[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 1.92, Mon Jun 11 18:51:23 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                     'long-string' =>
376                                 { sqlType => 'VARCHAR(500)',       maxLen => 500,          avglen => 255, sort => "",
377                                   indexMod =>   0, notes => "character string, 0 to 500 characters"},
378                  );                  );
379    
380  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 322  Line 383 
383                     'MM' => 'many-to-many'                     'MM' => 'many-to-many'
384                   );                   );
385    
386  # Table for interpreting string patterns.  # Options for XML input and output.
387    
388    my %XmlOptions = (GroupTags =>  { Relationships => 'Relationship',
389                                      Entities => 'Entity',
390                                      Fields => 'Field',
391                                      Indexes => 'Index',
392                                      IndexFields => 'IndexField'
393                                    },
394                      KeyAttr =>    { Relationship => 'name',
395                                      Entity => 'name',
396                                      Field => 'name'
397                                    },
398                      SuppressEmpty => 1,
399                     );
400    
401  my %PictureTable = ( 'A' => "abcdefghijklmnopqrstuvwxyz",  my %XmlInOpts  = (
402                       '9' => "0123456789",                    ForceArray => ['Field', 'Index', 'IndexField', 'Relationship', 'Entity'],
403                       'X' => "abcdefghijklmnopqrstuvwxyz0123456789",                    ForceContent => 1,
404                       'V' => "aeiou",                    NormalizeSpace => 2,
                      'K' => "bcdfghjklmnoprstvwxyz"  
405                     );                     );
406    my %XmlOutOpts = (
407                      RootName => 'Database',
408                      XMLDecl => 1,
409                     );
410    
411    
412  =head2 Public Methods  =head2 Public Methods
413    
# Line 369  Line 447 
447    
448  =head3 ShowMetaData  =head3 ShowMetaData
449    
450  C<< $database->ShowMetaData($fileName); >>  C<< $erdb->ShowMetaData($fileName); >>
451    
452  This method outputs a description of the database. This description can be used to help users create  This method outputs a description of the database. This description can be used to help users create
453  the data to be loaded into the relations.  the data to be loaded into the relations.
# Line 400  Line 478 
478      # Write the HTML heading stuff.      # Write the HTML heading stuff.
479      print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";      print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";
480      print HTMLOUT "</head>\n<body>\n";      print HTMLOUT "</head>\n<body>\n";
481        # Write the documentation.
482        print HTMLOUT $self->DisplayMetaData();
483        # Close the document.
484        print HTMLOUT "</body>\n</html>\n";
485        # Close the file.
486        close HTMLOUT;
487    }
488    
489    =head3 DisplayMetaData
490    
491    C<< my $html = $erdb->DisplayMetaData(); >>
492    
493    Return an HTML description of the database. This description can be used to help users create
494    the data to be loaded into the relations and form queries. The output is raw includable HTML
495    without any HEAD or BODY tags.
496    
497    =over 4
498    
499    =item filename
500    
501    The name of the output file.
502    
503    =back
504    
505    =cut
506    
507    sub DisplayMetaData {
508        # Get the parameters.
509        my ($self) = @_;
510        # Get the metadata and the title string.
511        my $metadata = $self->{_metaData};
512        # Get the title string.
513        my $title = $metadata->{Title};
514        # Get the entity and relationship lists.
515        my $entityList = $metadata->{Entities};
516        my $relationshipList = $metadata->{Relationships};
517        # Declare the return variable.
518        my $retVal = "";
519        # Open the output file.
520        Trace("Building MetaData table of contents.") if T(4);
521      # Here we do the table of contents. It starts as an unordered list of section names. Each      # Here we do the table of contents. It starts as an unordered list of section names. Each
522      # section contains an ordered list of entity or relationship subsections.      # section contains an ordered list of entity or relationship subsections.
523      print HTMLOUT "<ul>\n<li><a href=\"#EntitiesSection\">Entities</a>\n<ol>\n";      $retVal .= "<ul>\n<li><a href=\"#EntitiesSection\">Entities</a>\n<ol>\n";
524      # Loop through the Entities, displaying a list item for each.      # Loop through the Entities, displaying a list item for each.
525      foreach my $key (sort keys %{$entityList}) {      foreach my $key (sort keys %{$entityList}) {
526          # Display this item.          # Display this item.
527          print HTMLOUT "<li><a href=\"#$key\">$key</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$key</a></li>\n";
528      }      }
529      # Close off the entity section and start the relationship section.      # Close off the entity section and start the relationship section.
530      print HTMLOUT "</ol></li>\n<li><a href=\"#RelationshipsSection\">Relationships</a>\n<ol>\n";      $retVal .= "</ol></li>\n<li><a href=\"#RelationshipsSection\">Relationships</a>\n<ol>\n";
531      # Loop through the Relationships.      # Loop through the Relationships.
532      foreach my $key (sort keys %{$relationshipList}) {      foreach my $key (sort keys %{$relationshipList}) {
533          # Display this item.          # Display this item.
534          my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});          my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});
535          print HTMLOUT "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";
536      }      }
537      # Close off the relationship section and list the join table section.      # Close off the relationship section and list the join table section.
538      print HTMLOUT "</ol></li>\n<li><a href=\"#JoinTable\">Join Table</a></li>\n";      $retVal .= "</ol></li>\n<li><a href=\"#JoinTable\">Join Table</a></li>\n";
539      # Close off the table of contents itself.      # Close off the table of contents itself.
540      print HTMLOUT "</ul>\n";      $retVal .=  "</ul>\n";
541      # Now we start with the actual data. Denote we're starting the entity section.      # Now we start with the actual data. Denote we're starting the entity section.
542      print HTMLOUT "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";      $retVal .= "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";
543      # Loop through the entities.      # Loop through the entities.
544      for my $key (sort keys %{$entityList}) {      for my $key (sort keys %{$entityList}) {
545          Trace("Building MetaData entry for $key entity.") if T(4);          Trace("Building MetaData entry for $key entity.") if T(4);
546          # Create the entity header. It contains a bookmark and the entity name.          # Create the entity header. It contains a bookmark and the entity name.
547          print HTMLOUT "<a name=\"$key\"></a><h3>$key</h3>\n";          $retVal .= "<a name=\"$key\"></a><h3>$key</h3>\n";
548          # Get the entity data.          # Get the entity data.
549          my $entityData = $entityList->{$key};          my $entityData = $entityList->{$key};
550          # If there's descriptive text, display it.          # If there's descriptive text, display it.
551          if (my $notes = $entityData->{Notes}) {          if (my $notes = $entityData->{Notes}) {
552              print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
553          }          }
554          # Now we want a list of the entity's relationships. First, we set up the relationship subsection.          # See if we need a list of the entity's relationships.
555          print HTMLOUT "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          my $relCount = keys %{$relationshipList};
556            if ($relCount > 0) {
557                # First, we set up the relationship subsection.
558                $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
559          # Loop through the relationships.          # Loop through the relationships.
560          for my $relationship (sort keys %{$relationshipList}) {          for my $relationship (sort keys %{$relationshipList}) {
561              # Get the relationship data.              # Get the relationship data.
# Line 444  Line 565 
565                  # Get the relationship sentence and append the arity.                  # Get the relationship sentence and append the arity.
566                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);
567                  # Display the relationship data.                  # Display the relationship data.
568                  print HTMLOUT "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";                      $retVal .= "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";
569              }              }
570          }          }
571          # Close off the relationship list.          # Close off the relationship list.
572          print HTMLOUT "</ul>\n";              $retVal .= "</ul>\n";
573            }
574          # Get the entity's relations.          # Get the entity's relations.
575          my $relationList = $entityData->{Relations};          my $relationList = $entityData->{Relations};
576          # Create a header for the relation subsection.          # Create a header for the relation subsection.
577          print HTMLOUT "<h4>Relations for <b>$key</b></h4>\n";          $retVal .= "<h4>Relations for <b>$key</b></h4>\n";
578          # Loop through the relations, displaying them.          # Loop through the relations, displaying them.
579          for my $relation (sort keys %{$relationList}) {          for my $relation (sort keys %{$relationList}) {
580              my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});              my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});
581              print HTMLOUT $htmlString;              $retVal .= $htmlString;
582          }          }
583      }      }
584      # Denote we're starting the relationship section.      # Denote we're starting the relationship section.
585      print HTMLOUT "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";      $retVal .= "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";
586      # Loop through the relationships.      # Loop through the relationships.
587      for my $key (sort keys %{$relationshipList}) {      for my $key (sort keys %{$relationshipList}) {
588          Trace("Building MetaData entry for $key relationship.") if T(4);          Trace("Building MetaData entry for $key relationship.") if T(4);
# Line 468  Line 590 
590          my $relationshipStructure = $relationshipList->{$key};          my $relationshipStructure = $relationshipList->{$key};
591          # Create the relationship header.          # Create the relationship header.
592          my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);          my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);
593          print HTMLOUT "<h3><a name=\"$key\"></a>$headerText</h3>\n";          $retVal .= "<h3><a name=\"$key\"></a>$headerText</h3>\n";
594          # Get the entity names.          # Get the entity names.
595          my $fromEntity = $relationshipStructure->{from};          my $fromEntity = $relationshipStructure->{from};
596          my $toEntity = $relationshipStructure->{to};          my $toEntity = $relationshipStructure->{to};
# Line 478  Line 600 
600          # since both sentences will say the same thing.          # since both sentences will say the same thing.
601          my $arity = $relationshipStructure->{arity};          my $arity = $relationshipStructure->{arity};
602          if ($arity eq "11") {          if ($arity eq "11") {
603              print HTMLOUT "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";
604          } else {          } else {
605              print HTMLOUT "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";
606              if ($arity eq "MM" && $fromEntity ne $toEntity) {              if ($arity eq "MM" && $fromEntity ne $toEntity) {
607                  print HTMLOUT "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";                  $retVal .= "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";
608              }              }
609          }          }
610          print HTMLOUT "</p>\n";          $retVal .= "</p>\n";
611          # If there are notes on this relationship, display them.          # If there are notes on this relationship, display them.
612          if (my $notes = $relationshipStructure->{Notes}) {          if (my $notes = $relationshipStructure->{Notes}) {
613              print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
614          }          }
615          # Generate the relationship's relation table.          # Generate the relationship's relation table.
616          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
617          print HTMLOUT $htmlString;          $retVal .= $htmlString;
618      }      }
619      Trace("Building MetaData join table.") if T(4);      Trace("Building MetaData join table.") if T(4);
620      # Denote we're starting the join table.      # Denote we're starting the join table.
621      print HTMLOUT "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";      $retVal .= "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";
622      # Create a table header.      # Create a table header.
623      print HTMLOUT _OpenTable("Join Table", "Source", "Target", "Join Condition");      $retVal .= _OpenTable("Join Table", "Source", "Target", "Join Condition");
624      # Loop through the joins.      # Loop through the joins.
625      my $joinTable = $metadata->{Joins};      my $joinTable = $metadata->{Joins};
626      my @joinKeys = keys %{$joinTable};      my @joinKeys = keys %{$joinTable};
# Line 506  Line 628 
628          # Separate out the source, the target, and the join clause.          # Separate out the source, the target, and the join clause.
629          $joinKey =~ m!^([^/]+)/(.+)$!;          $joinKey =~ m!^([^/]+)/(.+)$!;
630          my ($sourceRelation, $targetRelation) = ($1, $2);          my ($sourceRelation, $targetRelation) = ($1, $2);
631          Trace("Join with key $joinKey is from $sourceRelation to $targetRelation.") if T(4);          Trace("Join with key $joinKey is from $sourceRelation to $targetRelation.") if T(Joins => 4);
632          my $source = $self->ComputeObjectSentence($sourceRelation);          my $source = $self->ComputeObjectSentence($sourceRelation);
633          my $target = $self->ComputeObjectSentence($targetRelation);          my $target = $self->ComputeObjectSentence($targetRelation);
634          my $clause = $joinTable->{$joinKey};          my $clause = $joinTable->{$joinKey};
635          # Display them in a table row.          # Display them in a table row.
636          print HTMLOUT "<tr><td>$source</td><td>$target</td><td>$clause</td></tr>\n";          $retVal .= "<tr><td>$source</td><td>$target</td><td>$clause</td></tr>\n";
637      }      }
638      # Close the table.      # Close the table.
639      print HTMLOUT _CloseTable();      $retVal .= _CloseTable();
640      # Close the document.      Trace("Built MetaData HTML.") if T(3);
641      print HTMLOUT "</body>\n</html>\n";      # Return the HTML.
642      # Close the file.      return $retVal;
     close HTMLOUT;  
     Trace("Built MetaData web page.") if T(3);  
643  }  }
644    
645  =head3 DumpMetaData  =head3 DumpMetaData
646    
647  C<< $database->DumpMetaData(); >>  C<< $erdb->DumpMetaData(); >>
648    
649  Return a dump of the metadata structure.  Return a dump of the metadata structure.
650    
# Line 537  Line 657 
657      return Data::Dumper::Dumper($self->{_metaData});      return Data::Dumper::Dumper($self->{_metaData});
658  }  }
659    
660    =head3 CreatePPO
661    
662    C<< ERDB::CreatePPO($erdbXMLFile, $ppoXMLFile); >>
663    
664    Create a PPO XML file from an ERDB data definition XML file. At the
665    current time, the PPO XML file can be used to create a database with
666    similar functionality. Eventually, the PPO will be able to use the
667    created XML to access the live ERDB database.
668    
669    =over 4
670    
671    =item erdbXMLFile
672    
673    Name of the XML data definition file for the ERDB database. This
674    file must exist.
675    
676    =item ppoXMLFile
677    
678    Output file for the PPO XML definition. If this file exists, it
679    will be overwritten.
680    
681    =back
682    
683    =cut
684    
685    sub CreatePPO {
686        # Get the parameters.
687        my ($erdbXMLFile, $ppoXMLFile) = @_;
688        # First, we want to slurp in the ERDB XML file in its raw form.
689        my $xml = ReadMetaXML($erdbXMLFile);
690        # Create a variable to hold all of the objects in the PPO project.
691        my @objects = ();
692        # Get the relationship hash.
693        my $relationships = $xml->{Relationships};
694        # Loop through the entities.
695        my $entities = $xml->{Entities};
696        for my $entityName (keys %{$entities}) {
697            # Get the entity's data structures.
698            my $entityObject = $entities->{$entityName};
699            # We put the object's fields in here, according to their type.
700            my (@object_refs, @scalars, @indexes, @arrays);
701            # Create the ID field for the entity. We get the key type from the
702            # entity object and compute the corresponding SQL type.
703            my $type = $TypeTable{$entityObject->{keyType}}->{sqlType};
704            push @scalars, { label => 'id', type => $type };
705            # Loop through the entity fields.
706            for my $fieldName ( keys %{$entityObject->{Fields}} ) {
707                # Get the field object.
708                my $fieldObject = $entityObject->{Fields}->{$fieldName};
709                # Convert it to a scalar tag.
710                my $scalar = _CreatePPOField($fieldName, $fieldObject);
711                # If we have a relation, this field is stored in an array.
712                # otherwise, it is a scalar. The array tag has scalars
713                # stored as an XML array. In ERDB, there is only ever one,
714                # but PPO can have more.
715                my $relation = $fieldObject->{relation};
716                if ($relation) {
717                    push @arrays, { scalar => [$scalar] };
718                } else {
719                    push @scalars, $scalar;
720                }
721            }
722            # Loop through the relationships. If this entity is the to-entity
723            # on a relationship of 1M arity, then it is implemented as a PPO
724            # object reference.
725            for my $relationshipName (keys %{$relationships}) {
726                # Get the relationship data.
727                my $relationshipData = $relationships->{$relationshipName};
728                # If we have a from for this entity and an arity of 1M, we
729                # have an object reference.
730                if ($relationshipData->{to} eq $entityName &&
731                    $relationshipData->{arity} eq '1M') {
732                    # Build the object reference tag.
733                    push @object_refs, { label => $relationshipName,
734                                         type => $relationshipData->{from} };
735                }
736            }
737            # Create the indexes.
