file should be sorted ascending by the first
2074    field, this method would return
2075    
2076        sort -k1 -t"\t"
2077    
2078    If the first field is numeric, the method would return
2079    
2080        sort -k1n -t"\t"
2081    
2082    Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate
2083    keys using a sort.
2084    
2085    =over 4
2086    
2087    =item relationName
2088    
2089    Name of the relation to be examined.
2090    
2091    =item
2092    
2093    Returns the sort command to use for sorting the relation, suitable for piping.
2094    
2095    =back
2096    
2097    =cut
2098    #: Return Type $;
2099    sub SortNeeded {
2100        # Get the parameters.
2101        my ($self, $relationName) = @_;
2102        # Declare a descriptor to hold the names of the key fields.
2103        my @keyNames = ();
2104        # Get the relation structure.
2105        my $relationData = $self->_FindRelation($relationName);
2106        # Find out if the relation is a primary entity relation,
2107        # a relationship relation, or a secondary entity relation.
2108        my $entityTable = $self->{_metaData}->{Entities};
2109        my $relationshipTable = $self->{_metaData}->{Relationships};
2110        if (exists $entityTable->{$relationName}) {
2111            # Here we have a primary entity relation.
2112            push @keyNames, "id";
2113        } elsif (exists $relationshipTable->{$relationName}) {
2114            # Here we have a relationship. We sort using the FROM index.
2115            my $relationshipData = $relationshipTable->{$relationName};
2116            my $index = $relationData->{Indexes}->{idxFrom};
2117            push @keyNames, @{$index->{IndexFields}};
2118        } else {
2119            # Here we have a secondary entity relation, so we have a sort on the ID field.
2120            push @keyNames, "id";
2121        }
2122        # Now we parse the key names into sort parameters. First, we prime the return
2123        # string.
2124        my $retVal = "sort -t\"\t\" ";
2125        # Get the relation's field list.
2126        my @fields = @{$relationData->{Fields}};
2127        # Loop through the keys.
2128        for my $keyData (@keyNames) {
2129            # Get the key and the ordering.
2130            my ($keyName, $ordering);
2131            if ($keyData =~ /^([^ ]+) DESC/) {
2132                ($keyName, $ordering) = ($1, "descending");
2133            } else {
2134                ($keyName, $ordering) = ($keyData, "ascending");
2135            }
2136            # Find the key's position and type.
2137            my $fieldSpec;
2138            for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {
2139                my $thisField = $fields[$i];
2140                if ($thisField->{name} eq $keyName) {
2141                    # Get the sort modifier for this field type. The modifier
2142                    # decides whether we're using a character, numeric, or
2143                    # floating-point sort.
2144                    my $modifier = $TypeTable{$thisField->{type}}->{sort};
2145                    # If the index is descending for this field, denote we want
2146                    # to reverse the sort order on this field.
2147                    if ($ordering eq 'descending') {
2148                        $modifier .= "r";
2149                    }
2150                    # Store the position and modifier into the field spec, which
2151                    # will stop the inner loop. Note that the field number is
2152                    # 1-based in the sort command, so we have to increment the
2153                    # index.
2154                    $fieldSpec = ($i + 1) . $modifier;
2155                }
2156            }
2157            # Add this field to the sort command.
2158            $retVal .= " -k$fieldSpec";
2159        }
2160        # Return the result.
2161        return $retVal;
2162    }
2163    
2164    =head3 GetList
2165    
2166    C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>
2167    
2168    Return a list of object descriptors for the specified objects as determined by the
2169    specified filter clause.
2170    
2171    This method is essentially the same as L</Get> except it returns a list of objects rather
2172    than a query object that can be used to get the results one record at a time.
2173    
2174    =over 4
2175    
2176    =item objectNames
2177    
2178    List containing the names of the entity and relationship objects to be retrieved.
2179    
2180    =item filterClause
2181    
2182    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
2183    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
2184    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
2185    in the filter clause should be added to the parameter list as additional parameters. The
2186    fields in a filter clause can come from primary entity relations, relationship relations,
2187    or secondary entity relations; however, all of the entities and relationships involved must
2188    be included in the list of object names.
2189    
2190    The filter clause can also specify a sort order. To do this, simply follow the filter string
2191    with an ORDER BY clause. For example, the following filter string gets all genomes for a
2192    particular genus and sorts them by species name.
2193    
2194    C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
2195    
2196    The rules for field references in a sort order are the same as those for field references in the
2197    filter clause in general; however, odd things may happen if a sort field is from a secondary
2198    relation.
2199    
2200    =item params
2201    
2202    Reference to a list of parameter values to be substituted into the filter clause.
2203    
2204    =item RETURN
2205    
2206    Returns a list of B<ERDBObject>s that satisfy the query conditions.
2207    
2208    =back
2209    
2210    =cut
2211    #: Return Type @%
2212    sub GetList {
2213        # Get the parameters.
2214        my ($self, $objectNames, $filterClause, $params) = @_;
2215        # Declare the return variable.
2216        my @retVal = ();
2217        # Perform the query.
2218        my $query = $self->Get($objectNames, $filterClause, $params);
2219        # Loop through the results.
2220        while (my $object = $query->Fetch) {
2221            push @retVal, $object;
2222        }
2223        # Return the result.
2224        return @retVal;
2225    }
2226    
2227    =head3 GetCount
2228    
2229    C<< my $count = $erdb->GetCount(\@objectNames, $filter, \@params); >>
2230    
2231    Return the number of rows found by a specified query. This method would
2232    normally be used to count the records in a single table. For example, in a
2233    genetics database
2234    
2235        my $count = $erdb->GetCount(['Genome'], 'Genome(genus-species) LIKE ?', ['homo %']);
2236    
2237    would return the number of genomes for the genus I<homo>. It is conceivable, however,
2238    to use it to return records based on a join. For example,
2239    
2240        my $count = $erdb->GetCount(['HasFeature', 'Genome'], 'Genome(genus-species) LIKE ?',
2241                                    ['homo %']);
2242    
2243    would return the number of features for genomes in the genus I<homo>. Note that
2244    only the rows from the first table are counted. If the above command were
2245    
2246        my $count = $erdb->GetCount(['Genome', 'Feature'], 'Genome(genus-species) LIKE ?',
2247                                    ['homo %']);
2248    
2249    it would return the number of genomes, not the number of genome/feature pairs.
2250    
2251    =over 4
2252    
2253    =item objectNames
2254    
2255    Reference to a list of the objects (entities and relationships) included in the
2256    query.
2257    
2258    =item filter
2259    
2260    A filter clause for restricting the query. The rules are the same as for the L</Get>
2261    method.
2262    
2263    =item params
2264    
2265    Reference to a list of the parameter values to be substituted for the parameter marks
2266    in the filter.
2267    
2268    =item RETURN
2269    
2270    Returns a count of the number of records in the first table that would satisfy
2271    the query.
2272    
2273    =back
2274    
2275    =cut
2276    
2277    sub GetCount {
2278        # Get the parameters.
2279        my ($self, $objectNames, $filter, $params) = @_;
2280        # Insure the params argument is an array reference if the caller left it off.
2281        if (! defined($params)) {
2282            $params = [];
2283        }
2284        # Declare the return variable.
2285        my $retVal;
2286        # Find out if we're counting an entity or a relationship.
2287        my $countedField;
2288        if ($self->IsEntity($objectNames->[0])) {
2289            $countedField = "id";
2290        } else {
2291            # For a relationship we count the to-link because it's usually more
2292            # numerous. Note we're automatically converting to the SQL form
2293            # of the field name (to_link vs. to-link).
