[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 1.55, Sat Jun 24 23:49:10 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 Digest::MD5 qw(md5_base64);
13        use FIG;
14    
15  =head1 Entity-Relationship Database Package  =head1 Entity-Relationship Database Package
16    
# Line 32  Line 34 
34  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>).
35  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
36  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
37  (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
38  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
39  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
40    C<FeatureVirulence>.
41    
42  Entities are connected by binary relationships implemented using single relations possessing the  Entities are connected by binary relationships implemented using single relations possessing the
43  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 72 
72  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
73  fully implemented.  fully implemented.
74    
75    =head2 XML Database Description
76    
77    =head3 Data Types
78    
79    The ERDB system supports the following data types. Note that there are numerous string
80    types depending on the maximum length. Some database packages limit the total number of
81    characters you have in an index key; to insure the database works in all environments,
82    the type of string should be the shortest one possible that supports all the known values.
83    
84    =over 4
85    
86    =item char
87    
88    single ASCII character
89    
90    =item int
91    
92    32-bit signed integer
93    
94    =item date
95    
96    64-bit unsigned integer, representing a PERL date/time value
97    
98    =item text
99    
100    long string; Text fields cannot be used in indexes or sorting and do not support the
101    normal syntax of filter clauses, but can be up to a billion character in length
102    
103    =item float
104    
105    double-precision floating-point number
106    
107    =item boolean
108    
109    single-bit numeric value; The value is stored as a 16-bit signed integer (for
110    compatability with certain database packages), but the only values supported are
111    0 and 1.
112    
113    =item id-string
114    
115    variable-length string, maximum 25 characters
116    
117    =item key-string
118    
119    variable-length string, maximum 40 characters
120    
121    =item name-string
122    
123    variable-length string, maximum 80 characters
124    
125    =item medium-string
126    
127    variable-length string, maximum 160 characters
128    
129    =item string
130    
131    variable-length string, maximum 255 characters
132    
133    =item hash-string
134    
135    variable-length string, maximum 22 characters
136    
137    =back
138    
139    The hash-string data type has a special meaning. The actual key passed into the loader will
140    be a string, but it will be digested into a 22-character MD5 code to save space. Although the
141    MD5 algorithm is not perfect, it is extremely unlikely two strings will have the same
142    digest. Therefore, it is presumed the keys will be unique. When the database is actually
143    in use, the hashed keys will be presented rather than the original values. For this reason,
144    they should not be used for entities where the key is meaningful.
145    
146    =head3 Global Tags
147    
148    The entire database definition must be inside a B<Database> tag. The display name of
149    the database is given by the text associated with the B<Title> tag. The display name
150    is only used in the automated documentation. It has no other effect. The entities and
151    relationships are listed inside the B<Entities> and B<Relationships> tags,
152    respectively. None of these tags have attributes.
153    
154        <Database>
155            <Title>... display title here...</Title>
156            <Entities>
157                ... entity definitions here ...
158            </Entities>
159            <Relationships>
160                ... relationship definitions here...
161            </Relationships>
162        </Database>
163    
164    Entities, relationships, indexes, and fields all allow a text tag called B<Notes>.
165    The text inside the B<Notes> tag contains comments that will appear when the database
166    documentation is generated. Within a B<Notes> tag, you may use C<[i]> and C<[/i]> for
167    italics, C<[b]> and C<[/b]> for bold, and C<[p]> for a new paragraph.
168    
169    =head3 Fields
170    
171    Both entities and relationships have fields described by B<Field> tags. A B<Field>
172    tag can have B<Notes> associated with it. The complete set of B<Field> tags for an
173    object mus be inside B<Fields> tags.
174    
175        <Entity ... >
176            <Fields>
177                ... Field tags ...
178            </Fields>
179        </Entity>
180    
181    The attributes for the B<Field> tag are as follows.
182    
183    =over 4
184    
185    =item name
186    
187    Name of the field. The field name should contain only letters, digits, and hyphens (C<->),
188    and the first character should be a letter. Most underlying databases are case-insensitive
189    with the respect to field names, so a best practice is to use lower-case letters only.
190    
191    =item type
192    
193    Data type of the field. The legal data types are given above.
194    
195    =item relation
196    
197    Name of the relation containing the field. This should only be specified for entity
198    fields. The ERDB system does not support optional fields or multi-occurring fields
199    in the primary relation of an entity. Instead, they are put into secondary relations.
200    So, for example, in the C<Genome> entity, the C<group-name> field indicates a special
201    grouping used to select a subset of the genomes. A given genome may not be in any
202    groups or may be in multiple groups. Therefore, C<group-name> specifies a relation
203    value. The relation name specified must be a valid table name. By convention, it is
204    usually the entity name followed by a qualifying word (e.g. C<GenomeGroup>). In an
205    entity, the fields without a relation attribute are said to belong to the
206    I<primary relation>. This relation has the same name as the entity itself.
207    
208    =back
209    
210    =head3 Indexes
211    
212    An entity can have multiple alternate indexes associated with it. The fields must
213    be from the primary relation. The alternate indexes assist in ordering results
214    from a query. A relationship can have up to two indexes-- a I<to-index> and a
215    I<from-index>. These order the results when crossing the relationship. For
216    example, in the relationship C<HasContig> from C<Genome> to C<Contig>, the
217    from-index would order the contigs of a ganome, and the to-index would order
218    the genomes of a contig. A relationship's index must specify only fields in
219    the relationship.
220    
221    The indexes for an entity must be listed inside the B<Indexes> tag. The from-index
222    of a relationship is specified using the B<FromIndex> tag; the to-index is specified
223    using the B<ToIndex> tag.
224    
225    Each index can contain a B<Notes> tag. In addition, it will have an B<IndexFields>
226    tag containing the B<IndexField> tags. These specify, in order, the fields used in
227    the index. The attributes of an B<IndexField> tag are as follows.
228    
229    =over 4
230    
231    =item name
232    
233    Name of the field.
234    
235    =item order
236    
237    Sort order of the field-- C<ascending> or C<descending>.
238    
239    =back
240    
241    The B<Index>, B<FromIndex>, and B<ToIndex> tags themselves have no attributes.
242    
243    =head3 Object and Field Names
244    
245    By convention entity and relationship names use capital casing (e.g. C<Genome> or
246    C<HasRegionsIn>. Most underlying databases, however, are aggressively case-insensitive
247    with respect to relation names, converting them internally to all-upper case or
248    all-lower case.
249    
250    If syntax or parsing errors occur when you try to load or use an ERDB database, the
251    most likely reason is that one of your objects has an SQL reserved word as its name.
252    The list of SQL reserved words keeps increasing; however, most are unlikely to show
253    up as a noun or declarative verb phrase. The exceptions are C<Group>, C<User>,
254    C<Table>, C<Index>, C<Object>, C<Date>, C<Number>, C<Update>, C<Time>, C<Percent>,
255    C<Memo>, C<Order>, and C<Sum>. This problem can crop up in field names as well.
256    
257    Every entity has a field called C<id> that acts as its primary key. Every relationship
258    has fields called C<from-link> and C<to-link> that contain copies of the relevant
259    entity IDs. These are essentially ERDB's reserved words, and should not be used
260    for user-defined field names.
261    
262    =head3 Entities
263    
264    An entity is described by the B<Entity> tag. The entity can contain B<Notes>, an
265    B<Indexes> tag containing one or more secondary indexes, and a B<Fields> tag
266    containing one or more fields. The attributes of the B<Entity> tag are as follows.
267    
268    =over 4
269    
270    =item name
271    
272    Name of the entity. The entity name, by convention, uses capital casing (e.g. C<Genome>
273    or C<GroupBlock>) and should be a noun or noun phrase.
274    
275    =item keyType
276    
277    Data type of the primary key. The primary key is always named C<id>.
278    
279    =back
280    
281    =head3 Relationships
282    
283    A relationship is described by the C<Relationship> tag. Within a relationship,
284    there can be a C<Notes> tag, a C<Fields> tag containing the intersection data
285    fields, a C<FromIndex> tag containing the from-index, and a C<ToIndex> tag containing
286    the to-index.
287    
288    The C<Relationship> tag has the following attributes.
289    
290    =over 4
291    
292    =item name
293    
294    Name of the relationship. The relationship name, by convention, uses capital casing
295    (e.g. C<ContainsRegionIn> or C<HasContig>), and should be a declarative verb
296    phrase, designed to fit between the from-entity and the to-entity (e.g.
297    Block C<ContainsRegionIn> Genome).
298    
299    =item from
300    
301    Name of the entity from which the relationship starts.
302    
303    =item to
304    
305    Name of the entity to which the relationship proceeds.
306    
307    =item arity
308    
309    Relationship type: C<1M> for one-to-many and C<MM> for many-to-many.
310    
311    =back
312    
313  =cut  =cut
314    
315  # GLOBALS  # GLOBALS
# Line 76  Line 317 
317  # 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.
318  # "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
319  # 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
320   #string is specified in the field definition.  # string is specified in the field definition. "avgLen" is the average byte length for estimating
321  my %TypeTable = ( char =>        { sqlType => 'CHAR(1)',                        maxLen => 1,                    dataGen => "StringGen('A')" },  # record sizes.
322                                    int =>         { sqlType => 'INTEGER',                        maxLen => 20,                   dataGen => "IntGen(0, 99999999)" },  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, dataGen => "StringGen('A')" },
323                                    string =>  { sqlType => 'VARCHAR(255)',               maxLen => 255,                  dataGen => "StringGen(IntGen(10,250))" },                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, dataGen => "IntGen(0, 99999999)" },
324                                    text =>        { sqlType => 'TEXT',                           maxLen => 1000000000,   dataGen => "StringGen(IntGen(80,1000))" },                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, dataGen => "StringGen(IntGen(10,250))" },
325                                    date =>        { sqlType => 'BIGINT',                         maxLen => 80,                   dataGen => "DateGen(-7, 7, IntGen(0,1400))" },                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, dataGen => "StringGen(IntGen(80,1000))" },
326                                    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))" },
327                                    boolean => { sqlType => 'SMALLINT',                   maxLen => 1,                    dataGen => "IntGen(0, 1)" },                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, dataGen => "FloatGen(0.0, 100.0)" },
328                      boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, dataGen => "IntGen(0, 1)" },
329                     'hash-string' =>
330                                 { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, dataGen => "SringGen(22)" },
331                     'id-string' =>
332                                 { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, dataGen => "SringGen(22)" },
333                               'key-string' =>                               'key-string' =>
334                                                           { sqlType => 'VARCHAR(40)',            maxLen => 40,                   dataGen => "StringGen(IntGen(10,40))" },                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, dataGen => "StringGen(IntGen(10,40))" },
335                                   'name-string' =>                                   'name-string' =>
336                                                           { sqlType => 'VARCHAR(80)',            maxLen => 80,                   dataGen => "StringGen(IntGen(10,80))" },                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, dataGen => "StringGen(IntGen(10,80))" },
337                                   'medium-string' =>                                   'medium-string' =>
338                                                           { sqlType => 'VARCHAR(160)',           maxLen => 160,                  dataGen => "StringGen(IntGen(10,160))" },                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, dataGen => "StringGen(IntGen(10,160))" },
339                                  );                                  );
340    
341  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 145  Line 391 
391    
392  =head3 ShowMetaData  =head3 ShowMetaData
393    
394  C<< $database->ShowMetaData($fileName); >>  C<< $erdb->ShowMetaData($fileName); >>
395    
396  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
397  the data to be loaded into the relations.  the data to be loaded into the relations.
# Line 176  Line 422 
422          # Write the HTML heading stuff.          # Write the HTML heading stuff.
423          print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";          print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";
424          print HTMLOUT "</head>\n<body>\n";          print HTMLOUT "</head>\n<body>\n";
425        # Write the documentation.
426        print HTMLOUT $self->DisplayMetaData();
427        # Close the document.
428        print HTMLOUT "</body>\n</html>\n";
429        # Close the file.
430        close HTMLOUT;
431    }
432    
433    =head3 DisplayMetaData
434    
435    C<< my $html = $erdb->DisplayMetaData(); >>
436    
437    Return an HTML description of the database. This description can be used to help users create
438    the data to be loaded into the relations and form queries. The output is raw includable HTML
439    without any HEAD or BODY tags.
440    
441    =over 4
442    
443    =item filename
444    
445    The name of the output file.
446    
447    =back
448    
449    =cut
450    
451    sub DisplayMetaData {
452        # Get the parameters.
453        my ($self) = @_;
454        # Get the metadata and the title string.
455        my $metadata = $self->{_metaData};
456        # Get the title string.
457        my $title = $metadata->{Title};
458        # Get the entity and relationship lists.
459        my $entityList = $metadata->{Entities};
460        my $relationshipList = $metadata->{Relationships};
461        # Declare the return variable.
462        my $retVal = "";
463        # Open the output file.