738            my $indexList = $entityObject->{Indexes};
739            push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
740            # Build the object XML tree.
741            my $object = { label => $entityName,
742                           object_ref => \@object_refs,
743                           scalar => \@scalars,
744                           index => \@indexes,
745                           array => \@arrays
746                          };
747            # Push the object onto the objects list.
748            push @objects, $object;
749        }
750        # Loop through the relationships, searching for MMs. The 1Ms were
751        # already handled by the entity search above.
752        for my $relationshipName (keys %{$relationships}) {
753            # Get this relationship's object.
754            my $relationshipObject = $relationships->{$relationshipName};
755            # Only proceed if it's many-to-many.
756            if ($relationshipObject->{arity} eq 'MM') {
757                # Create the tag lists for the relationship object.
758                my (@object_refs, @scalars, @indexes);
759                # The relationship will be created as an object with object
760                # references for its links to the participating entities.
761                my %links = ( from_link => $relationshipObject->{from},
762                              to_link => $relationshipObject->{to} );
763                for my $link (keys %links) {
764                    # Create an object_ref tag for this piece of the
765                    # relationship (from or to).
766                    my $object_ref = { label => $link,
767                                       type => $links{$link} };
768                    push @object_refs, $object_ref;
769                }
770                # Loop through the intersection data fields, creating scalar tags.
771                # There are no fancy array tags in a relationship.
772                for my $fieldName (keys %{$relationshipObject->{Fields}}) {
773                    my $fieldObject = $relationshipObject->{Fields}->{$fieldName};
774                    push @scalars, _CreatePPOField($fieldName, $fieldObject);
775                }
776                # Finally, the indexes: currently we cannot support the to-index and
777                # from-index in PPO, so we just process the alternate indexes.
778                my $indexList = $relationshipObject->{Indexes};
779                push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
780                # Wrap up all the stuff about this relationship.
781                my $object = { label => $relationshipName,
782                               scalar => \@scalars,
783                               object_ref => \@object_refs,
784                               index => \@indexes
785                             };
786                # Push it into the object list.
787                push @objects, $object;
788            }
789        }
790        # Compute a title.
791        my $title;
792        if ($erdbXMLFile =~ /(\/|^)([^\/]+)DBD\.xml/) {
793            # Here we have a standard file name we can use for a title.
794            $title = $2;
795        } else {
796            # Here the file name is non-standard, so we carve up the
797            # database title.
798            $title = $xml->{Title}->{content};
799            $title =~ s/\s\.,//g;
800        }
801        # Wrap up the XML as a project.
802        my $ppoXML = { project => { label => $title,
803                                    object => \@objects }};
804        # Write out the results.
805        my $ppoString = XML::Simple::XMLout($ppoXML,
806                                            AttrIndent => 1,
807                                            KeepRoot => 1);
808        Tracer::PutFile($ppoXMLFile, [ $ppoString ]);
809    }
810    
811    =head3 FindIndexForEntity
812    
813    C<< my $indexFound = ERDB::FindIndexForEntity($xml, $entityName, $attributeName); >>
814    
815    This method locates the entry in an entity's index list that begins with the
816    specified attribute name. If the entity has no index list, one will be
817    created. This method works on raw XML, not a live ERDB object.
818    
819    =over 4
820    
821    =item xml
822    
823    The raw XML structure defining the database.
824    
825    =item entityName
826    
827    The name of the relevant entity.
828    
829    =item attributeName
830    
831    The name of the attribute relevant to the search.
832    
833    =item RETURN
834    
835    The numerical index in the index list of the index entry for the specified entity and
836    attribute, or C<undef> if no such index exists.
837    
838    =back
839    
840    =cut
841    
842    sub FindIndexForEntity {
843        # Get the parameters.
844        my ($xml, $entityName, $attributeName) = @_;
845        # Declare the return variable.
846        my $retVal;
847        # Get the named entity.
848        my $entityData = $xml->{Entities}->{$entityName};
849        if (! $entityData) {
850            Confess("Entity $entityName not found in DBD structure.");
851        } else {
852            # Insure it has an index list.
853            if (! exists $entityData->{Indexes}) {
854                $entityData->{Indexes} = [];
855            } else {
856                # Search for the desired index.
857                my $indexList = $entityData->{Indexes};
858                my $n = scalar @{$indexList};
859                Trace("Searching $n indexes in index list for $entityName.") if T(2);
860                # We use an indexed FOR here because we're returning an
861                # index number instead of an object. We do THAT so we can
862                # delete the index from the list if needed.
863                for (my $i = 0; $i < $n && !defined($retVal); $i++) {
864                    my $index = $indexList->[$i];
865                    my $fields = $index->{IndexFields};
866                    # Technically this IF should be safe (that is, we are guaranteed
867                    # the existence of a "$fields->[0]"), because when we load the XML
868                    # we have SuppressEmpty specified.
869                    if ($fields->[0]->{name} eq $attributeName) {
870                        $retVal = $i;
871                    }
872                }
873            }
874        }
875        Trace("Index for $attributeName of $entityName found at position $retVal.") if defined($retVal) && T(3);
876        Trace("Index for $attributeName not found in $entityName.") if !defined($retVal) && T(3);
877        # Return the result.
878        return $retVal;
879    }
880    
881  =head3 CreateTables  =head3 CreateTables
882    
883  C<< $datanase->CreateTables(); >>  C<< $erdb->CreateTables(); >>
884    
885  This method creates the tables for the database from the metadata structure loaded by the  This method creates the tables for the database from the metadata structure loaded by the
886  constructor. It is expected this function will only be used on rare occasions, when the  constructor. It is expected this function will only be used on rare occasions, when the
# Line 551  Line 892 
892  sub CreateTables {  sub CreateTables {
893      # Get the parameters.      # Get the parameters.
894      my ($self) = @_;      my ($self) = @_;
895      my $metadata = $self->{_metaData};      # Get the relation names.
896      my $dbh = $self->{_dbh};      my @relNames = $self->GetTableNames();
897      # Loop through the entities.      # Loop through the relations.
898      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}}) {  
899              # Create a table for this relation.              # Create a table for this relation.
900              $self->CreateTable($relationName);          $self->CreateTable($relationName, 1);
901              Trace("Relation $relationName created.") if T(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);  
902      }      }
903  }  }
904    
905  =head3 CreateTable  =head3 CreateTable
906    
907  C<< $database->CreateTable($tableName, $indexFlag); >>  C<< $erdb->CreateTable($tableName, $indexFlag, $estimatedRows); >>
908    
909  Create the table for a relation and optionally create its indexes.  Create the table for a relation and optionally create its indexes.
910    
# Line 587  Line 914 
914    
915  Name of the relation (which will also be the table name).  Name of the relation (which will also be the table name).
916    
917  =item $indexFlag  =item indexFlag
918    
919  TRUE if the indexes for the relation should be created, else FALSE. If FALSE,  TRUE if the indexes for the relation should be created, else FALSE. If FALSE,
920  L</CreateIndexes> must be called later to bring the indexes into existence.  L</CreateIndexes> must be called later to bring the indexes into existence.
921    
922    =item estimatedRows (optional)
923    
924    If specified, the estimated maximum number of rows for the relation. This
925    information allows the creation of tables using storage engines that are
926    faster but require size estimates, such as MyISAM.
927    
928  =back  =back
929    
930  =cut  =cut
931    
932  sub CreateTable {  sub CreateTable {
933      # Get the parameters.      # Get the parameters.
934      my ($self, $relationName, $indexFlag) = @_;      my ($self, $relationName, $indexFlag, $estimatedRows) = @_;
935      # Get the database handle.      # Get the database handle.
936      my $dbh = $self->{_dbh};      my $dbh = $self->{_dbh};
937      # 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 955 
955      # Insure the table is not already there.      # Insure the table is not already there.
956      $dbh->drop_table(tbl => $relationName);      $dbh->drop_table(tbl => $relationName);
957      Trace("Table $relationName dropped.") if T(2);      Trace("Table $relationName dropped.") if T(2);
958        # If there are estimated rows, create an estimate so we can take advantage of
959        # faster DB technologies.
960        my $estimation = undef;
961        if ($estimatedRows) {
962            $estimation = [$self->EstimateRowSize($relationName), $estimatedRows];
963        }
964      # Create the table.      # Create the table.
965      Trace("Creating table $relationName: $fieldThing") if T(2);      Trace("Creating table $relationName: $fieldThing") if T(2);
966      $dbh->create_table(tbl => $relationName, flds => $fieldThing);      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);
967      Trace("Relation $relationName created in database.") if T(2);      Trace("Relation $relationName created in database.") if T(2);
968      # If we want to build the indexes, we do it here.      # If we want to build the indexes, we do it here. Note that the full-text search
969        # index will not be built until the table has been loaded.
970      if ($indexFlag) {      if ($indexFlag) {
971          $self->CreateIndex($relationName);          $self->CreateIndex($relationName);
972      }      }
973  }  }
974    
975    =head3 VerifyFields
976    
977    C<< my $count = $erdb->VerifyFields($relName, \@fieldList); >>
978    
979    Run through the list of proposed field values, insuring that all the character fields are
980    below the maximum length. If any fields are too long, they will be truncated in place.
981    
982    =over 4
983    
984    =item relName
985    
986    Name of the relation for which the specified fields are destined.
987    
988    =item fieldList
989    
990    Reference to a list, in order, of the fields to be put into the relation.
991    
992    =item RETURN
993    
994    Returns the number of fields truncated.
995    
996    =back
997    
998    =cut
999    
1000    sub VerifyFields {
1001        # Get the parameters.
1002        my ($self, $relName, $fieldList) = @_;
1003        # Initialize the return value.
1004        my $retVal = 0;
1005        # Get the relation definition.
1006        my $relData = $self->_FindRelation($relName);
1007        # Get the list of field descriptors.
1008        my $fieldTypes = $relData->{Fields};
1009        my $fieldCount = scalar @{$fieldTypes};
1010        # Loop through the two lists.
1011        for (my $i = 0; $i < $fieldCount; $i++) {
1012            # Get the type of the current field.
1013            my $fieldType = $fieldTypes->[$i]->{type};
1014            # If it's a character field, verify the length.
1015            if ($fieldType =~ /string/) {
1016                my $maxLen = $TypeTable{$fieldType}->{maxLen};
1017                my $oldString = $fieldList->[$i];
1018                if (length($oldString) > $maxLen) {
1019                    # Here it's too big, so we truncate it.
1020                    Trace("Truncating field $i ($fieldTypes->[$i]->{name}) in relation $relName to $maxLen characters from \"$oldString\".") if T(1);
1021                    $fieldList->[$i] = substr $oldString, 0, $maxLen;
1022                    $retVal++;
1023                }
1024            }
1025        }
1026        # Return the truncation count.
1027        return $retVal;
1028    }
1029    
1030    =head3 DigestFields
1031    
1032    C<< $erdb->DigestFields($relName, $fieldList); >>
1033    
1034    Digest the strings in the field list that correspond to data type C<hash-string> in the
1035    specified relation.
1036    
1037    =over 4
1038    
1039    =item relName
1040    
1041    Name of the relation to which the fields belong.
1042    
1043    =item fieldList
1044    
1045    List of field contents to be loaded into the relation.
1046    
1047    =back
1048    
1049    =cut
1050    #: Return Type ;
1051    sub DigestFields {
1052        # Get the parameters.
1053        my ($self, $relName, $fieldList) = @_;
1054        # Get the relation definition.
1055        my $relData = $self->_FindRelation($relName);
1056        # Get the list of field descriptors.
1057        my $fieldTypes = $relData->{Fields};
1058        my $fieldCount = scalar @{$fieldTypes};
1059        # Loop through the two lists.
1060        for (my $i = 0; $i < $fieldCount; $i++) {
1061            # Get the type of the current field.
1062            my $fieldType = $fieldTypes->[$i]->{type};
1063            # If it's a hash string, digest it in place.
1064            if ($fieldType eq 'hash-string') {
1065                $fieldList->[$i] = $self->DigestKey($fieldList->[$i]);
1066            }
1067        }
1068    }
1069    
1070    =head3 DigestKey
1071    
1072    C<< my $digested = $erdb->DigestKey($keyValue); >>
1073    
1074    Return the digested value of a symbolic key. The digested value can then be plugged into a
1075    key-based search into a table with key-type hash-string.
1076    
1077    Currently the digesting process is independent of the database structure, but that may not
1078    always be the case, so this is an instance method instead of a static method.
1079    
1080    =over 4
1081    
1082    =item keyValue
1083    
1084    Key value to digest.
1085    
1086    =item RETURN
1087    
1088    Digested value of the key.
1089    
1090    =back
1091    
1092    =cut
1093    
1094    sub DigestKey {
1095        # Get the parameters.
1096        my ($self, $keyValue) = @_;
1097        # Compute the digest.
1098        my $retVal = md5_base64($keyValue);
1099        # Return the result.
1100        return $retVal;
1101    }
1102    
1103  =head3 CreateIndex  =head3 CreateIndex
1104    
1105  C<< $database->CreateIndex($relationName); >>  C<< $erdb->CreateIndex($relationName); >>
1106    
1107  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
1108  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.
1109  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
1110  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.
1111    
1112  =cut  =cut
1113    
# Line 655  Line 1123 
1123      for my $indexName (keys %{$indexHash}) {      for my $indexName (keys %{$indexHash}) {
1124          my $indexData = $indexHash->{$indexName};          my $indexData = $indexHash->{$indexName};
1125          # Get the index's field list.          # Get the index's field list.
1126          my @fieldList = _FixNames(@{$indexData->{IndexFields}});          my @rawFields = @{$indexData->{IndexFields}};
1127            # Get a hash of the relation's field types.
1128            my %types = map { $_->{name} => $_->{type} } @{$relationData->{Fields}};
1129            # We need to check for text fields so we can append a length limitation for them. To do
1130            # that, we need the relation's field list.
1131            my $relFields = $relationData->{Fields};
1132            for (my $i = 0; $i <= $#rawFields; $i++) {
1133                # Get the field type.
1134                my $field = $rawFields[$i];
1135                my $type = $types{$field};
1136                # Ask if it requires using prefix notation for the index.
1137                my $mod = $TypeTable{$type}->{indexMod};
1138                Trace("Field $field ($i) in $relationName has type $type and indexMod $mod.") if T(3);
1139                if ($mod) {
1140                    # Append the prefix length to the field name,
1141                    $rawFields[$i] .= "($mod)";
1142                }
1143            }
1144            my @fieldList = _FixNames(@rawFields);
1145          my $flds = join(', ', @fieldList);          my $flds = join(', ', @fieldList);
1146          # Get the index's uniqueness flag.          # Get the index's uniqueness flag.
1147          my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
1148          # Create the index.          # Create the index.
1149          $dbh->create_index(idx => $indexName, tbl => $relationName, flds => $flds, unique => $unique);          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
1150                                        flds => $flds, kind => $unique);
1151            if ($rv) {
1152          Trace("Index created: $indexName for $relationName ($flds)") if T(1);          Trace("Index created: $indexName for $relationName ($flds)") if T(1);
1153            } else {
1154                Confess("Error creating index $indexName for $relationName using ($flds): " . $dbh->error_message());
1155            }
1156      }      }
1157  }  }
1158    
1159  =head3 LoadTables  =head3 GetSecondaryFields
   
 C<< my $stats = $database->LoadTables($directoryName, $rebuild); >>  
1160    
1161  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.  
1162    
1163  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
1164  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
1165  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
1166    or to have multiple values.
1167    
1168  =over 4  =over 4
1169    
1170  =item directoryName  =item entityName
   
 Name of the directory containing the relation files to be loaded.  
   
 =item rebuild  
1171    
1172  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.  
1173    
1174  =item RETURN  =item RETURN
1175    
1176  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.
1177    
1178  =back  =back
1179    
1180  =cut  =cut
1181    
1182  sub LoadTables {  sub GetSecondaryFields {
1183      # Get the parameters.      # Get the parameters.
