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

Diff of /Sprout/ERDB.pm

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

revision 1.6, Wed May 4 03:24:43 2005 UTC revision 1.78, Tue Nov 28 01:02:42 2006 UTC
# Line 2  Line 2 
2    
3          use strict;          use strict;
4          use Tracer;          use Tracer;
5          use DBKernel;      use DBrtns;
6          use Data::Dumper;          use Data::Dumper;
7          use XML::Simple;          use XML::Simple;
8          use DBQuery;          use DBQuery;
9          use DBObject;          use DBObject;
10          use Stats;          use Stats;
11          use Time::HiRes qw(gettimeofday);          use Time::HiRes qw(gettimeofday);
12        use Digest::MD5 qw(md5_base64);
13        use FIG;
14        use CGI;
15    
16  =head1 Entity-Relationship Database Package  =head1 Entity-Relationship Database Package
17    
# Line 32  Line 35 
35  relation that contains two fields-- the feature ID (C<id>) and the alias name (C<alias>).  relation that contains two fields-- the feature ID (C<id>) and the alias name (C<alias>).
36  The B<FEATURE> entity also contains an optional virulence number. This is implemented  The B<FEATURE> entity also contains an optional virulence number. This is implemented
37  as a separate relation C<FeatureVirulence> which contains an ID (C<id>) and a virulence number  as a separate relation C<FeatureVirulence> which contains an ID (C<id>) and a virulence number
38  (C<virulence>). If the virulence of a feature I<ABC> is known to be 6, there will be one row in the  (C<virulence>). If the virulence of a feature I<ABC> is known to be 6, there will be one row in
39  C<FeatureVirulence> relation possessing the value I<ABC> as its ID and 6 as its virulence number.  the C<FeatureVirulence> relation possessing the value I<ABC> as its ID and 6 as its virulence
40  If the virulence of I<ABC> is not known, there will not be any rows for it in C<FeatureVirulence>.  number. If the virulence of I<ABC> is not known, there will not be any rows for it in
41    C<FeatureVirulence>.
42    
43  Entities are connected by binary relationships implemented using single relations possessing the  Entities are connected by binary relationships implemented using single relations possessing the
44  same name as the relationship itself and that has an I<arity> of 1-to-1 (C<11>), 1-to-many (C<1M>),  same name as the relationship itself and that has an I<arity> of 1-to-1 (C<11>), 1-to-many (C<1M>),
# Line 56  Line 60 
60  B<start-position>, which indicates where in the contig that the sequence begins. This attribute  B<start-position>, which indicates where in the contig that the sequence begins. This attribute
61  is implemented as the C<start_position> field in the C<IsMadeUpOf> relation.  is implemented as the C<start_position> field in the C<IsMadeUpOf> relation.
62    
63  The database itself is described by an XML file using the F<ERDatabase.xsd> schema. In addition to  The database itself is described by an XML file. In addition to all the data required to define
64  all the data required to define the entities, relationships, and attributes, the schema provides  the entities, relationships, and attributes, the schema provides space for notes describing
65  space for notes describing the data and what it means. These notes are used by L</ShowMetaData>  the data and what it means. These notes are used by L</ShowMetaData> to generate documentation
66  to generate documentation for the database.  for the database.
67    
68    Special support is provided for text searching. An entity field can be marked as <em>searchable</em>,
69    in which case it will be used to generate a text search index in which the user searches for words
70    in the field instead of a particular field value.
71    
72  Finally, every entity and relationship object has a flag indicating if it is new or old. The object  Finally, every entity and relationship object has a flag indicating if it is new or old. The object
73  is considered I<old> if it was loaded by the L</LoadTables> method. It is considered I<new> if it  is considered I<old> if it was loaded by the L</LoadTables> method. It is considered I<new> if it
74  was inserted by the L</InsertObject> method.  was inserted by the L</InsertObject> method.
75    
76  To facilitate testing, the ERDB module supports automatic generation of test data. This process  =head2 XML Database Description
77  is described in the L</GenerateEntity> and L</GenerateConnection> methods, though it is not yet  
78  fully implemented.  =head3 Data Types
79    
80    The ERDB system supports the following data types. Note that there are numerous string
81    types depending on the maximum length. Some database packages limit the total number of
82    characters you have in an index key; to insure the database works in all environments,
83    the type of string should be the shortest one possible that supports all the known values.
84    
85    =over 4
86    
87    =item char
88    
89    single ASCII character
90    
91    =item int
92    
93    32-bit signed integer
94    
95    =item counter
96    
97    32-bit unsigned integer
98    
99    =item date
100    
101    64-bit unsigned integer, representing a PERL date/time value
102    
103    =item text
104    
105    long string; Text fields cannot be used in indexes or sorting and do not support the
106    normal syntax of filter clauses, but can be up to a billion character in length
107    
108    =item float
109    
110    double-precision floating-point number
111    
112    =item boolean
113    
114    single-bit numeric value; The value is stored as a 16-bit signed integer (for
115    compatability with certain database packages), but the only values supported are
116    0 and 1.
117    
118    =item id-string
119    
120    variable-length string, maximum 25 characters
121    
122    =item key-string
123    
124    variable-length string, maximum 40 characters
125    
126    =item name-string
127    
128    variable-length string, maximum 80 characters
129    
130    =item medium-string
131    
132    variable-length string, maximum 160 characters
133    
134    =item string
135    
136    variable-length string, maximum 255 characters
137    
138    =item hash-string
139    
140    variable-length string, maximum 22 characters
141    
142    =back
143    
144    The hash-string data type has a special meaning. The actual key passed into the loader will
145    be a string, but it will be digested into a 22-character MD5 code to save space. Although the
146    MD5 algorithm is not perfect, it is extremely unlikely two strings will have the same
147    digest. Therefore, it is presumed the keys will be unique. When the database is actually
148    in use, the hashed keys will be presented rather than the original values. For this reason,
149    they should not be used for entities where the key is meaningful.
150    
151    =head3 Global Tags
152    
153    The entire database definition must be inside a B<Database> tag. The display name of
154    the database is given by the text associated with the B<Title> tag. The display name
155    is only used in the automated documentation. It has no other effect. The entities and
156    relationships are listed inside the B<Entities> and B<Relationships> tags,
157    respectively. None of these tags have attributes.
158    
159        <Database>
160            <Title>... display title here...</Title>
161            <Entities>
162                ... entity definitions here ...
163            </Entities>
164            <Relationships>
165                ... relationship definitions here...
166            </Relationships>
167        </Database>
168    
169    Entities, relationships, indexes, and fields all allow a text tag called B<Notes>.
170    The text inside the B<Notes> tag contains comments that will appear when the database
171    documentation is generated. Within a B<Notes> tag, you may use C<[i]> and C<[/i]> for
172    italics, C<[b]> and C<[/b]> for bold, and C<[p]> for a new paragraph.
173    
174    =head3 Fields
175    
176    Both entities and relationships have fields described by B<Field> tags. A B<Field>
177    tag can have B<Notes> associated with it. The complete set of B<Field> tags for an
178    object mus be inside B<Fields> tags.
179    
180        <Entity ... >
181            <Fields>
182                ... Field tags ...
183            </Fields>
184        </Entity>
185    
186    The attributes for the B<Field> tag are as follows.
187    
188    =over 4
189    
190    =item name
191    
192    Name of the field. The field name should contain only letters, digits, and hyphens (C<->),
193    and the first character should be a letter. Most underlying databases are case-insensitive
194    with the respect to field names, so a best practice is to use lower-case letters only. Finally,
195    the name C<search-relevance> has special meaning for full-text searches and should not be
196    used as a field name.
197    
198    =item type
199    
200    Data type of the field. The legal data types are given above.
201    
202    =item relation
203    
204    Name of the relation containing the field. This should only be specified for entity
205    fields. The ERDB system does not support optional fields or multi-occurring fields
206    in the primary relation of an entity. Instead, they are put into secondary relations.
207    So, for example, in the C<Genome> entity, the C<group-name> field indicates a special
208    grouping used to select a subset of the genomes. A given genome may not be in any
209    groups or may be in multiple groups. Therefore, C<group-name> specifies a relation
210    value. The relation name specified must be a valid table name. By convention, it is
211    usually the entity name followed by a qualifying word (e.g. C<GenomeGroup>). In an
212    entity, the fields without a relation attribute are said to belong to the
213    I<primary relation>. This relation has the same name as the entity itself.
214    
215    =item searchable
216    
217    If specified, then the field is a candidate for full-text searching. A single full-text
218    index will be created for each relation with at least one searchable field in it.
219    For best results, this option should only be used for string or text fields.
220    
221    =item special
222    
223    This attribute allows the subclass to assign special meaning for certain fields.
224    The interpretation is up to the subclass itself. Currently, only entity fields
225    can have this attribute.
226    
227    =back
228    
229    =head3 Indexes
230    
231    An entity can have multiple alternate indexes associated with it. The fields 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 75  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 98  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 145  Line 444 
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 176  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 220  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 244  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 254  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 = $metadata->{Joins};
619          my @joinKeys = keys %{$joinTable};          my @joinKeys = keys %{$joinTable};
# Line 282  Line 621 
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 ($sourceRelation, $targetRelation) = ($1, $2);                  my ($sourceRelation, $targetRelation) = ($1, $2);
624                  Trace("Join with key $joinKey is from $sourceRelation to $targetRelation.") if T(4);          Trace("Join with key $joinKey is from $sourceRelation to $targetRelation.") if T(Joins => 4);
625                  my $source = $self->ComputeObjectSentence($sourceRelation);                  my $source = $self->ComputeObjectSentence($sourceRelation);
626                  my $target = $self->ComputeObjectSentence($targetRelation);                  my $target = $self->ComputeObjectSentence($targetRelation);
627                  my $clause = $joinTable->{$joinKey};                  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<< $erdb->DumpMetaData(); >>
641    
642  Return a dump of the metadata structure.  Return a dump of the metadata structure.
643    
# Line 313  Line 650 
650          return Data::Dumper::Dumper($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<< $erdb->CreateTables(); >>
726    
727  This method creates the tables for the database from the metadata structure loaded by the  This method creates the tables for the database from the metadata structure loaded by the
728  constructor. It is expected this function will only be used on rare occasions, when the  constructor. It is expected this function will only be used on rare occasions, when the
# Line 327  Line 734 
734  sub CreateTables {  sub CreateTables {
735          # Get the parameters.          # Get the parameters.
736          my ($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          my $entityHash = $metadata->{Entities};      for my $relationName (@relNames) {
         for my $entityName (keys %{$entityHash}) {  
                 my $entityData = $entityHash->{$entityName};  
                 # Tell the user what we're doing.  
                 Trace("Creating relations for entity $entityName.") if T(1);  
                 # Loop through the entity's relations.  
                 for my $relationName (keys %{$entityData->{Relations}}) {  
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 363  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 398  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 VerifyFields
818    
819    C<< my $count = $erdb->VerifyFields($relName, \@fieldList); >>
820    
821    Run through the list of proposed field values, insuring that all the character fields are
822    below the maximum length. If any fields are too long, they will be truncated in place.
823    
824    =over 4
825    
826    =item relName
827    
828    Name of the relation for which the specified fields are destined.
829    
830    =item fieldList
831    
832    Reference to a list, in order, of the fields to be put into the relation.
833    
834    =item RETURN
835    
836    Returns the number of fields truncated.
837    
838    =back
839    
840    =cut
841    
842    sub VerifyFields {
843        # Get the parameters.
844        my ($self, $relName, $fieldList) = @_;
845        # Initialize the return value.
846        my $retVal = 0;
847        # Get the relation definition.
848        my $relData = $self->_FindRelation($relName);
849        # Get the list of field descriptors.
850        my $fieldTypes = $relData->{Fields};
851        my $fieldCount = scalar @{$fieldTypes};
852        # Loop through the two lists.
853        for (my $i = 0; $i < $fieldCount; $i++) {
854            # Get the type of the current field.
855            my $fieldType = $fieldTypes->[$i]->{type};
856            # If it's a character field, verify the length.
857            if ($fieldType =~ /string/) {
858                my $maxLen = $TypeTable{$fieldType}->{maxLen};
859                my $oldString = $fieldList->[$i];
860                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            }
867        }
868        # Return the truncation count.
869        return $retVal;
870    }
871    
872    =head3 DigestFields
873    
874    C<< $erdb->DigestFields($relName, $fieldList); >>
875    
876    Digest the strings in the field list that correspond to data type C<hash-string> in the
877    specified relation.
878    
879    =over 4
880    
881    =item relName
882    
883    Name of the relation to which the fields belong.
884    
885    =item fieldList
886    
887    List of field contents to be loaded into the relation.
888    
889    =back
890    
891    =cut
892    #: Return Type ;
893    sub DigestFields {
894        # Get the parameters.
895        my ($self, $relName, $fieldList) = @_;
896        # Get the relation definition.
897        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 DigestKey
913    
914    C<< my $digested = $erdb->DigestKey($keyValue); >>
915    
916    Return the digested value of a symbolic key. The digested value can then be plugged into a
917    key-based search into a table with key-type hash-string.
918    
919    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    =over 4
923    
924    =item keyValue
925    
926    Key value to digest.
927    
928    =item RETURN
929    
930    Digested value of the key.
931    
932    =back
933    
934    =cut
935    
936    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  =head3 CreateIndex  =head3 CreateIndex
946    
947  C<< $database->CreateIndex($relationName); >>  C<< $erdb->CreateIndex($relationName); >>
948    
949  Create the indexes for a relation. If a table is being loaded from a large source file (as  Create the indexes for a relation. If a table is being loaded from a large source file (as
950  is the case in L</LoadTable>), it is best to create the indexes after the load. If that is  is the case in L</LoadTable>), it is sometimes best to create the indexes after the load.