2294            $countedField = "to_link";
2295        }
2296        # Create the SQL command suffix to get the desired records.
2297        my ($suffix, $mappedNameListRef, $mappedNameHashRef) = $self->_SetupSQL($objectNames,
2298                                                                                $filter);
2299        # Prefix it with text telling it we want a record count.
2300        my $firstObject = $mappedNameListRef->[0];
2301        my $command = "SELECT COUNT($firstObject.$countedField) $suffix";
2302        # Prepare and execute the command.
2303        my $sth = $self->_GetStatementHandle($command, $params);
2304        # Get the count value.
2305        ($retVal) = $sth->fetchrow_array();
2306        # Check for a problem.
2307        if (! defined($retVal)) {
2308            if ($sth->err) {
2309                # Here we had an SQL error.
2310                Confess("Error retrieving row count: " . $sth->errstr());
2311            } else {
2312                # Here we have no result.
2313                Confess("No result attempting to retrieve row count.");
2314            }
2315        }
2316        # Return the result.
2317        return $retVal;
2318    }
2319    
2320    =head3 ComputeObjectSentence
2321    
2322    C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>
2323    
2324    Check an object name, and if it is a relationship convert it to a relationship sentence.
2325    
2326    =over 4
2327    
2328    =item objectName
2329    
2330    Name of the entity or relationship.
2331    
2332    =item RETURN
2333    
2334    Returns a string containing the entity name or a relationship sentence.
2335    
2336    =back
2337    
2338    =cut
2339    
2340    sub ComputeObjectSentence {
2341        # Get the parameters.
2342        my ($self, $objectName) = @_;
2343        # Set the default return value.
2344        my $retVal = $objectName;
2345        # Look for the object as a relationship.
2346        my $relTable = $self->{_metaData}->{Relationships};
2347        if (exists $relTable->{$objectName}) {
2348            # Get the relationship sentence.
2349            $retVal = _ComputeRelationshipSentence($objectName, $relTable->{$objectName});
2350        }
2351        # Return the result.
2352        return $retVal;
2353    }
2354    
2355    =head3 DumpRelations
2356    
2357    C<< $erdb->DumpRelations($outputDirectory); >>
2358    
2359    Write the contents of all the relations to tab-delimited files in the specified directory.
2360    Each file will have the same name as the relation dumped, with an extension of DTX.
2361    
2362    =over 4
2363    
2364    =item outputDirectory
2365    
2366    Name of the directory into which the relation files should be dumped.
2367    
2368    =back
2369    
2370    =cut
2371    
2372    sub DumpRelations {
2373        # Get the parameters.
2374        my ($self, $outputDirectory) = @_;
2375        # Now we need to run through all the relations. First, we loop through the entities.
2376        my $metaData = $self->{_metaData};
2377        my $entities = $metaData->{Entities};
2378        for my $entityName (keys %{$entities}) {
2379            my $entityStructure = $entities->{$entityName};
2380            # Get the entity's relations.
2381            my $relationList = $entityStructure->{Relations};
2382            # Loop through the relations, dumping them.
2383            for my $relationName (keys %{$relationList}) {
2384                my $relation = $relationList->{$relationName};
2385                $self->_DumpRelation($outputDirectory, $relationName, $relation);
2386            }
2387        }
2388        # Next, we loop through the relationships.
2389        my $relationships = $metaData->{Relationships};
2390        for my $relationshipName (keys %{$relationships}) {
2391            my $relationshipStructure = $relationships->{$relationshipName};
2392            # Dump this relationship's relation.
2393            $self->_DumpRelation($outputDirectory, $relationshipName, $relationshipStructure->{Relations}->{$relationshipName});
2394        }
2395    }
2396    
2397    =head3 InsertValue
2398    
2399    C<< $erdb->InsertValue($entityID, $fieldName, $value); >>
2400    
2401    This method will insert a new value into the database. The value must be one
2402    associated with a secondary relation, since primary values cannot be inserted:
2403    they occur exactly once. Secondary values, on the other hand, can be missing
2404    or multiply-occurring.
2405    
2406    =over 4
2407    
2408    =item entityID
2409    
2410    ID of the object that is to receive the new value.
2411    
2412    =item fieldName
2413    
2414    Field name for the new value-- this includes the entity name, since
2415    field names are of the format I<objectName>C<(>I<fieldName>C<)>.
2416    
2417    =item value
2418    
2419    New value to be put in the field.
2420    
2421    =back
2422    
2423    =cut
2424    
2425    sub InsertValue {
2426        # Get the parameters.
2427        my ($self, $entityID, $fieldName, $value) = @_;
2428        # Parse the entity name and the real field name.
2429        if ($fieldName =~ /^([^(]+)\(([^)]+)\)/) {
2430            my $entityName = $1;
2431            my $fieldTitle = $2;
2432            # Get its descriptor.
2433            if (!$self->IsEntity($entityName)) {
2434                Confess("$entityName is not a valid entity.");
2435            } else {
2436                my $entityData = $self->{_metaData}->{Entities}->{$entityName};
2437                # Find the relation containing this field.
2438                my $fieldHash = $entityData->{Fields};
2439                if (! exists $fieldHash->{$fieldTitle}) {
2440                    Confess("$fieldTitle not found in $entityName.");
2441                } else {
2442                    my $relation = $fieldHash->{$fieldTitle}->{relation};
2443                    if ($relation eq $entityName) {
2444                        Confess("Cannot do InsertValue on primary field $fieldTitle of $entityName.");
2445                    } else {
2446                        # Now we can create an INSERT statement.
2447                        my $dbh = $self->{_dbh};
2448                        my $fixedName = _FixName($fieldTitle);
2449                        my $statement = "INSERT INTO $relation (id, $fixedName) VALUES(?, ?)";
2450                        # Execute the command.
2451                        $dbh->SQL($statement, 0, $entityID, $value);
2452                    }
2453                }
2454            }
2455        } else {
2456            Confess("$fieldName is not a valid field name.");
2457        }
2458    }
2459    
2460    =head3 InsertObject
2461    
2462    C<< $erdb->InsertObject($objectType, \%fieldHash); >>
2463    
2464    Insert an object into the database. The object is defined by a type name and then a hash
2465    of field names to values. Field values in the primary relation are represented by scalars.
2466    (Note that for relationships, the primary relation is the B<only> relation.)
2467    Field values for the other relations comprising the entity are always list references. For
2468    example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases
2469    C<ZP_00210270.1> and C<gi|46206278>.
2470    
2471    C<< $erdb->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>
2472    
2473    The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
2474    property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
2475    
2476    C<< $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>
2477    
2478    =over 4
2479    
2480    =item newObjectType
2481    
2482    Type name of the object to insert.
2483    
2484    =item fieldHash
2485    
2486    Hash of field names to values.
2487    
2488    =back
2489    
2490    =cut
2491    
2492    sub InsertObject {
2493        # Get the parameters.
2494        my ($self, $newObjectType, $fieldHash) = @_;
2495        # Denote that so far we appear successful.
2496        my $retVal = 1;
2497        # Get the database handle.
2498        my $dbh = $self->{_dbh};
2499        # Get the relation list.
2500        my $relationTable = $self->_GetRelationTable($newObjectType);
2501        # Loop through the relations. We'll build insert statements for each one. If a relation is
2502        # secondary, we may end up generating multiple insert statements. If an error occurs, we
2503        # stop the loop.
