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

Diff of /Sprout/ERDB.pm

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

revision 1.7, Thu May 5 03:14:03 2005 UTC revision 1.38, Fri Mar 17 22:02:03 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 =>   1, 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 408  Line 632 
632          }          }
633  }  }
634    
635    =head3 VerifyFields
636    
637    C<< my $count = $erdb->VerifyFields($relName, \@fieldList); >>
638    
639    Run through the list of proposed field values, insuring that all the character fields are
640    below the maximum length. If any fields are too long, they will be truncated in place.
641    
642    =over 4
643    
644    =item relName
645    
646    Name of the relation for which the specified fields are destined.
647    
648    =item fieldList
649    
650    Reference to a list, in order, of the fields to be put into the relation.
651    
652    =item RETURN
653    
654    Returns the number of fields truncated.
655    
656    =back
657    
658    =cut
659    
660    sub VerifyFields {
661        # Get the parameters.
662        my ($self, $relName, $fieldList) = @_;
663        # Initialize the return value.
664        my $retVal = 0;
665        # Get the relation definition.
666        my $relData = $self->_FindRelation($relName);
667        # Get the list of field descriptors.
668        my $fieldTypes = $relData->{Fields};
669        my $fieldCount = scalar @{$fieldTypes};
670        # Loop through the two lists.
671        for (my $i = 0; $i < $fieldCount; $i++) {
672            # Get the type of the current field.
673            my $fieldType = $fieldTypes->[$i]->{type};
674            # If it's a character field, verify the length.
675            if ($fieldType =~ /string/) {
676                my $maxLen = $TypeTable{$fieldType}->{maxLen};
677                my $oldString = $fieldList->[$i];
678                if (length($oldString) > $maxLen) {
679                    # Here it's too big, so we truncate it.
680                    Trace("Truncating field $i in relation $relName to $maxLen characters from \"$oldString\".") if T(1);
681                    $fieldList->[$i] = substr $oldString, 0, $maxLen;
682                    $retVal++;
683                }
684            }
685        }
686        # Return the truncation count.
687        return $retVal;
688    }
689    
690  =head3 CreateIndex  =head3 CreateIndex
691    
692  C<< $database->CreateIndex($relationName); >>  C<< $erdb->CreateIndex($relationName); >>
693    
694  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
695  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.
696  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
697  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.
698    
699  =cut  =cut
700    
# Line 436  Line 715 
715                  # Get the index's uniqueness flag.                  # Get the index's uniqueness flag.
716                  my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');                  my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');
717                  # Create the index.                  # Create the index.
718                  $dbh->create_index(idx => $indexName, tbl => $relationName, flds => $flds, unique => $unique);          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
719                                        flds => $flds, unique => $unique);
720            if ($rv) {
721                  Trace("Index created: $indexName for $relationName ($flds)") if T(1);                  Trace("Index created: $indexName for $relationName ($flds)") if T(1);
722            } else {
723                Confess("Error creating index $indexName for $relationName using ($flds): " . $dbh->error_message());
724            }
725          }          }
726  }  }
727    
728  =head3 LoadTables  =head3 LoadTables
729    
730  C<< my $stats = $database->LoadTables($directoryName, $rebuild); >>  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>
731    
732  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
733  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 770 
770          $directoryName =~ s!/\\$!!;          $directoryName =~ s!/\\$!!;
771          # Declare the return variable.          # Declare the return variable.
772          my $retVal = Stats->new();          my $retVal = Stats->new();
773          # Get the metadata structure.      # Get the relation names.
774          my $metaData = $self->{_metaData};      my @relNames = $self->GetTableNames();
775          # 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}}) {  
776                          # Try to load this relation.                          # Try to load this relation.
777                          my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);                          my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);
778                          # Accumulate the statistics.                          # Accumulate the statistics.
779                          $retVal->Accumulate($result);                          $retVal->Accumulate($result);
780                  }                  }
         }  
         # 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);  
         }  
781          # Add the duration of the load to the statistical object.          # Add the duration of the load to the statistical object.
782          $retVal->Add('duration', gettimeofday - $startTime);          $retVal->Add('duration', gettimeofday - $startTime);
783          # Return the accumulated statistics.          # Return the accumulated statistics.
784          return $retVal;          return $retVal;
785  }  }
786    
787    
788  =head3 GetTableNames  =head3 GetTableNames
789    
790  C<< my @names = $database->GetTableNames; >>  C<< my @names = $erdb->GetTableNames; >>
791    
792  Return a list of the relations required to implement this database.  Return a list of the relations required to implement this database.
793    
# Line 530  Line 804 
804    
805  =head3 GetEntityTypes  =head3 GetEntityTypes
806    
807  C<< my @names = $database->GetEntityTypes; >>  C<< my @names = $erdb->GetEntityTypes; >>
808    
809  Return a list of the entity type names.  Return a list of the entity type names.
810    
