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

Diff of /Sprout/ERDB.pm

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

revision 1.6, Wed May 4 03:24:43 2005 UTC revision 1.30, Wed Jan 11 19:39:03 2006 UTC
# Line 2  Line 2 
2    
3          use strict;          use strict;
4          use Tracer;          use Tracer;
5          use DBKernel;      use DBrtns;
6          use Data::Dumper;          use Data::Dumper;
7          use XML::Simple;          use XML::Simple;
8          use DBQuery;          use DBQuery;
9          use DBObject;          use 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 32  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 69  Line 71 
71  is described in the L</GenerateEntity> and L</GenerateConnection> methods, though it is not yet  is described in the L</GenerateEntity> and L</GenerateConnection> methods, though it is not yet
72  fully implemented.  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    
299  # GLOBALS  # GLOBALS
# 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 145  Line 371 
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 282  Line 508 
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 ($sourceRelation, $targetRelation) = ($1, $2);                  my ($sourceRelation, $targetRelation) = ($1, $2);
511                  Trace("Join with key $joinKey is from $sourceRelation to $targetRelation.") if T(4);          Trace("Join with key $joinKey is from $sourceRelation to $targetRelation.") if T(Joins => 4);
512                  my $source = $self->ComputeObjectSentence($sourceRelation);                  my $source = $self->ComputeObjectSentence($sourceRelation);
513                  my $target = $self->ComputeObjectSentence($targetRelation);                  my $target = $self->ComputeObjectSentence($targetRelation);
514                  my $clause = $joinTable->{$joinKey};                  my $clause = $joinTable->{$joinKey};
# Line 300  Line 526 
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 315  Line 541 
541    
542  =head3 CreateTables  =head3 CreateTables
543    
544  C<< $datanase->CreateTables(); >>  C<< $erdb->CreateTables(); >>
545    
546  This method creates the tables for the database from the metadata structure loaded by the  This method creates the tables for the database from the metadata structure loaded by the
547  constructor. It is expected this function will only be used on rare occasions, when the  constructor. It is expected this function will only be used on rare occasions, when the
# Line 327  Line 553 
553  sub CreateTables {  sub CreateTables {
554          # Get the parameters.          # Get the parameters.
555          my ($self) = @_;          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          my $entityHash = $metadata->{Entities};      for my $relationName (@relNames) {
         for my $entityName (keys %{$entityHash}) {  
                 my $entityData = $entityHash->{$entityName};  
                 # Tell the user what we're doing.  
                 Trace("Creating relations for entity $entityName.") if T(1);  
                 # Loop through the entity's relations.  
                 for my $relationName (keys %{$entityData->{Relations}}) {  
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 363  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, $relationName, $indexFlag) = @_;      my ($self, $relationName, $indexFlag, $estimatedRows) = @_;
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 398  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 410  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    
# Line 436  Line 660 
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 486  Line 715 
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 530  Line 749 
749    
750  =head3 GetEntityTypes  =head3 GetEntityTypes
751    
752  C<< my @names = $database->GetEntityTypes; >>  C<< my @names = $erdb->GetEntityTypes; >>
753    
754  Return a list of the entity type names.  Return a list of the entity type names.
755    
# Line 545  Line 764 
764          return sort keys %{$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 555  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 572  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 605  Line 851 
851    
852  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
853    
854    Note that the case is important. Only an uppercase "ORDER BY" with a single space will
855    be processed. The idea is to make it less likely to find the verb by accident.
856    
857  The rules for field references in a sort order are the same as those for field references in the  The rules for field references in a sort order are the same as those for field references in the
858  filter clause in general; however, odd things may happen if a sort field is from a secondary  filter clause in general; however, odd things may happen if a sort field is from a secondary
859  relation.  relation.
# Line 713  Line 962 
962                                  $lastObject = $thisObject;                                  $lastObject = $thisObject;
963                          }                          }
964                  }                  }
965                  # Now we need to handle the whole ORDER BY thing. We'll put the order by clause          # Now we need to handle the whole ORDER BY / LIMIT thing. The important part
966                  # in the following variable.          # here is we want the filter clause to be empty if there's no WHERE filter.
967            # We'll put the ORDER BY / LIMIT clauses in the following variable.
968                  my $orderClause = "";                  my $orderClause = "";
969                  # Locate the ORDER BY verb (if any).          # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy
970                  if ($filterString =~ m/^(.*)ORDER BY/g) {          # operator so that we find the first occurrence of either verb.