2504        my @relationList = keys %{$relationTable};
2505        for (my $i = 0; $retVal && $i <= $#relationList; $i++) {
2506            my $relationName = $relationList[$i];
2507            my $relationDefinition = $relationTable->{$relationName};
2508            # Get the relation's fields. For each field we will collect a value in the corresponding
2509            # position of the @valueList array. If one of the fields is missing, we will add it to the
2510            # @missing list.
2511            my @fieldList = @{$relationDefinition->{Fields}};
2512            my @fieldNameList = ();
2513            my @valueList = ();
2514            my @missing = ();
2515            my $recordCount = 1;
2516            for my $fieldDescriptor (@fieldList) {
2517                # Get the field name and save it. Note we need to fix it up so the hyphens
2518                # are converted to underscores.
2519                my $fieldName = $fieldDescriptor->{name};
2520                push @fieldNameList, _FixName($fieldName);
2521                # Look for the named field in the incoming structure. Note that we are looking
2522                # for the real field name, not the fixed-up one!
2523                if (exists $fieldHash->{$fieldName}) {
2524                    # Here we found the field. Stash it in the value list.
2525                    my $value = $fieldHash->{$fieldName};
2526                    push @valueList, $value;
2527                    # If the value is a list, we may need to increment the record count.
2528                    if (ref $value eq "ARRAY") {
2529                        my $thisCount = @{$value};
2530                        if ($recordCount == 1) {
2531                            # Here we have our first list, so we save its count.
2532                            $recordCount = $thisCount;
2533                        } elsif ($recordCount != $thisCount) {
2534                            # Here we have a second list, so its length has to match the
2535                            # previous lists.
2536                            Trace("Field $value in new $newObjectType object has an invalid list length $thisCount. Expected $recordCount.") if T(0);
2537                            $retVal = 0;
2538                        }
2539                    }
2540                } else {
2541                    # Here the field is not present. Flag it as missing.
2542                    push @missing, $fieldName;
2543                }
2544            }
2545            # If we are the primary relation, add the new-record flag.
2546            if ($relationName eq $newObjectType) {
2547                push @valueList, 1;
2548                push @fieldNameList, "new_record";
2549            }
2550            # Only proceed if there are no missing fields.
2551            if (@missing > 0) {
2552                Trace("Relation $relationName for $newObjectType skipped due to missing fields: " .
2553                    join(' ', @missing)) if T(1);
2554            } else {
2555                # Build the INSERT statement.
2556                my $statement = "INSERT INTO $relationName (" . join (', ', @fieldNameList) .
2557                    ") VALUES (";
2558                # Create a marker list of the proper size and put it in the statement.
2559                my @markers = ();
2560                while (@markers < @fieldNameList) { push @markers, '?'; }
2561                $statement .= join(', ', @markers) . ")";
2562                # We have the insert statement, so prepare it.
2563                my $sth = $dbh->prepare_command($statement);
2564                Trace("Insert statement prepared: $statement") if T(3);
2565                # Now we loop through the values. If a value is scalar, we use it unmodified. If it's
2566                # a list, we use the current element. The values are stored in the @parameterList array.
2567                my $done = 0;
2568                for (my $i = 0; $i < $recordCount; $i++) {
2569                    # Clear the parameter list array.
2570                    my @parameterList = ();
2571                    # Loop through the values.
2572                    for my $value (@valueList) {
2573                        # Check to see if this is a scalar value.
2574                        if (ref $value eq "ARRAY") {
2575                            # Here we have a list value. Pull the current entry.
2576                            push @parameterList, $value->[$i];
2577                        } else {
2578                            # Here we have a scalar value. Use it unmodified.
2579                            push @parameterList, $value;
2580                        }
2581                    }
2582                    # Execute the INSERT statement with the specified parameter list.
2583                    $retVal = $sth->execute(@parameterList);
2584                    if (!$retVal) {
2585                        my $errorString = $sth->errstr();
2586                        Confess("Error inserting into $relationName: $errorString");
2587                    } else {
2588                        Trace("Insert successful using $parameterList[0].") if T(3);
2589                    }
2590                }
2591            }
2592        }
2593        # Return a 1 for backward compatability.
2594        return 1;
2595    }
2596    
2597    =head3 UpdateEntity
2598    
2599    C<< $erdb->UpdateEntity($entityName, $id, \%fields); >>
2600    
2601    Update the values of an entity. This is an unprotected update, so it should only be
2602    done if the database resides on a database server.
2603    
2604    =over 4
2605    
2606    =item entityName
2607    
2608    Name of the entity to update. (This is the entity type.)
2609    
2610    =item id
2611    
2612    ID of the entity to update. If no entity exists with this ID, an error will be thrown.
2613    
2614    =item fields
2615    
2616    Reference to a hash mapping field names to their new values. All of the fields named
2617    must be in the entity's primary relation, and they cannot any of them be the ID field.
2618    
2619    =back
2620    
2621    =cut
2622    
2623    sub UpdateEntity {
2624        # Get the parameters.
2625        my ($self, $entityName, $id, $fields) = @_;
2626        # Get a list of the field names being updated.
2627        my @fieldList = keys %{$fields};
2628        # Verify that the fields exist.
2629        my $checker = $self->GetFieldTable($entityName);
2630        for my $field (@fieldList) {
2631            if ($field eq 'id') {
2632                Confess("Cannot update the ID field for entity $entityName.");
2633            } elsif ($checker->{$field}->{relation} ne $entityName) {
2634                Confess("Cannot find $field in primary relation of $entityName.");
2635            }
2636        }
2637        # Build the SQL statement.
2638        my @sets = ();
2639        my @valueList = ();
2640        for my $field (@fieldList) {
2641            push @sets, _FixName($field) . " = ?";
2642            push @valueList, $fields->{$field};
2643        }
2644        my $command = "UPDATE $entityName SET " . join(", ", @sets) . " WHERE id = ?";
2645        # Add the ID to the list of binding values.
2646        push @valueList, $id;
2647        # Call SQL to do the work.
2648        my $rows = $self->{_dbh}->SQL($command, 0, @valueList);
2649        # Check for errors.
2650        if ($rows == 0) {
2651            Confess("Entity $id of type $entityName not found.");
2652        }
2653    }
2654    
2655    =head3 LoadTable
2656    
2657    C<< my $results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>
2658    
2659    Load data from a tab-delimited file into a specified table, optionally re-creating the table
2660    first.
2661    
2662    =over 4
2663    
2664    =item fileName
2665    
2666    Name of the file from which the table data should be loaded.
2667    
2668    =item relationName
2669    
2670    Name of the relation to be loaded. This is the same as the table name.
2671    
2672    =item truncateFlag
2673    
2674    TRUE if the table should be dropped and re-created, else FALSE
2675    
2676    =item RETURN
2677    
2678    Returns a statistical object containing a list of the error messages.
2679    
2680    =back
2681    
2682    =cut
2683    sub LoadTable {
2684        # Get the parameters.
2685        my ($self, $fileName, $relationName, $truncateFlag) = @_;
2686        # Create the statistical return object.
2687        my $retVal = _GetLoadStats();
2688        # Trace the fact of the load.
2689        Trace("Loading table $relationName from $fileName") if T(2);
2690        # Get the database handle.
2691        my $dbh = $self->{_dbh};
2692        # Get the input file size.
2693        my $fileSize = -s $fileName;
2694        # Get the relation data.
2695        my $relation = $self->_FindRelation($relationName);
2696        # Check the truncation flag.
2697        if ($truncateFlag) {
2698            Trace("Creating table $relationName") if T(2);
2699            # Compute the row count estimate. We take the size of the load file,
2700            # divide it by the estimated row size, and then multiply by 1.5 to
2701            # leave extra room. We postulate a minimum row count of 1000 to
2702            # prevent problems with incoming empty load files.