1184      my ($self, $directoryName, $rebuild) = @_;      my ($self, $entityName) = @_;
     # Start the timer.  
     my $startTime = gettimeofday;  
     # Clean any trailing slash from the directory name.  
     $directoryName =~ s!/\\$!!;  
1185      # Declare the return variable.      # Declare the return variable.
1186      my $retVal = Stats->new();      my %retVal = ();
1187      # Get the metadata structure.      # Look for the entity.
1188      my $metaData = $self->{_metaData};      my $table = $self->GetFieldTable($entityName);
1189      # Loop through the entities.      # Loop through the fields, pulling out the secondaries.
1190      for my $entity (values %{$metaData->{Entities}}) {      for my $field (sort keys %{$table}) {
1191          # Loop through the entity's relations.          if ($table->{$field}->{relation} ne $entityName) {
1192          for my $relationName (keys %{$entity->{Relations}}) {              # Here we have a secondary field.
1193              # Try to load this relation.              $retVal{$field} = $table->{$field}->{type};
             my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);  
             # Accumulate the statistics.  
             $retVal->Accumulate($result);  
         }  
1194      }      }
     # 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);  
1195      }      }
1196      # Add the duration of the load to the statistical object.      # Return the result.
1197      $retVal->Add('duration', gettimeofday - $startTime);      return %retVal;
     # Return the accumulated statistics.  
     return $retVal;  
1198  }  }
1199    
1200  =head3 GetTableNames  =head3 GetFieldRelationName
1201    
1202  C<< my @names = $database->GetTableNames; >>  C<< my $name = $erdb->GetFieldRelationName($objectName, $fieldName); >>
1203    
1204  Return a list of the relations required to implement this database.  Return the name of the relation containing a specified field.
1205    
1206  =cut  =over 4
1207    
1208  sub GetTableNames {  =item objectName
     # Get the parameters.  
     my ($self) = @_;  
     # Get the relation list from the metadata.  
     my $relationTable = $self->{_metaData}->{RelationTable};  
     # Return the relation names.  
     return keys %{$relationTable};  
 }  
1209    
1210  =head3 GetEntityTypes  Name of the entity or relationship containing the field.
1211    
1212  C<< my @names = $database->GetEntityTypes; >>  =item fieldName
1213    
1214    Name of the relevant field in that entity or relationship.
1215    
1216    =item RETURN
1217    
1218    Returns the name of the database relation containing the field, or C<undef> if
1219    the field does not exist.
1220    
1221    =back
1222    
1223    =cut
1224    
1225    sub GetFieldRelationName {
1226        # Get the parameters.
1227        my ($self, $objectName, $fieldName) = @_;
1228        # Declare the return variable.
1229        my $retVal;
1230        # Get the object field table.
1231        my $table = $self->GetFieldTable($objectName);
1232        # Only proceed if the field exists.
1233        if (exists $table->{$fieldName}) {
1234            # Determine the name of the relation that contains this field.
1235            $retVal = $table->{$fieldName}->{relation};
1236        }
1237        # Return the result.
1238        return $retVal;
1239    }
1240    
1241    =head3 DeleteValue
1242    
1243    C<< my $numDeleted = $erdb->DeleteValue($entityName, $id, $fieldName, $fieldValue); >>
1244    
1245    Delete secondary field values from the database. This method can be used to delete all
1246    values of a specified field for a particular entity instance, or only a single value.
1247    
1248    Secondary fields are stored in two-column relations separate from an entity's primary
1249    table, and as a result a secondary field can legitimately have no value or multiple
1250    values. Therefore, it makes sense to talk about deleting secondary fields where it
1251    would not make sense for primary fields.
1252    
1253    =over 4
1254    
1255    =item entityName
1256    
1257    Name of the entity from which the fields are to be deleted.
1258    
1259    =item id
1260    
1261    ID of the entity instance to be processed. If the instance is not found, this
1262    method will have no effect. If C<undef> is specified, all values for all of
1263    the entity instances will be deleted.
1264    
1265    =item fieldName
1266    
1267    Name of the field whose values are to be deleted.
1268    
1269    =item fieldValue (optional)
1270    
1271    Value to be deleted. If not specified, then all values of the specified field
1272    will be deleted for the entity instance. If specified, then only the values which
1273    match this parameter will be deleted.
1274    
1275    =item RETURN
1276    
1277    Returns the number of rows deleted.
1278    
1279    =back
1280    
1281    =cut
1282    
1283    sub DeleteValue {
1284        # Get the parameters.
1285        my ($self, $entityName, $id, $fieldName, $fieldValue) = @_;
1286        # Declare the return value.
1287        my $retVal = 0;
1288        # We need to set up an SQL command to do the deletion. First, we
1289        # find the name of the field's relation.
1290        my $table = $self->GetFieldTable($entityName);
1291        my $field = $table->{$fieldName};
1292        my $relation = $field->{relation};
1293        # Make sure this is a secondary field.
1294        if ($relation eq $entityName) {
1295            Confess("Cannot delete values of $fieldName for $entityName.");
1296        } else {
1297            # Set up the SQL command to delete all values.
1298            my $sql = "DELETE FROM $relation";
1299            # Build the filter.
1300            my @filters = ();
1301            my @parms = ();
1302            # Check for a filter by ID.
1303            if (defined $id) {
1304                push @filters, "id = ?";
1305                push @parms, $id;
1306            }
1307            # Check for a filter by value.
1308            if (defined $fieldValue) {
1309                push @filters, "$fieldName = ?";
1310                push @parms, $fieldValue;
1311            }
1312            # Append the filters to the command.
1313            if (@filters) {
1314                $sql .= " WHERE " . join(" AND ", @filters);
1315            }
1316            # Execute the command.
1317            my $dbh = $self->{_dbh};
1318            $retVal = $dbh->SQL($sql, 0, @parms);
1319        }
1320        # Return the result.
1321        return $retVal;
1322    }
1323    
1324    =head3 LoadTables
1325    
1326    C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>
1327    
1328    This method will load the database tables from a directory. The tables must already have been created
1329    in the database. (This can be done by calling L</CreateTables>.) The caller passes in a directory name;
1330    all of the relations to be loaded must have a file in the directory with the same name as the relation
1331    (optionally with a suffix of C<.dtx>). Each file must be a tab-delimited table of field values. Each
1332    line of the file will be loaded as a row of the target relation table. The field values should be in
1333    the same order as the fields in the relation tables generated by L</ShowMetaData>. The old data is
1334    erased before the new data is loaded in.
1335    
1336    A certain amount of translation automatically takes place. Ctrl-M characters are deleted, and
1337    tab and new-line characters inside a field are escaped as C<\t> and C<\n>, respectively. Dates must
1338    be entered as a Unix timestamp, that is, as an integer number of seconds since the base epoch.
1339    
1340    =over 4
1341    
1342    =item directoryName
1343    
1344    Name of the directory containing the relation files to be loaded.
1345    
1346    =item rebuild
1347    
1348    TRUE if the tables should be dropped and rebuilt, else FALSE. This is, unfortunately, the
1349    only way to erase existing data in the tables, since the TRUNCATE command is not supported
1350    by all of the DB engines we use.
1351    
1352    =item RETURN
1353    
1354    Returns a statistical object describing the number of records read and a list of the error messages.
1355    
1356    =back
1357    
1358    =cut
1359    
1360    sub LoadTables {
1361        # Get the parameters.
1362        my ($self, $directoryName, $rebuild) = @_;
1363        # Start the timer.
1364        my $startTime = gettimeofday;
1365        # Clean any trailing slash from the directory name.
1366        $directoryName =~ s!/\\$!!;
1367        # Declare the return variable.
1368        my $retVal = Stats->new();
1369        # Get the relation names.
1370        my @relNames = $self->GetTableNames();
1371        for my $relationName (@relNames) {
1372            # Try to load this relation.
1373            my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);
1374            # Accumulate the statistics.
1375            $retVal->Accumulate($result);
1376        }
1377        # Add the duration of the load to the statistical object.
1378        $retVal->Add('duration', gettimeofday - $startTime);
1379        # Return the accumulated statistics.
1380        return $retVal;
1381    }
1382    
1383    
1384    =head3 GetTableNames
1385    
1386    C<< my @names = $erdb->GetTableNames; >>
1387    
1388    Return a list of the relations required to implement this database.
1389    
1390    =cut
1391    
1392    sub GetTableNames {
1393        # Get the parameters.
1394        my ($self) = @_;
1395        # Get the relation list from the metadata.
1396        my $relationTable = $self->{_metaData}->{RelationTable};
1397        # Return the relation names.
1398        return keys %{$relationTable};
1399    }
1400    
1401    =head3 GetEntityTypes
1402    
1403    C<< my @names = $erdb->GetEntityTypes; >>
1404    
1405  Return a list of the entity type names.  Return a list of the entity type names.
1406    
# Line 769  Line 1415 
1415      return sort keys %{$entityList};      return sort keys %{$entityList};
1416  }  }
1417    
1418    =head3 GetDataTypes
1419    
1420    C<< my %types = ERDB::GetDataTypes(); >>
1421    
1422    Return a table of ERDB data types. The table returned is a hash of hashes.
1423    The keys of the big hash are the datatypes. Each smaller hash has several
1424    values used to manage the data. The most interesting is the SQL type (key
1425    C<sqlType>) and the descriptive node (key C<notes>).
1426    
1427    Note that changing the values in the smaller hashes will seriously break
1428    things, so this data should be treated as read-only.
1429    
1430    =cut
1431    
1432    sub GetDataTypes {
1433        return %TypeTable;
1434    }
1435    
1436    
1437    =head3 IsEntity
1438    
1439    C<< my $flag = $erdb->IsEntity($entityName); >>
1440    
1441    Return TRUE if the parameter is an entity name, else FALSE.
1442    
1443    =over 4
1444    
1445    =item entityName
1446    
1447    Object name to be tested.
1448    
1449    =item RETURN
1450    
1451    Returns TRUE if the specified string is an entity name, else FALSE.
1452    
1453    =back
1454    
1455    =cut
1456    
1457    sub IsEntity {
1458        # Get the parameters.
1459        my ($self, $entityName) = @_;
1460        # Test to see if it's an entity.
1461        return exists $self->{_metaData}->{Entities}->{$entityName};
1462    }
1463    
1464  =head3 Get  =head3 Get
1465    
1466  C<< my $query = $database->Get(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  C<< my $query = $erdb->Get(\@objectNames, $filterClause, \@params); >>
1467    
1468  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.
1469  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 1471 
1471  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
1472  $genus.  $genus.
1473    
1474  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", [$genus]); >>
1475    
1476  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
1477  parameter representing the parameter value. It would also be possible to code  parameter representing the parameter value. It would also be possible to code
1478    
1479  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>
1480    
1481  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
1482  characters inside the variable C<$genus>.  characters inside the variable C<$genus>.
# Line 796  Line 1488 
1488  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
1489  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,
1490    
1491  C<< $query = $sprout->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]); >>
1492    
1493  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
1494  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.
1495  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
1496  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
1497  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  
1498  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,
1499  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.
1500    
1501    If an entity or relationship is mentioned twice, the name for the second occurrence will
1502    be suffixed with C<2>, the third occurrence will be suffixed with C<3>, and so forth. So,
1503    for example, if we have C<['Feature', 'HasContig', 'Contig', 'HasContig']>, then the
1504    B<to-link> field of the first B<HasContig> is specified as C<HasContig(to-link)>, while
1505    the B<to-link> field of the second B<HasContig> is specified as C<HasContig2(to-link)>.
1506    
1507  =over 4  =over 4
1508    
1509  =item objectNames  =item objectNames
# Line 829  Line 1526 
1526    
1527  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
1528    
1529    Note that the case is important. Only an uppercase "ORDER BY" with a single space will
1530    be processed. The idea is to make it less likely to find the verb by accident.
1531    
1532  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
1533  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
1534  relation.  relation.
1535    
1536  =item param1, param2, ..., paramN  Finally, you can limit the number of rows returned by adding a LIMIT clause. The LIMIT must
1537    be the last thing in the filter clause, and it contains only the word "LIMIT" followed by
1538    a positive number. So, for example
1539    
1540  Parameter values to be substituted into the filter clause.  C<< "Genome(genus) = ? ORDER BY Genome(species) LIMIT 10" >>
1541    
1542    will only return the first ten genomes for the specified genus. The ORDER BY clause is not
1543    required. For example, to just get the first 10 genomes in the B<Genome> table, you could
1544    use
1545    
1546    C<< "LIMIT 10" >>
1547    
1548    =item params
1549    
1550    Reference to a list of parameter values to be substituted into the filter clause.
1551    
1552  =item RETURN  =item RETURN
1553    
# Line 847  Line 1559 
1559    
1560  sub Get {  sub Get {
1561      # Get the parameters.      # Get the parameters.
1562      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $objectNames, $filterClause, $params) = @_;
1563      # Construct the SELECT statement. The general pattern is      # Process the SQL stuff.
1564      #      my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1565      # SELECT name1.*, name2.*, ... nameN.* FROM name1, name2, ... nameN          $self->_SetupSQL($objectNames, $filterClause);
1566      #      # Create the query.
1567      my $dbh = $self->{_dbh};      my $command = "SELECT DISTINCT " . join(".*, ", @{$mappedNameListRef}) .
1568      my $command = "SELECT DISTINCT " . join('.*, ', @{$objectNames}) . ".* FROM " .          ".* $suffix";
1569                  join(', ', @{$objectNames});      my $sth = $self->_GetStatementHandle($command, $params);
1570      # Check for a filter clause.      # Now we create the relation map, which enables DBQuery to determine the order, name
1571      if ($filterClause) {      # and mapped name for each object in the query.
1572          # Here we have one, so we convert its field names and add it to the query. First,      my @relationMap = ();
1573          # We create a copy of the filter string we can work with.      for my $mappedName (@{$mappedNameListRef}) {
1574          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";  
         }  
1575      }      }
     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());  
1576      # Return the statement object.      # Return the statement object.
1577      my $retVal = DBQuery::_new($self, $sth, @{$objectNames});      my $retVal = DBQuery::_new($self, $sth, \@relationMap);
1578      return $retVal;      return $retVal;
1579  }  }
1580    
 =head3 GetList  
1581    
 C<< my @dbObjects = $database->GetList(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  
1582    
1583  Return a list of object descriptors for the specified objects as determined by the  =head3 Search
 specified filter clause.  
1584    
1585  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, $filterClause, \@params); >>
1586  than a query object that can be used to get the results one record at a time.  
1587    Perform a full text search with filtering. The search will be against a specified object
1588    in the object name list. That object will get an extra field containing the search
1589    relevance. Note that except for the search expression, the parameters of this method are
1590    the same as those for L</Get> and follow the same rules.
1591    
1592  =over 4  =over 4
1593    
1594    =item searchExpression
1595    
1596    Boolean search expression for the text fields of the target object. The default mode for
1597    a Boolean search expression is OR, but we want the default to be AND, so we will
1598    add a C<+> operator to each word with no other operator before it.
1599    
1600    =item idx
1601    
1602    Index in the I<$objectNames> list of the table to be searched in full-text mode.
1603    
1604  =item objectNames  =item objectNames
1605    
1606  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 1615 
1615  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
1616  be included in the list of object names.  be included in the list of object names.
1617    
1618  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  
1619    
1620  Parameter values to be substituted into the filter clause.  Reference to a list of parameter values to be substituted into the filter clause.
1621    
1622  =item RETURN  =item RETURN
1623    
1624  Returns a list of B<DBObject>s that satisfy the query conditions.  Returns a query object for the specified search.
1625    
1626  =back  =back
1627    
1628  =cut  =cut
1629  #: Return Type @%  
1630  sub GetList {  sub Search {
1631      # Get the parameters.      # Get the parameters.
1632      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1633      # Declare the return variable.      # Declare the return variable.
1634      my @retVal = ();      my $retVal;
1635      # Perform the query.      # Create a safety copy of the parameter list. Note we have to be careful to insure
1636      my $query = $self->Get($objectNames, $filterClause, @params);      # a parameter list exists before we copy it.
