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

Diff of /Sprout/ERDB.pm

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

revision 1.5, Tue Apr 5 05:17:01 2005 UTC revision 1.80, Thu Nov 30 23:04:01 2006 UTC
# Line 1  Line 1 
1  package ERDB;  package ERDB;
2    
3          use strict;          use strict;
         use Carp;  
4          use Tracer;          use Tracer;
5          use DBKernel;      use DBrtns;
6          use Data::Dumper;          use Data::Dumper;
7          use XML::Simple;          use XML::Simple;
8          use DBQuery;          use DBQuery;
9          use DBObject;          use DBObject;
10          use Stats;          use Stats;
11          use Time::HiRes qw(gettimeofday);          use Time::HiRes qw(gettimeofday);
12        use Digest::MD5 qw(md5_base64);
13        use FIG;
14        use CGI;
15    
16  =head1 Entity-Relationship Database Package  =head1 Entity-Relationship Database Package
17    
# Line 33  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 57  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 must
232    all be from the same relation. The alternate indexes assist in ordering results
233    from a query. A relationship can have up to two indexes-- a I<to-index> and a
234    I<from-index>. These 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. A relationship's index must specify only fields in
238    the relationship.
239    
240    The indexes for an entity must be listed inside the B<Indexes> tag. The from-index
241    of a relationship is specified using the B<FromIndex> tag; the to-index is specified
242    using the B<ToIndex> tag.
243    
244    Each index can contain a B<Notes> tag. In addition, it will have an B<IndexFields>
245    tag containing the B<IndexField> tags. These specify, in order, the fields used in
246    the index. The attributes of an B<IndexField> tag are as follows.
247    
248    =over 4
249    
250    =item name
251    
252    Name of the field.
253    
254    =item order
255    
256    Sort order of the field-- C<ascending> or C<descending>.
257    
258    =back
259    
260    The B<FromIndex>, and B<ToIndex> tags have no attributes. The B<Index> tag can
261    have a B<Unique> attribute. If specified, the index will be generated as a unique
262    index.
263    
264    =head3 Object and Field Names
265    
266    By convention entity and relationship names use capital casing (e.g. C<Genome> or
267    C<HasRegionsIn>. Most underlying databases, however, are aggressively case-insensitive
268    with respect to relation names, converting them internally to all-upper case or
269    all-lower case.
270    
271    If syntax or parsing errors occur when you try to load or use an ERDB database, the
272    most likely reason is that one of your objects has an SQL reserved word as its name.
273    The list of SQL reserved words keeps increasing; however, most are unlikely to show
274    up as a noun or declarative verb phrase. The exceptions are C<Group>, C<User>,
275    C<Table>, C<Index>, C<Object>, C<Date>, C<Number>, C<Update>, C<Time>, C<Percent>,
276    C<Memo>, C<Order>, and C<Sum>. This problem can crop up in field names as well.
277    
278    Every entity has a field called C<id> that acts as its primary key. Every relationship
279    has fields called C<from-link> and C<to-link> that contain copies of the relevant
280    entity IDs. These are essentially ERDB's reserved words, and should not be used
281    for user-defined field names.
282    
283    =head3 Entities
284    
285    An entity is described by the B<Entity> tag. The entity can contain B<Notes>, an
286    B<Indexes> tag containing one or more secondary indexes, and a B<Fields> tag
287    containing one or more fields. The attributes of the B<Entity> tag are as follows.
288    
289    =over 4
290    
291    =item name
292    
293    Name of the entity. The entity name, by convention, uses capital casing (e.g. C<Genome>
294    or C<GroupBlock>) and should be a noun or noun phrase.
295    
296    =item keyType
297    
298    Data type of the primary key. The primary key is always named C<id>.
299    
300    =back
301    
302    =head3 Relationships
303    
304    A relationship is described by the C<Relationship> tag. Within a relationship,
305    there can be a C<Notes> tag, a C<Fields> tag containing the intersection data
306    fields, a C<FromIndex> tag containing the from-index, and a C<ToIndex> tag containing
307    the to-index.
308    
309    The C<Relationship> tag has the following attributes.
310    
311    =over 4
312    
313    =item name
314    
315    Name of the relationship. The relationship name, by convention, uses capital casing
316    (e.g. C<ContainsRegionIn> or C<HasContig>), and should be a declarative verb
317    phrase, designed to fit between the from-entity and the to-entity (e.g.
318    Block C<ContainsRegionIn> Genome).
319    
320    =item from
321    
322    Name of the entity from which the relationship starts.
323    
324    =item to
325    
326    Name of the entity to which the relationship proceeds.
327    
328    =item arity
329    
330    Relationship type: C<1M> for one-to-many and C<MM> for many-to-many.
331    
332    =back
333    
334  =cut  =cut
335    
# Line 76  Line 337 
337    
338  # 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.
339  # "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
340  # 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
341   #string is specified in the field definition.  # record sizes. "sort" is the key modifier for the sort command, "notes" is a type description,
342  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
343                                    int =>         { sqlType => 'INTEGER',                        maxLen => 20,                   dataGen => "IntGen(0, 99999999)" },  # index
344                                    string =>  { sqlType => 'VARCHAR(255)',               maxLen => 255,                  dataGen => "StringGen(IntGen(10,250))" },  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",
345                                    text =>        { sqlType => 'TEXT',                           maxLen => 1000000000,   dataGen => "StringGen(IntGen(80,1000))" },                                 indexMod =>   0, notes => "single ASCII character"},
346                                    date =>        { sqlType => 'BIGINT',                         maxLen => 80,                   dataGen => "DateGen(-7, 7, IntGen(0,1400))" },                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n",
347                                    float =>       { sqlType => 'DOUBLE PRECISION',       maxLen => 40,                   dataGen => "FloatGen(0.0, 100.0)" },                                 indexMod =>   0, notes => "signed 32-bit integer"},
348                                    boolean => { sqlType => 'SMALLINT',                   maxLen => 1,                    dataGen => "IntGen(0, 1)" },                    counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n",
349                                   indexMod =>   0, notes => "unsigned 32-bit integer"},
350                      string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, sort => "",
351                                   indexMod =>   0, notes => "character string, 0 to 255 characters"},
352                      text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, sort => "",
353                                   indexMod => 255, notes => "character string, nearly unlimited length, only first 255 characters are indexed"},
354                      date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, sort => "n",
355                                   indexMod =>   0, notes => "signed, 64-bit integer"},
356                      float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, sort => "g",
357                                   indexMod =>   0, notes => "64-bit double precision floating-point number"},
358                      boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, sort => "n",
359                                   indexMod =>   0, notes => "boolean value: 0 if false, 1 if true"},
360                     'hash-string' =>
361                                 { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, sort => "",
362                                   indexMod =>   0, notes => "string stored in digested form, used for certain types of key fields"},
363                     'id-string' =>
364                                 { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, sort => "",
365                                   indexMod =>   0, notes => "character string, 0 to 25 characters"},
366                               'key-string' =>                               'key-string' =>
367                                                           { sqlType => 'VARCHAR(40)',            maxLen => 40,                   dataGen => "StringGen(IntGen(10,40))" },                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, sort => "",
368                                   indexMod =>   0, notes => "character string, 0 to 40 characters"},
369                                   'name-string' =>                                   'name-string' =>
370                                                           { sqlType => 'VARCHAR(80)',            maxLen => 80,                   dataGen => "StringGen(IntGen(10,80))" },                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, sort => "",
371                                   indexMod =>   0, notes => "character string, 0 to 80 characters"},
372                                   'medium-string' =>                                   'medium-string' =>
373                                                           { sqlType => 'VARCHAR(160)',           maxLen => 160,                  dataGen => "StringGen(IntGen(10,160))" },                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",
374                                   indexMod =>   0, notes => "character string, 0 to 160 characters"},
375                                  );                                  );
376    
377  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 99  Line 380 
380                                     'MM' => 'many-to-many'                                     'MM' => 'many-to-many'
381                                   );                                   );
382    
383  # Table for interpreting string patterns.  # Options for XML input and output.
384    
385    my %XmlOptions = (GroupTags =>  { Relationships => 'Relationship',
386                                      Entities => 'Entity',
387                                      Fields => 'Field',
388                                      Indexes => 'Index',
389                                      IndexFields => 'IndexField'
390                                    },
391                      KeyAttr =>    { Relationship => 'name',
392                                      Entity => 'name',
393                                      Field => 'name'
394                                    },
395                      SuppressEmpty => 1,
396                     );
397    
398  my %PictureTable = ( 'A' => "abcdefghijklmnopqrstuvwxyz",  my %XmlInOpts  = (
399                                           '9' => "0123456789",                    ForceArray => ['Field', 'Index', 'IndexField', 'Relationship', 'Entity'],
400                                           'X' => "abcdefghijklmnopqrstuvwxyz0123456789",                    ForceContent => 1,
401                                           'V' => "aeiou",                    NormalizeSpace => 2,
402                                           'K' => "bcdfghjklmnoprstvwxyz"                   );
403    my %XmlOutOpts = (
404                      RootName => 'Database',
405                      XMLDecl => 1,
406                                     );                                     );
407    
408    
409  =head2 Public Methods  =head2 Public Methods
410    
411  =head3 new  =head3 new
# Line 140  Line 438 
438                                   _metaData => $metaData                                   _metaData => $metaData
439                             };                             };
440          # Bless and return it.          # Bless and return it.
441          bless $self;      bless $self, $class;
442          return $self;          return $self;
443  }  }
444    
445  =head3 ShowMetaData  =head3 ShowMetaData
446    
447  C<< $database->ShowMetaData($fileName); >>  C<< $erdb->ShowMetaData($fileName); >>
448    
449  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
450  the data to be loaded into the relations.  the data to be loaded into the relations.
# Line 177  Line 475 
475          # Write the HTML heading stuff.          # Write the HTML heading stuff.
476          print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";          print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";
477          print HTMLOUT "</head>\n<body>\n";          print HTMLOUT "</head>\n<body>\n";
478        # Write the documentation.
479        print HTMLOUT $self->DisplayMetaData();
480        # Close the document.
481        print HTMLOUT "</body>\n</html>\n";
482        # Close the file.
483        close HTMLOUT;
484    }
485    
486    =head3 DisplayMetaData
487    
488    C<< my $html = $erdb->DisplayMetaData(); >>
489    
490    Return an HTML description of the database. This description can be used to help users create
491    the data to be loaded into the relations and form queries. The output is raw includable HTML
492    without any HEAD or BODY tags.
493    
494    =over 4
495    
496    =item filename
497    
498    The name of the output file.
499    
500    =back
501    
502    =cut
503    
504    sub DisplayMetaData {
505        # Get the parameters.
506        my ($self) = @_;
507        # Get the metadata and the title string.
508        my $metadata = $self->{_metaData};
509        # Get the title string.
510        my $title = $metadata->{Title};
511        # Get the entity and relationship lists.
512        my $entityList = $metadata->{Entities};
513        my $relationshipList = $metadata->{Relationships};
514        # Declare the return variable.
515        my $retVal = "";
516        # Open the output file.
517        Trace("Building MetaData table of contents.") if T(4);
518          # 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
519          # section contains an ordered list of entity or relationship subsections.          # section contains an ordered list of entity or relationship subsections.
520          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";
521          # Loop through the Entities, displaying a list item for each.          # Loop through the Entities, displaying a list item for each.
522          foreach my $key (sort keys %{$entityList}) {          foreach my $key (sort keys %{$entityList}) {
523                  # Display this item.                  # Display this item.
524                  print HTMLOUT "<li><a href=\"#$key\">$key</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$key</a></li>\n";
525          }          }
526          # Close off the entity section and start the relationship section.          # Close off the entity section and start the relationship section.
527          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";
528          # Loop through the Relationships.          # Loop through the Relationships.
529          foreach my $key (sort keys %{$relationshipList}) {          foreach my $key (sort keys %{$relationshipList}) {
530                  # Display this item.                  # Display this item.
531                  my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});                  my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});
532                  print HTMLOUT "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";
533          }          }
534          # Close off the relationship section and list the join table section.          # Close off the relationship section and list the join table section.
535          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";
536          # Close off the table of contents itself.          # Close off the table of contents itself.
537          print HTMLOUT "</ul>\n";      $retVal .=  "</ul>\n";
538          # 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.
539          print HTMLOUT "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";      $retVal .= "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";
540          # Loop through the entities.          # Loop through the entities.
541          for my $key (sort keys %{$entityList}) {          for my $key (sort keys %{$entityList}) {
542                  Trace("Building MetaData entry for $key entity.") if T(4);                  Trace("Building MetaData entry for $key entity.") if T(4);
543                  # Create the entity header. It contains a bookmark and the entity name.                  # Create the entity header. It contains a bookmark and the entity name.
544                  print HTMLOUT "<a name=\"$key\"></a><h3>$key</h3>\n";          $retVal .= "<a name=\"$key\"></a><h3>$key</h3>\n";
545                  # Get the entity data.                  # Get the entity data.
546                  my $entityData = $entityList->{$key};                  my $entityData = $entityList->{$key};
547                  # If there's descriptive text, display it.                  # If there's descriptive text, display it.
548                  if (my $notes = $entityData->{Notes}) {                  if (my $notes = $entityData->{Notes}) {
549                          print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
550                  }                  }
551                  # Now we want a list of the entity's relationships. First, we set up the relationship subsection.                  # Now we want a list of the entity's relationships. First, we set up the relationship subsection.
552                  print HTMLOUT "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
553                  # Loop through the relationships.                  # Loop through the relationships.
554                  for my $relationship (sort keys %{$relationshipList}) {                  for my $relationship (sort keys %{$relationshipList}) {
555                          # Get the relationship data.                          # Get the relationship data.
# Line 221  Line 559 
559                                  # Get the relationship sentence and append the arity.                                  # Get the relationship sentence and append the arity.
560                                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);                                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);
561                                  # Display the relationship data.                                  # Display the relationship data.
562                                  print HTMLOUT "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";                  $retVal .= "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";
563                          }                          }
564                  }                  }
565                  # Close off the relationship list.                  # Close off the relationship list.
566                  print HTMLOUT "</ul>\n";          $retVal .= "</ul>\n";
567                  # Get the entity's relations.                  # Get the entity's relations.
568                  my $relationList = $entityData->{Relations};                  my $relationList = $entityData->{Relations};
569                  # Create a header for the relation subsection.                  # Create a header for the relation subsection.
570                  print HTMLOUT "<h4>Relations for <b>$key</b></h4>\n";          $retVal .= "<h4>Relations for <b>$key</b></h4>\n";
571                  # Loop through the relations, displaying them.                  # Loop through the relations, displaying them.
572                  for my $relation (sort keys %{$relationList}) {                  for my $relation (sort keys %{$relationList}) {
573                          my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});                          my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});
574                          print HTMLOUT $htmlString;              $retVal .= $htmlString;
575                  }                  }
576          }          }
577          # Denote we're starting the relationship section.          # Denote we're starting the relationship section.
578          print HTMLOUT "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";      $retVal .= "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";
579          # Loop through the relationships.          # Loop through the relationships.
580          for my $key (sort keys %{$relationshipList}) {          for my $key (sort keys %{$relationshipList}) {
581                  Trace("Building MetaData entry for $key relationship.") if T(4);                  Trace("Building MetaData entry for $key relationship.") if T(4);
# Line 245  Line 583 
583                  my $relationshipStructure = $relationshipList->{$key};                  my $relationshipStructure = $relationshipList->{$key};
584                  # Create the relationship header.                  # Create the relationship header.