464        Trace("Building MetaData table of contents.") if T(4);
465          # Here we do the table of contents. It starts as an unordered list of section names. Each          # Here we do the table of contents. It starts as an unordered list of section names. Each
466          # section contains an ordered list of entity or relationship subsections.          # section contains an ordered list of entity or relationship subsections.
467          print HTMLOUT "<ul>\n<li><a href=\"#EntitiesSection\">Entities</a>\n<ol>\n";      $retVal .= "<ul>\n<li><a href=\"#EntitiesSection\">Entities</a>\n<ol>\n";
468          # Loop through the Entities, displaying a list item for each.          # Loop through the Entities, displaying a list item for each.
469          foreach my $key (sort keys %{$entityList}) {          foreach my $key (sort keys %{$entityList}) {
470                  # Display this item.                  # Display this item.
471                  print HTMLOUT "<li><a href=\"#$key\">$key</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$key</a></li>\n";
472          }          }
473          # Close off the entity section and start the relationship section.          # Close off the entity section and start the relationship section.
474          print HTMLOUT "</ol></li>\n<li><a href=\"#RelationshipsSection\">Relationships</a>\n<ol>\n";      $retVal .= "</ol></li>\n<li><a href=\"#RelationshipsSection\">Relationships</a>\n<ol>\n";
475          # Loop through the Relationships.          # Loop through the Relationships.
476          foreach my $key (sort keys %{$relationshipList}) {          foreach my $key (sort keys %{$relationshipList}) {
477                  # Display this item.                  # Display this item.
478                  my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});                  my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});
479                  print HTMLOUT "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";
480          }          }
481          # Close off the relationship section and list the join table section.          # Close off the relationship section and list the join table section.
482          print HTMLOUT "</ol></li>\n<li><a href=\"#JoinTable\">Join Table</a></li>\n";      $retVal .= "</ol></li>\n<li><a href=\"#JoinTable\">Join Table</a></li>\n";
483          # Close off the table of contents itself.          # Close off the table of contents itself.
484          print HTMLOUT "</ul>\n";      $retVal .=  "</ul>\n";
485          # Now we start with the actual data. Denote we're starting the entity section.          # Now we start with the actual data. Denote we're starting the entity section.
486          print HTMLOUT "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";      $retVal .= "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";
487          # Loop through the entities.          # Loop through the entities.
488          for my $key (sort keys %{$entityList}) {          for my $key (sort keys %{$entityList}) {
489                  Trace("Building MetaData entry for $key entity.") if T(4);                  Trace("Building MetaData entry for $key entity.") if T(4);
490                  # Create the entity header. It contains a bookmark and the entity name.                  # Create the entity header. It contains a bookmark and the entity name.
491                  print HTMLOUT "<a name=\"$key\"></a><h3>$key</h3>\n";          $retVal .= "<a name=\"$key\"></a><h3>$key</h3>\n";
492                  # Get the entity data.                  # Get the entity data.
493                  my $entityData = $entityList->{$key};                  my $entityData = $entityList->{$key};
494                  # If there's descriptive text, display it.                  # If there's descriptive text, display it.
495                  if (my $notes = $entityData->{Notes}) {                  if (my $notes = $entityData->{Notes}) {
496                          print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";
497                  }                  }
498                  # Now we want a list of the entity's relationships. First, we set up the relationship subsection.                  # Now we want a list of the entity's relationships. First, we set up the relationship subsection.
499                  print HTMLOUT "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
500                  # Loop through the relationships.                  # Loop through the relationships.
501                  for my $relationship (sort keys %{$relationshipList}) {                  for my $relationship (sort keys %{$relationshipList}) {
502                          # Get the relationship data.                          # Get the relationship data.
# Line 220  Line 506 
506                                  # Get the relationship sentence and append the arity.                                  # Get the relationship sentence and append the arity.
507                                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);                                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);
508                                  # Display the relationship data.                                  # Display the relationship data.
509                                  print HTMLOUT "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";                  $retVal .= "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";
510                          }                          }
511                  }                  }
512                  # Close off the relationship list.                  # Close off the relationship list.
513                  print HTMLOUT "</ul>\n";          $retVal .= "</ul>\n";
514                  # Get the entity's relations.                  # Get the entity's relations.
515                  my $relationList = $entityData->{Relations};                  my $relationList = $entityData->{Relations};
516                  # Create a header for the relation subsection.                  # Create a header for the relation subsection.
517                  print HTMLOUT "<h4>Relations for <b>$key</b></h4>\n";          $retVal .= "<h4>Relations for <b>$key</b></h4>\n";
518                  # Loop through the relations, displaying them.                  # Loop through the relations, displaying them.
519                  for my $relation (sort keys %{$relationList}) {                  for my $relation (sort keys %{$relationList}) {
520                          my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});                          my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});
521                          print HTMLOUT $htmlString;              $retVal .= $htmlString;
522                  }                  }
523          }          }
524          # Denote we're starting the relationship section.          # Denote we're starting the relationship section.
525          print HTMLOUT "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";      $retVal .= "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";
526          # Loop through the relationships.          # Loop through the relationships.
527          for my $key (sort keys %{$relationshipList}) {          for my $key (sort keys %{$relationshipList}) {
528                  Trace("Building MetaData entry for $key relationship.") if T(4);                  Trace("Building MetaData entry for $key relationship.") if T(4);
# Line 244  Line 530 
530                  my $relationshipStructure = $relationshipList->{$key};                  my $relationshipStructure = $relationshipList->{$key};
531                  # Create the relationship header.                  # Create the relationship header.
532                  my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);                  my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);
533                  print HTMLOUT "<h3><a name=\"$key\"></a>$headerText</h3>\n";          $retVal .= "<h3><a name=\"$key\"></a>$headerText</h3>\n";
534                  # Get the entity names.                  # Get the entity names.
535                  my $fromEntity = $relationshipStructure->{from};                  my $fromEntity = $relationshipStructure->{from};
536                  my $toEntity = $relationshipStructure->{to};                  my $toEntity = $relationshipStructure->{to};
# Line 254  Line 540 
540                  # since both sentences will say the same thing.                  # since both sentences will say the same thing.
541                  my $arity = $relationshipStructure->{arity};                  my $arity = $relationshipStructure->{arity};
542                  if ($arity eq "11") {                  if ($arity eq "11") {
543                          print HTMLOUT "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";
544                  } else {                  } else {
545                          print HTMLOUT "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";
546                          if ($arity eq "MM" && $fromEntity ne $toEntity) {                          if ($arity eq "MM" && $fromEntity ne $toEntity) {
547                                  print HTMLOUT "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";                  $retVal .= "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";
548                          }                          }
549                  }                  }
550                  print HTMLOUT "</p>\n";          $retVal .= "</p>\n";
551                  # If there are notes on this relationship, display them.                  # If there are notes on this relationship, display them.
552                  if (my $notes = $relationshipStructure->{Notes}) {                  if (my $notes = $relationshipStructure->{Notes}) {
553                          print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";
554                  }                  }
555                  # Generate the relationship's relation table.                  # Generate the relationship's relation table.
556                  my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});                  my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
557                  print HTMLOUT $htmlString;          $retVal .= $htmlString;
558          }          }
559          Trace("Building MetaData join table.") if T(4);          Trace("Building MetaData join table.") if T(4);
560          # Denote we're starting the join table.          # Denote we're starting the join table.
561          print HTMLOUT "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";      $retVal .= "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";
562          # Create a table header.          # Create a table header.
563          print HTMLOUT _OpenTable("Join Table", "Source", "Target", "Join Condition");      $retVal .= _OpenTable("Join Table", "Source", "Target", "Join Condition");
564          # Loop through the joins.          # Loop through the joins.
565          my $joinTable = $metadata->{Joins};          my $joinTable = $metadata->{Joins};
566          my @joinKeys = keys %{$joinTable};          my @joinKeys = keys %{$joinTable};
# Line 282  Line 568 
568                  # Separate out the source, the target, and the join clause.                  # Separate out the source, the target, and the join clause.
569                  $joinKey =~ m!^([^/]+)/(.+)$!;                  $joinKey =~ m!^([^/]+)/(.+)$!;
570                  my ($sourceRelation, $targetRelation) = ($1, $2);                  my ($sourceRelation, $targetRelation) = ($1, $2);
571                  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);
572                  my $source = $self->ComputeObjectSentence($sourceRelation);                  my $source = $self->ComputeObjectSentence($sourceRelation);
573                  my $target = $self->ComputeObjectSentence($targetRelation);                  my $target = $self->ComputeObjectSentence($targetRelation);
574                  my $clause = $joinTable->{$joinKey};                  my $clause = $joinTable->{$joinKey};
575                  # Display them in a table row.                  # Display them in a table row.
576                  print HTMLOUT "<tr><td>$source</td><td>$target</td><td>$clause</td></tr>\n";          $retVal .= "<tr><td>$source</td><td>$target</td><td>$clause</td></tr>\n";
577          }          }
578          # Close the table.          # Close the table.
579          print HTMLOUT _CloseTable();      $retVal .= _CloseTable();
580          # Close the document.      Trace("Built MetaData HTML.") if T(3);
581          print HTMLOUT "</body>\n</html>\n";      # Return the HTML.
582          # Close the file.      return $retVal;
         close HTMLOUT;  
         Trace("Built MetaData web page.") if T(3);  
583  }  }
584    
585  =head3 DumpMetaData  =head3 DumpMetaData
586    
587  C<< $database->DumpMetaData(); >>  C<< $erdb->DumpMetaData(); >>
588    
589  Return a dump of the metadata structure.  Return a dump of the metadata structure.
590    
# Line 315  Line 599 
599    
600  =head3 CreateTables  =head3 CreateTables
601    
602  C<< $datanase->CreateTables(); >>  C<< $erdb->CreateTables(); >>
603    
604  This method creates the tables for the database from the metadata structure loaded by the  This method creates the tables for the database from the metadata structure loaded by the
605  constructor. It is expected this function will only be used on rare occasions, when the  constructor. It is expected this function will only be used on rare occasions, when the
# Line 327  Line 611 
611  sub CreateTables {  sub CreateTables {
612          # Get the parameters.          # Get the parameters.
613          my ($self) = @_;          my ($self) = @_;
614          my $metadata = $self->{_metaData};      # Get the relation names.
615          my $dbh = $self->{_dbh};      my @relNames = $self->GetTableNames();
616          # Loop through the entities.      # Loop through the relations.
617          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}}) {  
618                          # Create a table for this relation.                          # Create a table for this relation.
619                          $self->CreateTable($relationName);                          $self->CreateTable($relationName);
620                          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);  
621          }          }
622  }  }
623    
624  =head3 CreateTable  =head3 CreateTable
625    
626  C<< $database->CreateTable($tableName, $indexFlag); >>  C<< $erdb->CreateTable($tableName, $indexFlag, $estimatedRows); >>
627    
628  Create the table for a relation and optionally create its indexes.  Create the table for a relation and optionally create its indexes.
629    
# Line 363  Line 633 
633    
634  Name of the relation (which will also be the table name).  Name of the relation (which will also be the table name).
635    
636  =item $indexFlag  =item indexFlag
637    
638  TRUE if the indexes for the relation should be created, else FALSE. If FALSE,  TRUE if the indexes for the relation should be created, else FALSE. If FALSE,
639  L</CreateIndexes> must be called later to bring the indexes into existence.  L</CreateIndexes> must be called later to bring the indexes into existence.
640    
641    =item estimatedRows (optional)
642    
643    If specified, the estimated maximum number of rows for the relation. This
644    information allows the creation of tables using storage engines that are
645    faster but require size estimates, such as MyISAM.
646    
647  =back  =back
648    
649  =cut  =cut
650    
651  sub CreateTable {  sub CreateTable {
652          # Get the parameters.          # Get the parameters.
653          my ($self, $relationName, $indexFlag) = @_;      my ($self, $relationName, $indexFlag, $estimatedRows) = @_;
654          # Get the database handle.          # Get the database handle.
655          my $dbh = $self->{_dbh};          my $dbh = $self->{_dbh};
656          # 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 674 
674          # Insure the table is not already there.          # Insure the table is not already there.
675          $dbh->drop_table(tbl => $relationName);          $dbh->drop_table(tbl => $relationName);
676          Trace("Table $relationName dropped.") if T(2);          Trace("Table $relationName dropped.") if T(2);
677        # If there are estimated rows, create an estimate so we can take advantage of
678        # faster DB technologies.
679        my $estimation = undef;
680        if ($estimatedRows) {
681            $estimation = [$self->EstimateRowSize($relationName), $estimatedRows];
682        }
683          # Create the table.          # Create the table.
684          Trace("Creating table $relationName: $fieldThing") if T(2);          Trace("Creating table $relationName: $fieldThing") if T(2);
685          $dbh->create_table(tbl => $relationName, flds => $fieldThing);      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);
686          Trace("Relation $relationName created in database.") if T(2);          Trace("Relation $relationName created in database.") if T(2);
687          # If we want to build the indexes, we do it here.          # If we want to build the indexes, we do it here.