1637      # Loop through the results.      my @myParams = ();
1638      while (my $object = $query->Fetch) {      if (defined $params) {
1639          push @retVal, $object;          @myParams = @{$params};
1640        }
1641        # Get the first object's structure so we have access to the searchable fields.
1642        my $object1Name = $objectNames->[$idx];
1643        my $object1Structure = $self->_GetStructure($object1Name);
1644        # Get the field list.
1645        if (! exists $object1Structure->{searchFields}) {
1646            Confess("No searchable index for $object1Name.");
1647        } else {
1648            # Get the field list.
1649            my @fields = @{$object1Structure->{searchFields}};
1650            # Clean the search expression.
1651            my $actualKeywords = $self->CleanKeywords($searchExpression);
1652            # Prefix a "+" to each uncontrolled word. This converts the default
1653            # search mode from OR to AND.
1654            $actualKeywords =~ s/(^|\s)(\w|")/$1\+$2/g;
1655            Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1656            # We need two match expressions, one for the filter clause and one in the
1657            # query itself. Both will use a parameter mark, so we need to push the
1658            # search expression onto the front of the parameter list twice.
1659            unshift @myParams, $actualKeywords, $actualKeywords;
1660            # Build the match expression.
1661            my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
1662            my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
1663            # Process the SQL stuff.
1664            my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1665                $self->_SetupSQL($objectNames, $filterClause, $matchClause);
1666            # Create the query. Note that the match clause is inserted at the front of
1667            # the select fields.
1668            my $command = "SELECT DISTINCT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .
1669                ".* $suffix";
1670            my $sth = $self->_GetStatementHandle($command, \@myParams);
1671            # Now we create the relation map, which enables DBQuery to determine the order, name
1672            # and mapped name for each object in the query.
1673            my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
1674            # Return the statement object.
1675            $retVal = DBQuery::_new($self, $sth, \@relationMap, $object1Name);
1676      }      }
1677      # Return the result.      return $retVal;
     return @retVal;  
1678  }  }
1679    
1680  =head3 ComputeObjectSentence  =head3 GetFlat
1681    
1682  C<< my $sentence = $database->ComputeObjectSentence($objectName); >>  C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>
1683    
1684  Check an object name, and if it is a relationship convert it to a relationship sentence.  This is a variation of L</GetAll> that asks for only a single field per record and
1685    returns a single flattened list.
1686    
1687  =over 4  =over 4
1688    
1689  =item objectName  =item objectNames
1690    
1691  Name of the entity or relationship.  List containing the names of the entity and relationship objects to be retrieved.
1692    
1693    =item filterClause
1694    
1695    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1696    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
1697    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
1698    parameter list as additional parameters. The fields in a filter clause can come from primary
1699    entity relations, relationship relations, or secondary entity relations; however, all of the
1700    entities and relationships involved must be included in the list of object names.
1701    
1702    =item parameterList
1703    
1704    List of the parameters to be substituted in for the parameters marks in the filter clause.
1705    
1706    =item field
1707    
1708    Name of the field to be used to get the elements of the list returned.
1709    
1710  =item RETURN  =item RETURN
1711    
1712  Returns a string containing the entity name or a relationship sentence.  Returns a list of values.
1713    
1714  =back  =back
1715    
1716  =cut  =cut
1717    #: Return Type @;
1718  sub ComputeObjectSentence {  sub GetFlat {
1719      # Get the parameters.      # Get the parameters.
1720      my ($self, $objectName) = @_;      my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
1721      # Set the default return value.      # Construct the query.
1722      my $retVal = $objectName;      my $query = $self->Get($objectNames, $filterClause, $parameterList);
1723      # Look for the object as a relationship.      # Create the result list.
1724      my $relTable = $self->{_metaData}->{Relationships};      my @retVal = ();
1725      if (exists $relTable->{$objectName}) {      # Loop through the records, adding the field values found to the result list.
1726          # Get the relationship sentence.      while (my $row = $query->Fetch()) {
1727          $retVal = _ComputeRelationshipSentence($objectName, $relTable->{$objectName});          push @retVal, $row->Value($field);
1728      }      }
1729      # Return the result.      # Return the list created.
1730      return $retVal;      return @retVal;
1731  }  }
1732    
1733  =head3 DumpRelations  =head3 SpecialFields
1734    
1735  C<< $database->DumpRelations($outputDirectory); >>  C<< my %specials = $erdb->SpecialFields($entityName); >>
1736    
1737  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
1738  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
1739    attributes without needed to plumb the internal ERDB data structures.
1740    
1741  =over 4  =over 4
1742    
1743  =item outputDirectory  =item entityName
1744    
1745  Name of the directory into which the relation files should be dumped.  Name of the entity whose special fields are desired.
1746    
1747    =item RETURN
1748    
1749    Returns a hash. The keys of the hash are the special field names, and the values
1750    are the values from each special field's C<special> attribute.
1751    
1752  =back  =back
1753    
1754  =cut  =cut
1755    
1756  sub DumpRelations {  sub SpecialFields {
1757      # Get the parameters.      # Get the parameters.
1758      my ($self, $outputDirectory) = @_;      my ($self, $entityName) = @_;
1759      # Now we need to run through all the relations. First, we loop through the entities.      # Declare the return variable.
1760      my $metaData = $self->{_metaData};      my %retVal = ();
1761      my $entities = $metaData->{Entities};      # Find the entity's data structure.
1762      for my $entityName (keys %{$entities}) {      my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1763          my $entityStructure = $entities->{$entityName};      # Loop through its fields, adding each special field to the return hash.
1764          # Get the entity's relations.      my $fieldHash = $entityData->{Fields};
1765          my $relationList = $entityStructure->{Relations};      for my $fieldName (keys %{$fieldHash}) {
1766          # Loop through the relations, dumping them.          my $fieldData = $fieldHash->{$fieldName};
1767          for my $relationName (keys %{$relationList}) {          if (exists $fieldData->{special}) {
1768              my $relation = $relationList->{$relationName};              $retVal{$fieldName} = $fieldData->{special};
             $self->_DumpRelation($outputDirectory, $relationName, $relation);  
         }  
1769      }      }
     # 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});  
1770      }      }
1771        # Return the result.
1772        return %retVal;
1773  }  }
1774    
1775  =head3 InsertObject  =head3 Delete
1776    
1777  C<< my $ok = $database->InsertObject($objectType, \%fieldHash); >>  C<< my $stats = $erdb->Delete($entityName, $objectID, %options); >>
1778    
1779  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
1780  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>.  
1781    
1782  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
1783    relationship connected to a dependent entity or if it is the "to" entity connected to a 1-to-many
1784    dependent relationship.
1785    
1786  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>.  
1787    
1788  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
1789    
1790  =over 4  Name of the entity type for the instance being deleted.
1791    
1792  =item newObjectType  =item objectID
1793    
1794  Type name of the object to insert.  ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),
1795    then it is presumed to by a LIKE pattern.
1796    
1797  =item fieldHash  =item options
1798    
1799  Hash of field names to values.  A hash detailing the options for this delete operation.
1800    
1801  =item RETURN  =item RETURN
1802    
1803  Returns 1 if successful, 0 if an error occurred.  Returns a statistics object indicating how many records of each particular table were
1804    deleted.
1805    
1806  =back  =back
1807    
1808  =cut  The permissible options for this method are as follows.
1809    
1810  sub InsertObject {  =over 4
1811    
1812    =item testMode
1813    
1814    If TRUE, then the delete statements will be traced, but no changes will be made to the database.
1815    
1816    =item keepRoot
1817    
1818    If TRUE, then the entity instances will not be deleted, only the dependent records.
1819    
1820    =back
1821    
1822    =cut
1823    #: Return Type $%;
1824    sub Delete {
1825      # Get the parameters.      # Get the parameters.
1826      my ($self, $newObjectType, $fieldHash) = @_;      my ($self, $entityName, $objectID, %options) = @_;
1827      # Denote that so far we appear successful.      # Declare the return variable.
1828      my $retVal = 1;      my $retVal = Stats->new();
1829      # Get the database handle.      # Get the DBKernel object.
1830      my $dbh = $self->{_dbh};      my $db = $self->{_dbh};
1831      # Get the relation list.      # We're going to generate all the paths branching out from the starting entity. One of
1832      my $relationTable = $self->_GetRelationTable($newObjectType);      # the things we have to be careful about is preventing loops. We'll use a hash to
1833      # Loop through the relations. We'll build insert statements for each one. If a relation is      # determine if we've hit a loop.
1834      # secondary, we may end up generating multiple insert statements. If an error occurs, we      my %alreadyFound = ();
1835      # stop the loop.      # These next lists will serve as our result stack. We start by pushing object lists onto
1836      my @relationList = keys %{$relationTable};      # the stack, and then popping them off to do the deletes. This means the deletes will
1837      for (my $i = 0; $retVal && $i <= $#relationList; $i++) {      # start with the longer paths before getting to the shorter ones. That, in turn, makes
1838          my $relationName = $relationList[$i];      # sure we don't delete records that might be needed to forge relationships back to the
1839          my $relationDefinition = $relationTable->{$relationName};      # original item. We have two lists-- one for TO-relationships, and one for
1840          # Get the relation's fields. For each field we will collect a value in the corresponding      # FROM-relationships and entities.
1841          # position of the @valueList array. If one of the fields is missing, we will add it to the      my @fromPathList = ();
1842          # @missing list.      my @toPathList = ();
1843          my @fieldList = @{$relationDefinition->{Fields}};      # This final list is used to remember what work still needs to be done. We push paths
1844          my @fieldNameList = ();      # onto the list, then pop them off to extend the paths. We prime it with the starting
1845          my @valueList = ();      # point. Note that we will work hard to insure that the last item on a path in the
1846          my @missing = ();      # to-do list is always an entity.
1847          my $recordCount = 1;      my @todoList = ([$entityName]);
1848          for my $fieldDescriptor (@fieldList) {      while (@todoList) {
1849              # Get the field name and save it. Note we need to fix it up so the hyphens          # Get the current path.
1850              # are converted to underscores.          my $current = pop @todoList;
1851              my $fieldName = $fieldDescriptor->{name};          # Copy it into a list.
1852              push @fieldNameList, _FixName($fieldName);          my @stackedPath = @{$current};
1853              # 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.
1854              # for the real field name, not the fixed-up one!          my $myEntityName = pop @stackedPath;
1855              if (exists $fieldHash->{$fieldName}) {          # Add it to the alreadyFound list.
1856                  # Here we found the field. Stash it in the value list.          $alreadyFound{$myEntityName} = 1;
1857                  my $value = $fieldHash->{$fieldName};          # Figure out if we need to delete this entity.
1858                  push @valueList, $value;          if ($myEntityName ne $entityName || ! $options{keepRoot}) {
1859                  # If the value is a list, we may need to increment the record count.              # Get the entity data.
1860                  if (ref $value eq "ARRAY") {              my $entityData = $self->_GetStructure($myEntityName);
1861                      my $thisCount = @{$value};              # Loop through the entity's relations. A DELETE command will be needed for each of them.
1862                      if ($recordCount == 1) {              my $relations = $entityData->{Relations};
1863                          # Here we have our first list, so we save its count.              for my $relation (keys %{$relations}) {
1864                          $recordCount = $thisCount;                  my @augmentedList = (@stackedPath, $relation);
1865                      } elsif ($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;  
1866                      }                      }
1867                  }                  }
1868            # Now we need to look for relationships connected to this entity.
1869            my $relationshipList = $self->{_metaData}->{Relationships};
1870            for my $relationshipName (keys %{$relationshipList}) {
1871                my $relationship = $relationshipList->{$relationshipName};
1872                # Check the FROM field. We're only interested if it's us.
1873                if ($relationship->{from} eq $myEntityName) {
1874                    # Add the path to this relationship.
1875                    my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1876                    push @fromPathList, \@augmentedList;
1877                    # Check the arity. If it's MM we're done. If it's 1M
1878                    # and the target hasn't been seen yet, we want to
1879                    # stack the entity for future processing.
1880                    if ($relationship->{arity} eq '1M') {
1881                        my $toEntity = $relationship->{to};
1882                        if (! exists $alreadyFound{$toEntity}) {
1883                            # Here we have a new entity that's dependent on
1884                            # the current entity, so we need to stack it.
1885                            my @stackList = (@augmentedList, $toEntity);
1886                            push @fromPathList, \@stackList;
1887              } else {              } else {
1888                  # Here the field is not present. Flag it as missing.                          Trace("$toEntity ignored because it occurred previously.") if T(4);
                 push @missing, $fieldName;  
1889              }              }
1890          }          }
         # If we are the primary relation, add the new-record flag.  
         if ($relationName eq $newObjectType) {  
             push @valueList, 1;  
             push @fieldNameList, "new_record";  
1891          }          }
1892          # Only proceed if there are no missing fields.              # Now check the TO field. In this case only the relationship needs
1893          if (@missing > 0) {              # deletion.
1894              Trace("Relation $relationName for $newObjectType skipped due to missing fields: " .              if ($relationship->{to} eq $myEntityName) {
1895                  join(' ', @missing)) if T(1);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1896          } 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;  
1897                      }                      }
1898                  }                  }
                 # 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);  
1899                  }                  }
1900        # Create the first qualifier for the WHERE clause. This selects the
1901        # keys of the primary entity records to be deleted. When we're deleting
1902        # from a dependent table, we construct a join path from the first qualifier
1903        # to the table containing the dependent records to delete.
1904        my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
1905        # We need to make two passes. The first is through the to-list, and
1906        # the second through the from-list. The from-list is second because
1907        # the to-list may need to pass through some of the entities the
1908        # from-list would delete.
1909        my %stackList = ( from_link => \@fromPathList, to_link => \@toPathList );
1910        # Now it's time to do the deletes. We do it in two passes.
1911        for my $keyName ('to_link', 'from_link') {
1912            # Get the list for this key.
1913            my @pathList = @{$stackList{$keyName}};
1914            Trace(scalar(@pathList) . " entries in path list for $keyName.") if T(3);
1915            # Loop through this list.
1916            while (my $path = pop @pathList) {
1917                # Get the table whose rows are to be deleted.
1918                my @pathTables = @{$path};
1919                # Start the DELETE statement. We need to call DBKernel because the
1920                # syntax of a DELETE-USING varies among DBMSs.
1921                my $target = $pathTables[$#pathTables];
1922                my $stmt = $db->SetUsing(@pathTables);
1923                # Now start the WHERE. The first thing is the ID field from the starting table. That
1924                # starting table will either be the entity relation or one of the entity's
1925                # sub-relations.
1926                $stmt .= " WHERE $pathTables[0].id $qualifier";
1927                # Now we run through the remaining entities in the path, connecting them up.
1928                for (my $i = 1; $i <= $#pathTables; $i += 2) {
1929                    # Connect the current relationship to the preceding entity.
1930                    my ($entity, $rel) = @pathTables[$i-1,$i];
1931                    # The style of connection depends on the direction of the relationship.
1932                    $stmt .= " AND $entity.id = $rel.$keyName";
1933                    if ($i + 1 <= $#pathTables) {
1934                        # Here there's a next entity, so connect that to the relationship's
1935                        # to-link.
1936                        my $entity2 = $pathTables[$i+1];
1937                        $stmt .= " AND $rel.to_link = $entity2.id";
1938                    }
1939                }
1940                # Now we have our desired DELETE statement.
1941                if ($options{testMode}) {
1942                    # Here the user wants to trace without executing.
1943                    Trace($stmt) if T(0);
1944                } else {
1945                    # Here we can delete. Note that the SQL method dies with a confession
1946                    # if an error occurs, so we just go ahead and do it.
1947                    Trace("Executing delete from $target using '$objectID'.") if T(3);
1948                    my $rv = $db->SQL($stmt, 0, $objectID);
1949                    # Accumulate the statistics for this delete. The only rows deleted
1950                    # are from the target table, so we use its name to record the
1951                    # statistic.
1952                    $retVal->Add($target, $rv);
1953              }              }
1954          }          }
1955      }      }
1956      # Return the success indicator.      # Return the result.