951  the case, then L</CreateTable> should be called with the index flag set to FALSE, and this  If that is the case, then L</CreateTable> should be called with the index flag set to
952  method used after the load to create the indexes for the table.  FALSE, and this method used after the load to create the indexes for the table.
953    
954  =cut  =cut
955    
# Line 431  Line 965 
965          for my $indexName (keys %{$indexHash}) {          for my $indexName (keys %{$indexHash}) {
966                  my $indexData = $indexHash->{$indexName};                  my $indexData = $indexHash->{$indexName};
967                  # Get the index's field list.                  # Get the index's field list.
968                  my @fieldList = _FixNames(@{$indexData->{IndexFields}});          my @rawFields = @{$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);                  my $flds = join(', ', @fieldList);
988                  # Get the index's uniqueness flag.                  # Get the index's uniqueness flag.
989                  my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
990                  # Create the index.                  # Create the index.
991                  $dbh->create_index(idx => $indexName, tbl => $relationName, flds => $flds, unique => $unique);          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);                  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  =head3 LoadTables  =head3 GetSecondaryFields
1002    
1003  C<< my $stats = $database->LoadTables($directoryName, $rebuild); >>  C<< my %fieldTuples = $erdb->GetSecondaryFields($entityName); >>
1004    
1005  This method will load the database tables from a directory. The tables must already have been created  This method will return a list of the name and type of each of the secondary
1006  in the database. (This can be done by calling L</CreateTables>.) The caller passes in a directory name;  fields for a specified entity. Secondary fields are stored in two-column tables
1007  all of the relations to be loaded must have a file in the directory with the same name as the relation  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 entityName
1013    
1014    Name of the entity whose secondary fields are desired.
1015    
1016    =item RETURN
1017    
1018    Returns a hash mapping the field names to their field types.
1019    
1020    =back
1021    
1022    =cut
1023    
1024    sub GetSecondaryFields {
1025        # Get the parameters.
1026        my ($self, $entityName) = @_;
1027        # Declare the return variable.
1028        my %retVal = ();
1029        # Look for the entity.
1030        my $table = $self->GetFieldTable($entityName);
1031        # Loop through the fields, pulling out the secondaries.
1032        for my $field (sort keys %{$table}) {
1033            if ($table->{$field}->{relation} ne $entityName) {
1034                # Here we have a secondary field.
1035                $retVal{$field} = $table->{$field}->{type};
1036            }
1037        }
1038        # Return the result.
1039        return %retVal;
1040    }
1041    
1042    =head3 GetFieldRelationName
1043    
1044    C<< my $name = $erdb->GetFieldRelationName($objectName, $fieldName); >>
1045    
1046    Return the name of the relation containing a specified field.
1047    
1048    =over 4
1049    
1050    =item objectName
1051    
1052    Name of the entity or relationship containing the field.
1053    
1054    =item fieldName
1055    
1056    Name of the relevant field in that entity or relationship.
1057    
1058    =item RETURN
1059    
1060    Returns the name of the database relation containing the field, or C<undef> if
1061    the field does not exist.
1062    
1063    =back
1064    
1065    =cut
1066    
1067    sub GetFieldRelationName {
1068        # Get the parameters.
1069        my ($self, $objectName, $fieldName) = @_;
1070        # Declare the return variable.
1071        my $retVal;
1072        # Get the object field table.
1073        my $table = $self->GetFieldTable($objectName);
1074        # Only proceed if the field exists.
1075        if (exists $table->{$fieldName}) {
1076            # Determine the name of the relation that contains this field.
1077            $retVal = $table->{$fieldName}->{relation};
1078        }
1079        # Return the result.
1080        return $retVal;
1081    }
1082    
1083    =head3 DeleteValue
1084    
1085    C<< my $numDeleted = $erdb->DeleteValue($entityName, $id, $fieldName, $fieldValue); >>
1086    
1087    Delete secondary field values from the database. This method can be used to delete all
1088    values of a specified field for a particular entity instance, or only a single value.
1089    
1090    Secondary fields are stored in two-column relations separate from an entity's primary
1091    table, and as a result a secondary field can legitimately have no value or multiple
1092    values. Therefore, it makes sense to talk about deleting secondary fields where it
1093    would not make sense for primary fields.
1094    
1095    =over 4
1096    
1097    =item entityName
1098    
1099    Name of the entity from which the fields are to be deleted.
1100    
1101    =item id
1102    
1103    ID of the entity instance to be processed. If the instance is not found, this
1104    method will have no effect. If C<undef> is specified, all values for all of
1105    the entity instances will be deleted.
1106    
1107    =item fieldName
1108    
1109    Name of the field whose values are to be deleted.
1110    
1111    =item fieldValue (optional)
1112    
1113    Value to be deleted. If not specified, then all values of the specified field
1114    will be deleted for the entity instance. If specified, then only the values which
1115    match this parameter will be deleted.
1116    
1117    =item RETURN
1118    
1119    Returns the number of rows deleted.
1120    
1121    =back
1122    
1123    =cut
1124    
1125    sub DeleteValue {
1126        # Get the parameters.
1127        my ($self, $entityName, $id, $fieldName, $fieldValue) = @_;
1128        # Declare the return value.
1129        my $retVal = 0;
1130        # We need to set up an SQL command to do the deletion. First, we
1131        # find the name of the field's relation.
1132        my $table = $self->GetFieldTable($entityName);
1133        my $field = $table->{$fieldName};
1134        my $relation = $field->{relation};
1135        # Make sure this is a secondary field.
1136        if ($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            # Execute the command.
1159            my $dbh = $self->{_dbh};
1160            $retVal = $dbh->SQL($sql, 0, @parms);
1161        }
1162        # Return the result.
1163        return $retVal;
1164    }
1165    
1166    =head3 LoadTables
1167    
1168    C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>
1169    
1170    This method will load the database tables from a directory. The tables must already have been created
1171    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  (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  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  the same order as the fields in the relation tables generated by L</ShowMetaData>. The old data is
# Line 486  Line 1208 
1208          $directoryName =~ s!/\\$!!;          $directoryName =~ s!/\\$!!;
1209          # Declare the return variable.          # Declare the return variable.
1210          my $retVal = Stats->new();          my $retVal = Stats->new();
1211          # Get the metadata structure.      # Get the relation names.
1212          my $metaData = $self->{_metaData};      my @relNames = $self->GetTableNames();
1213          # Loop through the entities.      for my $relationName (@relNames) {
         for my $entity (values %{$metaData->{Entities}}) {  
                 # Loop through the entity's relations.  
                 for my $relationName (keys %{$entity->{Relations}}) {  
1214                          # Try to load this relation.                          # Try to load this relation.
1215                          my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);                          my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);
1216                          # Accumulate the statistics.                          # Accumulate the statistics.
1217                          $retVal->Accumulate($result);                          $retVal->Accumulate($result);
1218                  }                  }
         }  
         # 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);  
         }  
1219          # Add the duration of the load to the statistical object.          # Add the duration of the load to the statistical object.
1220          $retVal->Add('duration', gettimeofday - $startTime);          $retVal->Add('duration', gettimeofday - $startTime);
1221          # Return the accumulated statistics.          # Return the accumulated statistics.
1222          return $retVal;          return $retVal;
1223  }  }
1224    
1225    
1226  =head3 GetTableNames  =head3 GetTableNames
1227    
1228  C<< my @names = $database->GetTableNames; >>  C<< my @names = $erdb->GetTableNames; >>
1229    
1230  Return a list of the relations required to implement this database.  Return a list of the relations required to implement this database.
1231    
# Line 530  Line 1242 
1242    
1243  =head3 GetEntityTypes  =head3 GetEntityTypes
1244    
1245  C<< my @names = $database->GetEntityTypes; >>  C<< my @names = $erdb->GetEntityTypes; >>
1246    
1247  Return a list of the entity type names.  Return a list of the entity type names.
1248    
# Line 545  Line 1257 
1257          return sort keys %{$entityList};          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  =head3 Get
1307    
1308  C<< my $query = $database->Get(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  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.  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  The filter is a standard WHERE/ORDER BY clause with question marks as parameter markers and each
# Line 555  Line 1313 
1313  following call requests all B<Genome> objects for the genus specified in the variable  following call requests all B<Genome> objects for the genus specified in the variable
1314  $genus.  $genus.
1315    
1316  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", [$genus]); >>
1317    
1318  The WHERE clause contains a single question mark, so there is a single additional  The WHERE clause contains a single question mark, so there is a single additional
1319  parameter representing the parameter value. It would also be possible to code  parameter representing the parameter value. It would also be possible to code
1320    
1321  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>  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  however, this version of the call would generate a syntax error if there were any quote
1324  characters inside the variable C<$genus>.  characters inside the variable C<$genus>.
# Line 572  Line 1330 
1330  It is possible to specify multiple entity and relationship names in order to retrieve more than  It is possible to specify multiple entity and relationship names in order to retrieve more than
1331  one object's data at the same time, which allows highly complex joined queries. For example,  one object's data at the same time, which allows highly complex joined queries. For example,
1332    
1333  C<< $query = $sprout->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", $genus); >>  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  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.  join path between the entities and relationships. The algorithm used is very simplistic.
1337  In particular, you can't specify any entity or relationship more than once, and if a  In particular, if a relationship is recursive, the path is determined by the order in which
1338  relationship is recursive, the path is determined by the order in which the entity  the entity and the relationship appear. For example, consider a recursive relationship
1339  and the relationship appear. For example, consider a recursive relationship B<IsParentOf>  B<IsParentOf> which relates B<People> objects to other B<People> objects. If the join path is
 which relates B<People> objects to other B<People> objects. If the join path is  
1340  coded as C<['People', 'IsParentOf']>, then the people returned will be parents. If, however,  coded as C<['People', 'IsParentOf']>, then the people returned will be parents. If, however,
1341  the join path is C<['IsParentOf', 'People']>, then the people returned will be children.  the join path is C<['IsParentOf', 'People']>, then the people returned will be children.
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  =over 4
1350    
1351  =item objectNames  =item objectNames
# Line 605  Line 1368 
1368    
1369  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>  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  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  filter clause in general; however, odd things may happen if a sort field is from a secondary
1376  relation.  relation.
1377    
1378  =item param1, param2, ..., paramN  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  Parameter values to be substituted into the filter clause.  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  =item RETURN
1395    
# Line 623  Line 1401 
1401    
1402  sub Get {  sub Get {
1403          # Get the parameters.          # Get the parameters.
1404          my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $objectNames, $filterClause, $params) = @_;
1405          # Construct the SELECT statement. The general pattern is      # Process the SQL stuff.
1406          #      my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1407          # SELECT name1.*, name2.*, ... nameN.* FROM name1, name2, ... nameN          $self->_SetupSQL($objectNames, $filterClause);
1408          #      # Create the query.
1409          my $dbh = $self->{_dbh};      my $command = "SELECT DISTINCT " . join(".*, ", @{$mappedNameListRef}) .
1410          my $command = "SELECT DISTINCT " . join('.*, ', @{$objectNames}) . ".* FROM " .          ".* $suffix";
1411                                  join(', ', @{$objectNames});      my $sth = $self->_GetStatementHandle($command, $params);
1412          # Check for a filter clause.      # Now we create the relation map, which enables DBQuery to determine the order, name
1413          if ($filterClause) {      # and mapped name for each object in the query.
1414                  # Here we have one, so we convert its field names and add it to the query. First,      my @relationMap = ();
1415                  # We create a copy of the filter string we can work with.      for my $mappedName (@{$mappedNameListRef}) {
1416                  my $filterString = $filterClause;          push @relationMap, [$mappedName, $mappedNameHashRef->{$mappedName}];
                 # Next, we sort the object names by length. This helps protect us from finding  
                 # object names inside other object names when we're doing our search and replace.  
                 my @sortedNames = sort { length($b) - length($a) } @{$objectNames};  
                 # We will also keep a list of conditions to add to the WHERE clause in order to link  
                 # entities and relationships as well as primary relations to secondary ones.  
                 my @joinWhere = ();  
                 # The final preparatory step is to create a hash table of relation names. The  
                 # table begins with the relation names already in the SELECT command.  
                 my %fromNames = ();  
                 for my $objectName (@sortedNames) {  
                         $fromNames{$objectName} = 1;  
                 }  
                 # 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) {  
                         $command .= " WHERE " . join(' AND ', @joinWhere);  
1417                  }                  }
                 # Add the sort clause (if any) to the SELECT command.  
                 if ($orderClause) {  
                         $command .= " ORDER BY $orderClause";  
                 }  
         }  
         Trace("SQL query: $command") if T(2);  
         Trace("PARMS: '" . (join "', '", @params) . "'") if (T(3) && (@params > 0));  
         my $sth = $dbh->prepare_command($command);  
         # Execute it with the parameters bound in.  
         $sth->execute(@params) || Confess("SELECT error" . $sth->errstr());  
1418          # Return the statement object.          # Return the statement object.
1419          my $retVal = DBQuery::_new($self, $sth, @{$objectNames});      my $retVal = DBQuery::_new($self, $sth, \@relationMap);
1420          return $retVal;          return $retVal;
1421  }  }
1422    
 =head3 GetList  
1423    
 C<< my @dbObjects = $database->GetList(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  
1424    
1425  Return a list of object descriptors for the specified objects as determined by the  =head3 Search
 specified filter clause.  