971                          # Here we have an ORDER BY verb. Split it off of the filter string.          if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {
972                # Here we have an ORDER BY or LIMIT verb. Split it off of the filter string.
973                          my $pos = pos $filterString;                          my $pos = pos $filterString;
974                          $orderClause = substr($filterString, $pos);              $orderClause = $2 . substr($filterString, $pos);
975                          $filterString = $1;                          $filterString = $1;
976                  }                  }
977                  # Add the filter and the join clauses (if any) to the SELECT command.                  # Add the filter and the join clauses (if any) to the SELECT command.
# Line 730  Line 981 
981                  if (@joinWhere) {                  if (@joinWhere) {
982                          $command .= " WHERE " . join(' AND ', @joinWhere);                          $command .= " WHERE " . join(' AND ', @joinWhere);
983                  }                  }
984                  # Add the sort clause (if any) to the SELECT command.          # Add the sort or limit clause (if any) to the SELECT command.
985                  if ($orderClause) {                  if ($orderClause) {
986                          $command .= " ORDER BY $orderClause";              $command .= " $orderClause";
987                  }                  }
988          }          }
989          Trace("SQL query: $command") if T(2);      Trace("SQL query: $command") if T(SQL => 4);
990          Trace("PARMS: '" . (join "', '", @params) . "'") if (T(3) && (@params > 0));      Trace("PARMS: '" . (join "', '", @params) . "'") if (T(SQL => 4) && (@params > 0));
991          my $sth = $dbh->prepare_command($command);          my $sth = $dbh->prepare_command($command);
992          # Execute it with the parameters bound in.          # Execute it with the parameters bound in.
993          $sth->execute(@params) || Confess("SELECT error" . $sth->errstr());          $sth->execute(@params) || Confess("SELECT error" . $sth->errstr());
# Line 747  Line 998 
998    
999  =head3 GetList  =head3 GetList
1000    
1001  C<< my @dbObjects = $database->GetList(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>
1002    
1003  Return a list of object descriptors for the specified objects as determined by the  Return a list of object descriptors for the specified objects as determined by the
1004  specified filter clause.  specified filter clause.
1005    
1006  This method is essentially the same as L</Get> except it returns a list of objects rather  This method is essentially the same as L</Get> except it returns a list of objects rather
1007  that a query object that can be used to get the results one record at a time.  than a query object that can be used to get the results one record at a time.
   
 =over 4  
1008    
1009  =over 4  =over 4
1010    
# Line 812  Line 1061 
1061    
1062  =head3 ComputeObjectSentence  =head3 ComputeObjectSentence
1063    
1064  C<< my $sentence = $database->ComputeObjectSentence($objectName); >>  C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>
1065    
1066  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.
1067    
# Line 847  Line 1096 
1096    
1097  =head3 DumpRelations  =head3 DumpRelations
1098    
1099  C<< $database->DumpRelations($outputDirectory); >>  C<< $erdb->DumpRelations($outputDirectory); >>
1100    
1101  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.
1102  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 889  Line 1138 
1138    
1139  =head3 InsertObject  =head3 InsertObject
1140    
1141  C<< my $ok = $database->InsertObject($objectType, \%fieldHash); >>  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>
1142    
1143  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
1144  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 898  Line 1147 
1147  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
1148  C<ZP_00210270.1> and C<gi|46206278>.  C<ZP_00210270.1> and C<gi|46206278>.
1149    
1150  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']}); >>
1151    
1152  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
1153  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>.
1154    
1155  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'}); >>
1156    
1157  =over 4  =over 4
1158    
# Line 1028  Line 1277 
1277    
1278  =head3 LoadTable  =head3 LoadTable
1279    
1280  C<< my %results = $database->LoadTable($fileName, $relationName, $truncateFlag); >>  C<< my %results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>
1281    
1282  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
1283    first.
1284    
1285  =over 4  =over 4
1286    
# Line 1048  Line 1298 
1298    
1299  =item RETURN  =item RETURN
1300    
1301  Returns a statistical object containing the number of records read and a list of the error messages.  Returns a statistical object containing a list of the error messages.
1302    
1303  =back  =back
1304    
# Line 1059  Line 1309 
1309          # Create the statistical return object.          # Create the statistical return object.
1310          my $retVal = _GetLoadStats();          my $retVal = _GetLoadStats();
1311          # Trace the fact of the load.          # Trace the fact of the load.
