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

Diff of /Sprout/ERDB.pm

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

revision 1.3, Wed Jan 26 22:26:09 2005 UTC revision 1.26, Tue Oct 18 06:47:46 2005 UTC
# Line 1  Line 1 
1  package ERDB;  package ERDB;
2    
3          use strict;          use strict;
         use Carp;  
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 DBObject;
10          use Stats;          use Stats;
11          use Time::HiRes qw(gettimeofday);          use Time::HiRes qw(gettimeofday);
12        use FIG;
13    
14  =head1 Entity-Relationship Database Package  =head1 Entity-Relationship Database Package
15    
# Line 33  Line 33 
33  relation that contains two fields-- the feature ID (C<id>) and the alias name (C<alias>).  relation that contains two fields-- the feature ID (C<id>) and the alias name (C<alias>).
34  The B<FEATURE> entity also contains an optional virulence number. This is implemented  The B<FEATURE> entity also contains an optional virulence number. This is implemented
35  as a separate relation C<FeatureVirulence> which contains an ID (C<id>) and a virulence number  as a separate relation C<FeatureVirulence> which contains an ID (C<id>) and a virulence number
36  (C<virulence>). If the virulence of a feature I<ABC> is known to be 6, there will be one row in the  (C<virulence>). If the virulence of a feature I<ABC> is known to be 6, there will be one row in
37  C<FeatureVirulence> relation possessing the value I<ABC> as its ID and 6 as its virulence number.  the C<FeatureVirulence> relation possessing the value I<ABC> as its ID and 6 as its virulence
38  If the virulence of I<ABC> is not known, there will not be any rows for it in C<FeatureVirulence>.  number. If the virulence of I<ABC> is not known, there will not be any rows for it in
39    C<FeatureVirulence>.
40    
41  Entities are connected by binary relationships implemented using single relations possessing the  Entities are connected by binary relationships implemented using single relations possessing the
42  same name as the relationship itself and that has an I<arity> of 1-to-1 (C<11>), 1-to-many (C<1M>),  same name as the relationship itself and that has an I<arity> of 1-to-1 (C<11>), 1-to-many (C<1M>),
# Line 67  Line 68 
68  was inserted by the L</InsertObject> method.  was inserted by the L</InsertObject> method.
69    
70  To facilitate testing, the ERDB module supports automatic generation of test data. This process  To facilitate testing, the ERDB module supports automatic generation of test data. This process
71  is described in the L</GenerateEntity> and L</GenerateConnection> methods.  is described in the L</GenerateEntity> and L</GenerateConnection> methods, though it is not yet
72    fully implemented.
73    
74    =head2 XML Database Description
75    
76    =head3 Data Types
77    
78    The ERDB system supports the following data types. Note that there are numerous string
79    types depending on the maximum length. Some database packages limit the total number of
80    characters you have in an index key; to insure the database works in all environments,
81    the type of string should be the shortest one possible that supports all the known values.
82    
83    =over 4
84    
85    =item char
86    
87    single ASCII character
88    
89    =item int
90    
91    32-bit signed integer
92    
93    =item date
94    
95    64-bit unsigned integer, representing a PERL date/time value
96    
97    =item text
98    
99    long string; Text fields cannot be used in indexes or sorting and do not support the
100    normal syntax of filter clauses, but can be up to a billion character in length
101    
102    =item float
103    
104    double-precision floating-point number
105    
106    =item boolean
107    
108    single-bit numeric value; The value is stored as a 16-bit signed integer (for
109    compatability with certain database packages), but the only values supported are
110    0 and 1.
111    
112    =item key-string
113    
114    variable-length string, maximum 40 characters
115    
116    =item name-string
117    
118    variable-length string, maximum 80 characters
119    
120    =item medium-string
121    
122    variable-length string, maximum 160 characters
123    
124    =item string
125    
126    variable-length string, maximum 255 characters
127    
128    =back
129    
130    =head3 Global Tags
131    
132    The entire database definition must be inside a B<Database> tag. The display name of
133    the database is given by the text associated with the B<Title> tag. The display name
134    is only used in the automated documentation. It has no other effect. The entities and
135    relationships are listed inside the B<Entities> and B<Relationships> tags,
136    respectively. None of these tags have attributes.
137    
138        <Database>
139            <Title>... display title here...</Title>
140            <Entities>
141                ... entity definitions here ...
142            </Entities>
143            <Relationships>
144                ... relationship definitions here...
145            </Relationships>
146        </Database>
147    
148    Entities, relationships, indexes, and fields all allow a text tag called B<Notes>.
149    The text inside the B<Notes> tag contains comments that will appear when the database
150    documentation is generated. Within a B<Notes> tag, you may use C<[i]> and C<[/i]> for
151    italics, C<[b]> and C<[/b]> for bold, and C<[p]> for a new paragraph.
152    
153    =head3 Fields
154    
155    Both entities and relationships have fields described by B<Field> tags. A B<Field>
156    tag can have B<Notes> associated with it. The complete set of B<Field> tags for an
157    object mus be inside B<Fields> tags.
158    
159        <Entity ... >
160            <Fields>
161                ... Field tags ...
162            </Fields>
163        </Entity>
164    
165    The attributes for the B<Field> tag are as follows.
166    
167    =over 4
168    
169    =item name
170    
171    Name of the field. The field name should contain only letters, digits, and hyphens (C<->),
172    and the first character should be a letter. Most underlying databases are case-insensitive
173    with the respect to field names, so a best practice is to use lower-case letters only.
174    
175    =item type
176    
177    Data type of the field. The legal data types are given above.
178    
179    =item relation
180    
181    Name of the relation containing the field. This should only be specified for entity
182    fields. The ERDB system does not support optional fields or multi-occurring fields
183    in the primary relation of an entity. Instead, they are put into secondary relations.
184    So, for example, in the C<Genome> entity, the C<group-name> field indicates a special
185    grouping used to select a subset of the genomes. A given genome may not be in any
186    groups or may be in multiple groups. Therefore, C<group-name> specifies a relation
187    value. The relation name specified must be a valid table name. By convention, it is
188    usually the entity name followed by a qualifying word (e.g. C<GenomeGroup>). In an
189    entity, the fields without a relation attribute are said to belong to the
190    I<primary relation>. This relation has the same name as the entity itself.
191    
192    =back
193    
194    =head3 Indexes
195    
196    An entity can have multiple alternate indexes associated with it. The fields must
197    be from the primary relation. The alternate indexes assist in ordering results
198    from a query. A relationship can have up to two indexes-- a I<to-index> and a
199    I<from-index>. These order the results when crossing the relationship. For
200    example, in the relationship C<HasContig> from C<Genome> to C<Contig>, the
201    from-index would order the contigs of a ganome, and the to-index would order
202    the genomes of a contig. A relationship's index must specify only fields in
203    the relationship.
204    
205    The indexes for an entity must be listed inside the B<Indexes> tag. The from-index
206    of a relationship is specified using the B<FromIndex> tag; the to-index is specified
207    using the B<ToIndex> tag.
208    
209    Each index can contain a B<Notes> tag. In addition, it will have an B<IndexFields>
210    tag containing the B<IndexField> tags. These specify, in order, the fields used in
211    the index. The attributes of an B<IndexField> tag are as follows.
212    
213    =over 4
214    
215    =item name
216    
217    Name of the field.
218    
219    =item order
220    
221    Sort order of the field-- C<ascending> or C<descending>.
222    
223    =back
224    
225    The B<Index>, B<FromIndex>, and B<ToIndex> tags themselves have no attributes.
226    
227    =head3 Object and Field Names
228    
229    By convention entity and relationship names use capital casing (e.g. C<Genome> or
230    C<HasRegionsIn>. Most underlying databases, however, are aggressively case-insensitive
231    with respect to relation names, converting them internally to all-upper case or
232    all-lower case.
233    
234    If syntax or parsing errors occur when you try to load or use an ERDB database, the
235    most likely reason is that one of your objects has an SQL reserved word as its name.
236    The list of SQL reserved words keeps increasing; however, most are unlikely to show
237    up as a noun or declarative verb phrase. The exceptions are C<Group>, C<User>,
238    C<Table>, C<Index>, C<Object>, C<Date>, C<Number>, C<Update>, C<Time>, C<Percent>,
239    C<Memo>, C<Order>, and C<Sum>. This problem can crop up in field names as well.
240    
241    Every entity has a field called C<id> that acts as its primary key. Every relationship
242    has fields called C<from-link> and C<to-link> that contain copies of the relevant
243    entity IDs. These are essentially ERDB's reserved words, and should not be used
244    for user-defined field names.
245    
246    =head3 Entities
247    
248    An entity is described by the B<Entity> tag. The entity can contain B<Notes>, an
249    B<Indexes> tag containing one or more secondary indexes, and a B<Fields> tag
250    containing one or more fields. The attributes of the B<Entity> tag are as follows.