2703            my $rowSize = $self->EstimateRowSize($relationName);
2704            my $estimate = $fileSize * 1.5 / $rowSize;
2705            if ($estimate < 1000) {
2706                $estimate = 1000;
2707            }
2708            # Re-create the table without its index.
2709            $self->CreateTable($relationName, 0, $estimate);
2710            # If this is a pre-index DBMS, create the index here.
2711            if ($dbh->{_preIndex}) {
2712                eval {
2713                    $self->CreateIndex($relationName);
2714                };
2715                if ($@) {
2716                    $retVal->AddMessage($@);
2717                }
2718            }
2719        }
2720        # Load the table.
2721        my $rv;
2722        eval {
2723            $rv = $dbh->load_table(file => $fileName, tbl => $relationName);
2724        };
2725        if (!defined $rv) {
2726            $retVal->AddMessage($@) if ($@);
2727            $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2728            Trace("Table load failed for $relationName.") if T(1);
2729        } else {
2730            # Here we successfully loaded the table.
2731            $retVal->Add("tables");
2732            my $size = -s $fileName;
2733            Trace("$size bytes loaded into $relationName.") if T(2);
2734            # If we're rebuilding, we need to create the table indexes.
2735            if ($truncateFlag) {
2736                # Indexes are created here for PostGres. For PostGres, indexes are
2737                # best built at the end. For MySQL, the reverse is true.
2738                if (! $dbh->{_preIndex}) {
2739                    eval {
2740                        $self->CreateIndex($relationName);
2741                    };
2742                    if ($@) {
2743                        $retVal->AddMessage($@);
2744                    }
2745                }
2746                # The full-text index (if any) is always built last, even for MySQL.
2747                # First we need to see if this table has a full-text index. Only
2748                # primary relations are allowed that privilege.
2749                Trace("Checking for full-text index on $relationName.") if T(2);
2750                if ($self->_IsPrimary($relationName)) {
2751                    $self->CreateSearchIndex($relationName);
2752                }
2753            }
2754        }
2755        # Analyze the table to improve performance.
2756        Trace("Analyzing and compacting $relationName.") if T(3);
2757        $dbh->vacuum_it($relationName);
2758        Trace("$relationName load completed.") if T(3);
2759        # Return the statistics.
2760        return $retVal;
2761    }
2762    
2763    =head3 CreateSearchIndex
2764    
2765    C<< $erdb->CreateSearchIndex($objectName); >>
2766    
2767    Check for a full-text search index on the specified entity or relationship object, and
2768    if one is required, rebuild it.
2769    
2770    =over 4
2771    
2772    =item objectName
2773    
2774    Name of the entity or relationship to be indexed.
2775    
2776    =back
2777    
2778    =cut
2779    
2780    sub CreateSearchIndex {
2781        # Get the parameters.
2782        my ($self, $objectName) = @_;
2783        # Get the relation's entity/relationship structure.
2784        my $structure = $self->_GetStructure($objectName);
2785        # Get the database handle.
2786        my $dbh = $self->{_dbh};
2787        Trace("Checking for search fields in $objectName.") if T(3);
2788        # Check for a searchable fields list.
2789        if (exists $structure->{searchFields}) {
2790            # Here we know that we need to create a full-text search index.
2791            # Get an SQL-formatted field name list.
2792            my $fields = join(", ", _FixNames(@{$structure->{searchFields}}));
2793            # Create the index. If it already exists, it will be dropped.
2794            $dbh->create_index(tbl => $objectName, idx => "search_idx",
2795                               flds => $fields, kind => 'fulltext');
2796            Trace("Index created for $fields in $objectName.") if T(2);
2797        }
2798    }
2799    
2800    =head3 DropRelation
2801    
2802    C<< $erdb->DropRelation($relationName); >>
2803    
2804    Physically drop a relation from the database.
2805    
2806    =over 4
2807    
2808    =item relationName
2809    
2810    Name of the relation to drop. If it does not exist, this method will have
2811    no effect.
2812    
2813    =back
2814    
2815    =cut
2816    
2817    sub DropRelation {
2818        # Get the parameters.
2819        my ($self, $relationName) = @_;
2820        # Get the database handle.
2821        my $dbh = $self->{_dbh};
2822        # Drop the relation. The method used here has no effect if the relation
2823        # does not exist.
2824        Trace("Invoking DB Kernel to drop $relationName.") if T(3);
2825        $dbh->drop_table(tbl => $relationName);
2826    }
2827    
2828    =head3 MatchSqlPattern
2829    
2830    C<< my $matched = ERDB::MatchSqlPattern($value, $pattern); >>
2831    
2832    Determine whether or not a specified value matches an SQL pattern. An SQL
2833    pattern has two wild card characters: C<%> that matches multiple characters,
2834    and C<_> that matches a single character. These can be escaped using a
2835    backslash (C<\>). We pull this off by converting the SQL pattern to a
2836    PERL regular expression. As per SQL rules, the match is case-insensitive.
2837    
2838    =over 4
2839    
2840    =item value
2841    
2842    Value to be matched against the pattern. Note that an undefined or empty
2843    value will not match anything.
2844    
2845    =item pattern
2846    
2847    SQL pattern against which to match the value. An undefined or empty pattern will
2848    match everything.
2849    
2850    =item RETURN
2851    
2852    Returns TRUE if the value and pattern match, else FALSE.
2853    
2854    =back
2855    
2856    =cut
2857    
2858    sub MatchSqlPattern {
2859        # Get the parameters.
2860        my ($value, $pattern) = @_;
2861        # Declare the return variable.
2862        my $retVal;
2863        # Insure we have a pattern.
2864        if (! defined($pattern) || $pattern eq "") {
2865            $retVal = 1;
2866        } else {
2867            # Break the pattern into pieces around the wildcard characters. Because we
2868            # use parentheses in the split function's delimiter expression, we'll get
2869            # list elements for the delimiters as well as the rest of the string.
2870            my @pieces = split /([_%]|\\[_%])/, $pattern;
2871            # Check some fast special cases.
2872            if ($pattern eq '%') {
2873                # A null pattern matches everything.
2874                $retVal = 1;
2875            } elsif (@pieces == 1) {
2876                # No wildcards, so we have a literal comparison. Note we're case-insensitive.
2877                $retVal = (lc($value) eq lc($pattern));
2878            } elsif (@pieces == 2 && $pieces[1] eq '%') {
2879                # A wildcard at the end, so we have a substring match. This is also case-insensitive.
2880                $retVal = (lc(substr($value, 0, length($pieces[0]))) eq lc($pieces[0]));
2881            } else {
2882                # Okay, we have to do it the hard way. Convert each piece to a PERL pattern.
2883                my $realPattern = "";
2884                for my $piece (@pieces) {
2885                    # Determine the type of piece.
2886                    if ($piece eq "") {
2887                        # Empty pieces are ignored.
2888                    } elsif ($piece eq "%") {
2889                        # Here we have a multi-character wildcard. Note that it can match
2890                        # zero or more characters.
2891                        $realPattern .= ".*"
2892                    } elsif ($piece eq "_") {
2893                        # Here we have a single-character wildcard.
2894                        $realPattern .= ".";
2895                    } elsif ($piece eq "\\%" || $piece eq "\\_") {
2896                        # This is an escape sequence (which is a rare thing, actually).
2897                        $realPattern .= substr($piece, 1, 1);
2898                    } else {
2899                        # Here we have raw text.