585                  my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);                  my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);
586                  print HTMLOUT "<h3><a name=\"$key\"></a>$headerText</h3>\n";          $retVal .= "<h3><a name=\"$key\"></a>$headerText</h3>\n";
587                  # Get the entity names.                  # Get the entity names.
588                  my $fromEntity = $relationshipStructure->{from};                  my $fromEntity = $relationshipStructure->{from};
589                  my $toEntity = $relationshipStructure->{to};                  my $toEntity = $relationshipStructure->{to};
# Line 255  Line 593 
593                  # since both sentences will say the same thing.                  # since both sentences will say the same thing.
594                  my $arity = $relationshipStructure->{arity};                  my $arity = $relationshipStructure->{arity};
595                  if ($arity eq "11") {                  if ($arity eq "11") {
596                          print HTMLOUT "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";
597                  } else {                  } else {
598                          print HTMLOUT "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";
599                          if ($arity eq "MM" && $fromEntity ne $toEntity) {                          if ($arity eq "MM" && $fromEntity ne $toEntity) {
600                                  print HTMLOUT "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";                  $retVal .= "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";
601                          }                          }
602                  }                  }
603                  print HTMLOUT "</p>\n";          $retVal .= "</p>\n";
604                  # If there are notes on this relationship, display them.                  # If there are notes on this relationship, display them.
605                  if (my $notes = $relationshipStructure->{Notes}) {                  if (my $notes = $relationshipStructure->{Notes}) {
606                          print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
607                  }                  }
608                  # Generate the relationship's relation table.                  # Generate the relationship's relation table.
609                  my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});                  my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
610                  print HTMLOUT $htmlString;          $retVal .= $htmlString;
611          }          }
612          Trace("Building MetaData join table.") if T(4);          Trace("Building MetaData join table.") if T(4);
613          # Denote we're starting the join table.          # Denote we're starting the join table.
614          print HTMLOUT "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";      $retVal .= "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";
615          # Create a table header.          # Create a table header.
616          print HTMLOUT _OpenTable("Join Table", "Source", "Target", "Join Condition");      $retVal .= _OpenTable("Join Table", "Source", "Target", "Join Condition");
617          # Loop through the joins.          # Loop through the joins.
618          my $joinTable = $metadata->{Joins};          my $joinTable = $metadata->{Joins};
619          for my $joinKey (sort keys %{$joinTable}) {      my @joinKeys = keys %{$joinTable};
620        for my $joinKey (sort @joinKeys) {
621                  # Separate out the source, the target, and the join clause.                  # Separate out the source, the target, and the join clause.
622                  $joinKey =~ m!([^/]*)/(.*)$!;          $joinKey =~ m!^([^/]+)/(.+)$!;
623                  my ($source, $target, $clause) = ($self->ComputeObjectSentence($1),          my ($sourceRelation, $targetRelation) = ($1, $2);
624                                                                                    $self->ComputeObjectSentence($2),          Trace("Join with key $joinKey is from $sourceRelation to $targetRelation.") if T(Joins => 4);
625                                                                                    $joinTable->{$joinKey});          my $source = $self->ComputeObjectSentence($sourceRelation);
626            my $target = $self->ComputeObjectSentence($targetRelation);
627            my $clause = $joinTable->{$joinKey};
628                  # Display them in a table row.                  # Display them in a table row.
629                  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";
630          }          }
631          # Close the table.          # Close the table.
632          print HTMLOUT _CloseTable();      $retVal .= _CloseTable();
633          # Close the document.      Trace("Built MetaData HTML.") if T(3);
634          print HTMLOUT "</body>\n</html>\n";      # Return the HTML.
635          # Close the file.      return $retVal;
         close HTMLOUT;  
         Trace("Built MetaData web page.") if T(3);  
636  }  }
637    
638  =head3 DumpMetaData  =head3 DumpMetaData
639    
640  C<< $database->DumpMetaData(); >>  C<< $erdb->DumpMetaData(); >>
641    
642  Return a dump of the metadata structure.  Return a dump of the metadata structure.
643    
# Line 311  Line 650 
650          return Data::Dumper::Dumper($self->{_metaData});          return Data::Dumper::Dumper($self->{_metaData});
651  }  }
652    
653    =head3 FindIndexForEntity
654    
655    C<< my $indexFound = ERDB::FindIndexForEntity($xml, $entityName, $attributeName); >>
656    
657    This method locates the entry in an entity's index list that begins with the
658    specified attribute name. If the entity has no index list, one will be
659    created. This method works on raw XML, not a live ERDB object.
660    
661    =over 4
662    
663    =item xml
664    
665    The raw XML structure defining the database.
666    
667    =item entityName
668    
669    The name of the relevant entity.
670    
671    =item attributeName
672    
673    The name of the attribute relevant to the search.
674    
675    =item RETURN
676    
677    The numerical index in the index list of the index entry for the specified entity and
678    attribute, or C<undef> if no such index exists.
679    
680    =back
681    
682    =cut
683    
684    sub FindIndexForEntity {
685        # Get the parameters.
686        my ($xml, $entityName, $attributeName) = @_;
687        # Declare the return variable.
688        my $retVal;
689        # Get the named entity.
690        my $entityData = $xml->{Entities}->{$entityName};
691        if (! $entityData) {
692            Confess("Entity $entityName not found in DBD structure.");
693        } else {
694            # Insure it has an index list.
695            if (! exists $entityData->{Indexes}) {
696                $entityData->{Indexes} = [];
697            } else {
698                # Search for the desired index.
699                my $indexList = $entityData->{Indexes};
700                my $n = scalar @{$indexList};
701                Trace("Searching $n indexes in index list for $entityName.") if T(2);
702                # We use an indexed FOR here because we're returning an
703                # index number instead of an object. We do THAT so we can
704                # delete the index from the list if needed.
705                for (my $i = 0; $i < $n && !defined($retVal); $i++) {
706                    my $index = $indexList->[$i];
707                    my $fields = $index->{IndexFields};
708                    # Technically this IF should be safe (that is, we are guaranteed
709                    # the existence of a "$fields->[0]"), because when we load the XML
710                    # we have SuppressEmpty specified.
711                    if ($fields->[0]->{name} eq $attributeName) {
712                        $retVal = $i;
713                    }
714                }
715            }
716        }
717        Trace("Index for $attributeName of $entityName found at position $retVal.") if defined($retVal) && T(3);
718        Trace("Index for $attributeName not found in $entityName.") if !defined($retVal) && T(3);
719        # Return the result.
720        return $retVal;
721    }
722    
723  =head3 CreateTables  =head3 CreateTables
724    
725  C<< $datanase->CreateTables(); >>  C<< $erdb->CreateTables(); >>
726    
727  This method creates the tables for the database from the metadata structure loaded by the  This method creates the tables for the database from the metadata structure loaded by the
728  constructor. It is expected this function will only be used on rare occasions, when the  constructor. It is expected this function will only be used on rare occasions, when the
# Line 325  Line 734 
734  sub CreateTables {  sub CreateTables {
735          # Get the parameters.          # Get the parameters.
736          my ($self) = @_;          my ($self) = @_;
737          my $metadata = $self->{_metaData};      # Get the relation names.
738          my $dbh = $self->{_dbh};      my @relNames = $self->GetTableNames();
739          # Loop through the entities.      # Loop through the relations.
740          while (my ($entityName, $entityData) = each %{$metadata->{Entities}}) {      for my $relationName (@relNames) {
                 # Tell the user what we're doing.  
                 Trace("Creating relations for entity $entityName.") if T(1);  
                 # Loop through the entity's relations.  
                 for my $relationName (keys %{$entityData->{Relations}}) {  
741                          # Create a table for this relation.                          # Create a table for this relation.
742                          $self->CreateTable($relationName);                          $self->CreateTable($relationName);
743                          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);  
744          }          }
745  }  }
746    
747  =head3 CreateTable  =head3 CreateTable
748    
749  C<< $database->CreateTable($tableName, $indexFlag); >>  C<< $erdb->CreateTable($tableName, $indexFlag, $estimatedRows); >>
750    
751  Create the table for a relation and optionally create its indexes.  Create the table for a relation and optionally create its indexes.
752    
# Line 359  Line 756 
756    
757  Name of the relation (which will also be the table name).  Name of the relation (which will also be the table name).
758    
759  =item $indexFlag  =item indexFlag
760    
761  TRUE if the indexes for the relation should be created, else FALSE. If FALSE,  TRUE if the indexes for the relation should be created, else FALSE. If FALSE,
762  L</CreateIndexes> must be called later to bring the indexes into existence.  L</CreateIndexes> must be called later to bring the indexes into existence.
763    
764    =item estimatedRows (optional)
765    
766    If specified, the estimated maximum number of rows for the relation. This
767    information allows the creation of tables using storage engines that are
768    faster but require size estimates, such as MyISAM.
769    
770  =back  =back
771    
772  =cut  =cut
773    
774  sub CreateTable {  sub CreateTable {
775          # Get the parameters.          # Get the parameters.
776          my ($self, $relationName, $indexFlag) = @_;      my ($self, $relationName, $indexFlag, $estimatedRows) = @_;
777          # Get the database handle.          # Get the database handle.
778          my $dbh = $self->{_dbh};          my $dbh = $self->{_dbh};
779          # 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 394  Line 797 
797          # Insure the table is not already there.          # Insure the table is not already there.
798          $dbh->drop_table(tbl => $relationName);          $dbh->drop_table(tbl => $relationName);
799          Trace("Table $relationName dropped.") if T(2);          Trace("Table $relationName dropped.") if T(2);
800        # If there are estimated rows, create an estimate so we can take advantage of
801        # faster DB technologies.
802        my $estimation = undef;
803        if ($estimatedRows) {
804            $estimation = [$self->EstimateRowSize($relationName), $estimatedRows];
805        }
806          # Create the table.          # Create the table.
807          Trace("Creating table $relationName: $fieldThing") if T(2);          Trace("Creating table $relationName: $fieldThing") if T(2);
808          $dbh->create_table(tbl => $relationName, flds => $fieldThing);      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);
809          Trace("Relation $relationName created in database.") if T(2);          Trace("Relation $relationName created in database.") if T(2);
810          # If we want to build the indexes, we do it here.      # If we want to build the indexes, we do it here. Note that the full-text search
811        # index will not be built until the table has been loaded.
812          if ($indexFlag) {          if ($indexFlag) {
813                  $self->CreateIndex($relationName);                  $self->CreateIndex($relationName);
814          }          }
815  }  }
816    
817  =head3 CreateIndex  =head3 VerifyFields
   
 C<< $database->CreateIndex($relationName); >>  
   
 Create the indexes for a relation. If a table is being loaded from a large source file (as  
 is the case in L</LoadTable>), it is best to create the indexes after the load. If that is  
 the case, then L</CreateTable> should be called with the index flag set to FALSE, and this  
 method used after the load to create the indexes for the table.  
   
 =cut  
   
 sub CreateIndex {  
         # Get the parameters.  
         my ($self, $relationName) = @_;  
         # Get the relation's descriptor.  
         my $relationData = $self->_FindRelation($relationName);  
         # Get the database handle.  
         my $dbh = $self->{_dbh};  
         # Now we need to create this relation's indexes. We do this by looping through its index table.  
         while (my ($indexName, $indexData) = each %{$relationData->{Indexes}}) {  
                 # Get the index's field list.  
                 my @fieldList = _FixNames(@{$indexData->{IndexFields}});  
                 my $flds = join(', ', @fieldList);  
                 # Get the index's uniqueness flag.  
                 my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');  
                 # Create the index.  
                 $dbh->create_index(idx => $indexName, tbl => $relationName, flds => $flds, unique => $unique);  
                 Trace("Index created: $indexName for $relationName ($flds)") if T(1);  
         }  
 }  
   
 =head3 LoadTables  
   
 C<< my $stats = $database->LoadTables($directoryName, $rebuild); >>  
818    
819  This method will load the database tables from a directory. The tables must already have been created  C<< my $count = $erdb->VerifyFields($relName, \@fieldList); >>
 in the database. (This can be done by calling L</CreateTables>.) The caller passes in a directory name;  
 all of the relations to be loaded must have a file in the directory with the same name as the relation  
 (optionally with a suffix of C<.dtx>). Each file must be a tab-delimited table of field values. Each  
 line of the file will be loaded as a row of the target relation table. The field values should be in  
 the same order as the fields in the relation tables generated by L</ShowMetaData>. The old data is  
 erased before the new data is loaded in.  
820    
821  A certain amount of translation automatically takes place. Ctrl-M characters are deleted, and  Run through the list of proposed field values, insuring that all the character fields are
822  tab and new-line characters inside a field are escaped as C<\t> and C<\n>, respectively. Dates must  below the maximum length. If any fields are too long, they will be truncated in place.
 be entered as a Unix timestamp, that is, as an integer number of seconds since the base epoch.  
823    
824  =over 4  =over 4
825    
826  =item directoryName  =item relName
827    
828  Name of the directory containing the relation files to be loaded.  Name of the relation for which the specified fields are destined.
829    
830  =item rebuild  =item fieldList
831    
832  TRUE if the tables should be dropped and rebuilt, else FALSE. This is, unfortunately, the  Reference to a list, in order, of the fields to be put into the relation.
 only way to erase existing data in the tables, since the TRUNCATE command is not supported  
 by all of the DB engines we use.  
833    
834  =item RETURN  =item RETURN
835    
836  Returns a statistical object describing the number of records read and a list of the error messages.  Returns the number of fields truncated.
837    
838  =back  =back
839    
840  =cut  =cut
841    
842  sub LoadTables {  sub VerifyFields {
843          # Get the parameters.          # Get the parameters.
844          my ($self, $directoryName, $rebuild) = @_;      my ($self, $relName, $fieldList) = @_;
845          # Start the timer.      # Initialize the return value.
846          my $startTime = gettimeofday;      my $retVal = 0;
847          # Clean any trailing slash from the directory name.      # Get the relation definition.
848          $directoryName =~ s!/\\$!!;      my $relData = $self->_FindRelation($relName);
849          # Declare the return variable.      # Get the list of field descriptors.
850          my $retVal = Stats->new();      my $fieldTypes = $relData->{Fields};
851          # Get the metadata structure.      my $fieldCount = scalar @{$fieldTypes};
852          my $metaData = $self->{_metaData};      # Loop through the two lists.
853          # Loop through the entities.      for (my $i = 0; $i < $fieldCount; $i++) {
854          for my $entity (values %{$metaData->{Entities}}) {          # Get the type of the current field.
855                  # Loop through the entity's relations.          my $fieldType = $fieldTypes->[$i]->{type};
856                  for my $relationName (keys %{$entity->{Relations}}) {          # If it's a character field, verify the length.
857                          # Try to load this relation.          if ($fieldType =~ /string/) {
858                          my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);              my $maxLen = $TypeTable{$fieldType}->{maxLen};
859                          # Accumulate the statistics.              my $oldString = $fieldList->[$i];
860                          $retVal->Accumulate($result);              if (length($oldString) > $maxLen) {
861                    # Here it's too big, so we truncate it.
862                    Trace("Truncating field $i in relation $relName to $maxLen characters from \"$oldString\".") if T(1);
863                    $fieldList->[$i] = substr $oldString, 0, $maxLen;
864                    $retVal++;
865                  }                  }
866          }          }
         # 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);  
867          }          }
868          # Add the duration of the load to the statistical object.      # Return the truncation count.