251    
252    =over 4
253    
254    =item name
255    
256    Name of the entity. The entity name, by convention, uses capital casing (e.g. C<Genome>
257    or C<GroupBlock>) and should be a noun or noun phrase.
258    
259    =item keyType
260    
261    Data type of the primary key. The primary key is always named C<id>.
262    
263    =back
264    
265    =head3 Relationships
266    
267    A relationship is described by the C<Relationship> tag. Within a relationship,
268    there can be a C<Notes> tag, a C<Fields> tag containing the intersection data
269    fields, a C<FromIndex> tag containing the from-index, and a C<ToIndex> tag containing
270    the to-index.
271    
272    The C<Relationship> tag has the following attributes.
273    
274    =over 4
275    
276    =item name
277    
278    Name of the relationship. The relationship name, by convention, uses capital casing
279    (e.g. C<ContainsRegionIn> or C<HasContig>), and should be a declarative verb
280    phrase, designed to fit between the from-entity and the to-entity (e.g.
281    Block C<ContainsRegionIn> Genome).
282    
283    =item from
284    
285    Name of the entity from which the relationship starts.
286    
287    =item to
288    
289    Name of the entity to which the relationship proceeds.
290    
291    =item arity
292    
293    Relationship type: C<1M> for one-to-many and C<MM> for many-to-many.
294    
295    =back
296    
297  =cut  =cut
298    
# Line 76  Line 301 
301  # 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.
302  # "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
303  # of the specified type. "dataGen" is PERL string that will be evaluated if no test data generation  # of the specified type. "dataGen" is PERL string that will be evaluated if no test data generation
304   #string is specified in the field definition.  # string is specified in the field definition. "avgLen" is the average byte length for estimating
305  my %TypeTable = ( char =>        { sqlType => 'CHAR(1)',                        maxLen => 1,                    dataGen => "StringGen('A')" },  # record sizes.
306                                    int =>         { sqlType => 'INTEGER',                        maxLen => 20,                   dataGen => "IntGen(0, 99999999)" },  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, dataGen => "StringGen('A')" },
307                                    string =>  { sqlType => 'VARCHAR(255)',               maxLen => 255,                  dataGen => "StringGen(IntGen(10,250))" },                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, dataGen => "IntGen(0, 99999999)" },
308                                    text =>        { sqlType => 'TEXT',                           maxLen => 1000000000,   dataGen => "StringGen(IntGen(80,1000))" },                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, dataGen => "StringGen(IntGen(10,250))" },
309                                    date =>        { sqlType => 'BIGINT',                         maxLen => 80,                   dataGen => "DateGen(-7, 7, IntGen(0,1400))" },                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, dataGen => "StringGen(IntGen(80,1000))" },
310                                    float =>       { sqlType => 'DOUBLE PRECISION',       maxLen => 40,                   dataGen => "FloatGen(0.0, 100.0)" },                    date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, dataGen => "DateGen(-7, 7, IntGen(0,1400))" },
311                                    boolean => { sqlType => 'SMALLINT',                   maxLen => 1,                    dataGen => "IntGen(0, 1)" },                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, dataGen => "FloatGen(0.0, 100.0)" },
312                      boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   2, dataGen => "IntGen(0, 1)" },
313                               'key-string' =>                               'key-string' =>
314                                                           { sqlType => 'VARCHAR(40)',            maxLen => 40,                   dataGen => "StringGen(IntGen(10,40))" },                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, dataGen => "StringGen(IntGen(10,40))" },
315                                   'name-string' =>                                   'name-string' =>
316                                                           { sqlType => 'VARCHAR(80)',            maxLen => 80,                   dataGen => "StringGen(IntGen(10,80))" },                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, dataGen => "StringGen(IntGen(10,80))" },
317                                   'medium-string' =>                                   'medium-string' =>
318                                                           { sqlType => 'VARCHAR(160)',           maxLen => 160,                  dataGen => "StringGen(IntGen(10,160))" },                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, dataGen => "StringGen(IntGen(10,160))" },
319                                  );                                  );
320    
321  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 111  Line 337 
337    
338  =head3 new  =head3 new
339    
340  C<< my $database = ERDB::new($dbh, $metaFileName); >>  C<< my $database = ERDB->new($dbh, $metaFileName); >>
341    
342  Create a new ERDB object.  Create a new ERDB object.
343    
# Line 136  Line 362 
362          my $metaData = _LoadMetaData($metaFileName);          my $metaData = _LoadMetaData($metaFileName);
363          # Create the object.          # Create the object.
364          my $self = { _dbh => $dbh,          my $self = { _dbh => $dbh,
365                                   _metaData => $metaData,                   _metaData => $metaData
                                  _options => $options,  
366                             };                             };
367          # Bless and return it.          # Bless and return it.
368          bless $self;      bless $self, $class;
369          return $self;          return $self;
370  }  }
371    
372  =head3 ShowMetaData  =head3 ShowMetaData
373    
374  C<< $database->ShowMetaData($fileName); >>  C<< $erdb->ShowMetaData($fileName); >>
375    
376  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
377  the data to be loaded into the relations.  the data to be loaded into the relations.
# Line 163  Line 388 
388    
389  sub ShowMetaData {  sub ShowMetaData {
390          # Get the parameters.          # Get the parameters.
391          my $self = shift @_;      my ($self, $filename) = @_;
         my ($filename) = @_;  
392          # Get the metadata and the title string.          # Get the metadata and the title string.
393          my $metadata = $self->{_metaData};          my $metadata = $self->{_metaData};
394          # Get the title string.          # Get the title string.
# Line 174  Line 398 
398          my $relationshipList = $metadata->{Relationships};          my $relationshipList = $metadata->{Relationships};
399          # Open the output file.          # Open the output file.
400          open(HTMLOUT, ">$filename") || Confess("Could not open MetaData display file $filename: $!");          open(HTMLOUT, ">$filename") || Confess("Could not open MetaData display file $filename: $!");
401        Trace("Building MetaData table of contents.") if T(4);
402          # Write the HTML heading stuff.          # Write the HTML heading stuff.
403          print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";          print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";
404          print HTMLOUT "</head>\n<body>\n";          print HTMLOUT "</head>\n<body>\n";
# Line 201  Line 426 
426          print HTMLOUT "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";          print HTMLOUT "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";
427          # Loop through the entities.          # Loop through the entities.
428          for my $key (sort keys %{$entityList}) {          for my $key (sort keys %{$entityList}) {
429            Trace("Building MetaData entry for $key entity.") if T(4);
430                  # Create the entity header. It contains a bookmark and the entity name.                  # Create the entity header. It contains a bookmark and the entity name.
431                  print HTMLOUT "<a name=\"$key\"></a><h3>$key</h3>\n";                  print HTMLOUT "<a name=\"$key\"></a><h3>$key</h3>\n";
432                  # Get the entity data.                  # Get the entity data.
# Line 239  Line 465 
465          print HTMLOUT "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";          print HTMLOUT "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";
466          # Loop through the relationships.          # Loop through the relationships.
467          for my $key (sort keys %{$relationshipList}) {          for my $key (sort keys %{$relationshipList}) {
468            Trace("Building MetaData entry for $key relationship.") if T(4);
469                  # Get the relationship's structure.                  # Get the relationship's structure.
470                  my $relationshipStructure = $relationshipList->{$key};                  my $relationshipStructure = $relationshipList->{$key};
471                  # Create the relationship header.                  # Create the relationship header.
# Line 269  Line 496 
496                  my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});                  my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
497                  print HTMLOUT $htmlString;                  print HTMLOUT $htmlString;
498          }          }
499        Trace("Building MetaData join table.") if T(4);
500          # Denote we're starting the join table.          # Denote we're starting the join table.
501          print HTMLOUT "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";          print HTMLOUT "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";
502          # Create a table header.          # Create a table header.
503          print HTMLOUT _OpenTable("Join Table", "Source", "Target", "Join Condition");          print HTMLOUT _OpenTable("Join Table", "Source", "Target", "Join Condition");
504          # Loop through the joins.          # Loop through the joins.
505          my $joinTable = $metadata->{Joins};          my $joinTable = $metadata->{Joins};
506          for my $joinKey (sort keys %{$joinTable}) {      my @joinKeys = keys %{$joinTable};
507        for my $joinKey (sort @joinKeys) {
508                  # Separate out the source, the target, and the join clause.                  # Separate out the source, the target, and the join clause.