1426    
1427  This method is essentially the same as L</Get> except it returns a list of objects rather  C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>
 that a query object that can be used to get the results one record at a time.  
1428    
1429  =over 4  Perform a full text search with filtering. The search will be against a specified object
1430    in the object name list. That object will get an extra field containing the search
1431    relevance. Note that except for the search expression, the parameters of this method are
1432    the same as those for L</Get> and follow the same rules.
1433    
1434  =over 4  =over 4
1435    
1436    =item searchExpression
1437    
1438    Boolean search expression for the text fields of the target object. The default mode for
1439    a Boolean search expression is OR, but we want the default to be AND, so we will
1440    add a C<+> operator to each word with no other operator before it.
1441    
1442    =item idx
1443    
1444    Index in the I<$objectNames> list of the table to be searched in full-text mode.
1445    
1446  =item objectNames  =item objectNames
1447    
1448  List containing the names of the entity and relationship objects to be retrieved.  List containing the names of the entity and relationship objects to be retrieved.
# Line 773  Line 1457 
1457  or secondary entity relations; however, all of the entities and relationships involved must  or secondary entity relations; however, all of the entities and relationships involved must
1458  be included in the list of object names.  be included in the list of object names.
1459    
1460  The filter clause can also specify a sort order. To do this, simply follow the filter string  =item params
 with an ORDER BY clause. For example, the following filter string gets all genomes for a  
 particular genus and sorts them by species name.  
   
 C<< "Genome(genus) = ? ORDER BY Genome(species)" >>  
   
 The rules for field references in a sort order are the same as those for field references in the  
 filter clause in general; however, odd things may happen if a sort field is from a secondary  
 relation.  
   
 =item param1, param2, ..., paramN  
1461    
1462  Parameter values to be substituted into the filter clause.  Reference to a list of parameter values to be substituted into the filter clause.
1463    
1464  =item RETURN  =item RETURN
1465    
1466  Returns a list of B<DBObject>s that satisfy the query conditions.  Returns a query object for the specified search.
1467    
1468  =back  =back
1469    
1470  =cut  =cut
1471  #: Return Type @%  
1472  sub GetList {  sub Search {
1473      # Get the parameters.      # Get the parameters.
1474      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1475          # Declare the return variable.          # Declare the return variable.
1476          my @retVal = ();      my $retVal;
1477          # Perform the query.      # Create a safety copy of the parameter list. Note we have to be careful to insure
1478          my $query = $self->Get($objectNames, $filterClause, @params);      # a parameter list exists before we copy it.
1479          # Loop through the results.      my @myParams = ();
1480          while (my $object = $query->Fetch) {      if (defined $params) {
1481                  push @retVal, $object;          @myParams = @{$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 the result.      return $retVal;
     return @retVal;  
1520  }  }
1521    
1522  =head3 ComputeObjectSentence  =head3 GetFlat
1523    
1524  C<< my $sentence = $database->ComputeObjectSentence($objectName); >>  C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>
1525    
1526  Check an object name, and if it is a relationship convert it to a relationship sentence.  This is a variation of L</GetAll> that asks for only a single field per record and
1527    returns a single flattened list.
1528    
1529  =over 4  =over 4
1530    
1531  =item objectName  =item objectNames
1532    
1533  Name of the entity or relationship.  List containing the names of the entity and relationship objects to be retrieved.
1534    
1535    =item filterClause
1536    
1537    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1538    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
1539    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
1540    parameter list as additional parameters. The fields in a filter clause can come from primary
1541    entity relations, relationship relations, or secondary entity relations; however, all of the
1542    entities and relationships involved must be included in the list of object names.
1543    
1544    =item parameterList
1545    
1546    List of the parameters to be substituted in for the parameters marks in the filter clause.
1547    
1548    =item field
1549    
1550    Name of the field to be used to get the elements of the list returned.
1551    
1552  =item RETURN  =item RETURN
1553    
1554  Returns a string containing the entity name or a relationship sentence.  Returns a list of values.
1555    
1556  =back  =back
1557    
1558  =cut  =cut
1559    #: Return Type @;
1560  sub ComputeObjectSentence {  sub GetFlat {
1561          # Get the parameters.          # Get the parameters.
1562          my ($self, $objectName) = @_;      my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
1563          # Set the default return value.      # Construct the query.
1564          my $retVal = $objectName;      my $query = $self->Get($objectNames, $filterClause, $parameterList);
1565          # Look for the object as a relationship.      # Create the result list.
1566          my $relTable = $self->{_metaData}->{Relationships};      my @retVal = ();
1567          if (exists $relTable->{$objectName}) {      # Loop through the records, adding the field values found to the result list.
1568                  # Get the relationship sentence.      while (my $row = $query->Fetch()) {
1569                  $retVal = _ComputeRelationshipSentence($objectName, $relTable->{$objectName});          push @retVal, $row->Value($field);
1570          }      }
1571          # Return the result.      # Return the list created.
1572          return $retVal;      return @retVal;
1573  }  }
1574    
1575  =head3 DumpRelations  =head3 SpecialFields
1576    
1577  C<< $database->DumpRelations($outputDirectory); >>  C<< my %specials = $erdb->SpecialFields($entityName); >>
1578    
1579  Write the contents of all the relations to tab-delimited files in the specified directory.  Return a hash mapping special fields in the specified entity to the value of their
1580  Each file will have the same name as the relation dumped, with an extension of DTX.  C<special> attribute. This enables the subclass to get access to the special field
1581    attributes without needed to plumb the internal ERDB data structures.
1582    
1583  =over 4  =over 4
1584    
1585  =item outputDirectory  =item entityName
1586    
1587  Name of the directory into which the relation files should be dumped.  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  =back
1595    
1596  =cut  =cut
1597    
1598  sub DumpRelations {  sub SpecialFields {
1599          # Get the parameters.          # Get the parameters.
1600          my ($self, $outputDirectory) = @_;      my ($self, $entityName) = @_;
1601          # Now we need to run through all the relations. First, we loop through the entities.      # Declare the return variable.
1602          my $metaData = $self->{_metaData};      my %retVal = ();
1603          my $entities = $metaData->{Entities};      # Find the entity's data structure.
1604          for my $entityName (keys %{$entities}) {      my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1605                  my $entityStructure = $entities->{$entityName};      # Loop through its fields, adding each special field to the return hash.
1606                  # Get the entity's relations.      my $fieldHash = $entityData->{Fields};
1607                  my $relationList = $entityStructure->{Relations};      for my $fieldName (keys %{$fieldHash}) {
1608                  # Loop through the relations, dumping them.          my $fieldData = $fieldHash->{$fieldName};
1609                  for my $relationName (keys %{$relationList}) {          if (exists $fieldData->{special}) {
1610                          my $relation = $relationList->{$relationName};              $retVal{$fieldName} = $fieldData->{special};
                         $self->_DumpRelation($outputDirectory, $relationName, $relation);  
                 }  
1611          }          }
         # Next, we loop through the relationships.  
         my $relationships = $metaData->{Relationships};  
         for my $relationshipName (keys %{$relationships}) {  
                 my $relationshipStructure = $relationships->{$relationshipName};  
                 # Dump this relationship's relation.  
                 $self->_DumpRelation($outputDirectory, $relationshipName, $relationshipStructure->{Relations}->{$relationshipName});  
1612          }          }
1613        # Return the result.
1614        return %retVal;
1615  }  }
1616    
1617  =head3 InsertObject  =head3 Delete
1618    
1619  C<< my $ok = $database->InsertObject($objectType, \%fieldHash); >>  C<< my $stats = $erdb->Delete($entityName, $objectID, %options); >>
1620    
1621  Insert an object into the database. The object is defined by a type name and then a hash  Delete an entity instance from the database. The instance is deleted along with all entity and
1622  of field names to values. Field values in the primary relation are represented by scalars.  relationship instances dependent on it. The definition of I<dependence> is recursive.
 (Note that for relationships, the primary relation is the B<only> relation.)  
 Field values for the other relations comprising the entity are always list references. For  
 example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases  
 C<ZP_00210270.1> and C<gi|46206278>.  
1623    
1624  C<< $database->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>  An object is always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many
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  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and  =over 4
 property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.  
1629    
1630  C<< $database->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>  =item entityName
1631    
1632  =over 4  Name of the entity type for the instance being deleted.
1633    
1634  =item newObjectType  =item objectID
1635    
1636  Type name of the object to insert.  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 fieldHash  =item options
1640    
1641  Hash of field names to values.  A hash detailing the options for this delete operation.
1642    
1643  =item RETURN  =item RETURN
1644    
1645  Returns 1 if successful, 0 if an error occurred.  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, $originEntityID); >>
1805    
1806    Disconnect an entity instance from all the objects to which it is related. This
1807    will delete each relationship instance that connects to the specified entity.
1808    
1809    =over 4
1810    
1811    =item relationshipName
1812    
1813    Name of the relationship whose instances are to be deleted.
1814    
1815    =item originEntityName
1816    
1817    Name of the entity that is to be disconnected.
1818    
1819    =item originEntityID
1820    
1821    ID of the entity that is to be disconnected.
1822    
1823  =back  =back
1824    
1825  =cut  =cut
1826    
1827  sub InsertObject {  sub Disconnect {
1828          # Get the parameters.          # Get the parameters.
1829          my ($self, $newObjectType, $fieldHash) = @_;      my ($self, $relationshipName, $originEntityName, $originEntityID) = @_;
1830          # Denote that so far we appear successful.      # Get the relationship descriptor.
1831          my $retVal = 1;      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.          # Get the database handle.
1837          my $dbh = $self->{_dbh};          my $dbh = $self->{_dbh};
1838          # Get the relation list.          # We'll set this value to 1 if we find our entity.
1839          my $relationTable = $self->_GetRelationTable($newObjectType);          my $found = 0;
1840          # Loop through the relations. We'll build insert statements for each one. If a relation is          # Loop through the ends of the relationship.
1841          # secondary, we may end up generating multiple insert statements. If an error occurs, we          for my $dir ('from', 'to') {
1842          # stop the loop.              if ($structure->{$dir} eq $originEntityName) {
1843          my @relationList = keys %{$relationTable};                  # Delete all relationship instances on this side of the entity instance.
1844          for (my $i = 0; $retVal && $i <= $#relationList; $i++) {                  $dbh->SQL("DELETE FROM $relationshipName WHERE ${dir}_link = ?", 0, $originEntityID);
1845                  my $relationName = $relationList[$i];                  $found = 1;
                 my $relationDefinition = $relationTable->{$relationName};  
                 # Get the relation's fields. For each field we will collect a value in the corresponding  
                 # position of the @valueList array. If one of the fields is missing, we will add it to the  
                 # @missing list.  
                 my @fieldList = @{$relationDefinition->{Fields}};  
                 my @fieldNameList = ();  
                 my @valueList = ();  
                 my @missing = ();  
                 my $recordCount = 1;  
                 for my $fieldDescriptor (@fieldList) {  
                         # Get the field name and save it. Note we need to fix it up so the hyphens  
                         # are converted to underscores.  
                         my $fieldName = $fieldDescriptor->{name};  
                         push @fieldNameList, _FixName($fieldName);  
                         # Look for the named field in the incoming structure. Note that we are looking  
                         # for the real field name, not the fixed-up one!  
                         if (exists $fieldHash->{$fieldName}) {  
                                 # Here we found the field. Stash it in the value list.  
                                 my $value = $fieldHash->{$fieldName};  
                                 push @valueList, $value;  
                                 # If the value is a list, we may need to increment the record count.  
                                 if (ref $value eq "ARRAY") {  
                                         my $thisCount = @{$value};  
                                         if ($recordCount == 1) {  
                                                 # Here we have our first list, so we save its count.  
                                                 $recordCount = $thisCount;  
                                         } elsif ($recordCount != $thisCount) {  
                                                 # Here we have a second list, so its length has to match the  
                                                 # previous lists.  
                                                 Trace("Field $value in new $newObjectType object has an invalid list length $thisCount. Expected $recordCount.") if T(0);  
                                                 $retVal = 0;  
1846                                          }                                          }
1847                                  }                                  }
1848                          } else {          # Insure we found the entity on at least one end.
1849                                  # Here the field is not present. Flag it as missing.          if (! $found) {
1850                                  push @missing, $fieldName;              Confess("Entity \"$originEntityName\" does not use $relationshipName.");
1851                          }                          }
1852                  }                  }
                 # If we are the primary relation, add the new-record flag.  
                 if ($relationName eq $newObjectType) {  
                         push @valueList, 1;  
                         push @fieldNameList, "new_record";  
1853                  }                  }
1854                  # Only proceed if there are no missing fields.  
1855                  if (@missing > 0) {  =head3 SortNeeded
1856                          Trace("Relation $relationName for $newObjectType skipped due to missing fields: " .  
1857                                  join(' ', @missing)) if T(1);  C<< my $parms = $erdb->SortNeeded($relationName); >>
1858                  } else {  
1859                          # Build the INSERT statement.  Return the pipe command for the sort that should be applied to the specified
1860                          my $statement = "INSERT INTO $relationName (" . join (', ', @fieldNameList) .  relation when creating the load file.
