[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 1.102, Tue Sep 9 21:02:10 2008 UTC
# Line 2  Line 2 
2    
3          use strict;          use strict;
4          use Tracer;          use Tracer;
5          use DBKernel;      use DBrtns;
6          use Data::Dumper;          use Data::Dumper;
7          use XML::Simple;          use XML::Simple;
8          use DBQuery;          use DBQuery;
9          use DBObject;      use ERDBObject;
10          use Stats;          use Stats;
11          use Time::HiRes qw(gettimeofday);          use Time::HiRes qw(gettimeofday);
12        use Digest::MD5 qw(md5_base64);
13        use CGI;
14        use WikiTools;
15    
16  =head1 Entity-Relationship Database Package  =head1 Entity-Relationship Database Package
17    
# Line 32  Line 35 
35  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>).
36  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
37  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
38  (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
39  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
40  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
41    C<FeatureVirulence>.
42    
43  Entities are connected by binary relationships implemented using single relations possessing the  Entities are connected by binary relationships implemented using single relations possessing the
44  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 56  Line 60 
60  B<start-position>, which indicates where in the contig that the sequence begins. This attribute  B<start-position>, which indicates where in the contig that the sequence begins. This attribute
61  is implemented as the C<start_position> field in the C<IsMadeUpOf> relation.  is implemented as the C<start_position> field in the C<IsMadeUpOf> relation.
62    
63  The database itself is described by an XML file using the F<ERDatabase.xsd> schema. In addition to  The database itself is described by an XML file. In addition to all the data required to define
64  all the data required to define the entities, relationships, and attributes, the schema provides  the entities, relationships, and attributes, the schema provides space for notes describing
65  space for notes describing the data and what it means. These notes are used by L</ShowMetaData>  the data and what it means. These notes are used by L</ShowMetaData> to generate documentation
66  to generate documentation for the database.  for the database.
67    
68    Special support is provided for text searching. An entity field can be marked as <em>searchable</em>,
69    in which case it will be used to generate a text search index in which the user searches for words
70    in the field instead of a particular field value.
71    
72  Finally, every entity and relationship object has a flag indicating if it is new or old. The object  Finally, every entity and relationship object has a flag indicating if it is new or old. The object
73  is considered I<old> if it was loaded by the L</LoadTables> method. It is considered I<new> if it  is considered I<old> if it was loaded by the L</LoadTables> method. It is considered I<new> if it
74  was inserted by the L</InsertObject> method.  was inserted by the L</InsertObject> method.
75    
76  To facilitate testing, the ERDB module supports automatic generation of test data. This process  =head2 XML Database Description
77  is described in the L</GenerateEntity> and L</GenerateConnection> methods, though it is not yet  
78  fully implemented.  =head3 Data Types
79    
80    The ERDB system supports the following data types. Note that there are numerous string
81    types depending on the maximum length. Some database packages limit the total number of
82    characters you have in an index key; to insure the database works in all environments,
83    the type of string should be the shortest one possible that supports all the known values.
84    
85    =over 4
86    
87    =item char
88    
89    single ASCII character
90    
91    =item int
92    
93    32-bit signed integer
94    
95    =item counter
96    
97    32-bit unsigned integer
98    
99    =item date
100    
101    64-bit unsigned integer, representing a PERL date/time value
102    
103    =item text
104    
105    long string; Text fields cannot be used in indexes or sorting and do not support the
106    normal syntax of filter clauses, but can be up to a billion character in length
107    
108    =item float
109    
110    double-precision floating-point number
111    
112    =item boolean
113    
114    single-bit numeric value; The value is stored as a 16-bit signed integer (for
115    compatability with certain database packages), but the only values supported are
116    0 and 1.
117    
118    =item id-string
119    
120    variable-length string, maximum 25 characters
121    
122    =item key-string
123    
124    variable-length string, maximum 40 characters
125    
126    =item name-string
127    
128    variable-length string, maximum 80 characters
129    
130    =item medium-string
131    
132    variable-length string, maximum 160 characters
133    
134    =item string
135    
136    variable-length string, maximum 255 characters
137    
138    =item hash-string
139    
140    variable-length string, maximum 22 characters
141    
142    =back
143    
144    The hash-string data type has a special meaning. The actual key passed into the loader will
145    be a string, but it will be digested into a 22-character MD5 code to save space. Although the
146    MD5 algorithm is not perfect, it is extremely unlikely two strings will have the same
147    digest. Therefore, it is presumed the keys will be unique. When the database is actually
148    in use, the hashed keys will be presented rather than the original values. For this reason,
149    they should not be used for entities where the key is meaningful.
150    
151    =head3 Global Tags
152    
153    The entire database definition must be inside a B<Database> tag. The display name of
154    the database is given by the text associated with the B<Title> tag. The display name
155    is only used in the automated documentation. It has no other effect. The entities and
156    relationships are listed inside the B<Entities> and B<Relationships> tags,
157    respectively. None of these tags have attributes.
158    
159        <Database>
160            <Title>... display title here...</Title>
161            <Entities>
162                ... entity definitions here ...
163            </Entities>
164            <Relationships>
165                ... relationship definitions here...
166            </Relationships>
167        </Database>
168    
169    Entities, relationships, indexes, and fields all allow a text tag called B<Notes>.
170    The text inside the B<Notes> tag contains comments that will appear when the database
171    documentation is generated. Within a B<Notes> tag, you may use C<[i]> and C<[/i]> for
172    italics, C<[b]> and C<[/b]> for bold, and C<[p]> for a new paragraph.
173    
174    =head3 Fields
175    
176    Both entities and relationships have fields described by B<Field> tags. A B<Field>
177    tag can have B<Notes> associated with it. The complete set of B<Field> tags for an
178    object mus be inside B<Fields> tags.
179    
180        <Entity ... >
181            <Fields>
182                ... Field tags ...
183            </Fields>
184        </Entity>
185    
186    The attributes for the B<Field> tag are as follows.
187    
188    =over 4
189    
190    =item name
191    
192    Name of the field. The field name should contain only letters, digits, and hyphens (C<->),
193    and the first character should be a letter. Most underlying databases are case-insensitive
194    with the respect to field names, so a best practice is to use lower-case letters only. Finally,
195    the name C<search-relevance> has special meaning for full-text searches and should not be
196    used as a field name.
197    
198    =item type
199    
200    Data type of the field. The legal data types are given above.
201    
202    =item relation
203    
204    Name of the relation containing the field. This should only be specified for entity
205    fields. The ERDB system does not support optional fields or multi-occurring fields
206    in the primary relation of an entity. Instead, they are put into secondary relations.
207    So, for example, in the C<Genome> entity, the C<group-name> field indicates a special
208    grouping used to select a subset of the genomes. A given genome may not be in any
209    groups or may be in multiple groups. Therefore, C<group-name> specifies a relation
210    value. The relation name specified must be a valid table name. By convention, it is
211    usually the entity name followed by a qualifying word (e.g. C<GenomeGroup>). In an
212    entity, the fields without a relation attribute are said to belong to the
213    I<primary relation>. This relation has the same name as the entity itself.
214    
215    =item searchable
216    
217    If specified, then the field is a candidate for full-text searching. A single full-text
218    index will be created for each relation with at least one searchable field in it.
219    For best results, this option should only be used for string or text fields.
220    
221    =item special
222    
223    This attribute allows the subclass to assign special meaning for certain fields.
224    The interpretation is up to the subclass itself. Currently, only entity fields
225    can have this attribute.
226    
227    =back
228    
229    =head3 Indexes
230    
231    An entity can have multiple alternate indexes associated with it. The fields in an
232    index must all be from the same relation. The alternate indexes assist in searching
233    on fields other than the entity ID. A relationship has at least two indexes-- a I<to-index> and a
234    I<from-index> that order the results when crossing the relationship. For
235    example, in the relationship C<HasContig> from C<Genome> to C<Contig>, the
236    from-index would order the contigs of a ganome, and the to-index would order
237    the genomes of a contig. In addition, it can have zero or more alternate
238    indexes. A relationship's index must specify only fields in
239    the relationship.
240    
241    The alternate indexes for an entity or relationship must be listed inside the B<Indexes> tag.
242    The from-index of a relationship is specified using the B<FromIndex> tag; the to-index is
243    specified using the B<ToIndex> tag.
244    
245    Each index can contain a B<Notes> tag. In addition, it will have an B<IndexFields>
246    tag containing the B<IndexField> tags. These specify, in order, the fields used in
247    the index. The attributes of an B<IndexField> tag are as follows.
248    
249    =over 4
250    
251    =item name
252    
253    Name of the field.
254    
255    =item order
256    
257    Sort order of the field-- C<ascending> or C<descending>.
258    
259    =back
260    
261    The B<FromIndex>, and B<ToIndex> tags have no attributes. The B<Index> tag can
262    have a B<Unique> attribute. If specified, the index will be generated as a unique
263    index.
264    
265    =head3 Object and Field Names
266    
267    By convention entity and relationship names use capital casing (e.g. C<Genome> or
268    C<HasRegionsIn>. Most underlying databases, however, are aggressively case-insensitive
269    with respect to relation names, converting them internally to all-upper case or
270    all-lower case.
271    
272    If syntax or parsing errors occur when you try to load or use an ERDB database, the
273    most likely reason is that one of your objects has an SQL reserved word as its name.
274    The list of SQL reserved words keeps increasing; however, most are unlikely to show
275    up as a noun or declarative verb phrase. The exceptions are C<Group>, C<User>,
276    C<Table>, C<Index>, C<Object>, C<Date>, C<Number>, C<Update>, C<Time>, C<Percent>,
277    C<Memo>, C<Order>, and C<Sum>. This problem can crop up in field names as well.
278    
279    Every entity has a field called C<id> that acts as its primary key. Every relationship
280    has fields called C<from-link> and C<to-link> that contain copies of the relevant
281    entity IDs. These are essentially ERDB's reserved words, and should not be used
282    for user-defined field names.
283    
284    =head3 Entities
285    
286    An entity is described by the B<Entity> tag. The entity can contain B<Notes>, an
287    B<Indexes> tag containing one or more secondary indexes, and a B<Fields> tag
288    containing one or more fields. The attributes of the B<Entity> tag are as follows.
289    
290    =over 4
291    
292    =item name
293    
294    Name of the entity. The entity name, by convention, uses capital casing (e.g. C<Genome>
295    or C<GroupBlock>) and should be a noun or noun phrase.
296    
297    =item keyType
298    
299    Data type of the primary key. The primary key is always named C<id>.
300    
301    =back
302    
303    =head3 Relationships
304    
305    A relationship is described by the C<Relationship> tag. Within a relationship,
306    there can be a C<Notes> tag, a C<Fields> tag containing the intersection data
307    fields, a C<FromIndex> tag containing the from-index, a C<ToIndex> tag containing
308    the to-index, and an C<Indexes> tag containing the alternate indexes.
309    
310    The C<Relationship> tag has the following attributes.
311    
312    =over 4
313    
314    =item name
315    
316    Name of the relationship. The relationship name, by convention, uses capital casing
317    (e.g. C<ContainsRegionIn> or C<HasContig>), and should be a declarative verb
318    phrase, designed to fit between the from-entity and the to-entity (e.g.
319    Block C<ContainsRegionIn> Genome).
320    
321    =item from
322    
323    Name of the entity from which the relationship starts.
324    
325    =item to
326    
327    Name of the entity to which the relationship proceeds.
328    
329    =item arity
330    
331    Relationship type: C<1M> for one-to-many and C<MM> for many-to-many.
332    
333    =back
334    
335  =cut  =cut
336    
# Line 75  Line 338 
338    
339  # 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.
340  # "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
341  # of the specified type. "dataGen" is PERL string that will be evaluated if no test data generation  # of the specified type. "avgLen" is the average byte length for estimating
342   #string is specified in the field definition.  # record sizes. "sort" is the key modifier for the sort command, "notes" is a type description,
343  my %TypeTable = ( char =>        { sqlType => 'CHAR(1)',                        maxLen => 1,                    dataGen => "StringGen('A')" },  # and "indexMod", if non-zero, is the number of characters to use when the field is specified in an
344                                    int =>         { sqlType => 'INTEGER',                        maxLen => 20,                   dataGen => "IntGen(0, 99999999)" },  # index
345                                    string =>  { sqlType => 'VARCHAR(255)',               maxLen => 255,                  dataGen => "StringGen(IntGen(10,250))" },  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",
346                                    text =>        { sqlType => 'TEXT',                           maxLen => 1000000000,   dataGen => "StringGen(IntGen(80,1000))" },                                 indexMod =>   0, notes => "single ASCII character"},
347                                    date =>        { sqlType => 'BIGINT',                         maxLen => 80,                   dataGen => "DateGen(-7, 7, IntGen(0,1400))" },                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n",
348                                    float =>       { sqlType => 'DOUBLE PRECISION',       maxLen => 40,                   dataGen => "FloatGen(0.0, 100.0)" },                                 indexMod =>   0, notes => "signed 32-bit integer"},
349                                    boolean => { sqlType => 'SMALLINT',                   maxLen => 1,                    dataGen => "IntGen(0, 1)" },                    counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n",
350                                   indexMod =>   0, notes => "unsigned 32-bit integer"},
351                      string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, sort => "",
352                                   indexMod =>   0, notes => "character string, 0 to 255 characters"},
353                      text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, sort => "",
354                                   indexMod => 255, notes => "character string, nearly unlimited length, only first 255 characters are indexed"},
355                      date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, sort => "n",
356                                   indexMod =>   0, notes => "signed, 64-bit integer"},
357                      float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, sort => "g",
358                                   indexMod =>   0, notes => "64-bit double precision floating-point number"},
359                      boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, sort => "n",
360                                   indexMod =>   0, notes => "boolean value: 0 if false, 1 if true"},
361                     'hash-string' =>
362                                 { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, sort => "",
363                                   indexMod =>   0, notes => "string stored in digested form, used for certain types of key fields"},
364                     'id-string' =>
365                                 { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, sort => "",
366                                   indexMod =>   0, notes => "character string, 0 to 25 characters"},
367                               'key-string' =>                               'key-string' =>
368                                                           { sqlType => 'VARCHAR(40)',            maxLen => 40,                   dataGen => "StringGen(IntGen(10,40))" },                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, sort => "",
369                                   indexMod =>   0, notes => "character string, 0 to 40 characters"},
370                                   'name-string' =>                                   'name-string' =>
371                                                           { sqlType => 'VARCHAR(80)',            maxLen => 80,                   dataGen => "StringGen(IntGen(10,80))" },                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, sort => "",
372                                   indexMod =>   0, notes => "character string, 0 to 80 characters"},
373                                   'medium-string' =>                                   'medium-string' =>
374                                                           { sqlType => 'VARCHAR(160)',           maxLen => 160,                  dataGen => "StringGen(IntGen(10,160))" },                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",
375                                   indexMod =>   0, notes => "character string, 0 to 160 characters"},
376                     'long-string' =>
377                                 { sqlType => 'VARCHAR(500)',       maxLen => 500,          avglen => 255, sort => "",
378                                   indexMod =>   0, notes => "character string, 0 to 500 characters"},
379                                  );                                  );
380    
381  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 98  Line 384 
384                                     'MM' => 'many-to-many'                                     'MM' => 'many-to-many'
385                                   );                                   );
386    
387  # Table for interpreting string patterns.  # Options for XML input and output.
388    
389    my %XmlOptions = (GroupTags =>  { Relationships => 'Relationship',
390                                      Entities => 'Entity',
391                                      Fields => 'Field',
392                                      Indexes => 'Index',
393                                      IndexFields => 'IndexField',
394                                      Issues => 'Issue',
395                                      Shapes => 'Shape'
396                                    },
397                      KeyAttr =>    { Relationship => 'name',
398                                      Entity => 'name',
399                                      Field => 'name',
400                                      Shape => 'name'
401                                    },
402                      SuppressEmpty => 1,
403                     );
404    
405  my %PictureTable = ( 'A' => "abcdefghijklmnopqrstuvwxyz",  my %XmlInOpts  = (
406                                           '9' => "0123456789",                    ForceArray => [qw(Field Index IndexField Relationship Entity Shape)],
407                                           'X' => "abcdefghijklmnopqrstuvwxyz0123456789",                    ForceContent => 1,
408                                           'V' => "aeiou",                    NormalizeSpace => 2,
409                                           'K' => "bcdfghjklmnoprstvwxyz"                   );
410    my %XmlOutOpts = (
411                      RootName => 'Database',
412                      XMLDecl => 1,
413                                     );                                     );
414    
415  =head2 Public Methods  =head2 Public Methods
416    
417  =head3 new  =head3 new
418    
419  C<< my $database = ERDB->new($dbh, $metaFileName); >>      my $database = ERDB->new($dbh, $metaFileName);
420    
421  Create a new ERDB object.  Create a new ERDB object.
422    
# Line 131  Line 436 
436    
437  sub new {  sub new {
438          # Get the parameters.          # Get the parameters.
439          my ($class, $dbh, $metaFileName, $options) = @_;      my ($class, $dbh, $metaFileName, %options) = @_;
440          # Load the meta-data.          # Load the meta-data.
441          my $metaData = _LoadMetaData($metaFileName);          my $metaData = _LoadMetaData($metaFileName);
442          # Create the object.          # Create the object.
# Line 145  Line 450 
450    
451  =head3 ShowMetaData  =head3 ShowMetaData
452    
453  C<< $database->ShowMetaData($fileName); >>      $erdb->ShowMetaData($fileName);
454    
455  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
456  the data to be loaded into the relations.  the data to be loaded into the relations.
# Line 176  Line 481 
481          # Write the HTML heading stuff.          # Write the HTML heading stuff.
482          print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";          print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";
483          print HTMLOUT "</head>\n<body>\n";          print HTMLOUT "</head>\n<body>\n";
484        # Write the documentation.
485        print HTMLOUT $self->DisplayMetaData();
486        # Close the document.
487        print HTMLOUT "</body>\n</html>\n";
488        # Close the file.