509                  $joinKey =~ m!([^/]*)/(.*)$!;          $joinKey =~ m!^([^/]+)/(.+)$!;
510                  my ($source, $target, $clause) = ($self->ComputeObjectSentence($1),          my ($sourceRelation, $targetRelation) = ($1, $2);
511                                                                                    $self->ComputeObjectSentence($2),          Trace("Join with key $joinKey is from $sourceRelation to $targetRelation.") if T(4);
512                                                                                    $joinTable->{$joinKey});          my $source = $self->ComputeObjectSentence($sourceRelation);
513            my $target = $self->ComputeObjectSentence($targetRelation);
514            my $clause = $joinTable->{$joinKey};
515                  # Display them in a table row.                  # Display them in a table row.
516                  print HTMLOUT "<tr><td>$source</td><td>$target</td><td>$clause</td></tr>\n";                  print HTMLOUT "<tr><td>$source</td><td>$target</td><td>$clause</td></tr>\n";
517          }          }
# Line 290  Line 521 
521          print HTMLOUT "</body>\n</html>\n";          print HTMLOUT "</body>\n</html>\n";
522          # Close the file.          # Close the file.
523          close HTMLOUT;          close HTMLOUT;
524        Trace("Built MetaData web page.") if T(3);
525  }  }
526    
527  =head3 DumpMetaData  =head3 DumpMetaData
528    
529  C<< $database->DumpMetaData(); >>  C<< $erdb->DumpMetaData(); >>
530    
531  Return a dump of the metadata structure.  Return a dump of the metadata structure.
532    
# Line 302  Line 534 
534    
535  sub DumpMetaData {  sub DumpMetaData {
536          # Get the parameters.          # Get the parameters.
537          my $self = shift @_;      my ($self) = @_;
538          # Dump the meta-data.          # Dump the meta-data.
539          return Data::Dumper::Dumper($self->{_metaData});          return Data::Dumper::Dumper($self->{_metaData});
540  }  }
541    
542  =head3 CreateTables  =head3 CreateTables
543    
544  C<< $datanase->CreateTables(); >>  C<< $erdb->CreateTables(); >>
545    
546  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
547  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 320  Line 552 
552    
553  sub CreateTables {  sub CreateTables {
554          # Get the parameters.          # Get the parameters.
555          my $self = shift @_;      my ($self) = @_;
556          my $metadata = $self->{_metaData};      # Get the relation names.
557          my $dbh = $self->{_dbh};      my @relNames = $self->GetTableNames();
558          # Loop through the entities.      # Loop through the relations.
559          while (my ($entityName, $entityData) = each %{$metadata->{Entities}}) {      for my $relationName (@relNames) {
                 # 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}}) {  
560                          # Create a table for this relation.                          # Create a table for this relation.
561                          $self->CreateTable($relationName);                          $self->CreateTable($relationName);
562                          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);  
563          }          }
564  }  }
565    
566  =head3 CreateTable  =head3 CreateTable
567    
568  C<< $database->CreateTable($tableName, $indexFlag); >>  C<< $erdb->CreateTable($tableName, $indexFlag, $estimatedRows); >>
569    
570  Create the table for a relation and optionally create its indexes.  Create the table for a relation and optionally create its indexes.
571    
# Line 355  Line 575 
575    
576  Name of the relation (which will also be the table name).  Name of the relation (which will also be the table name).
577    
578  =item $indexFlag  =item indexFlag
579    
580  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,
581  L</CreateIndexes> must be called later to bring the indexes into existence.  L</CreateIndexes> must be called later to bring the indexes into existence.
582    
583    =item estimatedRows (optional)
584    
585    If specified, the estimated maximum number of rows for the relation. This
586    information allows the creation of tables using storage engines that are
587    faster but require size estimates, such as MyISAM.
588    
589  =back  =back
590    
591  =cut  =cut
592    
593  sub CreateTable {  sub CreateTable {
594          # Get the parameters.          # Get the parameters.
595          my $self = shift @_;      my ($self, $relationName, $indexFlag, $estimatedRows) = @_;
         my ($relationName, $indexFlag) = @_;  
596          # Get the database handle.          # Get the database handle.
597          my $dbh = $self->{_dbh};          my $dbh = $self->{_dbh};
598          # 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 391  Line 616 
616          # Insure the table is not already there.          # Insure the table is not already there.
617          $dbh->drop_table(tbl => $relationName);          $dbh->drop_table(tbl => $relationName);
618          Trace("Table $relationName dropped.") if T(2);          Trace("Table $relationName dropped.") if T(2);
619        # If there are estimated rows, create an estimate so we can take advantage of
620        # faster DB technologies.
621        my $estimation = undef;
622        if ($estimatedRows) {
623            $estimation = [$self->EstimateRowSize($relationName), $estimatedRows];
624        }
625          # Create the table.          # Create the table.
626          Trace("Creating table $relationName: $fieldThing") if T(2);          Trace("Creating table $relationName: $fieldThing") if T(2);
627          $dbh->create_table(tbl => $relationName, flds => $fieldThing);      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);
628          Trace("Relation $relationName created in database.") if T(2);          Trace("Relation $relationName created in database.") if T(2);
629          # If we want to build the indexes, we do it here.          # If we want to build the indexes, we do it here.
630          if ($indexFlag) {          if ($indexFlag) {
# Line 403  Line 634 
634    
635  =head3 CreateIndex  =head3 CreateIndex
636    
637  C<< $database->CreateIndex($relationName); >>  C<< $erdb->CreateIndex($relationName); >>
638    
639  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
640  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.
641  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
642  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.
643    
644  =cut  =cut
645    
646  sub CreateIndex {  sub CreateIndex {
647          # Get the parameters.          # Get the parameters.
648          my $self = shift @_;      my ($self, $relationName) = @_;
         my ($relationName) = @_;  
649          # Get the relation's descriptor.          # Get the relation's descriptor.
650          my $relationData = $self->_FindRelation($relationName);          my $relationData = $self->_FindRelation($relationName);
651          # Get the database handle.          # Get the database handle.
652          my $dbh = $self->{_dbh};          my $dbh = $self->{_dbh};
653          # Now we need to create this relation's indexes. We do this by looping through its index table.          # Now we need to create this relation's indexes. We do this by looping through its index table.
654          while (my ($indexName, $indexData) = each %{$relationData->{Indexes}}) {      my $indexHash = $relationData->{Indexes};
655        for my $indexName (keys %{$indexHash}) {
656            my $indexData = $indexHash->{$indexName};
657                  # Get the index's field list.                  # Get the index's field list.
658                  my @fieldList = _FixNames(@{$indexData->{IndexFields}});                  my @fieldList = _FixNames(@{$indexData->{IndexFields}});
659                  my $flds = join(', ', @fieldList);                  my $flds = join(', ', @fieldList);
660                  # Get the index's uniqueness flag.                  # Get the index's uniqueness flag.
661                  my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');                  my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');
662                  # Create the index.                  # Create the index.
663                  $dbh->create_index(idx => $indexName, tbl => $relationName, flds => $flds, unique => $unique);          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
664                                        flds => $flds, unique => $unique);
665            if ($rv) {
666                  Trace("Index created: $indexName for $relationName ($flds)") if T(1);                  Trace("Index created: $indexName for $relationName ($flds)") if T(1);
667            } else {
668                Confess("Error creating index $indexName for $relationName using ($flds): " . $dbh->error_message());
669            }
670          }          }
671  }  }
672    
673  =head3 LoadTables  =head3 LoadTables
674    
675  C<< my $stats = $database->LoadTables($directoryName, $rebuild); >>  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>
676    
677  This method will load the database tables from a directory. The tables must already have been created  This method will load the database tables from a directory. The tables must already have been created
678  in the database. (This can be done by calling L</CreateTables>.) The caller passes in a directory name;  in the database. (This can be done by calling L</CreateTables>.) The caller passes in a directory name;
# Line 471  Line 708 
708    
709  sub LoadTables {  sub LoadTables {
710          # Get the parameters.          # Get the parameters.
711          my $self = shift @_;      my ($self, $directoryName, $rebuild) = @_;
         my ($directoryName, $rebuild) = @_;  
712          # Start the timer.          # Start the timer.
713          my $startTime = gettimeofday;          my $startTime = gettimeofday;
714          # Clean any trailing slash from the directory name.          # Clean any trailing slash from the directory name.
715          $directoryName =~ s!/\\$!!;          $directoryName =~ s!/\\$!!;
716          # Declare the return variable.          # Declare the return variable.
717          my $retVal = Stats->new();          my $retVal = Stats->new();
718          # Get the metadata structure.      # Get the relation names.
719          my $metaData = $self->{_metaData};      my @relNames = $self->GetTableNames();
720          # Loop through the entities.      for my $relationName (@relNames) {
         for my $entity (values %{$metaData->{Entities}}) {  
                 # Loop through the entity's relations.  
                 for my $relationName (keys %{$entity->{Relations}}) {  
721                          # Try to load this relation.                          # Try to load this relation.