688          if ($indexFlag) {          if ($indexFlag) {
# Line 408  Line 690 
690          }          }
691  }  }
692    
693    =head3 VerifyFields
694    
695    C<< my $count = $erdb->VerifyFields($relName, \@fieldList); >>
696    
697    Run through the list of proposed field values, insuring that all the character fields are
698    below the maximum length. If any fields are too long, they will be truncated in place.
699    
700    =over 4
701    
702    =item relName
703    
704    Name of the relation for which the specified fields are destined.
705    
706    =item fieldList
707    
708    Reference to a list, in order, of the fields to be put into the relation.
709    
710    =item RETURN
711    
712    Returns the number of fields truncated.
713    
714    =back
715    
716    =cut
717    
718    sub VerifyFields {
719        # Get the parameters.
720        my ($self, $relName, $fieldList) = @_;
721        # Initialize the return value.
722        my $retVal = 0;
723        # Get the relation definition.
724        my $relData = $self->_FindRelation($relName);
725        # Get the list of field descriptors.
726        my $fieldTypes = $relData->{Fields};
727        my $fieldCount = scalar @{$fieldTypes};
728        # Loop through the two lists.
729        for (my $i = 0; $i < $fieldCount; $i++) {
730            # Get the type of the current field.
731            my $fieldType = $fieldTypes->[$i]->{type};
732            # If it's a character field, verify the length.
733            if ($fieldType =~ /string/) {
734                my $maxLen = $TypeTable{$fieldType}->{maxLen};
735                my $oldString = $fieldList->[$i];
736                if (length($oldString) > $maxLen) {
737                    # Here it's too big, so we truncate it.
738                    Trace("Truncating field $i in relation $relName to $maxLen characters from \"$oldString\".") if T(1);
739                    $fieldList->[$i] = substr $oldString, 0, $maxLen;
740                    $retVal++;
741                }
742            }
743        }
744        # Return the truncation count.
745        return $retVal;
746    }
747    
748    =head3 DigestFields
749    
750    C<< $erdb->DigestFields($relName, $fieldList); >>
751    
752    Digest the strings in the field list that correspond to data type C<hash-string> in the
753    specified relation.
754    
755    =over 4
756    
757    =item relName
758    
759    Name of the relation to which the fields belong.
760    
761    =item fieldList
762    
763    List of field contents to be loaded into the relation.
764    
765    =back
766    
767    =cut
768    #: Return Type ;
769    sub DigestFields {
770        # Get the parameters.
771        my ($self, $relName, $fieldList) = @_;
772        # Get the relation definition.
773        my $relData = $self->_FindRelation($relName);
774        # Get the list of field descriptors.
775        my $fieldTypes = $relData->{Fields};
776        my $fieldCount = scalar @{$fieldTypes};
777        # Loop through the two lists.
778        for (my $i = 0; $i < $fieldCount; $i++) {
779            # Get the type of the current field.
780            my $fieldType = $fieldTypes->[$i]->{type};
781            # If it's a hash string, digest it in place.
782            if ($fieldType eq 'hash-string') {
783                $fieldList->[$i] = $self->DigestKey($fieldList->[$i]);
784            }
785        }
786    }
787    
788    =head3 DigestKey
789    
790    C<< my $digested = $erdb->DigestKey($keyValue); >>
791    
792    Return the digested value of a symbolic key. The digested value can then be plugged into a
793    key-based search into a table with key-type hash-string.
794    
795    Currently the digesting process is independent of the database structure, but that may not
796    always be the case, so this is an instance method instead of a static method.
797    
798    =over 4
799    
800    =item keyValue
801    
802    Key value to digest.
803    
804    =item RETURN
805    
806    Digested value ofthe key.
807    
808    =back
809    
810    =cut
811    
812    sub DigestKey {
813        # Get the parameters.
814        my ($self, $keyValue) = @_;
815        # Compute the digest.
816        my $retVal = md5_base64($keyValue);
817        # Return the result.
818        return $retVal;
819    }
820    
821  =head3 CreateIndex  =head3 CreateIndex
822    
823  C<< $database->CreateIndex($relationName); >>  C<< $erdb->CreateIndex($relationName); >>
824    
825  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
826  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.
827  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
828  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.
829    
830  =cut  =cut
831    
# Line 436  Line 846 
846                  # Get the index's uniqueness flag.                  # Get the index's uniqueness flag.
847                  my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');                  my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');
848                  # Create the index.                  # Create the index.
849                  $dbh->create_index(idx => $indexName, tbl => $relationName, flds => $flds, unique => $unique);          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
850                                        flds => $flds, unique => $unique);
851            if ($rv) {
852                  Trace("Index created: $indexName for $relationName ($flds)") if T(1);                  Trace("Index created: $indexName for $relationName ($flds)") if T(1);
853            } else {
854                Confess("Error creating index $indexName for $relationName using ($flds): " . $dbh->error_message());
855            }
856          }          }
857  }  }
858    
859  =head3 LoadTables  =head3 LoadTables
860    
861  C<< my $stats = $database->LoadTables($directoryName, $rebuild); >>  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>
862    
863  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
864  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 901 
901          $directoryName =~ s!/\\$!!;          $directoryName =~ s!/\\$!!;
902          # Declare the return variable.          # Declare the return variable.
903          my $retVal = Stats->new();          my $retVal = Stats->new();
904          # Get the metadata structure.      # Get the relation names.
905          my $metaData = $self->{_metaData};      my @relNames = $self->GetTableNames();
906          # 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}}) {  
907                          # Try to load this relation.                          # Try to load this relation.
908                          my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);                          my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);
909                          # Accumulate the statistics.                          # Accumulate the statistics.
910                          $retVal->Accumulate($result);                          $retVal->Accumulate($result);
911                  }                  }
         }  
         # 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);  
         }  
912          # Add the duration of the load to the statistical object.          # Add the duration of the load to the statistical object.
913          $retVal->Add('duration', gettimeofday - $startTime);          $retVal->Add('duration', gettimeofday - $startTime);
914          # Return the accumulated statistics.          # Return the accumulated statistics.
915          return $retVal;          return $retVal;
916  }  }
917    
918    
919  =head3 GetTableNames  =head3 GetTableNames
920    
921  C<< my @names = $database->GetTableNames; >>  C<< my @names = $erdb->GetTableNames; >>
922    
923  Return a list of the relations required to implement this database.  Return a list of the relations required to implement this database.
924    
# Line 530  Line 935 
935    
936  =head3 GetEntityTypes  =head3 GetEntityTypes
937    
938  C<< my @names = $database->GetEntityTypes; >>  C<< my @names = $erdb->GetEntityTypes; >>
939    
940  Return a list of the entity type names.  Return a list of the entity type names.
941    
# Line 545  Line 950 
950          return sort keys %{$entityList};          return sort keys %{$entityList};
951  }  }
952    
953    =head3 IsEntity
954    
955    C<< my $flag = $erdb->IsEntity($entityName); >>
956    
957    Return TRUE if the parameter is an entity name, else FALSE.
958    
959    =over 4
960    
961    =item entityName
962    
963    Object name to be tested.
964    
965    =item RETURN
966    
967    Returns TRUE if the specified string is an entity name, else FALSE.
968    
969    =back
970    
971    =cut
972    
973    sub IsEntity {
974        # Get the parameters.
975        my ($self, $entityName) = @_;
976        # Test to see if it's an entity.
977        return exists $self->{_metaData}->{Entities}->{$entityName};
978    }
979    
980  =head3 Get  =head3 Get
981    
982  C<< my $query = $database->Get(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  C<< my $query = $erdb->Get(\@objectNames, $filterClause, \@params); >>
983    
984  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.
985  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 987 
987  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
988  $genus.  $genus.
989    
990  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", [$genus]); >>
991    
992  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
993  parameter representing the parameter value. It would also be possible to code  parameter representing the parameter value. It would also be possible to code
994    
995  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>
996    
997  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
998  characters inside the variable C<$genus>.  characters inside the variable C<$genus>.
# Line 572  Line 1004 
1004  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
1005  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,
1006    
1007  C<< $query = $sprout->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]); >>
1008    
1009  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
1010  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.
1011  In particular, you can't specify any entity or relationship more than once, and if a  In particular, if a relationship is recursive, the path is determined by the order in which
1012  relationship is recursive, the path is determined by the order in which the entity  the entity and the relationship appear. For example, consider a recursive relationship
1013  and the relationship appear. For example, consider a recursive relationship B<IsParentOf>  B<IsParentOf> which relates B<People> objects to other B<People> objects. If the join path is
 which relates B<People> objects to other B<People> objects. If the join path is  
1014  coded as C<['People', 'IsParentOf']>, then the people returned will be parents. If, however,  coded as C<['People', 'IsParentOf']>, then the people returned will be parents. If, however,
1015  the join path is C<['IsParentOf', 'People']>, then the people returned will be children.  the join path is C<['IsParentOf', 'People']>, then the people returned will be children.
1016    
1017    If an entity or relationship is mentioned twice, the name for the second occurrence will
1018    be suffixed with C<2>, the third occurrence will be suffixed with C<3>, and so forth. So,
1019    for example, if we have C<['Feature', 'HasContig', 'Contig', 'HasContig']>, then the
1020    B<to-link> field of the first B<HasContig> is specified as C<HasContig(to-link)>, while
1021    the B<to-link> field of the second B<HasContig> is specified as C<HasContig2(to-link)>.
1022    
1023  =over 4  =over 4
1024    
1025  =item objectNames  =item objectNames
# Line 605  Line 1042 
1042    
1043  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
1044    
1045    Note that the case is important. Only an uppercase "ORDER BY" with a single space will
1046    be processed. The idea is to make it less likely to find the verb by accident.
1047    
1048  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
1049  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
1050  relation.  relation.
1051    
1052  =item param1, param2, ..., paramN  Finally, you can limit the number of rows returned by adding a LIMIT clause. The LIMIT must
1053    be the last thing in the filter clause, and it contains only the word "LIMIT" followed by
1054    a positive number. So, for example
1055    
1056    C<< "Genome(genus) = ? ORDER BY Genome(species) LIMIT 10" >>
1057    
1058  Parameter values to be substituted into the filter clause.  will only return the first ten genomes for the specified genus. The ORDER BY clause is not
1059    required. For example, to just get the first 10 genomes in the B<Genome> table, you could
1060    use
1061    
1062    C<< "LIMIT 10" >>
1063    
1064    =item params
1065    
1066    Reference to a list of parameter values to be substituted into the filter clause.
1067    
1068  =item RETURN  =item RETURN
1069    
# Line 623  Line 1075 
1075    
1076  sub Get {  sub Get {
1077          # Get the parameters.          # Get the parameters.
1078          my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $objectNames, $filterClause, $params) = @_;
1079          # Construct the SELECT statement. The general pattern is      # Process the SQL stuff.
1080          #      my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1081          # SELECT name1.*, name2.*, ... nameN.* FROM name1, name2, ... nameN          $self->_SetupSQL($objectNames, $filterClause);
1082          #      # Create the query.
1083          my $dbh = $self->{_dbh};      my $command = "SELECT DISTINCT " . join(".*, ", @{$mappedNameListRef}) .
1084          my $command = "SELECT DISTINCT " . join('.*, ', @{$objectNames}) . ".* FROM " .          ".* $suffix";
1085                                  join(', ', @{$objectNames});      my $sth = $self->_GetStatementHandle($command, $params);
1086          # Check for a filter clause.      # Now we create the relation map, which enables DBQuery to determine the order, name
1087          if ($filterClause) {      # and mapped name for each object in the query.
1088                  # Here we have one, so we convert its field names and add it to the query. First,      my @relationMap = ();
1089                  # We create a copy of the filter string we can work with.      for my $mappedName (@{$mappedNameListRef}) {
1090                  my $filterString = $filterClause;          push @relationMap, [$mappedName, $mappedNameHashRef->{$mappedName}];
                 # Next, we sort the object names by length. This helps protect us from finding  
                 # object names inside other object names when we're doing our search and replace.  
                 my @sortedNames = sort { length($b) - length($a) } @{$objectNames};  
                 # We will also keep a list of conditions to add to the WHERE clause in order to link  
                 # entities and relationships as well as primary relations to secondary ones.  
                 my @joinWhere = ();  
                 # The final preparatory step is to create a hash table of relation names. The  
                 # table begins with the relation names already in the SELECT command.  
                 my %fromNames = ();  
                 for my $objectName (@sortedNames) {  
                         $fromNames{$objectName} = 1;  
1091                  }                  }
1092                  # We are ready to begin. We loop through the object names, replacing each      # Return the statement object.