1861                                  ") VALUES (";  
1862                          # Create a marker list of the proper size and put it in the statement.  For example, if the load file should be sorted ascending by the first
1863                          my @markers = ();  field, this method would return
1864                          while (@markers < @fieldNameList) { push @markers, '?'; }  
1865                          $statement .= join(', ', @markers) . ")";      sort -k1 -t"\t"
1866                          # We have the insert statement, so prepare it.  
1867                          my $sth = $dbh->prepare_command($statement);  If the first field is numeric, the method would return
1868                          Trace("Insert statement prepared: $statement") if T(3);  
1869                          # Now we loop through the values. If a value is scalar, we use it unmodified. If it's      sort -k1n -t"\t"
1870                          # a list, we use the current element. The values are stored in the @parameterList array.  
1871                          my $done = 0;  Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate
1872                          for (my $i = 0; $i < $recordCount; $i++) {  keys using a sort.
1873                                  # Clear the parameter list array.  
1874                                  my @parameterList = ();  =over 4
1875                                  # Loop through the values.  
1876                                  for my $value (@valueList) {  =item relationName
1877                                          # Check to see if this is a scalar value.  
1878                                          if (ref $value eq "ARRAY") {  Name of the relation to be examined.
1879                                                  # Here we have a list value. Pull the current entry.  
1880                                                  push @parameterList, $value->[$i];  =item
1881    
1882    Returns the sort command to use for sorting the relation, suitable for piping.
1883    
1884    =back
1885    
1886    =cut
1887    #: Return Type $;
1888    sub SortNeeded {
1889        # Get the parameters.
1890        my ($self, $relationName) = @_;
1891        # Declare a descriptor to hold the names of the key fields.
1892        my @keyNames = ();
1893        # Get the relation structure.
1894        my $relationData = $self->_FindRelation($relationName);
1895        # Find out if the relation is a primary entity relation,
1896        # a relationship relation, or a secondary entity relation.
1897        my $entityTable = $self->{_metaData}->{Entities};
1898        my $relationshipTable = $self->{_metaData}->{Relationships};
1899        if (exists $entityTable->{$relationName}) {
1900            # Here we have a primary entity relation.
1901            push @keyNames, "id";
1902        } elsif (exists $relationshipTable->{$relationName}) {
1903            # Here we have a relationship. We sort using the FROM index.
1904            my $relationshipData = $relationshipTable->{$relationName};
1905            my $index = $relationData->{Indexes}->{idxFrom};
1906            push @keyNames, @{$index->{IndexFields}};
1907                                          } else {                                          } else {
1908                                                  # Here we have a scalar value. Use it unmodified.          # Here we have a secondary entity relation, so we have a sort on the ID field.
1909                                                  push @parameterList, $value;          push @keyNames, "id";
1910                                          }                                          }
1911        # Now we parse the key names into sort parameters. First, we prime the return
1912        # string.
1913        my $retVal = "sort -t\"\t\" ";
1914        # Get the relation's field list.
1915        my @fields = @{$relationData->{Fields}};
1916        # Loop through the keys.
1917        for my $keyData (@keyNames) {
1918            # Get the key and the ordering.
1919            my ($keyName, $ordering);
1920            if ($keyData =~ /^([^ ]+) DESC/) {
1921                ($keyName, $ordering) = ($1, "descending");
1922            } else {
1923                ($keyName, $ordering) = ($keyData, "ascending");
1924                                  }                                  }
1925                                  # Execute the INSERT statement with the specified parameter list.          # Find the key's position and type.
1926                                  $retVal = $sth->execute(@parameterList);          my $fieldSpec;
1927                                  if (!$retVal) {          for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {
1928                                          my $errorString = $sth->errstr();              my $thisField = $fields[$i];
1929                                          Trace("Insert error: $errorString.") if T(0);              if ($thisField->{name} eq $keyName) {
1930                    # Get the sort modifier for this field type. The modifier
1931                    # decides whether we're using a character, numeric, or
1932                    # floating-point sort.
1933                    my $modifier = $TypeTable{$thisField->{type}}->{sort};
1934                    # If the index is descending for this field, denote we want
1935                    # to reverse the sort order on this field.
1936                    if ($ordering eq 'descending') {
1937                        $modifier .= "r";
1938                    }
1939                    # Store the position and modifier into the field spec, which
1940                    # will stop the inner loop. Note that the field number is
1941                    # 1-based in the sort command, so we have to increment the
1942                    # index.
1943                    $fieldSpec = ($i + 1) . $modifier;
1944                                  }                                  }
1945                          }                          }
1946            # Add this field to the sort command.
1947            $retVal .= " -k$fieldSpec";
1948                  }                  }
1949        # Return the result.
1950        return $retVal;
1951          }          }
1952          # Return the success indicator.  
1953    =head3 GetList
1954    
1955    C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>
1956    
1957    Return a list of object descriptors for the specified objects as determined by the
1958    specified filter clause.
1959    
1960    This method is essentially the same as L</Get> except it returns a list of objects rather
1961    than a query object that can be used to get the results one record at a time.
1962    
1963    =over 4
1964    
1965    =item objectNames
1966    
1967    List containing the names of the entity and relationship objects to be retrieved.
1968    
1969    =item filterClause
1970    
1971    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1972    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
1973    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
1974    in the filter clause should be added to the parameter list as additional parameters. The
1975    fields in a filter clause can come from primary entity relations, relationship relations,
1976    or secondary entity relations; however, all of the entities and relationships involved must
1977    be included in the list of object names.
1978    
1979    The filter clause can also specify a sort order. To do this, simply follow the filter string
1980    with an ORDER BY clause. For example, the following filter string gets all genomes for a
1981    particular genus and sorts them by species name.
1982    
1983    C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
1984    
1985    The rules for field references in a sort order are the same as those for field references in the
1986    filter clause in general; however, odd things may happen if a sort field is from a secondary
1987    relation.
1988    
1989    =item params
1990    
1991    Reference to a list of parameter values to be substituted into the filter clause.
1992    
1993    =item RETURN
1994    
1995    Returns a list of B<DBObject>s that satisfy the query conditions.
1996    
1997    =back
1998    
1999    =cut
2000    #: Return Type @%
2001    sub GetList {
2002        # Get the parameters.
2003        my ($self, $objectNames, $filterClause, $params) = @_;
2004        # Declare the return variable.
2005        my @retVal = ();
2006        # Perform the query.
2007        my $query = $self->Get($objectNames, $filterClause, $params);
2008        # Loop through the results.
2009        while (my $object = $query->Fetch) {
2010            push @retVal, $object;
2011        }
2012        # Return the result.
2013        return @retVal;
2014    }
2015    
2016    =head3 GetCount
2017    
2018    C<< my $count = $erdb->GetCount(\@objectNames, $filter, \@params); >>
2019    
2020    Return the number of rows found by a specified query. This method would
2021    normally be used to count the records in a single table. For example, in a
2022    genetics database
2023    
2024        my $count = $erdb->GetCount(['Genome'], 'Genome(genus-species) LIKE ?', ['homo %']);
2025    
2026    would return the number of genomes for the genus I<homo>. It is conceivable, however,
2027    to use it to return records based on a join. For example,
2028    
2029        my $count = $erdb->GetCount(['HasFeature', 'Genome'], 'Genome(genus-species) LIKE ?',
2030                                    ['homo %']);
2031    
2032    would return the number of features for genomes in the genus I<homo>. Note that
2033    only the rows from the first table are counted. If the above command were
2034    
2035        my $count = $erdb->GetCount(['Genome', 'Feature'], 'Genome(genus-species) LIKE ?',
2036                                    ['homo %']);
2037    
2038    it would return the number of genomes, not the number of genome/feature pairs.
2039    
2040    =over 4
2041    
2042    =item objectNames
2043    
2044    Reference to a list of the objects (entities and relationships) included in the
2045    query.
2046    
2047    =item filter
2048    
2049    A filter clause for restricting the query. The rules are the same as for the L</Get>
2050    method.
2051    
2052    =item params
2053    
2054    Reference to a list of the parameter values to be substituted for the parameter marks
2055    in the filter.
2056    
2057    =item RETURN
2058    
2059    Returns a count of the number of records in the first table that would satisfy
2060    the query.
2061    
2062    =back
2063    
2064    =cut
2065    
2066    sub GetCount {
2067        # Get the parameters.
2068        my ($self, $objectNames, $filter, $params) = @_;
2069        # Insure the params argument is an array reference if the caller left it off.
2070        if (! defined($params)) {
2071            $params = [];
2072        }
2073        # Declare the return variable.
2074        my $retVal;
2075        # Find out if we're counting an entity or a relationship.
2076        my $countedField;
2077        if ($self->IsEntity($objectNames->[0])) {
2078            $countedField = "id";
2079        } else {
2080            # For a relationship we count the to-link because it's usually more
2081            # numerous. Note we're automatically converting to the SQL form
2082            # of the field name (to_link vs. to-link).
2083            $countedField = "to_link";
2084        }
2085        # Create the SQL command suffix to get the desired records.
2086        my ($suffix, $mappedNameListRef, $mappedNameHashRef) = $self->_SetupSQL($objectNames,
2087                                                                                $filter);
2088        # Prefix it with text telling it we want a record count.
2089        my $firstObject = $mappedNameListRef->[0];
2090        my $command = "SELECT COUNT($firstObject.$countedField) $suffix";
2091        # Prepare and execute the command.
2092        my $sth = $self->_GetStatementHandle($command, $params);
2093        # Get the count value.
2094        ($retVal) = $sth->fetchrow_array();
2095        # Check for a problem.
2096        if (! defined($retVal)) {
2097            if ($sth->err) {
2098                # Here we had an SQL error.
2099                Confess("Error retrieving row count: " . $sth->errstr());
2100            } else {
2101                # Here we have no result.
2102                Confess("No result attempting to retrieve row count.");
2103            }
2104        }
2105        # Return the result.
2106        return $retVal;
2107    }
2108    
2109    =head3 ComputeObjectSentence
2110    
2111    C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>
2112    
2113    Check an object name, and if it is a relationship convert it to a relationship sentence.
2114    
2115    =over 4
2116    
2117    =item objectName
2118    
2119    Name of the entity or relationship.
2120    
2121    =item RETURN
2122    
2123    Returns a string containing the entity name or a relationship sentence.
2124    
2125    =back
2126    
2127    =cut
2128    
2129    sub ComputeObjectSentence {
2130        # Get the parameters.
2131        my ($self, $objectName) = @_;
2132        # Set the default return value.
2133        my $retVal = $objectName;
2134        # Look for the object as a relationship.
2135        my $relTable = $self->{_metaData}->{Relationships};
2136        if (exists $relTable->{$objectName}) {
2137            # Get the relationship sentence.
2138            $retVal = _ComputeRelationshipSentence($objectName, $relTable->{$objectName});
2139        }
2140        # Return the result.
2141        return $retVal;
2142    }
2143    
2144    =head3 DumpRelations
2145    
2146    C<< $erdb->DumpRelations($outputDirectory); >>
2147    
2148    Write the contents of all the relations to tab-delimited files in the specified directory.
2149    Each file will have the same name as the relation dumped, with an extension of DTX.
2150    
2151    =over 4
2152    
2153    =item outputDirectory
2154    
2155    Name of the directory into which the relation files should be dumped.
2156    
2157    =back
2158    
2159    =cut
2160    
2161    sub DumpRelations {
2162        # Get the parameters.
2163        my ($self, $outputDirectory) = @_;
2164        # Now we need to run through all the relations. First, we loop through the entities.
2165        my $metaData = $self->{_metaData};
2166        my $entities = $metaData->{Entities};
2167        for my $entityName (keys %{$entities}) {
2168            my $entityStructure = $entities->{$entityName};
2169            # Get the entity's relations.
2170            my $relationList = $entityStructure->{Relations};
2171            # Loop through the relations, dumping them.
2172            for my $relationName (keys %{$relationList}) {
2173                my $relation = $relationList->{$relationName};
2174                $self->_DumpRelation($outputDirectory, $relationName, $relation);
2175            }
2176        }
2177        # Next, we loop through the relationships.
2178        my $relationships = $metaData->{Relationships};
2179        for my $relationshipName (keys %{$relationships}) {
2180            my $relationshipStructure = $relationships->{$relationshipName};
2181            # Dump this relationship's relation.
2182            $self->_DumpRelation($outputDirectory, $relationshipName, $relationshipStructure->{Relations}->{$relationshipName});
2183        }
2184    }
2185    
2186    =head3 InsertValue
2187    
2188    C<< $erdb->InsertValue($entityID, $fieldName, $value); >>
2189    
2190    This method will insert a new value into the database. The value must be one
2191    associated with a secondary relation, since primary values cannot be inserted:
2192    they occur exactly once. Secondary values, on the other hand, can be missing
2193    or multiply-occurring.
2194    
2195    =over 4
2196    
2197    =item entityID
2198    
2199    ID of the object that is to receive the new value.
2200    
2201    =item fieldName
2202    
2203    Field name for the new value-- this includes the entity name, since
2204    field names are of the format I<objectName>C<(>I<fieldName>C<)>.
2205    
2206    =item value
2207    
2208    New value to be put in the field.
2209    
2210    =back
2211    
2212    =cut
2213    
2214    sub InsertValue {
2215        # Get the parameters.
2216        my ($self, $entityID, $fieldName, $value) = @_;
2217        # Parse the entity name and the real field name.
2218        if ($fieldName =~ /^([^(]+)\(([^)]+)\)/) {
2219            my $entityName = $1;
2220            my $fieldTitle = $2;
2221            # Get its descriptor.