722                          my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);                          my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);
723                          # Accumulate the statistics.                          # Accumulate the statistics.
724                          $retVal->Accumulate($result);                          $retVal->Accumulate($result);
725                  }                  }
         }  
         # 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);  
         }  
726          # Add the duration of the load to the statistical object.          # Add the duration of the load to the statistical object.
727          $retVal->Add('duration', gettimeofday - $startTime);          $retVal->Add('duration', gettimeofday - $startTime);
728          # Return the accumulated statistics.          # Return the accumulated statistics.
729          return $retVal;          return $retVal;
730  }  }
731    
732    
733  =head3 GetTableNames  =head3 GetTableNames
734    
735  C<< my @names = $database->GetTableNames; >>  C<< my @names = $erdb->GetTableNames; >>
736    
737  Return a list of the relations required to implement this database.  Return a list of the relations required to implement this database.
738    
# Line 514  Line 740 
740    
741  sub GetTableNames {  sub GetTableNames {
742          # Get the parameters.          # Get the parameters.
743          my $self = shift @_;      my ($self) = @_;
744          # Get the relation list from the metadata.          # Get the relation list from the metadata.
745          my $relationTable = $self->{_metaData}->{RelationTable};          my $relationTable = $self->{_metaData}->{RelationTable};
746          # Return the relation names.          # Return the relation names.
# Line 523  Line 749 
749    
750  =head3 GetEntityTypes  =head3 GetEntityTypes
751    
752  C<< my @names = $database->GetEntityTypes; >>  C<< my @names = $erdb->GetEntityTypes; >>
753    
754  Return a list of the entity type names.  Return a list of the entity type names.
755    
# Line 531  Line 757 
757    
758  sub GetEntityTypes {  sub GetEntityTypes {
759          # Get the database object.          # Get the database object.
760          my $self = shift @_;      my ($self) = @_;
761          # Get the entity list from the metadata object.          # Get the entity list from the metadata object.
762          my $entityList = $self->{_metaData}->{Entities};          my $entityList = $self->{_metaData}->{Entities};
763          # Return the list of entity names in alphabetical order.          # Return the list of entity names in alphabetical order.
764          return sort keys %{$entityList};          return sort keys %{$entityList};
765  }  }
766    
767    =head3 IsEntity
768    
769    C<< my $flag = $erdb->IsEntity($entityName); >>
770    
771    Return TRUE if the parameter is an entity name, else FALSE.
772    
773    =over 4
774    
775    =item entityName
776    
777    Object name to be tested.
778    
779    =item RETURN
780    
781    Returns TRUE if the specified string is an entity name, else FALSE.
782    
783    =back
784    
785    =cut
786    
787    sub IsEntity {
788        # Get the parameters.
789        my ($self, $entityName) = @_;
790        # Test to see if it's an entity.
791        return exists $self->{_metaData}->{Entities}->{$entityName};
792    }
793    
794  =head3 Get  =head3 Get
795    
796  C<< my $query = $database->Get(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  C<< my $query = $erdb->Get(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>
797    
798  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.
799  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 548  Line 801 
801  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
802  $genus.  $genus.
803    
804  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", $genus); >>
805    
806  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
807  parameter representing the parameter value. It would also be possible to code  parameter representing the parameter value. It would also be possible to code
808    
809  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>
810    
811  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
812  characters inside the variable C<$genus>.  characters inside the variable C<$genus>.
# Line 565  Line 818 
818  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
819  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,
820    
821  C<< $query = $sprout->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", $genus); >>
822    
823  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
824  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.
# Line 616  Line 869 
869    
870  sub Get {  sub Get {
871          # Get the parameters.          # Get the parameters.
872          my $self = shift @_;      my ($self, $objectNames, $filterClause, @params) = @_;
         my ($objectNames, $filterClause, @params) = @_;  
873          # Construct the SELECT statement. The general pattern is          # Construct the SELECT statement. The general pattern is
874          #          #
875          # SELECT name1.*, name2.*, ... nameN.* FROM name1, name2, ... nameN          # SELECT name1.*, name2.*, ... nameN.* FROM name1, name2, ... nameN
# Line 625  Line 877 
877          my $dbh = $self->{_dbh};          my $dbh = $self->{_dbh};
878          my $command = "SELECT DISTINCT " . join('.*, ', @{$objectNames}) . ".* FROM " .          my $command = "SELECT DISTINCT " . join('.*, ', @{$objectNames}) . ".* FROM " .
879                                  join(', ', @{$objectNames});                                  join(', ', @{$objectNames});
880        Trace("SQL = $command") if T(SQL => 4);
881          # Check for a filter clause.          # Check for a filter clause.
882          if ($filterClause) {          if ($filterClause) {
883                  # Here we have one, so we convert its field names and add it to the query. First,                  # Here we have one, so we convert its field names and add it to the query. First,
# Line 729  Line 982 
982                          $command .= " ORDER BY $orderClause";                          $command .= " ORDER BY $orderClause";
983                  }                  }
984          }          }
985          Trace("SQL query: $command") if T(2);      Trace("SQL query: $command") if T(3);
986          Trace("PARMS: '" . (join "', '", @params) . "'") if (T(3) && (@params > 0));      Trace("PARMS: '" . (join "', '", @params) . "'") if (T(4) && (@params > 0));
987          my $sth = $dbh->prepare_command($command);          my $sth = $dbh->prepare_command($command);
988          # Execute it with the parameters bound in.          # Execute it with the parameters bound in.
989          $sth->execute(@params) || Confess("SELECT error" . $sth->errstr());          $sth->execute(@params) || Confess("SELECT error" . $sth->errstr());
# Line 739  Line 992 
992          return $retVal;          return $retVal;
993  }  }
994    
995    =head3 GetList
996    
997    C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>
998    
999    Return a list of object descriptors for the specified objects as determined by the
1000    specified filter clause.
1001    
1002    This method is essentially the same as L</Get> except it returns a list of objects rather
1003    than a query object that can be used to get the results one record at a time.
1004    
1005    =over 4
1006    
1007    =item objectNames
1008    
1009    List containing the names of the entity and relationship objects to be retrieved.
1010    
1011    =item filterClause
1012    
1013    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1014    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
1015    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
1016    in the filter clause should be added to the parameter list as additional parameters. The
1017    fields in a filter clause can come from primary entity relations, relationship relations,
1018    or secondary entity relations; however, all of the entities and relationships involved must
1019    be included in the list of object names.
1020    
1021    The filter clause can also specify a sort order. To do this, simply follow the filter string
1022    with an ORDER BY clause. For example, the following filter string gets all genomes for a
1023    particular genus and sorts them by species name.
1024    
1025    C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
1026    
1027    The rules for field references in a sort order are the same as those for field references in the
1028    filter clause in general; however, odd things may happen if a sort field is from a secondary
1029    relation.
1030    
1031    =item param1, param2, ..., paramN
1032    
1033    Parameter values to be substituted into the filter clause.
1034    
1035    =item RETURN
1036    
1037    Returns a list of B<DBObject>s that satisfy the query conditions.
1038    
1039    =back
1040    
1041    =cut
1042    #: Return Type @%
1043    sub GetList {
1044        # Get the parameters.
1045        my ($self, $objectNames, $filterClause, @params) = @_;
1046        # Declare the return variable.
1047        my @retVal = ();
1048        # Perform the query.
1049        my $query = $self->Get($objectNames, $filterClause, @params);
1050        # Loop through the results.
1051        while (my $object = $query->Fetch) {
1052            push @retVal, $object;
1053        }
1054        # Return the result.
1055        return @retVal;
1056    }
1057    
1058  =head3 ComputeObjectSentence  =head3 ComputeObjectSentence
1059    
1060  C<< my $sentence = $database->ComputeObjectSentence($objectName); >>  C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>
1061    
1062  Check an object name, and if it is a relationship convert it to a relationship sentence.  Check an object name, and if it is a relationship convert it to a relationship sentence.
1063    
# Line 761  Line 1077 
1077    
1078  sub ComputeObjectSentence {  sub ComputeObjectSentence {
1079          # Get the parameters.          # Get the parameters.
1080          my $self = shift @_;      my ($self, $objectName) = @_;
         my ($objectName) = @_;  
1081          # Set the default return value.          # Set the default return value.
1082          my $retVal = $objectName;          my $retVal = $objectName;
1083          # Look for the object as a relationship.          # Look for the object as a relationship.
# Line 777  Line 1092 
1092    
1093  =head3 DumpRelations  =head3 DumpRelations
1094    
1095  C<< $database->DumpRelations($outputDirectory); >>  C<< $erdb->DumpRelations($outputDirectory); >>
1096    
1097  Write the contents of all the relations to tab-delimited files in the specified directory.  Write the contents of all the relations to tab-delimited files in the specified directory.