2900                        $realPattern .= quotemeta($piece);
2901                    }
2902                }
2903                # Do the match.
2904                $retVal = ($value =~ /^$realPattern$/i ? 1 : 0);
2905            }
2906        }
2907        # Return the result.
2908        return $retVal;
2909    }
2910    
2911    =head3 GetEntity
2912    
2913    C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>
2914    
2915    Return an object describing the entity instance with a specified ID.
2916    
2917    =over 4
2918    
2919    =item entityType
2920    
2921    Entity type name.
2922    
2923    =item ID
2924    
2925    ID of the desired entity.
2926    
2927    =item RETURN
2928    
2929    Returns a B<ERDBObject> representing the desired entity instance, or an undefined value if no
2930    instance is found with the specified key.
2931    
2932    =back
2933    
2934    =cut
2935    
2936    sub GetEntity {
2937        # Get the parameters.
2938        my ($self, $entityType, $ID) = @_;
2939        # Create a query.
2940        my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);
2941        # Get the first (and only) object.
2942        my $retVal = $query->Fetch();
2943        # Return the result.
2944        return $retVal;
2945    }
2946    
2947    =head3 GetChoices
2948    
2949    C<< my @values = $erdb->GetChoices($entityName, $fieldName); >>
2950    
2951    Return a list of all the values for the specified field that are represented in the
2952    specified entity.
2953    
2954    Note that if the field is not indexed, then this will be a very slow operation.
2955    
2956    =over 4
2957    
2958    =item entityName
2959    
2960    Name of an entity in the database.
2961    
2962    =item fieldName
2963    
2964    Name of a field belonging to the entity. This is a raw field name without
2965    the standard parenthesized notation used in most calls.
2966    
2967    =item RETURN
2968    
2969    Returns a list of the distinct values for the specified field in the database.
2970    
2971    =back
2972    
2973    =cut
2974    
2975    sub GetChoices {
2976        # Get the parameters.
2977        my ($self, $entityName, $fieldName) = @_;
2978        # Declare the return variable.
2979        my @retVal;
2980        # Get the entity data structure.
2981        my $entityData = $self->_GetStructure($entityName);
2982        # Get the field.
2983        my $fieldHash = $entityData->{Fields};
2984        if (! exists $fieldHash->{$fieldName}) {
2985            Confess("$fieldName not found in $entityName.");
2986        } else {
2987            # Get the name of the relation containing the field.
2988            my $relation = $fieldHash->{$fieldName}->{relation};
2989            # Fix up the field name.
2990            my $realName = _FixName($fieldName);
2991            # Get the database handle.
2992            my $dbh = $self->{_dbh};
2993            # Query the database.
2994            my $results = $dbh->SQL("SELECT DISTINCT $realName FROM $relation");
2995            # Clean the results. They are stored as a list of lists, and we just want the one list.
2996            @retVal = sort map { $_->[0] } @{$results};
2997        }
2998        # Return the result.
2999        return @retVal;
3000    }
3001    
3002    =head3 GetEntityValues
3003    
3004    C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>
3005    
3006    Return a list of values from a specified entity instance. If the entity instance
3007    does not exist, an empty list is returned.
3008    
3009    =over 4
3010    
3011    =item entityType
3012    
3013    Entity type name.
3014    
3015    =item ID
3016    
3017    ID of the desired entity.
3018    
3019    =item fields
3020    
3021    List of field names, each of the form I<objectName>C<(>I<fieldName>C<)>.
3022    
3023    =item RETURN
3024    
3025    Returns a flattened list of the values of the specified fields for the specified entity.
3026    
3027    =back
3028    
3029    =cut
3030    
3031    sub GetEntityValues {
3032        # Get the parameters.
3033        my ($self, $entityType, $ID, $fields) = @_;
3034        # Get the specified entity.
3035        my $entity = $self->GetEntity($entityType, $ID);
3036        # Declare the return list.
3037        my @retVal = ();
3038        # If we found the entity, push the values into the return list.
3039        if ($entity) {
3040            push @retVal, $entity->Values($fields);
3041        }
3042        # Return the result.
3043        return @retVal;
3044    }
3045    
3046    =head3 GetAll
3047    
3048    C<< my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>
3049    
3050    Return a list of values taken from the objects returned by a query. The first three
3051    parameters correspond to the parameters of the L</Get> method. The final parameter is
3052    a list of the fields desired from each record found by the query. The field name
3053    syntax is the standard syntax used for fields in the B<ERDB> system--
3054    B<I<objectName>(I<fieldName>)>-- where I<objectName> is the name of the relevant entity
3055    or relationship and I<fieldName> is the name of the field.
3056    
3057    The list returned will be a list of lists. Each element of the list will contain
3058    the values returned for the fields specified in the fourth parameter. If one of the
3059    fields specified returns multiple values, they are flattened in with the rest. For
3060    example, the following call will return a list of the features in a particular
3061    spreadsheet cell, and each feature will be represented by a list containing the
3062    feature ID followed by all of its aliases.
3063    
3064    C<< @query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>
3065    
3066    =over 4
3067    
3068    =item objectNames
3069    
3070    List containing the names of the entity and relationship objects to be retrieved.
3071    
3072    =item filterClause
3073    
3074    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
3075    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
3076    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
3077    parameter list as additional parameters. The fields in a filter clause can come from primary
3078    entity relations, relationship relations, or secondary entity relations; however, all of the
3079    entities and relationships involved must be included in the list of object names.
3080    
3081    =item parameterList
3082    
3083    List of the parameters to be substituted in for the parameters marks in the filter clause.
3084    
3085    =item fields
3086    
3087    List of the fields to be returned in each element of the list returned.
3088    
3089    =item count
3090    
3091    Maximum number of records to return. If omitted or 0, all available records will be returned.
3092    
3093    =item RETURN
3094    
3095    Returns a list of list references. Each element of the return list contains the values for the
3096    fields specified in the B<fields> parameter.
3097    
3098    =back
3099    
3100    =cut
3101    #: Return Type @@;
3102    sub GetAll {
3103        # Get the parameters.
3104        my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
3105        # Translate the parameters from a list reference to a list. If the parameter
3106        # list is a scalar we convert it into a singleton list.
3107        my @parmList = ();
3108        if (ref $parameterList eq "ARRAY") {
3109            Trace("GetAll parm list is an array.") if T(4);
3110            @parmList = @{$parameterList};
3111        } else {
3112            Trace("GetAll parm list is a scalar: $parameterList.") if T(4);
3113            push @parmList, $parameterList;
3114        }
3115        # Insure the counter has a value.
3116        if (!defined $count) {
3117            $count = 0;
3118        }
3119        # Add the row limit to the filter clause.
3120        if ($count > 0) {
3121            $filterClause .= " LIMIT $count";
3122        }
3123        # Create the query.
3124        my $query = $self->Get($objectNames, $filterClause, \@parmList);
3125        # Set up a counter of the number of records read.
3126        my $fetched = 0;
3127        # Loop through the records returned, extracting the fields. Note that if the
3128        # counter is non-zero, we stop when the number of records read hits the count.
3129        my @retVal = ();
3130        while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {
3131            my @rowData = $row->Values($fields);
3132            push @retVal, \@rowData;
3133            $fetched++;
3134        }
3135        Trace("$fetched rows returned in GetAll.") if T(SQL => 4);
3136        # Return the resulting list.