1957      return $retVal;      return $retVal;
1958  }  }
1959    
1960  =head3 LoadTable  =head3 Disconnect
1961    
1962  C<< my %results = $database->LoadTable($fileName, $relationName, $truncateFlag); >>  C<< $erdb->Disconnect($relationshipName, $originEntityName, $originEntityID); >>
1963    
1964  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
1965  first.  will delete each relationship instance that connects to the specified entity.
1966    
1967  =over 4  =over 4
1968    
1969  =item fileName  =item relationshipName
   
 Name of the file from which the table data should be loaded.  
   
 =item relationName  
1970    
1971  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.
1972    
1973  =item truncateFlag  =item originEntityName
1974    
1975  TRUE if the table should be dropped and re-created, else FALSE  Name of the entity that is to be disconnected.
1976    
1977  =item RETURN  =item originEntityID
1978    
1979  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.  
1980    
1981  =back  =back
1982    
1983  =cut  =cut
1984  sub LoadTable {  
1985    sub Disconnect {
1986      # Get the parameters.      # Get the parameters.
1987      my ($self, $fileName, $relationName, $truncateFlag) = @_;      my ($self, $relationshipName, $originEntityName, $originEntityID) = @_;
1988      # Create the statistical return object.      # Get the relationship descriptor.
1989      my $retVal = _GetLoadStats();      my $structure = $self->_GetStructure($relationshipName);
1990      # Trace the fact of the load.      # Insure we have a relationship.
1991      Trace("Loading table $relationName from $fileName") if T(2);      if (! exists $structure->{from}) {
1992            Confess("$relationshipName is not a relationship in the database.");
1993        } else {
1994      # Get the database handle.      # Get the database handle.
1995      my $dbh = $self->{_dbh};      my $dbh = $self->{_dbh};
1996      # Get the relation data.          # We'll set this value to 1 if we find our entity.
1997      my $relation = $self->_FindRelation($relationName);          my $found = 0;
1998      # Check the truncation flag.          # Loop through the ends of the relationship.
1999      if ($truncateFlag) {          for my $dir ('from', 'to') {
2000          Trace("Creating table $relationName") if T(2);              if ($structure->{$dir} eq $originEntityName) {
2001          # Re-create the table without its index.                  # Delete all relationship instances on this side of the entity instance.
2002          $self->CreateTable($relationName, 0);                  Trace("Disconnecting in $dir direction with ID \"$originEntityID\".");
2003          # If this is a pre-index DBMS, create the index here.                  $dbh->SQL("DELETE FROM $relationshipName WHERE ${dir}_link = ?", 0, $originEntityID);
2004          if ($dbh->{_preIndex}) {                  $found = 1;
             eval {  
                 $self->CreateIndex($relationName);  
             };  
             if ($@) {  
                 $retVal->AddMessage($@);  
             }  
         }  
2005      }      }
     # 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 ($@) {  
                 $retVal->AddMessage($@);  
2006              }              }
2007            # Insure we found the entity on at least one end.
2008            if (! $found) {
2009                Confess("Entity \"$originEntityName\" does not use $relationshipName.");
2010          }          }
2011      }      }
     # Commit the database changes.  
     $dbh->commit_tran;  
     # Delete the temporary file.  
     unlink $tempName;  
     # Return the statistics.  
     return $retVal;  
2012  }  }
2013    
2014  =head3 GenerateEntity  =head3 DeleteRow
2015    
2016  C<< my $fieldHash = $database->GenerateEntity($id, $type, \%values); >>  C<< $erdb->DeleteRow($relationshipName, $fromLink, $toLink, \%values); >>
2017    
2018  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
2019  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
2020  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.  
2021    
2022  =over 4  =over 4
2023    
2024  =item id  =item relationshipName
2025    
2026    Name of the relationship from which the row is to be deleted.
2027    
2028    =item fromLink
2029    
2030    ID of the entity instance in the From direction.
2031    
2032    =item toLink
2033    
2034    ID of the entity instance in the To direction.
2035    
2036    =item values
2037    
2038    Reference to a hash of other values to be used for filtering the delete.
2039    
2040    =back
2041    
2042    =cut
2043    
2044    sub DeleteRow {
2045        # Get the parameters.
2046        my ($self, $relationshipName, $fromLink, $toLink, $values) = @_;
2047        # Create a hash of all the filter information.
2048        my %filter = ('from-link' => $fromLink, 'to-link' => $toLink);
2049        if (defined $values) {
2050            for my $key (keys %{$values}) {
2051                $filter{$key} = $values->{$key};
2052            }
2053        }
2054        # Build an SQL statement out of the hash.
2055        my @filters = ();
2056        my @parms = ();
2057        for my $key (keys %filter) {
2058            push @filters, _FixName($key) . " = ?";
2059            push @parms, $filter{$key};
2060        }
2061        Trace("Parms for delete row are " . join(", ", map { "\"$_\"" } @parms) . ".") if T(SQL => 4);
2062        my $command = "DELETE FROM $relationshipName WHERE " .
2063                      join(" AND ", @filters);
2064        # Execute it.
2065        my $dbh = $self->{_dbh};
2066        $dbh->SQL($command, undef, @parms);
2067    }
2068    
2069    =head3 DeleteLike
2070    
2071    C<< my $deleteCount = $erdb->DeleteLike($relName, $filter, \@parms); >>
2072    
2073    Delete all the relationship rows that satisfy a particular filter condition. Unlike a normal
2074    filter, only fields from the relationship itself can be used.
2075    
2076    =over 4
2077    
2078    =item relName
2079    
2080    Name of the relationship whose records are to be deleted.
2081    
2082    =item filter
2083    
2084    A filter clause (L</Get>-style) for the delete query.
2085    
2086    =item parms
2087    
2088    Reference to a list of parameters for the filter clause.
2089    
2090    =item RETURN
2091    
2092    Returns a count of the number of rows deleted.
2093    
2094    =back
2095    
2096    =cut
2097    
2098    sub DeleteLike {
2099        # Get the parameters.
2100        my ($self, $objectName, $filter, $parms) = @_;
2101        # Declare the return variable.
2102        my $retVal;
2103        # Insure the parms argument is an array reference if the caller left it off.
2104        if (! defined($parms)) {
2105            $parms = [];
2106        }
2107        # Insure we have a relationship. The main reason for this is if we delete an entity
2108        # instance we have to yank out a bunch of other stuff with it.
2109        if ($self->IsEntity($objectName)) {
2110            Confess("Cannot use DeleteLike on $objectName, because it is not a relationship.");
2111        } else {
2112            # Create the SQL command suffix to get the desierd records.
2113            my ($suffix) = $self->_SetupSQL([$objectName], $filter);
2114            # Convert it to a DELETE command.
2115            my $command = "DELETE $suffix";
2116            # Execute the command.
2117            my $dbh = $self->{_dbh};
2118            my $result = $dbh->SQL($command, 0, @{$parms});
2119            # Check the results. Note we convert the "0D0" result to a real zero.
2120            # A failure causes an abnormal termination, so the caller isn't going to
2121            # worry about it.
2122            if (! defined $result) {
2123                Confess("Error deleting from $objectName: " . $dbh->errstr());
2124            } elsif ($result == 0) {
2125                $retVal = 0;
2126            } else {
2127                $retVal = $result;
2128            }
2129        }
2130        # Return the result count.
2131        return $retVal;
2132    }
2133    
2134    =head3 SortNeeded
2135    
2136    C<< my $parms = $erdb->SortNeeded($relationName); >>
2137    
2138    Return the pipe command for the sort that should be applied to the specified
2139    relation when creating the load file.
2140    
2141    For example, if the load file should be sorted ascending by the first
2142    field, this method would return
2143    
2144        sort -k1 -t"\t"
2145    
2146    If the first field is numeric, the method would return
2147    
2148        sort -k1n -t"\t"
2149    
2150    Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate
2151    keys using a sort.
2152    
2153    =over 4
2154    
2155    =item relationName
2156    
2157    Name of the relation to be examined.
2158    
2159    =item
2160    
2161    Returns the sort command to use for sorting the relation, suitable for piping.
2162    
2163    =back
2164    
2165    =cut
2166    #: Return Type $;
2167    sub SortNeeded {
2168        # Get the parameters.
2169        my ($self, $relationName) = @_;
2170        # Declare a descriptor to hold the names of the key fields.
2171        my @keyNames = ();
2172        # Get the relation structure.
2173        my $relationData = $self->_FindRelation($relationName);
2174        # Find out if the relation is a primary entity relation,
2175        # a relationship relation, or a secondary entity relation.
2176        my $entityTable = $self->{_metaData}->{Entities};
2177        my $relationshipTable = $self->{_metaData}->{Relationships};
2178        if (exists $entityTable->{$relationName}) {
2179            # Here we have a primary entity relation.
2180            push @keyNames, "id";
2181        } elsif (exists $relationshipTable->{$relationName}) {
2182            # Here we have a relationship. We sort using the FROM index.
2183            my $relationshipData = $relationshipTable->{$relationName};
2184            my $index = $relationData->{Indexes}->{idxFrom};
2185            push @keyNames, @{$index->{IndexFields}};
2186        } else {
2187            # Here we have a secondary entity relation, so we have a sort on the ID field.
2188            push @keyNames, "id";
2189        }
2190        # Now we parse the key names into sort parameters. First, we prime the return
2191        # string.
2192        my $retVal = "sort -t\"\t\" ";
2193        # Get the relation's field list.
2194        my @fields = @{$relationData->{Fields}};
2195        # Loop through the keys.
2196        for my $keyData (@keyNames) {
2197            # Get the key and the ordering.
2198            my ($keyName, $ordering);
2199            if ($keyData =~ /^([^ ]+) DESC/) {
2200                ($keyName, $ordering) = ($1, "descending");
2201            } else {
2202                ($keyName, $ordering) = ($keyData, "ascending");
2203            }
2204            # Find the key's position and type.
2205            my $fieldSpec;
2206            for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {
2207                my $thisField = $fields[$i];
2208                if ($thisField->{name} eq $keyName) {
2209                    # Get the sort modifier for this field type. The modifier
2210                    # decides whether we're using a character, numeric, or
2211                    # floating-point sort.
2212                    my $modifier = $TypeTable{$thisField->{type}}->{sort};
2213                    # If the index is descending for this field, denote we want
2214                    # to reverse the sort order on this field.
2215                    if ($ordering eq 'descending') {
2216                        $modifier .= "r";
2217                    }
2218                    # Store the position and modifier into the field spec, which
2219                    # will stop the inner loop. Note that the field number is
2220                    # 1-based in the sort command, so we have to increment the
2221                    # index.
2222                    $fieldSpec = ($i + 1) . $modifier;
2223                }
2224            }
2225            # Add this field to the sort command.
2226            $retVal .= " -k$fieldSpec";
2227        }
2228        # Return the result.
2229        return $retVal;
2230    }
2231    
2232    =head3 GetList
2233    
2234    C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>
2235    
2236    Return a list of object descriptors for the specified objects as determined by the
2237    specified filter clause.
2238    
2239    This method is essentially the same as L</Get> except it returns a list of objects rather
2240    than a query object that can be used to get the results one record at a time.
2241    
2242    =over 4
2243    
2244    =item objectNames
2245    
2246    List containing the names of the entity and relationship objects to be retrieved.
2247    
2248    =item filterClause
2249    
2250    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
2251    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
2252    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
2253    in the filter clause should be added to the parameter list as additional parameters. The
2254    fields in a filter clause can come from primary entity relations, relationship relations,
2255    or secondary entity relations; however, all of the entities and relationships involved must
2256    be included in the list of object names.
2257    
2258    The filter clause can also specify a sort order. To do this, simply follow the filter string
2259    with an ORDER BY clause. For example, the following filter string gets all genomes for a
2260    particular genus and sorts them by species name.
2261    
2262    C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
2263    
2264    The rules for field references in a sort order are the same as those for field references in the
2265    filter clause in general; however, odd things may happen if a sort field is from a secondary
2266    relation.
2267    
2268    =item params
2269    
2270    Reference to a list of parameter values to be substituted into the filter clause.
2271    
2272    =item RETURN
2273    
2274    Returns a list of B<ERDBObject>s that satisfy the query conditions.
2275    
2276    =back
2277    
2278    =cut
2279    #: Return Type @%
2280    sub GetList {
2281        # Get the parameters.
2282        my ($self, $objectNames, $filterClause, $params) = @_;
2283        # Declare the return variable.
2284        my @retVal = ();
2285        # Perform the query.
2286        my $query = $self->Get($objectNames, $filterClause, $params);
2287        # Loop through the results.
2288        while (my $object = $query->Fetch) {
2289            push @retVal, $object;
2290        }
2291        # Return the result.
2292        return @retVal;
2293    }
2294    
2295    =head3 GetCount
2296    
2297    C<< my $count = $erdb->GetCount(\@objectNames, $filter, \@params); >>
2298    
2299    Return the number of rows found by a specified query. This method would
2300    normally be used to count the records in a single table. For example, in a
2301    genetics database
2302    
2303        my $count = $erdb->GetCount(['Genome'], 'Genome(genus-species) LIKE ?', ['homo %']);
2304    
2305    would return the number of genomes for the genus I<homo>. It is conceivable, however,
2306    to use it to return records based on a join. For example,
2307    
2308        my $count = $erdb->GetCount(['HasFeature', 'Genome'], 'Genome(genus-species) LIKE ?',
2309                                    ['homo %']);
2310    
2311    would return the number of features for genomes in the genus I<homo>. Note that
2312    only the rows from the first table are counted. If the above command were
2313    
2314        my $count = $erdb->GetCount(['Genome', 'Feature'], 'Genome(genus-species) LIKE ?',
2315                                    ['homo %']);
2316    
2317    it would return the number of genomes, not the number of genome/feature pairs.
2318    
2319    =over 4
2320    
2321    =item objectNames
2322    
2323    Reference to a list of the objects (entities and relationships) included in the
2324    query.
2325    
2326    =item filter
2327    
2328    A filter clause for restricting the query. The rules are the same as for the L</Get>
2329    method.
2330    
2331    =item params
2332    
2333    Reference to a list of the parameter values to be substituted for the parameter marks
2334    in the filter.
2335    
2336    =item RETURN
2337    
2338    Returns a count of the number of records in the first table that would satisfy
2339    the query.
2340    
2341    =back
2342    
2343    =cut
2344    
2345    sub GetCount {
2346        # Get the parameters.
2347        my ($self, $objectNames, $filter, $params) = @_;
2348        # Insure the params argument is an array reference if the caller left it off.
2349        if (! defined($params)) {
2350            $params = [];
2351        }
2352        # Declare the return variable.
2353        my $retVal;
2354        # Find out if we're counting an entity or a relationship.
2355        my $countedField;
2356        if ($self->IsEntity($objectNames->[0])) {
2357            $countedField = "id";
2358        } else {
2359            # For a relationship we count the to-link because it's usually more
2360            # numerous. Note we're automatically converting to the SQL form
2361            # of the field name (to_link vs. to-link).
2362            $countedField = "to_link";
2363        }
2364        # Create the SQL command suffix to get the desired records.
2365        my ($suffix, $mappedNameListRef, $mappedNameHashRef) = $self->_SetupSQL($objectNames,
2366                                                                                $filter);
2367        # Prefix it with text telling it we want a record count.
2368        my $firstObject = $mappedNameListRef->[0];
2369        my $command = "SELECT COUNT($firstObject.$countedField) $suffix";
2370        # Prepare and execute the command.
2371        my $sth = $self->_GetStatementHandle($command, $params);
2372        # Get the count value.
2373        ($retVal) = $sth->fetchrow_array();
2374        # Check for a problem.
2375        if (! defined($retVal)) {
2376            if ($sth->err) {
2377                # Here we had an SQL error.
2378                Confess("Error retrieving row count: " . $sth->errstr());
2379            } else {
2380                # Here we have no result.
2381                Confess("No result attempting to retrieve row count.");
2382            }
2383        }
2384        # Return the result.