1098  Each file will have the same name as the relation dumped, with an extension of DTX.  Each file will have the same name as the relation dumped, with an extension of DTX.
# Line 794  Line 1109 
1109    
1110  sub DumpRelations {  sub DumpRelations {
1111          # Get the parameters.          # Get the parameters.
1112          my $self = shift @_;      my ($self, $outputDirectory) = @_;
         my ($outputDirectory) = @_;  
1113          # Now we need to run through all the relations. First, we loop through the entities.          # Now we need to run through all the relations. First, we loop through the entities.
1114          my $metaData = $self->{_metaData};          my $metaData = $self->{_metaData};
1115          my $entities = $metaData->{Entities};          my $entities = $metaData->{Entities};
1116          while (my ($entityName, $entityStructure) = each %{$entities}) {      for my $entityName (keys %{$entities}) {
1117            my $entityStructure = $entities->{$entityName};
1118                  # Get the entity's relations.                  # Get the entity's relations.
1119                  my $relationList = $entityStructure->{Relations};                  my $relationList = $entityStructure->{Relations};
1120                  # Loop through the relations, dumping them.                  # Loop through the relations, dumping them.
1121                  while (my ($relationName, $relation) = each %{$relationList}) {          for my $relationName (keys %{$relationList}) {
1122                my $relation = $relationList->{$relationName};
1123                          $self->_DumpRelation($outputDirectory, $relationName, $relation);                          $self->_DumpRelation($outputDirectory, $relationName, $relation);
1124                  }                  }
1125          }          }
1126          # Next, we loop through the relationships.          # Next, we loop through the relationships.
1127          my $relationships = $metaData->{Relationships};          my $relationships = $metaData->{Relationships};
1128          while (my ($relationshipName, $relationshipStructure) = each %{$relationships}) {      for my $relationshipName (keys %{$relationships}) {
1129            my $relationshipStructure = $relationships->{$relationshipName};
1130                  # Dump this relationship's relation.                  # Dump this relationship's relation.
1131                  $self->_DumpRelation($outputDirectory, $relationshipName, $relationshipStructure->{Relations}->{$relationshipName});                  $self->_DumpRelation($outputDirectory, $relationshipName, $relationshipStructure->{Relations}->{$relationshipName});
1132          }          }
# Line 817  Line 1134 
1134    
1135  =head3 InsertObject  =head3 InsertObject
1136    
1137  C<< my $ok = $database->InsertObject($objectType, \%fieldHash); >>  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>
1138    
1139  Insert an object into the database. The object is defined by a type name and then a hash  Insert an object into the database. The object is defined by a type name and then a hash
1140  of field names to values. Field values in the primary relation are represented by scalars.  of field names to values. Field values in the primary relation are represented by scalars.
# Line 826  Line 1143 
1143  example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases  example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases
1144  C<ZP_00210270.1> and C<gi|46206278>.  C<ZP_00210270.1> and C<gi|46206278>.
1145    
1146  C<< $database->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>  C<< $erdb->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>
1147    
1148  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
1149  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
1150    
1151  C<< $database->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>  C<< $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>
1152    
1153  =over 4  =over 4
1154    
# Line 853  Line 1170 
1170    
1171  sub InsertObject {  sub InsertObject {
1172          # Get the parameters.          # Get the parameters.
1173          my $self = shift @_;      my ($self, $newObjectType, $fieldHash) = @_;
         my ($newObjectType, $fieldHash) = @_;  
1174          # Denote that so far we appear successful.          # Denote that so far we appear successful.
1175          my $retVal = 1;          my $retVal = 1;
1176          # Get the database handle.          # Get the database handle.
# Line 864  Line 1180 
1180          # Loop through the relations. We'll build insert statements for each one. If a relation is          # Loop through the relations. We'll build insert statements for each one. If a relation is
1181          # secondary, we may end up generating multiple insert statements. If an error occurs, we          # secondary, we may end up generating multiple insert statements. If an error occurs, we
1182          # stop the loop.          # stop the loop.
1183          while ($retVal && (my ($relationName, $relationDefinition) = each %{$relationTable})) {      my @relationList = keys %{$relationTable};
1184        for (my $i = 0; $retVal && $i <= $#relationList; $i++) {
1185            my $relationName = $relationList[$i];
1186            my $relationDefinition = $relationTable->{$relationName};
1187                  # Get the relation's fields. For each field we will collect a value in the corresponding                  # Get the relation's fields. For each field we will collect a value in the corresponding
1188                  # position of the @valueList array. If one of the fields is missing, we will add it to the                  # position of the @valueList array. If one of the fields is missing, we will add it to the
1189                  # @missing list.                  # @missing list.
# Line 954  Line 1273 
1273    
1274  =head3 LoadTable  =head3 LoadTable
1275    
1276  C<< my %results = $database->LoadTable($fileName, $relationName, $truncateFlag); >>  C<< my %results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>
1277    
1278  Load data from a tab-delimited file into a specified table, optionally re-creating the table first.  Load data from a tab-delimited file into a specified table, optionally re-creating the table
1279    first.
1280    
1281  =over 4  =over 4
1282    
# Line 974  Line 1294 
1294    
1295  =item RETURN  =item RETURN
1296    
1297  Returns a statistical object containing the number of records read and a list of the error messages.  Returns a statistical object containing the number of records read and a list of
1298    the error messages.
1299    
1300  =back  =back
1301    
1302  =cut  =cut
1303  sub LoadTable {  sub LoadTable {
1304          # Get the parameters.          # Get the parameters.
1305          my $self = shift @_;      my ($self, $fileName, $relationName, $truncateFlag) = @_;
         my ($fileName, $relationName, $truncateFlag) = @_;  
1306          # Create the statistical return object.          # Create the statistical return object.
1307          my $retVal = _GetLoadStats();          my $retVal = _GetLoadStats();
1308          # Trace the fact of the load.          # Trace the fact of the load.
1309          Trace("Loading table $relationName from $fileName") if T(1);      Trace("Loading table $relationName from $fileName") if T(2);
1310          # Get the database handle.          # Get the database handle.
1311          my $dbh = $self->{_dbh};          my $dbh = $self->{_dbh};
1312        # Get the input file size.
1313        my $fileSize = -s $fileName;
1314          # Get the relation data.          # Get the relation data.
1315          my $relation = $self->_FindRelation($relationName);          my $relation = $self->_FindRelation($relationName);
1316          # Check the truncation flag.          # Check the truncation flag.
1317          if ($truncateFlag) {          if ($truncateFlag) {
1318                  Trace("Creating table $relationName") if T(1);          Trace("Creating table $relationName") if T(2);
1319            # Compute the row count estimate. We take the size of the load file,
1320            # divide it by the estimated row size, and then multiply by 1.5 to
1321            # leave extra room. We postulate a minimum row count of 1000 to
1322            # prevent problems with incoming empty load files.
1323            my $rowSize = $self->EstimateRowSize($relationName);
1324            my $estimate = FIG::max($fileSize * 1.5 / $rowSize, 1000);
1325                  # Re-create the table without its index.                  # Re-create the table without its index.
1326                  $self->CreateTable($relationName, 0);          $self->CreateTable($relationName, 0, $estimate);
1327            # If this is a pre-index DBMS, create the index here.
1328            if ($dbh->{_preIndex}) {
1329                eval {
1330                    $self->CreateIndex($relationName);
1331                };
1332                if ($@) {
1333                    $retVal->AddMessage($@);
1334                }
1335            }
1336          }          }
         # 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;  
         # Record the number of expected fields.  
         my $expectedFields = $fieldCount + ($primary ? 1 : 0);  
         # 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;  
         # Loop through the file.  
         while (<TABLEIN>) {  
                 # Chop off the new-line character.  
                 my $record = $_;  
                 chomp $record;  
         # Only proceed if the record is non-blank.  
         if ($record) {  
             # Escape all the backslashes found in the line.  
             $record =~ s/\\/\\\\/g;  
             # Eliminate any trailing tabs.  
             chop $record while substr($record, -1) eq "\t";  
             # 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) {  
                 $record .= "\t0";  
             }  
             # Write the record.  
             print TABLEOUT "$record\n";  
             # Count the record read.  
             my $count = $retVal->Add('records');  
             my $len = length $record;  
             Trace("Record $count written with $len characters.") if T(4);  
         }  
         }  
         # Close the files.  
         close TABLEIN;  
         close TABLEOUT;  
     Trace("Temporary file $tempName created.") if T(4);  
1337      # Load the table.      # Load the table.