1093                  # object name's field references by the corresponding SQL field reference.      my $retVal = DBQuery::_new($self, $sth, \@relationMap);
1094                  # Along the way, if we find a secondary relation, we will need to add it      return $retVal;
                 # to the FROM clause.  
                 for my $objectName (@sortedNames) {  
                         # Get the length of the object name plus 2. This is the value we add to the  
                         # size of the field name to determine the size of the field reference as a  
                         # whole.  
                         my $nameLength = 2 + length $objectName;  
                         # Get the object's field list.  
                         my $fieldList = $self->_GetFieldTable($objectName);  
                         # Find the field references for this object.  
                         while ($filterString =~ m/$objectName\(([^)]*)\)/g) {  
                                 # At this point, $1 contains the field name, and the current position  
                                 # is set immediately after the final parenthesis. We pull out the name of  
                                 # the field and the position and length of the field reference as a whole.  
                                 my $fieldName = $1;  
                                 my $len = $nameLength + length $fieldName;  
                                 my $pos = pos($filterString) - $len;  
                                 # Insure the field exists.  
                                 if (!exists $fieldList->{$fieldName}) {  
                                         Confess("Field $fieldName not found for object $objectName.");  
                                 } else {  
                                         # Get the field's relation.  
                                         my $relationName = $fieldList->{$fieldName}->{relation};  
                                         # Insure the relation is in the FROM clause.  
                                         if (!exists $fromNames{$relationName}) {  
                                                 # Add the relation to the FROM clause.  
                                                 $command .= ", $relationName";  
                                                 # Create its join sub-clause.  
                                                 push @joinWhere, "$objectName.id = $relationName.id";  
                                                 # Denote we have it available for future fields.  
                                                 $fromNames{$relationName} = 1;  
1095                                          }                                          }
1096                                          # Form an SQL field reference from the relation name and the field name.  
1097                                          my $sqlReference = "$relationName." . _FixName($fieldName);  =head3 GetFlat
1098                                          # Put it into the filter string in place of the old value.  
1099                                          substr($filterString, $pos, $len) = $sqlReference;  C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>
1100                                          # Reposition the search.  
1101                                          pos $filterString = $pos + length $sqlReference;  This is a variation of L</GetAll> that asks for only a single field per record and
1102    returns a single flattened list.
1103    
1104    =over 4
1105    
1106    =item objectNames
1107    
1108    List containing the names of the entity and relationship objects to be retrieved.
1109    
1110    =item filterClause
1111    
1112    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1113    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
1114    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
1115    parameter list as additional parameters. The fields in a filter clause can come from primary
1116    entity relations, relationship relations, or secondary entity relations; however, all of the
1117    entities and relationships involved must be included in the list of object names.
1118    
1119    =item parameterList
1120    
1121    List of the parameters to be substituted in for the parameters marks in the filter clause.
1122    
1123    =item field
1124    
1125    Name of the field to be used to get the elements of the list returned.
1126    
1127    =item RETURN
1128    
1129    Returns a list of values.
1130    
1131    =back
1132    
1133    =cut
1134    #: Return Type @;
1135    sub GetFlat {
1136        # Get the parameters.
1137        my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
1138        # Construct the query.
1139        my $query = $self->Get($objectNames, $filterClause, $parameterList);
1140        # Create the result list.
1141        my @retVal = ();
1142        # Loop through the records, adding the field values found to the result list.
1143        while (my $row = $query->Fetch()) {
1144            push @retVal, $row->Value($field);
1145                                  }                                  }
1146        # Return the list created.
1147        return @retVal;
1148                          }                          }
1149    
1150    =head3 Delete
1151    
1152    C<< my $stats = $erdb->Delete($entityName, $objectID); >>
1153    
1154    Delete an entity instance from the database. The instance is deleted along with all entity and
1155    relationship instances dependent on it. The idea of dependence here is recursive. An object is
1156    always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many
1157    relationship connected to a dependent entity or the "to" entity connected to a 1-to-many
1158    dependent relationship.
1159    
1160    =over 4
1161    
1162    =item entityName
1163    
1164    Name of the entity type for the instance being deleted.
1165    
1166    =item objectID
1167    
1168    ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),
1169    then it is presumed to by a LIKE pattern.
1170    
1171    =item testFlag
1172    
1173    If TRUE, the delete statements will be traced without being executed.
1174    
1175    =item RETURN
1176    
1177    Returns a statistics object indicating how many records of each particular table were
1178    deleted.
1179    
1180    =back
1181    
1182    =cut
1183    #: Return Type $%;
1184    sub Delete {
1185        # Get the parameters.
1186        my ($self, $entityName, $objectID, $testFlag) = @_;
1187        # Declare the return variable.
1188        my $retVal = Stats->new();
1189        # Get the DBKernel object.
1190        my $db = $self->{_dbh};
1191        # We're going to generate all the paths branching out from the starting entity. One of
1192        # the things we have to be careful about is preventing loops. We'll use a hash to
1193        # determine if we've hit a loop.
1194        my %alreadyFound = ();
1195        # These next lists will serve as our result stack. We start by pushing object lists onto
1196        # the stack, and then popping them off to do the deletes. This means the deletes will
1197        # start with the longer paths before getting to the shorter ones. That, in turn, makes
1198        # sure we don't delete records that might be needed to forge relationships back to the
1199        # original item. We have two lists-- one for TO-relationships, and one for
1200        # FROM-relationships and entities.
1201        my @fromPathList = ();
1202        my @toPathList = ();
1203        # This final hash is used to remember what work still needs to be done. We push paths
1204        # onto the list, then pop them off to extend the paths. We prime it with the starting
1205        # point. Note that we will work hard to insure that the last item on a path in the
1206        # TODO list is always an entity.
1207        my @todoList = ([$entityName]);
1208        while (@todoList) {
1209            # Get the current path.
1210            my $current = pop @todoList;
1211            # Copy it into a list.
1212            my @stackedPath = @{$current};
1213            # Pull off the last item on the path. It will always be an entity.
1214            my $entityName = pop @stackedPath;
1215            # Add it to the alreadyFound list.
1216            $alreadyFound{$entityName} = 1;
1217            # Get the entity data.
1218            my $entityData = $self->_GetStructure($entityName);
1219            # The first task is to loop through the entity's relation. A DELETE command will
1220            # be needed for each of them.
1221            my $relations = $entityData->{Relations};
1222            for my $relation (keys %{$relations}) {
1223                my @augmentedList = (@stackedPath, $relation);
1224                push @fromPathList, \@augmentedList;
1225                  }                  }
1226                  # The next step is to join the objects together. We only need to do this if there          # Now we need to look for relationships connected to this entity.
1227                  # is more than one object in the object list. We start with the first object and          my $relationshipList = $self->{_metaData}->{Relationships};
1228                  # run through the objects after it. Note also that we make a safety copy of the          for my $relationshipName (keys %{$relationshipList}) {
1229                  # list before running through it.              my $relationship = $relationshipList->{$relationshipName};
1230                  my @objectList = @{$objectNames};              # Check the FROM field. We're only interested if it's us.
1231                  my $lastObject = shift @objectList;              if ($relationship->{from} eq $entityName) {
1232                  # Get the join table.                  # Add the path to this relationship.
1233                  my $joinTable = $self->{_metaData}->{Joins};                  my @augmentedList = (@stackedPath, $entityName, $relationshipName);
1234                  # Loop through the object list.                  push @fromPathList, \@augmentedList;
1235                  for my $thisObject (@objectList) {                  # Check the arity. If it's MM we're done. If it's 1M
1236                          # Look for a join.                  # and the target hasn't been seen yet, we want to
1237                          my $joinKey = "$lastObject/$thisObject";                  # stack the entity for future processing.
1238                          if (!exists $joinTable->{$joinKey}) {                  if ($relationship->{arity} eq '1M') {
1239                                  # Here there's no join, so we throw an error.                      my $toEntity = $relationship->{to};
1240                                  Confess("No join exists to connect from $lastObject to $thisObject.");                      if (! exists $alreadyFound{$toEntity}) {
1241                            # Here we have a new entity that's dependent on
1242                            # the current entity, so we need to stack it.
1243                            my @stackList = (@augmentedList, $toEntity);
1244                            push @fromPathList, \@stackList;
1245                          } else {                          } else {
1246                                  # Get the join clause and add it to the WHERE list.                          Trace("$toEntity ignored because it occurred previously.") if T(4);
                                 push @joinWhere, $joinTable->{$joinKey};  
                                 # Save this object as the last object for the next iteration.  
                                 $lastObject = $thisObject;  
1247                          }                          }
1248                  }                  }
                 # Now we need to handle the whole ORDER BY thing. We'll put the order by clause  
                 # in the following variable.  
                 my $orderClause = "";  
                 # Locate the ORDER BY verb (if any).  
                 if ($filterString =~ m/^(.*)ORDER BY/g) {  
                         # Here we have an ORDER BY verb. Split it off of the filter string.  
                         my $pos = pos $filterString;  
                         $orderClause = substr($filterString, $pos);  
                         $filterString = $1;  
1249                  }                  }
1250                  # Add the filter and the join clauses (if any) to the SELECT command.              # Now check the TO field. In this case only the relationship needs
1251                  if ($filterString) {              # deletion.
1252                          push @joinWhere, "($filterString)";              if ($relationship->{to} eq $entityName) {
1253                    my @augmentedList = (@stackedPath, $entityName, $relationshipName);
1254                    push @toPathList, \@augmentedList;
1255                  }                  }
                 if (@joinWhere) {  
                         $command .= " WHERE " . join(' AND ', @joinWhere);  
1256                  }                  }
                 # Add the sort clause (if any) to the SELECT command.  
                 if ($orderClause) {  
                         $command .= " ORDER BY $orderClause";  
1257                  }                  }
1258        # Create the first qualifier for the WHERE clause. This selects the
1259        # keys of the primary entity records to be deleted. When we're deleting
1260        # from a dependent table, we construct a join page from the first qualifier
1261        # to the table containing the dependent records to delete.
1262        my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
1263        # We need to make two passes. The first is through the to-list, and
1264        # the second through the from-list. The from-list is second because
1265        # the to-list may need to pass through some of the entities the
1266        # from-list would delete.
1267        my %stackList = ( from_link => \@fromPathList, to_link => \@toPathList );
1268        # Now it's time to do the deletes. We do it in two passes.
1269        for my $keyName ('to_link', 'from_link') {
1270            # Get the list for this key.
1271            my @pathList = @{$stackList{$keyName}};
1272            Trace(scalar(@pathList) . " entries in path list for $keyName.") if T(3);
1273            # Loop through this list.
1274            while (my $path = pop @pathList) {
1275                # Get the table whose rows are to be deleted.
1276                my @pathTables = @{$path};
1277                # Start the DELETE statement. We need to call DBKernel because the
1278                # syntax of a DELETE-USING varies among DBMSs.
1279                my $target = $pathTables[$#pathTables];
1280                my $stmt = $db->SetUsing(@pathTables);
1281                # Now start the WHERE. The first thing is the ID field from the starting table. That
1282                # starting table will either be the entity relation or one of the entity's
1283                # sub-relations.
1284                $stmt .= " WHERE $pathTables[0].id $qualifier";
1285                # Now we run through the remaining entities in the path, connecting them up.
1286                for (my $i = 1; $i <= $#pathTables; $i += 2) {
1287                    # Connect the current relationship to the preceding entity.
1288                    my ($entity, $rel) = @pathTables[$i-1,$i];
1289                    # The style of connection depends on the direction of the relationship.
1290                    $stmt .= " AND $entity.id = $rel.$keyName";
1291                    if ($i + 1 <= $#pathTables) {
1292                        # Here there's a next entity, so connect that to the relationship's
1293                        # to-link.
1294                        my $entity2 = $pathTables[$i+1];
1295                        $stmt .= " AND $rel.to_link = $entity2.id";
1296                    }
1297                }
1298                # Now we have our desired DELETE statement.
1299                if ($testFlag) {
1300                    # Here the user wants to trace without executing.
1301                    Trace($stmt) if T(0);
1302                } else {
1303                    # Here we can delete. Note that the SQL method dies with a confessing
1304                    # if an error occurs, so we just go ahead and do it.
1305                    Trace("Executing delete from $target using '$objectID'.") if T(3);
1306                    my $rv = $db->SQL($stmt, 0, $objectID);
1307                    # Accumulate the statistics for this delete. The only rows deleted
1308                    # are from the target table, so we use its name to record the
1309                    # statistic.
1310                    $retVal->Add($target, $rv);
1311          }          }
1312          Trace("SQL query: $command") if T(2);          }
1313          Trace("PARMS: '" . (join "', '", @params) . "'") if (T(3) && (@params > 0));      }
1314          my $sth = $dbh->prepare_command($command);      # Return the result.
         # Execute it with the parameters bound in.  
         $sth->execute(@params) || Confess("SELECT error" . $sth->errstr());  
         # Return the statement object.  
         my $retVal = DBQuery::_new($self, $sth, @{$objectNames});  
1315          return $retVal;          return $retVal;
1316  }  }
1317    
1318  =head3 GetList  =head3 GetList
1319    
1320  C<< my @dbObjects = $database->GetList(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>
1321    
1322  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
1323  specified filter clause.  specified filter clause.