2385        return $retVal;
2386    }
2387    
2388    =head3 ComputeObjectSentence
2389    
2390    C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>
2391    
2392    Check an object name, and if it is a relationship convert it to a relationship sentence.
2393    
2394    =over 4
2395    
2396    =item objectName
2397    
2398    Name of the entity or relationship.
2399    
2400    =item RETURN
2401    
2402    Returns a string containing the entity name or a relationship sentence.
2403    
2404    =back
2405    
2406    =cut
2407    
2408    sub ComputeObjectSentence {
2409        # Get the parameters.
2410        my ($self, $objectName) = @_;
2411        # Set the default return value.
2412        my $retVal = $objectName;
2413        # Look for the object as a relationship.
2414        my $relTable = $self->{_metaData}->{Relationships};
2415        if (exists $relTable->{$objectName}) {
2416            # Get the relationship sentence.
2417            $retVal = _ComputeRelationshipSentence($objectName, $relTable->{$objectName});
2418        }
2419        # Return the result.
2420        return $retVal;
2421    }
2422    
2423    =head3 DumpRelations
2424    
2425    C<< $erdb->DumpRelations($outputDirectory); >>
2426    
2427    Write the contents of all the relations to tab-delimited files in the specified directory.
2428    Each file will have the same name as the relation dumped, with an extension of DTX.
2429    
2430    =over 4
2431    
2432    =item outputDirectory
2433    
2434    Name of the directory into which the relation files should be dumped.
2435    
2436    =back
2437    
2438    =cut
2439    
2440    sub DumpRelations {
2441        # Get the parameters.
2442        my ($self, $outputDirectory) = @_;
2443        # Now we need to run through all the relations. First, we loop through the entities.
2444        my $metaData = $self->{_metaData};
2445        my $entities = $metaData->{Entities};
2446        for my $entityName (keys %{$entities}) {
2447            my $entityStructure = $entities->{$entityName};
2448            # Get the entity's relations.
2449            my $relationList = $entityStructure->{Relations};
2450            # Loop through the relations, dumping them.
2451            for my $relationName (keys %{$relationList}) {
2452                my $relation = $relationList->{$relationName};
2453                $self->_DumpRelation($outputDirectory, $relationName, $relation);
2454            }
2455        }
2456        # Next, we loop through the relationships.
2457        my $relationships = $metaData->{Relationships};
2458        for my $relationshipName (keys %{$relationships}) {
2459            my $relationshipStructure = $relationships->{$relationshipName};
2460            # Dump this relationship's relation.
2461            $self->_DumpRelation($outputDirectory, $relationshipName, $relationshipStructure->{Relations}->{$relationshipName});
2462        }
2463    }
2464    
2465    =head3 InsertValue
2466    
2467    C<< $erdb->InsertValue($entityID, $fieldName, $value); >>
2468    
2469    This method will insert a new value into the database. The value must be one
2470    associated with a secondary relation, since primary values cannot be inserted:
2471    they occur exactly once. Secondary values, on the other hand, can be missing
2472    or multiply-occurring.
2473    
2474    =over 4
2475    
2476    =item entityID
2477    
2478    ID of the object that is to receive the new value.
2479    
2480    =item fieldName
2481    
2482    Field name for the new value-- this includes the entity name, since
2483    field names are of the format I<objectName>C<(>I<fieldName>C<)>.
2484    
2485    =item value
2486    
2487    New value to be put in the field.
2488    
2489    =back
2490    
2491    =cut
2492    
2493    sub InsertValue {
2494        # Get the parameters.
2495        my ($self, $entityID, $fieldName, $value) = @_;
2496        # Parse the entity name and the real field name.
2497        if ($fieldName =~ /^([^(]+)\(([^)]+)\)/) {
2498            my $entityName = $1;
2499            my $fieldTitle = $2;
2500            # Get its descriptor.
2501            if (!$self->IsEntity($entityName)) {
2502                Confess("$entityName is not a valid entity.");
2503            } else {
2504                my $entityData = $self->{_metaData}->{Entities}->{$entityName};
2505                # Find the relation containing this field.
2506                my $fieldHash = $entityData->{Fields};
2507                if (! exists $fieldHash->{$fieldTitle}) {
2508                    Confess("$fieldTitle not found in $entityName.");
2509                } else {
2510                    my $relation = $fieldHash->{$fieldTitle}->{relation};
2511                    if ($relation eq $entityName) {
2512                        Confess("Cannot do InsertValue on primary field $fieldTitle of $entityName.");
2513                    } else {
2514                        # Now we can create an INSERT statement.
2515                        my $dbh = $self->{_dbh};
2516                        my $fixedName = _FixName($fieldTitle);
2517                        my $statement = "INSERT INTO $relation (id, $fixedName) VALUES(?, ?)";
2518                        # Execute the command.
2519                        $dbh->SQL($statement, 0, $entityID, $value);
2520                    }
2521                }
2522            }
2523        } else {
2524            Confess("$fieldName is not a valid field name.");
2525        }
2526    }
2527    
2528    =head3 InsertObject
2529    
2530    C<< $erdb->InsertObject($objectType, \%fieldHash); >>
2531    
2532    Insert an object into the database. The object is defined by a type name and then a hash
2533    of field names to values. Field values in the primary relation are represented by scalars.
2534    (Note that for relationships, the primary relation is the B<only> relation.)
2535    Field values for the other relations comprising the entity are always list references. For
2536    example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases
2537    C<ZP_00210270.1> and C<gi|46206278>.
2538    
2539    C<< $erdb->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>
2540    
2541    The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
2542    property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
2543    
2544    C<< $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>
2545    
2546    =over 4
2547    
2548    =item newObjectType
2549    
2550    Type name of the object to insert.
2551    
2552    =item fieldHash
2553    
2554    Hash of field names to values.
2555    
2556    =back
2557    
2558    =cut
2559    
2560    sub InsertObject {
2561        # Get the parameters.
2562        my ($self, $newObjectType, $fieldHash) = @_;
2563        # Denote that so far we appear successful.
2564        my $retVal = 1;
2565        # Get the database handle.
2566        my $dbh = $self->{_dbh};
2567        # Get the relation list.
2568        my $relationTable = $self->_GetRelationTable($newObjectType);
2569        # Loop through the relations. We'll build insert statements for each one. If a relation is
2570        # secondary, we may end up generating multiple insert statements. If an error occurs, we
2571        # stop the loop.
2572        my @relationList = keys %{$relationTable};
2573        for (my $i = 0; $retVal && $i <= $#relationList; $i++) {
2574            my $relationName = $relationList[$i];
2575            my $relationDefinition = $relationTable->{$relationName};
2576            # Get the relation's fields. For each field we will collect a value in the corresponding
2577            # position of the @valueList array. If one of the fields is missing, we will add it to the
2578            # @missing list.
2579            my @fieldList = @{$relationDefinition->{Fields}};
2580            my @fieldNameList = ();
2581            my @valueList = ();
2582            my @missing = ();
2583            my $recordCount = 1;
2584            for my $fieldDescriptor (@fieldList) {
2585                # Get the field name and save it. Note we need to fix it up so the hyphens
2586                # are converted to underscores.
2587                my $fieldName = $fieldDescriptor->{name};
2588                push @fieldNameList, _FixName($fieldName);
2589                # Look for the named field in the incoming structure. Note that we are looking
2590                # for the real field name, not the fixed-up one!
2591                if (exists $fieldHash->{$fieldName}) {
2592                    # Here we found the field. Stash it in the value list.
2593                    my $value = $fieldHash->{$fieldName};
2594                    push @valueList, $value;
2595                    # If the value is a list, we may need to increment the record count.
2596                    if (ref $value eq "ARRAY") {
2597                        my $thisCount = @{$value};
2598                        if ($recordCount == 1) {
2599                            # Here we have our first list, so we save its count.
2600                            $recordCount = $thisCount;
2601                        } elsif ($recordCount != $thisCount) {
2602                            # Here we have a second list, so its length has to match the
2603                            # previous lists.
2604                            Trace("Field $value in new $newObjectType object has an invalid list length $thisCount. Expected $recordCount.") if T(0);
2605                            $retVal = 0;
2606                        }
2607                    }
2608                } else {
2609                    # Here the field is not present. Flag it as missing.
2610                    push @missing, $fieldName;
2611                }
2612            }
2613            # If we are the primary relation, add the new-record flag.
2614            if ($relationName eq $newObjectType) {
2615                push @valueList, 1;
2616                push @fieldNameList, "new_record";
2617            }
2618            # Only proceed if there are no missing fields.
2619            if (@missing > 0) {
2620                Trace("Relation $relationName for $newObjectType skipped due to missing fields: " .
2621                    join(' ', @missing)) if T(1);
2622            } else {
2623                # Build the INSERT statement.
2624                my $statement = "INSERT INTO $relationName (" . join (', ', @fieldNameList) .
2625                    ") VALUES (";
2626                # Create a marker list of the proper size and put it in the statement.
2627                my @markers = ();
2628                while (@markers < @fieldNameList) { push @markers, '?'; }
2629                $statement .= join(', ', @markers) . ")";
2630                # We have the insert statement, so prepare it.
2631                my $sth = $dbh->prepare_command($statement);
2632                Trace("Insert statement prepared: $statement") if T(3);
2633                # Now we loop through the values. If a value is scalar, we use it unmodified. If it's
2634                # a list, we use the current element. The values are stored in the @parameterList array.
2635                my $done = 0;
2636                for (my $i = 0; $i < $recordCount; $i++) {
2637                    # Clear the parameter list array.
2638                    my @parameterList = ();
2639                    # Loop through the values.
2640                    for my $value (@valueList) {
2641                        # Check to see if this is a scalar value.
2642                        if (ref $value eq "ARRAY") {
2643                            # Here we have a list value. Pull the current entry.
2644                            push @parameterList, $value->[$i];
2645                        } else {
2646                            # Here we have a scalar value. Use it unmodified.
2647                            push @parameterList, $value;
2648                        }
2649                    }
2650                    # Execute the INSERT statement with the specified parameter list.
2651                    $retVal = $sth->execute(@parameterList);
2652                    if (!$retVal) {
2653                        my $errorString = $sth->errstr();
2654                        Confess("Error inserting into $relationName: $errorString");
2655                    } else {
2656                        Trace("Insert successful using $parameterList[0].") if T(3);
2657                    }
2658                }
2659            }
2660        }
2661        # Return a 1 for backward compatability.
2662        return 1;
2663    }
2664    
2665    =head3 UpdateEntity
2666    
2667    C<< $erdb->UpdateEntity($entityName, $id, \%fields); >>
2668    
2669    Update the values of an entity. This is an unprotected update, so it should only be
2670    done if the database resides on a database server.
2671    
2672    =over 4
2673    
2674    =item entityName
2675    
2676    Name of the entity to update. (This is the entity type.)
2677    
2678    =item id
2679    
2680    ID of the entity to update. If no entity exists with this ID, an error will be thrown.
2681    
2682    =item fields
2683    
2684    Reference to a hash mapping field names to their new values. All of the fields named
2685    must be in the entity's primary relation, and they cannot any of them be the ID field.
2686    
2687    =back
2688    
2689    =cut
2690    
2691    sub UpdateEntity {
2692        # Get the parameters.
2693        my ($self, $entityName, $id, $fields) = @_;
2694        # Get a list of the field names being updated.
2695        my @fieldList = keys %{$fields};
2696        # Verify that the fields exist.
2697        my $checker = $self->GetFieldTable($entityName);
2698        for my $field (@fieldList) {
2699            if ($field eq 'id') {
2700                Confess("Cannot update the ID field for entity $entityName.");
2701            } elsif ($checker->{$field}->{relation} ne $entityName) {
2702                Confess("Cannot find $field in primary relation of $entityName.");
2703            }
2704        }
2705        # Build the SQL statement.
2706        my @sets = ();
2707        my @valueList = ();
2708        for my $field (@fieldList) {
2709            push @sets, _FixName($field) . " = ?";
2710            push @valueList, $fields->{$field};
2711        }
2712        my $command = "UPDATE $entityName SET " . join(", ", @sets) . " WHERE id = ?";
2713        # Add the ID to the list of binding values.
2714        push @valueList, $id;
2715        # Call SQL to do the work.
2716        my $rows = $self->{_dbh}->SQL($command, 0, @valueList);
2717        # Check for errors.
2718        if ($rows == 0) {
2719            Confess("Entity $id of type $entityName not found.");
2720        }
2721    }
2722    
2723    =head3 LoadTable
2724    
2725    C<< my $results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>
2726    
2727    Load data from a tab-delimited file into a specified table, optionally re-creating the table
2728    first.
2729    
2730    =over 4
2731    
2732    =item fileName
2733    
2734    Name of the file from which the table data should be loaded.
2735    
2736    =item relationName
2737    
2738    Name of the relation to be loaded. This is the same as the table name.
2739    
2740    =item truncateFlag
2741    
2742    TRUE if the table should be dropped and re-created, else FALSE
2743    
2744    =item RETURN
2745    
2746    Returns a statistical object containing a list of the error messages.
2747    
2748    =back
2749    
2750    =cut
2751    sub LoadTable {
2752        # Get the parameters.
2753        my ($self, $fileName, $relationName, $truncateFlag) = @_;
2754        # Create the statistical return object.
2755        my $retVal = _GetLoadStats();
2756        # Trace the fact of the load.
2757        Trace("Loading table $relationName from $fileName") if T(2);
2758        # Get the database handle.
2759        my $dbh = $self->{_dbh};
2760        # Get the input file size.
2761        my $fileSize = -s $fileName;
2762        # Get the relation data.
2763        my $relation = $self->_FindRelation($relationName);
2764        # Check the truncation flag.
2765        if ($truncateFlag) {
2766            Trace("Creating table $relationName") if T(2);
2767            # Compute the row count estimate. We take the size of the load file,
2768            # divide it by the estimated row size, and then multiply by 1.5 to
2769            # leave extra room. We postulate a minimum row count of 1000 to
2770            # prevent problems with incoming empty load files.
2771            my $rowSize = $self->EstimateRowSize($relationName);
2772            my $estimate = $fileSize * 1.5 / $rowSize;
2773            if ($estimate < 1000) {
2774                $estimate = 1000;
2775            }
2776            # Re-create the table without its index.
2777            $self->CreateTable($relationName, 0, $estimate);
2778            # If this is a pre-index DBMS, create the index here.
2779            if ($dbh->{_preIndex}) {
2780                eval {
2781                    $self->CreateIndex($relationName);
2782                };
2783                if ($@) {
2784                    $retVal->AddMessage($@);
2785                }
2786            }
2787        }
2788        # Load the table.
2789        my $rv;
2790        eval {
2791            $rv = $dbh->load_table(file => $fileName, tbl => $relationName);
2792        };
2793        if (!defined $rv) {
2794            $retVal->AddMessage($@) if ($@);
2795            $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2796            Trace("Table load failed for $relationName.") if T(1);
2797        } else {
2798            # Here we successfully loaded the table.
2799            $retVal->Add("tables");
2800            my $size = -s $fileName;
2801            Trace("$size bytes loaded into $relationName.") if T(2);
2802            # If we're rebuilding, we need to create the table indexes.
2803            if ($truncateFlag) {
2804                # Indexes are created here for PostGres. For PostGres, indexes are
2805                # best built at the end. For MySQL, the reverse is true.
2806                if (! $dbh->{_preIndex}) {
2807                    eval {
2808                        $self->CreateIndex($relationName);
2809                    };
2810                    if ($@) {
2811                        $retVal->AddMessage($@);
2812                    }
2813                }
2814                # The full-text index (if any) is always built last, even for MySQL.
2815                # First we need to see if this table has a full-text index. Only
2816                # primary relations are allowed that privilege.
2817                Trace("Checking for full-text index on $relationName.") if T(2);
2818                if ($self->_IsPrimary($relationName)) {
2819                    $self->CreateSearchIndex($relationName);
2820                }
2821            }
2822        }
2823        # Analyze the table to improve performance.
2824        Trace("Analyzing and compacting $relationName.") if T(3);
2825        $dbh->vacuum_it($relationName);
2826        Trace("$relationName load completed.") if T(3);
2827        # Return the statistics.