489        close HTMLOUT;
490    }
491    
492    =head3 DisplayMetaData
493    
494        my $html = $erdb->DisplayMetaData();
495    
496    Return an HTML description of the database. This description can be used to help users create
497    the data to be loaded into the relations and form queries. The output is raw includable HTML
498    without any HEAD or BODY tags.
499    
500    =over 4
501    
502    =item filename
503    
504    The name of the output file.
505    
506    =back
507    
508    =cut
509    
510    sub DisplayMetaData {
511        # Get the parameters.
512        my ($self) = @_;
513        # Get the metadata and the title string.
514        my $metadata = $self->{_metaData};
515        # Get the title string.
516        my $title = $metadata->{Title};
517        # Get the entity and relationship lists.
518        my $entityList = $metadata->{Entities};
519        my $relationshipList = $metadata->{Relationships};
520        # Declare the return variable.
521        my $retVal = "";
522        # Open the output file.
523        Trace("Building MetaData table of contents.") if T(4);
524          # 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
525          # section contains an ordered list of entity or relationship subsections.          # section contains an ordered list of entity or relationship subsections.
526          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";
527          # Loop through the Entities, displaying a list item for each.          # Loop through the Entities, displaying a list item for each.
528          foreach my $key (sort keys %{$entityList}) {          foreach my $key (sort keys %{$entityList}) {
529                  # Display this item.                  # Display this item.
530                  print HTMLOUT "<li><a href=\"#$key\">$key</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$key</a></li>\n";
531          }          }
532          # Close off the entity section and start the relationship section.          # Close off the entity section and start the relationship section.
533          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";
534          # Loop through the Relationships.          # Loop through the Relationships.
535          foreach my $key (sort keys %{$relationshipList}) {          foreach my $key (sort keys %{$relationshipList}) {
536                  # Display this item.                  # Display this item.
537                  my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});                  my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});
538                  print HTMLOUT "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";
539          }          }
540          # Close off the relationship section and list the join table section.          # Close off the relationship section and list the join table section.
541          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";
542          # Close off the table of contents itself.          # Close off the table of contents itself.
543          print HTMLOUT "</ul>\n";      $retVal .=  "</ul>\n";
544          # 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.
545          print HTMLOUT "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";      $retVal .= "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";
546          # Loop through the entities.          # Loop through the entities.
547          for my $key (sort keys %{$entityList}) {          for my $key (sort keys %{$entityList}) {
548                  Trace("Building MetaData entry for $key entity.") if T(4);                  Trace("Building MetaData entry for $key entity.") if T(4);
549                  # Create the entity header. It contains a bookmark and the entity name.                  # Create the entity header. It contains a bookmark and the entity name.
550                  print HTMLOUT "<a name=\"$key\"></a><h3>$key</h3>\n";          $retVal .= "<a name=\"$key\"></a><h3>$key</h3>\n";
551                  # Get the entity data.                  # Get the entity data.
552                  my $entityData = $entityList->{$key};                  my $entityData = $entityList->{$key};
553                  # If there's descriptive text, display it.                  # If there's descriptive text, display it.
554                  if (my $notes = $entityData->{Notes}) {                  if (my $notes = $entityData->{Notes}) {
555                          print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
556                  }                  }
557                  # Now we want a list of the entity's relationships. First, we set up the relationship subsection.          # See if we need a list of the entity's relationships.
558                  print HTMLOUT "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          my $relCount = keys %{$relationshipList};
559            if ($relCount > 0) {
560                # First, we set up the relationship subsection.
561                $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
562                  # Loop through the relationships.                  # Loop through the relationships.
563                  for my $relationship (sort keys %{$relationshipList}) {                  for my $relationship (sort keys %{$relationshipList}) {
564                          # Get the relationship data.                          # Get the relationship data.
# Line 220  Line 568 
568                                  # Get the relationship sentence and append the arity.                                  # Get the relationship sentence and append the arity.
569                                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);                                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);
570                                  # Display the relationship data.                                  # Display the relationship data.
571                                  print HTMLOUT "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";                      $retVal .= "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";
572                          }                          }
573                  }                  }
574                  # Close off the relationship list.                  # Close off the relationship list.
575                  print HTMLOUT "</ul>\n";              $retVal .= "</ul>\n";
576            }
577                  # Get the entity's relations.                  # Get the entity's relations.
578                  my $relationList = $entityData->{Relations};                  my $relationList = $entityData->{Relations};
579                  # Create a header for the relation subsection.                  # Create a header for the relation subsection.
580                  print HTMLOUT "<h4>Relations for <b>$key</b></h4>\n";          $retVal .= "<h4>Relations for <b>$key</b></h4>\n";
581                  # Loop through the relations, displaying them.                  # Loop through the relations, displaying them.
582                  for my $relation (sort keys %{$relationList}) {                  for my $relation (sort keys %{$relationList}) {
583                          my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});                          my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});
584                          print HTMLOUT $htmlString;              $retVal .= $htmlString;
585                  }                  }
586          }          }
587          # Denote we're starting the relationship section.          # Denote we're starting the relationship section.
588          print HTMLOUT "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";      $retVal .= "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";
589          # Loop through the relationships.          # Loop through the relationships.
590          for my $key (sort keys %{$relationshipList}) {          for my $key (sort keys %{$relationshipList}) {
591                  Trace("Building MetaData entry for $key relationship.") if T(4);                  Trace("Building MetaData entry for $key relationship.") if T(4);
# Line 244  Line 593 
593                  my $relationshipStructure = $relationshipList->{$key};                  my $relationshipStructure = $relationshipList->{$key};
594                  # Create the relationship header.                  # Create the relationship header.
595                  my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);                  my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);
596                  print HTMLOUT "<h3><a name=\"$key\"></a>$headerText</h3>\n";          $retVal .= "<h3><a name=\"$key\"></a>$headerText</h3>\n";
597                  # Get the entity names.                  # Get the entity names.
598                  my $fromEntity = $relationshipStructure->{from};                  my $fromEntity = $relationshipStructure->{from};
599                  my $toEntity = $relationshipStructure->{to};                  my $toEntity = $relationshipStructure->{to};
# Line 254  Line 603 
603                  # since both sentences will say the same thing.                  # since both sentences will say the same thing.
604                  my $arity = $relationshipStructure->{arity};                  my $arity = $relationshipStructure->{arity};
605                  if ($arity eq "11") {                  if ($arity eq "11") {
606                          print HTMLOUT "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";
607                  } else {                  } else {
608                          print HTMLOUT "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";
609                          if ($arity eq "MM" && $fromEntity ne $toEntity) {                          if ($arity eq "MM" && $fromEntity ne $toEntity) {
610                                  print HTMLOUT "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";                  $retVal .= "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";
611                          }                          }
612                  }                  }
613                  print HTMLOUT "</p>\n";          $retVal .= "</p>\n";
614                  # If there are notes on this relationship, display them.                  # If there are notes on this relationship, display them.
615                  if (my $notes = $relationshipStructure->{Notes}) {                  if (my $notes = $relationshipStructure->{Notes}) {
616                          print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
617                  }                  }
618                  # Generate the relationship's relation table.                  # Generate the relationship's relation table.
619                  my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});                  my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
620                  print HTMLOUT $htmlString;          $retVal .= $htmlString;
621          }          }
622          Trace("Building MetaData join table.") if T(4);          Trace("Building MetaData join table.") if T(4);
623          # Denote we're starting the join table.          # Denote we're starting the join table.
624          print HTMLOUT "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";      $retVal .= "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";
625          # Create a table header.          # Create a table header.
626          print HTMLOUT _OpenTable("Join Table", "Source", "Target", "Join Condition");      $retVal .= _OpenTable("Join Table", "Source", "Target", "Join Condition");
627          # Loop through the joins.          # Loop through the joins.
628          my $joinTable = $metadata->{Joins};          my $joinTable = $metadata->{Joins};
629          my @joinKeys = keys %{$joinTable};          my @joinKeys = keys %{$joinTable};
# Line 282  Line 631 
631                  # Separate out the source, the target, and the join clause.                  # Separate out the source, the target, and the join clause.
632                  $joinKey =~ m!^([^/]+)/(.+)$!;                  $joinKey =~ m!^([^/]+)/(.+)$!;
633                  my ($sourceRelation, $targetRelation) = ($1, $2);                  my ($sourceRelation, $targetRelation) = ($1, $2);
634                  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);
635                  my $source = $self->ComputeObjectSentence($sourceRelation);                  my $source = $self->ComputeObjectSentence($sourceRelation);
636                  my $target = $self->ComputeObjectSentence($targetRelation);                  my $target = $self->ComputeObjectSentence($targetRelation);
637                  my $clause = $joinTable->{$joinKey};                  my $clause = $joinTable->{$joinKey};
638                  # Display them in a table row.                  # Display them in a table row.
639                  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";
640          }          }
641          # Close the table.          # Close the table.
642          print HTMLOUT _CloseTable();      $retVal .= _CloseTable();
643          # Close the document.      Trace("Built MetaData HTML.") if T(3);
644          print HTMLOUT "</body>\n</html>\n";      # Return the HTML.
645          # Close the file.      return $retVal;
         close HTMLOUT;  
         Trace("Built MetaData web page.") if T(3);  
646  }  }
647    
648  =head3 DumpMetaData  =head3 DumpMetaData
649    
650  C<< $database->DumpMetaData(); >>      $erdb->DumpMetaData();
651    
652  Return a dump of the metadata structure.  Return a dump of the metadata structure.
653    
# Line 313  Line 660 
660          return Data::Dumper::Dumper($self->{_metaData});          return Data::Dumper::Dumper($self->{_metaData});
661  }  }
662    
663    =head3 GenerateWikiData
664    
665        my @wikiLines = $erdb->GenerateWikiData();
666    
667    Build a description of the database for the wiki. The database will be
668    organized into a single page, with sections for each entity and relationship.
669    The return value is a list of text lines.
670    
671    =cut
672    
673    sub GenerateWikiData {
674        # Get the parameters.
675        my ($self) = @_;
676        # We'll build the wiki text in here.
677        my @retVal = ();
678        # Get the metadata object.
679        my $metadata = $self->{_metaData};
680        # Get the title string. This will become the page name.
681        my $title = $metadata->{Title}->{content};
682        # Get the entity and relationship lists.
683        my $entityList = $metadata->{Entities};
684        my $relationshipList = $metadata->{Relationships};
685        my $shapeList = $metadata->{Shapes};
686        # Start with the introductory text.
687        push @retVal, WikiTools::Heading(2, "Introduction");
688        if (my $notes = $metadata->{Notes}) {
689            push @retVal, WikiNote($notes->{content});
690        }
691        # Generate issue list.
692        if (my $issues = $metadata->{Issues}) {
693            push @retVal, WikiTools::Heading(3, 'Issues');
694            push @retVal, WikiTools::List(map { $_->{content} } @{$issues});
695        }
696        # Start the entity section.
697        push @retVal, WikiTools::Heading(2, "Entities");
698        # Loop through the entities. Note that unlike the situation with HTML, we
699        # don't need to generate the table of contents manually, just the data
700        # itself.
701        for my $key (sort keys %$entityList) {
702            # Create a header for this entity.
703            push @retVal, "", WikiTools::Heading(3, $key);
704            # Get the entity data.
705            my $entityData = $entityList->{$key};
706            # Plant the notes here, if there are any.
707            push @retVal, _ObjectNotes($entityData);
708            # Now we list the entity's relationships (if any). First, we build a list
709            # of the relationships relevant to this entity.
710            my @rels = ();
711            for my $rel (sort keys %$relationshipList) {
712                my $relStructure = $relationshipList->{$rel};
713                if ($relStructure->{from} eq $key || $relStructure->{to} eq $key) {
714                    # Get the relationship sentence.
715                    my $relSentence = _ComputeRelationshipSentence($rel, $relStructure);
716                    # Linkify it.
717                    my $linkedRel = WikiTools::LinkMarkup("#$rel", $rel);
718                    $relSentence =~ s/$rel/$linkedRel/;
719                    push @rels, $relSentence;
720                }
721            }
722            # Add the relationships as a Wiki list.
723            push @retVal, WikiTools::List(@rels);
724            # Get the entity's relations.
725            my $relationList = $entityData->{Relations};
726            # Loop through the relations, displaying them.
727            for my $relation (sort keys %{$relationList}) {
728                my $wikiString = _WikiRelationTable($relation, $relationList->{$relation});
729                push @retVal, $wikiString;
730            }
731        }
732        # Now the entities are documented. Next we do the relationships.
733        push @retVal, WikiTools::Heading(2, "Relationships");
734        for my $key (sort keys %$relationshipList) {
735            my $relationshipData = $relationshipList->{$key};
736            # Create the relationship heading.
737            push @retVal, WikiTools::Heading(3, $key);
738            # Describe the relationship arity. Note there's a bit of trickiness involving recursive
739            # many-to-many relationships. In a normal many-to-many we use two sentences to describe
740            # the arity (one for each direction). This is a bad idea for a recursive relationship,
741            # since both sentences will say the same thing.
742            my $arity = $relationshipData->{arity};
743            my $fromEntity = $relationshipData->{from};
744            my $toEntity = $relationshipData->{to};
745            my @listElements = ();
746            my $boldCode = WikiTools::BoldCode();
747            if ($arity eq "11") {
748                push @listElements, "Each $boldCode$fromEntity$boldCode relates to at most one $boldCode$toEntity$boldCode.";
749            } else {
750                push @listElements, "Each $boldCode$fromEntity$boldCode relates to multiple $boldCode${toEntity}s$boldCode.";
751                if ($arity eq "MM" && $fromEntity ne $toEntity) {
752                    push @listElements, "Each $boldCode$toEntity$boldCode relates to multiple $boldCode${fromEntity}s$boldCode.";
753                }
754            }
755            push @retVal, WikiTools::List(@listElements);
756            # Plant the notes here, if there are any.
757            push @retVal, _ObjectNotes($relationshipData);
758            # Finally, the relationship table.
759            my $wikiString = _WikiRelationTable($key, $relationshipData->{Relations}->{$key});
760            push @retVal, $wikiString;
761        }
762        # Now loop through the miscellaneous shapes.
763        if ($shapeList) {
764            push @retVal, WikiTools::Heading(2, "Miscellaneous");
765            for my $shape (sort keys %$shapeList) {
766                push @retVal, WikiTools::Heading(3, $shape);
767                my $shapeData = $shapeList->{$shape};
768                push @retVal, _ObjectNotes($shapeData);
769            }
770        }
771        # All done. Return the lines.
772        return @retVal;
773    }
774    
775    
776    =head3 CreatePPO
777    
778        ERDB::CreatePPO($erdbXMLFile, $ppoXMLFile);
779    
780    Create a PPO XML file from an ERDB data definition XML file. At the
781    current time, the PPO XML file can be used to create a database with
782    similar functionality. Eventually, the PPO will be able to use the
783    created XML to access the live ERDB database.
784    
785    =over 4
786    
787    =item erdbXMLFile
788    
789    Name of the XML data definition file for the ERDB database. This
790    file must exist.
791    
792    =item ppoXMLFile
793    
794    Output file for the PPO XML definition. If this file exists, it
795    will be overwritten.
796    
797    =back
798    
799    =cut
800    
801    sub CreatePPO {
802        # Get the parameters.
803        my ($erdbXMLFile, $ppoXMLFile) = @_;
804        # First, we want to slurp in the ERDB XML file in its raw form.
805        my $xml = ReadMetaXML($erdbXMLFile);
806        # Create a variable to hold all of the objects in the PPO project.
807        my @objects = ();
808        # Get the relationship hash.
809        my $relationships = $xml->{Relationships};
810        # Loop through the entities.
811        my $entities = $xml->{Entities};
812        for my $entityName (keys %{$entities}) {
813            # Get the entity's data structures.
814            my $entityObject = $entities->{$entityName};
815            # We put the object's fields in here, according to their type.
816            my (@object_refs, @scalars, @indexes, @arrays);
817            # Create the ID field for the entity. We get the key type from the
818            # entity object and compute the corresponding SQL type.
819            my $type = $TypeTable{$entityObject->{keyType}}->{sqlType};
820            push @scalars, { label => 'id', type => $type };
821            # Loop through the entity fields.
822            for my $fieldName ( keys %{$entityObject->{Fields}} ) {
823                # Get the field object.
824                my $fieldObject = $entityObject->{Fields}->{$fieldName};
825                # Convert it to a scalar tag.
826                my $scalar = _CreatePPOField($fieldName, $fieldObject);
827                # If we have a relation, this field is stored in an array.
828                # otherwise, it is a scalar. The array tag has scalars
829                # stored as an XML array. In ERDB, there is only ever one,
830                # but PPO can have more.
831                my $relation = $fieldObject->{relation};
832                if ($relation) {
833                    push @arrays, { scalar => [$scalar] };
834                } else {
835                    push @scalars, $scalar;
836                }
837            }
838            # Loop through the relationships. If this entity is the to-entity
839            # on a relationship of 1M arity, then it is implemented as a PPO
840            # object reference.
841            for my $relationshipName (keys %{$relationships}) {
842                # Get the relationship data.
843                my $relationshipData = $relationships->{$relationshipName};
844                # If we have a from for this entity and an arity of 1M, we
845                # have an object reference.
846                if ($relationshipData->{to} eq $entityName &&
847                    $relationshipData->{arity} eq '1M') {
848                    # Build the object reference tag.
849                    push @object_refs, { label => $relationshipName,
850                                         type => $relationshipData->{from} };
851                }
852            }
853            # Create the indexes.
854            my $indexList = $entityObject->{Indexes};
855            push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
856            # Build the object XML tree.
857            my $object = { label => $entityName,
858                           object_ref => \@object_refs,
859                           scalar => \@scalars,
860                           index => \@indexes,
861                           array => \@arrays
862                          };
863            # Push the object onto the objects list.
864            push @objects, $object;
865        }
866        # Loop through the relationships, searching for MMs. The 1Ms were
867        # already handled by the entity search above.
868        for my $relationshipName (keys %{$relationships}) {
869            # Get this relationship's object.
870            my $relationshipObject = $relationships->{$relationshipName};
871            # Only proceed if it's many-to-many.
872            if ($relationshipObject->{arity} eq 'MM') {
873                # Create the tag lists for the relationship object.