1324    
1325  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
1326  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  
1327    
1328  =over 4  =over 4
1329    
# Line 783  Line 1351 
1351  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
1352  relation.  relation.
1353    
1354  =item param1, param2, ..., paramN  =item params
1355    
1356  Parameter values to be substituted into the filter clause.  Reference to a list of parameter values to be substituted into the filter clause.
1357    
1358  =item RETURN  =item RETURN
1359    
# Line 797  Line 1365 
1365  #: Return Type @%  #: Return Type @%
1366  sub GetList {  sub GetList {
1367      # Get the parameters.      # Get the parameters.
1368      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $objectNames, $filterClause, $params) = @_;
1369          # Declare the return variable.          # Declare the return variable.
1370          my @retVal = ();          my @retVal = ();
1371          # Perform the query.          # Perform the query.
1372          my $query = $self->Get($objectNames, $filterClause, @params);      my $query = $self->Get($objectNames, $filterClause, $params);
1373          # Loop through the results.          # Loop through the results.
1374          while (my $object = $query->Fetch) {          while (my $object = $query->Fetch) {
1375                  push @retVal, $object;                  push @retVal, $object;
# Line 810  Line 1378 
1378      return @retVal;      return @retVal;
1379  }  }
1380    
1381    =head3 GetCount
1382    
1383    C<< my $count = $erdb->GetCount(\@objectNames, $filter, \@params); >>
1384    
1385    Return the number of rows found by a specified query. This method would
1386    normally be used to count the records in a single table. For example, in a
1387    genetics database
1388    
1389        my $count = $erdb->GetCount(['Genome'], 'Genome(genus-species) LIKE ?', ['homo %']);
1390    
1391    would return the number of genomes for the genus I<homo>. It is conceivable, however,
1392    to use it to return records based on a join. For example,
1393    
1394        my $count = $erdb->GetCount(['HasFeature', 'Genome'], 'Genome(genus-species) LIKE ?',
1395                                    ['homo %']);
1396    
1397    would return the number of features for genomes in the genus I<homo>. Note that
1398    only the rows from the first table are counted. If the above command were
1399    
1400        my $count = $erdb->GetCount(['Genome', 'Feature'], 'Genome(genus-species) LIKE ?',
1401                                    ['homo %']);
1402    
1403    it would return the number of genomes, not the number of genome/feature pairs.
1404    
1405    =over 4
1406    
1407    =item objectNames
1408    
1409    Reference to a list of the objects (entities and relationships) included in the
1410    query.
1411    
1412    =item filter
1413    
1414    A filter clause for restricting the query. The rules are the same as for the L</Get>
1415    method.
1416    
1417    =item params
1418    
1419    Reference to a list of the parameter values to be substituted for the parameter marks
1420    in the filter.
1421    
1422    =item RETURN
1423    
1424    Returns a count of the number of records in the first table that would satisfy
1425    the query.
1426    
1427    =back
1428    
1429    =cut
1430    
1431    sub GetCount {
1432        # Get the parameters.
1433        my ($self, $objectNames, $filter, $params) = @_;
1434        # Declare the return variable.
1435        my $retVal;
1436        # Find out if we're counting an entity or a relationship.
1437        my $countedField;
1438        if ($self->IsEntity($objectNames->[0])) {
1439            $countedField = "id";
1440        } else {
1441            # For a relationship we count the to-link because it's usually more
1442            # numerous. Note we're automatically converting to the SQL form
1443            # of the field name (to_link vs. to-link).
1444            $countedField = "to_link";
1445        }
1446        # Create the SQL command suffix to get the desired records.
1447        my ($suffix, $mappedNameListRef, $mappedNameHashRef) = $self->_SetupSQL($objectNames,
1448                                                                                $filter);
1449        # Prefix it with text telling it we want a record count.
1450        my $firstObject = $mappedNameListRef->[0];
1451        my $command = "SELECT COUNT($firstObject.$countedField) $suffix";
1452        # Prepare and execute the command.
1453        my $sth = $self->_GetStatementHandle($command, $params);
1454        # Get the count value.
1455        ($retVal) = $sth->fetchrow_array();
1456        # Check for a problem.
1457        if (! defined($retVal)) {
1458            if ($sth->err) {
1459                # Here we had an SQL error.
1460                Confess("Error retrieving row count: " . $sth->errstr());
1461            } else {
1462                # Here we have no result.
1463                Confess("No result attempting to retrieve row count.");
1464            }
1465        }
1466        # Return the result.
1467        return $retVal;
1468    }
1469    
1470  =head3 ComputeObjectSentence  =head3 ComputeObjectSentence
1471    
1472  C<< my $sentence = $database->ComputeObjectSentence($objectName); >>  C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>
1473    
1474  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.
1475    
# Line 847  Line 1504 
1504    
1505  =head3 DumpRelations  =head3 DumpRelations
1506    
1507  C<< $database->DumpRelations($outputDirectory); >>  C<< $erdb->DumpRelations($outputDirectory); >>
1508    
1509  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.
1510  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 1544 
1544          }          }
1545  }  }
1546    
1547    =head3 InsertValue
1548    
1549    C<< $erdb->InsertValue($entityID, $fieldName, $value); >>
1550    
1551    This method will insert a new value into the database. The value must be one
1552    associated with a secondary relation, since primary values cannot be inserted:
1553    they occur exactly once. Secondary values, on the other hand, can be missing
1554    or multiply-occurring.
1555    
1556    =over 4
1557    
1558    =item entityID
1559    
1560    ID of the object that is to receive the new value.
1561    
1562    =item fieldName
1563    
1564    Field name for the new value-- this includes the entity name, since
1565    field names are of the format I<objectName>C<(>I<fieldName>C<)>.
1566    
1567    =item value
1568    
1569    New value to be put in the field.
1570    
1571    =back
1572    
1573    =cut
1574    
1575    sub InsertValue {
1576        # Get the parameters.
1577        my ($self, $entityID, $fieldName, $value) = @_;
1578        # Parse the entity name and the real field name.
1579        if ($fieldName =~ /^([^(]+)\(([^)]+)\)/) {
1580            my $entityName = $1;
1581            my $fieldTitle = $2;
1582            # Get its descriptor.
1583            if (!$self->IsEntity($entityName)) {
1584                Confess("$entityName is not a valid entity.");
1585            } else {
1586                my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1587                # Find the relation containing this field.
1588                my $fieldHash = $entityData->{Fields};
1589                if (! exists $fieldHash->{$fieldTitle}) {
1590                    Confess("$fieldTitle not found in $entityName.");
1591                } else {
1592                    my $relation = $fieldHash->{$fieldTitle}->{relation};
1593                    if ($relation eq $entityName) {
1594                        Confess("Cannot do InsertValue on primary field $fieldTitle of $entityName.");
1595                    } else {
1596                        # Now we can create an INSERT statement.
1597                        my $dbh = $self->{_dbh};
1598                        my $fixedName = _FixName($fieldTitle);
1599                        my $statement = "INSERT INTO $relation (id, $fixedName) VALUES(?, ?)";
1600                        # Execute the command.
1601                        $dbh->SQL($statement, 0, $entityID, $value);
1602                    }
1603                }
1604            }
1605        } else {
1606            Confess("$fieldName is not a valid field name.");
1607        }
1608    }
1609    
1610  =head3 InsertObject  =head3 InsertObject
1611    
1612  C<< my $ok = $database->InsertObject($objectType, \%fieldHash); >>  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>
1613    
1614  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
1615  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 1618 
1618  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
1619  C<ZP_00210270.1> and C<gi|46206278>.  C<ZP_00210270.1> and C<gi|46206278>.
1620    
1621  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']}); >>
1622    
1623  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
1624  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>.
1625    
1626  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'}); >>
1627    
1628  =over 4  =over 4
1629    
# Line 1028  Line 1748 
1748    
1749  =head3 LoadTable  =head3 LoadTable
1750    
1751  C<< my %results = $database->LoadTable($fileName, $relationName, $truncateFlag); >>  C<< my %results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>
1752    
1753  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
1754    first.
1755    
1756  =over 4  =over 4
1757    
# Line 1048  Line 1769 
1769    
1770  =item RETURN  =item RETURN
1771    
1772  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.
1773    
1774  =back  =back
1775    
# Line 1059  Line 1780 
1780          # Create the statistical return object.          # Create the statistical return object.
1781          my $retVal = _GetLoadStats();          my $retVal = _GetLoadStats();
1782          # Trace the fact of the load.          # Trace the fact of the load.
1783          Trace("Loading table $relationName from $fileName") if T(1);      Trace("Loading table $relationName from $fileName") if T(2);
1784          # Get the database handle.          # Get the database handle.
1785          my $dbh = $self->{_dbh};          my $dbh = $self->{_dbh};
1786        # Get the input file size.
1787        my $fileSize = -s $fileName;
1788          # Get the relation data.          # Get the relation data.
1789          my $relation = $self->_FindRelation($relationName);          my $relation = $self->_FindRelation($relationName);
1790          # Check the truncation flag.          # Check the truncation flag.
1791          if ($truncateFlag) {          if ($truncateFlag) {
1792                  Trace("Creating table $relationName") if T(1);          Trace("Creating table $relationName") if T(2);
1793            # Compute the row count estimate. We take the size of the load file,
1794            # divide it by the estimated row size, and then multiply by 1.5 to
1795            # leave extra room. We postulate a minimum row count of 1000 to
1796            # prevent problems with incoming empty load files.
1797            my $rowSize = $self->EstimateRowSize($relationName);
1798            my $estimate = FIG::max($fileSize * 1.5 / $rowSize, 1000);
1799                  # Re-create the table without its index.                  # Re-create the table without its index.
1800                  $self->CreateTable($relationName, 0);          $self->CreateTable($relationName, 0, $estimate);
1801            # If this is a pre-index DBMS, create the index here.
1802            if ($dbh->{_preIndex}) {
1803                eval {
1804                    $self->CreateIndex($relationName);
1805                };
1806                if ($@) {
1807                    $retVal->AddMessage($@);
1808                }
1809            }
1810          }          }
         # 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);  
1811      # Load the table.      # Load the table.
1812          my $rv;          my $rv;
1813          eval {          eval {
1814                  $rv = $dbh->load_table(file => $tempName, tbl => $relationName);          $rv = $dbh->load_table(file => $fileName, tbl => $relationName);
1815          };          };
1816          if (!defined $rv) {          if (!defined $rv) {
1817          $retVal->AddMessage($@) if ($@);          $retVal->AddMessage($@) if ($@);
1818          $retVal->AddMessage("Table load failed for $relationName using $tempName.");          $retVal->AddMessage("Table load failed for $relationName using $fileName.");
1819                  Trace("Table load failed for $relationName.") if T(1);                  Trace("Table load failed for $relationName.") if T(1);
1820          } else {          } else {
1821                  # Here we successfully loaded the table. Trace the number of records loaded.          # Here we successfully loaded the table.
1822                  Trace("$retVal->{records} records read for $relationName.") if T(1);          $retVal->Add("tables");
1823            my $size = -s $fileName;
1824            Trace("$size bytes loaded into $relationName.") if T(2);
1825                  # If we're rebuilding, we need to create the table indexes.                  # If we're rebuilding, we need to create the table indexes.
1826                  if ($truncateFlag) {          if ($truncateFlag && ! $dbh->{_preIndex}) {
1827                          eval {                          eval {
1828                                  $self->CreateIndex($relationName);                                  $self->CreateIndex($relationName);
1829                          };                          };
# Line 1134  Line 1832 
1832                          }                          }
1833                  }                  }
1834          }          }
1835          # Commit the database changes.      # Analyze the table to improve performance.
1836          $dbh->commit_tran;      $dbh->vacuum_it($relationName);
         # Delete the temporary file.  
         unlink $tempName;  
1837          # Return the statistics.          # Return the statistics.
1838          return $retVal;          return $retVal;
1839  }  }
1840    
1841  =head3 GenerateEntity  =head3 GenerateEntity
1842    
1843    C<< my $fieldHash = $erdb->GenerateEntity($id, $type, \%values); >>
1844    
1845    Generate the data for a new entity instance. This method creates a field hash suitable for
1846    passing as a parameter to L</InsertObject>. The ID is specified by the callr, but the rest
1847    of the fields are generated using information in the database schema.
1848    
1849    Each data type has a default algorithm for generating random test data. This can be overridden
1850    by including a B<DataGen> element in the field. If this happens, the content of the element is
1851    executed as a PERL program in the context of this module. The element may make use of a C<$this>
1852    variable which contains the field hash as it has been built up to the current point. If any
1853    fields are dependent on other fields, the C<pass> attribute can be used to control the order
1854    in which the fields are generated. A field with a high data pass number will be generated after
1855    a field with a lower one. If any external values are needed, they should be passed in via the
1856    optional third parameter, which will be available to the data generation script under the name
1857    C<$value>. Several useful utility methods are provided for generating random values, including
1858    L</IntGen>, L</StringGen>, L</FloatGen>, and L</DateGen>. Note that dates are stored and generated
1859    in the form of a timestamp number rather than a string.