2828        return $retVal;
2829    }
2830    
2831    =head3 CreateSearchIndex
2832    
2833    C<< $erdb->CreateSearchIndex($objectName); >>
2834    
2835    Check for a full-text search index on the specified entity or relationship object, and
2836    if one is required, rebuild it.
2837    
2838    =over 4
2839    
2840    =item objectName
2841    
2842    Name of the entity or relationship to be indexed.
2843    
2844    =back
2845    
2846    =cut
2847    
2848    sub CreateSearchIndex {
2849        # Get the parameters.
2850        my ($self, $objectName) = @_;
2851        # Get the relation's entity/relationship structure.
2852        my $structure = $self->_GetStructure($objectName);
2853        # Get the database handle.
2854        my $dbh = $self->{_dbh};
2855        Trace("Checking for search fields in $objectName.") if T(3);
2856        # Check for a searchable fields list.
2857        if (exists $structure->{searchFields}) {
2858            # Here we know that we need to create a full-text search index.
2859            # Get an SQL-formatted field name list.
2860            my $fields = join(", ", _FixNames(@{$structure->{searchFields}}));
2861            # Create the index. If it already exists, it will be dropped.
2862            $dbh->create_index(tbl => $objectName, idx => "search_idx",
2863                               flds => $fields, kind => 'fulltext');
2864            Trace("Index created for $fields in $objectName.") if T(2);
2865        }
2866    }
2867    
2868    =head3 DropRelation
2869    
2870    C<< $erdb->DropRelation($relationName); >>
2871    
2872    Physically drop a relation from the database.
2873    
2874    =over 4
2875    
2876    =item relationName
2877    
2878    Name of the relation to drop. If it does not exist, this method will have
2879    no effect.
2880    
2881    =back
2882    
2883    =cut
2884    
2885    sub DropRelation {
2886        # Get the parameters.
2887        my ($self, $relationName) = @_;
2888        # Get the database handle.
2889        my $dbh = $self->{_dbh};
2890        # Drop the relation. The method used here has no effect if the relation
2891        # does not exist.
2892        Trace("Invoking DB Kernel to drop $relationName.") if T(3);
2893        $dbh->drop_table(tbl => $relationName);
2894    }
2895    
2896    =head3 MatchSqlPattern
2897    
2898    C<< my $matched = ERDB::MatchSqlPattern($value, $pattern); >>
2899    
2900    Determine whether or not a specified value matches an SQL pattern. An SQL
2901    pattern has two wild card characters: C<%> that matches multiple characters,
2902    and C<_> that matches a single character. These can be escaped using a
2903    backslash (C<\>). We pull this off by converting the SQL pattern to a
2904    PERL regular expression. As per SQL rules, the match is case-insensitive.
2905    
2906    =over 4
2907    
2908    =item value
2909    
2910    Value to be matched against the pattern. Note that an undefined or empty
2911    value will not match anything.
2912    
2913    =item pattern
2914    
2915    SQL pattern against which to match the value. An undefined or empty pattern will
2916    match everything.
2917    
2918    =item RETURN
2919    
2920    Returns TRUE if the value and pattern match, else FALSE.
2921    
2922    =back
2923    
2924    =cut
2925    
2926    sub MatchSqlPattern {
2927        # Get the parameters.
2928        my ($value, $pattern) = @_;
2929        # Declare the return variable.
2930        my $retVal;
2931        # Insure we have a pattern.
2932        if (! defined($pattern) || $pattern eq "") {
2933            $retVal = 1;
2934        } else {
2935            # Break the pattern into pieces around the wildcard characters. Because we
2936            # use parentheses in the split function's delimiter expression, we'll get
2937            # list elements for the delimiters as well as the rest of the string.
2938            my @pieces = split /([_%]|\\[_%])/, $pattern;
2939            # Check some fast special cases.
2940            if ($pattern eq '%') {
2941                # A null pattern matches everything.
2942                $retVal = 1;
2943            } elsif (@pieces == 1) {
2944                # No wildcards, so we have a literal comparison. Note we're case-insensitive.
2945                $retVal = (lc($value) eq lc($pattern));
2946            } elsif (@pieces == 2 && $pieces[1] eq '%') {
2947                # A wildcard at the end, so we have a substring match. This is also case-insensitive.
2948                $retVal = (lc(substr($value, 0, length($pieces[0]))) eq lc($pieces[0]));
2949            } else {
2950                # Okay, we have to do it the hard way. Convert each piece to a PERL pattern.
2951                my $realPattern = "";
2952                for my $piece (@pieces) {
2953                    # Determine the type of piece.
2954                    if ($piece eq "") {
2955                        # Empty pieces are ignored.
2956                    } elsif ($piece eq "%") {
2957                        # Here we have a multi-character wildcard. Note that it can match
2958                        # zero or more characters.
2959                        $realPattern .= ".*"
2960                    } elsif ($piece eq "_") {
2961                        # Here we have a single-character wildcard.
2962                        $realPattern .= ".";
2963                    } elsif ($piece eq "\\%" || $piece eq "\\_") {
2964                        # This is an escape sequence (which is a rare thing, actually).
2965                        $realPattern .= substr($piece, 1, 1);
2966                    } else {
2967                        # Here we have raw text.
2968                        $realPattern .= quotemeta($piece);
2969                    }
2970                }
2971                # Do the match.
2972                $retVal = ($value =~ /^$realPattern$/i ? 1 : 0);
2973            }
2974        }
2975        # Return the result.
2976        return $retVal;
2977    }
2978    
2979    =head3 GetEntity
2980    
2981    C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>
2982    
2983    Return an object describing the entity instance with a specified ID.
2984    
2985    =over 4
2986    
2987    =item entityType
2988    
2989    Entity type name.
2990    
2991    =item ID
2992    
2993    ID of the desired entity.
2994    
2995    =item RETURN
2996    
2997    Returns a B<ERDBObject> representing the desired entity instance, or an undefined value if no
2998    instance is found with the specified key.
2999    
3000    =back
3001    
3002    =cut
3003    
3004    sub GetEntity {
3005        # Get the parameters.
3006        my ($self, $entityType, $ID) = @_;
3007        # Create a query.
3008        my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);
3009        # Get the first (and only) object.
3010        my $retVal = $query->Fetch();
3011        # Return the result.
3012        return $retVal;
3013    }
3014    
3015    =head3 GetChoices
3016    
3017    C<< my @values = $erdb->GetChoices($entityName, $fieldName); >>
3018    
3019    Return a list of all the values for the specified field that are represented in the
3020    specified entity.
3021    
3022    Note that if the field is not indexed, then this will be a very slow operation.
3023    
3024    =over 4
3025    
3026    =item entityName
3027    
3028    Name of an entity in the database.
3029    
3030    =item fieldName
3031    
3032    Name of a field belonging to the entity. This is a raw field name without
3033    the standard parenthesized notation used in most calls.
3034    
3035    =item RETURN
3036    
3037    Returns a list of the distinct values for the specified field in the database.
3038    
3039    =back
3040    
3041    =cut
3042    
3043    sub GetChoices {
3044        # Get the parameters.
3045        my ($self, $entityName, $fieldName) = @_;
3046        # Declare the return variable.
3047        my @retVal;
3048        # Get the entity data structure.
3049        my $entityData = $self->_GetStructure($entityName);
3050        # Get the field.
3051        my $fieldHash = $entityData->{Fields};
3052        if (! exists $fieldHash->{$fieldName}) {
3053            Confess("$fieldName not found in $entityName.");
3054        } else {
3055            # Get the name of the relation containing the field.
3056            my $relation = $fieldHash->{$fieldName}->{relation};
3057            # Fix up the field name.
3058            my $realName = _FixName($fieldName);
3059            # Get the database handle.
3060            my $dbh = $self->{_dbh};
3061            # Query the database.
3062            my $results = $dbh->SQL("SELECT DISTINCT $realName FROM $relation");
3063            # Clean the results. They are stored as a list of lists, and we just want the one list.
3064            @retVal = sort map { $_->[0] } @{$results};
3065        }
3066        # Return the result.
3067        return @retVal;
3068    }
3069    
3070    =head3 GetEntityValues
3071    
3072    C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>
3073    
3074    Return a list of values from a specified entity instance. If the entity instance
3075    does not exist, an empty list is returned.
3076    
3077    =over 4
3078    
3079    =item entityType
3080    
3081    Entity type name.
3082    
3083    =item ID
3084    
3085    ID of the desired entity.
3086    
3087    =item fields
3088    
3089    List of field names, each of the form I<objectName>C<(>I<fieldName>C<)>.
3090    
3091    =item RETURN
3092    
3093    Returns a flattened list of the values of the specified fields for the specified entity.
3094    
3095    =back
3096    
3097    =cut
3098    
3099    sub GetEntityValues {
3100        # Get the parameters.
3101        my ($self, $entityType, $ID, $fields) = @_;
3102        # Get the specified entity.
3103        my $entity = $self->GetEntity($entityType, $ID);
3104        # Declare the return list.
3105        my @retVal = ();
3106        # If we found the entity, push the values into the return list.
3107        if ($entity) {
3108            push @retVal, $entity->Values($fields);
3109        }
3110        # Return the result.
3111        return @retVal;
3112    }
3113    
3114    =head3 GetAll
3115    
3116    C<< my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>
3117    
3118    Return a list of values taken from the objects returned by a query. The first three
3119    parameters correspond to the parameters of the L</Get> method. The final parameter is
3120    a list of the fields desired from each record found by the query. The field name
3121    syntax is the standard syntax used for fields in the B<ERDB> system--
3122    B<I<objectName>(I<fieldName>)>-- where I<objectName> is the name of the relevant entity
3123    or relationship and I<fieldName> is the name of the field.
3124    
3125    The list returned will be a list of lists. Each element of the list will contain
3126    the values returned for the fields specified in the fourth parameter. If one of the
3127    fields specified returns multiple values, they are flattened in with the rest. For
3128    example, the following call will return a list of the features in a particular
3129    spreadsheet cell, and each feature will be represented by a list containing the
3130    feature ID followed by all of its essentiality determinations.
3131    
3132    C<< @query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(essential)']); >>
3133    
3134    =over 4
3135    
3136    =item objectNames
3137    
3138    List containing the names of the entity and relationship objects to be retrieved.
3139    
3140    =item filterClause
3141    
3142    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
3143    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
3144    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
3145    parameter list as additional parameters. The fields in a filter clause can come from primary
3146    entity relations, relationship relations, or secondary entity relations; however, all of the
3147    entities and relationships involved must be included in the list of object names.
3148    
3149    =item parameterList
3150    
3151    List of the parameters to be substituted in for the parameters marks in the filter clause.
3152    
3153    =item fields
3154    
3155    List of the fields to be returned in each element of the list returned.
3156    
3157    =item count
3158    
3159    Maximum number of records to return. If omitted or 0, all available records will be returned.
3160    
3161    =item RETURN
3162    
3163    Returns a list of list references. Each element of the return list contains the values for the
3164    fields specified in the B<fields> parameter.
3165    
3166    =back
3167    
3168    =cut
3169    #: Return Type @@;
3170    sub GetAll {
3171        # Get the parameters.
3172        my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
3173        # Translate the parameters from a list reference to a list. If the parameter
3174        # list is a scalar we convert it into a singleton list.
3175        my @parmList = ();
3176        if (ref $parameterList eq "ARRAY") {
3177            Trace("GetAll parm list is an array.") if T(4);
3178            @parmList = @{$parameterList};
3179        } else {
3180            Trace("GetAll parm list is a scalar: $parameterList.") if T(4);
3181            push @parmList, $parameterList;
3182        }
3183        # Insure the counter has a value.
3184        if (!defined $count) {
3185            $count = 0;
3186        }
3187        # Add the row limit to the filter clause.
3188        if ($count > 0) {
3189            $filterClause .= " LIMIT $count";
3190        }
3191        # Create the query.
3192        my $query = $self->Get($objectNames, $filterClause, \@parmList);
3193        # Set up a counter of the number of records read.
3194        my $fetched = 0;
3195        # Loop through the records returned, extracting the fields. Note that if the
3196        # counter is non-zero, we stop when the number of records read hits the count.
3197        my @retVal = ();
3198        while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {
3199            my @rowData = $row->Values($fields);
3200            push @retVal, \@rowData;
3201            $fetched++;
3202        }
3203        Trace("$fetched rows returned in GetAll.") if T(SQL => 4);
3204        # Return the resulting list.
3205        return @retVal;
3206    }
3207    
3208    =head3 Exists
3209    
3210    C<< my $found = $sprout->Exists($entityName, $entityID); >>
3211    
3212    Return TRUE if an entity exists, else FALSE.
3213    
3214    =over 4
3215    
3216    =item entityName
3217    
3218    Name of the entity type (e.g. C<Feature>) relevant to the existence check.
3219    
3220    =item entityID
3221    
3222    ID of the entity instance whose existence is to be checked.
3223    
3224    =item RETURN
3225    
3226    Returns TRUE if the entity instance exists, else FALSE.
3227    
3228    =back
3229    
3230    =cut
3231    #: Return Type $;
3232    sub Exists {
3233        # Get the parameters.
3234        my ($self, $entityName, $entityID) = @_;
3235        # Check for the entity instance.
3236        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
3237        my $testInstance = $self->GetEntity($entityName, $entityID);
3238        # Return an existence indicator.
3239        my $retVal = ($testInstance ? 1 : 0);
3240        return $retVal;
3241    }
3242    
3243    =head3 EstimateRowSize
3244    
3245    C<< my $rowSize = $erdb->EstimateRowSize($relName); >>
3246    
3247    Estimate the row size of the specified relation. The estimated row size is computed by adding
3248    up the average length for each data type.
3249    
3250    =over 4
3251    
3252    =item relName
3253    
3254    Name of the relation whose estimated row size is desired.
3255    
3256    =item RETURN
3257    
3258    Returns an estimate of the row size for the specified relation.
3259    
3260    =back
3261    
3262    =cut
3263    #: Return Type $;
3264    sub EstimateRowSize {
3265        # Get the parameters.
3266        my ($self, $relName) = @_;
3267        # Declare the return variable.
3268        my $retVal = 0;
3269        # Find the relation descriptor.
3270        my $relation = $self->_FindRelation($relName);
3271        # Get the list of fields.
3272        for my $fieldData (@{$relation->{Fields}}) {
3273            # Get the field type and add its length.
3274            my $fieldLen = $TypeTable{$fieldData->{type}}->{avgLen};
3275            $retVal += $fieldLen;
3276        }
3277        # Return the result.
3278        return $retVal;
3279    }
3280    
3281    =head3 GetFieldTable
3282    
3283    C<< my $fieldHash = $self->GetFieldTable($objectnName); >>
3284    
3285    Get the field structure for a specified entity or relationship.
3286    
3287    =over 4
3288    
3289    =item objectName
3290    
3291    Name of the desired entity or relationship.
3292    
3293    =item RETURN
3294    
3295    The table containing the field descriptors for the specified object.
3296    
3297    =back
3298    
3299    =cut
3300    
3301    sub GetFieldTable {
3302        # Get the parameters.
3303        my ($self, $objectName) = @_;
3304        # Get the descriptor from the metadata.
3305        my $objectData = $self->_GetStructure($objectName);
3306        # Return the object's field table.
3307        return $objectData->{Fields};
3308    }
3309    
3310    =head3 SplitKeywords
3311    
3312    C<< my @keywords = ERDB::SplitKeywords($keywordString); >>
3313    
3314    This method returns a list of the positive keywords in the specified
3315    keyword string. All of the operators will have been stripped off,
3316    and if the keyword is preceded by a minus operator (C<->), it will
3317    not be in the list returned. The idea here is to get a list of the
3318    keywords the user wants to see. The list will be processed to remove
3319    duplicates.
3320    
3321    It is possible to create a string that confuses this method. For example
3322    
3323        frog toad -frog
3324    
3325    would return both C<frog> and C<toad>. If this is a problem we can deal
3326    with it later.
3327    
3328    =over 4
3329    
3330    =item keywordString
3331    
3332    The keyword string to be parsed.
3333    
3334    =item RETURN
3335    
3336    Returns a list of the words in the keyword string the user wants to
3337    see.