         $retVal->Add('duration', gettimeofday - $startTime);  
         # Return the accumulated statistics.  
869          return $retVal;          return $retVal;
870  }  }
871    
872  =head3 GetTableNames  =head3 DigestFields
873    
874  C<< my @names = $database->GetTableNames; >>  C<< $erdb->DigestFields($relName, $fieldList); >>
875    
876  Return a list of the relations required to implement this database.  Digest the strings in the field list that correspond to data type C<hash-string> in the
877    specified relation.
878    
879  =cut  =over 4
880    
881  sub GetTableNames {  =item relName
         # Get the parameters.  
         my ($self) = @_;  
         # Get the relation list from the metadata.  
         my $relationTable = $self->{_metaData}->{RelationTable};  
         # Return the relation names.  
         return keys %{$relationTable};  
 }  
882    
883  =head3 GetEntityTypes  Name of the relation to which the fields belong.
884    
885  C<< my @names = $database->GetEntityTypes; >>  =item fieldList
886    
887  Return a list of the entity type names.  List of field contents to be loaded into the relation.
888    
889  =cut  =back
890    
891  sub GetEntityTypes {  =cut
892          # Get the database object.  #: Return Type ;
893          my ($self) = @_;  sub DigestFields {
894          # Get the entity list from the metadata object.      # Get the parameters.
895          my $entityList = $self->{_metaData}->{Entities};      my ($self, $relName, $fieldList) = @_;
896          # Return the list of entity names in alphabetical order.      # Get the relation definition.
897          return sort keys %{$entityList};      my $relData = $self->_FindRelation($relName);
898        # Get the list of field descriptors.
899        my $fieldTypes = $relData->{Fields};
900        my $fieldCount = scalar @{$fieldTypes};
901        # Loop through the two lists.
902        for (my $i = 0; $i < $fieldCount; $i++) {
903            # Get the type of the current field.
904            my $fieldType = $fieldTypes->[$i]->{type};
905            # If it's a hash string, digest it in place.
906            if ($fieldType eq 'hash-string') {
907                $fieldList->[$i] = $self->DigestKey($fieldList->[$i]);
908            }
909        }
910  }  }
911    
912  =head3 Get  =head3 DigestKey
913    
914  C<< my $query = $database->Get(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  C<< my $digested = $erdb->DigestKey($keyValue); >>
915    
916  This method returns a query object for entities of a specified type using a specified filter.  Return the digested value of a symbolic key. The digested value can then be plugged into a
917  The filter is a standard WHERE/ORDER BY clause with question marks as parameter markers and each  key-based search into a table with key-type hash-string.
 field name represented in the form B<I<objectName>(I<fieldName>)>. For example, the  
 following call requests all B<Genome> objects for the genus specified in the variable  
 $genus.  
918    
919  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = ?", $genus); >>  Currently the digesting process is independent of the database structure, but that may not
920    always be the case, so this is an instance method instead of a static method.
921    
922  The WHERE clause contains a single question mark, so there is a single additional  =over 4
 parameter representing the parameter value. It would also be possible to code  
923    
924  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>  =item keyValue
925    
926  however, this version of the call would generate a syntax error if there were any quote  Key value to digest.
 characters inside the variable C<$genus>.  
927    
928  The use of the strange parenthesized notation for field names enables us to distinguish  =item RETURN
 hyphens contained within field names from minus signs that participate in the computation  
 of the WHERE clause. All of the methods that manipulate fields will use this same notation.  
929    
930  It is possible to specify multiple entity and relationship names in order to retrieve more than  Digested value of the key.
 one object's data at the same time, which allows highly complex joined queries. For example,  
931    
932  C<< $query = $sprout->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", $genus); >>  =back
933    
934  If multiple names are specified, then the query processor will automatically determine a  =cut
 join path between the entities and relationships. The algorithm used is very simplistic.  
 In particular, you can't specify any entity or relationship more than once, and if a  
 relationship is recursive, the path is determined by the order in which the entity  
 and the relationship appear. For example, consider a recursive relationship B<IsParentOf>  
 which relates B<People> objects to other B<People> objects. If the join path is  
 coded as C<['People', 'IsParentOf']>, then the people returned will be parents. If, however,  
 the join path is C<['IsParentOf', 'People']>, then the people returned will be children.  
935    
936  =over 4  sub DigestKey {
937        # Get the parameters.
938        my ($self, $keyValue) = @_;
939        # Compute the digest.
940        my $retVal = md5_base64($keyValue);
941        # Return the result.
942        return $retVal;
943    }
944    
945  =item objectNames  =head3 CreateIndex
946    
947  List containing the names of the entity and relationship objects to be retrieved.  C<< $erdb->CreateIndex($relationName); >>
948    
949  =item filterClause  Create the indexes for a relation. If a table is being loaded from a large source file (as
950    is the case in L</LoadTable>), it is sometimes best to create the indexes after the load.
951    If that is the case, then L</CreateTable> should be called with the index flag set to
952    FALSE, and this method used after the load to create the indexes for the table.
953    
954  WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  =cut
 be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be  
 specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified  
 in the filter clause should be added to the parameter list as additional parameters. The  
 fields in a filter clause can come from primary entity relations, relationship relations,  
 or secondary entity relations; however, all of the entities and relationships involved must  
 be included in the list of object names.  
955    
956  The filter clause can also specify a sort order. To do this, simply follow the filter string  sub CreateIndex {
957  with an ORDER BY clause. For example, the following filter string gets all genomes for a      # Get the parameters.
958  particular genus and sorts them by species name.      my ($self, $relationName) = @_;
959        # Get the relation's descriptor.
960        my $relationData = $self->_FindRelation($relationName);
961        # Get the database handle.
962        my $dbh = $self->{_dbh};
963        # Now we need to create this relation's indexes. We do this by looping through its index table.
964        my $indexHash = $relationData->{Indexes};
965        for my $indexName (keys %{$indexHash}) {
966            my $indexData = $indexHash->{$indexName};
967            # Get the index's field list.
968            my @rawFields = @{$indexData->{IndexFields}};
969            # Get a hash of the relation's field types.
970            my %types = map { $_->{name} => $_->{type} } @{$relationData->{Fields}};
971            # We need to check for text fields so we can append a length limitation for them. To do
972            # that, we need the relation's field list.
973            my $relFields = $relationData->{Fields};
974            for (my $i = 0; $i <= $#rawFields; $i++) {
975                # Get the field type.
976                my $field = $rawFields[$i];
977                my $type = $types{$field};
978                # Ask if it requires using prefix notation for the index.
979                my $mod = $TypeTable{$type}->{indexMod};
980                Trace("Field $field ($i) in $relationName has type $type and indexMod $mod.") if T(3);
981                if ($mod) {
982                    # Append the prefix length to the field name,
983                    $rawFields[$i] .= "($mod)";
984                }
985            }
986            my @fieldList = _FixNames(@rawFields);
987            my $flds = join(', ', @fieldList);
988            # Get the index's uniqueness flag.
989            my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
990            # Create the index.
991            my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
992                                        flds => $flds, kind => $unique);
993            if ($rv) {
994                Trace("Index created: $indexName for $relationName ($flds)") if T(1);
995            } else {
996                Confess("Error creating index $indexName for $relationName using ($flds): " . $dbh->error_message());
997            }
998        }
999    }
1000    
1001  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>  =head3 GetSecondaryFields
1002    
1003  The rules for field references in a sort order are the same as those for field references in the  C<< my %fieldTuples = $erdb->GetSecondaryFields($entityName); >>
1004  filter clause in general; however, odd things may happen if a sort field is from a secondary  
1005  relation.  This method will return a list of the name and type of each of the secondary
1006    fields for a specified entity. Secondary fields are stored in two-column tables
1007    in addition to the primary entity table. This enables the field to have no value
1008    or to have multiple values.
1009    
1010    =over 4
1011    
1012  =item param1, param2, ..., paramN  =item entityName
1013    
1014  Parameter values to be substituted into the filter clause.  Name of the entity whose secondary fields are desired.
1015    
1016  =item RETURN  =item RETURN
1017    
1018  Returns a B<DBQuery> that can be used to iterate through all of the results.  Returns a hash mapping the field names to their field types.
1019    
1020  =back  =back
1021    
1022  =cut  =cut
1023    
1024  sub Get {  sub GetSecondaryFields {
1025          # Get the parameters.          # Get the parameters.
1026          my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $entityName) = @_;
1027          # Construct the SELECT statement. The general pattern is      # Declare the return variable.
1028          #      my %retVal = ();
1029          # SELECT name1.*, name2.*, ... nameN.* FROM name1, name2, ... nameN      # Look for the entity.
1030          #      my $table = $self->GetFieldTable($entityName);
1031          my $dbh = $self->{_dbh};      # Loop through the fields, pulling out the secondaries.
1032          my $command = "SELECT DISTINCT " . join('.*, ', @{$objectNames}) . ".* FROM " .      for my $field (sort keys %{$table}) {
1033                                  join(', ', @{$objectNames});          if ($table->{$field}->{relation} ne $entityName) {
1034          # Check for a filter clause.              # Here we have a secondary field.
1035          if ($filterClause) {              $retVal{$field} = $table->{$field}->{type};
                 # Here we have one, so we convert its field names and add it to the query. First,  
                 # We create a copy of the filter string we can work with.  
                 my $filterString = $filterClause;  
                 # Next, we sort the object names by length. This helps protect us from finding  
                 # object names inside other object names when we're doing our search and replace.  
                 my @sortedNames = sort { length($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;  
                 }  
                 # We are ready to begin. We loop through the object names, replacing each  
                 # object name's field references by the corresponding SQL field reference.  
                 # Along the way, if we find a secondary relation, we will need to add it  
                 # 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";  
1036                  }                  }
1037          }          }
1038          Trace("SQL query: $command") if T(2);      # Return the result.
1039          Trace("PARMS: '" . (join "', '", @params) . "'") if (T(3) && (@params > 0));      return %retVal;
         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;  
1040  }  }
1041    
1042  =head3 ComputeObjectSentence  =head3 GetFieldRelationName
1043    
1044  C<< my $sentence = $database->ComputeObjectSentence($objectName); >>  C<< my $name = $erdb->GetFieldRelationName($objectName, $fieldName); >>
1045    
1046  Check an object name, and if it is a relationship convert it to a relationship sentence.  Return the name of the relation containing a specified field.
1047    
1048  =over 4  =over 4
1049    
1050  =item objectName  =item objectName
1051    
1052  Name of the entity or relationship.  Name of the entity or relationship containing the field.
1053    
1054    =item fieldName
1055    
1056    Name of the relevant field in that entity or relationship.
1057    
1058  =item RETURN  =item RETURN
1059    
1060  Returns a string containing the entity name or a relationship sentence.  Returns the name of the database relation containing the field, or C<undef> if
1061    the field does not exist.
1062    
1063  =back  =back
1064    
1065  =cut  =cut
1066    
1067  sub ComputeObjectSentence {  sub GetFieldRelationName {
1068          # Get the parameters.          # Get the parameters.
1069          my ($self, $objectName) = @_;      my ($self, $objectName, $fieldName) = @_;
1070          # Set the default return value.      # Declare the return variable.
1071          my $retVal = $objectName;      my $retVal;
1072          # Look for the object as a relationship.      # Get the object field table.
1073          my $relTable = $self->{_metaData}->{Relationships};      my $table = $self->GetFieldTable($objectName);
1074          if (exists $relTable->{$objectName}) {      # Only proceed if the field exists.
1075                  # Get the relationship sentence.      if (exists $table->{$fieldName}) {
1076                  $retVal = _ComputeRelationshipSentence($objectName, $relTable->{$objectName});          # Determine the name of the relation that contains this field.
1077            $retVal = $table->{$fieldName}->{relation};
1078          }          }
1079          # Return the result.          # Return the result.
1080          return $retVal;          return $retVal;
1081  }  }
1082    
1083  =head3 DumpRelations  =head3 DeleteValue
1084    
1085  C<< $database->DumpRelations($outputDirectory); >>  C<< my $numDeleted = $erdb->DeleteValue($entityName, $id, $fieldName, $fieldValue); >>
1086    
1087  Write the contents of all the relations to tab-delimited files in the specified directory.  Delete secondary field values from the database. This method can be used to delete all
1088  Each file will have the same name as the relation dumped, with an extension of DTX.  values of a specified field for a particular entity instance, or only a single value.
1089    
1090    Secondary fields are stored in two-column relations separate from an entity's primary
1091    table, and as a result a secondary field can legitimately have no value or multiple
1092    values. Therefore, it makes sense to talk about deleting secondary fields where it
1093    would not make sense for primary fields.
1094    
1095  =over 4  =over 4
1096    
1097  =item outputDirectory  =item entityName
1098    
1099  Name of the directory into which the relation files should be dumped.  Name of the entity from which the fields are to be deleted.
1100    
1101    =item id
1102    
1103    ID of the entity instance to be processed. If the instance is not found, this
1104    method will have no effect. If C<undef> is specified, all values for all of
1105    the entity instances will be deleted.
1106    
1107    =item fieldName
1108    
1109    Name of the field whose values are to be deleted.
1110    
1111    =item fieldValue (optional)
1112    
1113    Value to be deleted. If not specified, then all values of the specified field
1114    will be deleted for the entity instance. If specified, then only the values which
1115    match this parameter will be deleted.
1116    
1117    =item RETURN
1118    
1119    Returns the number of rows deleted.
1120    
1121  =back  =back
1122    
1123  =cut  =cut
1124    
1125  sub DumpRelations {  sub DeleteValue {
1126          # Get the parameters.          # Get the parameters.
1127          my ($self, $outputDirectory) = @_;      my ($self, $entityName, $id, $fieldName, $fieldValue) = @_;
1128          # Now we need to run through all the relations. First, we loop through the entities.      # Declare the return value.
1129          my $metaData = $self->{_metaData};      my $retVal = 0;
1130          my $entities = $metaData->{Entities};      # We need to set up an SQL command to do the deletion. First, we
1131          while (my ($entityName, $entityStructure) = each %{$entities}) {      # find the name of the field's relation.
1132                  # Get the entity's relations.      my $table = $self->GetFieldTable($entityName);
1133                  my $relationList = $entityStructure->{Relations};      my $field = $table->{$fieldName};
1134                  # Loop through the relations, dumping them.      my $relation = $field->{relation};
1135                  while (my ($relationName, $relation) = each %{$relationList}) {      # Make sure this is a secondary field.
1136                          $self->_DumpRelation($outputDirectory, $relationName, $relation);      if ($relation eq $entityName) {
1137                  }          Confess("Cannot delete values of $fieldName for $entityName.");
1138        } else {
1139            # Set up the SQL command to delete all values.
1140            my $sql = "DELETE FROM $relation";
1141            # Build the filter.
1142            my @filters = ();
1143            my @parms = ();
1144            # Check for a filter by ID.
1145            if (defined $id) {
1146                push @filters, "id = ?";
1147                push @parms, $id;
1148            }
1149            # Check for a filter by value.
1150            if (defined $fieldValue) {
1151                push @filters, "$fieldName = ?";
1152                push @parms, $fieldValue;
1153            }
1154            # Append the filters to the command.
1155            if (@filters) {
1156                $sql .= " WHERE " . join(" AND ", @filters);
1157          }          }
1158          # Next, we loop through the relationships.          # Execute the command.