3137        return @retVal;
3138    }
3139    
3140    =head3 Exists
3141    
3142    C<< my $found = $sprout->Exists($entityName, $entityID); >>
3143    
3144    Return TRUE if an entity exists, else FALSE.
3145    
3146    =over 4
3147    
3148    =item entityName
3149    
3150    Name of the entity type (e.g. C<Feature>) relevant to the existence check.
3151    
3152    =item entityID
3153    
3154    ID of the entity instance whose existence is to be checked.
3155    
3156    =item RETURN
3157    
3158    Returns TRUE if the entity instance exists, else FALSE.
3159    
3160    =back
3161    
3162    =cut
3163    #: Return Type $;
3164    sub Exists {
3165        # Get the parameters.
3166        my ($self, $entityName, $entityID) = @_;
3167        # Check for the entity instance.
3168        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
3169        my $testInstance = $self->GetEntity($entityName, $entityID);
3170        # Return an existence indicator.
3171        my $retVal = ($testInstance ? 1 : 0);
3172        return $retVal;
3173    }
3174    
3175    =head3 EstimateRowSize
3176    
3177    C<< my $rowSize = $erdb->EstimateRowSize($relName); >>
3178    
3179    Estimate the row size of the specified relation. The estimated row size is computed by adding
3180    up the average length for each data type.
3181    
3182    =over 4
3183    
3184    =item relName
3185    
3186    Name of the relation whose estimated row size is desired.
3187    
3188    =item RETURN
3189    
3190    Returns an estimate of the row size for the specified relation.
3191    
3192    =back
3193    
3194    =cut
3195    #: Return Type $;
3196    sub EstimateRowSize {
3197        # Get the parameters.
3198        my ($self, $relName) = @_;
3199        # Declare the return variable.
3200        my $retVal = 0;
3201        # Find the relation descriptor.
3202        my $relation = $self->_FindRelation($relName);
3203        # Get the list of fields.
3204        for my $fieldData (@{$relation->{Fields}}) {
3205            # Get the field type and add its length.
3206            my $fieldLen = $TypeTable{$fieldData->{type}}->{avgLen};
3207            $retVal += $fieldLen;
3208        }
3209        # Return the result.
3210        return $retVal;
3211    }
3212    
3213    =head3 GetFieldTable
3214    
3215    C<< my $fieldHash = $self->GetFieldTable($objectnName); >>
3216    
3217    Get the field structure for a specified entity or relationship.
3218    
3219    =over 4
3220    
3221    =item objectName
3222    
3223    Name of the desired entity or relationship.
3224    
3225    =item RETURN
3226    
3227    The table containing the field descriptors for the specified object.
3228    
3229    =back
3230    
3231    =cut
3232    
3233    sub GetFieldTable {
3234        # Get the parameters.
3235        my ($self, $objectName) = @_;
3236        # Get the descriptor from the metadata.
3237        my $objectData = $self->_GetStructure($objectName);
3238        # Return the object's field table.
3239        return $objectData->{Fields};
3240    }
3241    
3242    =head3 SplitKeywords
3243    
3244    C<< my @keywords = ERDB::SplitKeywords($keywordString); >>
3245    
3246    This method returns a list of the positive keywords in the specified
3247    keyword string. All of the operators will have been stripped off,
3248    and if the keyword is preceded by a minus operator (C<->), it will
3249    not be in the list returned. The idea here is to get a list of the
3250    keywords the user wants to see. The list will be processed to remove
3251    duplicates.
3252    
3253    It is possible to create a string that confuses this method. For example
3254    
3255        frog toad -frog
3256    
3257    would return both C<frog> and C<toad>. If this is a problem we can deal
3258    with it later.
3259    
3260    =over 4
3261    
3262    =item keywordString
3263    
3264    The keyword string to be parsed.
3265    
3266    =item RETURN
3267    
3268    Returns a list of the words in the keyword string the user wants to
3269    see.
3270    
3271    =back
3272    
3273    =cut
3274    
3275    sub SplitKeywords {
3276        # Get the parameters.
3277        my ($keywordString) = @_;
3278        # Make a safety copy of the string. (This helps during debugging.)
3279        my $workString = $keywordString;
3280        # Convert operators we don't care about to spaces.
3281        $workString =~ tr/+"()<>/ /;
3282        # Split the rest of the string along space boundaries. Note that we
3283        # eliminate any words that are zero length or begin with a minus sign.
3284        my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
3285        # Use a hash to remove duplicates.
3286        my %words = map { $_ => 1 } @wordList;
3287        # Return the result.
3288        return sort keys %words;
3289    }
3290    
3291    =head3 ValidateFieldName
3292    
3293    C<< my $okFlag = ERDB::ValidateFieldName($fieldName); >>
3294    
3295    Return TRUE if the specified field name is valid, else FALSE. Valid field names must
3296    be hyphenated words subject to certain restrictions.
3297    
3298    =over 4
3299    
3300    =item fieldName
3301    
3302    Field name to be validated.
3303    
3304    =item RETURN
3305    
3306    Returns TRUE if the field name is valid, else FALSE.
3307    
3308    =back
3309    
3310    =cut
3311    
3312    sub ValidateFieldName {
3313        # Get the parameters.
3314        my ($fieldName) = @_;
3315        # Declare the return variable. The field name is valid until we hear
3316        # differently.
3317        my $retVal = 1;
3318        # Compute the maximum name length.
3319        my $maxLen = $TypeTable{'name-string'}->{maxLen};
3320        # Look for bad stuff in the name.
3321        if ($fieldName =~ /--/) {
3322            # Here we have a doubled minus sign.
3323            Trace("Field name $fieldName has a doubled hyphen.") if T(1);
3324            $retVal = 0;
3325        } elsif ($fieldName !~ /^[A-Za-z]/) {
3326            # Here the field name is missing the initial letter.
3327            Trace("Field name $fieldName does not begin with a letter.") if T(1);
3328            $retVal = 0;
3329        } elsif (length($fieldName) > $maxLen) {
3330            # Here the field name is too long.
3331            Trace("Maximum field name length is $maxLen. Field name must be truncated to " . substr($fieldName,0, $maxLen) . ".");
3332        } else {
3333            # Strip out the minus signs. Everything remaining must be a letter,
3334            # underscore, or digit.
3335            my $strippedName = $fieldName;
3336            $strippedName =~ s/-//g;
3337            if ($strippedName !~ /^(\w|\d)+$/) {
3338                Trace("Field name $fieldName contains illegal characters.") if T(1);
3339                $retVal = 0;
3340            }
3341        }
3342        # Return the result.
3343        return $retVal;
3344    }
3345    
3346    =head3 ReadMetaXML
3347    
3348    C<< my $rawMetaData = ERDB::ReadDBD($fileName); >>
3349    
3350    This method reads a raw database definition XML file and returns it.
3351    Normally, the metadata used by the ERDB system has been processed and
3352    modified to make it easier to load and retrieve the data; however,
3353    this method can be used to get the data in its raw form.
3354    
3355    =over 4
3356    
3357    =item fileName
3358    
3359    Name of the XML file to read.
3360    
3361    =item RETURN
3362    
3363    Returns a hash reference containing the raw XML data from the specified file.
3364    
3365    =back
3366    
3367    =cut
3368    
3369    sub ReadMetaXML {
3370        # Get the parameters.
3371        my ($fileName) = @_;
3372        # Read the XML.
3373        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
3374        Trace("XML metadata loaded from file $fileName.") if T(1);
3375        # Return the result.
3376        return $retVal;
3377    }
3378    
3379    =head3 GetEntityFieldHash
3380    
3381    C<< my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName); >>
3382    
3383    Get the field hash of the named entity in the specified raw XML structure.
3384    The field hash may not exist, in which case we need to create it.
3385    
3386    =over 4
3387    
3388    =item structure
3389    
3390    Raw XML structure defininng the database. This is not the run-time XML used by
3391    an ERDB object, since that has all sorts of optimizations built-in.