1312          Trace("Loading table $relationName from $fileName") if T(1);      Trace("Loading table $relationName from $fileName") if T(2);
1313          # Get the database handle.          # Get the database handle.
1314          my $dbh = $self->{_dbh};          my $dbh = $self->{_dbh};
1315        # Get the input file size.
1316        my $fileSize = -s $fileName;
1317          # Get the relation data.          # Get the relation data.
1318          my $relation = $self->_FindRelation($relationName);          my $relation = $self->_FindRelation($relationName);
1319          # Check the truncation flag.          # Check the truncation flag.
1320          if ($truncateFlag) {          if ($truncateFlag) {
1321                  Trace("Creating table $relationName") if T(1);          Trace("Creating table $relationName") if T(2);
1322            # Compute the row count estimate. We take the size of the load file,
1323            # divide it by the estimated row size, and then multiply by 1.5 to
1324            # leave extra room. We postulate a minimum row count of 1000 to
1325            # prevent problems with incoming empty load files.
1326            my $rowSize = $self->EstimateRowSize($relationName);
1327            my $estimate = FIG::max($fileSize * 1.5 / $rowSize, 1000);
1328                  # Re-create the table without its index.                  # Re-create the table without its index.
1329                  $self->CreateTable($relationName, 0);          $self->CreateTable($relationName, 0, $estimate);
1330            # If this is a pre-index DBMS, create the index here.
1331            if ($dbh->{_preIndex}) {
1332                eval {
1333                    $self->CreateIndex($relationName);
1334                };
1335                if ($@) {
1336                    $retVal->AddMessage($@);
1337                }
1338            }
1339          }          }
         # 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);  
1340      # Load the table.      # Load the table.
1341          my $rv;          my $rv;
1342          eval {          eval {
1343                  $rv = $dbh->load_table(file => $tempName, tbl => $relationName);          $rv = $dbh->load_table(file => $fileName, tbl => $relationName);
1344          };          };
1345          if (!defined $rv) {          if (!defined $rv) {
1346          $retVal->AddMessage($@) if ($@);          $retVal->AddMessage($@) if ($@);
1347          $retVal->AddMessage("Table load failed for $relationName using $tempName.");          $retVal->AddMessage("Table load failed for $relationName using $fileName.");
1348                  Trace("Table load failed for $relationName.") if T(1);                  Trace("Table load failed for $relationName.") if T(1);
1349          } else {          } else {
1350                  # Here we successfully loaded the table. Trace the number of records loaded.          # Here we successfully loaded the table.
1351                  Trace("$retVal->{records} records read for $relationName.") if T(1);          $retVal->Add("tables");
1352            my $size = -s $fileName;
1353            Trace("$size bytes loaded into $relationName.") if T(2);
1354                  # If we're rebuilding, we need to create the table indexes.                  # If we're rebuilding, we need to create the table indexes.
1355                  if ($truncateFlag) {          if ($truncateFlag && ! $dbh->{_preIndex}) {
1356                          eval {                          eval {
1357                                  $self->CreateIndex($relationName);                                  $self->CreateIndex($relationName);
1358                          };                          };
# Line 1134  Line 1361 
1361                          }                          }
1362                  }                  }
1363          }          }
1364          # Commit the database changes.      # Analyze the table to improve performance.
1365          $dbh->commit_tran;      $dbh->vacuum_it($relationName);
         # Delete the temporary file.  
         unlink $tempName;  
1366          # Return the statistics.          # Return the statistics.
1367          return $retVal;          return $retVal;
1368  }  }
1369    
1370  =head3 GenerateEntity  =head3 GenerateEntity
1371    
1372  C<< my $fieldHash = $database->GenerateEntity($id, $type, \%values); >>  C<< my $fieldHash = $erdb->GenerateEntity($id, $type, \%values); >>
1373    
1374  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
1375  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 1202  Line 1427 
1427    
1428  =head3 GetEntity  =head3 GetEntity
1429    
1430  C<< my $entityObject = $sprout->GetEntity($entityType, $ID); >>  C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>
1431    
1432  Return an object describing the entity instance with a specified ID.  Return an object describing the entity instance with a specified ID.
1433    
# Line 1238  Line 1463 
1463    
1464  =head3 GetEntityValues  =head3 GetEntityValues
1465    
1466  C<< my @values = GetEntityValues($entityType, $ID, \@fields); >>  C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>
1467    
1468  Return a list of values from a specified entity instance.  Return a list of values from a specified entity instance.