1860    
1861    =over 4
1862    
1863    =item id
1864    
1865    ID to assign to the new entity.
1866    
1867    =item type
1868    
1869    Type name for the new entity.
1870    
1871    =item values
1872    
1873    Hash containing additional values that might be needed by the data generation methods (optional).
1874    
1875    =back
1876    
1877    =cut
1878    
1879    sub GenerateEntity {
1880        # Get the parameters.
1881        my ($self, $id, $type, $values) = @_;
1882        # Create the return hash.
1883        my $this = { id => $id };
1884        # Get the metadata structure.
1885        my $metadata = $self->{_metaData};
1886        # Get this entity's list of fields.
1887        if (!exists $metadata->{Entities}->{$type}) {
1888            Confess("Unrecognized entity type $type in GenerateEntity.");
1889        } else {
1890            my $entity = $metadata->{Entities}->{$type};
1891            my $fields = $entity->{Fields};
1892            # Generate data from the fields.
1893            _GenerateFields($this, $fields, $type, $values);
1894        }
1895        # Return the hash created.
1896        return $this;
1897    }
1898    
1899    =head3 GetEntity
1900    
1901    C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>
1902    
1903    Return an object describing the entity instance with a specified ID.
1904    
1905    =over 4
1906    
1907    =item entityType
1908    
1909    Entity type name.
1910    
1911    =item ID
1912    
1913    ID of the desired entity.
1914    
1915    =item RETURN
1916    
1917    Returns a B<DBObject> representing the desired entity instance, or an undefined value if no
1918    instance is found with the specified key.
1919    
1920    =back
1921    
1922    =cut
1923    
1924    sub GetEntity {
1925        # Get the parameters.
1926        my ($self, $entityType, $ID) = @_;
1927        # Create a query.
1928        my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);
1929        # Get the first (and only) object.
1930        my $retVal = $query->Fetch();
1931        # Return the result.
1932        return $retVal;
1933    }
1934    
1935    =head3 GetEntityValues
1936    
1937    C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>
1938    
1939    Return a list of values from a specified entity instance.
1940    
1941    =over 4
1942    
1943    =item entityType
1944    
1945    Entity type name.
1946    
1947    =item ID
1948    
1949    ID of the desired entity.
1950    
1951    =item fields
1952    
1953    List of field names, each of the form I<objectName>C<(>I<fieldName>C<)>.
1954    
1955    =item RETURN
1956    
1957    Returns a flattened list of the values of the specified fields for the specified entity.
1958    
1959    =back
1960    
1961    =cut
1962    
1963    sub GetEntityValues {
1964        # Get the parameters.
1965        my ($self, $entityType, $ID, $fields) = @_;
1966        # Get the specified entity.
1967        my $entity = $self->GetEntity($entityType, $ID);
1968        # Declare the return list.
1969        my @retVal = ();
1970        # If we found the entity, push the values into the return list.
1971        if ($entity) {
1972            push @retVal, $entity->Values($fields);
1973        }
1974        # Return the result.
1975        return @retVal;
1976    }
1977    
1978    =head3 GetAll
1979    
1980    C<< my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>
1981    
1982    Return a list of values taken from the objects returned by a query. The first three
1983    parameters correspond to the parameters of the L</Get> method. The final parameter is
1984    a list of the fields desired from each record found by the query. The field name
1985    syntax is the standard syntax used for fields in the B<ERDB> system--
1986    B<I<objectName>(I<fieldName>)>-- where I<objectName> is the name of the relevant entity
1987    or relationship and I<fieldName> is the name of the field.
1988    
1989    The list returned will be a list of lists. Each element of the list will contain
1990    the values returned for the fields specified in the fourth parameter. If one of the
1991    fields specified returns multiple values, they are flattened in with the rest. For
1992    example, the following call will return a list of the features in a particular
1993    spreadsheet cell, and each feature will be represented by a list containing the
1994    feature ID followed by all of its aliases.
1995    
1996    C<< $query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>
1997    
1998    =over 4
1999    
2000    =item objectNames
2001    
2002    List containing the names of the entity and relationship objects to be retrieved.
2003    
2004    =item filterClause
2005    
2006    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
2007    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
2008    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
2009    parameter list as additional parameters. The fields in a filter clause can come from primary
2010    entity relations, relationship relations, or secondary entity relations; however, all of the
2011    entities and relationships involved must be included in the list of object names.
2012    
2013    =item parameterList
2014    
2015    List of the parameters to be substituted in for the parameters marks in the filter clause.
2016    
2017    =item fields
2018    
2019    List of the fields to be returned in each element of the list returned.
2020    
2021    =item count
2022    
2023    Maximum number of records to return. If omitted or 0, all available records will be returned.
2024    
2025    =item RETURN
2026    
2027    Returns a list of list references. Each element of the return list contains the values for the
2028    fields specified in the B<fields> parameter.
2029    
2030    =back
2031    
2032    =cut
2033    #: Return Type @@;
2034    sub GetAll {
2035        # Get the parameters.
2036        my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
2037        # Translate the parameters from a list reference to a list. If the parameter
2038        # list is a scalar we convert it into a singleton list.
2039        my @parmList = ();
2040        if (ref $parameterList eq "ARRAY") {
2041            Trace("GetAll parm list is an array.") if T(4);
2042            @parmList = @{$parameterList};
2043        } else {
2044            Trace("GetAll parm list is a scalar: $parameterList.") if T(4);
2045            push @parmList, $parameterList;
2046        }
2047        # Insure the counter has a value.
2048        if (!defined $count) {
2049            $count = 0;
2050        }
2051        # Add the row limit to the filter clause.
2052        if ($count > 0) {
2053            $filterClause .= " LIMIT $count";
2054        }
2055        # Create the query.
2056        my $query = $self->Get($objectNames, $filterClause, \@parmList);
2057        # Set up a counter of the number of records read.
2058        my $fetched = 0;
2059        # Loop through the records returned, extracting the fields. Note that if the
2060        # counter is non-zero, we stop when the number of records read hits the count.
2061        my @retVal = ();
2062        while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {
2063            my @rowData = $row->Values($fields);
2064            push @retVal, \@rowData;
2065            $fetched++;
2066        }
2067        Trace("$fetched rows returned in GetAll.") if T(SQL => 4);
2068        # Return the resulting list.
2069        return @retVal;
2070    }
2071    
2072    =head3 Exists
2073    
2074    C<< my $found = $sprout->Exists($entityName, $entityID); >>
2075    
2076    Return TRUE if an entity exists, else FALSE.
2077    
2078    =over 4
2079    
2080    =item entityName
2081    
2082    Name of the entity type (e.g. C<Feature>) relevant to the existence check.
2083    
2084    =item entityID
2085    
2086    ID of the entity instance whose existence is to be checked.
2087    
2088    =item RETURN
2089    
2090    Returns TRUE if the entity instance exists, else FALSE.
2091    
2092    =back
2093    
2094    =cut
2095    #: Return Type $;
2096    sub Exists {
2097        # Get the parameters.
2098        my ($self, $entityName, $entityID) = @_;
2099        # Check for the entity instance.
2100        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
2101        my $testInstance = $self->GetEntity($entityName, $entityID);
2102        # Return an existence indicator.
2103        my $retVal = ($testInstance ? 1 : 0);
2104        return $retVal;
2105    }
2106    
2107    =head3 EstimateRowSize
2108    
2109    C<< my $rowSize = $erdb->EstimateRowSize($relName); >>
2110    
2111    Estimate the row size of the specified relation. The estimated row size is computed by adding
2112    up the average length for each data type.
2113    
2114    =over 4
2115    
2116    =item relName
2117    
2118    Name of the relation whose estimated row size is desired.
2119    
2120    =item RETURN
2121    
2122    Returns an estimate of the row size for the specified relation.
2123    
2124    =back
2125    
2126    =cut
2127    #: Return Type $;
2128    sub EstimateRowSize {
2129        # Get the parameters.
2130        my ($self, $relName) = @_;
2131        # Declare the return variable.
2132        my $retVal = 0;
2133        # Find the relation descriptor.
2134        my $relation = $self->_FindRelation($relName);
2135        # Get the list of fields.
2136        for my $fieldData (@{$relation->{Fields}}) {
2137            # Get the field type and add its length.
2138            my $fieldLen = $TypeTable{$fieldData->{type}}->{avgLen};
2139            $retVal += $fieldLen;
2140        }
2141        # Return the result.
2142        return $retVal;
2143    }
2144    
2145    =head3 GetFieldTable
2146    
2147    C<< my $fieldHash = $self->GetFieldTable($objectnName); >>
2148    
2149    Get the field structure for a specified entity or relationship.
2150    
2151    =over 4
2152    
2153    =item objectName
2154    
2155    Name of the desired entity or relationship.
2156    
2157    =item RETURN
2158    
2159    The table containing the field descriptors for the specified object.
2160    
2161    =back
2162    
2163    =cut
2164    
2165    sub GetFieldTable {
2166        # Get the parameters.
2167        my ($self, $objectName) = @_;
2168        # Get the descriptor from the metadata.
2169        my $objectData = $self->_GetStructure($objectName);
2170        # Return the object's field table.
2171        return $objectData->{Fields};
2172    }
2173    
2174    =head2 Data Mining Methods
2175    
2176    =head3 GetUsefulCrossValues
2177    
2178    C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>
2179    
2180    Return a list of the useful attributes that would be returned by a B<Cross> call
2181    from an entity of the source entity type through the specified relationship. This
2182    means it will return the fields of the target entity type and the intersection data
2183    fields in the relationship. Only primary table fields are returned. In other words,
2184    the field names returned will be for fields where there is always one and only one
2185    value.
2186    
2187    =over 4
2188    
2189    =item sourceEntity
2190    
2191    Name of the entity from which the relationship crossing will start.
2192    
2193    =item relationship
2194    
2195    Name of the relationship being crossed.
2196    
2197  C<< my $fieldHash = $database->GenerateEntity($id, $type, \%values); >>  =item RETURN
2198    
2199  Generate the data for a new entity instance. This method creates a field hash suitable for  Returns a list of field names in Sprout field format (I<objectName>C<(>I<fieldName>C<)>.
 passing as a parameter to L</InsertObject>. The ID is specified by the callr, but the rest  
 of the fields are generated using information in the database schema.  
2200    
2201  Each data type has a default algorithm for generating random test data. This can be overridden  =back
2202  by including a B<DataGen> element in the field. If this happens, the content of the element is  
2203  executed as a PERL program in the context of this module. The element may make use of a C<$this>  =cut
2204  variable which contains the field hash as it has been built up to the current point. If any  #: Return Type @;
2205  fields are dependent on other fields, the C<pass> attribute can be used to control the order  sub GetUsefulCrossValues {
2206  in which the fields are generated. A field with a high data pass number will be generated after      # Get the parameters.
2207  a field with a lower one. If any external values are needed, they should be passed in via the      my ($self, $sourceEntity, $relationship) = @_;
2208  optional third parameter, which will be available to the data generation script under the name      # Declare the return variable.
2209  C<$value>. Several useful utility methods are provided for generating random values, including      my @retVal = ();
2210  L</IntGen>, L</StringGen>, L</FloatGen>, and L</DateGen>. Note that dates are stored and generated      # Determine the target entity for the relationship. This is whichever entity is not
2211  in the form of a timestamp number rather than a string.      # the source entity. So, if the source entity is the FROM, we'll get the name of
2212        # the TO, and vice versa.
2213        my $relStructure = $self->_GetStructure($relationship);
2214        my $targetEntityType = ($relStructure->{from} eq $sourceEntity ? "to" : "from");
2215        my $targetEntity = $relStructure->{$targetEntityType};
2216        # Get the field table for the entity.
2217        my $entityFields = $self->GetFieldTable($targetEntity);
2218        # The field table is a hash. The hash key is the field name. The hash value is a structure.
2219        # For the entity fields, the key aspect of the target structure is that the {relation} value
2220        # must match the entity name.
2221        my @fieldList = map { "$targetEntity($_)" } grep { $entityFields->{$_}->{relation} eq $targetEntity }
2222                            keys %{$entityFields};
2223        # Push the fields found onto the return variable.
2224        push @retVal, sort @fieldList;
2225        # Get the field table for the relationship.
2226        my $relationshipFields = $self->GetFieldTable($relationship);
2227        # Here we have a different rule. We want all the fields other than "from-link" and "to-link".
2228        # This may end up being an empty set.
2229        my @fieldList2 = map { "$relationship($_)" } grep { $_ ne "from-link" && $_ ne "to-link" }
2230                            keys %{$relationshipFields};
2231        # Push these onto the return list.
2232        push @retVal, sort @fieldList2;
2233        # Return the result.