1159          my $relationships = $metaData->{Relationships};          my $dbh = $self->{_dbh};
1160          while (my ($relationshipName, $relationshipStructure) = each %{$relationships}) {          $retVal = $dbh->SQL($sql, 0, @parms);
                 # Dump this relationship's relation.  
                 $self->_DumpRelation($outputDirectory, $relationshipName, $relationshipStructure->{Relations}->{$relationshipName});  
1161          }          }
1162        # Return the result.
1163        return $retVal;
1164  }  }
1165    
1166  =head3 InsertObject  =head3 LoadTables
   
 C<< my $ok = $database->InsertObject($objectType, \%fieldHash); >>  
   
 Insert an object into the database. The object is defined by a type name and then a hash  
 of field names to values. Field values in the primary relation are represented by scalars.  
 (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>.  
1167    
1168  C<< $database->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>
1169    
1170  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and  This method will load the database tables from a directory. The tables must already have been created
1171  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.  in the database. (This can be done by calling L</CreateTables>.) The caller passes in a directory name;
1172    all of the relations to be loaded must have a file in the directory with the same name as the relation
1173    (optionally with a suffix of C<.dtx>). Each file must be a tab-delimited table of field values. Each
1174    line of the file will be loaded as a row of the target relation table. The field values should be in
1175    the same order as the fields in the relation tables generated by L</ShowMetaData>. The old data is
1176    erased before the new data is loaded in.
1177    
1178  C<< $database->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>  A certain amount of translation automatically takes place. Ctrl-M characters are deleted, and
1179    tab and new-line characters inside a field are escaped as C<\t> and C<\n>, respectively. Dates must
1180    be entered as a Unix timestamp, that is, as an integer number of seconds since the base epoch.
1181    
1182  =over 4  =over 4
1183    
1184  =item newObjectType  =item directoryName
1185    
1186  Type name of the object to insert.  Name of the directory containing the relation files to be loaded.
1187    
1188  =item fieldHash  =item rebuild
1189    
1190  Hash of field names to values.  TRUE if the tables should be dropped and rebuilt, else FALSE. This is, unfortunately, the
1191    only way to erase existing data in the tables, since the TRUNCATE command is not supported
1192    by all of the DB engines we use.
1193    
1194  =item RETURN  =item RETURN
1195    
1196  Returns 1 if successful, 0 if an error occurred.  Returns a statistical object describing the number of records read and a list of the error messages.
1197    
1198    =back
1199    
1200    =cut
1201    
1202    sub LoadTables {
1203        # Get the parameters.
1204        my ($self, $directoryName, $rebuild) = @_;
1205        # Start the timer.
1206        my $startTime = gettimeofday;
1207        # Clean any trailing slash from the directory name.
1208        $directoryName =~ s!/\\$!!;
1209        # Declare the return variable.
1210        my $retVal = Stats->new();
1211        # Get the relation names.
1212        my @relNames = $self->GetTableNames();
1213        for my $relationName (@relNames) {
1214            # Try to load this relation.
1215            my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);
1216            # Accumulate the statistics.
1217            $retVal->Accumulate($result);
1218        }
1219        # Add the duration of the load to the statistical object.
1220        $retVal->Add('duration', gettimeofday - $startTime);
1221        # Return the accumulated statistics.
1222        return $retVal;
1223    }
1224    
1225    
1226    =head3 GetTableNames
1227    
1228    C<< my @names = $erdb->GetTableNames; >>
1229    
1230    Return a list of the relations required to implement this database.
1231    
1232    =cut
1233    
1234    sub GetTableNames {
1235        # Get the parameters.
1236        my ($self) = @_;
1237        # Get the relation list from the metadata.
1238        my $relationTable = $self->{_metaData}->{RelationTable};
1239        # Return the relation names.
1240        return keys %{$relationTable};
1241    }
1242    
1243    =head3 GetEntityTypes
1244    
1245    C<< my @names = $erdb->GetEntityTypes; >>
1246    
1247    Return a list of the entity type names.
1248    
1249    =cut
1250    
1251    sub GetEntityTypes {
1252        # Get the database object.
1253        my ($self) = @_;
1254        # Get the entity list from the metadata object.
1255        my $entityList = $self->{_metaData}->{Entities};
1256        # Return the list of entity names in alphabetical order.
1257        return sort keys %{$entityList};
1258    }
1259    
1260    =head3 GetDataTypes
1261    
1262    C<< my %types = ERDB::GetDataTypes(); >>
1263    
1264    Return a table of ERDB data types. The table returned is a hash of hashes.
1265    The keys of the big hash are the datatypes. Each smaller hash has several
1266    values used to manage the data. The most interesting is the SQL type (key
1267    C<sqlType>) and the descriptive node (key C<notes>).
1268    
1269    Note that changing the values in the smaller hashes will seriously break
1270    things, so this data should be treated as read-only.
1271    
1272    =cut
1273    
1274    sub GetDataTypes {
1275        return %TypeTable;
1276    }
1277    
1278    
1279    =head3 IsEntity
1280    
1281    C<< my $flag = $erdb->IsEntity($entityName); >>
1282    
1283    Return TRUE if the parameter is an entity name, else FALSE.
1284    
1285    =over 4
1286    
1287    =item entityName
1288    
1289    Object name to be tested.
1290    
1291    =item RETURN
1292    
1293    Returns TRUE if the specified string is an entity name, else FALSE.
1294    
1295    =back
1296    
1297    =cut
1298    
1299    sub IsEntity {
1300        # Get the parameters.
1301        my ($self, $entityName) = @_;
1302        # Test to see if it's an entity.
1303        return exists $self->{_metaData}->{Entities}->{$entityName};
1304    }
1305    
1306    =head3 Get
1307    
1308    C<< my $query = $erdb->Get(\@objectNames, $filterClause, \@params); >>
1309    
1310    This method returns a query object for entities of a specified type using a specified filter.
1311    The filter is a standard WHERE/ORDER BY clause with question marks as parameter markers and each
1312    field name represented in the form B<I<objectName>(I<fieldName>)>. For example, the
1313    following call requests all B<Genome> objects for the genus specified in the variable
1314    $genus.
1315    
1316    C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", [$genus]); >>
1317    
1318    The WHERE clause contains a single question mark, so there is a single additional
1319    parameter representing the parameter value. It would also be possible to code
1320    
1321    C<< $query = $erdb->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>
1322    
1323    however, this version of the call would generate a syntax error if there were any quote
1324    characters inside the variable C<$genus>.
1325    
1326    The use of the strange parenthesized notation for field names enables us to distinguish
1327    hyphens contained within field names from minus signs that participate in the computation
1328    of the WHERE clause. All of the methods that manipulate fields will use this same notation.
1329    
1330    It is possible to specify multiple entity and relationship names in order to retrieve more than
1331    one object's data at the same time, which allows highly complex joined queries. For example,
1332    
1333    C<< $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]); >>
1334    
1335    If multiple names are specified, then the query processor will automatically determine a
1336    join path between the entities and relationships. The algorithm used is very simplistic.
1337    In particular, if a relationship is recursive, the path is determined by the order in which
1338    the entity and the relationship appear. For example, consider a recursive relationship
1339    B<IsParentOf> which relates B<People> objects to other B<People> objects. If the join path is
1340    coded as C<['People', 'IsParentOf']>, then the people returned will be parents. If, however,
1341    the join path is C<['IsParentOf', 'People']>, then the people returned will be children.
1342    
1343    If an entity or relationship is mentioned twice, the name for the second occurrence will
1344    be suffixed with C<2>, the third occurrence will be suffixed with C<3>, and so forth. So,
1345    for example, if we have C<['Feature', 'HasContig', 'Contig', 'HasContig']>, then the
1346    B<to-link> field of the first B<HasContig> is specified as C<HasContig(to-link)>, while
1347    the B<to-link> field of the second B<HasContig> is specified as C<HasContig2(to-link)>.
1348    
1349    =over 4
1350    
1351    =item objectNames
1352    
1353    List containing the names of the entity and relationship objects to be retrieved.
1354    
1355    =item filterClause
1356    
1357    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1358    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
1359    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
1360    in the filter clause should be added to the parameter list as additional parameters. The
1361    fields in a filter clause can come from primary entity relations, relationship relations,
1362    or secondary entity relations; however, all of the entities and relationships involved must
1363    be included in the list of object names.
1364    
1365    The filter clause can also specify a sort order. To do this, simply follow the filter string
1366    with an ORDER BY clause. For example, the following filter string gets all genomes for a
1367    particular genus and sorts them by species name.
1368    
1369    C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
1370    
1371    Note that the case is important. Only an uppercase "ORDER BY" with a single space will
1372    be processed. The idea is to make it less likely to find the verb by accident.
1373    
1374    The rules for field references in a sort order are the same as those for field references in the
1375    filter clause in general; however, odd things may happen if a sort field is from a secondary
1376    relation.
1377    
1378    Finally, you can limit the number of rows returned by adding a LIMIT clause. The LIMIT must
1379    be the last thing in the filter clause, and it contains only the word "LIMIT" followed by
1380    a positive number. So, for example
1381    
1382    C<< "Genome(genus) = ? ORDER BY Genome(species) LIMIT 10" >>
1383    
1384    will only return the first ten genomes for the specified genus. The ORDER BY clause is not
1385    required. For example, to just get the first 10 genomes in the B<Genome> table, you could
1386    use
1387    
1388    C<< "LIMIT 10" >>
1389    
1390    =item params
1391    
1392    Reference to a list of parameter values to be substituted into the filter clause.
1393    
1394    =item RETURN
1395    
1396    Returns a B<DBQuery> that can be used to iterate through all of the results.
1397    
1398    =back
1399    
1400    =cut
1401    
1402    sub Get {
1403        # Get the parameters.
1404        my ($self, $objectNames, $filterClause, $params) = @_;
1405        # Process the SQL stuff.
1406        my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1407            $self->_SetupSQL($objectNames, $filterClause);
1408        # Create the query.
1409        my $command = "SELECT DISTINCT " . join(".*, ", @{$mappedNameListRef}) .
1410            ".* $suffix";
1411        my $sth = $self->_GetStatementHandle($command, $params);
1412        # Now we create the relation map, which enables DBQuery to determine the order, name
1413        # and mapped name for each object in the query.
1414        my @relationMap = ();
1415        for my $mappedName (@{$mappedNameListRef}) {
1416            push @relationMap, [$mappedName, $mappedNameHashRef->{$mappedName}];
1417        }
1418        # Return the statement object.
1419        my $retVal = DBQuery::_new($self, $sth, \@relationMap);
1420        return $retVal;
1421    }
1422    
1423    
1424    
1425    =head3 Search
1426    
1427    C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>
1428    
1429    Perform a full text search with filtering. The search will be against a specified object
1430    in the object name list. That object will get an extra field containing the search
1431    relevance. Note that except for the search expression, the parameters of this method are
1432    the same as those for L</Get> and follow the same rules.
1433    
1434    =over 4
1435    
1436    =item searchExpression
1437    
1438    Boolean search expression for the text fields of the target object. The default mode for
1439    a Boolean search expression is OR, but we want the default to be AND, so we will
1440    add a C<+> operator to each word with no other operator before it.
1441    
1442    =item idx
1443    
1444    Index in the I<$objectNames> list of the table to be searched in full-text mode.
1445    
1446    =item objectNames
1447    
1448    List containing the names of the entity and relationship objects to be retrieved.
1449    
1450    =item filterClause
1451    
1452    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1453    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
1454    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
1455    in the filter clause should be added to the parameter list as additional parameters. The
1456    fields in a filter clause can come from primary entity relations, relationship relations,
1457    or secondary entity relations; however, all of the entities and relationships involved must
1458    be included in the list of object names.
1459    
1460    =item params
1461    
1462    Reference to a list of parameter values to be substituted into the filter clause.
1463    
1464    =item RETURN
1465    
1466    Returns a query object for the specified search.
1467    
1468    =back
1469    
1470    =cut
1471    
1472    sub Search {
1473        # Get the parameters.
1474        my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1475        # Declare the return variable.
1476        my $retVal;
1477        # Create a safety copy of the parameter list. Note we have to be careful to insure
1478        # a parameter list exists before we copy it.
1479        my @myParams = ();
1480        if (defined $params) {
1481            @myParams = @{$params};
1482        }
1483        # Get the first object's structure so we have access to the searchable fields.
1484        my $object1Name = $objectNames->[$idx];
1485        my $object1Structure = $self->_GetStructure($object1Name);
1486        # Get the field list.
1487        if (! exists $object1Structure->{searchFields}) {
1488            Confess("No searchable index for $object1Name.");
1489        } else {
1490            # Get the field list.
1491            my @fields = @{$object1Structure->{searchFields}};
1492            # Clean the search expression.
1493            my $actualKeywords = $self->CleanKeywords($searchExpression);
1494            # Prefix a "+" to each uncontrolled word. This converts the default
1495            # search mode from OR to AND.
1496            $actualKeywords =~ s/(^|\s)(\w|")/$1\+$2/g;
1497            Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1498            # We need two match expressions, one for the filter clause and one in the
1499            # query itself. Both will use a parameter mark, so we need to push the
1500            # search expression onto the front of the parameter list twice.
1501            unshift @myParams, $actualKeywords, $actualKeywords;
1502            # Build the match expression.
1503            my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
1504            my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
1505            # Process the SQL stuff.
1506            my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1507                $self->_SetupSQL($objectNames, $filterClause, $matchClause);
1508            # Create the query. Note that the match clause is inserted at the front of
1509            # the select fields.
1510            my $command = "SELECT DISTINCT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .
1511                ".* $suffix";
1512            my $sth = $self->_GetStatementHandle($command, \@myParams);
1513            # Now we create the relation map, which enables DBQuery to determine the order, name
1514            # and mapped name for each object in the query.
1515            my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
1516            # Return the statement object.
1517            $retVal = DBQuery::_new($self, $sth, \@relationMap, $object1Name);
1518        }
1519        return $retVal;
1520    }
1521    
1522    =head3 GetFlat
1523    
1524    C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>
1525    
1526    This is a variation of L</GetAll> that asks for only a single field per record and
1527    returns a single flattened list.
1528    
1529    =over 4
1530    
1531    =item objectNames
1532    
1533    List containing the names of the entity and relationship objects to be retrieved.
1534    
1535    =item filterClause
1536    
1537    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1538    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
1539    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
1540    parameter list as additional parameters. The fields in a filter clause can come from primary
1541    entity relations, relationship relations, or secondary entity relations; however, all of the
1542    entities and relationships involved must be included in the list of object names.
1543    
1544    =item parameterList
1545    
1546    List of the parameters to be substituted in for the parameters marks in the filter clause.
1547    
1548    =item field
1549    
1550    Name of the field to be used to get the elements of the list returned.
1551    
1552    =item RETURN
1553    
1554    Returns a list of values.
1555    
1556    =back
1557    
1558    =cut
1559    #: Return Type @;
1560    sub GetFlat {
1561        # Get the parameters.
1562        my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
1563        # Construct the query.
1564        my $query = $self->Get($objectNames, $filterClause, $parameterList);
1565        # Create the result list.
1566        my @retVal = ();
1567        # Loop through the records, adding the field values found to the result list.
1568        while (my $row = $query->Fetch()) {
1569            push @retVal, $row->Value($field);
1570        }
1571        # Return the list created.