# Line 545  Line 819 
819          return sort keys %{$entityList};          return sort keys %{$entityList};
820  }  }
821    
822    =head3 IsEntity
823    
824    C<< my $flag = $erdb->IsEntity($entityName); >>
825    
826    Return TRUE if the parameter is an entity name, else FALSE.
827    
828    =over 4
829    
830    =item entityName
831    
832    Object name to be tested.
833    
834    =item RETURN
835    
836    Returns TRUE if the specified string is an entity name, else FALSE.
837    
838    =back
839    
840    =cut
841    
842    sub IsEntity {
843        # Get the parameters.
844        my ($self, $entityName) = @_;
845        # Test to see if it's an entity.
846        return exists $self->{_metaData}->{Entities}->{$entityName};
847    }
848    
849  =head3 Get  =head3 Get
850    
851  C<< my $query = $database->Get(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  C<< my $query = $erdb->Get(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>
852    
853  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.
854  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 856 
856  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
857  $genus.  $genus.
858    
859  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", $genus); >>
860    
861  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
862  parameter representing the parameter value. It would also be possible to code  parameter representing the parameter value. It would also be possible to code
863    
864  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>
865    
866  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
867  characters inside the variable C<$genus>.  characters inside the variable C<$genus>.
# Line 572  Line 873 
873  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
874  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,
875    
876  C<< $query = $sprout->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", $genus); >>
877    
878  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
879  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 906 
906    
907  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
908    
909    Note that the case is important. Only an uppercase "ORDER BY" with a single space will
910    be processed. The idea is to make it less likely to find the verb by accident.
911    
912  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
913  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
914  relation.  relation.
# Line 658  Line 962 
962                          # whole.                          # whole.
963                          my $nameLength = 2 + length $objectName;                          my $nameLength = 2 + length $objectName;
964                          # Get the object's field list.                          # Get the object's field list.
965                          my $fieldList = $self->_GetFieldTable($objectName);              my $fieldList = $self->GetFieldTable($objectName);
966                          # Find the field references for this object.                          # Find the field references for this object.
967                          while ($filterString =~ m/$objectName\(([^)]*)\)/g) {                          while ($filterString =~ m/$objectName\(([^)]*)\)/g) {
968                                  # At this point, $1 contains the field name, and the current position                                  # At this point, $1 contains the field name, and the current position
# Line 713  Line 1017 
1017                                  $lastObject = $thisObject;                                  $lastObject = $thisObject;
1018                          }                          }
1019                  }                  }
1020                  # 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
1021                  # in the following variable.          # here is we want the filter clause to be empty if there's no WHERE filter.
1022            # We'll put the ORDER BY / LIMIT clauses in the following variable.
1023                  my $orderClause = "";                  my $orderClause = "";
1024                  # Locate the ORDER BY verb (if any).          # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy
1025                  if ($filterString =~ m/^(.*)ORDER BY/g) {          # operator so that we find the first occurrence of either verb.
1026                          # Here we have an ORDER BY verb. Split it off of the filter string.          if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {
1027                # Here we have an ORDER BY or LIMIT verb. Split it off of the filter string.
1028                          my $pos = pos $filterString;                          my $pos = pos $filterString;
1029                          $orderClause = substr($filterString, $pos);              $orderClause = $2 . substr($filterString, $pos);
1030                          $filterString = $1;                          $filterString = $1;
1031                  }                  }
1032                  # 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 1036 
1036                  if (@joinWhere) {                  if (@joinWhere) {
1037                          $command .= " WHERE " . join(' AND ', @joinWhere);                          $command .= " WHERE " . join(' AND ', @joinWhere);
1038                  }                  }
1039                  # Add the sort clause (if any) to the SELECT command.          # Add the sort or limit clause (if any) to the SELECT command.
1040                  if ($orderClause) {                  if ($orderClause) {
1041                          $command .= " ORDER BY $orderClause";              $command .= " $orderClause";
1042                  }                  }
1043          }          }
1044          Trace("SQL query: $command") if T(2);      Trace("SQL query: $command") if T(SQL => 4);
1045          Trace("PARMS: '" . (join "', '", @params) . "'") if (T(3) && (@params > 0));      Trace("PARMS: '" . (join "', '", @params) . "'") if (T(SQL => 4) && (@params > 0));
1046          my $sth = $dbh->prepare_command($command);          my $sth = $dbh->prepare_command($command);
1047          # Execute it with the parameters bound in.          # Execute it with the parameters bound in.