874                my (@object_refs, @scalars, @indexes);
875                # The relationship will be created as an object with object
876                # references for its links to the participating entities.
877                my %links = ( from_link => $relationshipObject->{from},
878                              to_link => $relationshipObject->{to} );
879                for my $link (keys %links) {
880                    # Create an object_ref tag for this piece of the
881                    # relationship (from or to).
882                    my $object_ref = { label => $link,
883                                       type => $links{$link} };
884                    push @object_refs, $object_ref;
885                }
886                # Loop through the intersection data fields, creating scalar tags.
887                # There are no fancy array tags in a relationship.
888                for my $fieldName (keys %{$relationshipObject->{Fields}}) {
889                    my $fieldObject = $relationshipObject->{Fields}->{$fieldName};
890                    push @scalars, _CreatePPOField($fieldName, $fieldObject);
891                }
892                # Finally, the indexes: currently we cannot support the to-index and
893                # from-index in PPO, so we just process the alternate indexes.
894                my $indexList = $relationshipObject->{Indexes};
895                push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
896                # Wrap up all the stuff about this relationship.
897                my $object = { label => $relationshipName,
898                               scalar => \@scalars,
899                               object_ref => \@object_refs,
900                               index => \@indexes
901                             };
902                # Push it into the object list.
903                push @objects, $object;
904            }
905        }
906        # Compute a title.
907        my $title;
908        if ($erdbXMLFile =~ /(\/|^)([^\/]+)DBD\.xml/) {
909            # Here we have a standard file name we can use for a title.
910            $title = $2;
911        } else {
912            # Here the file name is non-standard, so we carve up the
913            # database title.
914            $title = $xml->{Title}->{content};
915            $title =~ s/\s\.,//g;
916        }
917        # Wrap up the XML as a project.
918        my $ppoXML = { project => { label => $title,
919                                    object => \@objects }};
920        # Write out the results.
921        my $ppoString = XML::Simple::XMLout($ppoXML,
922                                            AttrIndent => 1,
923                                            KeepRoot => 1);
924        Tracer::PutFile($ppoXMLFile, [ $ppoString ]);
925    }
926    
927    =head3 FindIndexForEntity
928    
929        my $indexFound = ERDB::FindIndexForEntity($xml, $entityName, $attributeName);
930    
931    This method locates the entry in an entity's index list that begins with the
932    specified attribute name. If the entity has no index list, one will be
933    created. This method works on raw XML, not a live ERDB object.
934    
935    =over 4
936    
937    =item xml
938    
939    The raw XML structure defining the database.
940    
941    =item entityName
942    
943    The name of the relevant entity.
944    
945    =item attributeName
946    
947    The name of the attribute relevant to the search.
948    
949    =item RETURN
950    
951    The numerical index in the index list of the index entry for the specified entity and
952    attribute, or C<undef> if no such index exists.
953    
954    =back
955    
956    =cut
957    
958    sub FindIndexForEntity {
959        # Get the parameters.
960        my ($xml, $entityName, $attributeName) = @_;
961        # Declare the return variable.
962        my $retVal;
963        # Get the named entity.
964        my $entityData = $xml->{Entities}->{$entityName};
965        if (! $entityData) {
966            Confess("Entity $entityName not found in DBD structure.");
967        } else {
968            # Insure it has an index list.
969            if (! exists $entityData->{Indexes}) {
970                $entityData->{Indexes} = [];
971            } else {
972                # Search for the desired index.
973                my $indexList = $entityData->{Indexes};
974                my $n = scalar @{$indexList};
975                Trace("Searching $n indexes in index list for $entityName.") if T(2);
976                # We use an indexed FOR here because we're returning an
977                # index number instead of an object. We do THAT so we can
978                # delete the index from the list if needed.
979                for (my $i = 0; $i < $n && !defined($retVal); $i++) {
980                    my $index = $indexList->[$i];
981                    my $fields = $index->{IndexFields};
982                    # Technically this IF should be safe (that is, we are guaranteed
983                    # the existence of a "$fields->[0]"), because when we load the XML
984                    # we have SuppressEmpty specified.
985                    if ($fields->[0]->{name} eq $attributeName) {
986                        $retVal = $i;
987                    }
988                }
989            }
990        }
991        Trace("Index for $attributeName of $entityName found at position $retVal.") if defined($retVal) && T(3);
992        Trace("Index for $attributeName not found in $entityName.") if !defined($retVal) && T(3);
993        # Return the result.
994        return $retVal;
995    }
996    
997  =head3 CreateTables  =head3 CreateTables
998    
999  C<< $datanase->CreateTables(); >>      $erdb->CreateTables();
1000    
1001  This method creates the tables for the database from the metadata structure loaded by the  This method creates the tables for the database from the metadata structure loaded by the
1002  constructor. It is expected this function will only be used on rare occasions, when the  constructor. It is expected this function will only be used on rare occasions, when the
# Line 327  Line 1008 
1008  sub CreateTables {  sub CreateTables {
1009          # Get the parameters.          # Get the parameters.
1010          my ($self) = @_;          my ($self) = @_;
1011          my $metadata = $self->{_metaData};      # Get the relation names.
1012          my $dbh = $self->{_dbh};      my @relNames = $self->GetTableNames();
1013          # Loop through the entities.      # Loop through the relations.
1014          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}}) {  
1015                          # Create a table for this relation.                          # Create a table for this relation.
1016                          $self->CreateTable($relationName);          $self->CreateTable($relationName, 1);
1017                          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);  
1018          }          }
1019  }  }
1020    
1021  =head3 CreateTable  =head3 CreateTable
1022    
1023  C<< $database->CreateTable($tableName, $indexFlag); >>      $erdb->CreateTable($tableName, $indexFlag, $estimatedRows);
1024    
1025  Create the table for a relation and optionally create its indexes.  Create the table for a relation and optionally create its indexes.
1026    
# Line 363  Line 1030 
1030    
1031  Name of the relation (which will also be the table name).  Name of the relation (which will also be the table name).
1032    
1033  =item $indexFlag  =item indexFlag
1034    
1035  TRUE if the indexes for the relation should be created, else FALSE. If FALSE,  TRUE if the indexes for the relation should be created, else FALSE. If FALSE,
1036  L</CreateIndexes> must be called later to bring the indexes into existence.  L</CreateIndexes> must be called later to bring the indexes into existence.
1037    
1038    =item estimatedRows (optional)
1039    
1040    If specified, the estimated maximum number of rows for the relation. This
1041    information allows the creation of tables using storage engines that are
1042    faster but require size estimates, such as MyISAM.
1043    
1044  =back  =back
1045    
1046  =cut  =cut
1047    
1048  sub CreateTable {  sub CreateTable {
1049          # Get the parameters.          # Get the parameters.
1050          my ($self, $relationName, $indexFlag) = @_;      my ($self, $relationName, $indexFlag, $estimatedRows) = @_;
1051          # Get the database handle.          # Get the database handle.
1052          my $dbh = $self->{_dbh};          my $dbh = $self->{_dbh};
1053          # 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 389  Line 1062 
1062                  # Push the result into the field list.                  # Push the result into the field list.
1063                  push @fieldList, $fieldString;                  push @fieldList, $fieldString;
1064          }          }
         # If this is a root table, add the "new_record" flag. It defaults to 0, so  
         if ($rootFlag) {  
                 push @fieldList, "new_record $TypeTable{boolean}->{sqlType} NOT NULL DEFAULT 0";  
         }  
1065          # Convert the field list into a comma-delimited string.          # Convert the field list into a comma-delimited string.
1066          my $fieldThing = join(', ', @fieldList);          my $fieldThing = join(', ', @fieldList);
1067          # Insure the table is not already there.          # Insure the table is not already there.
1068          $dbh->drop_table(tbl => $relationName);          $dbh->drop_table(tbl => $relationName);
1069          Trace("Table $relationName dropped.") if T(2);          Trace("Table $relationName dropped.") if T(2);
1070        # If there are estimated rows, create an estimate so we can take advantage of
1071        # faster DB technologies.
1072        my $estimation = undef;
1073        if ($estimatedRows) {
1074            $estimation = [$self->EstimateRowSize($relationName), $estimatedRows];
1075            Trace("$estimation->[1] rows of $estimation->[0] bytes each.") if T(3);
1076        }
1077          # Create the table.          # Create the table.
1078          Trace("Creating table $relationName: $fieldThing") if T(2);          Trace("Creating table $relationName: $fieldThing") if T(2);
1079          $dbh->create_table(tbl => $relationName, flds => $fieldThing);      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);
1080          Trace("Relation $relationName created in database.") if T(2);          Trace("Relation $relationName created in database.") if T(2);
1081          # If we want to build the indexes, we do it here.      # If we want to build the indexes, we do it here. Note that the full-text search
1082        # index will not be built until the table has been loaded.
1083          if ($indexFlag) {          if ($indexFlag) {
1084                  $self->CreateIndex($relationName);                  $self->CreateIndex($relationName);
1085          }          }
1086  }  }
1087    
1088    =head3 VerifyFields
1089    
1090        my $count = $erdb->VerifyFields($relName, \@fieldList);
1091    
1092    Run through the list of proposed field values, insuring that all the character fields are
1093    below the maximum length. If any fields are too long, they will be truncated in place.
1094    
1095    =over 4
1096    
1097    =item relName
1098    
1099    Name of the relation for which the specified fields are destined.
1100    
1101    =item fieldList
1102    
1103    Reference to a list, in order, of the fields to be put into the relation.
1104    
1105    =item RETURN
1106    
1107    Returns the number of fields truncated.
1108    
1109    =back
1110    
1111    =cut
1112    
1113    sub VerifyFields {
1114        # Get the parameters.
1115        my ($self, $relName, $fieldList) = @_;
1116        # Initialize the return value.
1117        my $retVal = 0;
1118        # Get the relation definition.
1119        my $relData = $self->_FindRelation($relName);
1120        # Get the list of field descriptors.
1121        my $fieldTypes = $relData->{Fields};
1122        my $fieldCount = scalar @{$fieldTypes};
1123        # Loop through the two lists.
1124        for (my $i = 0; $i < $fieldCount; $i++) {
1125            # Get the type of the current field.
1126            my $fieldType = $fieldTypes->[$i]->{type};
1127            # If it's a character field, verify the length.
1128            if ($fieldType =~ /string/) {
1129                my $maxLen = $TypeTable{$fieldType}->{maxLen};
1130                my $oldString = $fieldList->[$i];
1131                if (length($oldString) > $maxLen) {
1132                    # Here it's too big, so we truncate it.
1133                    Trace("Truncating field $i ($fieldTypes->[$i]->{name}) in relation $relName to $maxLen characters from \"$oldString\".") if T(1);
1134                    $fieldList->[$i] = substr $oldString, 0, $maxLen;
1135                    $retVal++;
1136                }
1137            }
1138        }
1139        # Return the truncation count.
1140        return $retVal;
1141    }
1142    
1143    =head3 DigestFields
1144    
1145        $erdb->DigestFields($relName, $fieldList);
1146    
1147    Digest the strings in the field list that correspond to data type C<hash-string> in the
1148    specified relation.
1149    
1150    =over 4
1151    
1152    =item relName
1153    
1154    Name of the relation to which the fields belong.
1155    
1156    =item fieldList
1157    
1158    List of field contents to be loaded into the relation.
1159    
1160    =back
1161    
1162    =cut
1163    #: Return Type ;
1164    sub DigestFields {
1165        # Get the parameters.
1166        my ($self, $relName, $fieldList) = @_;
1167        # Get the relation definition.
1168        my $relData = $self->_FindRelation($relName);
1169        # Get the list of field descriptors.
1170        my $fieldTypes = $relData->{Fields};
1171        my $fieldCount = scalar @{$fieldTypes};
1172        # Loop through the two lists.
1173        for (my $i = 0; $i < $fieldCount; $i++) {
1174            # Get the type of the current field.
1175            my $fieldType = $fieldTypes->[$i]->{type};
1176            # If it's a hash string, digest it in place.
1177            if ($fieldType eq 'hash-string') {
1178                $fieldList->[$i] = $self->DigestKey($fieldList->[$i]);
1179            }
1180        }
1181    }
1182    
1183    =head3 DigestKey
1184    
1185        my $digested = $erdb->DigestKey($keyValue);
1186    
1187    Return the digested value of a symbolic key. The digested value can then be plugged into a
1188    key-based search into a table with key-type hash-string.
1189    
1190    Currently the digesting process is independent of the database structure, but that may not
1191    always be the case, so this is an instance method instead of a static method.
1192    
1193    =over 4
1194    
1195    =item keyValue
1196    
1197    Key value to digest.
1198    
1199    =item RETURN
1200    
1201    Digested value of the key.
1202    
1203    =back
1204    
1205    =cut
1206    
1207    sub DigestKey {
1208        # Get the parameters.
1209        my ($self, $keyValue) = @_;
1210        # Compute the digest.
1211        my $retVal = md5_base64($keyValue);
1212        # Return the result.
1213        return $retVal;
1214    }
1215    
1216  =head3 CreateIndex  =head3 CreateIndex
1217    
1218  C<< $database->CreateIndex($relationName); >>      $erdb->CreateIndex($relationName);
1219    
1220  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
1221  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.
1222  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
1223  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.
1224    
1225  =cut  =cut
1226    
# Line 431  Line 1236 
1236          for my $indexName (keys %{$indexHash}) {          for my $indexName (keys %{$indexHash}) {
1237                  my $indexData = $indexHash->{$indexName};                  my $indexData = $indexHash->{$indexName};
1238                  # Get the index's field list.                  # Get the index's field list.
1239                  my @fieldList = _FixNames(@{$indexData->{IndexFields}});          my @rawFields = @{$indexData->{IndexFields}};
1240            # Get a hash of the relation's field types.
1241            my %types = map { $_->{name} => $_->{type} } @{$relationData->{Fields}};
1242            # We need to check for text fields so we can append a length limitation for them. To do
1243            # that, we need the relation's field list.
1244            my $relFields = $relationData->{Fields};
1245            for (my $i = 0; $i <= $#rawFields; $i++) {
1246                # Get the field type.
1247                my $field = $rawFields[$i];
1248                my $type = $types{$field};
1249                # Ask if it requires using prefix notation for the index.
1250                my $mod = $TypeTable{$type}->{indexMod};
1251                Trace("Field $field ($i) in $relationName has type $type and indexMod $mod.") if T(3);
1252                if ($mod) {
1253                    # Append the prefix length to the field name,
1254                    $rawFields[$i] .= "($mod)";
1255                }
1256            }
1257            my @fieldList = _FixNames(@rawFields);
1258                  my $flds = join(', ', @fieldList);                  my $flds = join(', ', @fieldList);
1259                  # Get the index's uniqueness flag.                  # Get the index's uniqueness flag.
1260                  my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
1261                  # Create the index.                  # Create the index.
1262                  $dbh->create_index(idx => $indexName, tbl => $relationName, flds => $flds, unique => $unique);          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
1263                                        flds => $flds, kind => $unique);
1264            if ($rv) {
1265                  Trace("Index created: $indexName for $relationName ($flds)") if T(1);                  Trace("Index created: $indexName for $relationName ($flds)") if T(1);
1266            } else {
1267                Confess("Error creating index $indexName for $relationName using ($flds): " . $dbh->error_message());
1268            }
1269        }
1270    }
1271    
1272    =head3 GetSecondaryFields
1273    
1274        my %fieldTuples = $erdb->GetSecondaryFields($entityName);
1275    
1276    This method will return a list of the name and type of each of the secondary
1277    fields for a specified entity. Secondary fields are stored in two-column tables
1278    in addition to the primary entity table. This enables the field to have no value
1279    or to have multiple values.
1280    
1281    =over 4
1282    
1283    =item entityName
1284    
1285    Name of the entity whose secondary fields are desired.
1286    
1287    =item RETURN
1288    
1289    Returns a hash mapping the field names to their field types.
1290    
1291    =back
1292    
1293    =cut
1294    
1295    sub GetSecondaryFields {
1296        # Get the parameters.
1297        my ($self, $entityName) = @_;
1298        # Declare the return variable.
1299        my %retVal = ();
1300        # Look for the entity.
1301        my $table = $self->GetFieldTable($entityName);
1302        # Loop through the fields, pulling out the secondaries.
1303        for my $field (sort keys %{$table}) {
1304            if ($table->{$field}->{relation} ne $entityName) {
1305                # Here we have a secondary field.
1306                $retVal{$field} = $table->{$field}->{type};
1307            }
1308        }
1309        # Return the result.
1310        return %retVal;
1311    }
1312    
1313    =head3 GetFieldRelationName
1314    
1315        my $name = $erdb->GetFieldRelationName($objectName, $fieldName);
1316    
1317    Return the name of the relation containing a specified field.
1318    
1319    =over 4
1320    
1321    =item objectName
1322    
1323    Name of the entity or relationship containing the field.
1324    
1325    =item fieldName
1326    
1327    Name of the relevant field in that entity or relationship.
1328    
1329    =item RETURN
1330    
1331    Returns the name of the database relation containing the field, or C<undef> if
1332    the field does not exist.
1333    
1334    =back
1335    
1336    =cut
1337    
1338    sub GetFieldRelationName {
1339        # Get the parameters.
1340        my ($self, $objectName, $fieldName) = @_;
1341        # Declare the return variable.
1342        my $retVal;
1343        # Get the object field table.
1344        my $table = $self->GetFieldTable($objectName);
1345        # Only proceed if the field exists.
1346        if (exists $table->{$fieldName}) {
1347            # Determine the name of the relation that contains this field.
1348            $retVal = $table->{$fieldName}->{relation};
1349        }
1350        # Return the result.
1351        return $retVal;
1352    }
1353    
1354    =head3 DeleteValue
1355    
1356        my $numDeleted = $erdb->DeleteValue($entityName, $id, $fieldName, $fieldValue);
1357    
1358    Delete secondary field values from the database. This method can be used to delete all
1359    values of a specified field for a particular entity instance, or only a single value.
1360    
1361    Secondary fields are stored in two-column relations separate from an entity's primary
1362    table, and as a result a secondary field can legitimately have no value or multiple
1363    values. Therefore, it makes sense to talk about deleting secondary fields where it
1364    would not make sense for primary fields.