3392    
3393    =item entityName
3394    
3395    Name of the entity whose field structure is desired.
3396    
3397    =item RETURN
3398    
3399    Returns the field hash used to define the entity's fields.
3400    
3401    =back
3402    
3403    =cut
3404    
3405    sub GetEntityFieldHash {
3406        # Get the parameters.
3407        my ($structure, $entityName) = @_;
3408        # Get the entity structure.
3409        my $entityData = $structure->{Entities}->{$entityName};
3410        # Look for a field structure.
3411        my $retVal = $entityData->{Fields};
3412        # If it doesn't exist, create it.
3413        if (! defined($retVal)) {
3414            $entityData->{Fields} = {};
3415            $retVal = $entityData->{Fields};
3416        }
3417        # Return the result.
3418        return $retVal;
3419    }
3420    
3421    =head3 WriteMetaXML
3422    
3423    C<< ERDB::WriteMetaXML($structure, $fileName); >>
3424    
3425    Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
3426    used to update the database definition. It must be used with care, however, since it
3427    will only work on a raw structure, not on the processed structure created by an ERDB
3428    constructor.
3429    
3430    =over 4
3431    
3432    =item structure
3433    
3434    XML structure to be written to the file.
3435    
3436    =item fileName
3437    
3438    Name of the output file to which the updated XML should be stored.
3439    
3440    =back
3441    
3442    =cut
3443    
3444    sub WriteMetaXML {
3445        # Get the parameters.
3446        my ($structure, $fileName) = @_;
3447        # Compute the output.
3448        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
3449        # Write it to the file.
3450        my $xmlOut = Open(undef, ">$fileName");
3451        print $xmlOut $fileString;
3452    }
3453    
3454    
3455    =head3 HTMLNote
3456    
3457    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
3458    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
3459    Except for C<[p]>, all the codes are closed by slash-codes. So, for
3460    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
3461    
3462    C<< my $realHtml = ERDB::HTMLNote($dataString); >>
3463    
3464    =over 4
3465    
3466    =item dataString
3467    
3468    String to convert to HTML.
3469    
3470    =item RETURN
3471    
3472    An HTML string derived from the input string.
3473    
3474    =back
3475    
3476    =cut
3477    
3478    sub HTMLNote {
3479        # Get the parameter.
3480        my ($dataString) = @_;
3481        # HTML-escape the text.
3482        my $retVal = CGI::escapeHTML($dataString);
3483        # Substitute the bulletin board codes.
3484        $retVal =~ s!\[(/?[bi])\]!<$1>!g;
3485        $retVal =~ s!\[p\]!</p><p>!g;
3486        $retVal =~ s!\[link\s+([^\]]+)\]!<a href="$1">!g;
3487        $retVal =~ s!\[/link\]!</a>!g;
3488        # Return the result.
3489        return $retVal;
3490    }
3491    
3492    =head3 BeginTran
3493    
3494    C<< $erdb->BeginTran(); >>
3495    
3496    Start a database transaction.
3497    
3498    =cut
3499    
3500    sub BeginTran {
3501        my ($self) = @_;
3502        $self->{_dbh}->begin_tran();
3503    
3504    }
3505    
3506    =head3 CommitTran
3507    
3508    C<< $erdb->CommitTran(); >>
3509    
3510    Commit an active database transaction.
3511    
3512    =cut
3513    
3514    sub CommitTran {
3515        my ($self) = @_;
3516        $self->{_dbh}->commit_tran();
3517    }
3518    
3519    =head3 RollbackTran
3520    
3521    C<< $erdb->RollbackTran(); >>
3522    
3523    Roll back an active database transaction.
3524    
3525    =cut
3526    
3527    sub RollbackTran {
3528        my ($self) = @_;
3529        $self->{_dbh}->roll_tran();
3530    }
3531    
3532    =head3 UpdateField
3533    
3534    C<< my $count = $erdb->UpdateField($objectNames, $fieldName, $oldValue, $newValue, $filter, $parms); >>
3535    
3536    Update all occurrences of a specific field value to a new value. The number of rows changed will be
3537    returned.
3538    
3539    =over 4
3540    
3541    =item fieldName
3542    
3543    Name of the field in standard I<objectName>C<(>I<fieldName>C<)> format.
3544    
3545    =item oldValue
3546    
3547    Value to be modified. All occurrences of this value in the named field will be replaced by the
3548    new value.
3549    
3550    =item newValue
3551    
3552    New value to be substituted for the old value when it's found.
3553    
3554    =item filter
3555    
3556    A standard ERDB filter clause (see L</Get>). The filter will be applied before any substitutions take place.
3557    
3558    =item parms
3559    
3560    Reference to a list of parameter values in the filter.
3561    
3562    =item RETURN
3563    
3564    Returns the number of rows modified.
3565    
3566    =back
3567    
3568    =cut
3569    
3570    sub UpdateField {
3571        # Get the parameters.
3572        my ($self, $fieldName, $oldValue, $newValue, $filter, $parms) = @_;
3573        # Get the object and field names from the field name parameter.
3574        $fieldName =~ /^([^(]+)\(([^)]+)\)/;
3575        my $objectName = $1;
3576        my $realFieldName = _FixName($2);
3577        # Add the old value to the filter. Note we allow the possibility that no
3578        # filter was specified.
3579        my $realFilter = "$fieldName = ?";
3580        if ($filter) {
3581            $realFilter .= " AND $filter";
3582        }
3583        # Format the query filter.
3584        my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
3585            $self->_SetupSQL([$objectName], $realFilter);
3586        # Create the query. Since there is only one object name, the mapped-name data is not
3587        # necessary. Neither is the FROM clause.
3588        $suffix =~ s/^FROM.+WHERE\s+//;
3589        # Create the update statement.
3590        my $command = "UPDATE $objectName SET $realFieldName = ? WHERE $suffix";
3591        # Get the database handle.
3592        my $dbh = $self->{_dbh};
3593        # Add the old and new values to the parameter list. Note we allow the possibility that
3594        # there are no user-supplied parameters.
3595        my @params = ($newValue, $oldValue);
3596        if (defined $parms) {
3597            push @params, @{$parms};
3598        }
3599        # Execute the update.
3600        my $retVal = $dbh->SQL($command, 0, @params);
3601        # Make the funky zero a real zero.
3602        if ($retVal == 0) {
3603            $retVal = 0;
3604        }
3605        # Return the result.
3606        return $retVal;
3607    }
3608    
3609    
3610    =head2 Data Mining Methods
3611    
3612    =head3 GetUsefulCrossValues
3613    
3614    C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>
3615    
3616    Return a list of the useful attributes that would be returned by a B<Cross> call
3617    from an entity of the source entity type through the specified relationship. This
3618    means it will return the fields of the target entity type and the intersection data
3619    fields in the relationship. Only primary table fields are returned. In other words,
3620    the field names returned will be for fields where there is always one and only one
3621    value.
3622    
3623    =over 4
3624    
3625    =item sourceEntity
3626    
3627    Name of the entity from which the relationship crossing will start.
3628    
3629    =item relationship
3630    
3631    Name of the relationship being crossed.
3632    
3633    =item RETURN
3634    
3635    Returns a list of field names in Sprout field format (I<objectName>C<(>I<fieldName>C<)>.
3636    
3637    =back
3638    
3639    =cut
3640    #: Return Type @;
3641    sub GetUsefulCrossValues {
3642        # Get the parameters.