1338          my $rv;          my $rv;
1339          eval {          eval {
1340                  $rv = $dbh->load_table(file => $tempName, tbl => $relationName);          $rv = $dbh->load_table(file => $fileName, tbl => $relationName);
1341          };          };
1342          if (!defined $rv) {          if (!defined $rv) {
1343          $retVal->AddMessage($@) if ($@);          $retVal->AddMessage($@) if ($@);
1344          $retVal->AddMessage("Table load failed for $relationName using $tempName.");          $retVal->AddMessage("Table load failed for $relationName using $fileName.");
1345                  Trace("Table load failed for $relationName.") if T(1);                  Trace("Table load failed for $relationName.") if T(1);
1346          } else {          } else {
1347                  # Here we successfully loaded the table. Trace the number of records loaded.          # Here we successfully loaded the table.
1348                  Trace("$retVal->{records} records read for $relationName.") if T(1);          $retVal->Add("tables");
1349            my $size = -s $fileName;
1350            Trace("$size bytes loaded into $relationName.") if T(2);
1351                  # If we're rebuilding, we need to create the table indexes.                  # If we're rebuilding, we need to create the table indexes.
1352                  if ($truncateFlag) {          if ($truncateFlag && ! $dbh->{_preIndex}) {
1353                          eval {                          eval {
1354                                  $self->CreateIndex($relationName);                                  $self->CreateIndex($relationName);
1355                          };                          };
# Line 1061  Line 1358 
1358                          }                          }
1359                  }                  }
1360          }          }
1361          # Commit the database changes.      # Analyze the table to improve performance.
1362          $dbh->commit_tran;      $dbh->vacuum_it($relationName);
         # Delete the temporary file.  
         unlink $tempName;  
1363          # Return the statistics.          # Return the statistics.
1364          return $retVal;          return $retVal;
1365  }  }
1366    
1367  =head3 GenerateEntity  =head3 GenerateEntity
1368    
1369  C<< my $fieldHash = $database->GenerateEntity($id, $type, \%values); >>  C<< my $fieldHash = $erdb->GenerateEntity($id, $type, \%values); >>
1370    
1371  Generate the data for a new entity instance. This method creates a field hash suitable for  Generate the data for a new entity instance. This method creates a field hash suitable for
1372  passing as a parameter to L</InsertObject>. The ID is specified by the callr, but the rest  passing as a parameter to L</InsertObject>. The ID is specified by the callr, but the rest
# Line 1109  Line 1404 
1404    
1405  sub GenerateEntity {  sub GenerateEntity {
1406          # Get the parameters.          # Get the parameters.
1407          my $self = shift @_;      my ($self, $id, $type, $values) = @_;
         my ($id, $type, $values) = @_;  
1408          # Create the return hash.          # Create the return hash.
1409          my $this = { id => $id };          my $this = { id => $id };
1410          # Get the metadata structure.          # Get the metadata structure.
# Line 1128  Line 1422 
1422          return $this;          return $this;
1423  }  }
1424    
1425    =head3 GetEntity
1426    
1427    C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>
1428    
1429    Return an object describing the entity instance with a specified ID.
1430    
1431    =over 4
1432    
1433    =item entityType
1434    
1435    Entity type name.
1436    
1437    =item ID
1438    
1439    ID of the desired entity.
1440    
1441    =item RETURN
1442    
1443    Returns a B<DBObject> representing the desired entity instance, or an undefined value if no
1444    instance is found with the specified key.
1445    
1446    =back
1447    
1448    =cut
1449    
1450    sub GetEntity {
1451        # Get the parameters.
1452        my ($self, $entityType, $ID) = @_;
1453        # Create a query.
1454        my $query = $self->Get([$entityType], "$entityType(id) = ?", $ID);
1455        # Get the first (and only) object.
1456        my $retVal = $query->Fetch();
1457        # Return the result.
1458        return $retVal;
1459    }
1460    
1461    =head3 GetEntityValues
1462    
1463    C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>
1464    
1465    Return a list of values from a specified entity instance.
1466    
1467    =over 4
1468    
1469    =item entityType
1470    
1471    Entity type name.
1472    
1473    =item ID
1474    
1475    ID of the desired entity.
1476    
1477    =item fields
1478    
1479    List of field names, each of the form I<objectName>C<(>I<fieldName>C<)>.
1480    
1481    =item RETURN
1482    
1483    Returns a flattened list of the values of the specified fields for the specified entity.
1484    
1485    =back
1486    
1487    =cut
1488    
1489    sub GetEntityValues {
1490        # Get the parameters.
1491        my ($self, $entityType, $ID, $fields) = @_;
1492        # Get the specified entity.
1493        my $entity = $self->GetEntity($entityType, $ID);
1494        # Declare the return list.
1495        my @retVal = ();
1496        # If we found the entity, push the values into the return list.
1497        if ($entity) {
1498            push @retVal, $entity->Values($fields);
1499        }
1500        # Return the result.
1501        return @retVal;
1502    }
1503    
1504    =head3 GetAll
1505    
1506    C<< my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>
1507    
1508    Return a list of values taken from the objects returned by a query. The first three
1509    parameters correspond to the parameters of the L</Get> method. The final parameter is
1510    a list of the fields desired from each record found by the query. The field name
1511    syntax is the standard syntax used for fields in the B<ERDB> system--
1512    B<I<objectName>(I<fieldName>)>-- where I<objectName> is the name of the relevant entity
1513    or relationship and I<fieldName> is the name of the field.
1514    
1515    The list returned will be a list of lists. Each element of the list will contain
1516    the values returned for the fields specified in the fourth parameter. If one of the
1517    fields specified returns multiple values, they are flattened in with the rest. For
1518    example, the following call will return a list of the features in a particular
1519    spreadsheet cell, and each feature will be represented by a list containing the
1520    feature ID followed by all of its aliases.
1521    
1522    C<< $query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>
1523    
1524    =over 4
1525    
1526    =item objectNames
1527    
1528    List containing the names of the entity and relationship objects to be retrieved.
1529    
1530    =item filterClause
1531    
1532    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1533    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
1534    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
1535    parameter list as additional parameters. The fields in a filter clause can come from primary
1536    entity relations, relationship relations, or secondary entity relations; however, all of the
1537    entities and relationships involved must be included in the list of object names.
1538    
1539    =item parameterList
1540    
1541    List of the parameters to be substituted in for the parameters marks in the filter clause.
1542    
1543    =item fields
1544    
1545    List of the fields to be returned in each element of the list returned.
1546    
1547    =item count
1548    
1549    Maximum number of records to return. If omitted or 0, all available records will be returned.
1550    
1551    =item RETURN
1552    
1553    Returns a list of list references. Each element of the return list contains the values for the
1554    fields specified in the B<fields> parameter.
1555    
1556    =back
1557    
1558    =cut
1559    #: Return Type @@;
1560    sub GetAll {
1561        # Get the parameters.
1562        my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
1563        # Translate the parameters from a list reference to a list. If the parameter
1564        # list is a scalar we convert it into a singleton list.
1565        my @parmList = ();
1566        if (ref $parameterList eq "ARRAY") {
1567            @parmList = @{$parameterList};
1568        } else {
1569            push @parmList, $parameterList;
1570        }
1571        # Create the query.
1572        my $query = $self->Get($objectNames, $filterClause, @parmList);
1573        # Set up a counter of the number of records read.
1574        my $fetched = 0;
1575        # Insure the counter has a value.
1576        if (!defined $count) {
1577            $count = 0;
1578        }
1579        # Loop through the records returned, extracting the fields. Note that if the
1580        # counter is non-zero, we stop when the number of records read hits the count.
1581        my @retVal = ();
1582        while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {
1583            my @rowData = $row->Values($fields);
1584            push @retVal, \@rowData;
1585            $fetched++;
1586        }
1587        # Return the resulting list.
1588        return @retVal;
1589    }
1590    
1591    =head3 EstimateRowSize
1592    
1593    C<< my $rowSize = $erdb->EstimateRowSize($relName); >>
1594    
1595    Estimate the row size of the specified relation. The estimated row size is computed by adding
1596    up the average length for each data type.
1597    
1598    =over 4
1599    
1600    =item relName
1601    
1602    Name of the relation whose estimated row size is desired.
1603    
1604    =item RETURN
1605    
1606    Returns an estimate of the row size for the specified relation.
1607    
1608    =back
1609    
1610    =cut
1611    #: Return Type $;
1612    sub EstimateRowSize {
1613        # Get the parameters.
1614        my ($self, $relName) = @_;
1615        # Declare the return variable.
1616        my $retVal = 0;
1617        # Find the relation descriptor.
1618        my $relation = $self->_FindRelation($relName);
1619        # Get the list of fields.
1620        for my $fieldData (@{$relation->{Fields}}) {
1621            # Get the field type and add its length.
1622            my $fieldLen = $TypeTable{$fieldData->{type}}->{avgLen};
1623            $retVal += $fieldLen;
1624        }
1625        # Return the result.