1365    
1366    =over 4
1367    
1368    =item entityName
1369    
1370    Name of the entity from which the fields are to be deleted.
1371    
1372    =item id
1373    
1374    ID of the entity instance to be processed. If the instance is not found, this
1375    method will have no effect. If C<undef> is specified, all values for all of
1376    the entity instances will be deleted.
1377    
1378    =item fieldName
1379    
1380    Name of the field whose values are to be deleted.
1381    
1382    =item fieldValue (optional)
1383    
1384    Value to be deleted. If not specified, then all values of the specified field
1385    will be deleted for the entity instance. If specified, then only the values which
1386    match this parameter will be deleted.
1387    
1388    =item RETURN
1389    
1390    Returns the number of rows deleted.
1391    
1392    =back
1393    
1394    =cut
1395    
1396    sub DeleteValue {
1397        # Get the parameters.
1398        my ($self, $entityName, $id, $fieldName, $fieldValue) = @_;
1399        # Declare the return value.
1400        my $retVal = 0;
1401        # We need to set up an SQL command to do the deletion. First, we
1402        # find the name of the field's relation.
1403        my $table = $self->GetFieldTable($entityName);
1404        my $field = $table->{$fieldName};
1405        my $relation = $field->{relation};
1406        # Make sure this is a secondary field.
1407        if ($relation eq $entityName) {
1408            Confess("Cannot delete values of $fieldName for $entityName.");
1409        } else {
1410            # Set up the SQL command to delete all values.
1411            my $sql = "DELETE FROM $relation";
1412            # Build the filter.
1413            my @filters = ();
1414            my @parms = ();
1415            # Check for a filter by ID.
1416            if (defined $id) {
1417                push @filters, "id = ?";
1418                push @parms, $id;
1419            }
1420            # Check for a filter by value.
1421            if (defined $fieldValue) {
1422                push @filters, "$fieldName = ?";
1423                push @parms, $fieldValue;
1424            }
1425            # Append the filters to the command.
1426            if (@filters) {
1427                $sql .= " WHERE " . join(" AND ", @filters);
1428            }
1429            # Execute the command.
1430            my $dbh = $self->{_dbh};
1431            $retVal = $dbh->SQL($sql, 0, @parms);
1432          }          }
1433        # Return the result.
1434        return $retVal;
1435  }  }
1436    
1437  =head3 LoadTables  =head3 LoadTables
1438    
1439  C<< my $stats = $database->LoadTables($directoryName, $rebuild); >>      my $stats = $erdb->LoadTables($directoryName, $rebuild);
1440    
1441  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
1442  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 1479 
1479          $directoryName =~ s!/\\$!!;          $directoryName =~ s!/\\$!!;
1480          # Declare the return variable.          # Declare the return variable.
1481          my $retVal = Stats->new();          my $retVal = Stats->new();
1482          # Get the metadata structure.      # Get the relation names.
1483          my $metaData = $self->{_metaData};      my @relNames = $self->GetTableNames();
1484          # 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}}) {  
1485                          # Try to load this relation.                          # Try to load this relation.
1486                          my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);                          my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);
1487                          # Accumulate the statistics.                          # Accumulate the statistics.
1488                          $retVal->Accumulate($result);                          $retVal->Accumulate($result);
1489                  }                  }
         }  
         # 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);  
         }  
1490          # Add the duration of the load to the statistical object.          # Add the duration of the load to the statistical object.
1491          $retVal->Add('duration', gettimeofday - $startTime);          $retVal->Add('duration', gettimeofday - $startTime);
1492          # Return the accumulated statistics.          # Return the accumulated statistics.
1493          return $retVal;          return $retVal;
1494  }  }
1495    
1496    
1497  =head3 GetTableNames  =head3 GetTableNames
1498    
1499  C<< my @names = $database->GetTableNames; >>      my @names = $erdb->GetTableNames;
1500    
1501  Return a list of the relations required to implement this database.  Return a list of the relations required to implement this database.
1502    
# Line 530  Line 1513 
1513    
1514  =head3 GetEntityTypes  =head3 GetEntityTypes
1515    
1516  C<< my @names = $database->GetEntityTypes; >>      my @names = $erdb->GetEntityTypes;
1517    
1518  Return a list of the entity type names.  Return a list of the entity type names.
1519    
# Line 545  Line 1528 
1528          return sort keys %{$entityList};          return sort keys %{$entityList};
1529  }  }
1530    
1531    
1532    =head3 GetConnectingRelationships
1533    
1534        my @list = $erdb->GetConnectingRelationships($entityName);
1535    
1536    Return a list of the relationships connected to the specified entity.
1537    
1538    =over 4
1539    
1540    =item entityName
1541    
1542    Entity whose connected relationships are desired.
1543    
1544    =item RETURN
1545    
1546    Returns a list of the relationships that originate from the entity.
1547    If the entity is on the from end, it will return the relationship
1548    name. If the entity is on the to end it will return the converse of
1549    the relationship name.
1550    
1551    =back
1552    
1553    =cut
1554    
1555    sub GetConnectingRelationships {
1556        # Get the parameters.
1557        my ($self, $entityName) = @_;
1558        # Declare the return variable.
1559        my @retVal;
1560        # Get the relationship list.
1561        my $relationships = $self->{_metaData}->{Relationships};
1562        # Find the entity.
1563        my $entity = $self->{_metaData}->{Entities}->{$entityName};
1564        # Only proceed if the entity exists.
1565        if (! defined $entity) {
1566            Trace("Entity $entityName not found.") if T(3);
1567        } else {
1568            # Loop through the relationships.
1569            my @rels = keys %$relationships;
1570            Trace(scalar(@rels) . " relationships found in connection search.") if T(3);
1571            for my $relationshipName (@rels) {
1572                my $relationship = $relationships->{$relationshipName};
1573                if ($relationship->{from} eq $entityName) {
1574                    # Here we have a forward relationship.
1575                    push @retVal, $relationshipName;
1576                } elsif ($relationship->{to} eq $entityName) {
1577                    # Here we have a backward relationship. In this case, the
1578                    # converse relationship name is preferred if it exists.
1579                    my $converse = $relationship->{converse} || $relationshipName;
1580                    push @retVal, $converse;
1581                }
1582            }
1583        }
1584        # Return the result.
1585        return @retVal;
1586    }
1587    
1588    
1589    =head3 GetDataTypes
1590    
1591        my %types = ERDB::GetDataTypes();
1592    
1593    Return a table of ERDB data types. The table returned is a hash of hashes.
1594    The keys of the big hash are the datatypes. Each smaller hash has several
1595    values used to manage the data. The most interesting is the SQL type (key
1596    C<sqlType>) and the descriptive node (key C<notes>).
1597    
1598    Note that changing the values in the smaller hashes will seriously break
1599    things, so this data should be treated as read-only.
1600    
1601    =cut
1602    
1603    sub GetDataTypes {
1604        return %TypeTable;
1605    }
1606    
1607    
1608    =head3 IsEntity
1609    
1610        my $flag = $erdb->IsEntity($entityName);
1611    
1612    Return TRUE if the parameter is an entity name, else FALSE.
1613    
1614    =over 4
1615    
1616    =item entityName
1617    
1618    Object name to be tested.
1619    
1620    =item RETURN
1621    
1622    Returns TRUE if the specified string is an entity name, else FALSE.
1623    
1624    =back
1625    
1626    =cut
1627    
1628    sub IsEntity {
1629        # Get the parameters.
1630        my ($self, $entityName) = @_;
1631        # Test to see if it's an entity.
1632        return exists $self->{_metaData}->{Entities}->{$entityName};
1633    }
1634    
1635  =head3 Get  =head3 Get
1636    
1637  C<< my $query = $database->Get(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>      my $query = $erdb->Get(\@objectNames, $filterClause, \@params);
1638    
1639  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.
1640  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 1642 
1642  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
1643  $genus.  $genus.
1644    
1645  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = ?", $genus); >>      $query = $erdb->Get(['Genome'], "Genome(genus) = ?", [$genus]);
1646    
1647  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
1648  parameter representing the parameter value. It would also be possible to code  parameter representing the parameter value. It would also be possible to code
1649    
1650  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>      $query = $erdb->Get(['Genome'], "Genome(genus) = \'$genus\'");
1651    
1652  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
1653  characters inside the variable C<$genus>.  characters inside the variable C<$genus>.
# Line 572  Line 1659 
1659  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
1660  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,
1661    
1662  C<< $query = $sprout->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", $genus); >>      $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]);
1663    
1664  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
1665  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.
1666  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
1667  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
1668  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  
1669  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,
1670  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.
1671    
1672    If an entity or relationship is mentioned twice, the name for the second occurrence will
1673    be suffixed with C<2>, the third occurrence will be suffixed with C<3>, and so forth. So,
1674    for example, if we have C<['Feature', 'HasContig', 'Contig', 'HasContig']>, then the
1675    B<to-link> field of the first B<HasContig> is specified as C<HasContig(to-link)>, while
1676    the B<to-link> field of the second B<HasContig> is specified as C<HasContig2(to-link)>.
1677    
1678  =over 4  =over 4
1679    
1680  =item objectNames  =item objectNames
# Line 603  Line 1695 
1695  with an ORDER BY clause. For example, the following filter string gets all genomes for a  with an ORDER BY clause. For example, the following filter string gets all genomes for a
1696  particular genus and sorts them by species name.  particular genus and sorts them by species name.
1697    
1698  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>      "Genome(genus) = ? ORDER BY Genome(species)"
1699    
1700    Note that the case is important. Only an uppercase "ORDER BY" with a single space will
1701    be processed. The idea is to make it less likely to find the verb by accident.
1702    
1703  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
1704  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
1705  relation.  relation.
1706    
1707  =item param1, param2, ..., paramN  Finally, you can limit the number of rows returned by adding a LIMIT clause. The LIMIT must
1708    be the last thing in the filter clause, and it contains only the word "LIMIT" followed by
1709    a positive number. So, for example
1710    
1711        "Genome(genus) = ? ORDER BY Genome(species) LIMIT 10"
1712    
1713    will only return the first ten genomes for the specified genus. The ORDER BY clause is not
1714    required. For example, to just get the first 10 genomes in the B<Genome> table, you could
1715    use
1716    
1717  Parameter values to be substituted into the filter clause.      "LIMIT 10"
1718    
1719    =item params
1720    
1721    Reference to a list of parameter values to be substituted into the filter clause.
1722    
1723  =item RETURN  =item RETURN
1724    
# Line 623  Line 1730 
1730    
1731  sub Get {  sub Get {
1732          # Get the parameters.          # Get the parameters.
1733          my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $objectNames, $filterClause, $params) = @_;
1734          # Construct the SELECT statement. The general pattern is      # Process the SQL stuff.
1735          #      my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1736          # SELECT name1.*, name2.*, ... nameN.* FROM name1, name2, ... nameN          $self->_SetupSQL($objectNames, $filterClause);
1737          #      # Create the query.
1738          my $dbh = $self->{_dbh};      my $command = "SELECT " . join(".*, ", @{$mappedNameListRef}) .
1739          my $command = "SELECT DISTINCT " . join('.*, ', @{$objectNames}) . ".* FROM " .          ".* $suffix";
1740                                  join(', ', @{$objectNames});      my $sth = $self->_GetStatementHandle($command, $params);
1741          # Check for a filter clause.      # Now we create the relation map, which enables DBQuery to determine the order, name
1742          if ($filterClause) {      # and mapped name for each object in the query.
1743                  # Here we have one, so we convert its field names and add it to the query. First,      my @relationMap = ();
1744                  # We create a copy of the filter string we can work with.      for my $mappedName (@{$mappedNameListRef}) {
1745                  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;  
1746                  }                  }
1747                  # We are ready to begin. We loop through the object names, replacing each      # Return the statement object.
1748                  # object name's field references by the corresponding SQL field reference.      my $retVal = DBQuery::_new($self, $sth, \@relationMap);
1749                  # 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;  
                                         }  
                                         # Form an SQL field reference from the relation name and the field name.  
                                         my $sqlReference = "$relationName." . _FixName($fieldName);  
                                         # Put it into the filter string in place of the old value.  
                                         substr($filterString, $pos, $len) = $sqlReference;  
                                         # Reposition the search.  
                                         pos $filterString = $pos + length $sqlReference;  
                                 }  
                         }  
                 }  
                 # The next step is to join the objects together. We only need to do this if there  
                 # is more than one object in the object list. We start with the first object and  
                 # run through the objects after it. Note also that we make a safety copy of the  
                 # list before running through it.  
                 my @objectList = @{$objectNames};  
                 my $lastObject = shift @objectList;  
                 # Get the join table.  
                 my $joinTable = $self->{_metaData}->{Joins};  
                 # Loop through the object list.  
                 for my $thisObject (@objectList) {  
                         # Look for a join.  
                         my $joinKey = "$lastObject/$thisObject";  
                         if (!exists $joinTable->{$joinKey}) {  
                                 # Here there's no join, so we throw an error.  
                                 Confess("No join exists to connect from $lastObject to $thisObject.");  
                         } else {  
                                 # Get the join clause and add it to the WHERE list.  
                                 push @joinWhere, $joinTable->{$joinKey};  
                                 # Save this object as the last object for the next iteration.  
                                 $lastObject = $thisObject;  
                         }  
                 }  
                 # Now we need to handle the whole ORDER BY thing. We'll put the order by clause  
                 # in the following variable.  
                 my $orderClause = "";  
                 # Locate the ORDER BY verb (if any).  
                 if ($filterString =~ m/^(.*)ORDER BY/g) {  
                         # Here we have an ORDER BY verb. Split it off of the filter string.  
                         my $pos = pos $filterString;  
                         $orderClause = substr($filterString, $pos);  
                         $filterString = $1;  
                 }  
                 # Add the filter and the join clauses (if any) to the SELECT command.  
                 if ($filterString) {  
                         push @joinWhere, "($filterString)";  
                 }  
                 if (@joinWhere) {  
                         $command .= " WHERE " . join(' AND ', @joinWhere);  
                 }  
                 # Add the sort clause (if any) to the SELECT command.  
                 if ($orderClause) {  
                         $command .= " ORDER BY $orderClause";  
                 }  
         }  
         Trace("SQL query: $command") if T(2);  
         Trace("PARMS: '" . (join "', '", @params) . "'") if (T(3) && (@params > 0));  
         my $sth = $dbh->prepare_command($command);  
         # Execute it with the parameters bound in.  
         $sth->execute(@params) || Confess("SELECT error" . $sth->errstr());  
         # Return the statement object.  
         my $retVal = DBQuery::_new($self, $sth, @{$objectNames});  
         return $retVal;  
1750  }  }
1751    
 =head3 GetList  
1752    
 C<< my @dbObjects = $database->GetList(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  
1753    
1754  Return a list of object descriptors for the specified objects as determined by the  =head3 Search
 specified filter clause.  
1755    
1756  This method is essentially the same as L</Get> except it returns a list of objects rather      my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params);
 that a query object that can be used to get the results one record at a time.  
1757    
1758  =over 4  Perform a full text search with filtering. The search will be against a specified object
1759    in the object name list. That object will get an extra field containing the search
1760    relevance. Note that except for the search expression, the parameters of this method are
1761    the same as those for L</Get> and follow the same rules.
1762    
1763  =over 4  =over 4
1764    
1765    =item searchExpression
1766    
1767    Boolean search expression for the text fields of the target object. The default mode for
1768    a Boolean search expression is OR, but we want the default to be AND, so we will
1769    add a C<+> operator to each word with no other operator before it.
1770    
1771    =item idx
1772    
1773    Index in the I<$objectNames> list of the table to be searched in full-text mode.
1774    
1775  =item objectNames  =item objectNames
1776    
1777  List containing the names of the entity and relationship objects to be retrieved.  List containing the names of the entity and relationship objects to be retrieved.
# Line 773  Line 1786 
1786  or secondary entity relations; however, all of the entities and relationships involved must  or secondary entity relations; however, all of the entities and relationships involved must
1787  be included in the list of object names.  be included in the list of object names.
1788    
1789  The filter clause can also specify a sort order. To do this, simply follow the filter string  =item params
 with an ORDER BY clause. For example, the following filter string gets all genomes for a  
 particular genus and sorts them by species name.  
   
 C<< "Genome(genus) = ? ORDER BY Genome(species)" >>  
1790    
1791  The rules for field references in a sort order are the same as those for field references in the  Reference to a list of parameter values to be substituted into the filter clause.
 filter clause in general; however, odd things may happen if a sort field is from a secondary  
 relation.  
   
 =item param1, param2, ..., paramN  
   
 Parameter values to be substituted into the filter clause.  
1792    
1793  =item RETURN  =item RETURN
1794    
1795  Returns a list of B<DBObject>s that satisfy the query conditions.  Returns a query object for the specified search.
1796    
1797  =back  =back
1798    
1799  =cut  =cut
1800  #: Return Type @%  
1801  sub GetList {  sub Search {
1802      # Get the parameters.      # Get the parameters.
1803      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1804          # Declare the return variable.          # Declare the return variable.
1805          my @retVal = ();      my $retVal;
1806          # Perform the query.      # Create a safety copy of the parameter list. Note we have to be careful to insure
1807          my $query = $self->Get($objectNames, $filterClause, @params);      # a parameter list exists before we copy it.
1808          # Loop through the results.      my @myParams = ();
1809          while (my $object = $query->Fetch) {      if (defined $params) {
1810                  push @retVal, $object;          @myParams = @{$params};
1811        }
1812        # Get the first object's structure so we have access to the searchable fields.
1813        my $object1Name = $objectNames->[$idx];
1814        my $object1Structure = $self->_GetStructure($object1Name);
1815        # Get the field list.
1816        if (! exists $object1Structure->{searchFields}) {
1817            Confess("No searchable index for $object1Name.");
1818        } else {
1819            # Get the field list.
1820            my @fields = @{$object1Structure->{searchFields}};
1821            # Clean the search expression.
1822            my $actualKeywords = $self->CleanKeywords($searchExpression);
1823            # Prefix a "+" to each uncontrolled word. This converts the default
1824            # search mode from OR to AND.