1572        return @retVal;
1573    }
1574    
1575    =head3 SpecialFields
1576    
1577    C<< my %specials = $erdb->SpecialFields($entityName); >>
1578    
1579    Return a hash mapping special fields in the specified entity to the value of their
1580    C<special> attribute. This enables the subclass to get access to the special field
1581    attributes without needed to plumb the internal ERDB data structures.
1582    
1583    =over 4
1584    
1585    =item entityName
1586    
1587    Name of the entity whose special fields are desired.
1588    
1589    =item RETURN
1590    
1591    Returns a hash. The keys of the hash are the special field names, and the values
1592    are the values from each special field's C<special> attribute.
1593    
1594    =back
1595    
1596    =cut
1597    
1598    sub SpecialFields {
1599        # Get the parameters.
1600        my ($self, $entityName) = @_;
1601        # Declare the return variable.
1602        my %retVal = ();
1603        # Find the entity's data structure.
1604        my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1605        # Loop through its fields, adding each special field to the return hash.
1606        my $fieldHash = $entityData->{Fields};
1607        for my $fieldName (keys %{$fieldHash}) {
1608            my $fieldData = $fieldHash->{$fieldName};
1609            if (exists $fieldData->{special}) {
1610                $retVal{$fieldName} = $fieldData->{special};
1611            }
1612        }
1613        # Return the result.
1614        return %retVal;
1615    }
1616    
1617    =head3 Delete
1618    
1619    C<< my $stats = $erdb->Delete($entityName, $objectID, %options); >>
1620    
1621    Delete an entity instance from the database. The instance is deleted along with all entity and
1622    relationship instances dependent on it. The definition of I<dependence> is recursive.
1623    
1624    An object is always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many
1625    relationship connected to a dependent entity or if it is the "to" entity connected to a 1-to-many
1626    dependent relationship.
1627    
1628    =over 4
1629    
1630    =item entityName
1631    
1632    Name of the entity type for the instance being deleted.
1633    
1634    =item objectID
1635    
1636    ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),
1637    then it is presumed to by a LIKE pattern.
1638    
1639    =item options
1640    
1641    A hash detailing the options for this delete operation.
1642    
1643    =item RETURN
1644    
1645    Returns a statistics object indicating how many records of each particular table were
1646    deleted.
1647    
1648    =back
1649    
1650    The permissible options for this method are as follows.
1651    
1652    =over 4
1653    
1654    =item testMode
1655    
1656    If TRUE, then the delete statements will be traced, but no changes will be made to the database.
1657    
1658    =item keepRoot
1659    
1660    If TRUE, then the entity instances will not be deleted, only the dependent records.
1661    
1662    =back
1663    
1664    =cut
1665    #: Return Type $%;
1666    sub Delete {
1667        # Get the parameters.
1668        my ($self, $entityName, $objectID, %options) = @_;
1669        # Declare the return variable.
1670        my $retVal = Stats->new();
1671        # Get the DBKernel object.
1672        my $db = $self->{_dbh};
1673        # We're going to generate all the paths branching out from the starting entity. One of
1674        # the things we have to be careful about is preventing loops. We'll use a hash to
1675        # determine if we've hit a loop.
1676        my %alreadyFound = ();
1677        # These next lists will serve as our result stack. We start by pushing object lists onto
1678        # the stack, and then popping them off to do the deletes. This means the deletes will
1679        # start with the longer paths before getting to the shorter ones. That, in turn, makes
1680        # sure we don't delete records that might be needed to forge relationships back to the
1681        # original item. We have two lists-- one for TO-relationships, and one for
1682        # FROM-relationships and entities.
1683        my @fromPathList = ();
1684        my @toPathList = ();
1685        # This final list is used to remember what work still needs to be done. We push paths
1686        # onto the list, then pop them off to extend the paths. We prime it with the starting
1687        # point. Note that we will work hard to insure that the last item on a path in the
1688        # to-do list is always an entity.
1689        my @todoList = ([$entityName]);
1690        while (@todoList) {
1691            # Get the current path.
1692            my $current = pop @todoList;
1693            # Copy it into a list.
1694            my @stackedPath = @{$current};
1695            # Pull off the last item on the path. It will always be an entity.
1696            my $myEntityName = pop @stackedPath;
1697            # Add it to the alreadyFound list.
1698            $alreadyFound{$myEntityName} = 1;
1699            # Figure out if we need to delete this entity.
1700            if ($myEntityName ne $entityName || ! $options{keepRoot}) {
1701                # Get the entity data.
1702                my $entityData = $self->_GetStructure($myEntityName);
1703                # Loop through the entity's relations. A DELETE command will be needed for each of them.
1704                my $relations = $entityData->{Relations};
1705                for my $relation (keys %{$relations}) {
1706                    my @augmentedList = (@stackedPath, $relation);
1707                    push @fromPathList, \@augmentedList;
1708                }
1709            }
1710            # Now we need to look for relationships connected to this entity.
1711            my $relationshipList = $self->{_metaData}->{Relationships};
1712            for my $relationshipName (keys %{$relationshipList}) {
1713                my $relationship = $relationshipList->{$relationshipName};
1714                # Check the FROM field. We're only interested if it's us.
1715                if ($relationship->{from} eq $myEntityName) {
1716                    # Add the path to this relationship.
1717                    my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1718                    push @fromPathList, \@augmentedList;
1719                    # Check the arity. If it's MM we're done. If it's 1M
1720                    # and the target hasn't been seen yet, we want to
1721                    # stack the entity for future processing.
1722                    if ($relationship->{arity} eq '1M') {
1723                        my $toEntity = $relationship->{to};
1724                        if (! exists $alreadyFound{$toEntity}) {
1725                            # Here we have a new entity that's dependent on
1726                            # the current entity, so we need to stack it.
1727                            my @stackList = (@augmentedList, $toEntity);
1728                            push @fromPathList, \@stackList;
1729                        } else {
1730                            Trace("$toEntity ignored because it occurred previously.") if T(4);
1731                        }
1732                    }
1733                }
1734                # Now check the TO field. In this case only the relationship needs
1735                # deletion.
1736                if ($relationship->{to} eq $myEntityName) {
1737                    my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1738                    push @toPathList, \@augmentedList;
1739                }
1740            }
1741        }
1742        # Create the first qualifier for the WHERE clause. This selects the
1743        # keys of the primary entity records to be deleted. When we're deleting
1744        # from a dependent table, we construct a join path from the first qualifier
1745        # to the table containing the dependent records to delete.
1746        my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
1747        # We need to make two passes. The first is through the to-list, and
1748        # the second through the from-list. The from-list is second because
1749        # the to-list may need to pass through some of the entities the
1750        # from-list would delete.
1751        my %stackList = ( from_link => \@fromPathList, to_link => \@toPathList );
1752        # Now it's time to do the deletes. We do it in two passes.
1753        for my $keyName ('to_link', 'from_link') {
1754            # Get the list for this key.
1755            my @pathList = @{$stackList{$keyName}};
1756            Trace(scalar(@pathList) . " entries in path list for $keyName.") if T(3);
1757            # Loop through this list.
1758            while (my $path = pop @pathList) {
1759                # Get the table whose rows are to be deleted.
1760                my @pathTables = @{$path};
1761                # Start the DELETE statement. We need to call DBKernel because the
1762                # syntax of a DELETE-USING varies among DBMSs.
1763                my $target = $pathTables[$#pathTables];
1764                my $stmt = $db->SetUsing(@pathTables);
1765                # Now start the WHERE. The first thing is the ID field from the starting table. That
1766                # starting table will either be the entity relation or one of the entity's
1767                # sub-relations.
1768                $stmt .= " WHERE $pathTables[0].id $qualifier";
1769                # Now we run through the remaining entities in the path, connecting them up.
1770                for (my $i = 1; $i <= $#pathTables; $i += 2) {
1771                    # Connect the current relationship to the preceding entity.
1772                    my ($entity, $rel) = @pathTables[$i-1,$i];
1773                    # The style of connection depends on the direction of the relationship.
1774                    $stmt .= " AND $entity.id = $rel.$keyName";
1775                    if ($i + 1 <= $#pathTables) {
1776                        # Here there's a next entity, so connect that to the relationship's
1777                        # to-link.
1778                        my $entity2 = $pathTables[$i+1];
1779                        $stmt .= " AND $rel.to_link = $entity2.id";
1780                    }
1781                }
1782                # Now we have our desired DELETE statement.
1783                if ($options{testMode}) {
1784                    # Here the user wants to trace without executing.
1785                    Trace($stmt) if T(0);
1786                } else {
1787                    # Here we can delete. Note that the SQL method dies with a confession
1788                    # if an error occurs, so we just go ahead and do it.
1789                    Trace("Executing delete from $target using '$objectID'.") if T(3);
1790                    my $rv = $db->SQL($stmt, 0, $objectID);
1791                    # Accumulate the statistics for this delete. The only rows deleted
1792                    # are from the target table, so we use its name to record the
1793                    # statistic.
1794                    $retVal->Add($target, $rv);
1795                }
1796            }
1797        }
1798        # Return the result.
1799        return $retVal;
1800    }
1801    
1802    =head3 Disconnect
1803    
1804    C<< $erdb->Disconnect($relationshipName, $originEntityName, $originEntityID); >>
1805    
1806    Disconnect an entity instance from all the objects to which it is related. This
1807    will delete each relationship instance that connects to the specified entity.
1808    
1809    =over 4
1810    
1811    =item relationshipName
1812    
1813    Name of the relationship whose instances are to be deleted.
1814    
1815    =item originEntityName
1816    
1817    Name of the entity that is to be disconnected.
1818    
1819    =item originEntityID
1820    
1821    ID of the entity that is to be disconnected.
1822    
1823    =back
1824    
1825    =cut
1826    
1827    sub Disconnect {
1828        # Get the parameters.
1829        my ($self, $relationshipName, $originEntityName, $originEntityID) = @_;
1830        # Get the relationship descriptor.
1831        my $structure = $self->_GetStructure($relationshipName);
1832        # Insure we have a relationship.
1833        if (! exists $structure->{from}) {
1834            Confess("$relationshipName is not a relationship in the database.");
1835        } else {
1836            # Get the database handle.
1837            my $dbh = $self->{_dbh};
1838            # We'll set this value to 1 if we find our entity.
1839            my $found = 0;
1840            # Loop through the ends of the relationship.
1841            for my $dir ('from', 'to') {
1842                if ($structure->{$dir} eq $originEntityName) {
1843                    # Delete all relationship instances on this side of the entity instance.
1844                    $dbh->SQL("DELETE FROM $relationshipName WHERE ${dir}_link = ?", 0, $originEntityID);
1845                    $found = 1;
1846                }
1847            }
1848            # Insure we found the entity on at least one end.
1849            if (! $found) {
1850                Confess("Entity \"$originEntityName\" does not use $relationshipName.");
1851            }
1852        }
1853    }
1854    
1855    =head3 DeleteRow
1856    
1857    C<< $erdb->DeleteRow($relationshipName, $fromLink, $toLink, \%values); >>
1858    
1859    Delete a row from a relationship. In most cases, only the from-link and to-link are
1860    needed; however, for relationships with intersection data values can be specified
1861    for the other fields using a hash.
1862    
1863    =over 4
1864    
1865    =item relationshipName
1866    
1867    Name of the relationship from which the row is to be deleted.
1868    
1869    =item fromLink
1870    
1871    ID of the entity instance in the From direction.
1872    
1873    =item toLink
1874    
1875    ID of the entity instance in the To direction.
1876    
1877    =item values
1878    
1879    Reference to a hash of other values to be used for filtering the delete.
1880    
1881    =back
1882    
1883    =cut
1884    
1885    sub DeleteRow {
1886        # Get the parameters.
1887        my ($self, $relationshipName, $fromLink, $toLink, $values) = @_;
1888        # Create a hash of all the filter information.
1889        my %filter = ('from-link' => $fromLink, 'to-link' => $toLink);
1890        if (defined $values) {
1891            for my $key (keys %{$values}) {
1892                $filter{$key} = $values->{$key};
1893            }
1894        }
1895        # Build an SQL statement out of the hash.
1896        my @filters = ();
1897        my @parms = ();
1898        for my $key (keys %filter) {
1899            push @filters, _FixName($key) . " = ?";
1900            push @parms, $filter{$key};
1901        }
1902        Trace("Parms for delete row are " . join(", ", map { "\"$_\"" } @parms) . ".") if T(SQL => 4);
1903        my $command = "DELETE FROM $relationshipName WHERE " .
1904                      join(" AND ", @filters);
1905        # Execute it.
1906        my $dbh = $self->{_dbh};
1907        $dbh->SQL($command, undef, @parms);
1908    }
1909    
1910    =head3 SortNeeded
1911    
1912    C<< my $parms = $erdb->SortNeeded($relationName); >>
1913    
1914    Return the pipe command for the sort that should be applied to the specified
1915    relation when creating the load file.
1916    
1917    For example, if the load file should be sorted ascending by the first
1918    field, this method would return
1919    
1920        sort -k1 -t"\t"
1921    
1922    If the first field is numeric, the method would return
1923    
1924        sort -k1n -t"\t"
1925    
1926    Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate
1927    keys using a sort.
1928    
1929    =over 4
1930    
1931    =item relationName
1932    
1933    Name of the relation to be examined.
1934    
1935    =item
1936    
1937    Returns the sort command to use for sorting the relation, suitable for piping.
1938    
1939    =back
1940    
1941    =cut
1942    #: Return Type $;
1943    sub SortNeeded {
1944        # Get the parameters.
1945        my ($self, $relationName) = @_;
1946        # Declare a descriptor to hold the names of the key fields.
1947        my @keyNames = ();
1948        # Get the relation structure.
1949        my $relationData = $self->_FindRelation($relationName);
1950        # Find out if the relation is a primary entity relation,
1951        # a relationship relation, or a secondary entity relation.
1952        my $entityTable = $self->{_metaData}->{Entities};
1953        my $relationshipTable = $self->{_metaData}->{Relationships};
1954        if (exists $entityTable->{$relationName}) {
1955            # Here we have a primary entity relation.
1956            push @keyNames, "id";
1957        } elsif (exists $relationshipTable->{$relationName}) {
1958            # Here we have a relationship. We sort using the FROM index.
1959            my $relationshipData = $relationshipTable->{$relationName};
1960            my $index = $relationData->{Indexes}->{idxFrom};
1961            push @keyNames, @{$index->{IndexFields}};
1962        } else {
1963            # Here we have a secondary entity relation, so we have a sort on the ID field.
1964            push @keyNames, "id";
1965        }
1966        # Now we parse the key names into sort parameters. First, we prime the return
1967        # string.
1968        my $retVal = "sort -t\"\t\" ";
1969        # Get the relation's field list.
1970        my @fields = @{$relationData->{Fields}};
1971        # Loop through the keys.
1972        for my $keyData (@keyNames) {
1973            # Get the key and the ordering.
1974            my ($keyName, $ordering);
1975            if ($keyData =~ /^([^ ]+) DESC/) {
1976                ($keyName, $ordering) = ($1, "descending");
1977            } else {
1978                ($keyName, $ordering) = ($keyData, "ascending");
1979            }
1980            # Find the key's position and type.
1981            my $fieldSpec;
1982            for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {
1983                my $thisField = $fields[$i];
1984                if ($thisField->{name} eq $keyName) {
1985                    # Get the sort modifier for this field type. The modifier
1986                    # decides whether we're using a character, numeric, or
1987                    # floating-point sort.
1988                    my $modifier = $TypeTable{$thisField->{type}}->{sort};
1989                    # If the index is descending for this field, denote we want
1990                    # to reverse the sort order on this field.