1626        return $retVal;
1627    }
1628    
1629  =head2 Internal Utility Methods  =head2 Internal Utility Methods
1630    
# Line 1243  Line 1740 
1740    
1741  sub _DumpRelation {  sub _DumpRelation {
1742          # Get the parameters.          # Get the parameters.
1743          my $self = shift @_;      my ($self, $outputDirectory, $relationName, $relation) = @_;
         my ($outputDirectory, $relationName, $relation) = @_;  
1744          # Open the output file.          # Open the output file.
1745          my $fileName = "$outputDirectory/$relationName.dtx";          my $fileName = "$outputDirectory/$relationName.dtx";
1746          open(DTXOUT, ">$fileName") || Confess("Could not open dump file $fileName: $!");          open(DTXOUT, ">$fileName") || Confess("Could not open dump file $fileName: $!");
# Line 1290  Line 1786 
1786    
1787  sub _GetStructure {  sub _GetStructure {
1788          # Get the parameters.          # Get the parameters.
1789          my $self = shift @_;      my ($self, $objectName) = @_;
         my ($objectName) = @_;  
1790          # Get the metadata structure.          # Get the metadata structure.
1791          my $metadata = $self->{_metaData};          my $metadata = $self->{_metaData};
1792          # Declare the variable to receive the descriptor.          # Declare the variable to receive the descriptor.
# Line 1330  Line 1825 
1825    
1826  sub _GetRelationTable {  sub _GetRelationTable {
1827          # Get the parameters.          # Get the parameters.
1828          my $self = shift @_;      my ($self, $objectName) = @_;
         my ($objectName) = @_;  
1829          # Get the descriptor from the metadata.          # Get the descriptor from the metadata.
1830          my $objectData = $self->_GetStructure($objectName);          my $objectData = $self->_GetStructure($objectName);
1831          # Return the object's relation list.          # Return the object's relation list.
# Line 1360  Line 1854 
1854    
1855  sub _GetFieldTable {  sub _GetFieldTable {
1856          # Get the parameters.          # Get the parameters.
1857          my $self = shift @_;      my ($self, $objectName) = @_;
         my ($objectName) = @_;  
1858          # Get the descriptor from the metadata.          # Get the descriptor from the metadata.
1859          my $objectData = $self->_GetStructure($objectName);          my $objectData = $self->_GetStructure($objectName);
1860          # Return the object's field table.          # Return the object's field table.
# Line 1458  Line 1951 
1951    
1952  sub _LoadRelation {  sub _LoadRelation {
1953          # Get the parameters.          # Get the parameters.
1954          my $self = shift @_;      my ($self, $directoryName, $relationName, $rebuild) = @_;
         my ($directoryName, $relationName, $rebuild) = @_;  
1955          # Create the file name.          # Create the file name.
1956          my $fileName = "$directoryName/$relationName";          my $fileName = "$directoryName/$relationName";
1957          # If the file doesn't exist, try adding the .dtx suffix.          # If the file doesn't exist, try adding the .dtx suffix.
# Line 1509  Line 2001 
2001  sub _LoadMetaData {  sub _LoadMetaData {
2002          # Get the parameters.          # Get the parameters.
2003          my ($filename) = @_;          my ($filename) = @_;
2004        Trace("Reading Sprout DBD from $filename.") if T(2);
2005          # Slurp the XML file into a variable. Extensive use of options is used to insure we          # Slurp the XML file into a variable. Extensive use of options is used to insure we
2006          # get the exact structure we want.          # get the exact structure we want.
2007          my $metadata = XML::Simple::XMLin($filename,          my $metadata = XML::Simple::XMLin($filename,
# Line 1533  Line 2026 
2026          my %masterRelationTable = ();          my %masterRelationTable = ();
2027          # Loop through the entities.          # Loop through the entities.
2028          my $entityList = $metadata->{Entities};          my $entityList = $metadata->{Entities};
2029          while (my ($entityName, $entityStructure) = each %{$entityList}) {      for my $entityName (keys %{$entityList}) {
2030            my $entityStructure = $entityList->{$entityName};
2031                  #                  #
2032                  # The first step is to run creating all the entity's default values. For C<Field> elements,          # The first step is to create all the entity's default values. For C<Field> elements,
2033                  # the relation name must be added where it is not specified. For relationships,                  # the relation name must be added where it is not specified. For relationships,
2034                  # the B<from-link> and B<to-link> fields must be inserted, and for entities an B<id>                  # the B<from-link> and B<to-link> fields must be inserted, and for entities an B<id>
2035                  # field must be added to each relation. Finally, each field will have a C<PrettySort> attribute                  # field must be added to each relation. Finally, each field will have a C<PrettySort> attribute
# Line 1581  Line 2075 
2075                  # to a list of fields. First, we need the ID field itself.                  # to a list of fields. First, we need the ID field itself.
2076                  my $idField = $fieldList->{id};                  my $idField = $fieldList->{id};
2077                  # Loop through the relations.                  # Loop through the relations.
2078                  while (my ($relationName, $relation) = each %{$relationTable}) {          for my $relationName (keys %{$relationTable}) {
2079                my $relation = $relationTable->{$relationName};
2080                          # Get the relation's field list.                          # Get the relation's field list.
2081                          my $relationFieldList = $relation->{Fields};                          my $relationFieldList = $relation->{Fields};
2082                          # Add the ID field to it. If the field's already there, it will not make any                          # Add the ID field to it. If the field's already there, it will not make any
# Line 1631  Line 2126 
2126                  # The next step is to insure that each relation has at least one index that begins with the ID field.                  # The next step is to insure that each relation has at least one index that begins with the ID field.
2127                  # After that, we convert each relation's index list to an index table. We first need to loop through                  # After that, we convert each relation's index list to an index table. We first need to loop through
2128                  # the relations.                  # the relations.
2129                  while (my ($relationName, $relation) = each %{$relationTable}) {          for my $relationName (keys %{$relationTable}) {
2130                my $relation = $relationTable->{$relationName};
2131                          # Get the relation's index list.                          # Get the relation's index list.
2132                          my $indexList = $relation->{Indexes};                          my $indexList = $relation->{Indexes};
2133                          # Insure this relation has an ID index.                          # Insure this relation has an ID index.
# Line 1662  Line 2158 
2158          # Loop through the relationships. Relationships actually turn out to be much simpler than entities.          # Loop through the relationships. Relationships actually turn out to be much simpler than entities.
2159          # For one thing, there is only a single constituent relation.          # For one thing, there is only a single constituent relation.
2160          my $relationshipList = $metadata->{Relationships};          my $relationshipList = $metadata->{Relationships};
2161          while (my ($relationshipName, $relationshipStructure) = each %{$relationshipList}) {      for my $relationshipName (keys %{$relationshipList}) {
2162            my $relationshipStructure = $relationshipList->{$relationshipName};
2163                  # Fix up this relationship.                  # Fix up this relationship.
2164                  _FixupFields($relationshipStructure, $relationshipName, 2, 3);                  _FixupFields($relationshipStructure, $relationshipName, 2, 3);
2165                  # Format a description for the FROM field.                  # Format a description for the FROM field.
# Line 1711  Line 2208 
2208                  my @fromList = ();                  my @fromList = ();
2209                  my @toList = ();                  my @toList = ();
2210                  my @bothList = ();                  my @bothList = ();
2211                  while (my ($relationshipName, $relationship) = each %{$relationshipList}) {          Trace("Join table build for $entityName.") if T(metadata => 4);
2212            for my $relationshipName (keys %{$relationshipList}) {
2213                my $relationship = $relationshipList->{$relationshipName};
2214                          # Determine if this relationship has our entity in one of its link fields.                          # Determine if this relationship has our entity in one of its link fields.
2215                          if ($relationship->{from} eq $entityName) {              my $fromEntity = $relationship->{from};
2216                                  if ($relationship->{to} eq $entityName) {              my $toEntity = $relationship->{to};
2217                Trace("Join check for relationship $relationshipName from $fromEntity to $toEntity.") if T(4);
2218                if ($fromEntity eq $entityName) {
2219                    if ($toEntity eq $entityName) {
2220                                          # Here the relationship is recursive.                                          # Here the relationship is recursive.
2221                                          push @bothList, $relationshipName;                                          push @bothList, $relationshipName;
2222                        Trace("Relationship $relationshipName put in both-list.") if T(metadata => 4);
2223                                  } else {                                  } else {
2224                                          # Here the relationship comes from the entity.                                          # Here the relationship comes from the entity.