1825            $actualKeywords =~ s/(^|\s)(\w|")/$1\+$2/g;
1826            Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1827            # We need two match expressions, one for the filter clause and one in the
1828            # query itself. Both will use a parameter mark, so we need to push the
1829            # search expression onto the front of the parameter list twice.
1830            unshift @myParams, $actualKeywords, $actualKeywords;
1831            # Build the match expression.
1832            my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
1833            my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
1834            # Process the SQL stuff.
1835            my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1836                $self->_SetupSQL($objectNames, $filterClause, $matchClause);
1837            # Create the query. Note that the match clause is inserted at the front of
1838            # the select fields.
1839            my $command = "SELECT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .
1840                ".* $suffix";
1841            my $sth = $self->_GetStatementHandle($command, \@myParams);
1842            # Now we create the relation map, which enables DBQuery to determine the order, name
1843            # and mapped name for each object in the query.
1844            my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
1845            # Return the statement object.
1846            $retVal = DBQuery::_new($self, $sth, \@relationMap, $object1Name);
1847          }          }
1848      # Return the result.      return $retVal;
     return @retVal;  
1849  }  }
1850    
1851  =head3 ComputeObjectSentence  =head3 GetFlat
1852    
1853  C<< my $sentence = $database->ComputeObjectSentence($objectName); >>      my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field);
1854    
1855  Check an object name, and if it is a relationship convert it to a relationship sentence.  This is a variation of L</GetAll> that asks for only a single field per record and
1856    returns a single flattened list.
1857    
1858  =over 4  =over 4
1859    
1860  =item objectName  =item objectNames
1861    
1862  Name of the entity or relationship.  List containing the names of the entity and relationship objects to be retrieved.
1863    
1864    =item filterClause
1865    
1866    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1867    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
1868    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
1869    parameter list as additional parameters. The fields in a filter clause can come from primary
1870    entity relations, relationship relations, or secondary entity relations; however, all of the
1871    entities and relationships involved must be included in the list of object names.
1872    
1873    =item parameterList
1874    
1875    List of the parameters to be substituted in for the parameters marks in the filter clause.
1876    
1877    =item field
1878    
1879    Name of the field to be used to get the elements of the list returned.
1880    
1881  =item RETURN  =item RETURN
1882    
1883  Returns a string containing the entity name or a relationship sentence.  Returns a list of values.
1884    
1885  =back  =back
1886    
1887  =cut  =cut
1888    #: Return Type @;
1889  sub ComputeObjectSentence {  sub GetFlat {
1890          # Get the parameters.          # Get the parameters.
1891          my ($self, $objectName) = @_;      my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
1892          # Set the default return value.      # Construct the query.
1893          my $retVal = $objectName;      my $query = $self->Get($objectNames, $filterClause, $parameterList);
1894          # Look for the object as a relationship.      # Create the result list.
1895          my $relTable = $self->{_metaData}->{Relationships};      my @retVal = ();
1896          if (exists $relTable->{$objectName}) {      # Loop through the records, adding the field values found to the result list.
1897                  # Get the relationship sentence.      while (my $row = $query->Fetch()) {
1898                  $retVal = _ComputeRelationshipSentence($objectName, $relTable->{$objectName});          push @retVal, $row->Value($field);
1899          }          }
1900          # Return the result.      # Return the list created.
1901          return $retVal;      return @retVal;
1902  }  }
1903    
1904  =head3 DumpRelations  =head3 SpecialFields
1905    
1906  C<< $database->DumpRelations($outputDirectory); >>      my %specials = $erdb->SpecialFields($entityName);
1907    
1908  Write the contents of all the relations to tab-delimited files in the specified directory.  Return a hash mapping special fields in the specified entity to the value of their
1909  Each file will have the same name as the relation dumped, with an extension of DTX.  C<special> attribute. This enables the subclass to get access to the special field
1910    attributes without needed to plumb the internal ERDB data structures.
1911    
1912  =over 4  =over 4
1913    
1914  =item outputDirectory  =item entityName
1915    
1916  Name of the directory into which the relation files should be dumped.  Name of the entity whose special fields are desired.
1917    
1918    =item RETURN
1919    
1920    Returns a hash. The keys of the hash are the special field names, and the values
1921    are the values from each special field's C<special> attribute.
1922    
1923  =back  =back
1924    
1925  =cut  =cut
1926    
1927  sub DumpRelations {  sub SpecialFields {
1928          # Get the parameters.          # Get the parameters.
1929          my ($self, $outputDirectory) = @_;      my ($self, $entityName) = @_;
1930          # Now we need to run through all the relations. First, we loop through the entities.      # Declare the return variable.
1931          my $metaData = $self->{_metaData};      my %retVal = ();
1932          my $entities = $metaData->{Entities};      # Find the entity's data structure.
1933          for my $entityName (keys %{$entities}) {      my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1934                  my $entityStructure = $entities->{$entityName};      # Loop through its fields, adding each special field to the return hash.
1935                  # Get the entity's relations.      my $fieldHash = $entityData->{Fields};
1936                  my $relationList = $entityStructure->{Relations};      for my $fieldName (keys %{$fieldHash}) {
1937                  # Loop through the relations, dumping them.          my $fieldData = $fieldHash->{$fieldName};
1938                  for my $relationName (keys %{$relationList}) {          if (exists $fieldData->{special}) {
1939                          my $relation = $relationList->{$relationName};              $retVal{$fieldName} = $fieldData->{special};
                         $self->_DumpRelation($outputDirectory, $relationName, $relation);  
                 }  
1940          }          }
         # Next, we loop through the relationships.  
         my $relationships = $metaData->{Relationships};  
         for my $relationshipName (keys %{$relationships}) {  
                 my $relationshipStructure = $relationships->{$relationshipName};  
                 # Dump this relationship's relation.  
                 $self->_DumpRelation($outputDirectory, $relationshipName, $relationshipStructure->{Relations}->{$relationshipName});  
1941          }          }
1942        # Return the result.
1943        return %retVal;
1944  }  }
1945    
1946  =head3 InsertObject  =head3 Delete
1947    
1948  C<< my $ok = $database->InsertObject($objectType, \%fieldHash); >>      my $stats = $erdb->Delete($entityName, $objectID, %options);
1949    
1950  Insert an object into the database. The object is defined by a type name and then a hash  Delete an entity instance from the database. The instance is deleted along with all entity and
1951  of field names to values. Field values in the primary relation are represented by scalars.  relationship instances dependent on it. The definition of I<dependence> is recursive.
 (Note that for relationships, the primary relation is the B<only> relation.)  
 Field values for the other relations comprising the entity are always list references. For  
 example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases  
 C<ZP_00210270.1> and C<gi|46206278>.  
1952    
1953  C<< $database->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>  An object is always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many
1954    relationship connected to a dependent entity or if it is the "to" entity connected to a 1-to-many
1955    dependent relationship.
1956    
1957  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and  =over 4
 property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.  
1958    
1959  C<< $database->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>  =item entityName
1960    
1961  =over 4  Name of the entity type for the instance being deleted.
1962    
1963  =item newObjectType  =item objectID
1964    
1965  Type name of the object to insert.  ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),
1966    then it is presumed to by a LIKE pattern.
1967    
1968  =item fieldHash  =item options
1969    
1970  Hash of field names to values.  A hash detailing the options for this delete operation.
1971    
1972  =item RETURN  =item RETURN
1973    
1974  Returns 1 if successful, 0 if an error occurred.  Returns a statistics object indicating how many records of each particular table were
1975    deleted.
1976    
1977  =back  =back
1978    
1979  =cut  The permissible options for this method are as follows.
1980    
1981  sub InsertObject {  =over 4
1982    
1983    =item testMode
1984    
1985    If TRUE, then the delete statements will be traced, but no changes will be made to the database.
1986    
1987    =item keepRoot
1988    
1989    If TRUE, then the entity instances will not be deleted, only the dependent records.
1990    
1991    =back
1992    
1993    =cut
1994    #: Return Type $%;
1995    sub Delete {
1996          # Get the parameters.          # Get the parameters.
1997          my ($self, $newObjectType, $fieldHash) = @_;      my ($self, $entityName, $objectID, %options) = @_;
1998          # Denote that so far we appear successful.      # Declare the return variable.
1999          my $retVal = 1;      my $retVal = Stats->new();
2000          # Get the database handle.      # Get the DBKernel object.
2001          my $dbh = $self->{_dbh};      my $db = $self->{_dbh};
2002          # Get the relation list.      # We're going to generate all the paths branching out from the starting entity. One of
2003          my $relationTable = $self->_GetRelationTable($newObjectType);      # the things we have to be careful about is preventing loops. We'll use a hash to
2004          # Loop through the relations. We'll build insert statements for each one. If a relation is      # determine if we've hit a loop.
2005          # secondary, we may end up generating multiple insert statements. If an error occurs, we      my %alreadyFound = ();
2006          # stop the loop.      # These next lists will serve as our result stack. We start by pushing object lists onto
2007          my @relationList = keys %{$relationTable};      # the stack, and then popping them off to do the deletes. This means the deletes will
2008          for (my $i = 0; $retVal && $i <= $#relationList; $i++) {      # start with the longer paths before getting to the shorter ones. That, in turn, makes
2009                  my $relationName = $relationList[$i];      # sure we don't delete records that might be needed to forge relationships back to the
2010                  my $relationDefinition = $relationTable->{$relationName};      # original item. We have two lists-- one for TO-relationships, and one for
2011                  # Get the relation's fields. For each field we will collect a value in the corresponding      # FROM-relationships and entities.
2012                  # position of the @valueList array. If one of the fields is missing, we will add it to the      my @fromPathList = ();
2013                  # @missing list.      my @toPathList = ();
2014                  my @fieldList = @{$relationDefinition->{Fields}};      # This final list is used to remember what work still needs to be done. We push paths
2015                  my @fieldNameList = ();      # onto the list, then pop them off to extend the paths. We prime it with the starting
2016                  my @valueList = ();      # point. Note that we will work hard to insure that the last item on a path in the
2017                  my @missing = ();      # to-do list is always an entity.
2018                  my $recordCount = 1;      my @todoList = ([$entityName]);
2019                  for my $fieldDescriptor (@fieldList) {      while (@todoList) {
2020                          # Get the field name and save it. Note we need to fix it up so the hyphens          # Get the current path.
2021                          # are converted to underscores.          my $current = pop @todoList;
2022                          my $fieldName = $fieldDescriptor->{name};          # Copy it into a list.
2023                          push @fieldNameList, _FixName($fieldName);          my @stackedPath = @{$current};
2024                          # Look for the named field in the incoming structure. Note that we are looking          # Pull off the last item on the path. It will always be an entity.
2025                          # for the real field name, not the fixed-up one!          my $myEntityName = pop @stackedPath;
2026                          if (exists $fieldHash->{$fieldName}) {          # Add it to the alreadyFound list.
2027                                  # Here we found the field. Stash it in the value list.          $alreadyFound{$myEntityName} = 1;
2028                                  my $value = $fieldHash->{$fieldName};          # Figure out if we need to delete this entity.
2029                                  push @valueList, $value;          if ($myEntityName ne $entityName || ! $options{keepRoot}) {
2030                                  # If the value is a list, we may need to increment the record count.              # Get the entity data.
2031                                  if (ref $value eq "ARRAY") {              my $entityData = $self->_GetStructure($myEntityName);
2032                                          my $thisCount = @{$value};              # Loop through the entity's relations. A DELETE command will be needed for each of them.
2033                                          if ($recordCount == 1) {              my $relations = $entityData->{Relations};
2034                                                  # Here we have our first list, so we save its count.              for my $relation (keys %{$relations}) {
2035                                                  $recordCount = $thisCount;                  my @augmentedList = (@stackedPath, $relation);
2036                                          } elsif ($recordCount != $thisCount) {                  push @fromPathList, \@augmentedList;
                                                 # Here we have a second list, so its length has to match the  
                                                 # previous lists.  
                                                 Trace("Field $value in new $newObjectType object has an invalid list length $thisCount. Expected $recordCount.") if T(0);  
                                                 $retVal = 0;  
2037                                          }                                          }
2038                                  }                                  }
2039            # Now we need to look for relationships connected to this entity.
2040            my $relationshipList = $self->{_metaData}->{Relationships};
2041            for my $relationshipName (keys %{$relationshipList}) {
2042                my $relationship = $relationshipList->{$relationshipName};
2043                # Check the FROM field. We're only interested if it's us.
2044                if ($relationship->{from} eq $myEntityName) {
2045                    # Add the path to this relationship.
2046                    my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
2047                    push @fromPathList, \@augmentedList;
2048                    # Check the arity. If it's MM we're done. If it's 1M
2049                    # and the target hasn't been seen yet, we want to
2050                    # stack the entity for future processing.
2051                    if ($relationship->{arity} eq '1M') {
2052                        my $toEntity = $relationship->{to};
2053                        if (! exists $alreadyFound{$toEntity}) {
2054                            # Here we have a new entity that's dependent on
2055                            # the current entity, so we need to stack it.
2056                            my @stackList = (@augmentedList, $toEntity);
2057                            push @fromPathList, \@stackList;
2058                          } else {                          } else {
2059                                  # Here the field is not present. Flag it as missing.                          Trace("$toEntity ignored because it occurred previously.") if T(4);
                                 push @missing, $fieldName;  
2060                          }                          }
2061                  }                  }
                 # If we are the primary relation, add the new-record flag.  
                 if ($relationName eq $newObjectType) {  
                         push @valueList, 1;  
                         push @fieldNameList, "new_record";  
2062                  }                  }
2063                  # Only proceed if there are no missing fields.              # Now check the TO field. In this case only the relationship needs
2064                  if (@missing > 0) {              # deletion.
2065                          Trace("Relation $relationName for $newObjectType skipped due to missing fields: " .              if ($relationship->{to} eq $myEntityName) {
2066                                  join(' ', @missing)) if T(1);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
2067                  } else {                  push @toPathList, \@augmentedList;
                         # Build the INSERT statement.  
                         my $statement = "INSERT INTO $relationName (" . join (', ', @fieldNameList) .  
                                 ") VALUES (";  
                         # Create a marker list of the proper size and put it in the statement.  
                         my @markers = ();  
                         while (@markers < @fieldNameList) { push @markers, '?'; }  
                         $statement .= join(', ', @markers) . ")";  
                         # We have the insert statement, so prepare it.  
                         my $sth = $dbh->prepare_command($statement);  
                         Trace("Insert statement prepared: $statement") if T(3);  
                         # Now we loop through the values. If a value is scalar, we use it unmodified. If it's  
                         # a list, we use the current element. The values are stored in the @parameterList array.  
                         my $done = 0;  
                         for (my $i = 0; $i < $recordCount; $i++) {  
                                 # Clear the parameter list array.  
                                 my @parameterList = ();  
                                 # Loop through the values.  
                                 for my $value (@valueList) {  
                                         # Check to see if this is a scalar value.  
                                         if (ref $value eq "ARRAY") {  
                                                 # Here we have a list value. Pull the current entry.  
                                                 push @parameterList, $value->[$i];  
                                         } else {  
                                                 # Here we have a scalar value. Use it unmodified.  
                                                 push @parameterList, $value;  
2068                                          }                                          }
2069                                  }                                  }
                                 # Execute the INSERT statement with the specified parameter list.  
                                 $retVal = $sth->execute(@parameterList);  
                                 if (!$retVal) {  
                                         my $errorString = $sth->errstr();  
                                         Trace("Insert error: $errorString.") if T(0);  
2070                                  }                                  }
2071        # Create the first qualifier for the WHERE clause. This selects the
2072        # keys of the primary entity records to be deleted. When we're deleting
2073        # from a dependent table, we construct a join path from the first qualifier
2074        # to the table containing the dependent records to delete.
2075        my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
2076        # We need to make two passes. The first is through the to-list, and
2077        # the second through the from-list. The from-list is second because
2078        # the to-list may need to pass through some of the entities the
2079        # from-list would delete.
2080        my %stackList = ( from_link => \@fromPathList, to_link => \@toPathList );
2081        # Now it's time to do the deletes. We do it in two passes.
2082        for my $keyName ('to_link', 'from_link') {
2083            # Get the list for this key.
2084            my @pathList = @{$stackList{$keyName}};
2085            Trace(scalar(@pathList) . " entries in path list for $keyName.") if T(3);
2086            # Loop through this list.
2087            while (my $path = pop @pathList) {
2088                # Get the table whose rows are to be deleted.
2089                my @pathTables = @{$path};
2090                # Start the DELETE statement. We need to call DBKernel because the
2091                # syntax of a DELETE-USING varies among DBMSs.
2092                my $target = $pathTables[$#pathTables];
2093                my $stmt = $db->SetUsing(@pathTables);
2094                # Now start the WHERE. The first thing is the ID field from the starting table. That
2095                # starting table will either be the entity relation or one of the entity's
2096                # sub-relations.
2097                $stmt .= " WHERE $pathTables[0].id $qualifier";
2098                # Now we run through the remaining entities in the path, connecting them up.
2099                for (my $i = 1; $i <= $#pathTables; $i += 2) {
2100                    # Connect the current relationship to the preceding entity.
2101                    my ($entity, $rel) = @pathTables[$i-1,$i];
2102                    # The style of connection depends on the direction of the relationship.
2103                    $stmt .= " AND $entity.id = $rel.$keyName";
2104                    if ($i + 1 <= $#pathTables) {
2105                        # Here there's a next entity, so connect that to the relationship's
2106                        # to-link.
2107                        my $entity2 = $pathTables[$i+1];
2108                        $stmt .= " AND $rel.to_link = $entity2.id";
2109                    }
2110                }
2111                # Now we have our desired DELETE statement.
2112                if ($options{testMode}) {
2113                    # Here the user wants to trace without executing.
2114                    Trace($stmt) if T(0);
2115                } else {
2116                    # Here we can delete. Note that the SQL method dies with a confession
2117                    # if an error occurs, so we just go ahead and do it.
2118                    Trace("Executing delete from $target using '$objectID'.") if T(3);
2119                    my $rv = $db->SQL($stmt, 0, $objectID);
2120                    # Accumulate the statistics for this delete. The only rows deleted
2121                    # are from the target table, so we use its name to record the
2122                    # statistic.