1048          $sth->execute(@params) || Confess("SELECT error" . $sth->errstr());          $sth->execute(@params) || Confess("SELECT error" . $sth->errstr());
# Line 745  Line 1051 
1051          return $retVal;          return $retVal;
1052  }  }
1053    
1054    =head3 Delete
1055    
1056    C<< my $stats = $erdb->Delete($entityName, $objectID); >>
1057    
1058    Delete an entity instance from the database. The instance is deleted along with all entity and
1059    relationship instances dependent on it. The idea of dependence here is recursive. An object is
1060    always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many
1061    relationship connected to a dependent entity or the "to" entity connected to a 1-to-many
1062    dependent relationship.
1063    
1064    =over 4
1065    
1066    =item entityName
1067    
1068    Name of the entity type for the instance being deleted.
1069    
1070    =item objectID
1071    
1072    ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),
1073    then it is presumed to by a LIKE pattern.
1074    
1075    =item testFlag
1076    
1077    If TRUE, the delete statements will be traced without being executed.
1078    
1079    =item RETURN
1080    
1081    Returns a statistics object indicating how many records of each particular table were
1082    deleted.
1083    
1084    =back
1085    
1086    =cut
1087    #: Return Type $%;
1088    sub Delete {
1089        # Get the parameters.
1090        my ($self, $entityName, $objectID, $testFlag) = @_;
1091        # Declare the return variable.
1092        my $retVal = Stats->new();
1093        # Get the DBKernel object.
1094        my $db = $self->{_dbh};
1095        # We're going to generate all the paths branching out from the starting entity. One of
1096        # the things we have to be careful about is preventing loops. We'll use a hash to
1097        # determine if we've hit a loop.
1098        my %alreadyFound = ();
1099        # These next lists will serve as our result stack. We start by pushing object lists onto
1100        # the stack, and then popping them off to do the deletes. This means the deletes will
1101        # start with the longer paths before getting to the shorter ones. That, in turn, makes
1102        # sure we don't delete records that might be needed to forge relationships back to the
1103        # original item. We have two lists-- one for TO-relationships, and one for
1104        # FROM-relationships and entities.
1105        my @fromPathList = ();
1106        my @toPathList = ();
1107        # This final hash is used to remember what work still needs to be done. We push paths
1108        # onto the list, then pop them off to extend the paths. We prime it with the starting
1109        # point. Note that we will work hard to insure that the last item on a path in the
1110        # TODO list is always an entity.
1111        my @todoList = ([$entityName]);
1112        while (@todoList) {
1113            # Get the current path.
1114            my $current = pop @todoList;
1115            # Copy it into a list.
1116            my @stackedPath = @{$current};
1117            # Pull off the last item on the path. It will always be an entity.
1118            my $entityName = pop @stackedPath;
1119            # Add it to the alreadyFound list.
1120            $alreadyFound{$entityName} = 1;
1121            # Get the entity data.
1122            my $entityData = $self->_GetStructure($entityName);
1123            # The first task is to loop through the entity's relation. A DELETE command will
1124            # be needed for each of them.
1125            my $relations = $entityData->{Relations};
1126            for my $relation (keys %{$relations}) {
1127                my @augmentedList = (@stackedPath, $relation);
1128                push @fromPathList, \@augmentedList;
1129            }
1130            # Now we need to look for relationships connected to this entity.
1131            my $relationshipList = $self->{_metaData}->{Relationships};
1132            for my $relationshipName (keys %{$relationshipList}) {
1133                my $relationship = $relationshipList->{$relationshipName};
1134                # Check the FROM field. We're only interested if it's us.
1135                if ($relationship->{from} eq $entityName) {
1136                    # Add the path to this relationship.
1137                    my @augmentedList = (@stackedPath, $entityName, $relationshipName);
1138                    push @fromPathList, \@augmentedList;
1139                    # Check the arity. If it's MM we're done. If it's 1M
1140                    # and the target hasn't been seen yet, we want to
1141                    # stack the entity for future processing.
1142                    if ($relationship->{arity} eq '1M') {
1143                        my $toEntity = $relationship->{to};
1144                        if (! exists $alreadyFound{$toEntity}) {
1145                            # Here we have a new entity that's dependent on
1146                            # the current entity, so we need to stack it.
1147                            my @stackList = (@augmentedList, $toEntity);
1148                            push @fromPathList, \@stackList;
1149                        } else {
1150                            Trace("$toEntity ignored because it occurred previously.") if T(4);
1151                        }
1152                    }
1153                }
1154                # Now check the TO field. In this case only the relationship needs
1155                # deletion.
1156                if ($relationship->{to} eq $entityName) {
1157                    my @augmentedList = (@stackedPath, $entityName, $relationshipName);
1158                    push @toPathList, \@augmentedList;
1159                }
1160            }
1161        }
1162        # Create the first qualifier for the WHERE clause. This selects the
1163        # keys of the primary entity records to be deleted. When we're deleting
1164        # from a dependent table, we construct a join page from the first qualifier
1165        # to the table containing the dependent records to delete.
1166        my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
1167        # We need to make two passes. The first is through the to-list, and
1168        # the second through the from-list. The from-list is second because