2225                                          push @fromList, $relationshipName;                                          push @fromList, $relationshipName;
2226                        Trace("Relationship $relationshipName put in from-list.") if T(metadata => 4);
2227                                  }                                  }
2228                          } elsif ($relationship->{to} eq $entityName) {              } elsif ($toEntity eq $entityName) {
2229                                  # Here the relationship goes to the entity.                                  # Here the relationship goes to the entity.
2230                                  push @toList, $relationshipName;                                  push @toList, $relationshipName;
2231                    Trace("Relationship $relationshipName put in to-list.") if T(metadata => 4);
2232                          }                          }
2233                  }                  }
2234                  # Create the nonrecursive joins. Note that we build two hashes for running                  # Create the nonrecursive joins. Note that we build two hashes for running
# Line 1732  Line 2237 
2237                  # hash table at the same time.                  # hash table at the same time.
2238                  my %directRelationships = ( from => \@fromList, to => \@toList );                  my %directRelationships = ( from => \@fromList, to => \@toList );
2239                  my %otherRelationships = ( from => \@fromList, to => \@toList );                  my %otherRelationships = ( from => \@fromList, to => \@toList );
2240                  while (my ($linkType, $relationships) = each %directRelationships) {          for my $linkType (keys %directRelationships) {
2241                my $relationships = $directRelationships{$linkType};
2242                          # Loop through all the relationships.                          # Loop through all the relationships.
2243                          for my $relationshipName (@{$relationships}) {                          for my $relationshipName (@{$relationships}) {
2244                                  # Create joins between the entity and this relationship.                                  # Create joins between the entity and this relationship.
2245                                  my $linkField = "$relationshipName.${linkType}_link";                                  my $linkField = "$relationshipName.${linkType}_link";
2246                                  my $joinClause = "$entityName.id = $linkField";                                  my $joinClause = "$entityName.id = $linkField";
2247                    Trace("Entity join clause is $joinClause for $entityName and $relationshipName.") if T(metadata => 4);
2248                                  $joinTable{"$entityName/$relationshipName"} = $joinClause;                                  $joinTable{"$entityName/$relationshipName"} = $joinClause;
2249                                  $joinTable{"$relationshipName/$entityName"} = $joinClause;                                  $joinTable{"$relationshipName/$entityName"} = $joinClause;
2250                                  # Create joins between this relationship and the other relationships.                                  # Create joins between this relationship and the other relationships.
2251                                  while (my ($otherType, $otherships) = each %otherRelationships) {                  for my $otherType (keys %otherRelationships) {
2252                        my $otherships = $otherRelationships{$otherType};
2253                                          for my $otherName (@{$otherships}) {                                          for my $otherName (@{$otherships}) {
2254                                                  # Get the key for this join.                                                  # Get the key for this join.
2255                                                  my $joinKey = "$otherName/$relationshipName";                                                  my $joinKey = "$otherName/$relationshipName";
# Line 1751  Line 2259 
2259                                                          # path is ambiguous. We delete the join from the join                                                          # path is ambiguous. We delete the join from the join
2260                                                          # table to prevent it from being used.                                                          # table to prevent it from being used.
2261                                                          delete $joinTable{$joinKey};                                                          delete $joinTable{$joinKey};
2262                                Trace("Deleting ambiguous join $joinKey.") if T(4);
2263                                                  } elsif ($otherName ne $relationshipName) {                                                  } elsif ($otherName ne $relationshipName) {
2264                                                          # Here we have a valid join. Note that joins between a                                                          # Here we have a valid join. Note that joins between a
2265                                                          # relationship and itself are prohibited.                                                          # relationship and itself are prohibited.
2266                                                          $joinTable{$joinKey} = "$otherName.${otherType}_link = $linkField";                              my $relJoinClause = "$otherName.${otherType}_link = $linkField";
2267                                $joinTable{$joinKey} = $relJoinClause;
2268                                Trace("Relationship join clause is $relJoinClause for $joinKey.") if T(metadata => 4);
2269                                                  }                                                  }
2270                                          }                                          }
2271                                  }                                  }
# Line 1763  Line 2274 
2274                                  # relationship can only be ambiguous with another recursive relationship,                                  # relationship can only be ambiguous with another recursive relationship,
2275                                  # and the incoming relationship from the outer loop is never recursive.                                  # and the incoming relationship from the outer loop is never recursive.
2276                                  for my $otherName (@bothList) {                                  for my $otherName (@bothList) {
2277                        Trace("Setting up relationship joins to recursive relationship $otherName with $relationshipName.") if T(metadata => 4);
2278                                          # Join from the left.                                          # Join from the left.
2279                                          $joinTable{"$relationshipName/$otherName"} =                                          $joinTable{"$relationshipName/$otherName"} =
2280                                                  "$linkField = $otherName.from_link";                                                  "$linkField = $otherName.from_link";
# Line 1777  Line 2289 
2289                  # rise to situations where we can't create the path we want; however, it is always                  # rise to situations where we can't create the path we want; however, it is always
2290                  # possible to get the same effect using multiple queries.                  # possible to get the same effect using multiple queries.
2291                  for my $relationshipName (@bothList) {                  for my $relationshipName (@bothList) {
2292                Trace("Setting up entity joins to recursive relationship $relationshipName with $entityName.") if T(metadata => 4);
2293                          # Join to the entity from each direction.                          # Join to the entity from each direction.
2294                          $joinTable{"$entityName/$relationshipName"} =                          $joinTable{"$entityName/$relationshipName"} =
2295                                  "$entityName.id = $relationshipName.from_link";                                  "$entityName.id = $relationshipName.from_link";
# Line 1827  Line 2340 
2340          # index descriptor does not exist, it will be created automatically so we can add          # index descriptor does not exist, it will be created automatically so we can add
2341          # the field to it.          # the field to it.
2342          unshift @{$newIndex->{IndexFields}}, $firstField;          unshift @{$newIndex->{IndexFields}}, $firstField;
2343        # If this is a one-to-many relationship, the "To" index is unique.
2344        if ($relationshipStructure->{arity} eq "1M" && $indexKey eq "To") {
2345            $newIndex->{Unique} = 'true';
2346        }
2347          # Add the index to the relation.          # Add the index to the relation.
2348          _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);          _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);
2349  }  }
# Line 1916  Line 2433 
2433                  $structure->{Fields} = { };                  $structure->{Fields} = { };
2434          } else {          } else {
2435                  # Here we have a field list. Loop through its fields.                  # Here we have a field list. Loop through its fields.
2436                  while (my ($fieldName, $fieldData) = each %{$structure->{Fields}}) {          my $fieldStructures = $structure->{Fields};
2437            for my $fieldName (keys %{$fieldStructures}) {
2438                Trace("Processing field $fieldName of $defaultRelationName.") if T(4);
2439                my $fieldData = $fieldStructures->{$fieldName};
2440                          # Get the field type.                          # Get the field type.
2441                          my $type = $fieldData->{type};                          my $type = $fieldData->{type};
2442                          # Plug in a relation name if it is needed.                          # Plug in a relation name if it is needed.
# Line 2113  Line 2633 
2633    
2634  sub _IsPrimary {  sub _IsPrimary {
2635          # Get the parameters.          # Get the parameters.
2636          my $self = shift @_;      my ($self, $relationName) = @_;
         my ($relationName) = @_;  
2637          # Check for the relation in the entity table.          # Check for the relation in the entity table.
2638          my $entityTable = $self->{_metaData}->{Entities};          my $entityTable = $self->{_metaData}->{Entities};
2639          my $retVal = exists $entityTable->{$relationName};          my $retVal = exists $entityTable->{$relationName};
# Line 2148  Line 2667 
2667  =cut  =cut
2668  sub _FindRelation {  sub _FindRelation {
2669          # Get the parameters.          # Get the parameters.
2670          my $self = shift @_;      my ($self, $relationName) = @_;
         my ($relationName) = @_;  
2671          # Get the relation's structure from the master relation table in the metadata structure.          # Get the relation's structure from the master relation table in the metadata structure.
2672          my $metaData = $self->{_metaData};          my $metaData = $self->{_metaData};
2673          my $retVal = $metaData->{RelationTable}->{$relationName};          my $retVal = $metaData->{RelationTable}->{$relationName};
# Line 2277  Line 2795 
2795                  my $indexData = $indexTable->{$indexName};                  my $indexData = $indexTable->{$indexName};
2796                  # Determine whether or not the index is unique.                  # Determine whether or not the index is unique.
2797                  my $fullName = $indexName;                  my $fullName = $indexName;
2798                  if ($indexData->{Unique} eq "true") {          if (exists $indexData->{Unique} && $indexData->{Unique} eq "true") {
2799                          $fullName .= " (unique)";                          $fullName .= " (unique)";
2800                  }                  }
2801                  # Start an HTML list item for this index.                  # Start an HTML list item for this index.

Legend:
Removed from v.1.3  
changed lines
  Added in v.1.26

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3