1991                    if ($ordering eq 'descending') {
1992                        $modifier .= "r";
1993                    }
1994                    # Store the position and modifier into the field spec, which
1995                    # will stop the inner loop. Note that the field number is
1996                    # 1-based in the sort command, so we have to increment the
1997                    # index.
1998                    $fieldSpec = ($i + 1) . $modifier;
1999                }
2000            }
2001            # Add this field to the sort command.
2002            $retVal .= " -k$fieldSpec";
2003        }
2004        # Return the result.
2005        return $retVal;
2006    }
2007    
2008    =head3 GetList
2009    
2010    C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>
2011    
2012    Return a list of object descriptors for the specified objects as determined by the
2013    specified filter clause.
2014    
2015    This method is essentially the same as L</Get> except it returns a list of objects rather
2016    than a query object that can be used to get the results one record at a time.
2017    
2018    =over 4
2019    
2020    =item objectNames
2021    
2022    List containing the names of the entity and relationship objects to be retrieved.
2023    
2024    =item filterClause
2025    
2026    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
2027    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
2028    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
2029    in the filter clause should be added to the parameter list as additional parameters. The
2030    fields in a filter clause can come from primary entity relations, relationship relations,
2031    or secondary entity relations; however, all of the entities and relationships involved must
2032    be included in the list of object names.
2033    
2034    The filter clause can also specify a sort order. To do this, simply follow the filter string
2035    with an ORDER BY clause. For example, the following filter string gets all genomes for a
2036    particular genus and sorts them by species name.
2037    
2038    C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
2039    
2040    The rules for field references in a sort order are the same as those for field references in the
2041    filter clause in general; however, odd things may happen if a sort field is from a secondary
2042    relation.
2043    
2044    =item params
2045    
2046    Reference to a list of parameter values to be substituted into the filter clause.
2047    
2048    =item RETURN
2049    
2050    Returns a list of B<DBObject>s that satisfy the query conditions.
2051    
2052    =back
2053    
2054    =cut
2055    #: Return Type @%
2056    sub GetList {
2057        # Get the parameters.
2058        my ($self, $objectNames, $filterClause, $params) = @_;
2059        # Declare the return variable.
2060        my @retVal = ();
2061        # Perform the query.
2062        my $query = $self->Get($objectNames, $filterClause, $params);
2063        # Loop through the results.
2064        while (my $object = $query->Fetch) {
2065            push @retVal, $object;
2066        }
2067        # Return the result.
2068        return @retVal;
2069    }
2070    
2071    =head3 GetCount
2072    
2073    C<< my $count = $erdb->GetCount(\@objectNames, $filter, \@params); >>
2074    
2075    Return the number of rows found by a specified query. This method would
2076    normally be used to count the records in a single table. For example, in a
2077    genetics database
2078    
2079        my $count = $erdb->GetCount(['Genome'], 'Genome(genus-species) LIKE ?', ['homo %']);
2080    
2081    would return the number of genomes for the genus I<homo>. It is conceivable, however,
2082    to use it to return records based on a join. For example,
2083    
2084        my $count = $erdb->GetCount(['HasFeature', 'Genome'], 'Genome(genus-species) LIKE ?',
2085                                    ['homo %']);
2086    
2087    would return the number of features for genomes in the genus I<homo>. Note that
2088    only the rows from the first table are counted. If the above command were
2089    
2090        my $count = $erdb->GetCount(['Genome', 'Feature'], 'Genome(genus-species) LIKE ?',
2091                                    ['homo %']);
2092    
2093    it would return the number of genomes, not the number of genome/feature pairs.
2094    
2095    =over 4
2096    
2097    =item objectNames
2098    
2099    Reference to a list of the objects (entities and relationships) included in the
2100    query.
2101    
2102    =item filter
2103    
2104    A filter clause for restricting the query. The rules are the same as for the L</Get>
2105    method.
2106    
2107    =item params
2108    
2109    Reference to a list of the parameter values to be substituted for the parameter marks
2110    in the filter.
2111    
2112    =item RETURN
2113    
2114    Returns a count of the number of records in the first table that would satisfy
2115    the query.
2116    
2117    =back
2118    
2119    =cut
2120    
2121    sub GetCount {
2122        # Get the parameters.
2123        my ($self, $objectNames, $filter, $params) = @_;
2124        # Insure the params argument is an array reference if the caller left it off.
2125        if (! defined($params)) {
2126            $params = [];
2127        }
2128        # Declare the return variable.
2129        my $retVal;
2130        # Find out if we're counting an entity or a relationship.
2131        my $countedField;
2132        if ($self->IsEntity($objectNames->[0])) {
2133            $countedField = "id";
2134        } else {
2135            # For a relationship we count the to-link because it's usually more
2136            # numerous. Note we're automatically converting to the SQL form
2137            # of the field name (to_link vs. to-link).
2138            $countedField = "to_link";
2139        }
2140        # Create the SQL command suffix to get the desired records.
2141        my ($suffix, $mappedNameListRef, $mappedNameHashRef) = $self->_SetupSQL($objectNames,
2142                                                                                $filter);
2143        # Prefix it with text telling it we want a record count.
2144        my $firstObject = $mappedNameListRef->[0];
2145        my $command = "SELECT COUNT($firstObject.$countedField) $suffix";
2146        # Prepare and execute the command.
2147        my $sth = $self->_GetStatementHandle($command, $params);
2148        # Get the count value.
2149        ($retVal) = $sth->fetchrow_array();
2150        # Check for a problem.
2151        if (! defined($retVal)) {
2152            if ($sth->err) {
2153                # Here we had an SQL error.
2154                Confess("Error retrieving row count: " . $sth->errstr());
2155            } else {
2156                # Here we have no result.
2157                Confess("No result attempting to retrieve row count.");
2158            }
2159        }
2160        # Return the result.
2161        return $retVal;
2162    }
2163    
2164    =head3 ComputeObjectSentence
2165    
2166    C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>
2167    
2168    Check an object name, and if it is a relationship convert it to a relationship sentence.
2169    
2170    =over 4
2171    
2172    =item objectName
2173    
2174    Name of the entity or relationship.
2175    
2176    =item RETURN
2177    
2178    Returns a string containing the entity name or a relationship sentence.
2179    
2180    =back
2181    
2182    =cut
2183    
2184    sub ComputeObjectSentence {
2185        # Get the parameters.
2186        my ($self, $objectName) = @_;
2187        # Set the default return value.
2188        my $retVal = $objectName;
2189        # Look for the object as a relationship.
2190        my $relTable = $self->{_metaData}->{Relationships};
2191        if (exists $relTable->{$objectName}) {
2192            # Get the relationship sentence.
2193            $retVal = _ComputeRelationshipSentence($objectName, $relTable->{$objectName});
2194        }
2195        # Return the result.
2196        return $retVal;
2197    }
2198    
2199    =head3 DumpRelations
2200    
2201    C<< $erdb->DumpRelations($outputDirectory); >>
2202    
2203    Write the contents of all the relations to tab-delimited files in the specified directory.
2204    Each file will have the same name as the relation dumped, with an extension of DTX.
2205    
2206    =over 4
2207    
2208    =item outputDirectory
2209    
2210    Name of the directory into which the relation files should be dumped.
2211    
2212    =back
2213    
2214    =cut
2215    
2216    sub DumpRelations {
2217        # Get the parameters.
2218        my ($self, $outputDirectory) = @_;
2219        # Now we need to run through all the relations. First, we loop through the entities.
2220        my $metaData = $self->{_metaData};
2221        my $entities = $metaData->{Entities};
2222        for my $entityName (keys %{$entities}) {
2223            my $entityStructure = $entities->{$entityName};
2224            # Get the entity's relations.
2225            my $relationList = $entityStructure->{Relations};
2226            # Loop through the relations, dumping them.
2227            for my $relationName (keys %{$relationList}) {
2228                my $relation = $relationList->{$relationName};
2229                $self->_DumpRelation($outputDirectory, $relationName, $relation);
2230            }
2231        }
2232        # Next, we loop through the relationships.
2233        my $relationships = $metaData->{Relationships};
2234        for my $relationshipName (keys %{$relationships}) {
2235            my $relationshipStructure = $relationships->{$relationshipName};
2236            # Dump this relationship's relation.
2237            $self->_DumpRelation($outputDirectory, $relationshipName, $relationshipStructure->{Relations}->{$relationshipName});
2238        }
2239    }
2240    
2241    =head3 InsertValue
2242    
2243    C<< $erdb->InsertValue($entityID, $fieldName, $value); >>
2244    
2245    This method will insert a new value into the database. The value must be one
2246    associated with a secondary relation, since primary values cannot be inserted:
2247    they occur exactly once. Secondary values, on the other hand, can be missing
2248    or multiply-occurring.
2249    
2250    =over 4
2251    
2252    =item entityID
2253    
2254    ID of the object that is to receive the new value.
2255    
2256    =item fieldName
2257    
2258    Field name for the new value-- this includes the entity name, since
2259    field names are of the format I<objectName>C<(>I<fieldName>C<)>.
2260    
2261    =item value
2262    
2263    New value to be put in the field.
2264    
2265    =back
2266    
2267    =cut
2268    
2269    sub InsertValue {
2270        # Get the parameters.
2271        my ($self, $entityID, $fieldName, $value) = @_;
2272        # Parse the entity name and the real field name.
2273        if ($fieldName =~ /^([^(]+)\(([^)]+)\)/) {
2274            my $entityName = $1;
2275            my $fieldTitle = $2;
2276            # Get its descriptor.
2277            if (!$self->IsEntity($entityName)) {
2278                Confess("$entityName is not a valid entity.");
2279            } else {
2280                my $entityData = $self->{_metaData}->{Entities}->{$entityName};
2281                # Find the relation containing this field.
2282                my $fieldHash = $entityData->{Fields};
2283                if (! exists $fieldHash->{$fieldTitle}) {
2284                    Confess("$fieldTitle not found in $entityName.");
2285                } else {
2286                    my $relation = $fieldHash->{$fieldTitle}->{relation};
2287                    if ($relation eq $entityName) {
2288                        Confess("Cannot do InsertValue on primary field $fieldTitle of $entityName.");
2289                    } else {
2290                        # Now we can create an INSERT statement.
2291                        my $dbh = $self->{_dbh};
2292                        my $fixedName = _FixName($fieldTitle);
2293                        my $statement = "INSERT INTO $relation (id, $fixedName) VALUES(?, ?)";
2294                        # Execute the command.
2295                        $dbh->SQL($statement, 0, $entityID, $value);
2296                    }
2297                }
2298            }
2299        } else {
2300            Confess("$fieldName is not a valid field name.");
2301        }
2302    }
2303    
2304    =head3 InsertObject
2305    
2306    C<< $erdb->InsertObject($objectType, \%fieldHash); >>
2307    
2308    Insert an object into the database. The object is defined by a type name and then a hash
2309    of field names to values. Field values in the primary relation are represented by scalars.
2310    (Note that for relationships, the primary relation is the B<only> relation.)
2311    Field values for the other relations comprising the entity are always list references. For
2312    example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases
2313    C<ZP_00210270.1> and C<gi|46206278>.
2314    
2315    C<< $erdb->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>
2316    
2317    The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
2318    property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
2319    
2320    C<< $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>
2321    
2322    =over 4
2323    
2324    =item newObjectType
2325    
2326    Type name of the object to insert.
2327    
2328    =item fieldHash
2329    
2330    Hash of field names to values.
2331    
2332  =back  =back
2333    
# Line 851  Line 2335 
2335    
2336  sub InsertObject {  sub InsertObject {
2337          # Get the parameters.          # Get the parameters.
2338          my ($self, $newObjectType, $fieldHash) = @_;      my ($self, $newObjectType, $fieldHash) = @_;
2339          # Denote that so far we appear successful.      # Denote that so far we appear successful.
2340          my $retVal = 1;      my $retVal = 1;
2341        # Get the database handle.
2342        my $dbh = $self->{_dbh};
2343        # Get the relation list.
2344        my $relationTable = $self->_GetRelationTable($newObjectType);
2345        # Loop through the relations. We'll build insert statements for each one. If a relation is
2346        # secondary, we may end up generating multiple insert statements. If an error occurs, we
2347        # stop the loop.
2348        my @relationList = keys %{$relationTable};
2349        for (my $i = 0; $retVal && $i <= $#relationList; $i++) {
2350            my $relationName = $relationList[$i];
2351            my $relationDefinition = $relationTable->{$relationName};
2352            # Get the relation's fields. For each field we will collect a value in the corresponding
2353            # position of the @valueList array. If one of the fields is missing, we will add it to the
2354            # @missing list.
2355            my @fieldList = @{$relationDefinition->{Fields}};
2356            my @fieldNameList = ();
2357            my @valueList = ();
2358            my @missing = ();
2359            my $recordCount = 1;
2360            for my $fieldDescriptor (@fieldList) {
2361                # Get the field name and save it. Note we need to fix it up so the hyphens
2362                # are converted to underscores.
2363                my $fieldName = $fieldDescriptor->{name};
2364                push @fieldNameList, _FixName($fieldName);
2365                # Look for the named field in the incoming structure. Note that we are looking
2366                # for the real field name, not the fixed-up one!
2367                if (exists $fieldHash->{$fieldName}) {
2368                    # Here we found the field. Stash it in the value list.
2369                    my $value = $fieldHash->{$fieldName};
2370                    push @valueList, $value;
2371                    # If the value is a list, we may need to increment the record count.
2372                    if (ref $value eq "ARRAY") {
2373                        my $thisCount = @{$value};
2374                        if ($recordCount == 1) {
2375                            # Here we have our first list, so we save its count.
2376                            $recordCount = $thisCount;
2377                        } elsif ($recordCount != $thisCount) {
2378                            # Here we have a second list, so its length has to match the
2379                            # previous lists.
2380                            Trace("Field $value in new $newObjectType object has an invalid list length $thisCount. Expected $recordCount.") if T(0);
2381                            $retVal = 0;
2382                        }
2383                    }
2384                } else {
2385                    # Here the field is not present. Flag it as missing.
2386                    push @missing, $fieldName;
2387                }
2388            }
2389            # If we are the primary relation, add the new-record flag.
2390            if ($relationName eq $newObjectType) {
2391                push @valueList, 1;
2392                push @fieldNameList, "new_record";
2393            }
2394            # Only proceed if there are no missing fields.
2395            if (@missing > 0) {
2396                Trace("Relation $relationName for $newObjectType skipped due to missing fields: " .
2397                    join(' ', @missing)) if T(1);
2398            } else {
2399                # Build the INSERT statement.
2400                my $statement = "INSERT INTO $relationName (" . join (', ', @fieldNameList) .
2401                    ") VALUES (";
2402                # Create a marker list of the proper size and put it in the statement.
2403                my @markers = ();
2404                while (@markers < @fieldNameList) { push @markers, '?'; }
2405                $statement .= join(', ', @markers) . ")";
2406                # We have the insert statement, so prepare it.
2407                my $sth = $dbh->prepare_command($statement);
2408                Trace("Insert statement prepared: $statement") if T(3);
2409                # Now we loop through the values. If a value is scalar, we use it unmodified. If it's
2410                # a list, we use the current element. The values are stored in the @parameterList array.
2411                my $done = 0;
2412                for (my $i = 0; $i < $recordCount; $i++) {
2413                    # Clear the parameter list array.
2414                    my @parameterList = ();
2415                    # Loop through the values.