2222            if (!$self->IsEntity($entityName)) {
2223                Confess("$entityName is not a valid entity.");
2224            } else {
2225                my $entityData = $self->{_metaData}->{Entities}->{$entityName};
2226                # Find the relation containing this field.
2227                my $fieldHash = $entityData->{Fields};
2228                if (! exists $fieldHash->{$fieldTitle}) {
2229                    Confess("$fieldTitle not found in $entityName.");
2230                } else {
2231                    my $relation = $fieldHash->{$fieldTitle}->{relation};
2232                    if ($relation eq $entityName) {
2233                        Confess("Cannot do InsertValue on primary field $fieldTitle of $entityName.");
2234                    } else {
2235                        # Now we can create an INSERT statement.
2236                        my $dbh = $self->{_dbh};
2237                        my $fixedName = _FixName($fieldTitle);
2238                        my $statement = "INSERT INTO $relation (id, $fixedName) VALUES(?, ?)";
2239                        # Execute the command.
2240                        $dbh->SQL($statement, 0, $entityID, $value);
2241                    }
2242                }
2243            }
2244        } else {
2245            Confess("$fieldName is not a valid field name.");
2246        }
2247    }
2248    
2249    =head3 InsertObject
2250    
2251    C<< $erdb->InsertObject($objectType, \%fieldHash); >>
2252    
2253    Insert an object into the database. The object is defined by a type name and then a hash
2254    of field names to values. Field values in the primary relation are represented by scalars.
2255    (Note that for relationships, the primary relation is the B<only> relation.)
2256    Field values for the other relations comprising the entity are always list references. For
2257    example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases
2258    C<ZP_00210270.1> and C<gi|46206278>.
2259    
2260    C<< $erdb->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>
2261    
2262    The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
2263    property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
2264    
2265    C<< $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>
2266    
2267    =over 4
2268    
2269    =item newObjectType
2270    
2271    Type name of the object to insert.
2272    
2273    =item fieldHash
2274    
2275    Hash of field names to values.
2276    
2277    =back
2278    
2279    =cut
2280    
2281    sub InsertObject {
2282        # Get the parameters.
2283        my ($self, $newObjectType, $fieldHash) = @_;
2284        # Denote that so far we appear successful.
2285        my $retVal = 1;
2286        # Get the database handle.
2287        my $dbh = $self->{_dbh};
2288        # Get the relation list.
2289        my $relationTable = $self->_GetRelationTable($newObjectType);
2290        # Loop through the relations. We'll build insert statements for each one. If a relation is
2291        # secondary, we may end up generating multiple insert statements. If an error occurs, we
2292        # stop the loop.
2293        my @relationList = keys %{$relationTable};
2294        for (my $i = 0; $retVal && $i <= $#relationList; $i++) {
2295            my $relationName = $relationList[$i];
2296            my $relationDefinition = $relationTable->{$relationName};
2297            # Get the relation's fields. For each field we will collect a value in the corresponding
2298            # position of the @valueList array. If one of the fields is missing, we will add it to the
2299            # @missing list.
2300            my @fieldList = @{$relationDefinition->{Fields}};
2301            my @fieldNameList = ();
2302            my @valueList = ();
2303            my @missing = ();
2304            my $recordCount = 1;
2305            for my $fieldDescriptor (@fieldList) {
2306                # Get the field name and save it. Note we need to fix it up so the hyphens
2307                # are converted to underscores.
2308                my $fieldName = $fieldDescriptor->{name};
2309                push @fieldNameList, _FixName($fieldName);
2310                # Look for the named field in the incoming structure. Note that we are looking
2311                # for the real field name, not the fixed-up one!
2312                if (exists $fieldHash->{$fieldName}) {
2313                    # Here we found the field. Stash it in the value list.
2314                    my $value = $fieldHash->{$fieldName};
2315                    push @valueList, $value;
2316                    # If the value is a list, we may need to increment the record count.
2317                    if (ref $value eq "ARRAY") {
2318                        my $thisCount = @{$value};
2319                        if ($recordCount == 1) {
2320                            # Here we have our first list, so we save its count.
2321                            $recordCount = $thisCount;
2322                        } elsif ($recordCount != $thisCount) {
2323                            # Here we have a second list, so its length has to match the
2324                            # previous lists.
2325                            Trace("Field $value in new $newObjectType object has an invalid list length $thisCount. Expected $recordCount.") if T(0);
2326                            $retVal = 0;
2327                        }
2328                    }
2329                } else {
2330                    # Here the field is not present. Flag it as missing.
2331                    push @missing, $fieldName;
2332                }
2333            }
2334            # If we are the primary relation, add the new-record flag.
2335            if ($relationName eq $newObjectType) {
2336                push @valueList, 1;
2337                push @fieldNameList, "new_record";
2338            }
2339            # Only proceed if there are no missing fields.
2340            if (@missing > 0) {
2341                Trace("Relation $relationName for $newObjectType skipped due to missing fields: " .
2342                    join(' ', @missing)) if T(1);
2343            } else {
2344                # Build the INSERT statement.
2345                my $statement = "INSERT INTO $relationName (" . join (', ', @fieldNameList) .
2346                    ") VALUES (";
2347                # Create a marker list of the proper size and put it in the statement.
2348                my @markers = ();
2349                while (@markers < @fieldNameList) { push @markers, '?'; }
2350                $statement .= join(', ', @markers) . ")";
2351                # We have the insert statement, so prepare it.
2352                my $sth = $dbh->prepare_command($statement);
2353                Trace("Insert statement prepared: $statement") if T(3);
2354                # Now we loop through the values. If a value is scalar, we use it unmodified. If it's
2355                # a list, we use the current element. The values are stored in the @parameterList array.
2356                my $done = 0;
2357                for (my $i = 0; $i < $recordCount; $i++) {
2358                    # Clear the parameter list array.
2359                    my @parameterList = ();
2360                    # Loop through the values.
2361                    for my $value (@valueList) {
2362                        # Check to see if this is a scalar value.
2363                        if (ref $value eq "ARRAY") {
2364                            # Here we have a list value. Pull the current entry.
2365                            push @parameterList, $value->[$i];
2366                        } else {
2367                            # Here we have a scalar value. Use it unmodified.
2368                            push @parameterList, $value;
2369                        }
2370                    }
2371                    # Execute the INSERT statement with the specified parameter list.
2372                    $retVal = $sth->execute(@parameterList);
2373                    if (!$retVal) {
2374                        my $errorString = $sth->errstr();
2375                        Confess("Error inserting into $relationName: $errorString");
2376                    }
2377                }
2378            }
2379        }
2380        # Return a 1 for backward compatability.
2381        return 1;
2382    }
2383    
2384    =head3 UpdateEntity
2385    
2386    C<< $erdb->UpdateEntity($entityName, $id, \%fields); >>
2387    
2388    Update the values of an entity. This is an unprotected update, so it should only be
2389    done if the database resides on a database server.
2390    
2391    =over 4
2392    
2393    =item entityName
2394    
2395    Name of the entity to update. (This is the entity type.)
2396    
2397    =item id
2398    
2399    ID of the entity to update. If no entity exists with this ID, an error will be thrown.
2400    
2401    =item fields
2402    
2403    Reference to a hash mapping field names to their new values. All of the fields named
2404    must be in the entity's primary relation, and they cannot any of them be the ID field.
2405    
2406    =back
2407    
2408    =cut
2409    
2410    sub UpdateEntity {
2411        # Get the parameters.
2412        my ($self, $entityName, $id, $fields) = @_;
2413        # Get a list of the field names being updated.
2414        my @fieldList = keys %{$fields};
2415        # Verify that the fields exist.
2416        my $checker = $self->GetFieldTable($entityName);
2417        for my $field (@fieldList) {
2418            if ($field eq 'id') {
2419                Confess("Cannot update the ID field for entity $entityName.");
2420            } elsif ($checker->{$field}->{relation} ne $entityName) {
2421                Confess("Cannot find $field in primary relation of $entityName.");
2422            }
2423        }
2424        # Build the SQL statement.
2425        my @sets = ();
2426        my @valueList = ();
2427        for my $field (@fieldList) {
2428            push @sets, _FixName($field) . " = ?";
2429            push @valueList, $fields->{$field};
2430        }
2431        my $command = "UPDATE $entityName SET " . join(", ", @sets) . " WHERE id = ?";
2432        # Add the ID to the list of binding values.
2433        push @valueList, $id;
2434        # Call SQL to do the work.
2435        my $rows = $self->{_dbh}->SQL($command, 0, @valueList);
2436        # Check for errors.
2437        if ($rows == 0) {
2438            Confess("Entity $id of type $entityName not found.");
2439        }
2440    }
2441    
2442    =head3 LoadTable
2443    
2444    C<< my $results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>
2445    
2446    Load data from a tab-delimited file into a specified table, optionally re-creating the table
2447    first.
2448    
2449    =over 4
2450    
2451    =item fileName
2452    
2453    Name of the file from which the table data should be loaded.
2454    
2455    =item relationName
2456    
2457    Name of the relation to be loaded. This is the same as the table name.
2458    
2459    =item truncateFlag
2460    
2461    TRUE if the table should be dropped and re-created, else FALSE
2462    
2463    =item RETURN
2464    
2465    Returns a statistical object containing a list of the error messages.
2466    
2467    =back
2468    
2469    =cut
2470    sub LoadTable {
2471        # Get the parameters.
2472        my ($self, $fileName, $relationName, $truncateFlag) = @_;
2473        # Create the statistical return object.
2474        my $retVal = _GetLoadStats();
2475        # Trace the fact of the load.
2476        Trace("Loading table $relationName from $fileName") if T(2);
2477        # Get the database handle.
2478        my $dbh = $self->{_dbh};
2479        # Get the input file size.
2480        my $fileSize = -s $fileName;
2481        # Get the relation data.
2482        my $relation = $self->_FindRelation($relationName);
2483        # Check the truncation flag.
2484        if ($truncateFlag) {
2485            Trace("Creating table $relationName") if T(2);
2486            # Compute the row count estimate. We take the size of the load file,
2487            # divide it by the estimated row size, and then multiply by 1.5 to
2488            # leave extra room. We postulate a minimum row count of 1000 to
2489            # prevent problems with incoming empty load files.
2490            my $rowSize = $self->EstimateRowSize($relationName);
2491            my $estimate = FIG::max($fileSize * 1.5 / $rowSize, 1000);
2492            # Re-create the table without its index.
2493            $self->CreateTable($relationName, 0, $estimate);
2494            # If this is a pre-index DBMS, create the index here.
2495            if ($dbh->{_preIndex}) {
2496                eval {
2497                    $self->CreateIndex($relationName);
2498                };
2499                if ($@) {
2500                    $retVal->AddMessage($@);
2501                }
2502            }
2503        }
2504        # Load the table.
2505        my $rv;
2506        eval {
2507            $rv = $dbh->load_table(file => $fileName, tbl => $relationName);
2508        };
2509        if (!defined $rv) {
2510            $retVal->AddMessage($@) if ($@);
2511            $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2512            Trace("Table load failed for $relationName.") if T(1);
2513        } else {
2514            # Here we successfully loaded the table.
2515            $retVal->Add("tables");
2516            my $size = -s $fileName;
2517            Trace("$size bytes loaded into $relationName.") if T(2);
2518            # If we're rebuilding, we need to create the table indexes.
2519            if ($truncateFlag) {
2520                # Indexes are created here for PostGres. For PostGres, indexes are
2521                # best built at the end. For MySQL, the reverse is true.
2522                if (! $dbh->{_preIndex}) {
2523                    eval {
2524                        $self->CreateIndex($relationName);
2525                    };
2526                    if ($@) {
2527                        $retVal->AddMessage($@);
2528                    }
2529                }
2530                # The full-text index (if any) is always built last, even for MySQL.
2531                # First we need to see if this table has a full-text index. Only
2532                # primary relations are allowed that privilege.
2533                if ($self->_IsPrimary($relationName)) {
2534                    # Get the relation's entity/relationship structure.
2535                    my $structure = $self->_GetStructure($relationName);
2536                    # Check for a searchable fields list.
2537                    if (exists $structure->{searchFields}) {
2538                        # Here we know that we need to create a full-text search index.
2539                        # Get an SQL-formatted field name list.
2540                        my $fields = join(", ", $self->_FixNames(@{$structure->{searchFields}}));
2541                        # Create the index.
2542                        $dbh->create_index(tbl => $relationName, idx => "search_idx",
2543                                           flds => $fields, kind => 'fulltext');
2544                    }
2545                }
2546            }
2547        }
2548        # Analyze the table to improve performance.
2549        Trace("Analyzing and compacting $relationName.") if T(3);
2550        $dbh->vacuum_it($relationName);
2551        Trace("$relationName load completed.") if T(3);
2552        # Return the statistics.
2553        return $retVal;
2554    }
2555    
2556    =head3 DropRelation
2557    
2558    C<< $erdb->DropRelation($relationName); >>
2559    
2560    Physically drop a relation from the database.
2561    
2562    =over 4
2563    
2564    =item relationName
2565    
2566    Name of the relation to drop. If it does not exist, this method will have
2567    no effect.
2568    
2569    =back
2570    
2571    =cut
2572    
2573    sub DropRelation {
2574        # Get the parameters.
2575        my ($self, $relationName) = @_;
2576        # Get the database handle.
2577        my $dbh = $self->{_dbh};
2578        # Drop the relation. The method used here has no effect if the relation
2579        # does not exist.