1169        # the to-list may need to pass through some of the entities the
1170        # from-list would delete.
1171        my %stackList = ( from_link => \@fromPathList, to_link => \@toPathList );
1172        # Now it's time to do the deletes. We do it in two passes.
1173        for my $keyName ('to_link', 'from_link') {
1174            # Get the list for this key.
1175            my @pathList = @{$stackList{$keyName}};
1176            Trace(scalar(@pathList) . " entries in path list for $keyName.") if T(3);
1177            # Loop through this list.
1178            while (my $path = pop @pathList) {
1179                # Get the table whose rows are to be deleted.
1180                my @pathTables = @{$path};
1181                # Start the DELETE statement. We need to call DBKernel because the
1182                # syntax of a DELETE-USING varies among DBMSs.
1183                my $target = $pathTables[$#pathTables];
1184                my $stmt = $db->SetUsing(@pathTables);
1185                # Now start the WHERE. The first thing is the ID field from the starting table. That
1186                # starting table will either be the entity relation or one of the entity's
1187                # sub-relations.
1188                $stmt .= " WHERE $pathTables[0].id $qualifier";
1189                # Now we run through the remaining entities in the path, connecting them up.
1190                for (my $i = 1; $i <= $#pathTables; $i += 2) {
1191                    # Connect the current relationship to the preceding entity.
1192                    my ($entity, $rel) = @pathTables[$i-1,$i];
1193                    # The style of connection depends on the direction of the relationship.
1194                    $stmt .= " AND $entity.id = $rel.$keyName";
1195                    if ($i + 1 <= $#pathTables) {
1196                        # Here there's a next entity, so connect that to the relationship's
1197                        # to-link.
1198                        my $entity2 = $pathTables[$i+1];
1199                        $stmt .= " AND $rel.to_link = $entity2.id";
1200                    }
1201                }
1202                # Now we have our desired DELETE statement.
1203                if ($testFlag) {
1204                    # Here the user wants to trace without executing.
1205                    Trace($stmt) if T(0);
1206                } else {
1207                    # Here we can delete. Note that the SQL method dies with a confessing
1208                    # if an error occurs, so we just go ahead and do it.
1209                    Trace("Executing delete from $target using '$objectID'.") if T(3);
1210                    my $rv = $db->SQL($stmt, 0, $objectID);
1211                    # Accumulate the statistics for this delete. The only rows deleted
1212                    # are from the target table, so we use its name to record the
1213                    # statistic.
1214                    $retVal->Add($target, $rv);
1215                }
1216            }
1217        }
1218        # Return the result.
1219        return $retVal;
1220    }
1221    
1222  =head3 GetList  =head3 GetList
1223    
1224  C<< my @dbObjects = $database->GetList(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>
1225    
1226  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
1227  specified filter clause.  specified filter clause.
# Line 810  Line 1284 
1284    
1285  =head3 ComputeObjectSentence  =head3 ComputeObjectSentence
1286    
1287  C<< my $sentence = $database->ComputeObjectSentence($objectName); >>  C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>
1288    
1289  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.
1290    
# Line 845  Line 1319 
1319    
1320  =head3 DumpRelations  =head3 DumpRelations
1321    
1322  C<< $database->DumpRelations($outputDirectory); >>  C<< $erdb->DumpRelations($outputDirectory); >>
1323    
1324  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.
1325  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 887  Line 1361 
1361    
1362  =head3 InsertObject  =head3 InsertObject
1363    
1364  C<< my $ok = $database->InsertObject($objectType, \%fieldHash); >>  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>
1365    
1366  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
1367  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 896  Line 1370 
1370  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
1371  C<ZP_00210270.1> and C<gi|46206278>.  C<ZP_00210270.1> and C<gi|46206278>.
1372    
1373  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']}); >>
1374    
1375  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
1376  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>.
1377    
1378  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'}); >>
1379    
1380  =over 4  =over 4
1381    
# Line 1026  Line 1500 
1500    
1501  =head3 LoadTable  =head3 LoadTable
1502    
1503  C<< my %results = $database->LoadTable($fileName, $relationName, $truncateFlag); >>  C<< my %results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>
1504    
1505  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
1506    first.
1507    
1508  =over 4  =over 4
1509    
# Line 1046  Line 1521 
1521    
1522  =item RETURN  =item RETURN
1523    
1524  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.
1525    
1526  =back  =back
1527    
# Line 1057  Line 1532 
1532          # Create the statistical return object.          # Create the statistical return object.
1533          my $retVal = _GetLoadStats();          my $retVal = _GetLoadStats();
1534          # Trace the fact of the load.          # Trace the fact of the load.
1535          Trace("Loading table $relationName from $fileName") if T(1);      Trace("Loading table $relationName from $fileName") if T(2);
1536          # Get the database handle.          # Get the database handle.
1537          my $dbh = $self->{_dbh};          my $dbh = $self->{_dbh};
1538        # Get the input file size.
1539        my $fileSize = -s $fileName;
1540          # Get the relation data.          # Get the relation data.
1541          my $relation = $self->_FindRelation($relationName);          my $relation = $self->_FindRelation($relationName);
1542          # Check the truncation flag.          # Check the truncation flag.