2234        return @retVal;
2235    }
2236    
2237    =head3 FindColumn
2238    
2239    C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>
2240    
2241    Return the location a desired column in a data mining header line. The data
2242    mining header line is a tab-separated list of column names. The column
2243    identifier is either the numerical index of a column or the actual column
2244    name.
2245    
2246  =over 4  =over 4
2247    
2248  =item id  =item headerLine
2249    
2250  ID to assign to the new entity.  The header line from a data mining command, which consists of a tab-separated
2251    list of column names.
2252    
2253  =item type  =item columnIdentifier
2254    
2255  Type name for the new entity.  Either the ordinal number of the desired column (1-based), or the name of the
2256    desired column.
2257    
2258  =item values  =item RETURN
2259    
2260  Hash containing additional values that might be needed by the data generation methods (optional).  Returns the array index (0-based) of the desired column.
2261    
2262  =back  =back
2263    
2264  =cut  =cut
2265    
2266  sub GenerateEntity {  sub FindColumn {
2267          # Get the parameters.          # Get the parameters.
2268          my ($self, $id, $type, $values) = @_;      my ($headerLine, $columnIdentifier) = @_;
2269          # Create the return hash.      # Declare the return variable.
2270          my $this = { id => $id };      my $retVal;
2271          # Get the metadata structure.      # Split the header line into column names.
2272          my $metadata = $self->{_metaData};      my @headers = ParseColumns($headerLine);
2273          # Get this entity's list of fields.      # Determine whether we have a number or a name.
2274          if (!exists $metadata->{Entities}->{$type}) {      if ($columnIdentifier =~ /^\d+$/) {
2275                  Confess("Unrecognized entity type $type in GenerateEntity.");          # Here we have a number. Subtract 1 and validate the result.
2276            $retVal = $columnIdentifier - 1;
2277            if ($retVal < 0 || $retVal > $#headers) {
2278                Confess("Invalid column identifer \"$columnIdentifier\": value out of range.");
2279            }
2280          } else {          } else {
2281                  my $entity = $metadata->{Entities}->{$type};          # Here we have a name. We need to find it in the list.
2282                  my $fields = $entity->{Fields};          for (my $i = 0; $i <= $#headers && ! defined($retVal); $i++) {
2283                  # Generate data from the fields.              if ($headers[$i] eq $columnIdentifier) {
2284                  _GenerateFields($this, $fields, $type, $values);                  $retVal = $i;
2285          }          }
2286          # Return the hash created.          }
2287          return $this;          if (! defined($retVal)) {
2288                Confess("Invalid column identifier \"$columnIdentifier\": value not found.");
2289            }
2290        }
2291        # Return the result.
2292        return $retVal;
2293  }  }
2294    
2295  =head3 GetEntity  =head3 ParseColumns
2296    
2297  C<< my $entityObject = $sprout->GetEntity($entityType, $ID); >>  C<< my @columns = ERDB::ParseColumns($line); >>
2298    
2299  Return an object describing the entity instance with a specified ID.  Convert the specified data line to a list of columns.
2300    
2301  =over 4  =over 4
2302    
2303  =item entityType  =item line
   
 Entity type name.  
   
 =item ID  
2304    
2305  ID of the desired entity.  A data mining input, consisting of a tab-separated list of columns terminated by a
2306    new-line.
2307    
2308  =item RETURN  =item RETURN
2309    
2310  Returns a B<DBObject> representing the desired entity instance, or an undefined value if no  Returns a list consisting of the column values.
 instance is found with the specified key.  
2311    
2312  =back  =back
2313    
2314  =cut  =cut
2315    
2316  sub GetEntity {  sub ParseColumns {
2317          # Get the parameters.          # Get the parameters.
2318          my ($self, $entityType, $ID) = @_;      my ($line) = @_;
2319          # Create a query.      # Chop off the line-end.
2320          my $query = $self->Get([$entityType], "$entityType(id) = ?", $ID);      chomp $line;
2321          # Get the first (and only) object.      # Split it into a list.
2322          my $retVal = $query->Fetch();      my @retVal = split(/\t/, $line);
2323          # Return the result.          # Return the result.
2324          return $retVal;      return @retVal;
2325  }  }
2326    
2327  =head3 GetEntityValues  =head2 Internal Utility Methods
2328    
2329  C<< my @values = GetEntityValues($entityType, $ID, \@fields); >>  =head3 SetupSQL
2330    
2331  Return a list of values from a specified entity instance.  Process a list of object names and a filter clause so that they can be used to
2332    build an SQL statement. This method takes in a reference to a list of object names
2333    and a filter clause. It will return a corrected filter clause, a list of mapped
2334    names and the mapped name hash.
2335    
2336    This is an instance method.
2337    
2338  =over 4  =over 4
2339    
2340  =item entityType  =item objectNames
2341    
2342  Entity type name.  Reference to a list of the object names to be included in the query.
2343    
2344  =item ID  =item filterClause
2345    
2346  ID of the desired entity.  A string containing the WHERE clause for the query (without the C<WHERE>) and also
2347    optionally the C<ORDER BY> and C<LIMIT> clauses.
2348    
2349  =item fields  =item RETURN
2350    
2351  List of field names, each of the form I<objectName>C<(>I<fieldName>C<)>.  Returns a three-element list. The first element is the SQL statement suffix, beginning
2352    with the FROM clause. The second element is a reference to a list of the names to be
2353    used in retrieving the fields. The third element is a hash mapping the names to the
2354    objects they represent.
2355    
2356    =back
2357    
2358    =cut
2359    
2360    sub _SetupSQL {
2361        my ($self, $objectNames, $filterClause) = @_;
2362        # Adjust the list of object names to account for multiple occurrences of the
2363        # same object. We start with a hash table keyed on object name that will
2364        # return the object suffix. The first time an object is encountered it will
2365        # not be found in the hash. The next time the hash will map the object name
2366        # to 2, then 3, and so forth.
2367        my %objectHash = ();
2368        # This list will contain the object names as they are to appear in the
2369        # FROM list.
2370        my @fromList = ();
2371        # This list contains the suffixed object name for each object. It is exactly
2372        # parallel to the list in the $objectNames parameter.
2373        my @mappedNameList = ();
2374        # Finally, this hash translates from a mapped name to its original object name.
2375        my %mappedNameHash = ();
2376        # Now we create the lists. Note that for every single name we push something into
2377        # @fromList and @mappedNameList. This insures that those two arrays are exactly
2378        # parallel to $objectNames.
2379        for my $objectName (@{$objectNames}) {
2380            # Get the next suffix for this object.
2381            my $suffix = $objectHash{$objectName};
2382            if (! $suffix) {
2383                # Here we are seeing the object for the first time. The object name
2384                # is used as is.
2385                push @mappedNameList, $objectName;
2386                push @fromList, $objectName;
2387                $mappedNameHash{$objectName} = $objectName;
2388                # Denote the next suffix will be 2.
2389                $objectHash{$objectName} = 2;
2390            } else {
2391                # Here we've seen the object before. We construct a new name using
2392                # the suffix from the hash and update the hash.
2393                my $mappedName = "$objectName$suffix";
2394                $objectHash{$objectName} = $suffix + 1;
2395                # The FROM list has the object name followed by the mapped name. This
2396                # tells SQL it's still the same table, but we're using a different name
2397                # for it to avoid confusion.
2398                push @fromList, "$objectName $mappedName";
2399                # The mapped-name list contains the real mapped name.
2400                push @mappedNameList, $mappedName;
2401                # Finally, enable us to get back from the mapped name to the object name.
2402                $mappedNameHash{$mappedName} = $objectName;
2403            }
2404        }
2405        # Begin the SELECT suffix. It starts with
2406        #
2407        # FROM name1, name2, ... nameN
2408        #
2409        my $suffix = "FROM " . join(', ', @fromList);
2410        # Check for a filter clause.
2411        if ($filterClause) {
2412            # Here we have one, so we convert its field names and add it to the query. First,
2413            # We create a copy of the filter string we can work with.
2414            my $filterString = $filterClause;
2415            # Next, we sort the object names by length. This helps protect us from finding
2416            # object names inside other object names when we're doing our search and replace.
2417            my @sortedNames = sort { length($b) - length($a) } @mappedNameList;
2418            # We will also keep a list of conditions to add to the WHERE clause in order to link
2419            # entities and relationships as well as primary relations to secondary ones.
2420            my @joinWhere = ();
2421            # The final preparatory step is to create a hash table of relation names. The
2422            # table begins with the relation names already in the SELECT command. We may
2423            # need to add relations later if there is filtering on a field in a secondary
2424            # relation. The secondary relations are the ones that contain multiply-
2425            # occurring or optional fields.
2426            my %fromNames = map { $_ => 1 } @sortedNames;
2427            # We are ready to begin. We loop through the object names, replacing each
2428            # object name's field references by the corresponding SQL field reference.
2429            # Along the way, if we find a secondary relation, we will need to add it
2430            # to the FROM clause.
2431            for my $mappedName (@sortedNames) {
2432                # Get the length of the object name plus 2. This is the value we add to the
2433                # size of the field name to determine the size of the field reference as a
2434                # whole.
2435                my $nameLength = 2 + length $mappedName;
2436                # Get the real object name for this mapped name.
2437                my $objectName = $mappedNameHash{$mappedName};
2438                Trace("Processing $mappedName for object $objectName.") if T(4);
2439                # Get the object's field list.
2440                my $fieldList = $self->GetFieldTable($objectName);
2441                # Find the field references for this object.
2442                while ($filterString =~ m/$mappedName\(([^)]*)\)/g) {
2443                    # At this point, $1 contains the field name, and the current position
2444                    # is set immediately after the final parenthesis. We pull out the name of
2445                    # the field and the position and length of the field reference as a whole.
2446                    my $fieldName = $1;
2447                    my $len = $nameLength + length $fieldName;
2448                    my $pos = pos($filterString) - $len;
2449                    # Insure the field exists.
2450                    if (!exists $fieldList->{$fieldName}) {
2451                        Confess("Field $fieldName not found for object $objectName.");
2452                    } else {
2453                        Trace("Processing $fieldName at position $pos.") if T(4);
2454                        # Get the field's relation.
2455                        my $relationName = $fieldList->{$fieldName}->{relation};
2456                        # Now we have a secondary relation. We need to insure it matches the
2457                        # mapped name of the primary relation. First we peel off the suffix
2458                        # from the mapped name.
2459                        my $mappingSuffix = substr $mappedName, length($objectName);
2460                        # Put the mapping suffix onto the relation name to get the
2461                        # mapped relation name.
2462                        my $mappedRelationName = "$relationName$mappingSuffix";
2463                        # Insure the relation is in the FROM clause.
2464                        if (!exists $fromNames{$mappedRelationName}) {
2465                            # Add the relation to the FROM clause.
2466                            if ($mappedRelationName eq $relationName) {
2467                                # The name is un-mapped, so we add it without
2468                                # any frills.
2469                                $suffix .= ", $relationName";
2470                                push @joinWhere, "$objectName.id = $relationName.id";
2471                            } else {
2472                                # Here we have a mapping situation.
2473                                $suffix .= ", $relationName $mappedRelationName";
2474                                push @joinWhere, "$mappedRelationName.id = $mappedName.id";
2475                            }
2476                            # Denote we have this relation available for future fields.
2477                            $fromNames{$mappedRelationName} = 1;
2478                        }
2479                        # Form an SQL field reference from the relation name and the field name.
2480                        my $sqlReference = "$mappedRelationName." . _FixName($fieldName);
2481                        # Put it into the filter string in place of the old value.
2482                        substr($filterString, $pos, $len) = $sqlReference;
2483                        # Reposition the search.
2484                        pos $filterString = $pos + length $sqlReference;
2485                    }
2486                }
2487            }
2488            # The next step is to join the objects together. We only need to do this if there
2489            # is more than one object in the object list. We start with the first object and
2490            # run through the objects after it. Note also that we make a safety copy of the
2491            # list before running through it.
2492            my @mappedObjectList = @mappedNameList;
2493            my $lastMappedObject = shift @mappedObjectList;
2494            # Get the join table.
2495            my $joinTable = $self->{_metaData}->{Joins};
2496            # Loop through the object list.
2497            for my $thisMappedObject (@mappedObjectList) {
2498                # Look for a join using the real object names.
2499                my $lastObject = $mappedNameHash{$lastMappedObject};
2500                my $thisObject = $mappedNameHash{$thisMappedObject};
2501                my $joinKey = "$lastObject/$thisObject";
2502                if (!exists $joinTable->{$joinKey}) {
2503                    # Here there's no join, so we throw an error.
2504                    Confess("No join exists to connect from $lastMappedObject to $thisMappedObject.");
2505                } else {
2506                    # Get the join clause.
2507                    my $unMappedJoin = $joinTable->{$joinKey};
2508                    # Fix the names.
2509                    $unMappedJoin =~ s/$lastObject/$lastMappedObject/;
2510                    $unMappedJoin =~ s/$thisObject/$thisMappedObject/;
2511                    push @joinWhere, $unMappedJoin;
2512                    # Save this object as the last object for the next iteration.