2580        Trace("Invoking DB Kernel to drop $relationName.") if T(3);
2581        $dbh->drop_table(tbl => $relationName);
2582    }
2583    
2584    =head3 MatchSqlPattern
2585    
2586    C<< my $matched = ERDB::MatchSqlPattern($value, $pattern); >>
2587    
2588    Determine whether or not a specified value matches an SQL pattern. An SQL
2589    pattern has two wild card characters: C<%> that matches multiple characters,
2590    and C<_> that matches a single character. These can be escaped using a
2591    backslash (C<\>). We pull this off by converting the SQL pattern to a
2592    PERL regular expression. As per SQL rules, the match is case-insensitive.
2593    
2594    =over 4
2595    
2596    =item value
2597    
2598    Value to be matched against the pattern. Note that an undefined or empty
2599    value will not match anything.
2600    
2601    =item pattern
2602    
2603    SQL pattern against which to match the value. An undefined or empty pattern will
2604    match everything.
2605    
2606    =item RETURN
2607    
2608    Returns TRUE if the value and pattern match, else FALSE.
2609    
2610    =back
2611    
2612    =cut
2613    
2614    sub MatchSqlPattern {
2615        # Get the parameters.
2616        my ($value, $pattern) = @_;
2617        # Declare the return variable.
2618        my $retVal;
2619        # Insure we have a pattern.
2620        if (! defined($pattern) || $pattern eq "") {
2621            $retVal = 1;
2622        } else {
2623            # Break the pattern into pieces around the wildcard characters. Because we
2624            # use parentheses in the split function's delimiter expression, we'll get
2625            # list elements for the delimiters as well as the rest of the string.
2626            my @pieces = split /([_%]|\\[_%])/, $pattern;
2627            # Check some fast special cases.
2628            if ($pattern eq '%') {
2629                # A null pattern matches everything.
2630                $retVal = 1;
2631            } elsif (@pieces == 1) {
2632                # No wildcards, so we have a literal comparison. Note we're case-insensitive.
2633                $retVal = (lc($value) eq lc($pattern));
2634            } elsif (@pieces == 2 && $pieces[1] eq '%') {
2635                # A wildcard at the end, so we have a substring match. This is also case-insensitive.
2636                $retVal = (lc(substr($value, 0, length($pieces[0]))) eq lc($pieces[0]));
2637            } else {
2638                # Okay, we have to do it the hard way. Convert each piece to a PERL pattern.
2639                my $realPattern = "";
2640                for my $piece (@pieces) {
2641                    # Determine the type of piece.
2642                    if ($piece eq "") {
2643                        # Empty pieces are ignored.
2644                    } elsif ($piece eq "%") {
2645                        # Here we have a multi-character wildcard. Note that it can match
2646                        # zero or more characters.
2647                        $realPattern .= ".*"
2648                    } elsif ($piece eq "_") {
2649                        # Here we have a single-character wildcard.
2650                        $realPattern .= ".";
2651                    } elsif ($piece eq "\\%" || $piece eq "\\_") {
2652                        # This is an escape sequence (which is a rare thing, actually).
2653                        $realPattern .= substr($piece, 1, 1);
2654                    } else {
2655                        # Here we have raw text.
2656                        $realPattern .= quotemeta($piece);
2657                    }
2658                }
2659                # Do the match.
2660                $retVal = ($value =~ /^$realPattern$/i ? 1 : 0);
2661            }
2662        }
2663        # Return the result.
2664        return $retVal;
2665    }
2666    
2667    =head3 GetEntity
2668    
2669    C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>
2670    
2671    Return an object describing the entity instance with a specified ID.
2672    
2673    =over 4
2674    
2675    =item entityType
2676    
2677    Entity type name.
2678    
2679    =item ID
2680    
2681    ID of the desired entity.
2682    
2683    =item RETURN
2684    
2685    Returns a B<DBObject> representing the desired entity instance, or an undefined value if no
2686    instance is found with the specified key.
2687    
2688    =back
2689    
2690    =cut
2691    
2692    sub GetEntity {
2693        # Get the parameters.
2694        my ($self, $entityType, $ID) = @_;
2695        # Create a query.
2696        my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);
2697        # Get the first (and only) object.
2698        my $retVal = $query->Fetch();
2699        # Return the result.
2700        return $retVal;
2701    }
2702    
2703    =head3 GetChoices
2704    
2705    C<< my @values = $erdb->GetChoices($entityName, $fieldName); >>
2706    
2707    Return a list of all the values for the specified field that are represented in the
2708    specified entity.
2709    
2710    Note that if the field is not indexed, then this will be a very slow operation.
2711    
2712    =over 4
2713    
2714    =item entityName
2715    
2716    Name of an entity in the database.
2717    
2718    =item fieldName
2719    
2720    Name of a field belonging to the entity. This is a raw field name without
2721    the standard parenthesized notation used in most calls.
2722    
2723    =item RETURN
2724    
2725    Returns a list of the distinct values for the specified field in the database.
2726    
2727    =back
2728    
2729    =cut
2730    
2731    sub GetChoices {
2732        # Get the parameters.
2733        my ($self, $entityName, $fieldName) = @_;
2734        # Declare the return variable.
2735        my @retVal;
2736        # Get the entity data structure.
2737        my $entityData = $self->_GetStructure($entityName);
2738        # Get the field.
2739        my $fieldHash = $entityData->{Fields};
2740        if (! exists $fieldHash->{$fieldName}) {
2741            Confess("$fieldName not found in $entityName.");
2742        } else {
2743            # Get the name of the relation containing the field.
2744            my $relation = $fieldHash->{$fieldName}->{relation};
2745            # Fix up the field name.
2746            my $realName = _FixName($fieldName);
2747            # Get the database handle.
2748            my $dbh = $self->{_dbh};
2749            # Query the database.
2750            my $results = $dbh->SQL("SELECT DISTINCT $realName FROM $relation");
2751            # Clean the results. They are stored as a list of lists, and we just want the one list.
2752            @retVal = sort map { $_->[0] } @{$results};
2753        }
2754        # Return the result.
2755        return @retVal;
2756    }
2757    
2758    =head3 GetEntityValues
2759    
2760    C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>
2761    
2762    Return a list of values from a specified entity instance. If the entity instance
2763    does not exist, an empty list is returned.
2764    
2765    =over 4
2766    
2767    =item entityType
2768    
2769    Entity type name.
2770    
2771    =item ID
2772    
2773    ID of the desired entity.
2774    
2775    =item fields
2776    
2777    List of field names, each of the form I<objectName>C<(>I<fieldName>C<)>.
2778    
2779    =item RETURN
2780    
2781    Returns a flattened list of the values of the specified fields for the specified entity.
2782    
2783    =back
2784    
2785    =cut
2786    
2787    sub GetEntityValues {
2788        # Get the parameters.
2789        my ($self, $entityType, $ID, $fields) = @_;
2790        # Get the specified entity.
2791        my $entity = $self->GetEntity($entityType, $ID);
2792        # Declare the return list.
2793        my @retVal = ();
2794        # If we found the entity, push the values into the return list.
2795        if ($entity) {
2796            push @retVal, $entity->Values($fields);
2797        }
2798        # Return the result.
2799        return @retVal;
2800    }
2801    
2802    =head3 GetAll
2803    
2804    C<< my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>
2805    
2806    Return a list of values taken from the objects returned by a query. The first three
2807    parameters correspond to the parameters of the L</Get> method. The final parameter is
2808    a list of the fields desired from each record found by the query. The field name
2809    syntax is the standard syntax used for fields in the B<ERDB> system--
2810    B<I<objectName>(I<fieldName>)>-- where I<objectName> is the name of the relevant entity
2811    or relationship and I<fieldName> is the name of the field.
2812    
2813    The list returned will be a list of lists. Each element of the list will contain
2814    the values returned for the fields specified in the fourth parameter. If one of the
2815    fields specified returns multiple values, they are flattened in with the rest. For
2816    example, the following call will return a list of the features in a particular
2817    spreadsheet cell, and each feature will be represented by a list containing the
2818    feature ID followed by all of its aliases.
2819    
2820    C<< @query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>
2821    
2822    =over 4
2823    
2824    =item objectNames
2825    
2826    List containing the names of the entity and relationship objects to be retrieved.
2827    
2828    =item filterClause
2829    
2830    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
2831    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
2832    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
2833    parameter list as additional parameters. The fields in a filter clause can come from primary
2834    entity relations, relationship relations, or secondary entity relations; however, all of the
2835    entities and relationships involved must be included in the list of object names.
2836    
2837    =item parameterList
2838    
2839    List of the parameters to be substituted in for the parameters marks in the filter clause.
2840    
2841    =item fields
2842    
2843    List of the fields to be returned in each element of the list returned.
2844    
2845    =item count
2846    
2847    Maximum number of records to return. If omitted or 0, all available records will be returned.
2848    
2849    =item RETURN
2850    
2851    Returns a list of list references. Each element of the return list contains the values for the
2852    fields specified in the B<fields> parameter.
2853    
2854    =back
2855    
2856    =cut
2857    #: Return Type @@;
2858    sub GetAll {
2859        # Get the parameters.
2860        my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
2861        # Translate the parameters from a list reference to a list. If the parameter
2862        # list is a scalar we convert it into a singleton list.
2863        my @parmList = ();
2864        if (ref $parameterList eq "ARRAY") {
2865            Trace("GetAll parm list is an array.") if T(4);
2866            @parmList = @{$parameterList};
2867        } else {
2868            Trace("GetAll parm list is a scalar: $parameterList.") if T(4);
2869            push @parmList, $parameterList;
2870        }
2871        # Insure the counter has a value.
2872        if (!defined $count) {
2873            $count = 0;
2874        }
2875        # Add the row limit to the filter clause.
2876        if ($count > 0) {
2877            $filterClause .= " LIMIT $count";
2878        }
2879        # Create the query.
2880        my $query = $self->Get($objectNames, $filterClause, \@parmList);
2881        # Set up a counter of the number of records read.
2882        my $fetched = 0;
2883        # Loop through the records returned, extracting the fields. Note that if the
2884        # counter is non-zero, we stop when the number of records read hits the count.
2885        my @retVal = ();
2886        while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {
2887            my @rowData = $row->Values($fields);
2888            push @retVal, \@rowData;
2889            $fetched++;
2890        }
2891        Trace("$fetched rows returned in GetAll.") if T(SQL => 4);
2892        # Return the resulting list.
2893        return @retVal;
2894    }
2895    
2896    =head3 Exists
2897    
2898    C<< my $found = $sprout->Exists($entityName, $entityID); >>
2899    
2900    Return TRUE if an entity exists, else FALSE.
2901    
2902    =over 4
2903    
2904    =item entityName
2905    
2906    Name of the entity type (e.g. C<Feature>) relevant to the existence check.
2907    
2908    =item entityID
2909    
2910    ID of the entity instance whose existence is to be checked.
2911    
2912    =item RETURN
2913    
2914    Returns TRUE if the entity instance exists, else FALSE.
2915    
2916    =back
2917    
2918    =cut
2919    #: Return Type $;
2920    sub Exists {
2921        # Get the parameters.
2922        my ($self, $entityName, $entityID) = @_;
2923        # Check for the entity instance.
2924        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
2925        my $testInstance = $self->GetEntity($entityName, $entityID);
2926        # Return an existence indicator.
2927        my $retVal = ($testInstance ? 1 : 0);
2928        return $retVal;
2929    }
2930    
2931    =head3 EstimateRowSize
2932    
2933    C<< my $rowSize = $erdb->EstimateRowSize($relName); >>
2934    
2935    Estimate the row size of the specified relation. The estimated row size is computed by adding
2936    up the average length for each data type.
2937    
2938    =over 4
2939    
2940    =item relName
2941    
2942    Name of the relation whose estimated row size is desired.
2943    
2944    =item RETURN
2945    
2946    Returns an estimate of the row size for the specified relation.
2947    
2948    =back
2949    
2950    =cut
2951    #: Return Type $;
2952    sub EstimateRowSize {
2953        # Get the parameters.
2954        my ($self, $relName) = @_;
2955        # Declare the return variable.
2956        my $retVal = 0;
2957        # Find the relation descriptor.
2958        my $relation = $self->_FindRelation($relName);
2959        # Get the list of fields.
2960        for my $fieldData (@{$relation->{Fields}}) {
2961            # Get the field type and add its length.
2962            my $fieldLen = $TypeTable{$fieldData->{type}}->{avgLen};
2963            $retVal += $fieldLen;
2964        }
2965        # Return the result.
2966        return $retVal;
2967    }
2968    
2969    =head3 GetFieldTable
2970    
2971    C<< my $fieldHash = $self->GetFieldTable($objectnName); >>
2972    
2973    Get the field structure for a specified entity or relationship.
2974    
2975    =over 4
2976    
2977    =item objectName
2978    
2979    Name of the desired entity or relationship.
2980    
2981    =item RETURN
2982    
2983    The table containing the field descriptors for the specified object.
2984    
2985    =back
2986    
2987    =cut
2988    
2989    sub GetFieldTable {
2990        # Get the parameters.
2991        my ($self, $objectName) = @_;
2992        # Get the descriptor from the metadata.
2993        my $objectData = $self->_GetStructure($objectName);
2994        # Return the object's field table.