1543          if ($truncateFlag) {          if ($truncateFlag) {
1544                  Trace("Creating table $relationName") if T(1);          Trace("Creating table $relationName") if T(2);
1545            # Compute the row count estimate. We take the size of the load file,
1546            # divide it by the estimated row size, and then multiply by 1.5 to
1547            # leave extra room. We postulate a minimum row count of 1000 to
1548            # prevent problems with incoming empty load files.
1549            my $rowSize = $self->EstimateRowSize($relationName);
1550            my $estimate = FIG::max($fileSize * 1.5 / $rowSize, 1000);
1551                  # Re-create the table without its index.                  # Re-create the table without its index.
1552                  $self->CreateTable($relationName, 0);          $self->CreateTable($relationName, 0, $estimate);
1553            # If this is a pre-index DBMS, create the index here.
1554            if ($dbh->{_preIndex}) {
1555                eval {
1556                    $self->CreateIndex($relationName);
1557                };
1558                if ($@) {
1559                    $retVal->AddMessage($@);
1560                }
1561            }
1562          }          }
         # 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);  
1563      # Load the table.      # Load the table.
1564          my $rv;          my $rv;
1565          eval {          eval {
1566                  $rv = $dbh->load_table(file => $tempName, tbl => $relationName);          $rv = $dbh->load_table(file => $fileName, tbl => $relationName);
1567          };          };
1568          if (!defined $rv) {          if (!defined $rv) {
1569          $retVal->AddMessage($@) if ($@);          $retVal->AddMessage($@) if ($@);
1570          $retVal->AddMessage("Table load failed for $relationName using $tempName.");          $retVal->AddMessage("Table load failed for $relationName using $fileName.");
1571                  Trace("Table load failed for $relationName.") if T(1);                  Trace("Table load failed for $relationName.") if T(1);
1572          } else {          } else {
1573                  # Here we successfully loaded the table. Trace the number of records loaded.          # Here we successfully loaded the table.
1574                  Trace("$retVal->{records} records read for $relationName.") if T(1);          $retVal->Add("tables");
1575            my $size = -s $fileName;
1576            Trace("$size bytes loaded into $relationName.") if T(2);
1577                  # If we're rebuilding, we need to create the table indexes.                  # If we're rebuilding, we need to create the table indexes.
1578                  if ($truncateFlag) {          if ($truncateFlag && ! $dbh->{_preIndex}) {
1579                          eval {                          eval {
1580                                  $self->CreateIndex($relationName);                                  $self->CreateIndex($relationName);
1581                          };                          };
# Line 1132  Line 1584 
1584                          }                          }
1585                  }                  }
1586          }          }
1587          # Commit the database changes.      # Analyze the table to improve performance.
1588          $dbh->commit_tran;      $dbh->vacuum_it($relationName);
         # Delete the temporary file.  
         unlink $tempName;  
1589          # Return the statistics.          # Return the statistics.
1590          return $retVal;          return $retVal;
1591  }  }
1592    
1593  =head3 GenerateEntity  =head3 GenerateEntity
1594    
1595  C<< my $fieldHash = $database->GenerateEntity($id, $type, \%values); >>  C<< my $fieldHash = $erdb->GenerateEntity($id, $type, \%values); >>
1596    
1597  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
1598  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 1200  Line 1650 
1650    
1651  =head3 GetEntity  =head3 GetEntity
1652    
1653  C<< my $entityObject = $sprout->GetEntity($entityType, $ID); >>  C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>
1654    
1655  Return an object describing the entity instance with a specified ID.  Return an object describing the entity instance with a specified ID.
1656    
# Line 1236  Line 1686 
1686    
1687  =head3 GetEntityValues  =head3 GetEntityValues
1688    
1689  C<< my @values = GetEntityValues($entityType, $ID, \@fields); >>  C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>
1690    
1691  Return a list of values from a specified entity instance.  Return a list of values from a specified entity instance.
1692    
# Line 1279  Line 1729 
1729    
1730  =head3 GetAll  =head3 GetAll
1731    
1732  C<< my @list = $sprout->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>  C<< my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>
1733    
1734  Return a list of values taken from the objects returned by a query. The first three  Return a list of values taken from the objects returned by a query. The first three
1735  parameters correspond to the parameters of the L</Get> method. The final parameter is  parameters correspond to the parameters of the L</Get> method. The final parameter is
# Line 1295  Line 1745 
1745  spreadsheet cell, and each feature will be represented by a list containing the  spreadsheet cell, and each feature will be represented by a list containing the
1746  feature ID followed by all of its aliases.  feature ID followed by all of its aliases.
1747    
1748  C<< $query = $sprout->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>  C<< $query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>
1749    
1750  =over 4  =over 4
1751    
# Line 1344  Line 1794 
1794          } else {          } else {
1795                  push @parmList, $parameterList;                  push @parmList, $parameterList;
1796          }          }
         # Create the query.  
         my $query = $self->Get($objectNames, $filterClause, @parmList);  
         # Set up a counter of the number of records read.  
         my $fetched = 0;  
1797          # Insure the counter has a value.          # Insure the counter has a value.
1798          if (!defined $count) {          if (!defined $count) {
1799                  $count = 0;                  $count = 0;
1800          }          }