2123                    $retVal->Add($target, $rv);
2124                          }                          }
2125                  }                  }
2126          }          }
2127          # Return the success indicator.      # Return the result.
2128          return $retVal;          return $retVal;
2129  }  }
2130    
2131  =head3 LoadTable  =head3 Disconnect
2132    
2133  C<< my %results = $database->LoadTable($fileName, $relationName, $truncateFlag); >>      $erdb->Disconnect($relationshipName, $originEntityName, $originEntityID);
2134    
2135  Load data from a tab-delimited file into a specified table, optionally re-creating the table first.  Disconnect an entity instance from all the objects to which it is related. This
2136    will delete each relationship instance that connects to the specified entity.
2137    
2138  =over 4  =over 4
2139    
2140  =item fileName  =item relationshipName
   
 Name of the file from which the table data should be loaded.  
   
 =item relationName  
2141    
2142  Name of the relation to be loaded. This is the same as the table name.  Name of the relationship whose instances are to be deleted.
2143    
2144  =item truncateFlag  =item originEntityName
2145    
2146  TRUE if the table should be dropped and re-created, else FALSE  Name of the entity that is to be disconnected.
2147    
2148  =item RETURN  =item originEntityID
2149    
2150  Returns a statistical object containing the number of records read and a list of the error messages.  ID of the entity that is to be disconnected.
2151    
2152  =back  =back
2153    
2154  =cut  =cut
2155  sub LoadTable {  
2156    sub Disconnect {
2157          # Get the parameters.          # Get the parameters.
2158          my ($self, $fileName, $relationName, $truncateFlag) = @_;      my ($self, $relationshipName, $originEntityName, $originEntityID) = @_;
2159          # Create the statistical return object.      # Get the relationship descriptor.
2160          my $retVal = _GetLoadStats();      my $structure = $self->_GetStructure($relationshipName);
2161          # Trace the fact of the load.      # Insure we have a relationship.
2162          Trace("Loading table $relationName from $fileName") if T(1);      if (! exists $structure->{from}) {
2163            Confess("$relationshipName is not a relationship in the database.");
2164        } else {
2165          # Get the database handle.          # Get the database handle.
2166          my $dbh = $self->{_dbh};          my $dbh = $self->{_dbh};
2167          # Get the relation data.          # We'll set this value to 1 if we find our entity.
2168            my $found = 0;
2169            # Loop through the ends of the relationship.
2170            for my $dir ('from', 'to') {
2171                if ($structure->{$dir} eq $originEntityName) {
2172                    $found = 1;
2173                    # Here we want to delete all relationship instances on this side of the
2174                    # entity instance.
2175                    Trace("Disconnecting in $dir direction with ID \"$originEntityID\".");
2176                    # We do this delete in batches to keep it from dragging down the
2177                    # server.
2178                    my $limitClause = ($FIG_Config::delete_limit ? "LIMIT $FIG_Config::delete_limit" : "");
2179                    my $done = 0;
2180                    while (! $done) {
2181                        # Do the delete.
2182                        my $rows = $dbh->SQL("DELETE FROM $relationshipName WHERE ${dir}_link = ? $limitClause", 0, $originEntityID);
2183                        # See if we're done. We're done if no rows were found or the delete is unlimited.
2184                        $done = ($rows == 0 || ! $limitClause);
2185                    }
2186                }
2187            }
2188            # Insure we found the entity on at least one end.
2189            if (! $found) {
2190                Confess("Entity \"$originEntityName\" does not use $relationshipName.");
2191            }
2192        }
2193    }
2194    
2195    =head3 DeleteRow
2196    
2197        $erdb->DeleteRow($relationshipName, $fromLink, $toLink, \%values);
2198    
2199    Delete a row from a relationship. In most cases, only the from-link and to-link are
2200    needed; however, for relationships with intersection data values can be specified
2201    for the other fields using a hash.
2202    
2203    =over 4
2204    
2205    =item relationshipName
2206    
2207    Name of the relationship from which the row is to be deleted.
2208    
2209    =item fromLink
2210    
2211    ID of the entity instance in the From direction.
2212    
2213    =item toLink
2214    
2215    ID of the entity instance in the To direction.
2216    
2217    =item values
2218    
2219    Reference to a hash of other values to be used for filtering the delete.
2220    
2221    =back
2222    
2223    =cut
2224    
2225    sub DeleteRow {
2226        # Get the parameters.
2227        my ($self, $relationshipName, $fromLink, $toLink, $values) = @_;
2228        # Create a hash of all the filter information.
2229        my %filter = ('from-link' => $fromLink, 'to-link' => $toLink);
2230        if (defined $values) {
2231            for my $key (keys %{$values}) {
2232                $filter{$key} = $values->{$key};
2233            }
2234        }
2235        # Build an SQL statement out of the hash.
2236        my @filters = ();
2237        my @parms = ();
2238        for my $key (keys %filter) {
2239            push @filters, _FixName($key) . " = ?";
2240            push @parms, $filter{$key};
2241        }
2242        Trace("Parms for delete row are " . join(", ", map { "\"$_\"" } @parms) . ".") if T(SQL => 4);
2243        my $command = "DELETE FROM $relationshipName WHERE " .
2244                      join(" AND ", @filters);
2245        # Execute it.
2246        my $dbh = $self->{_dbh};
2247        $dbh->SQL($command, undef, @parms);
2248    }
2249    
2250    =head3 DeleteLike
2251    
2252        my $deleteCount = $erdb->DeleteLike($relName, $filter, \@parms);
2253    
2254    Delete all the relationship rows that satisfy a particular filter condition. Unlike a normal
2255    filter, only fields from the relationship itself can be used.
2256    
2257    =over 4
2258    
2259    =item relName
2260    
2261    Name of the relationship whose records are to be deleted.
2262    
2263    =item filter
2264    
2265    A filter clause (L</Get>-style) for the delete query.
2266    
2267    =item parms
2268    
2269    Reference to a list of parameters for the filter clause.
2270    
2271    =item RETURN
2272    
2273    Returns a count of the number of rows deleted.
2274    
2275    =back
2276    
2277    =cut
2278    
2279    sub DeleteLike {
2280        # Get the parameters.
2281        my ($self, $objectName, $filter, $parms) = @_;
2282        # Declare the return variable.
2283        my $retVal;
2284        # Insure the parms argument is an array reference if the caller left it off.
2285        if (! defined($parms)) {
2286            $parms = [];
2287        }
2288        # Insure we have a relationship. The main reason for this is if we delete an entity
2289        # instance we have to yank out a bunch of other stuff with it.
2290        if ($self->IsEntity($objectName)) {
2291            Confess("Cannot use DeleteLike on $objectName, because it is not a relationship.");
2292        } else {
2293            # Create the SQL command suffix to get the desierd records.
2294            my ($suffix) = $self->_SetupSQL([$objectName], $filter);
2295            # Convert it to a DELETE command.
2296            my $command = "DELETE $suffix";
2297            # Execute the command.
2298            my $dbh = $self->{_dbh};
2299            my $result = $dbh->SQL($command, 0, @{$parms});
2300            # Check the results. Note we convert the "0D0" result to a real zero.
2301            # A failure causes an abnormal termination, so the caller isn't going to
2302            # worry about it.
2303            if (! defined $result) {
2304                Confess("Error deleting from $objectName: " . $dbh->errstr());
2305            } elsif ($result == 0) {
2306                $retVal = 0;
2307            } else {
2308                $retVal = $result;
2309            }
2310        }
2311        # Return the result count.
2312        return $retVal;
2313    }
2314    
2315    =head3 SortNeeded
2316    
2317        my $parms = $erdb->SortNeeded($relationName);
2318    
2319    Return the pipe command for the sort that should be applied to the specified
2320    relation when creating the load file.
2321    
2322    For example, if the load file should be sorted ascending by the first
2323    field, this method would return
2324    
2325        sort -k1 -t"\t"
2326    
2327    If the first field is numeric, the method would return
2328    
2329        sort -k1n -t"\t"
2330    
2331    Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate
2332    keys using a sort.
2333    
2334    =over 4
2335    
2336    =item relationName
2337    
2338    Name of the relation to be examined.
2339    
2340    =item
2341    
2342    Returns the sort command to use for sorting the relation, suitable for piping.
2343    
2344    =back
2345    
2346    =cut
2347    #: Return Type $;
2348    sub SortNeeded {
2349        # Get the parameters.
2350        my ($self, $relationName) = @_;
2351        # Declare a descriptor to hold the names of the key fields.
2352        my @keyNames = ();
2353        # Get the relation structure.
2354        my $relationData = $self->_FindRelation($relationName);
2355        # Find out if the relation is a primary entity relation,
2356        # a relationship relation, or a secondary entity relation.
2357        my $entityTable = $self->{_metaData}->{Entities};
2358        my $relationshipTable = $self->{_metaData}->{Relationships};
2359        if (exists $entityTable->{$relationName}) {
2360            # Here we have a primary entity relation.
2361            push @keyNames, "id";
2362        } elsif (exists $relationshipTable->{$relationName}) {
2363            # Here we have a relationship. We sort using the FROM index.
2364            my $relationshipData = $relationshipTable->{$relationName};
2365            my $index = $relationData->{Indexes}->{idxFrom};
2366            push @keyNames, @{$index->{IndexFields}};
2367        } else {
2368            # Here we have a secondary entity relation, so we have a sort on the ID field.
2369            push @keyNames, "id";
2370        }
2371        # Now we parse the key names into sort parameters. First, we prime the return
2372        # string.
2373        my $retVal = "sort -S 1G -T\"$FIG_Config::temp\" -t\"\t\" ";
2374        # Get the relation's field list.
2375        my @fields = @{$relationData->{Fields}};
2376        # Loop through the keys.
2377        for my $keyData (@keyNames) {
2378            # Get the key and the ordering.
2379            my ($keyName, $ordering);
2380            if ($keyData =~ /^([^ ]+) DESC/) {
2381                ($keyName, $ordering) = ($1, "descending");
2382            } else {
2383                ($keyName, $ordering) = ($keyData, "ascending");
2384            }
2385            # Find the key's position and type.
2386            my $fieldSpec;
2387            for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {
2388                my $thisField = $fields[$i];
2389                if ($thisField->{name} eq $keyName) {
2390                    # Get the sort modifier for this field type. The modifier
2391                    # decides whether we're using a character, numeric, or
2392                    # floating-point sort.
2393                    my $modifier = $TypeTable{$thisField->{type}}->{sort};
2394                    # If the index is descending for this field, denote we want
2395                    # to reverse the sort order on this field.
2396                    if ($ordering eq 'descending') {
2397                        $modifier .= "r";
2398                    }
2399                    # Store the position and modifier into the field spec, which
2400                    # will stop the inner loop. Note that the field number is
2401                    # 1-based in the sort command, so we have to increment the
2402                    # index.
2403                    my $realI = $i + 1;
2404                    $fieldSpec = "$realI,$realI$modifier";
2405                }
2406            }
2407            # Add this field to the sort command.
2408            $retVal .= " -k$fieldSpec";
2409        }
2410        # Return the result.
2411        return $retVal;
2412    }
2413    
2414    =head3 GetList
2415    
2416        my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params);
2417    
2418    Return a list of object descriptors for the specified objects as determined by the
2419    specified filter clause.
2420    
2421    This method is essentially the same as L</Get> except it returns a list of objects rather
2422    than a query object that can be used to get the results one record at a time.
2423    
2424    =over 4
2425    
2426    =item objectNames
2427    
2428    List containing the names of the entity and relationship objects to be retrieved.
2429    
2430    =item filterClause
2431    
2432    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
2433    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
2434    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
2435    in the filter clause should be added to the parameter list as additional parameters. The
2436    fields in a filter clause can come from primary entity relations, relationship relations,
2437    or secondary entity relations; however, all of the entities and relationships involved must
2438    be included in the list of object names.
2439    
2440    The filter clause can also specify a sort order. To do this, simply follow the filter string
2441    with an ORDER BY clause. For example, the following filter string gets all genomes for a
2442    particular genus and sorts them by species name.
2443    
2444        "Genome(genus) = ? ORDER BY Genome(species)"
2445    
2446    The rules for field references in a sort order are the same as those for field references in the
2447    filter clause in general; however, odd things may happen if a sort field is from a secondary
2448    relation.
2449    
2450    =item params
2451    
2452    Reference to a list of parameter values to be substituted into the filter clause.
2453    
2454    =item RETURN
2455    
2456    Returns a list of B<ERDBObject>s that satisfy the query conditions.
2457    
2458    =back
2459    
2460    =cut
2461    #: Return Type @%
2462    sub GetList {
2463        # Get the parameters.
2464        my ($self, $objectNames, $filterClause, $params) = @_;
2465        # Declare the return variable.
2466        my @retVal = ();
2467        # Perform the query.
2468        my $query = $self->Get($objectNames, $filterClause, $params);
2469        # Loop through the results.
2470        while (my $object = $query->Fetch) {
2471            push @retVal, $object;
2472        }
2473        # Return the result.
2474        return @retVal;
2475    }
2476    
2477    =head3 GetCount
2478    
2479        my $count = $erdb->GetCount(\@objectNames, $filter, \@params);
2480    
2481    Return the number of rows found by a specified query. This method would
2482    normally be used to count the records in a single table. For example, in a
2483    genetics database
2484    
2485        my $count = $erdb->GetCount(['Genome'], 'Genome(genus-species) LIKE ?', ['homo %']);
2486    
2487    would return the number of genomes for the genus I<homo>. It is conceivable, however,
2488    to use it to return records based on a join. For example,
2489    
2490        my $count = $erdb->GetCount(['HasFeature', 'Genome'], 'Genome(genus-species) LIKE ?',
2491                                    ['homo %']);
2492    
2493    would return the number of features for genomes in the genus I<homo>. Note that
2494    only the rows from the first table are counted. If the above command were
2495    
2496        my $count = $erdb->GetCount(['Genome', 'Feature'], 'Genome(genus-species) LIKE ?',
2497                                    ['homo %']);
2498    
2499    it would return the number of genomes, not the number of genome/feature pairs.
2500    
2501    =over 4
2502    
2503    =item objectNames
2504    
2505    Reference to a list of the objects (entities and relationships) included in the
2506    query.
2507    
2508    =item filter
2509    
2510    A filter clause for restricting the query. The rules are the same as for the L</Get>
2511    method.
2512    
2513    =item params
2514    
2515    Reference to a list of the parameter values to be substituted for the parameter marks
2516    in the filter.
2517    
2518    =item RETURN
2519    
2520    Returns a count of the number of records in the first table that would satisfy
2521    the query.
2522    
2523    =back
2524    
2525    =cut
2526    
2527    sub GetCount {
2528        # Get the parameters.
2529        my ($self, $objectNames, $filter, $params) = @_;
2530        # Insure the params argument is an array reference if the caller left it off.
2531        if (! defined($params)) {
2532            $params = [];
2533        }
2534        # Declare the return variable.
2535        my $retVal;
2536        # Find out if we're counting an entity or a relationship.
2537        my $countedField;
2538        if ($self->IsEntity($objectNames->[0])) {
2539            $countedField = "id";
2540        } else {
2541            # For a relationship we count the to-link because it's usually more
2542            # numerous. Note we're automatically converting to the SQL form
2543            # of the field name (to_link vs. to-link).
2544            $countedField = "to_link";
2545        }
2546        # Create the SQL command suffix to get the desired records.
2547        my ($suffix, $mappedNameListRef, $mappedNameHashRef) = $self->_SetupSQL($objectNames,
2548                                                                                $filter);
2549        # Prefix it with text telling it we want a record count.
2550        my $firstObject = $mappedNameListRef->[0];
2551        my $command = "SELECT COUNT($firstObject.$countedField) $suffix";
2552        # Prepare and execute the command.
2553        my $sth = $self->_GetStatementHandle($command, $params);
2554        # Get the count value.
2555        ($retVal) = $sth->fetchrow_array();
2556        # Check for a problem.
2557        if (! defined($retVal)) {
2558            if ($sth->err) {
2559                # Here we had an SQL error.
2560                Confess("Error retrieving row count: " . $sth->errstr());
2561            } else {
2562                # Here we have no result.
2563                Confess("No result attempting to retrieve row count.");
2564            }
2565        }
2566        # Return the result.
2567        return $retVal;
2568    }
2569    
2570    =head3 ComputeObjectSentence
2571    
2572        my $sentence = $erdb->ComputeObjectSentence($objectName);
2573    
2574    Check an object name, and if it is a relationship convert it to a relationship sentence.
2575    
2576    =over 4
2577    
2578    =item objectName
2579    
2580    Name of the entity or relationship.
2581    
2582    =item RETURN
2583    
2584    Returns a string containing the entity name or a relationship sentence.
2585    
2586    =back
2587    
2588    =cut
2589    
2590    sub ComputeObjectSentence {
2591        # Get the parameters.
2592        my ($self, $objectName) = @_;
2593        # Set the default return value.
2594        my $retVal = $objectName;
2595        # Look for the object as a relationship.
2596        my $relTable = $self->{_metaData}->{Relationships};
2597        if (exists $relTable->{$objectName}) {
2598            # Get the relationship sentence.
2599            $retVal = _ComputeRelationshipSentence($objectName, $relTable->{$objectName});
2600        }
2601        # Return the result.
2602        return $retVal;
2603    }
2604    
2605    =head3 DumpRelations
2606    
2607        $erdb->DumpRelations($outputDirectory);
2608    
2609    Write the contents of all the relations to tab-delimited files in the specified directory.
2610    Each file will have the same name as the relation dumped, with an extension of DTX.
2611    
2612    =over 4
2613    
2614    =item outputDirectory
2615    
2616    Name of the directory into which the relation files should be dumped.
2617    
2618    =back
2619    
2620    =cut
2621    
2622    sub DumpRelations {
2623        # Get the parameters.
2624        my ($self, $outputDirectory) = @_;
2625        # Now we need to run through all the relations. First, we loop through the entities.