2995        return $objectData->{Fields};
2996    }
2997    
2998    =head3 SplitKeywords
2999    
3000    C<< my @keywords = ERDB::SplitKeywords($keywordString); >>
3001    
3002    This method returns a list of the positive keywords in the specified
3003    keyword string. All of the operators will have been stripped off,
3004    and if the keyword is preceded by a minus operator (C<->), it will
3005    not be in the list returned. The idea here is to get a list of the
3006    keywords the user wants to see. The list will be processed to remove
3007    duplicates.
3008    
3009    It is possible to create a string that confuses this method. For example
3010    
3011        frog toad -frog
3012    
3013    would return both C<frog> and C<toad>. If this is a problem we can deal
3014    with it later.
3015    
3016    =over 4
3017    
3018    =item keywordString
3019    
3020    The keyword string to be parsed.
3021    
3022    =item RETURN
3023    
3024    Returns a list of the words in the keyword string the user wants to
3025    see.
3026    
3027    =back
3028    
3029    =cut
3030    
3031    sub SplitKeywords {
3032        # Get the parameters.
3033        my ($keywordString) = @_;
3034        # Make a safety copy of the string. (This helps during debugging.)
3035        my $workString = $keywordString;
3036        # Convert operators we don't care about to spaces.
3037        $workString =~ tr/+"()<>/ /;
3038        # Split the rest of the string along space boundaries. Note that we
3039        # eliminate any words that are zero length or begin with a minus sign.
3040        my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
3041        # Use a hash to remove duplicates.
3042        my %words = map { $_ => 1 } @wordList;
3043        # Return the result.
3044        return sort keys %words;
3045    }
3046    
3047    =head3 ValidateFieldName
3048    
3049    C<< my $okFlag = ERDB::ValidateFieldName($fieldName); >>
3050    
3051    Return TRUE if the specified field name is valid, else FALSE. Valid field names must
3052    be hyphenated words subject to certain restrictions.
3053    
3054    =over 4
3055    
3056    =item fieldName
3057    
3058    Field name to be validated.
3059    
3060    =item RETURN
3061    
3062    Returns TRUE if the field name is valid, else FALSE.
3063    
3064    =back
3065    
3066    =cut
3067    
3068    sub ValidateFieldName {
3069        # Get the parameters.
3070        my ($fieldName) = @_;
3071        # Declare the return variable. The field name is valid until we hear
3072        # differently.
3073        my $retVal = 1;
3074        # Compute the maximum name length.
3075        my $maxLen = $TypeTable{'name-string'}->{maxLen};
3076        # Look for bad stuff in the name.
3077        if ($fieldName =~ /--/) {
3078            # Here we have a doubled minus sign.
3079            Trace("Field name $fieldName has a doubled hyphen.") if T(1);
3080            $retVal = 0;
3081        } elsif ($fieldName !~ /^[A-Za-z]/) {
3082            # Here the field name is missing the initial letter.
3083            Trace("Field name $fieldName does not begin with a letter.") if T(1);
3084            $retVal = 0;
3085        } elsif (length($fieldName) > $maxLen) {
3086            # Here the field name is too long.
3087            Trace("Maximum field name length is $maxLen. Field name must be truncated to " . substr($fieldName,0, $maxLen) . ".");
3088        } else {
3089            # Strip out the minus signs. Everything remaining must be a letter,
3090            # underscore, or digit.
3091            my $strippedName = $fieldName;
3092            $strippedName =~ s/-//g;
3093            if ($strippedName !~ /^(\w|\d)+$/) {
3094                Trace("Field name $fieldName contains illegal characters.") if T(1);
3095                $retVal = 0;
3096            }
3097        }
3098        # Return the result.
3099        return $retVal;
3100    }
3101    
3102    =head3 ReadMetaXML
3103    
3104    C<< my $rawMetaData = ERDB::ReadDBD($fileName); >>
3105    
3106    This method reads a raw database definition XML file and returns it.
3107    Normally, the metadata used by the ERDB system has been processed and
3108    modified to make it easier to load and retrieve the data; however,
3109    this method can be used to get the data in its raw form.
3110    
3111    =over 4
3112    
3113    =item fileName
3114    
3115    Name of the XML file to read.
3116    
3117    =item RETURN
3118    
3119    Returns a hash reference containing the raw XML data from the specified file.
3120    
3121    =back
3122    
3123    =cut
3124    
3125    sub ReadMetaXML {
3126        # Get the parameters.
3127        my ($fileName) = @_;
3128        # Read the XML.
3129        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
3130        Trace("XML metadata loaded from file $fileName.") if T(1);
3131        # Return the result.
3132        return $retVal;
3133    }
3134    
3135    =head3 GetEntityFieldHash
3136    
3137    C<< my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName); >>
3138    
3139    Get the field hash of the named entity in the specified raw XML structure.
3140    The field hash may not exist, in which case we need to create it.
3141    
3142    =over 4
3143    
3144    =item structure
3145    
3146    Raw XML structure defininng the database. This is not the run-time XML used by
3147    an ERDB object, since that has all sorts of optimizations built-in.
3148    
3149    =item entityName
3150    
3151    Name of the entity whose field structure is desired.
3152    
3153    =item RETURN
3154    
3155    Returns the field hash used to define the entity's fields.
3156    
3157    =back
3158    
3159    =cut
3160    
3161    sub GetEntityFieldHash {
3162        # Get the parameters.
3163        my ($structure, $entityName) = @_;
3164        # Get the entity structure.
3165        my $entityData = $structure->{Entities}->{$entityName};
3166        # Look for a field structure.
3167        my $retVal = $entityData->{Fields};
3168        # If it doesn't exist, create it.
3169        if (! defined($retVal)) {
3170            $entityData->{Fields} = {};
3171            $retVal = $entityData->{Fields};
3172        }
3173        # Return the result.
3174        return $retVal;
3175    }
3176    
3177    =head3 WriteMetaXML
3178    
3179    C<< ERDB::WriteMetaXML($structure, $fileName); >>
3180    
3181    Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
3182    used to update the database definition. It must be used with care, however, since it
3183    will only work on a raw structure, not on the processed structure created by an ERDB
3184    constructor.
3185    
3186    =over 4
3187    
3188    =item structure
3189    
3190    XML structure to be written to the file.
3191    
3192    =item fileName
3193    
3194    Name of the output file to which the updated XML should be stored.
3195    
3196    =back
3197    
3198    =cut
3199    
3200    sub WriteMetaXML {
3201        # Get the parameters.
3202        my ($structure, $fileName) = @_;
3203        # Compute the output.
3204        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
3205        # Write it to the file.
3206        my $xmlOut = Open(undef, ">$fileName");
3207        print $xmlOut $fileString;
3208    }
3209    
3210    
3211    =head3 HTMLNote
3212    
3213    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
3214    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
3215    Except for C<[p]>, all the codes are closed by slash-codes. So, for
3216    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
3217    
3218    C<< my $realHtml = ERDB::HTMLNote($dataString); >>
3219    
3220    =over 4
3221    
3222    =item dataString
3223    
3224    String to convert to HTML.
3225    
3226    =item RETURN
3227    
3228    An HTML string derived from the input string.
3229    
3230    =back
3231    
3232    =cut
3233    
3234    sub HTMLNote {
3235        # Get the parameter.
3236        my ($dataString) = @_;
3237        # HTML-escape the text.
3238        my $retVal = CGI::escapeHTML($dataString);
3239        # Substitute the bulletin board codes.
3240        $retVal =~ s!\[(/?[bi])\]!<$1>!g;
3241        $retVal =~ s!\[p\]!</p><p>!g;
3242        # Return the result.
3243          return $retVal;          return $retVal;
3244  }  }
3245    
 =head3 LoadTable  
3246    
3247  C<< my %results = $database->LoadTable($fileName, $relationName, $truncateFlag); >>  =head2 Data Mining Methods
3248    
3249    =head3 GetUsefulCrossValues
3250    
3251    C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>
3252    
3253  Load data from a tab-delimited file into a specified table, optionally re-creating the table first.  Return a list of the useful attributes that would be returned by a B<Cross> call
3254    from an entity of the source entity type through the specified relationship. This
3255    means it will return the fields of the target entity type and the intersection data
3256    fields in the relationship. Only primary table fields are returned. In other words,
3257    the field names returned will be for fields where there is always one and only one
3258    value.
3259    
3260  =over 4  =over 4
3261    
3262  =item fileName  =item sourceEntity
3263    
3264  Name of the file from which the table data should be loaded.  Name of the entity from which the relationship crossing will start.
3265    
3266  =item relationName  =item relationship
3267    
3268  Name of the relation to be loaded. This is the same as the table name.  Name of the relationship being crossed.
3269    
3270  =item truncateFlag  =item RETURN
3271    
3272  TRUE if the table should be dropped and re-created, else FALSE  Returns a list of field names in Sprout field format (I<objectName>C<(>I<fieldName>C<)>.
3273    
3274    =back
3275    
3276    =cut
3277    #: Return Type @;
3278    sub GetUsefulCrossValues {
3279        # Get the parameters.
3280        my ($self, $sourceEntity, $relationship) = @_;
3281        # Declare the return variable.
3282        my @retVal = ();
3283        # Determine the target entity for the relationship. This is whichever entity is not
3284        # the source entity. So, if the source entity is the FROM, we'll get the name of
3285        # the TO, and vice versa.
3286        my $relStructure = $self->_GetStructure($relationship);
3287        my $targetEntityType = ($relStructure->{from} eq $sourceEntity ? "to" : "from");
3288        my $targetEntity = $relStructure->{$targetEntityType};
3289        # Get the field table for the entity.
3290        my $entityFields = $self->GetFieldTable($targetEntity);
3291        # The field table is a hash. The hash key is the field name. The hash value is a structure.
3292        # For the entity fields, the key aspect of the target structure is that the {relation} value
3293        # must match the entity name.
3294        my @fieldList = map { "$targetEntity($_)" } grep { $entityFields->{$_}->{relation} eq $targetEntity }
3295                            keys %{$entityFields};
3296        # Push the fields found onto the return variable.
3297        push @retVal, sort @fieldList;
3298        # Get the field table for the relationship.
3299        my $relationshipFields = $self->GetFieldTable($relationship);
3300        # Here we have a different rule. We want all the fields other than "from-link" and "to-link".
3301        # This may end up being an empty set.
3302        my @fieldList2 = map { "$relationship($_)" } grep { $_ ne "from-link" && $_ ne "to-link" }
3303                            keys %{$relationshipFields};
3304        # Push these onto the return list.
3305        push @retVal, sort @fieldList2;
3306        # Return the result.
3307        return @retVal;
3308    }
3309    
3310    =head3 FindColumn
3311    
3312    C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>
3313    
3314    Return the location a desired column in a data mining header line. The data
3315    mining header line is a tab-separated list of column names. The column
3316    identifier is either the numerical index of a column or the actual column
3317    name.
3318    
3319    =over 4
3320    
3321    =item headerLine
3322    
3323    The header line from a data mining command, which consists of a tab-separated
3324    list of column names.
3325    
3326    =item columnIdentifier
3327    
3328    Either the ordinal number of the desired column (1-based), or the name of the
3329    desired column.
3330    
3331  =item RETURN  =item RETURN
3332    
3333  Returns a statistical object containing the number of records read and a list of the error messages.  Returns the array index (0-based) of the desired column.
3334    
3335  =back  =back
3336    
3337  =cut  =cut
3338  sub LoadTable {  
3339    sub FindColumn {
3340          # Get the parameters.          # Get the parameters.
3341          my ($self, $fileName, $relationName, $truncateFlag) = @_;      my ($headerLine, $columnIdentifier) = @_;
3342          # Create the statistical return object.      # Declare the return variable.
3343          my $retVal = _GetLoadStats();      my $retVal;
3344          # Trace the fact of the load.      # Split the header line into column names.
3345          Trace("Loading table $relationName from $fileName") if T(1);      my @headers = ParseColumns($headerLine);
3346          # Get the database handle.      # Determine whether we have a number or a name.
3347          my $dbh = $self->{_dbh};      if ($columnIdentifier =~ /^\d+$/) {
3348          # Get the relation data.          # Here we have a number. Subtract 1 and validate the result.
3349          my $relation = $self->_FindRelation($relationName);          $retVal = $columnIdentifier - 1;
3350          # Check the truncation flag.          if ($retVal < 0 || $retVal > $#headers) {
3351          if ($truncateFlag) {              Confess("Invalid column identifer \"$columnIdentifier\": value out of range.");
                 Trace("Creating table $relationName") if T(1);  
                 # Re-create the table without its index.  
                 $self->CreateTable($relationName, 0);  
3352          }          }
         # Determine whether or not this is a primary relation. Primary relations have an extra  
         # field indicating whether or not a given object is new or was loaded from the flat files.  
         my $primary = $self->_IsPrimary($relationName);  
         # Get the number of fields in this relation.  
         my @fieldList = @{$relation->{Fields}};  
         my $fieldCount = @fieldList;  
         # Record the number of expected fields.  
         my $expectedFields = $fieldCount + ($primary ? 1 : 0);  
         # Start a database transaction.  
         $dbh->begin_tran;  
         # Open the relation file. We need to create a cleaned-up copy before loading.  
         open TABLEIN, '<', $fileName;  
         my $tempName = "$fileName.tbl";  
         open TABLEOUT, '>', $tempName;  
         # Loop through the file.  
         while (<TABLEIN>) {  
                 # Chop off the new-line character.  
                 my $record = $_;  
                 chomp $record;  
         # Only proceed if the record is non-blank.  
         if ($record) {  
             # Escape all the backslashes found in the line.  
             $record =~ s/\\/\\\\/g;  
             # Eliminate any trailing tabs.  
             chop $record while substr($record, -1) eq "\t";  
             # If this is a primary relation, add a 0 for the new-record flag (indicating that  
             # this record is not new, but part of the original load).  
             if ($primary) {  
                 $record .= "\t0";  
             }  
             # Write the record.  
             print TABLEOUT "$record\n";  
             # Count the record read.  
             my $count = $retVal->Add('records');  
             my $len = length $record;  
             Trace("Record $count written with $len characters.") if T(4);  
         }  
         }  
         # Close the files.  
         close TABLEIN;  
         close TABLEOUT;  
     Trace("Temporary file $tempName created.") if T(4);  
     # Load the table.  
         my $rv;  
         eval {  
                 $rv = $dbh->load_table(file => $tempName, tbl => $relationName);  
         };  
         if (!defined $rv) {  
         $retVal->AddMessage($@) if ($@);  
         $retVal->AddMessage("Table load failed for $relationName using $tempName.");  
                 Trace("Table load failed for $relationName.") if T(1);  
3353          } else {          } else {
3354                  # Here we successfully loaded the table. Trace the number of records loaded.          # Here we have a name. We need to find it in the list.