1801        # Add the row limit to the filter clause.
1802        if ($count > 0) {
1803            $filterClause .= " LIMIT $count";
1804        }
1805        # Create the query.
1806        my $query = $self->Get($objectNames, $filterClause, @parmList);
1807        # Set up a counter of the number of records read.
1808        my $fetched = 0;
1809          # Loop through the records returned, extracting the fields. Note that if the          # Loop through the records returned, extracting the fields. Note that if the
1810          # counter is non-zero, we stop when the number of records read hits the count.          # counter is non-zero, we stop when the number of records read hits the count.
1811          my @retVal = ();          my @retVal = ();
# Line 1364  Line 1818 
1818          return @retVal;          return @retVal;
1819  }  }
1820    
1821    =head3 EstimateRowSize
1822    
1823    C<< my $rowSize = $erdb->EstimateRowSize($relName); >>
1824    
1825    Estimate the row size of the specified relation. The estimated row size is computed by adding
1826    up the average length for each data type.
1827    
1828    =over 4
1829    
1830    =item relName
1831    
1832    Name of the relation whose estimated row size is desired.
1833    
1834    =item RETURN
1835    
1836    Returns an estimate of the row size for the specified relation.
1837    
1838    =back
1839    
1840    =cut
1841    #: Return Type $;
1842    sub EstimateRowSize {
1843        # Get the parameters.
1844        my ($self, $relName) = @_;
1845        # Declare the return variable.
1846        my $retVal = 0;
1847        # Find the relation descriptor.
1848        my $relation = $self->_FindRelation($relName);
1849        # Get the list of fields.
1850        for my $fieldData (@{$relation->{Fields}}) {
1851            # Get the field type and add its length.
1852            my $fieldLen = $TypeTable{$fieldData->{type}}->{avgLen};
1853            $retVal += $fieldLen;
1854        }
1855        # Return the result.
1856        return $retVal;
1857    }
1858    
1859    =head3 GetFieldTable
1860    
1861    C<< my $fieldHash = $self->GetFieldTable($objectnName); >>
1862    
1863    Get the field structure for a specified entity or relationship.
1864    
1865    =over 4
1866    
1867    =item objectName
1868    
1869    Name of the desired entity or relationship.
1870    
1871    =item RETURN
1872    
1873    The table containing the field descriptors for the specified object.
1874    
1875    =back
1876    
1877    =cut
1878    
1879    sub GetFieldTable {
1880        # Get the parameters.
1881        my ($self, $objectName) = @_;
1882        # Get the descriptor from the metadata.
1883        my $objectData = $self->_GetStructure($objectName);
1884        # Return the object's field table.
1885        return $objectData->{Fields};
1886    }
1887    
1888    =head3 GetUsefulCrossValues
1889    
1890    C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>
1891    
1892    Return a list of the useful attributes that would be returned by a B<Cross> call
1893    from an entity of the source entity type through the specified relationship. This
1894    means it will return the fields of the target entity type and the intersection data
1895    fields in the relationship. Only primary table fields are returned. In other words,
1896    the field names returned will be for fields where there is always one and only one
1897    value.
1898    
1899    =over 4
1900    
1901    =item sourceEntity
1902    
1903    Name of the entity from which the relationship crossing will start.
1904    
1905    =item relationship
1906    
1907    Name of the relationship being crossed.
1908    
1909    =item RETURN
1910    
1911    Returns a list of field names in Sprout field format (I<objectName>C<(>I<fieldName>C<)>.
1912    
1913    =back
1914    
1915    =cut
1916    #: Return Type @;
1917    sub GetUsefulCrossValues {
1918        # Get the parameters.
1919        my ($self, $sourceEntity, $relationship) = @_;
1920        # Declare the return variable.
1921        my @retVal = ();
1922        # Determine the target entity for the relationship. This is whichever entity is not
1923        # the source entity. So, if the source entity is the FROM, we'll get the name of
1924        # the TO, and vice versa.
1925        my $relStructure = $self->_GetStructure($relationship);
1926        my $targetEntityType = ($relStructure->{from} eq $sourceEntity ? "to" : "from");
1927        my $targetEntity = $relStructure->{$targetEntityType};
1928        # Get the field table for the entity.
1929        my $entityFields = $self->GetFieldTable($targetEntity);
1930        # The field table is a hash. The hash key is the field name. The hash value is a structure.
1931        # For the entity fields, the key aspect of the target structure is that the {relation} value
1932        # must match the entity name.
1933        my @fieldList = map { "$targetEntity($_)" } grep { $entityFields->{$_}->{relation} eq $targetEntity }
1934                            keys %{$entityFields};
1935        # Push the fields found onto the return variable.
1936        push @retVal, sort @fieldList;
1937        # Get the field table for the relationship.
1938        my $relationshipFields = $self->GetFieldTable($relationship);
1939        # Here we have a different rule. We want all the fields other than "from-link" and "to-link".
1940        # This may end up being an empty set.
1941        my @fieldList2 = map { "$relationship($_)" } grep { $_ ne "from-link" && $_ ne "to-link" }
1942                            keys %{$relationshipFields};
1943        # Push these onto the return list.
1944        push @retVal, sort @fieldList2;
1945        # Return the result.
1946        return @retVal;
1947    }
1948    
1949  =head2 Internal Utility Methods  =head2 Internal Utility Methods
1950    
1951  =head3 GetLoadStats  =head3 GetLoadStats
# Line 1375  Line 1957 
1957  =cut  =cut
1958    
1959  sub _GetLoadStats {  sub _GetLoadStats {
1960          return Stats->new('records');      return Stats->new();
1961  }  }
1962    
1963  =head3 GenerateFields  =head3 GenerateFields
# Line 1570  Line 2152 
2152          return $objectData->{Relations};          return $objectData->{Relations};
2153  }  }
2154    
 =head3 GetFieldTable  
   