2626        my $metaData = $self->{_metaData};
2627        my $entities = $metaData->{Entities};
2628        for my $entityName (keys %{$entities}) {
2629            my $entityStructure = $entities->{$entityName};
2630            # Get the entity's relations.
2631            my $relationList = $entityStructure->{Relations};
2632            # Loop through the relations, dumping them.
2633            for my $relationName (keys %{$relationList}) {
2634                my $relation = $relationList->{$relationName};
2635                $self->_DumpRelation($outputDirectory, $relationName, $relation);
2636            }
2637        }
2638        # Next, we loop through the relationships.
2639        my $relationships = $metaData->{Relationships};
2640        for my $relationshipName (keys %{$relationships}) {
2641            my $relationshipStructure = $relationships->{$relationshipName};
2642            # Dump this relationship's relation.
2643            $self->_DumpRelation($outputDirectory, $relationshipName, $relationshipStructure->{Relations}->{$relationshipName});
2644        }
2645    }
2646    
2647    =head3 InsertValue
2648    
2649        $erdb->InsertValue($entityID, $fieldName, $value);
2650    
2651    This method will insert a new value into the database. The value must be one
2652    associated with a secondary relation, since primary values cannot be inserted:
2653    they occur exactly once. Secondary values, on the other hand, can be missing
2654    or multiply-occurring.
2655    
2656    =over 4
2657    
2658    =item entityID
2659    
2660    ID of the object that is to receive the new value.
2661    
2662    =item fieldName
2663    
2664    Field name for the new value-- this includes the entity name, since
2665    field names are of the format I<objectName>C<(>I<fieldName>C<)>.
2666    
2667    =item value
2668    
2669    New value to be put in the field.
2670    
2671    =back
2672    
2673    =cut
2674    
2675    sub InsertValue {
2676        # Get the parameters.
2677        my ($self, $entityID, $fieldName, $value) = @_;
2678        # Parse the entity name and the real field name.
2679        if ($fieldName =~ /^([^(]+)\(([^)]+)\)/) {
2680            my $entityName = $1;
2681            my $fieldTitle = $2;
2682            # Get its descriptor.
2683            if (!$self->IsEntity($entityName)) {
2684                Confess("$entityName is not a valid entity.");
2685            } else {
2686                my $entityData = $self->{_metaData}->{Entities}->{$entityName};
2687                # Find the relation containing this field.
2688                my $fieldHash = $entityData->{Fields};
2689                if (! exists $fieldHash->{$fieldTitle}) {
2690                    Confess("$fieldTitle not found in $entityName.");
2691                } else {
2692                    my $relation = $fieldHash->{$fieldTitle}->{relation};
2693                    if ($relation eq $entityName) {
2694                        Confess("Cannot do InsertValue on primary field $fieldTitle of $entityName.");
2695                    } else {
2696                        # Now we can create an INSERT statement.
2697                        my $dbh = $self->{_dbh};
2698                        my $fixedName = _FixName($fieldTitle);
2699                        my $statement = "INSERT INTO $relation (id, $fixedName) VALUES(?, ?)";
2700                        # Execute the command.
2701                        $dbh->SQL($statement, 0, $entityID, $value);
2702                    }
2703                }
2704            }
2705        } else {
2706            Confess("$fieldName is not a valid field name.");
2707        }
2708    }
2709    
2710    =head3 InsertObject
2711    
2712        $erdb->InsertObject($objectType, \%fieldHash);
2713    
2714    Insert an object into the database. The object is defined by a type name and then a hash
2715    of field names to values. Field values in the primary relation are represented by scalars.
2716    (Note that for relationships, the primary relation is the B<only> relation.)
2717    Field values for the other relations comprising the entity are always list references. For
2718    example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases
2719    C<ZP_00210270.1> and C<gi|46206278>.
2720    
2721        $erdb->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']});
2722    
2723    The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
2724    property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
2725    
2726        $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'});
2727    
2728    =over 4
2729    
2730    =item newObjectType
2731    
2732    Type name of the object to insert.
2733    
2734    =item fieldHash
2735    
2736    Hash of field names to values.
2737    
2738    =back
2739    
2740    =cut
2741    
2742    sub InsertObject {
2743        # Get the parameters.
2744        my ($self, $newObjectType, $fieldHash) = @_;
2745        # Denote that so far we appear successful.
2746        my $retVal = 1;
2747        # Get the database handle.
2748        my $dbh = $self->{_dbh};
2749        # Get the relation list.
2750        my $relationTable = $self->_GetRelationTable($newObjectType);
2751        # Loop through the relations. We'll build insert statements for each one. If a relation is
2752        # secondary, we may end up generating multiple insert statements. If an error occurs, we
2753        # stop the loop.
2754        my @relationList = keys %{$relationTable};
2755        for (my $i = 0; $retVal && $i <= $#relationList; $i++) {
2756            my $relationName = $relationList[$i];
2757            my $relationDefinition = $relationTable->{$relationName};
2758            # Get the relation's fields. For each field we will collect a value in the corresponding
2759            # position of the @valueList array. If one of the fields is missing, we will add it to the
2760            # @missing list.
2761            my @fieldList = @{$relationDefinition->{Fields}};
2762            my @fieldNameList = ();
2763            my @valueList = ();
2764            my @missing = ();
2765            my $recordCount = 1;
2766            for my $fieldDescriptor (@fieldList) {
2767                # Get the field name and save it. Note we need to fix it up so the hyphens
2768                # are converted to underscores.
2769                my $fieldName = $fieldDescriptor->{name};
2770                push @fieldNameList, _FixName($fieldName);
2771                # Look for the named field in the incoming structure. Note that we are looking
2772                # for the real field name, not the fixed-up one!
2773                if (exists $fieldHash->{$fieldName}) {
2774                    # Here we found the field. Stash it in the value list.
2775                    my $value = $fieldHash->{$fieldName};
2776                    push @valueList, $value;
2777                    # If the value is a list, we may need to increment the record count.
2778                    if (ref $value eq "ARRAY") {
2779                        my $thisCount = @{$value};
2780                        if ($recordCount == 1) {
2781                            # Here we have our first list, so we save its count.
2782                            $recordCount = $thisCount;
2783                        } elsif ($recordCount != $thisCount) {
2784                            # Here we have a second list, so its length has to match the
2785                            # previous lists.
2786                            Trace("Field $value in new $newObjectType object has an invalid list length $thisCount. Expected $recordCount.") if T(0);
2787                            $retVal = 0;
2788                        }
2789                    }
2790                } else {
2791                    # Here the field is not present. Flag it as missing.
2792                    push @missing, $fieldName;
2793                }
2794            }
2795            # Only proceed if there are no missing fields.
2796            if (@missing > 0) {
2797                Trace("Relation $relationName for $newObjectType skipped due to missing fields: " .
2798                    join(' ', @missing)) if T(1);
2799            } else {
2800                # Build the INSERT statement.
2801                my $statement = "INSERT INTO $relationName (" . join (', ', @fieldNameList) .
2802                    ") VALUES (";
2803                # Create a marker list of the proper size and put it in the statement.
2804                my @markers = ();
2805                while (@markers < @fieldNameList) { push @markers, '?'; }
2806                $statement .= join(', ', @markers) . ")";
2807                # We have the insert statement, so prepare it.
2808                my $sth = $dbh->prepare_command($statement);
2809                Trace("Insert statement prepared: $statement") if T(3);
2810                # Now we loop through the values. If a value is scalar, we use it unmodified. If it's
2811                # a list, we use the current element. The values are stored in the @parameterList array.
2812                my $done = 0;
2813                for (my $i = 0; $i < $recordCount; $i++) {
2814                    # Clear the parameter list array.
2815                    my @parameterList = ();
2816                    # Loop through the values.
2817                    for my $value (@valueList) {
2818                        # Check to see if this is a scalar value.
2819                        if (ref $value eq "ARRAY") {
2820                            # Here we have a list value. Pull the current entry.
2821                            push @parameterList, $value->[$i];
2822                        } else {
2823                            # Here we have a scalar value. Use it unmodified.
2824                            push @parameterList, $value;
2825                        }
2826                    }
2827                    # Execute the INSERT statement with the specified parameter list.
2828                    $retVal = $sth->execute(@parameterList);
2829                    if (!$retVal) {
2830                        my $errorString = $sth->errstr();
2831                        Confess("Error inserting into $relationName: $errorString");
2832                    } else {
2833                        Trace("Insert successful using $parameterList[0].") if T(3);
2834                    }
2835                }
2836            }
2837        }
2838        # Return a 1 for backward compatability.
2839        return 1;
2840    }
2841    
2842    =head3 UpdateEntity
2843    
2844        $erdb->UpdateEntity($entityName, $id, \%fields);
2845    
2846    Update the values of an entity. This is an unprotected update, so it should only be
2847    done if the database resides on a database server.
2848    
2849    =over 4
2850    
2851    =item entityName
2852    
2853    Name of the entity to update. (This is the entity type.)
2854    
2855    =item id
2856    
2857    ID of the entity to update. If no entity exists with this ID, an error will be thrown.
2858    
2859    =item fields
2860    
2861    Reference to a hash mapping field names to their new values. All of the fields named
2862    must be in the entity's primary relation, and they cannot any of them be the ID field.
2863    
2864    =back
2865    
2866    =cut
2867    
2868    sub UpdateEntity {
2869        # Get the parameters.
2870        my ($self, $entityName, $id, $fields) = @_;
2871        # Get a list of the field names being updated.
2872        my @fieldList = keys %{$fields};
2873        # Verify that the fields exist.
2874        my $checker = $self->GetFieldTable($entityName);
2875        for my $field (@fieldList) {
2876            if ($field eq 'id') {
2877                Confess("Cannot update the ID field for entity $entityName.");
2878            } elsif ($checker->{$field}->{relation} ne $entityName) {
2879                Confess("Cannot find $field in primary relation of $entityName.");
2880            }
2881        }
2882        # Build the SQL statement.
2883        my @sets = ();
2884        my @valueList = ();
2885        for my $field (@fieldList) {
2886            push @sets, _FixName($field) . " = ?";
2887            push @valueList, $fields->{$field};
2888        }
2889        my $command = "UPDATE $entityName SET " . join(", ", @sets) . " WHERE id = ?";
2890        # Add the ID to the list of binding values.
2891        push @valueList, $id;
2892        # Call SQL to do the work.
2893        my $rows = $self->{_dbh}->SQL($command, 0, @valueList);
2894        # Check for errors.
2895        if ($rows == 0) {
2896            Confess("Entity $id of type $entityName not found.");
2897        }
2898    }
2899    
2900    =head3 LoadTable
2901    
2902        my $results = $erdb->LoadTable($fileName, $relationName, %options);
2903    
2904    Load data from a tab-delimited file into a specified table, optionally re-creating the table
2905    first.
2906    
2907    =over 4
2908    
2909    =item fileName
2910    
2911    Name of the file from which the table data should be loaded.
2912    
2913    =item relationName
2914    
2915    Name of the relation to be loaded. This is the same as the table name.
2916    
2917    =item options
2918    
2919    A hash of load options.
2920    
2921    =item RETURN
2922    
2923    Returns a statistical object containing a list of the error messages.
2924    
2925    =back
2926    
2927    The permissible options are as follows.
2928    
2929    =over 4
2930    
2931    =item truncate
2932    
2933    If TRUE, then the table will be erased before loading.
2934    
2935    =item mode
2936    
2937    Mode in which the load should operate, either C<low_priority> or C<concurrent>.
2938    This option is only applicable to a MySQL database.
2939    
2940    =item partial
2941    
2942    If TRUE, then it is assumed that this is a partial load, and the table will not
2943    be analyzed and compacted at the end.
2944    
2945    =back
2946    
2947    =cut
2948    sub LoadTable {
2949        # Get the parameters.
2950        my ($self, $fileName, $relationName, %options) = @_;
2951        # Create the statistical return object.
2952        my $retVal = _GetLoadStats();
2953        # Trace the fact of the load.
2954        Trace("Loading table $relationName from $fileName") if T(2);
2955        # Get the database handle.
2956        my $dbh = $self->{_dbh};
2957        # Get the input file size.
2958        my $fileSize = -s $fileName;
2959        # Get the relation data.
2960          my $relation = $self->_FindRelation($relationName);          my $relation = $self->_FindRelation($relationName);
2961          # Check the truncation flag.          # Check the truncation flag.
2962          if ($truncateFlag) {      if ($options{truncate}) {
2963                  Trace("Creating table $relationName") if T(1);          Trace("Creating table $relationName") if T(2);
2964            # Compute the row count estimate. We take the size of the load file,
2965            # divide it by the estimated row size, and then multiply by 2 to
2966            # leave extra room. We postulate a minimum row count of 1000 to
2967            # prevent problems with incoming empty load files.
2968            my $rowSize = $self->EstimateRowSize($relationName);
2969            my $estimate = $fileSize * 8 / $rowSize;
2970            if ($estimate < 1000) {
2971                $estimate = 1000;
2972            }
2973                  # Re-create the table without its index.                  # Re-create the table without its index.
2974                  $self->CreateTable($relationName, 0);          $self->CreateTable($relationName, 0, $estimate);
2975            # If this is a pre-index DBMS, create the index here.
2976            if ($dbh->{_preIndex}) {
2977                eval {
2978                    $self->CreateIndex($relationName);
2979                };
2980                if ($@) {
2981                    $retVal->AddMessage($@);
2982                }
2983            }
2984        }
2985        # Load the table.
2986        my $rv;
2987        eval {
2988            $rv = $dbh->load_table(file => $fileName, tbl => $relationName, style => $options{mode});
2989        };
2990        if (!defined $rv) {
2991            $retVal->AddMessage($@) if ($@);
2992            $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2993            Trace("Table load failed for $relationName.") if T(1);
2994        } else {
2995            # Here we successfully loaded the table.
2996            $retVal->Add("tables");
2997            my $size = -s $fileName;
2998            Trace("$size bytes loaded into $relationName.") if T(2);
2999            $retVal->Add("bytes", $size);
3000            # If we're rebuilding, we need to create the table indexes.
3001            if ($options{truncate}) {
3002                # Indexes are created here for PostGres. For PostGres, indexes are
3003                # best built at the end. For MySQL, the reverse is true.
3004                if (! $dbh->{_preIndex}) {
3005                    eval {
3006                        $self->CreateIndex($relationName);
3007                    };
3008                    if ($@) {
3009                        $retVal->AddMessage($@);
3010                    }
3011                }
3012                # The full-text index (if any) is always built last, even for MySQL.
3013                # First we need to see if this table has a full-text index. Only
3014                # primary relations are allowed that privilege.
3015                Trace("Checking for full-text index on $relationName.") if T(2);
3016                if ($self->_IsPrimary($relationName)) {
3017                    $self->CreateSearchIndex($relationName);
3018                }
3019            }
3020        }
3021        # Analyze the table to improve performance.
3022        if (! $options{partial}) {
3023            Trace("Analyzing and compacting $relationName.") if T(3);
3024            $self->Analyze($relationName);
3025        }
3026        Trace("$relationName load completed.") if T(3);
3027        # Return the statistics.
3028        return $retVal;
3029    }
3030    
3031    =head3 Analyze
3032    
3033        $erdb->Analyze($tableName);
3034    
3035    Analyze and compact a table in the database. This is useful after a load
3036    to improve the performance of the indexes.
3037    
3038    =over 4
3039    
3040    =item tableName
3041    
3042    Name of the table to be analyzed and compacted.
3043    
3044    =back
3045    
3046    =cut
3047    
3048    sub Analyze {
3049        # Get the parameters.
3050        my ($self, $tableName) = @_;
3051        # Analyze the table.
3052        $self->{_dbh}->vacuum_it($tableName);
3053    }
3054    
3055    =head3 TruncateTable
3056    
3057        $erdb->TruncateTable($table);
3058    
3059    Delete all rows from a table quickly. This uses the built-in SQL
3060    C<TRUNCATE> statement, which effectively drops and re-creates a table
3061    with all its settings intact.
3062    
3063    =over 4
3064    
3065    =item table
3066    
3067    Name of the table to be cleared.
3068    
3069    =back
3070    
3071    =cut
3072    
3073    sub TruncateTable {
3074        # Get the parameters.
3075        my ($self, $table) = @_;
3076        # Get the database handle.
3077        my $dbh = $self->{_dbh};
3078        # Execute a truncation comment.
3079        $dbh->SQL("TRUNCATE TABLE $table");
3080    }
3081    
3082    
3083    =head3 CreateSearchIndex
3084    
3085        $erdb->CreateSearchIndex($objectName);
3086    
3087    Check for a full-text search index on the specified entity or relationship object, and
3088    if one is required, rebuild it.
3089    
3090    =over 4
3091    
3092    =item objectName
3093    
3094    Name of the entity or relationship to be indexed.
3095    
3096    =back
3097    
3098    =cut
3099    
3100    sub CreateSearchIndex {
3101        # Get the parameters.
3102        my ($self, $objectName) = @_;
3103        # Get the relation's entity/relationship structure.
3104        my $structure = $self->_GetStructure($objectName);
3105        # Get the database handle.
3106        my $dbh = $self->{_dbh};
3107        Trace("Checking for search fields in $objectName.") if T(3);
3108        # Check for a searchable fields list.
3109        if (exists $structure->{searchFields}) {
3110            # Here we know that we need to create a full-text search index.
3111            # Get an SQL-formatted field name list.
3112            my $fields = join(", ", _FixNames(@{$structure->{searchFields}}));
3113            # Create the index. If it already exists, it will be dropped.
3114            $dbh->create_index(tbl => $objectName, idx => "search_idx",
3115                               flds => $fields, kind => 'fulltext');
3116            Trace("Index created for $fields in $objectName.") if T(2);
3117        }
3118    }
3119    
3120    =head3 DropRelation
3121    
3122        $erdb->DropRelation($relationName);
3123    
3124    Physically drop a relation from the database.
3125    
3126    =over 4
3127    
3128    =item relationName
3129    
3130    Name of the relation to drop. If it does not exist, this method will have
3131    no effect.
3132    
3133    =back
3134    
3135    =cut
3136    
3137    sub DropRelation {
3138        # Get the parameters.