3338    
3339    =back
3340    
3341    =cut
3342    
3343    sub SplitKeywords {
3344        # Get the parameters.
3345        my ($keywordString) = @_;
3346        # Make a safety copy of the string. (This helps during debugging.)
3347        my $workString = $keywordString;
3348        # Convert operators we don't care about to spaces.
3349        $workString =~ tr/+"()<>/ /;
3350        # Split the rest of the string along space boundaries. Note that we
3351        # eliminate any words that are zero length or begin with a minus sign.
3352        my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
3353        # Use a hash to remove duplicates.
3354        my %words = map { $_ => 1 } @wordList;
3355        # Return the result.
3356        return sort keys %words;
3357    }
3358    
3359    =head3 ValidateFieldName
3360    
3361    C<< my $okFlag = ERDB::ValidateFieldName($fieldName); >>
3362    
3363    Return TRUE if the specified field name is valid, else FALSE. Valid field names must
3364    be hyphenated words subject to certain restrictions.
3365    
3366    =over 4
3367    
3368    =item fieldName
3369    
3370    Field name to be validated.
3371    
3372    =item RETURN
3373    
3374    Returns TRUE if the field name is valid, else FALSE.
3375    
3376    =back
3377    
3378    =cut
3379    
3380    sub ValidateFieldName {
3381        # Get the parameters.
3382        my ($fieldName) = @_;
3383        # Declare the return variable. The field name is valid until we hear
3384        # differently.
3385        my $retVal = 1;
3386        # Compute the maximum name length.
3387        my $maxLen = $TypeTable{'name-string'}->{maxLen};
3388        # Look for bad stuff in the name.
3389        if ($fieldName =~ /--/) {
3390            # Here we have a doubled minus sign.
3391            Trace("Field name $fieldName has a doubled hyphen.") if T(1);
3392            $retVal = 0;
3393        } elsif ($fieldName !~ /^[A-Za-z]/) {
3394            # Here the field name is missing the initial letter.
3395            Trace("Field name $fieldName does not begin with a letter.") if T(1);
3396            $retVal = 0;
3397        } elsif (length($fieldName) > $maxLen) {
3398            # Here the field name is too long.
3399            Trace("Maximum field name length is $maxLen. Field name must be truncated to " . substr($fieldName,0, $maxLen) . ".");
3400        } else {
3401            # Strip out the minus signs. Everything remaining must be a letter,
3402            # underscore, or digit.
3403            my $strippedName = $fieldName;
3404            $strippedName =~ s/-//g;
3405            if ($strippedName !~ /^(\w|\d)+$/) {
3406                Trace("Field name $fieldName contains illegal characters.") if T(1);
3407                $retVal = 0;
3408            }
3409        }
3410        # Return the result.
3411        return $retVal;
3412    }
3413    
3414    =head3 ReadMetaXML
3415    
3416    C<< my $rawMetaData = ERDB::ReadDBD($fileName); >>
3417    
3418    This method reads a raw database definition XML file and returns it.
3419    Normally, the metadata used by the ERDB system has been processed and
3420    modified to make it easier to load and retrieve the data; however,
3421    this method can be used to get the data in its raw form.
3422    
3423    =over 4
3424    
3425    =item fileName
3426    
3427    Name of the XML file to read.
3428    
3429    =item RETURN
3430    
3431    Returns a hash reference containing the raw XML data from the specified file.
3432    
3433    =back
3434    
3435    =cut
3436    
3437    sub ReadMetaXML {
3438        # Get the parameters.
3439        my ($fileName) = @_;
3440        # Read the XML.
3441        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
3442        Trace("XML metadata loaded from file $fileName.") if T(1);
3443        # Return the result.
3444        return $retVal;
3445    }
3446    
3447    =head3 GetEntityFieldHash
3448    
3449    C<< my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName); >>
3450    
3451    Get the field hash of the named entity in the specified raw XML structure.
3452    The field hash may not exist, in which case we need to create it.
3453    
3454    =over 4
3455    
3456    =item structure
3457    
3458    Raw XML structure defininng the database. This is not the run-time XML used by
3459    an ERDB object, since that has all sorts of optimizations built-in.
3460    
3461    =item entityName
3462    
3463    Name of the entity whose field structure is desired.
3464    
3465    =item RETURN
3466    
3467    Returns the field hash used to define the entity's fields.
3468    
3469    =back
3470    
3471    =cut
3472    
3473    sub GetEntityFieldHash {
3474        # Get the parameters.
3475        my ($structure, $entityName) = @_;
3476        # Get the entity structure.
3477        my $entityData = $structure->{Entities}->{$entityName};
3478        # Look for a field structure.
3479        my $retVal = $entityData->{Fields};
3480        # If it doesn't exist, create it.
3481        if (! defined($retVal)) {
3482            $entityData->{Fields} = {};
3483            $retVal = $entityData->{Fields};
3484        }
3485        # Return the result.
3486        return $retVal;
3487    }
3488    
3489    =head3 WriteMetaXML
3490    
3491    C<< ERDB::WriteMetaXML($structure, $fileName); >>
3492    
3493    Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
3494    used to update the database definition. It must be used with care, however, since it
3495    will only work on a raw structure, not on the processed structure created by an ERDB
3496    constructor.
3497    
3498    =over 4
3499    
3500    =item structure
3501    
3502    XML structure to be written to the file.
3503    
3504    =item fileName
3505    
3506    Name of the output file to which the updated XML should be stored.
3507    
3508    =back
3509    
3510    =cut
3511    
3512    sub WriteMetaXML {
3513        # Get the parameters.
3514        my ($structure, $fileName) = @_;
3515        # Compute the output.
3516        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
3517        # Write it to the file.
3518        my $xmlOut = Open(undef, ">$fileName");
3519        print $xmlOut $fileString;
3520    }
3521    
3522    
3523    =head3 HTMLNote
3524    
3525    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
3526    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
3527    Except for C<[p]>, all the codes are closed by slash-codes. So, for
3528    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
3529    
3530    C<< my $realHtml = ERDB::HTMLNote($dataString); >>
3531    
3532    =over 4
3533    
3534    =item dataString
3535    
3536    String to convert to HTML.
3537    
3538    =item RETURN
3539    
3540    An HTML string derived from the input string.
3541    
3542    =back
3543    
3544    =cut
3545    
3546    sub HTMLNote {
3547        # Get the parameter.
3548        my ($dataString) = @_;
3549        # HTML-escape the text.
3550        my $retVal = CGI::escapeHTML($dataString);
3551        # Substitute the bulletin board codes.
3552        $retVal =~ s!\[(/?[bi])\]!<$1>!g;
3553        $retVal =~ s!\[p\]!</p><p>!g;
3554        $retVal =~ s!\[link\s+([^\]]+)\]!<a href="$1">!g;
3555        $retVal =~ s!\[/link\]!</a>!g;
3556        # Return the result.
3557        return $retVal;
3558    }
3559    
3560    =head3 BeginTran
3561    
3562    C<< $erdb->BeginTran(); >>
3563    
3564    Start a database transaction.
3565    
3566    =cut
3567    
3568    sub BeginTran {
3569        my ($self) = @_;
3570        $self->{_dbh}->begin_tran();
3571    
3572    }
3573    
3574    =head3 CommitTran
3575    
3576    C<< $erdb->CommitTran(); >>
3577    
3578    Commit an active database transaction.
3579    
3580    =cut
3581    
3582    sub CommitTran {
3583        my ($self) = @_;
3584        $self->{_dbh}->commit_tran();
3585    }
3586    
3587    =head3 RollbackTran
3588    
3589    C<< $erdb->RollbackTran(); >>
3590    
3591    Roll back an active database transaction.
3592    
3593    =cut
3594    
3595    sub RollbackTran {
3596        my ($self) = @_;
3597        $self->{_dbh}->roll_tran();
3598    }
3599    
3600    =head3 UpdateField
3601    
3602    C<< my $count = $erdb->UpdateField($objectNames, $fieldName, $oldValue, $newValue, $filter, $parms); >>
3603    
3604    Update all occurrences of a specific field value to a new value. The number of rows changed will be
3605    returned.
3606    
3607    =over 4
3608    
3609    =item fieldName
3610    
3611    Name of the field in standard I<objectName>C<(>I<fieldName>C<)> format.
3612    
3613    =item oldValue
3614    
3615    Value to be modified. All occurrences of this value in the named field will be replaced by the
3616    new value.
3617    
3618    =item newValue
3619    
3620    New value to be substituted for the old value when it's found.
3621    
3622    =item filter
3623    
3624    A standard ERDB filter clause (see L</Get>). The filter will be applied before any substitutions take place.
3625    
3626    =item parms
3627    
3628    Reference to a list of parameter values in the filter.
3629    
3630    =item RETURN
3631    
3632    Returns the number of rows modified.
3633    
3634    =back
3635    
3636    =cut
3637    
3638    sub UpdateField {
3639        # Get the parameters.
3640        my ($self, $fieldName, $oldValue, $newValue, $filter, $parms) = @_;
3641        # Get the object and field names from the field name parameter.
3642        $fieldName =~ /^([^(]+)\(([^)]+)\)/;
3643        my $objectName = $1;
3644        my $realFieldName = _FixName($2);
3645        # Add the old value to the filter. Note we allow the possibility that no
3646        # filter was specified.
3647        my $realFilter = "$fieldName = ?";
3648        if ($filter) {
3649            $realFilter .= " AND $filter";
3650        }
3651        # Format the query filter.
3652        my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
3653            $self->_SetupSQL([$objectName], $realFilter);
3654        # Create the query. Since there is only one object name, the mapped-name data is not
3655        # necessary. Neither is the FROM clause.
3656        $suffix =~ s/^FROM.+WHERE\s+//;
3657        # Create the update statement.
3658        my $command = "UPDATE $objectName SET $realFieldName = ? WHERE $suffix";
3659        # Get the database handle.
3660        my $dbh = $self->{_dbh};
3661        # Add the old and new values to the parameter list. Note we allow the possibility that
3662        # there are no user-supplied parameters.
3663        my @params = ($newValue, $oldValue);
3664        if (defined $parms) {
3665            push @params, @{$parms};
3666        }
3667        # Execute the update.
3668        my $retVal = $dbh->SQL($command, 0, @params);
3669        # Make the funky zero a real zero.
3670        if ($retVal == 0) {
3671            $retVal = 0;
3672        }
3673        # Return the result.
3674        return $retVal;
3675    }
3676    
3677    
3678    =head2 Data Mining Methods
3679    
3680    =head3 GetUsefulCrossValues
3681    
3682    C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>
3683    
3684    Return a list of the useful attributes that would be returned by a B<Cross> call
3685    from an entity of the source entity type through the specified relationship. This
3686    means it will return the fields of the target entity type and the intersection data
3687    fields in the relationship. Only primary table fields are returned. In other words,
3688    the field names returned will be for fields where there is always one and only one
3689    value.
3690    
3691    =over 4
3692    
3693    =item sourceEntity
3694    
3695    Name of the entity from which the relationship crossing will start.
3696    
3697    =item relationship
3698    
3699    Name of the relationship being crossed.
3700    
3701    =item RETURN
3702    
3703    Returns a list of field names in Sprout field format (I<objectName>C<(>I<fieldName>C<)>.
3704    
3705    =back
3706    
3707    =cut
3708    #: Return Type @;
3709    sub GetUsefulCrossValues {
3710        # Get the parameters.
3711        my ($self, $sourceEntity, $relationship) = @_;
3712        # Declare the return variable.
3713        my @retVal = ();
3714        # Determine the target entity for the relationship. This is whichever entity is not
3715        # the source entity. So, if the source entity is the FROM, we'll get the name of
3716        # the TO, and vice versa.
3717        my $relStructure = $self->_GetStructure($relationship);
3718        my $targetEntityType = ($relStructure->{from} eq $sourceEntity ? "to" : "from");
3719        my $targetEntity = $relStructure->{$targetEntityType};
3720        # Get the field table for the entity.
3721        my $entityFields = $self->GetFieldTable($targetEntity);
3722        # The field table is a hash. The hash key is the field name. The hash value is a structure.
3723        # For the entity fields, the key aspect of the target structure is that the {relation} value
3724        # must match the entity name.
3725        my @fieldList = map { "$targetEntity($_)" } grep { $entityFields->{$_}->{relation} eq $targetEntity }
3726                            keys %{$entityFields};
3727        # Push the fields found onto the return variable.
3728        push @retVal, sort @fieldList;
3729        # Get the field table for the relationship.
3730        my $relationshipFields = $self->GetFieldTable($relationship);
3731        # Here we have a different rule. We want all the fields other than "from-link" and "to-link".
3732        # This may end up being an empty set.
3733        my @fieldList2 = map { "$relationship($_)" } grep { $_ ne "from-link" && $_ ne "to-link" }
3734                            keys %{$relationshipFields};
3735        # Push these onto the return list.
3736        push @retVal, sort @fieldList2;
3737        # Return the result.
3738        return @retVal;
3739    }
3740    
3741    =head3 FindColumn
3742    
3743    C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>
3744    
3745    Return the location a desired column in a data mining header line. The data
3746    mining header line is a tab-separated list of column names. The column
3747    identifier is either the numerical index of a column or the actual column
3748    name.
3749    
3750    =over 4
3751    
3752    =item headerLine
3753    
3754    The header line from a data mining command, which consists of a tab-separated
3755    list of column names.
3756    
3757    =item columnIdentifier
3758    
3759    Either the ordinal number of the desired column (1-based), or the name of the
3760    desired column.
3761    
3762    =item RETURN
3763    
3764    Returns the array index (0-based) of the desired column.
3765    
3766    =back
3767    
3768    =cut
3769    
3770    sub FindColumn {
3771        # Get the parameters.
3772        my ($headerLine, $columnIdentifier) = @_;
3773        # Declare the return variable.
3774        my $retVal;
3775        # Split the header line into column names.
3776        my @headers = ParseColumns($headerLine);
3777        # Determine whether we have a number or a name.
3778        if ($columnIdentifier =~ /^\d+$/) {
3779            # Here we have a number. Subtract 1 and validate the result.
3780            $retVal = $columnIdentifier - 1;
3781            if ($retVal < 0 || $retVal > $#headers) {
3782                Confess("Invalid column identifer \"$columnIdentifier\": value out of range.");
3783            }
3784        } else {
3785            # Here we have a name. We need to find it in the list.
3786            for (my $i = 0; $i <= $#headers && ! defined($retVal); $i++) {
3787                if ($headers[$i] eq $columnIdentifier) {
3788                    $retVal = $i;
3789                }
3790            }
3791            if (! defined($retVal)) {
3792                Confess("Invalid column identifier \"$columnIdentifier\": value not found.");
3793            }
3794        }
3795        # Return the result.
3796        return $retVal;
3797    }
3798    
3799    =head3 ParseColumns
3800    
3801    C<< my @columns = ERDB::ParseColumns($line); >>
3802    
3803    Convert the specified data line to a list of columns.
3804    
3805    =over 4
3806    
3807    =item line
3808    
3809    A data mining input, consisting of a tab-separated list of columns terminated by a
3810    new-line.
3811    
3812    =item RETURN
3813    
3814    Returns a list consisting of the column values.
3815    
3816    =back
3817    
3818    =cut
3819    
3820    sub ParseColumns {
3821        # Get the parameters.
3822        my ($line) = @_;
3823        # Chop off the line-end.
3824        chomp $line;
3825        # Split it into a list.
3826        my @retVal = split(/\t/, $line);
3827        # Return the result.
3828        return @retVal;
3829    }
3830    
3831    =head2 Virtual Methods
3832    
3833    =head3 _CreatePPOIndex
3834    
3835    C<< my $index = ERDB::_CreatePPOIndex($indexObject); >>
3836    
3837    Convert the XML for an ERDB index to the XML structure for a PPO
3838    index.
3839    
3840    =over 4
3841    
3842    ERDB XML structure for an index.
3843    
3844    =item RETURN
3845    
3846    PPO XML structure for the same index.
3847    
3848    =back
3849