 Get the field structure for a specified entity or relationship.  
   
 This is an instance method.  
   
 =over 4  
   
 =item objectName  
   
 Name of the desired entity or relationship.  
   
 =item RETURN  
   
 The table containing the field descriptors for the specified object.  
   
 =back  
   
 =cut  
   
 sub _GetFieldTable {  
         # Get the parameters.  
         my ($self, $objectName) = @_;  
         # Get the descriptor from the metadata.  
         my $objectData = $self->_GetStructure($objectName);  
         # Return the object's field table.  
         return $objectData->{Fields};  
 }  
   
2155  =head3 ValidateFieldNames  =head3 ValidateFieldNames
2156    
2157  Determine whether or not the field names are valid. A description of the problems with the names  Determine whether or not the field names are valid. A description of the problems with the names
# Line 1739  Line 2292 
2292  sub _LoadMetaData {  sub _LoadMetaData {
2293          # Get the parameters.          # Get the parameters.
2294          my ($filename) = @_;          my ($filename) = @_;
2295        Trace("Reading Sprout DBD from $filename.") if T(2);
2296          # 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
2297          # get the exact structure we want.          # get the exact structure we want.
2298          my $metadata = XML::Simple::XMLin($filename,          my $metadata = XML::Simple::XMLin($filename,
# Line 1766  Line 2320 
2320          for my $entityName (keys %{$entityList}) {          for my $entityName (keys %{$entityList}) {
2321                  my $entityStructure = $entityList->{$entityName};                  my $entityStructure = $entityList->{$entityName};
2322                  #                  #
2323                  # 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,
2324                  # 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,
2325                  # 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>
2326                  # 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 1945  Line 2499 
2499                  my @fromList = ();                  my @fromList = ();
2500                  my @toList = ();                  my @toList = ();
2501                  my @bothList = ();                  my @bothList = ();
2502                  Trace("Join table build for $entityName.") if T(3);          Trace("Join table build for $entityName.") if T(metadata => 4);
2503                  for my $relationshipName (keys %{$relationshipList}) {                  for my $relationshipName (keys %{$relationshipList}) {
2504                          my $relationship = $relationshipList->{$relationshipName};                          my $relationship = $relationshipList->{$relationshipName};
2505                          # 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.
2506                          my $fromEntity = $relationship->{from};                          my $fromEntity = $relationship->{from};
2507                          my $toEntity = $relationship->{to};                          my $toEntity = $relationship->{to};
2508                          Trace("Join check for relationship $relationshipName from $fromEntity to $toEntity.") if T(3);              Trace("Join check for relationship $relationshipName from $fromEntity to $toEntity.") if T(4);
2509                          if ($fromEntity eq $entityName) {                          if ($fromEntity eq $entityName) {
2510                                  if ($toEntity eq $entityName) {                                  if ($toEntity eq $entityName) {
2511                                          # Here the relationship is recursive.                                          # Here the relationship is recursive.
2512                                          push @bothList, $relationshipName;                                          push @bothList, $relationshipName;
2513                                          Trace("Relationship $relationshipName put in both-list.") if T(3);                      Trace("Relationship $relationshipName put in both-list.") if T(metadata => 4);
2514                                  } else {                                  } else {
2515                                          # Here the relationship comes from the entity.                                          # Here the relationship comes from the entity.
2516                                          push @fromList, $relationshipName;                                          push @fromList, $relationshipName;
2517                                          Trace("Relationship $relationshipName put in from-list.") if T(3);                      Trace("Relationship $relationshipName put in from-list.") if T(metadata => 4);
2518                                  }                                  }
2519                          } elsif ($toEntity eq $entityName) {                          } elsif ($toEntity eq $entityName) {
2520                                  # Here the relationship goes to the entity.                                  # Here the relationship goes to the entity.
2521                                  push @toList, $relationshipName;                                  push @toList, $relationshipName;
2522                                  Trace("Relationship $relationshipName put in to-list.") if T(3);                  Trace("Relationship $relationshipName put in to-list.") if T(metadata => 4);
2523                          }                          }
2524                  }                  }
2525                  # 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 1981  Line 2535 
2535                                  # Create joins between the entity and this relationship.                                  # Create joins between the entity and this relationship.
2536                                  my $linkField = "$relationshipName.${linkType}_link";                                  my $linkField = "$relationshipName.${linkType}_link";