2416                    for my $value (@valueList) {
2417                        # Check to see if this is a scalar value.
2418                        if (ref $value eq "ARRAY") {
2419                            # Here we have a list value. Pull the current entry.
2420                            push @parameterList, $value->[$i];
2421                        } else {
2422                            # Here we have a scalar value. Use it unmodified.
2423                            push @parameterList, $value;
2424                        }
2425                    }
2426                    # Execute the INSERT statement with the specified parameter list.
2427                    $retVal = $sth->execute(@parameterList);
2428                    if (!$retVal) {
2429                        my $errorString = $sth->errstr();
2430                        Confess("Error inserting into $relationName: $errorString");
2431                    }
2432                }
2433            }
2434        }
2435        # Return a 1 for backward compatability.
2436        return 1;
2437    }
2438    
2439    =head3 UpdateEntity
2440    
2441    C<< $erdb->UpdateEntity($entityName, $id, \%fields); >>
2442    
2443    Update the values of an entity. This is an unprotected update, so it should only be
2444    done if the database resides on a database server.
2445    
2446    =over 4
2447    
2448    =item entityName
2449    
2450    Name of the entity to update. (This is the entity type.)
2451    
2452    =item id
2453    
2454    ID of the entity to update. If no entity exists with this ID, an error will be thrown.
2455    
2456    =item fields
2457    
2458    Reference to a hash mapping field names to their new values. All of the fields named
2459    must be in the entity's primary relation, and they cannot any of them be the ID field.
2460    
2461    =back
2462    
2463    =cut
2464    
2465    sub UpdateEntity {
2466        # Get the parameters.
2467        my ($self, $entityName, $id, $fields) = @_;
2468        # Get a list of the field names being updated.
2469        my @fieldList = keys %{$fields};
2470        # Verify that the fields exist.
2471        my $checker = $self->GetFieldTable($entityName);
2472        for my $field (@fieldList) {
2473            if ($field eq 'id') {
2474                Confess("Cannot update the ID field for entity $entityName.");
2475            } elsif ($checker->{$field}->{relation} ne $entityName) {
2476                Confess("Cannot find $field in primary relation of $entityName.");
2477            }
2478        }
2479        # Build the SQL statement.
2480        my @sets = ();
2481        my @valueList = ();
2482        for my $field (@fieldList) {
2483            push @sets, _FixName($field) . " = ?";
2484            push @valueList, $fields->{$field};
2485        }
2486        my $command = "UPDATE $entityName SET " . join(", ", @sets) . " WHERE id = ?";
2487        # Add the ID to the list of binding values.
2488        push @valueList, $id;
2489        # Call SQL to do the work.
2490        my $rows = $self->{_dbh}->SQL($command, 0, @valueList);
2491        # Check for errors.
2492        if ($rows == 0) {
2493            Confess("Entity $id of type $entityName not found.");
2494        }
2495    }
2496    
2497    =head3 LoadTable
2498    
2499    C<< my $results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>
2500    
2501    Load data from a tab-delimited file into a specified table, optionally re-creating the table
2502    first.
2503    
2504    =over 4
2505    
2506    =item fileName
2507    
2508    Name of the file from which the table data should be loaded.
2509    
2510    =item relationName
2511    
2512    Name of the relation to be loaded. This is the same as the table name.
2513    
2514    =item truncateFlag
2515    
2516    TRUE if the table should be dropped and re-created, else FALSE
2517    
2518    =item RETURN
2519    
2520    Returns a statistical object containing a list of the error messages.
2521    
2522    =back
2523    
2524    =cut
2525    sub LoadTable {
2526        # Get the parameters.
2527        my ($self, $fileName, $relationName, $truncateFlag) = @_;
2528        # Create the statistical return object.
2529        my $retVal = _GetLoadStats();
2530        # Trace the fact of the load.
2531        Trace("Loading table $relationName from $fileName") if T(2);
2532          # Get the database handle.          # Get the database handle.
2533          my $dbh = $self->{_dbh};          my $dbh = $self->{_dbh};
2534          # Get the relation list.      # Get the input file size.
2535          my $relationTable = $self->_GetRelationTable($newObjectType);      my $fileSize = -s $fileName;
2536          # Loop through the relations. We'll build insert statements for each one. If a relation is      # Get the relation data.
2537          # secondary, we may end up generating multiple insert statements. If an error occurs, we      my $relation = $self->_FindRelation($relationName);
2538          # stop the loop.      # Check the truncation flag.
2539          while ($retVal && (my ($relationName, $relationDefinition) = each %{$relationTable})) {      if ($truncateFlag) {
2540                  # Get the relation's fields. For each field we will collect a value in the corresponding          Trace("Creating table $relationName") if T(2);
2541                  # position of the @valueList array. If one of the fields is missing, we will add it to the          # Compute the row count estimate. We take the size of the load file,
2542                  # @missing list.          # divide it by the estimated row size, and then multiply by 1.5 to
2543                  my @fieldList = @{$relationDefinition->{Fields}};          # leave extra room. We postulate a minimum row count of 1000 to
2544                  my @fieldNameList = ();          # prevent problems with incoming empty load files.
2545                  my @valueList = ();          my $rowSize = $self->EstimateRowSize($relationName);
2546                  my @missing = ();          my $estimate = FIG::max($fileSize * 1.5 / $rowSize, 1000);
2547                  my $recordCount = 1;          # Re-create the table without its index.
2548                  for my $fieldDescriptor (@fieldList) {          $self->CreateTable($relationName, 0, $estimate);
2549                          # Get the field name and save it. Note we need to fix it up so the hyphens          # If this is a pre-index DBMS, create the index here.
2550                          # are converted to underscores.          if ($dbh->{_preIndex}) {
2551                          my $fieldName = $fieldDescriptor->{name};              eval {
2552                          push @fieldNameList, _FixName($fieldName);                  $self->CreateIndex($relationName);
2553                          # Look for the named field in the incoming structure. Note that we are looking              };
2554                          # for the real field name, not the fixed-up one!              if ($@) {
2555                          if (exists $fieldHash->{$fieldName}) {                  $retVal->AddMessage($@);
2556                                  # Here we found the field. Stash it in the value list.              }
2557                                  my $value = $fieldHash->{$fieldName};          }
2558                                  push @valueList, $value;      }
2559                                  # If the value is a list, we may need to increment the record count.      # Load the table.
2560                                  if (ref $value eq "ARRAY") {      my $rv;
2561                                          my $thisCount = @{$value};      eval {
2562                                          if ($recordCount == 1) {          $rv = $dbh->load_table(file => $fileName, tbl => $relationName);
2563                                                  # Here we have our first list, so we save its count.      };
2564                                                  $recordCount = $thisCount;      if (!defined $rv) {
2565                                          } elsif ($recordCount != $thisCount) {          $retVal->AddMessage($@) if ($@);
2566                                                  # Here we have a second list, so its length has to match the          $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2567                                                  # previous lists.          Trace("Table load failed for $relationName.") if T(1);
2568                                                  Trace("Field $value in new $newObjectType object has an invalid list length $thisCount. Expected $recordCount.") if T(0);      } else {
2569                                                  $retVal = 0;          # Here we successfully loaded the table.
2570            $retVal->Add("tables");
2571            my $size = -s $fileName;
2572            Trace("$size bytes loaded into $relationName.") if T(2);
2573            # If we're rebuilding, we need to create the table indexes.
2574            if ($truncateFlag) {
2575                # Indexes are created here for PostGres. For PostGres, indexes are
2576                # best built at the end. For MySQL, the reverse is true.
2577                if (! $dbh->{_preIndex}) {
2578                    eval {
2579                        $self->CreateIndex($relationName);
2580                    };
2581                    if ($@) {
2582                        $retVal->AddMessage($@);
2583                    }
2584                }
2585                # The full-text index (if any) is always built last, even for MySQL.
2586                # First we need to see if this table has a full-text index. Only
2587                # primary relations are allowed that privilege.
2588                if ($self->_IsPrimary($relationName)) {
2589                    # Get the relation's entity/relationship structure.
2590                    my $structure = $self->_GetStructure($relationName);
2591                    # Check for a searchable fields list.
2592                    if (exists $structure->{searchFields}) {
2593                        # Here we know that we need to create a full-text search index.
2594                        # Get an SQL-formatted field name list.
2595                        my $fields = join(", ", $self->_FixNames(@{$structure->{searchFields}}));
2596                        # Create the index.
2597                        $dbh->create_index(tbl => $relationName, idx => "search_idx",
2598                                           flds => $fields, kind => 'fulltext');
2599                    }
2600                }
2601            }
2602        }
2603        # Analyze the table to improve performance.
2604        Trace("Analyzing and compacting $relationName.") if T(3);
2605        $dbh->vacuum_it($relationName);
2606        Trace("$relationName load completed.") if T(3);
2607        # Return the statistics.
2608        return $retVal;
2609    }
2610    
2611    =head3 DropRelation
2612    
2613    C<< $erdb->DropRelation($relationName); >>
2614    
2615    Physically drop a relation from the database.
2616    
2617    =over 4
2618    
2619    =item relationName
2620    
2621    Name of the relation to drop. If it does not exist, this method will have
2622    no effect.
2623    
2624    =back
2625    
2626    =cut
2627    
2628    sub DropRelation {
2629        # Get the parameters.
2630        my ($self, $relationName) = @_;
2631        # Get the database handle.
2632        my $dbh = $self->{_dbh};
2633        # Drop the relation. The method used here has no effect if the relation
2634        # does not exist.
2635        Trace("Invoking DB Kernel to drop $relationName.") if T(3);
2636        $dbh->drop_table(tbl => $relationName);
2637    }
2638    
2639    =head3 MatchSqlPattern
2640    
2641    C<< my $matched = ERDB::MatchSqlPattern($value, $pattern); >>
2642    
2643    Determine whether or not a specified value matches an SQL pattern. An SQL
2644    pattern has two wild card characters: C<%> that matches multiple characters,
2645    and C<_> that matches a single character. These can be escaped using a
2646    backslash (C<\>). We pull this off by converting the SQL pattern to a
2647    PERL regular expression. As per SQL rules, the match is case-insensitive.
2648    
2649    =over 4
2650    
2651    =item value
2652    
2653    Value to be matched against the pattern. Note that an undefined or empty
2654    value will not match anything.
2655    
2656    =item pattern
2657    
2658    SQL pattern against which to match the value. An undefined or empty pattern will
2659    match everything.
2660    
2661    =item RETURN
2662    
2663    Returns TRUE if the value and pattern match, else FALSE.
2664    
2665    =back
2666    
2667    =cut
2668    
2669    sub MatchSqlPattern {
2670        # Get the parameters.
2671        my ($value, $pattern) = @_;
2672        # Declare the return variable.
2673        my $retVal;
2674        # Insure we have a pattern.
2675        if (! defined($pattern) || $pattern eq "") {
2676            $retVal = 1;
2677        } else {
2678            # Break the pattern into pieces around the wildcard characters. Because we
2679            # use parentheses in the split function's delimiter expression, we'll get
2680            # list elements for the delimiters as well as the rest of the string.
2681            my @pieces = split /([_%]|\\[_%])/, $pattern;
2682            # Check some fast special cases.
2683            if ($pattern eq '%') {
2684                # A null pattern matches everything.
2685                $retVal = 1;
2686            } elsif (@pieces == 1) {
2687                # No wildcards, so we have a literal comparison. Note we're case-insensitive.
2688                $retVal = (lc($value) eq lc($pattern));
2689            } elsif (@pieces == 2 && $pieces[1] eq '%') {
2690                # A wildcard at the end, so we have a substring match. This is also case-insensitive.
2691                $retVal = (lc(substr($value, 0, length($pieces[0]))) eq lc($pieces[0]));
2692            } else {
2693                # Okay, we have to do it the hard way. Convert each piece to a PERL pattern.
2694                my $realPattern = "";
2695                for my $piece (@pieces) {
2696                    # Determine the type of piece.
2697                    if ($piece eq "") {
2698                        # Empty pieces are ignored.
2699                    } elsif ($piece eq "%") {
2700                        # Here we have a multi-character wildcard. Note that it can match
2701                        # zero or more characters.
2702                        $realPattern .= ".*"
2703                    } elsif ($piece eq "_") {
2704                        # Here we have a single-character wildcard.
2705                        $realPattern .= ".";
2706                    } elsif ($piece eq "\\%" || $piece eq "\\_") {
2707                        # This is an escape sequence (which is a rare thing, actually).
2708                        $realPattern .= substr($piece, 1, 1);
2709                    } else {
2710                        # Here we have raw text.
2711                        $realPattern .= quotemeta($piece);
2712                    }
2713                }
2714                # Do the match.
2715                $retVal = ($value =~ /^$realPattern$/i ? 1 : 0);
2716            }
2717        }
2718        # Return the result.
2719        return $retVal;
2720    }
2721    
2722    =head3 GetEntity
2723    
2724    C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>
2725    
2726    Return an object describing the entity instance with a specified ID.
2727    
2728    =over 4
2729    
2730    =item entityType
2731    
2732    Entity type name.
2733    
2734    =item ID
2735    
2736    ID of the desired entity.
2737    
2738    =item RETURN
2739    
2740    Returns a B<DBObject> representing the desired entity instance, or an undefined value if no
2741    instance is found with the specified key.
2742    
2743    =back
2744    
2745    =cut
2746    
2747    sub GetEntity {
2748        # Get the parameters.
2749        my ($self, $entityType, $ID) = @_;
2750        # Create a query.
2751        my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);
2752        # Get the first (and only) object.
2753        my $retVal = $query->Fetch();
2754        # Return the result.
2755        return $retVal;
2756    }
2757    
2758    =head3 GetChoices
2759    
2760    C<< my @values = $erdb->GetChoices($entityName, $fieldName); >>
2761    
2762    Return a list of all the values for the specified field that are represented in the
2763    specified entity.
2764    
2765    Note that if the field is not indexed, then this will be a very slow operation.
2766    
2767    =over 4
2768    
2769    =item entityName
2770    
2771    Name of an entity in the database.
2772    
2773    =item fieldName
2774    
2775    Name of a field belonging to the entity. This is a raw field name without
2776    the standard parenthesized notation used in most calls.
2777    
2778    =item RETURN
2779    
2780    Returns a list of the distinct values for the specified field in the database.
2781    
2782    =back
2783    
2784    =cut
2785    
2786    sub GetChoices {
2787        # Get the parameters.
2788        my ($self, $entityName, $fieldName) = @_;
2789        # Declare the return variable.
2790        my @retVal;
2791        # Get the entity data structure.
2792        my $entityData = $self->_GetStructure($entityName);
2793        # Get the field.
2794        my $fieldHash = $entityData->{Fields};
2795        if (! exists $fieldHash->{$fieldName}) {
2796            Confess("$fieldName not found in $entityName.");
2797        } else {
2798            # Get the name of the relation containing the field.
2799            my $relation = $fieldHash->{$fieldName}->{relation};
2800            # Fix up the field name.
2801            my $realName = _FixName($fieldName);
2802            # Get the database handle.
2803            my $dbh = $self->{_dbh};
2804            # Query the database.
2805            my $results = $dbh->SQL("SELECT DISTINCT $realName FROM $relation");
2806            # Clean the results. They are stored as a list of lists, and we just want the one list.
2807            @retVal = sort map { $_->[0] } @{$results};
2808        }
2809        # Return the result.