2513                    $lastMappedObject = $thisMappedObject;
2514                }
2515            }
2516            # Now we need to handle the whole ORDER BY / LIMIT thing. The important part
2517            # here is we want the filter clause to be empty if there's no WHERE filter.
2518            # We'll put the ORDER BY / LIMIT clauses in the following variable.
2519            my $orderClause = "";
2520            # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy
2521            # operator so that we find the first occurrence of either verb.
2522            if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {
2523                # Here we have an ORDER BY or LIMIT verb. Split it off of the filter string.
2524                my $pos = pos $filterString;
2525                $orderClause = $2 . substr($filterString, $pos);
2526                $filterString = $1;
2527            }
2528            # Add the filter and the join clauses (if any) to the SELECT command.
2529            if ($filterString) {
2530                Trace("Filter string is \"$filterString\".") if T(4);
2531                push @joinWhere, "($filterString)";
2532            }
2533            if (@joinWhere) {
2534                $suffix .= " WHERE " . join(' AND ', @joinWhere);
2535            }
2536            # Add the sort or limit clause (if any) to the SELECT command.
2537            if ($orderClause) {
2538                $suffix .= " $orderClause";
2539            }
2540        }
2541        # Return the suffix, the mapped name list, and the mapped name hash.
2542        return ($suffix, \@mappedNameList, \%mappedNameHash);
2543    }
2544    
2545    =head3 GetStatementHandle
2546    
2547    This method will prepare and execute an SQL query, returning the statement handle.
2548    The main reason for doing this here is so that everybody who does SQL queries gets
2549    the benefit of tracing.
2550    
2551    This is an instance method.
2552    
2553    =over 4
2554    
2555    =item command
2556    
2557    Command to prepare and execute.
2558    
2559    =item params
2560    
2561    Reference to a list of the values to be substituted in for the parameter marks.
2562    
2563  =item RETURN  =item RETURN
2564    
2565  Returns a flattened list of the values of the specified fields for the specified entity.  Returns a prepared and executed statement handle from which the caller can extract
2566    results.
2567    
2568  =back  =back
2569    
2570  =cut  =cut
2571    
2572  sub GetEntityValues {  sub _GetStatementHandle {
2573          # Get the parameters.          # Get the parameters.
2574          my ($self, $entityType, $ID, $fields) = @_;      my ($self, $command, $params) = @_;
2575          # Get the specified entity.      # Trace the query.
2576          my $entity = $self->GetEntity($entityType, $ID);      Trace("SQL query: $command") if T(SQL => 3);
2577          # Declare the return list.      Trace("PARMS: '" . (join "', '", @{$params}) . "'") if (T(SQL => 4) && (@{$params} > 0));
2578          my @retVal = ();      # Get the database handle.
2579          # If we found the entity, push the values into the return list.      my $dbh = $self->{_dbh};
2580          if ($entity) {      # Prepare the command.
2581                  push @retVal, $entity->Values($fields);      my $sth = $dbh->prepare_command($command);
2582          }      # Execute it with the parameters bound in.
2583          # Return the result.      $sth->execute(@{$params}) || Confess("SELECT error" . $sth->errstr());
2584          return @retVal;      # Return the statement handle.
2585        return $sth;
2586  }  }
2587    
 =head2 Internal Utility Methods  
   
2588  =head3 GetLoadStats  =head3 GetLoadStats
2589    
2590  Return a blank statistics object for use by the load methods.  Return a blank statistics object for use by the load methods.
# Line 1290  Line 2594 
2594  =cut  =cut
2595    
2596  sub _GetLoadStats {  sub _GetLoadStats {
2597          return Stats->new('records');      return Stats->new();
2598  }  }
2599    
2600  =head3 GenerateFields  =head3 GenerateFields
# Line 1485  Line 2789 
2789          return $objectData->{Relations};          return $objectData->{Relations};
2790  }  }
2791    
 =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};  
 }  
   
2792  =head3 ValidateFieldNames  =head3 ValidateFieldNames
2793    
2794  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 1654  Line 2929 
2929  sub _LoadMetaData {  sub _LoadMetaData {
2930          # Get the parameters.          # Get the parameters.
2931          my ($filename) = @_;          my ($filename) = @_;
2932        Trace("Reading Sprout DBD from $filename.") if T(2);
2933          # 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
2934          # get the exact structure we want.          # get the exact structure we want.
2935          my $metadata = XML::Simple::XMLin($filename,          my $metadata = XML::Simple::XMLin($filename,
# Line 1681  Line 2957 
2957          for my $entityName (keys %{$entityList}) {          for my $entityName (keys %{$entityList}) {
2958                  my $entityStructure = $entityList->{$entityName};                  my $entityStructure = $entityList->{$entityName};
2959                  #                  #
2960                  # 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,
2961                  # 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,
2962                  # 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>
2963                  # 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 3136 
3136                  my @fromList = ();                  my @fromList = ();
3137                  my @toList = ();                  my @toList = ();
3138                  my @bothList = ();                  my @bothList = ();
3139                  Trace("Join table build for $entityName.") if T(3);          Trace("Join table build for $entityName.") if T(metadata => 4);
3140                  for my $relationshipName (keys %{$relationshipList}) {                  for my $relationshipName (keys %{$relationshipList}) {
3141                          my $relationship = $relationshipList->{$relationshipName};                          my $relationship = $relationshipList->{$relationshipName};
3142                          # 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.
3143                          my $fromEntity = $relationship->{from};                          my $fromEntity = $relationship->{from};
3144                          my $toEntity = $relationship->{to};                          my $toEntity = $relationship->{to};
3145                          Trace("Join check for relationship $relationshipName from $fromEntity to $toEntity.") if T(3);              Trace("Join check for relationship $relationshipName from $fromEntity to $toEntity.") if T(Joins => 4);
3146                          if ($fromEntity eq $entityName) {                          if ($fromEntity eq $entityName) {
3147                                  if ($toEntity eq $entityName) {                                  if ($toEntity eq $entityName) {
3148                                          # Here the relationship is recursive.                                          # Here the relationship is recursive.
3149                                          push @bothList, $relationshipName;                                          push @bothList, $relationshipName;
3150                                          Trace("Relationship $relationshipName put in both-list.") if T(3);                      Trace("Relationship $relationshipName put in both-list.") if T(metadata => 4);
3151                                  } else {                                  } else {
3152                                          # Here the relationship comes from the entity.                                          # Here the relationship comes from the entity.
3153                                          push @fromList, $relationshipName;                                          push @fromList, $relationshipName;
3154                                          Trace("Relationship $relationshipName put in from-list.") if T(3);                      Trace("Relationship $relationshipName put in from-list.") if T(metadata => 4);
3155                                  }                                  }
3156                          } elsif ($toEntity eq $entityName) {                          } elsif ($toEntity eq $entityName) {
3157                                  # Here the relationship goes to the entity.                                  # Here the relationship goes to the entity.
3158                                  push @toList, $relationshipName;                                  push @toList, $relationshipName;
3159                                  Trace("Relationship $relationshipName put in to-list.") if T(3);                  Trace("Relationship $relationshipName put in to-list.") if T(metadata => 4);
3160                          }                          }
3161                  }                  }
3162                  # 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 3172 
3172                                  # Create joins between the entity and this relationship.                                  # Create joins between the entity and this relationship.
3173                                  my $linkField = "$relationshipName.${linkType}_link";                                  my $linkField = "$relationshipName.${linkType}_link";
3174                                  my $joinClause = "$entityName.id = $linkField";                                  my $joinClause = "$entityName.id = $linkField";
3175                                  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);
3176                                  $joinTable{"$entityName/$relationshipName"} = $joinClause;                                  $joinTable{"$entityName/$relationshipName"} = $joinClause;
3177                                  $joinTable{"$relationshipName/$entityName"} = $joinClause;                                  $joinTable{"$relationshipName/$entityName"} = $joinClause;
3178                                  # Create joins between this relationship and the other relationships.                                  # Create joins between this relationship and the other relationships.
# Line 1917  Line 3193 
3193                                                          # relationship and itself are prohibited.                                                          # relationship and itself are prohibited.
3194                                                          my $relJoinClause = "$otherName.${otherType}_link = $linkField";                                                          my $relJoinClause = "$otherName.${otherType}_link = $linkField";
3195                                                          $joinTable{$joinKey} = $relJoinClause;                                                          $joinTable{$joinKey} = $relJoinClause;
3196                                                          Trace("Relationship join clause is $relJoinClause for $joinKey.") if T(4);                              Trace("Relationship join clause is $relJoinClause for $joinKey.") if T(metadata => 4);
3197                                                  }                                                  }
3198                                          }                                          }
3199                                  }                                  }
# Line 1926  Line 3202 
3202                                  # relationship can only be ambiguous with another recursive relationship,                                  # relationship can only be ambiguous with another recursive relationship,
3203                                  # and the incoming relationship from the outer loop is never recursive.                                  # and the incoming relationship from the outer loop is never recursive.
3204                                  for my $otherName (@bothList) {                                  for my $otherName (@bothList) {
3205                                          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);
3206                                          # Join from the left.                                          # Join from the left.
3207                                          $joinTable{"$relationshipName/$otherName"} =                                          $joinTable{"$relationshipName/$otherName"} =
3208                                                  "$linkField = $otherName.from_link";                                                  "$linkField = $otherName.from_link";
# Line 1941  Line 3217 
3217                  # 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
3218                  # possible to get the same effect using multiple queries.                  # possible to get the same effect using multiple queries.
3219                  for my $relationshipName (@bothList) {                  for my $relationshipName (@bothList) {
3220                          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);
3221                          # Join to the entity from each direction.                          # Join to the entity from each direction.
3222                          $joinTable{"$entityName/$relationshipName"} =                          $joinTable{"$entityName/$relationshipName"} =
3223                                  "$entityName.id = $relationshipName.from_link";                                  "$entityName.id = $relationshipName.from_link";
# Line 1955  Line 3231 
3231          return $metadata;          return $metadata;
3232  }  }
3233    
3234    =head3 SortNeeded
3235    
3236    C<< my $flag = $erdb->SortNeeded($relationName); >>
3237    
3238    Return TRUE if the specified relation should be sorted during loading to remove duplicate keys,
3239    else FALSE.
3240    
3241    =over 4
3242    
3243    =item relationName
3244    
3245    Name of the relation to be examined.
3246    
3247    =item RETURN
3248    
3249    Returns TRUE if the relation needs a sort, else FALSE.
3250    
3251    =back
3252    
3253    =cut
3254    #: Return Type $;
3255    sub SortNeeded {
3256        # Get the parameters.
3257        my ($self, $relationName) = @_;
3258        # Declare the return variable.
3259        my $retVal = 0;
3260        # Find out if the relation is a primary entity relation.
3261        my $entityTable = $self->{_metaData}->{Entities};
3262        if (exists $entityTable->{$relationName}) {
3263            my $keyType = $entityTable->{$relationName}->{keyType};
3264            Trace("Relation $relationName found in entity table with key type $keyType.") if T(3);
3265            # If the key is not a hash string, we must do the sort.
3266            if ($keyType ne 'hash-string') {
3267                $retVal = 1;
3268            }
3269        }
3270        # Return the result.
3271        return $retVal;
3272    }
3273    
3274  =head3 CreateRelationshipIndex  =head3 CreateRelationshipIndex
3275    
3276  Create an index for a relationship's relation.  Create an index for a relationship's relation.
# Line 1992  Line 3308 
3308          # index descriptor does not exist, it will be created automatically so we can add          # index descriptor does not exist, it will be created automatically so we can add
3309          # the field to it.          # the field to it.
3310          unshift @{$newIndex->{IndexFields}}, $firstField;          unshift @{$newIndex->{IndexFields}}, $firstField;
3311        # If this is a one-to-many relationship, the "To" index is unique.
3312        if ($relationshipStructure->{arity} eq "1M" && $indexKey eq "To") {
3313            $newIndex->{Unique} = 'true';
3314        }
3315          # Add the index to the relation.          # Add the index to the relation.
3316          _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);          _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);
3317  }  }
# Line 2083  Line 3403 
3403                  # Here we have a field list. Loop through its fields.                  # Here we have a field list. Loop through its fields.
3404                  my $fieldStructures = $structure->{Fields};                  my $fieldStructures = $structure->{Fields};
3405                  for my $fieldName (keys %{$fieldStructures}) {                  for my $fieldName (keys %{$fieldStructures}) {
3406                Trace("Processing field $fieldName of $defaultRelationName.") if T(4);
3407                          my $fieldData = $fieldStructures->{$fieldName};                          my $fieldData = $fieldStructures->{$fieldName};
3408                          # Get the field type.                          # Get the field type.
3409                          my $type = $fieldData->{type};                          my $type = $fieldData->{type};

Legend:
Removed from v.1.6  
changed lines
  Added in v.1.55

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3