1469    
# Line 1279  Line 1504 
1504          return @retVal;          return @retVal;
1505  }  }
1506    
1507    =head3 GetAll
1508    
1509    C<< my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>
1510    
1511    Return a list of values taken from the objects returned by a query. The first three
1512    parameters correspond to the parameters of the L</Get> method. The final parameter is
1513    a list of the fields desired from each record found by the query. The field name
1514    syntax is the standard syntax used for fields in the B<ERDB> system--
1515    B<I<objectName>(I<fieldName>)>-- where I<objectName> is the name of the relevant entity
1516    or relationship and I<fieldName> is the name of the field.
1517    
1518    The list returned will be a list of lists. Each element of the list will contain
1519    the values returned for the fields specified in the fourth parameter. If one of the
1520    fields specified returns multiple values, they are flattened in with the rest. For
1521    example, the following call will return a list of the features in a particular
1522    spreadsheet cell, and each feature will be represented by a list containing the
1523    feature ID followed by all of its aliases.
1524    
1525    C<< $query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>
1526    
1527    =over 4
1528    
1529    =item objectNames
1530    
1531    List containing the names of the entity and relationship objects to be retrieved.
1532    
1533    =item filterClause
1534    
1535    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1536    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
1537    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
1538    parameter list as additional parameters. The fields in a filter clause can come from primary
1539    entity relations, relationship relations, or secondary entity relations; however, all of the
1540    entities and relationships involved must be included in the list of object names.
1541    
1542    =item parameterList
1543    
1544    List of the parameters to be substituted in for the parameters marks in the filter clause.
1545    
1546    =item fields
1547    
1548    List of the fields to be returned in each element of the list returned.
1549    
1550    =item count
1551    
1552    Maximum number of records to return. If omitted or 0, all available records will be returned.
1553    
1554    =item RETURN
1555    
1556    Returns a list of list references. Each element of the return list contains the values for the
1557    fields specified in the B<fields> parameter.
1558    
1559    =back
1560    
1561    =cut
1562    #: Return Type @@;
1563    sub GetAll {
1564        # Get the parameters.
1565        my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
1566        # Translate the parameters from a list reference to a list. If the parameter
1567        # list is a scalar we convert it into a singleton list.
1568        my @parmList = ();
1569        if (ref $parameterList eq "ARRAY") {
1570            @parmList = @{$parameterList};
1571        } else {
1572            push @parmList, $parameterList;
1573        }
1574        # Insure the counter has a value.
1575        if (!defined $count) {
1576            $count = 0;
1577        }
1578        # Add the row limit to the filter clause.
1579        if ($count > 0) {
1580            $filterClause .= " LIMIT $count";
1581        }
1582        # Create the query.
1583        my $query = $self->Get($objectNames, $filterClause, @parmList);
1584        # Set up a counter of the number of records read.
1585        my $fetched = 0;
1586        # Loop through the records returned, extracting the fields. Note that if the
1587        # counter is non-zero, we stop when the number of records read hits the count.
1588        my @retVal = ();
1589        while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {
1590            my @rowData = $row->Values($fields);
1591            push @retVal, \@rowData;
1592            $fetched++;
1593        }
1594        # Return the resulting list.
1595        return @retVal;
1596    }
1597    
1598    =head3 EstimateRowSize
1599    
1600    C<< my $rowSize = $erdb->EstimateRowSize($relName); >>
1601    
1602    Estimate the row size of the specified relation. The estimated row size is computed by adding
1603    up the average length for each data type.
1604    
1605    =over 4
1606    
1607    =item relName
1608    
1609    Name of the relation whose estimated row size is desired.
1610    
1611    =item RETURN
1612    
1613    Returns an estimate of the row size for the specified relation.
1614    
1615    =back
1616    
1617    =cut
1618    #: Return Type $;
1619    sub EstimateRowSize {
1620        # Get the parameters.
1621        my ($self, $relName) = @_;
1622        # Declare the return variable.
1623        my $retVal = 0;
1624        # Find the relation descriptor.
1625        my $relation = $self->_FindRelation($relName);
1626        # Get the list of fields.
1627        for my $fieldData (@{$relation->{Fields}}) {
1628            # Get the field type and add its length.