3139        my ($self, $relationName) = @_;
3140        # Get the database handle.
3141        my $dbh = $self->{_dbh};
3142        # Drop the relation. The method used here has no effect if the relation
3143        # does not exist.
3144        Trace("Invoking DB Kernel to drop $relationName.") if T(3);
3145        $dbh->drop_table(tbl => $relationName);
3146    }
3147    
3148    =head3 MatchSqlPattern
3149    
3150        my $matched = ERDB::MatchSqlPattern($value, $pattern);
3151    
3152    Determine whether or not a specified value matches an SQL pattern. An SQL
3153    pattern has two wild card characters: C<%> that matches multiple characters,
3154    and C<_> that matches a single character. These can be escaped using a
3155    backslash (C<\>). We pull this off by converting the SQL pattern to a
3156    PERL regular expression. As per SQL rules, the match is case-insensitive.
3157    
3158    =over 4
3159    
3160    =item value
3161    
3162    Value to be matched against the pattern. Note that an undefined or empty
3163    value will not match anything.
3164    
3165    =item pattern
3166    
3167    SQL pattern against which to match the value. An undefined or empty pattern will
3168    match everything.
3169    
3170    =item RETURN
3171    
3172    Returns TRUE if the value and pattern match, else FALSE.
3173    
3174    =back
3175    
3176    =cut
3177    
3178    sub MatchSqlPattern {
3179        # Get the parameters.
3180        my ($value, $pattern) = @_;
3181        # Declare the return variable.
3182        my $retVal;
3183        # Insure we have a pattern.
3184        if (! defined($pattern) || $pattern eq "") {
3185            $retVal = 1;
3186        } else {
3187            # Break the pattern into pieces around the wildcard characters. Because we
3188            # use parentheses in the split function's delimiter expression, we'll get
3189            # list elements for the delimiters as well as the rest of the string.
3190            my @pieces = split /([_%]|\\[_%])/, $pattern;
3191            # Check some fast special cases.
3192            if ($pattern eq '%') {
3193                # A null pattern matches everything.
3194                $retVal = 1;
3195            } elsif (@pieces == 1) {
3196                # No wildcards, so we have a literal comparison. Note we're case-insensitive.
3197                $retVal = (lc($value) eq lc($pattern));
3198            } elsif (@pieces == 2 && $pieces[1] eq '%') {
3199                # A wildcard at the end, so we have a substring match. This is also case-insensitive.
3200                $retVal = (lc(substr($value, 0, length($pieces[0]))) eq lc($pieces[0]));
3201            } else {
3202                # Okay, we have to do it the hard way. Convert each piece to a PERL pattern.
3203                my $realPattern = "";
3204                for my $piece (@pieces) {
3205                    # Determine the type of piece.
3206                    if ($piece eq "") {
3207                        # Empty pieces are ignored.
3208                    } elsif ($piece eq "%") {
3209                        # Here we have a multi-character wildcard. Note that it can match
3210                        # zero or more characters.
3211                        $realPattern .= ".*"
3212                    } elsif ($piece eq "_") {
3213                        # Here we have a single-character wildcard.
3214                        $realPattern .= ".";
3215                    } elsif ($piece eq "\\%" || $piece eq "\\_") {
3216                        # This is an escape sequence (which is a rare thing, actually).
3217                        $realPattern .= substr($piece, 1, 1);
3218                    } else {
3219                        # Here we have raw text.
3220                        $realPattern .= quotemeta($piece);
3221                    }
3222                }
3223                # Do the match.
3224                $retVal = ($value =~ /^$realPattern$/i ? 1 : 0);
3225            }
3226        }
3227        # Return the result.
3228        return $retVal;
3229    }
3230    
3231    =head3 GetEntity
3232    
3233        my $entityObject = $erdb->GetEntity($entityType, $ID);
3234    
3235    Return an object describing the entity instance with a specified ID.
3236    
3237    =over 4
3238    
3239    =item entityType
3240    
3241    Entity type name.
3242    
3243    =item ID
3244    
3245    ID of the desired entity.
3246    
3247    =item RETURN
3248    
3249    Returns a B<ERDBObject> representing the desired entity instance, or an undefined value if no
3250    instance is found with the specified key.
3251    
3252    =back
3253    
3254    =cut
3255    
3256    sub GetEntity {
3257        # Get the parameters.
3258        my ($self, $entityType, $ID) = @_;
3259        # Create a query.
3260        my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);
3261        # Get the first (and only) object.
3262        my $retVal = $query->Fetch();
3263        if (T(3)) {
3264            if ($retVal) {
3265                Trace("Entity $entityType \"$ID\" found.");
3266            } else {
3267                Trace("Entity $entityType \"$ID\" not found.");
3268            }
3269        }
3270        # Return the result.
3271        return $retVal;
3272    }
3273    
3274    =head3 GetChoices
3275    
3276        my @values = $erdb->GetChoices($entityName, $fieldName);
3277    
3278    Return a list of all the values for the specified field that are represented in the
3279    specified entity.
3280    
3281    Note that if the field is not indexed, then this will be a very slow operation.
3282    
3283    =over 4
3284    
3285    =item entityName
3286    
3287    Name of an entity in the database.
3288    
3289    =item fieldName
3290    
3291    Name of a field belonging to the entity. This is a raw field name without
3292    the standard parenthesized notation used in most calls.
3293    
3294    =item RETURN
3295    
3296    Returns a list of the distinct values for the specified field in the database.
3297    
3298    =back
3299    
3300    =cut
3301    
3302    sub GetChoices {
3303        # Get the parameters.
3304        my ($self, $entityName, $fieldName) = @_;
3305        # Declare the return variable.
3306        my @retVal;
3307        # Get the entity data structure.
3308        my $entityData = $self->_GetStructure($entityName);
3309        # Get the field.
3310        my $fieldHash = $entityData->{Fields};
3311        if (! exists $fieldHash->{$fieldName}) {
3312            Confess("$fieldName not found in $entityName.");
3313        } else {
3314            # Get the name of the relation containing the field.
3315            my $relation = $fieldHash->{$fieldName}->{relation};
3316            # Fix up the field name.
3317            my $realName = _FixName($fieldName);
3318            # Get the database handle.
3319            my $dbh = $self->{_dbh};
3320            # Query the database.
3321            my $results = $dbh->SQL("SELECT DISTINCT $realName FROM $relation");
3322            # Clean the results. They are stored as a list of lists, and we just want the one list.
3323            @retVal = sort map { $_->[0] } @{$results};
3324        }
3325        # Return the result.
3326        return @retVal;
3327    }
3328    
3329    =head3 GetEntityValues
3330    
3331        my @values = $erdb->GetEntityValues($entityType, $ID, \@fields);
3332    
3333    Return a list of values from a specified entity instance. If the entity instance
3334    does not exist, an empty list is returned.
3335    
3336    =over 4
3337    
3338    =item entityType
3339    
3340    Entity type name.
3341    
3342    =item ID
3343    
3344    ID of the desired entity.
3345    
3346    =item fields
3347    
3348    List of field names, each of the form I<objectName>C<(>I<fieldName>C<)>.
3349    
3350    =item RETURN
3351    
3352    Returns a flattened list of the values of the specified fields for the specified entity.
3353    
3354    =back
3355    
3356    =cut
3357    
3358    sub GetEntityValues {
3359        # Get the parameters.
3360        my ($self, $entityType, $ID, $fields) = @_;
3361        # Get the specified entity.
3362        my $entity = $self->GetEntity($entityType, $ID);
3363        # Declare the return list.
3364        my @retVal = ();
3365        # If we found the entity, push the values into the return list.
3366        if ($entity) {
3367            push @retVal, $entity->Values($fields);
3368        }
3369        # Return the result.
3370        return @retVal;
3371    }
3372    
3373    =head3 GetAll
3374    
3375        my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count);
3376    
3377    Return a list of values taken from the objects returned by a query. The first three
3378    parameters correspond to the parameters of the L</Get> method. The final parameter is
3379    a list of the fields desired from each record found by the query. The field name
3380    syntax is the standard syntax used for fields in the B<ERDB> system--
3381    B<I<objectName>(I<fieldName>)>-- where I<objectName> is the name of the relevant entity
3382    or relationship and I<fieldName> is the name of the field.
3383    
3384    The list returned will be a list of lists. Each element of the list will contain
3385    the values returned for the fields specified in the fourth parameter. If one of the
3386    fields specified returns multiple values, they are flattened in with the rest. For
3387    example, the following call will return a list of the features in a particular
3388    spreadsheet cell, and each feature will be represented by a list containing the
3389    feature ID followed by all of its essentiality determinations.
3390    
3391        @query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(essential)']);
3392    
3393    =over 4
3394    
3395    =item objectNames
3396    
3397    List containing the names of the entity and relationship objects to be retrieved.
3398    
3399    =item filterClause
3400    
3401    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
3402    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
3403    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
3404    parameter list as additional parameters. The fields in a filter clause can come from primary
3405    entity relations, relationship relations, or secondary entity relations; however, all of the
3406    entities and relationships involved must be included in the list of object names.
3407    
3408    =item parameterList
3409    
3410    List of the parameters to be substituted in for the parameters marks in the filter clause.
3411    
3412    =item fields
3413    
3414    List of the fields to be returned in each element of the list returned.
3415    
3416    =item count
3417    
3418    Maximum number of records to return. If omitted or 0, all available records will be returned.
3419    
3420    =item RETURN
3421    
3422    Returns a list of list references. Each element of the return list contains the values for the
3423    fields specified in the B<fields> parameter.
3424    
3425    =back
3426    
3427    =cut
3428    #: Return Type @@;
3429    sub GetAll {
3430        # Get the parameters.
3431        my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
3432        # Translate the parameters from a list reference to a list. If the parameter
3433        # list is a scalar we convert it into a singleton list.
3434        my @parmList = ();
3435        if (ref $parameterList eq "ARRAY") {
3436            Trace("GetAll parm list is an array.") if T(4);
3437            @parmList = @{$parameterList};
3438        } else {
3439            Trace("GetAll parm list is a scalar: $parameterList.") if T(4);
3440            push @parmList, $parameterList;
3441        }
3442        # Insure the counter has a value.
3443        if (!defined $count) {
3444            $count = 0;
3445        }
3446        # Add the row limit to the filter clause.
3447        if ($count > 0) {
3448            $filterClause .= " LIMIT $count";
3449        }
3450        # Create the query.
3451        my $query = $self->Get($objectNames, $filterClause, \@parmList);
3452        # Set up a counter of the number of records read.
3453        my $fetched = 0;
3454        # Loop through the records returned, extracting the fields. Note that if the
3455        # counter is non-zero, we stop when the number of records read hits the count.
3456        my @retVal = ();
3457        while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {
3458            my @rowData = $row->Values($fields);
3459            push @retVal, \@rowData;
3460            $fetched++;
3461        }
3462        Trace("$fetched rows returned in GetAll.") if T(SQL => 4);
3463        # Return the resulting list.
3464        return @retVal;
3465    }
3466    
3467    =head3 Exists
3468    
3469        my $found = $sprout->Exists($entityName, $entityID);
3470    
3471    Return TRUE if an entity exists, else FALSE.
3472    
3473    =over 4
3474    
3475    =item entityName
3476    
3477    Name of the entity type (e.g. C<Feature>) relevant to the existence check.
3478    
3479    =item entityID
3480    
3481    ID of the entity instance whose existence is to be checked.
3482    
3483    =item RETURN
3484    
3485    Returns TRUE if the entity instance exists, else FALSE.
3486    
3487    =back
3488    
3489    =cut
3490    #: Return Type $;
3491    sub Exists {
3492        # Get the parameters.
3493        my ($self, $entityName, $entityID) = @_;
3494        # Check for the entity instance.
3495        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
3496        my $testInstance = $self->GetEntity($entityName, $entityID);
3497        # Return an existence indicator.
3498        my $retVal = ($testInstance ? 1 : 0);
3499        return $retVal;
3500    }
3501    
3502    =head3 EstimateRowSize
3503    
3504        my $rowSize = $erdb->EstimateRowSize($relName);
3505    
3506    Estimate the row size of the specified relation. The estimated row size is computed by adding
3507    up the average length for each data type.
3508    
3509    =over 4
3510    
3511    =item relName
3512    
3513    Name of the relation whose estimated row size is desired.
3514    
3515    =item RETURN
3516    
3517    Returns an estimate of the row size for the specified relation.
3518    
3519    =back
3520    
3521    =cut
3522    #: Return Type $;
3523    sub EstimateRowSize {
3524        # Get the parameters.
3525        my ($self, $relName) = @_;
3526        # Declare the return variable.
3527        my $retVal = 0;
3528        # Find the relation descriptor.
3529        my $relation = $self->_FindRelation($relName);
3530        # Get the list of fields.
3531        for my $fieldData (@{$relation->{Fields}}) {
3532            # Get the field type and add its length.
3533            my $fieldLen = $TypeTable{$fieldData->{type}}->{avgLen};
3534            $retVal += $fieldLen;
3535        }
3536        # Return the result.
3537        return $retVal;
3538    }
3539    
3540    =head3 GetFieldTable
3541    
3542        my $fieldHash = $self->GetFieldTable($objectnName);
3543    
3544    Get the field structure for a specified entity or relationship.
3545    
3546    =over 4
3547    
3548    =item objectName
3549    
3550    Name of the desired entity or relationship.
3551    
3552    =item RETURN
3553    
3554    The table containing the field descriptors for the specified object.
3555    
3556    =back
3557    
3558    =cut
3559    
3560    sub GetFieldTable {
3561        # Get the parameters.
3562        my ($self, $objectName) = @_;
3563        # Get the descriptor from the metadata.
3564        my $objectData = $self->_GetStructure($objectName);
3565        # Return the object's field table.
3566        return $objectData->{Fields};
3567    }
3568    
3569    =head3 SplitKeywords
3570    
3571        my @keywords = ERDB::SplitKeywords($keywordString);
3572    
3573    This method returns a list of the positive keywords in the specified
3574    keyword string. All of the operators will have been stripped off,
3575    and if the keyword is preceded by a minus operator (C<->), it will
3576    not be in the list returned. The idea here is to get a list of the
3577    keywords the user wants to see. The list will be processed to remove
3578    duplicates.
3579    
3580    It is possible to create a string that confuses this method. For example
3581    
3582        frog toad -frog
3583    
3584    would return both C<frog> and C<toad>. If this is a problem we can deal
3585    with it later.
3586    
3587    =over 4
3588    
3589    =item keywordString
3590    
3591    The keyword string to be parsed.
3592    
3593    =item RETURN
3594    
3595    Returns a list of the words in the keyword string the user wants to
3596    see.
3597    
3598    =back
3599    
3600    =cut
3601    
3602    sub SplitKeywords {
3603        # Get the parameters.
3604        my ($keywordString) = @_;
3605        # Make a safety copy of the string. (This helps during debugging.)
3606        my $workString = $keywordString;
3607        # Convert operators we don't care about to spaces.
3608        $workString =~ tr/+"()<>/ /;
3609        # Split the rest of the string along space boundaries. Note that we
3610        # eliminate any words that are zero length or begin with a minus sign.
3611        my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
3612        # Use a hash to remove duplicates.
3613        my %words = map { $_ => 1 } @wordList;
3614        # Return the result.
3615        return sort keys %words;
3616    }
3617    
3618    =head3 ValidateFieldName
3619    
3620        my $okFlag = ERDB::ValidateFieldName($fieldName);
3621    
3622    Return TRUE if the specified field name is valid, else FALSE. Valid field names must
3623    be hyphenated words subject to certain restrictions.
3624    
3625    =over 4
3626    
3627    =item fieldName
3628    
3629    Field name to be validated.
3630    
3631    =item RETURN
3632    
3633    Returns TRUE if the field name is valid, else FALSE.
3634    
3635    =back
3636    
3637    =cut
3638    
3639    sub ValidateFieldName {
3640        # Get the parameters.
3641        my ($fieldName) = @_;
3642        # Declare the return variable. The field name is valid until we hear
3643        # differently.
3644        my $retVal = 1;
3645        # Compute the maximum name length.
3646        my $maxLen = $TypeTable{'name-string'}->{maxLen};
3647        # Look for bad stuff in the name.
3648        if ($fieldName =~ /--/) {
3649            # Here we have a doubled minus sign.
3650            Trace("Field name $fieldName has a doubled hyphen.") if T(1);
3651            $retVal = 0;
3652        } elsif ($fieldName !~ /^[A-Za-z]/) {
3653            # Here the field name is missing the initial letter.
3654            Trace("Field name $fieldName does not begin with a letter.") if T(1);
3655            $retVal = 0;
3656        } elsif (length($fieldName) > $maxLen) {
3657            # Here the field name is too long.
3658            Trace("Maximum field name length is $maxLen. Field name must be truncated to " . substr($fieldName,0, $maxLen) . ".");
3659        } else {
3660            # Strip out the minus signs. Everything remaining must be a letter,
3661            # underscore, or digit.
3662            my $strippedName = $fieldName;
3663            $strippedName =~ s/-//g;
3664            if ($strippedName !~ /^(\w|\d)+$/) {
3665                Trace("Field name $fieldName contains illegal characters.") if T(1);
3666                $retVal = 0;
3667            }
3668        }
3669        # Return the result.
3670        return $retVal;
3671    }
3672    
3673    =head3 ReadMetaXML
3674    
3675        my $rawMetaData = ERDB::ReadDBD($fileName);
3676    
3677    This method reads a raw database definition XML file and returns it.
3678    Normally, the metadata used by the ERDB system has been processed and
3679    modified to make it easier to load and retrieve the data; however,
3680    this method can be used to get the data in its raw form.
3681    
3682    =over 4
3683    
3684    =item fileName
3685    
3686    Name of the XML file to read.
3687    
3688    =item RETURN
3689    
3690    Returns a hash reference containing the raw XML data from the specified file.
3691    
3692    =back
3693    
3694    =cut
3695    
3696    sub ReadMetaXML {
3697        # Get the parameters.
3698        my ($fileName) = @_;
3699        # Read the XML.
3700        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
3701        Trace("XML metadata loaded from file $fileName.") if T(1);
3702        # Return the result.
3703<