2537                                  my $joinClause = "$entityName.id = $linkField";                                  my $joinClause = "$entityName.id = $linkField";
2538                                  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);
2539                                  $joinTable{"$entityName/$relationshipName"} = $joinClause;                                  $joinTable{"$entityName/$relationshipName"} = $joinClause;
2540                                  $joinTable{"$relationshipName/$entityName"} = $joinClause;                                  $joinTable{"$relationshipName/$entityName"} = $joinClause;
2541                                  # Create joins between this relationship and the other relationships.                                  # Create joins between this relationship and the other relationships.
# Line 2002  Line 2556 
2556                                                          # relationship and itself are prohibited.                                                          # relationship and itself are prohibited.
2557                                                          my $relJoinClause = "$otherName.${otherType}_link = $linkField";                                                          my $relJoinClause = "$otherName.${otherType}_link = $linkField";
2558                                                          $joinTable{$joinKey} = $relJoinClause;                                                          $joinTable{$joinKey} = $relJoinClause;
2559                                                          Trace("Relationship join clause is $relJoinClause for $joinKey.") if T(4);                              Trace("Relationship join clause is $relJoinClause for $joinKey.") if T(metadata => 4);
2560                                                  }                                                  }
2561                                          }                                          }
2562                                  }                                  }
# Line 2011  Line 2565 
2565                                  # relationship can only be ambiguous with another recursive relationship,                                  # relationship can only be ambiguous with another recursive relationship,
2566                                  # and the incoming relationship from the outer loop is never recursive.                                  # and the incoming relationship from the outer loop is never recursive.
2567                                  for my $otherName (@bothList) {                                  for my $otherName (@bothList) {
2568                                          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);
2569                                          # Join from the left.                                          # Join from the left.
2570                                          $joinTable{"$relationshipName/$otherName"} =                                          $joinTable{"$relationshipName/$otherName"} =
2571                                                  "$linkField = $otherName.from_link";                                                  "$linkField = $otherName.from_link";
# Line 2026  Line 2580 
2580                  # 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
2581                  # possible to get the same effect using multiple queries.                  # possible to get the same effect using multiple queries.
2582                  for my $relationshipName (@bothList) {                  for my $relationshipName (@bothList) {
2583                          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);
2584                          # Join to the entity from each direction.                          # Join to the entity from each direction.
2585                          $joinTable{"$entityName/$relationshipName"} =                          $joinTable{"$entityName/$relationshipName"} =
2586                                  "$entityName.id = $relationshipName.from_link";                                  "$entityName.id = $relationshipName.from_link";
# Line 2077  Line 2631 
2631          # index descriptor does not exist, it will be created automatically so we can add          # index descriptor does not exist, it will be created automatically so we can add
2632          # the field to it.          # the field to it.
2633          unshift @{$newIndex->{IndexFields}}, $firstField;          unshift @{$newIndex->{IndexFields}}, $firstField;
2634        # If this is a one-to-many relationship, the "To" index is unique.
2635        if ($relationshipStructure->{arity} eq "1M" && $indexKey eq "To") {
2636            $newIndex->{Unique} = 'true';
2637        }
2638          # Add the index to the relation.          # Add the index to the relation.
2639          _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);          _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);
2640  }  }
# Line 2168  Line 2726 
2726                  # Here we have a field list. Loop through its fields.                  # Here we have a field list. Loop through its fields.
2727                  my $fieldStructures = $structure->{Fields};                  my $fieldStructures = $structure->{Fields};
2728                  for my $fieldName (keys %{$fieldStructures}) {                  for my $fieldName (keys %{$fieldStructures}) {
2729                Trace("Processing field $fieldName of $defaultRelationName.") if T(4);
2730                          my $fieldData = $fieldStructures->{$fieldName};                          my $fieldData = $fieldStructures->{$fieldName};
2731                          # Get the field type.                          # Get the field type.
2732                          my $type = $fieldData->{type};                          my $type = $fieldData->{type};

Legend:
Removed from v.1.7  
changed lines
  Added in v.1.38

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3