1629            my $fieldLen = $TypeTable{$fieldData->{type}}->{avgLen};
1630            $retVal += $fieldLen;
1631        }
1632        # Return the result.
1633        return $retVal;
1634    }
1635    
1636  =head2 Internal Utility Methods  =head2 Internal Utility Methods
1637    
1638  =head3 GetLoadStats  =head3 GetLoadStats
# Line 1290  Line 1644 
1644  =cut  =cut
1645    
1646  sub _GetLoadStats {  sub _GetLoadStats {
1647          return Stats->new('records');      return Stats->new();
1648  }  }
1649    
1650  =head3 GenerateFields  =head3 GenerateFields
# Line 1654  Line 2008 
2008  sub _LoadMetaData {  sub _LoadMetaData {
2009          # Get the parameters.          # Get the parameters.
2010          my ($filename) = @_;          my ($filename) = @_;
2011        Trace("Reading Sprout DBD from $filename.") if T(2);
2012          # 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
2013          # get the exact structure we want.          # get the exact structure we want.
2014          my $metadata = XML::Simple::XMLin($filename,          my $metadata = XML::Simple::XMLin($filename,
# Line 1681  Line 2036 
2036          for my $entityName (keys %{$entityList}) {          for my $entityName (keys %{$entityList}) {
2037                  my $entityStructure = $entityList->{$entityName};                  my $entityStructure = $entityList->{$entityName};
2038                  #                  #
2039                  # 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,
2040                  # 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,
2041                  # 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>
2042                  # 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 1860  Line 2215 
2215                  my @fromList = ();                  my @fromList = ();
2216                  my @toList = ();                  my @toList = ();
2217                  my @bothList = ();                  my @bothList = ();
2218                  Trace("Join table build for $entityName.") if T(3);          Trace("Join table build for $entityName.") if T(metadata => 4);
2219                  for my $relationshipName (keys %{$relationshipList}) {                  for my $relationshipName (keys %{$relationshipList}) {
2220                          my $relationship = $relationshipList->{$relationshipName};                          my $relationship = $relationshipList->{$relationshipName};
2221                          # 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.
2222                          my $fromEntity = $relationship->{from};                          my $fromEntity = $relationship->{from};
2223                          my $toEntity = $relationship->{to};                          my $toEntity = $relationship->{to};
2224                          Trace("Join check for relationship $relationshipName from $fromEntity to $toEntity.") if T(3);              Trace("Join check for relationship $relationshipName from $fromEntity to $toEntity.") if T(4);
2225                          if ($fromEntity eq $entityName) {                          if ($fromEntity eq $entityName) {
2226                                  if ($toEntity eq $entityName) {                                  if ($toEntity eq $entityName) {
2227                                          # Here the relationship is recursive.                                          # Here the relationship is recursive.
2228                                          push @bothList, $relationshipName;                                          push @bothList, $relationshipName;
2229                                          Trace("Relationship $relationshipName put in both-list.") if T(3);                      Trace("Relationship $relationshipName put in both-list.") if T(metadata => 4);
2230                                  } else {                                  } else {
2231                                          # Here the relationship comes from the entity.                                          # Here the relationship comes from the entity.
2232                                          push @fromList, $relationshipName;                                          push @fromList, $relationshipName;
2233                                          Trace("Relationship $relationshipName put in from-list.") if T(3);                      Trace("Relationship $relationshipName put in from-list.") if T(metadata => 4);
2234                                  }                                  }
2235                          } elsif ($toEntity eq $entityName) {                          } elsif ($toEntity eq $entityName) {
2236                                  # Here the relationship goes to the entity.                                  # Here the relationship goes to the entity.
2237                                  push @toList, $relationshipName;                                  push @toList, $relationshipName;
2238                                  Trace("Relationship $relationshipName put in to-list.") if T(3);                  Trace("Relationship $relationshipName put in to-list.") if T(metadata => 4);
2239                          }                          }
2240                  }                  }
2241                  # 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 1896  Line 2251 
2251                                  # Create joins between the entity and this relationship.                                  # Create joins between the entity and this relationship.