2810        return @retVal;
2811    }
2812    
2813    =head3 GetEntityValues
2814    
2815    C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>
2816    
2817    Return a list of values from a specified entity instance. If the entity instance
2818    does not exist, an empty list is returned.
2819    
2820    =over 4
2821    
2822    =item entityType
2823    
2824    Entity type name.
2825    
2826    =item ID
2827    
2828    ID of the desired entity.
2829    
2830    =item fields
2831    
2832    List of field names, each of the form I<objectName>C<(>I<fieldName>C<)>.
2833    
2834    =item RETURN
2835    
2836    Returns a flattened list of the values of the specified fields for the specified entity.
2837    
2838    =back
2839    
2840    =cut
2841    
2842    sub GetEntityValues {
2843        # Get the parameters.
2844        my ($self, $entityType, $ID, $fields) = @_;
2845        # Get the specified entity.
2846        my $entity = $self->GetEntity($entityType, $ID);
2847        # Declare the return list.
2848        my @retVal = ();
2849        # If we found the entity, push the values into the return list.
2850        if ($entity) {
2851            push @retVal, $entity->Values($fields);
2852                                          }                                          }
2853        # Return the result.
2854        return @retVal;
2855                                  }                                  }
2856    
2857    =head3 GetAll
2858    
2859    C<< my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>
2860    
2861    Return a list of values taken from the objects returned by a query. The first three
2862    parameters correspond to the parameters of the L</Get> method. The final parameter is
2863    a list of the fields desired from each record found by the query. The field name
2864    syntax is the standard syntax used for fields in the B<ERDB> system--
2865    B<I<objectName>(I<fieldName>)>-- where I<objectName> is the name of the relevant entity
2866    or relationship and I<fieldName> is the name of the field.
2867    
2868    The list returned will be a list of lists. Each element of the list will contain
2869    the values returned for the fields specified in the fourth parameter. If one of the
2870    fields specified returns multiple values, they are flattened in with the rest. For
2871    example, the following call will return a list of the features in a particular
2872    spreadsheet cell, and each feature will be represented by a list containing the
2873    feature ID followed by all of its aliases.
2874    
2875    C<< @query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>
2876    
2877    =over 4
2878    
2879    =item objectNames
2880    
2881    List containing the names of the entity and relationship objects to be retrieved.
2882    
2883    =item filterClause
2884    
2885    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
2886    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
2887    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
2888    parameter list as additional parameters. The fields in a filter clause can come from primary
2889    entity relations, relationship relations, or secondary entity relations; however, all of the
2890    entities and relationships involved must be included in the list of object names.
2891    
2892    =item parameterList
2893    
2894    List of the parameters to be substituted in for the parameters marks in the filter clause.
2895    
2896    =item fields
2897    
2898    List of the fields to be returned in each element of the list returned.
2899    
2900    =item count
2901    
2902    Maximum number of records to return. If omitted or 0, all available records will be returned.
2903    
2904    =item RETURN
2905    
2906    Returns a list of list references. Each element of the return list contains the values for the
2907    fields specified in the B<fields> parameter.
2908    
2909    =back
2910    
2911    =cut
2912    #: Return Type @@;
2913    sub GetAll {
2914        # Get the parameters.
2915        my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
2916        # Translate the parameters from a list reference to a list. If the parameter
2917        # list is a scalar we convert it into a singleton list.
2918        my @parmList = ();
2919        if (ref $parameterList eq "ARRAY") {
2920            Trace("GetAll parm list is an array.") if T(4);
2921            @parmList = @{$parameterList};
2922                          } else {                          } else {
2923                                  # Here the field is not present. Flag it as missing.          Trace("GetAll parm list is a scalar: $parameterList.") if T(4);
2924                                  push @missing, $fieldName;          push @parmList, $parameterList;
2925                          }                          }
2926        # Insure the counter has a value.
2927        if (!defined $count) {
2928            $count = 0;
2929        }
2930        # Add the row limit to the filter clause.
2931        if ($count > 0) {
2932            $filterClause .= " LIMIT $count";
2933        }
2934        # Create the query.
2935        my $query = $self->Get($objectNames, $filterClause, \@parmList);
2936        # Set up a counter of the number of records read.
2937        my $fetched = 0;
2938        # Loop through the records returned, extracting the fields. Note that if the
2939        # counter is non-zero, we stop when the number of records read hits the count.
2940        my @retVal = ();
2941        while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {
2942            my @rowData = $row->Values($fields);
2943            push @retVal, \@rowData;
2944            $fetched++;
2945                  }                  }
2946                  # If we are the primary relation, add the new-record flag.      Trace("$fetched rows returned in GetAll.") if T(SQL => 4);
2947                  if ($relationName eq $newObjectType) {      # Return the resulting list.
2948                          push @valueList, 1;      return @retVal;
                         push @fieldNameList, "new_record";  
2949                  }                  }
2950                  # Only proceed if there are no missing fields.  
2951                  if (@missing > 0) {  =head3 Exists
2952                          Trace("Relation $relationName for $newObjectType skipped due to missing fields: " .  
2953                                  join(' ', @missing)) if T(1);  C<< my $found = $sprout->Exists($entityName, $entityID); >>
2954                  } else {  
2955                          # Build the INSERT statement.  Return TRUE if an entity exists, else FALSE.
2956                          my $statement = "INSERT INTO $relationName (" . join (', ', @fieldNameList) .  
2957                                  ") VALUES (";  =over 4
2958                          # Create a marker list of the proper size and put it in the statement.  
2959                          my @markers = ();  =item entityName
2960                          while (@markers < @fieldNameList) { push @markers, '?'; }  
2961                          $statement .= join(', ', @markers) . ")";  Name of the entity type (e.g. C<Feature>) relevant to the existence check.
2962                          # We have the insert statement, so prepare it.  
2963                          my $sth = $dbh->prepare_command($statement);  =item entityID
2964                          Trace("Insert statement prepared: $statement") if T(3);  
2965                          # Now we loop through the values. If a value is scalar, we use it unmodified. If it's  ID of the entity instance whose existence is to be checked.
2966                          # a list, we use the current element. The values are stored in the @parameterList array.  
2967                          my $done = 0;  =item RETURN
2968                          for (my $i = 0; $i < $recordCount; $i++) {  
2969                                  # Clear the parameter list array.  Returns TRUE if the entity instance exists, else FALSE.
2970                                  my @parameterList = ();  
2971                                  # Loop through the values.  =back
2972                                  for my $value (@valueList) {  
2973                                          # Check to see if this is a scalar value.  =cut
2974                                          if (ref $value eq "ARRAY") {  #: Return Type $;
2975                                                  # Here we have a list value. Pull the current entry.  sub Exists {
2976                                                  push @parameterList, $value->[$i];      # Get the parameters.
2977        my ($self, $entityName, $entityID) = @_;
2978        # Check for the entity instance.
2979        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
2980        my $testInstance = $self->GetEntity($entityName, $entityID);
2981        # Return an existence indicator.
2982        my $retVal = ($testInstance ? 1 : 0);
2983        return $retVal;
2984    }
2985    
2986    =head3 EstimateRowSize
2987    
2988    C<< my $rowSize = $erdb->EstimateRowSize($relName); >>
2989    
2990    Estimate the row size of the specified relation. The estimated row size is computed by adding
2991    up the average length for each data type.
2992    
2993    =over 4
2994    
2995    =item relName
2996    
2997    Name of the relation whose estimated row size is desired.
2998    
2999    =item RETURN
3000    
3001    Returns an estimate of the row size for the specified relation.
3002    
3003    =back
3004    
3005    =cut
3006    #: Return Type $;
3007    sub EstimateRowSize {
3008        # Get the parameters.
3009        my ($self, $relName) = @_;
3010        # Declare the return variable.
3011        my $retVal = 0;
3012        # Find the relation descriptor.
3013        my $relation = $self->_FindRelation($relName);
3014        # Get the list of fields.
3015        for my $fieldData (@{$relation->{Fields}}) {
3016            # Get the field type and add its length.
3017            my $fieldLen = $TypeTable{$fieldData->{type}}->{avgLen};
3018            $retVal += $fieldLen;
3019        }
3020        # Return the result.
3021        return $retVal;
3022    }
3023    
3024    =head3 GetFieldTable
3025    
3026    C<< my $fieldHash = $self->GetFieldTable($objectnName); >>
3027    
3028    Get the field structure for a specified entity or relationship.
3029    
3030    =over 4
3031    
3032    =item objectName
3033    
3034    Name of the desired entity or relationship.
3035    
3036    =item RETURN
3037    
3038    The table containing the field descriptors for the specified object.
3039    
3040    =back
3041    
3042    =cut
3043    
3044    sub GetFieldTable {
3045        # Get the parameters.
3046        my ($self, $objectName) = @_;
3047        # Get the descriptor from the metadata.
3048        my $objectData = $self->_GetStructure($objectName);
3049        # Return the object's field table.
3050        return $objectData->{Fields};
3051    }
3052    
3053    =head3 SplitKeywords
3054    
3055    C<< my @keywords = ERDB::SplitKeywords($keywordString); >>
3056    
3057    This method returns a list of the positive keywords in the specified
3058    keyword string. All of the operators will have been stripped off,
3059    and if the keyword is preceded by a minus operator (C<->), it will
3060    not be in the list returned. The idea here is to get a list of the
3061    keywords the user wants to see. The list will be processed to remove
3062    duplicates.
3063    
3064    It is possible to create a string that confuses this method. For example
3065    
3066        frog toad -frog
3067    
3068    would return both C<frog> and C<toad>. If this is a problem we can deal
3069    with it later.
3070    
3071    =over 4
3072    
3073    =item keywordString
3074    
3075    The keyword string to be parsed.
3076    
3077    =item RETURN
3078    
3079    Returns a list of the words in the keyword string the user wants to
3080    see.
3081    
3082    =back
3083    
3084    =cut
3085    
3086    sub SplitKeywords {
3087        # Get the parameters.
3088        my ($keywordString) = @_;
3089        # Make a safety copy of the string. (This helps during debugging.)
3090        my $workString = $keywordString;
3091        # Convert operators we don't care about to spaces.
3092        $workString =~ tr/+"()<>/ /;
3093        # Split the rest of the string along space boundaries. Note that we
3094        # eliminate any words that are zero length or begin with a minus sign.
3095        my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
3096        # Use a hash to remove duplicates.
3097        my %words = map { $_ => 1 } @wordList;
3098        # Return the result.
3099        return sort keys %words;
3100    }
3101    
3102    =head3 ValidateFieldName
3103    
3104    C<< my $okFlag = ERDB::ValidateFieldName($fieldName); >>
3105    
3106    Return TRUE if the specified field name is valid, else FALSE. Valid field names must
3107    be hyphenated words subject to certain restrictions.
3108    
3109    =over 4
3110    
3111    =item fieldName
3112    
3113    Field name to be validated.
3114    
3115    =item RETURN
3116    
3117    Returns TRUE if the field name is valid, else FALSE.
3118    
3119    =back
3120    
3121    =cut
3122    
3123    sub ValidateFieldName {
3124        # Get the parameters.
3125        my ($fieldName) = @_;
3126        # Declare the return variable. The field name is valid until we hear
3127        # differently.
3128        my $retVal = 1;
3129        # Compute the maximum name length.
3130        my $maxLen = $TypeTable{'name-string'}->{maxLen};
3131        # Look for bad stuff in the name.
3132        if ($fieldName =~ /--/) {
3133            # Here we have a doubled minus sign.
3134            Trace("Field name $fieldName has a doubled hyphen.") if T(1);
3135            $retVal = 0;
3136        } elsif ($fieldName !~ /^[A-Za-z]/) {
3137            # Here the field name is missing the initial letter.
3138            Trace("Field name $fieldName does not begin with a letter.") if T(1);
3139            $retVal = 0;
3140        } elsif (length($fieldName) > $maxLen) {
3141            # Here the field name is too long.
3142            Trace("Maximum field name length is $maxLen. Field name must be truncated to " . substr($fieldName,0, $maxLen) . ".");
3143                                          } else {                                          } else {
3144                                                  # Here we have a scalar value. Use it unmodified.          # Strip out the minus signs. Everything remaining must be a letter,
3145                                                  push @parameterList, $value;          # underscore, or digit.
3146            my $strippedName = $fieldName;
3147            $strippedName =~ s/-//g;
3148            if ($strippedName !~ /^(\w|\d)+$/) {
3149                Trace("Field name $fieldName contains illegal characters.") if T(1);
3150                $retVal = 0;
3151                                          }                                          }
3152                                  }                                  }
3153                                  # Execute the INSERT statement with the specified parameter list.      # Return the result.
3154                                  $retVal = $sth->execute(@parameterList);      return $retVal;
3155                                  if (!$retVal) {  }
3156                                          my $errorString = $sth->errstr();  
3157                                          Trace("Insert error: $errorString.") if T(0);  =head3 ReadMetaXML
3158    
3159    C<< my $rawMetaData = ERDB::ReadDBD($fileName); >>
3160    
3161    This method reads a raw database definition XML file and returns it.
3162    Normally, the metadata used by the ERDB system has been processed and
3163    modified to make it easier to load and retrieve the data; however,
3164    this method can be used to get the data in its raw form.
3165    
3166    =over 4
3167    
3168    =item fileName
3169    
3170    Name of the XML file to read.
3171    
3172    =item RETURN
3173    
3174    Returns a hash reference containing the raw XML data from the specified file.
3175    
3176    =back
3177    
3178    =cut
3179    
3180    sub ReadMetaXML {
3181        # Get the parameters.
3182        my ($fileName) = @_;
3183        # Read the XML.
3184        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
3185        Trace("XML metadata loaded from file $fileName.") if T(1);
3186        # Return the result.
3187        return $retVal;
3188                                  }                                  }
3189    
3190    =head3 GetEntityFieldHash
3191    
3192    C<< my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName); >>
3193    
3194    Get the field hash of the named entity in the specified raw XML structure.
3195    The field hash may not exist, in which case we need to create it.
3196    
3197    =over 4
3198    
3199    =item structure
3200    
3201    Raw XML structure defininng the database. This is not the run-time XML used by
3202    an ERDB object, since that has all sorts of optimizations built-in.
3203    
3204    =item entityName
3205    
3206    Name of the entity whose field structure is desired.
3207    
3208    =item RETURN
3209    
3210    Returns the field hash used to define the entity's fields.
3211    
3212    =back
3213    
3214    =cut
3215    
3216    sub GetEntityFieldHash {
3217        # Get the parameters.
3218        my ($structure, $entityName) = @_;
3219        # Get the entity structure.
3220        my $entityData = $structure->{Entities}->{$entityName};
3221        # Look for a field structure.
3222        my $retVal = $entityData->{Fields};
3223        # If it doesn't exist, create it.
3224        if (! defined($retVal)) {
3225            $entityData->{Fields} = {};
3226            $retVal = $entityData->{Fields};
3227                          }                          }
3228        # Return the result.
3229        return $retVal;
3230                  }                  }
3231    
3232    =head3 WriteMetaXML
3233    
3234    C<< ERDB::WriteMetaXML($structure, $fileName); >>
3235    
3236    Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
3237    used to update the database definition. It must be used with care, however, since it
3238    will only work on a raw structure, not on the processed structure created by an ERDB
3239    constructor.
3240    
3241    =over 4
3242    
3243    =item structure
3244    
3245    XML structure to be written to the file.
3246    
3247    =item fileName
3248    
3249    Name of the output file to which the updated XML should be stored.
3250