3643        my ($self, $sourceEntity, $relationship) = @_;
3644        # Declare the return variable.
3645        my @retVal = ();
3646        # Determine the target entity for the relationship. This is whichever entity is not
3647        # the source entity. So, if the source entity is the FROM, we'll get the name of
3648        # the TO, and vice versa.
3649        my $relStructure = $self->_GetStructure($relationship);
3650        my $targetEntityType = ($relStructure->{from} eq $sourceEntity ? "to" : "from");
3651        my $targetEntity = $relStructure->{$targetEntityType};
3652        # Get the field table for the entity.
3653        my $entityFields = $self->GetFieldTable($targetEntity);
3654        # The field table is a hash. The hash key is the field name. The hash value is a structure.
3655        # For the entity fields, the key aspect of the target structure is that the {relation} value
3656        # must match the entity name.
3657        my @fieldList = map { "$targetEntity($_)" } grep { $entityFields->{$_}->{relation} eq $targetEntity }
3658                            keys %{$entityFields};
3659        # Push the fields found onto the return variable.
3660        push @retVal, sort @fieldList;
3661        # Get the field table for the relationship.
3662        my $relationshipFields = $self->GetFieldTable($relationship);
3663        # Here we have a different rule. We want all the fields other than "from-link" and "to-link".
3664        # This may end up being an empty set.
3665        my @fieldList2 = map { "$relationship($_)" } grep { $_ ne "from-link" && $_ ne "to-link" }
3666                            keys %{$relationshipFields};
3667        # Push these onto the return list.
3668        push @retVal, sort @fieldList2;
3669        # Return the result.
3670        return @retVal;
3671    }
3672    
3673    =head3 FindColumn
3674    
3675    C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>
3676    
3677    Return the location a desired column in a data mining header line. The data
3678    mining header line is a tab-separated list of column names. The column
3679    identifier is either the numerical index of a column or the actual column
3680    name.
3681    
3682    =over 4
3683    
3684    =item headerLine
3685    
3686    The header line from a data mining command, which consists of a tab-separated
3687    list of column names.
3688    
3689    =item columnIdentifier
3690    
3691    Either the ordinal number of the desired column (1-based), or the name of the
3692    desired column.
3693    
3694    =item RETURN
3695    
3696    Returns the array index (0-based) of the desired column.
3697    
3698    =back
3699    
3700    =cut
3701    
3702    sub FindColumn {
3703        # Get the parameters.
3704        my ($headerLine, $columnIdentifier) = @_;
3705        # Declare the return variable.
3706        my $retVal;
3707        # Split the header line into column names.
3708        my @headers = ParseColumns($headerLine);
3709        # Determine whether we have a number or a name.
3710        if ($columnIdentifier =~ /^\d+$/) {
3711            # Here we have a number. Subtract 1 and validate the result.
3712            $retVal = $columnIdentifier - 1;
3713            if ($retVal < 0 || $retVal > $#headers) {
3714                Confess("Invalid column identifer \"$columnIdentifier\": value out of range.");
3715            }
3716        } else {
3717            # Here we have a name. We need to find it in the list.
3718            for (my $i = 0; $i <= $#headers && ! defined($retVal); $i++) {
3719                if ($headers[$i] eq $columnIdentifier) {
3720                    $retVal = $i;
3721                }
3722            }
3723            if (! defined($retVal)) {
3724                Confess("Invalid column identifier \"$columnIdentifier\": value not found.");
3725            }
3726        }
3727        # Return the result.
3728        return $retVal;
3729    }
3730    
3731    =head3 ParseColumns
3732    
3733    C<< my @columns = ERDB::ParseColumns($line); >>
3734    
3735    Convert the specified data line to a list of columns.
3736    
3737    =over 4
3738    
3739    =item line
3740    
3741    A data mining input, consisting of a tab-separated list of columns terminated by a
3742    new-line.
3743    
3744    =item RETURN
3745    
3746    Returns a list consisting of the column values.
3747    
3748    =back
3749    
3750    =cut
3751    
3752    sub ParseColumns {
3753        # Get the parameters.
3754        my ($line) = @_;
3755        # Chop off the line-end.
3756        chomp $line;
3757        # Split it into a list.
3758        my @retVal = split(/\t/, $line);
3759        # Return the result.
3760        return @retVal;
3761    }
3762    
3763    =head2 Virtual Methods
3764    
3765    =head3 _CreatePPOIndex
3766    
3767    C<< my $index = ERDB::_CreatePPOIndex($indexObject); >>
3768    
3769    Convert the XML for an ERDB index to the XML structure for a PPO
3770    index.
3771    
3772    =over 4
3773    
3774    ERDB XML structure for an index.
3775    
3776    =item RETURN
3777    
3778    PPO XML structure for the same index.
3779    
3780    =back
3781    
3782    =cut
3783    
3784    sub _CreatePPOIndex {
3785        # Get the parameters.
3786        my ($indexObject) = @_;
3787        # The incoming index contains a list of the index fields in the IndexFields
3788        # member. We loop through it to create the index tags.
3789        my @fields = map { { label => _FixName($_->{name}) } } @{$indexObject->{IndexFields}};
3790        # Wrap the fields in attribute tags.
3791        my $retVal = { attribute => \@fields };
3792        # Return the result.
3793        return $retVal;
3794    }
3795    
3796    =head3 _CreatePPOField
3797    
3798    C<< my $fieldXML = ERDB::_CreatePPOField($fieldName, $fieldObject); >>
3799    
3800    Convert the ERDB XML structure for a field to a PPO scalar XML structure.
3801    
3802    =over 4
3803    
3804    =item fieldName
3805    
3806    Name of the scalar field.
3807    
3808    =item fieldObject
3809    
3810  Type name for the new entity.  ERDB XML structure describing the field.
3811    
3812  =item values  =item RETURN
3813    
3814  Hash containing additional values that might be needed by the data generation methods (optional).  Returns a PPO XML structure for the same field.
3815    
3816  =back  =back
3817    
3818  =cut  =cut
3819    
3820  sub GenerateEntity {  sub _CreatePPOField {
3821      # Get the parameters.      # Get the parameters.
3822      my ($self, $id, $type, $values) = @_;      my ($fieldName, $fieldObject) = @_;
3823      # Create the return hash.      # Get the field type.
3824      my $this = { id => $id };      my $type = $TypeTable{$fieldObject->{type}}->{sqlType};
3825      # Get the metadata structure.      # Fix up the field name.
3826      my $metadata = $self->{_metaData};      $fieldName = _FixName($fieldName);
3827      # Get this entity's list of fields.      # Build the scalar tag.
3828      if (!exists $metadata->{Entities}->{$type}) {      my $retVal = { label => $fieldName, type => $type };
3829          Confess("Unrecognized entity type $type in GenerateEntity.");      # Return the result.
3830      } 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;  
3831  }  }
3832    
3833  =head3 GetEntity  =head3 CleanKeywords
3834    
3835  C<< my $entityObject = $sprout->GetEntity($entityType, $ID); >>  C<< my $cleanedString = $erdb->CleanKeywords($searchExpression); >>
3836    
3837  Return an object describing the entity instance with a specified ID.  Clean up a search expression or keyword list. This is a virtual method that may
3838    be overridden by the subclass. The base-class method removes extra spaces
3839    and converts everything to lower case.
3840    
3841  =over 4  =over 4
3842    
3843  =item entityType  =item searchExpression
   
 Entity type name.  
   
 =item ID  
3844  </