2252                                  my $linkField = "$relationshipName.${linkType}_link";                                  my $linkField = "$relationshipName.${linkType}_link";
2253                                  my $joinClause = "$entityName.id = $linkField";                                  my $joinClause = "$entityName.id = $linkField";
2254                                  Trace("Entity join clause is $joinClause for $entityName and $relationshipName.") if T(4);                  Trace("Entity join clause is $joinClause for $entityName and $relationshipName.") if T(metadata => 4);
2255                                  $joinTable{"$entityName/$relationshipName"} = $joinClause;                                  $joinTable{"$entityName/$relationshipName"} = $joinClause;
2256                                  $joinTable{"$relationshipName/$entityName"} = $joinClause;                                  $joinTable{"$relationshipName/$entityName"} = $joinClause;
2257                                  # Create joins between this relationship and the other relationships.                                  # Create joins between this relationship and the other relationships.
# Line 1917  Line 2272 
2272                                                          # relationship and itself are prohibited.                                                          # relationship and itself are prohibited.
2273                                                          my $relJoinClause = "$otherName.${otherType}_link = $linkField";                                                          my $relJoinClause = "$otherName.${otherType}_link = $linkField";
2274                                                          $joinTable{$joinKey} = $relJoinClause;                                                          $joinTable{$joinKey} = $relJoinClause;
2275                                                          Trace("Relationship join clause is $relJoinClause for $joinKey.") if T(4);                              Trace("Relationship join clause is $relJoinClause for $joinKey.") if T(metadata => 4);
2276                                                  }                                                  }
2277                                          }                                          }
2278                                  }                                  }
# Line 1926  Line 2281 
2281                                  # relationship can only be ambiguous with another recursive relationship,                                  # relationship can only be ambiguous with another recursive relationship,
2282                                  # and the incoming relationship from the outer loop is never recursive.                                  # and the incoming relationship from the outer loop is never recursive.
2283                                  for my $otherName (@bothList) {                                  for my $otherName (@bothList) {
2284                                          Trace("Setting up relationship joins to recursive relationship $otherName with $relationshipName.") if T(3);                      Trace("Setting up relationship joins to recursive relationship $otherName with $relationshipName.") if T(metadata => 4);
2285                                          # Join from the left.                                          # Join from the left.
2286                                          $joinTable{"$relationshipName/$otherName"} =                                          $joinTable{"$relationshipName/$otherName"} =
2287                                                  "$linkField = $otherName.from_link";                                                  "$linkField = $otherName.from_link";
# Line 1941  Line 2296 
2296                  # 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
2297                  # possible to get the same effect using multiple queries.                  # possible to get the same effect using multiple queries.
2298                  for my $relationshipName (@bothList) {                  for my $relationshipName (@bothList) {
2299                          Trace("Setting up entity joins to recursive relationship $relationshipName with $entityName.") if T(3);              Trace("Setting up entity joins to recursive relationship $relationshipName with $entityName.") if T(metadata => 4);
2300                          # Join to the entity from each direction.                          # Join to the entity from each direction.
2301                          $joinTable{"$entityName/$relationshipName"} =                          $joinTable{"$entityName/$relationshipName"} =
2302                                  "$entityName.id = $relationshipName.from_link";                                  "$entityName.id = $relationshipName.from_link";
# Line 1992  Line 2347 
2347          # index descriptor does not exist, it will be created automatically so we can add          # index descriptor does not exist, it will be created automatically so we can add
2348          # the field to it.          # the field to it.
2349          unshift @{$newIndex->{IndexFields}}, $firstField;          unshift @{$newIndex->{IndexFields}}, $firstField;
2350        # If this is a one-to-many relationship, the "To" index is unique.
2351        if ($relationshipStructure->{arity} eq "1M" && $indexKey eq "To") {
2352            $newIndex->{Unique} = 'true';
2353        }
2354          # Add the index to the relation.          # Add the index to the relation.
2355          _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);          _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);
2356  }  }
# Line 2083  Line 2442 
2442                  # Here we have a field list. Loop through its fields.                  # Here we have a field list. Loop through its fields.
2443                  my $fieldStructures = $structure->{Fields};                  my $fieldStructures = $structure->{Fields};
2444                  for my $fieldName (keys %{$fieldStructures}) {                  for my $fieldName (keys %{$fieldStructures}) {
2445                Trace("Processing field $fieldName of $defaultRelationName.") if T(4);
2446                          my $fieldData = $fieldStructures->{$fieldName};                          my $fieldData = $fieldStructures->{$fieldName};
2447                          # Get the field type.                          # Get the field type.
2448                          my $type = $fieldData->{type};                          my $type = $fieldData->{type};

Legend:
Removed from v.1.6  
changed lines
  Added in v.1.30

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3