3355                  Trace("$retVal->{records} records read for $relationName.") if T(1);          for (my $i = 0; $i <= $#headers && ! defined($retVal); $i++) {
3356                  # If we're rebuilding, we need to create the table indexes.              if ($headers[$i] eq $columnIdentifier) {
3357                  if ($truncateFlag) {                  $retVal = $i;
                         eval {  
                                 $self->CreateIndex($relationName);  
                         };  
                         if ($@) {  
                                 $retVal->AddMessage($@);  
3358                          }                          }
3359                  }                  }
3360            if (! defined($retVal)) {
3361                Confess("Invalid column identifier \"$columnIdentifier\": value not found.");
3362          }          }
3363          # Commit the database changes.      }
3364          $dbh->commit_tran;      # Return the result.
         # Delete the temporary file.  
         unlink $tempName;  
         # Return the statistics.  
3365          return $retVal;          return $retVal;
3366  }  }
3367    
3368  =head3 GenerateEntity  =head3 ParseColumns
3369    
3370  C<< my $fieldHash = $database->GenerateEntity($id, $type, \%values); >>  C<< my @columns = ERDB::ParseColumns($line); >>
3371    
3372  Generate the data for a new entity instance. This method creates a field hash suitable for  Convert the specified data line to a list of columns.
 passing as a parameter to L</InsertObject>. The ID is specified by the callr, but the rest  
 of the fields are generated using information in the database schema.  
   
 Each data type has a default algorithm for generating random test data. This can be overridden  
 by including a B<DataGen> element in the field. If this happens, the content of the element is  
 executed as a PERL program in the context of this module. The element may make use of a C<$this>  
 variable which contains the field hash as it has been built up to the current point. If any  
 fields are dependent on other fields, the C<pass> attribute can be used to control the order  
 in which the fields are generated. A field with a high data pass number will be generated after  
 a field with a lower one. If any external values are needed, they should be passed in via the  
 optional third parameter, which will be available to the data generation script under the name  
 C<$value>. Several useful utility methods are provided for generating random values, including  
 L</IntGen>, L</StringGen>, L</FloatGen>, and L</DateGen>. Note that dates are stored and generated  
 in the form of a timestamp number rather than a string.  
3373    
3374  =over 4  =over 4
3375    
3376  =item id  =item line
   
 ID to assign to the new entity.  
3377    
3378  =item type  A data mining input, consisting of a tab-separated list of columns terminated by a
3379    new-line.
 Type name for the new entity.  
3380    
3381  =item values  =item RETURN
3382    
3383  Hash containing additional values that might be needed by the data generation methods (optional).  Returns a list consisting of the column values.
3384    
3385  =back  =back
3386    
3387  =cut  =cut
3388    
3389  sub GenerateEntity {  sub ParseColumns {
3390          # Get the parameters.          # Get the parameters.
3391          my ($self, $id, $type, $values) = @_;      my ($line) = @_;
3392          # Create the return hash.      # Chop off the line-end.
3393          my $this = { id => $id };      chomp $line;
3394          # Get the metadata structure.      # Split it into a list.
3395          my $metadata = $self->{_metaData};      my @retVal = split(/\t/, $line);
3396          # Get this entity's list of fields.      # Return the result.
3397          if (!exists $metadata->{Entities}->{$type}) {      return @retVal;
                 Confess("Unrecognized entity type $type in GenerateEntity.");  
         } else {  
                 my $entity = $metadata->{Entities}->{$type};  
                 my $fields = $entity->{Fields};  
                 # Generate data from the fields.  
                 _GenerateFields($this, $fields, $type, $values);  
         }  
         # Return the hash created.  
         return $this;  
3398  }  }
3399    
3400  =head3 GetEntity  =head2 Virtual Methods
   
 C<< my $entityObject = $sprout->GetEntity($entityType, $ID); >>  
3401    
3402  Return an object describing the entity instance with a specified ID.  =head3 CleanKeywords
3403    
3404  =over 4  C<< my $cleanedString = $erdb->CleanKeywords($searchExpression); >>
3405    
3406  =item entityType  Clean up a search expression or keyword list. This is a virtual method that may
3407    be overridden by the subclass. The base-class method removes extra spaces
3408    and converts everything to lower case.
3409    
3410  Entity type name.  =over 4
3411    
3412  =item ID  =item searchExpression
3413    
3414  ID of the desired entity.  Search expression or keyword list to clean. Note that a search expression may
3415    contain boolean operators which need to be preserved. This includes leading
3416    minus signs.
3417    
3418  =item RETURN  =item RETURN
3419    
3420  Returns a B<DBObject> representing the desired entity instance, or an undefined value if no  Cleaned expression or keyword list.
 instance is found with the specified key.  
3421    
3422  =back  =back
3423    
3424  =cut  =cut
3425    
3426  sub GetEntity {  sub CleanKeywords {
3427          # Get the parameters.          # Get the parameters.
3428          my ($self, $entityType, $ID) = @_;      my ($self, $searchExpression) = @_;
3429          # Create a query.      # Lower-case the expression and copy it into the return variable. Note that we insure we
3430          my $query = $self->Get([$entityType], "$entityType(id) = ?", $ID);      # don't accidentally end up with an undefined value.
3431          # Get the first (and only) object.      my $retVal = lc($searchExpression || "");
3432          my $retVal = $query->Fetch();      # Remove extra spaces.
3433        $retVal =~ s/\s+/ /g;
3434        $retVal =~ s/(^\s+)|(\s+$)//g;
3435          # Return the result.          # Return the result.
3436          return $retVal;          return $retVal;
3437  }  }
3438    
3439  =head3 GetEntityValues  =head3 GetSourceObject
3440    
3441  C<< my @values = GetEntityValues($entityType, $ID, \@fields); >>  C<< my $source = $erdb->GetSourceObject($entityName); >>
3442    
3443  Return a list of values from a specified entity instance.  Return the object to be used in loading special attributes of the specified entity. The
3444    algorithm for loading special attributes is stored in the C<DataGen> elements of the
3445    XML
3446    
3447  =over 4  =head2 Internal Utility Methods
3448    
3449  =item entityType  =head3 _RelationMap
3450    
3451  Entity type name.  C<< my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef); >>
3452    
3453  =item ID  Create the relation map for an SQL query. The relation map is used by B<DBObject>
3454    to determine how to interpret the results of the query.
3455    
3456  ID of the desired entity.  =over 4
3457    
3458  =item fields  =item mappedNameHashRef
3459    
3460  List of field names, each of the form I<objectName>C<(>I<fieldName>C<)>.  Reference to a hash that maps modified object names to real object names.
3461    
3462    =item mappedNameListRef
3463    
3464    Reference to a list of modified object names in the order they appear in the
3465    SELECT list.
3466    
3467  =item RETURN  =item RETURN
3468    
3469  Returns a flattened list of the values of the specified fields for the specified entity.  Returns a list of 2-tuples. Each tuple consists of an object name as used in the
3470    query followed by the actual name of that object. This enables the B<DBObject> to
3471    determine the order of the tables in the query and which object name belongs to each
3472    mapped object name. Most of the time these two values are the same; however, if a
3473    relation occurs twice in the query, the relation name in the field list and WHERE
3474    clause will use a mapped name (generally the actual relation name with a numeric
3475    suffix) that does not match the actual relation name.
3476    
3477  =back  =back
3478    
3479  =cut  =cut
3480    
3481  sub GetEntityValues {  sub _RelationMap {
3482          # Get the parameters.          # Get the parameters.
3483          my ($self, $entityType, $ID, $fields) = @_;      my ($mappedNameHashRef, $mappedNameListRef) = @_;
3484          # Get the specified entity.      # Declare the return variable.
         my $entity = $self->GetEntity($entityType, $ID);  
         # Declare the return list.  
3485          my @retVal = ();          my @retVal = ();
3486          # If we found the entity, push the values into the return list.      # Build the map.
3487          if ($entity) {      for my $mappedName (@{$mappedNameListRef}) {
3488                  push @retVal, $entity->Values($fields);          push @retVal, [$mappedName, $mappedNameHashRef->{$mappedName}];
3489          }          }
3490          # Return the result.      # Return it.
3491          return @retVal;          return @retVal;
3492  }  }
3493    
 =head2 Internal Utility Methods  
3494    
3495  =head3 GetLoadStats  =head3 _SetupSQL
3496    
3497  Return a blank statistics object for use by the load methods.  Process a list of object names and a filter clause so that they can be used to
3498    build an SQL statement. This method takes in a reference to a list of object names
3499    and a filter clause. It will return a corrected filter clause, a list of mapped
3500    names and the mapped name hash.
3501    
3502  This is a static method.  This is an instance method.
3503    
3504  =cut  =over 4
3505    
3506  sub _GetLoadStats {  =item objectNames
         return Stats->new('records');  
 }  
3507    
3508  =head3 GenerateFields  Reference to a list of the object names to be included in the query.
3509    
3510  Generate field values from a field structure and store in a specified table. The field names  =item filterClause
 are first sorted by pass count, certain pre-defined fields are removed from the list, and  
 then we rip through them evaluation the data generation string. Fields in the primary relation  
 are stored as scalars; fields in secondary relations are stored as value lists.  
3511    
3512  This is a static method.  A string containing the WHERE clause for the query (without the C<WHERE>) and also
3513    optionally the C<ORDER BY> and C<LIMIT> clauses.
3514    
3515  =over 4  =item matchClause
3516    
3517  =item this  An optional full-text search clause. If specified, it will be inserted at the
3518    front of the WHERE clause. It should already be SQL-formatted; that is, the
3519    field names should be in the form I<table>C<.>I<fieldName>.
3520    
3521  Hash table into which the field values should be placed.  =item RETURN
3522    
3523  =item fields  Returns a three-element list. The first element is the SQL statement suffix, beginning
3524    with the FROM clause. The second element is a reference to a list of the names to be
3525    used in retrieving the fields. The third element is a hash mapping the names to the
3526    objects they represent.
3527    
3528  Field structure from which the field descriptors should be taken.  =back
3529    
3530  =item type  =cut
3531    
3532    sub _SetupSQL {
3533        my ($self, $objectNames, $filterClause, $matchClause) = @_;
3534        # Adjust the list of object names to account for multiple occurrences of the
3535        # same object. We start with a hash table keyed on object name that will
3536        # return the object suffix. The first time an object is encountered it will
3537        # not be found in the hash. The next time the hash will map the object name
3538        # to 2, then 3, and so forth.
3539        my %objectHash = ();
3540        # This list will contain the object names as they are to appear in the
3541        # FROM list.
3542        my @fromList = ();
3543        # This list contains the suffixed object name for each object. It is exactly
3544        # parallel to the list in the $objectNames parameter.
3545        my @mappedNameList = ();
3546        # Finally, this hash translates from a mapped name to its original object name.
3547        my %mappedNameHash = ();
3548        # Now we create the lists. Note that for every single name we push something into
3549        # @fromList and @mappedNameList. This insures that those two arrays are exactly
3550        # parallel to $objectNames.
3551        for my $objectName (@{$objectNames}) {
3552            # Get the next suffix for this object.
3553            my $suffix = $objectHash{$objectName};
3554            if (! $suffix) {
3555                # Here we are seeing the object for the first time. The object name
3556                # is used as is.
3557                push @mappedNameList, $objectName;
3558                push @fromList, $objectName;
3559                $mappedNameHash{$objectName} = $objectName;
3560                # Denote the next suffix will be 2.
3561                $objectHash{$objectName} = 2;
3562            } else {
3563                # Here we've seen the object before. We construct a new name using
3564                # the suffix from the hash and update the hash.
3565                my $mappedName = "$objectName$suffix";
3566                $objectHash{$objectName} = $suffix + 1;
3567                # The FROM list has the object name followed by the mapped name. This
3568                # tells SQL it's still the same table, but we're using a different name
3569                # for it to avoid confusion.
3570                push @fromList, "$objectName $mappedName";
3571                # The mapped-name list contains the real mapped name.
3572                push @mappedNameList, $mappedName;
3573                # Finally, enable us to get back from the mapped name to the object name.
3574                $mappedNameHash{$mappedName} = $objectName;
3575            }
3576        }
3577        # Begin the SELECT suffix. It starts with
3578        #
3579        # FROM name1, name2, ... nameN
3580        #
3581        my $suffix = "FROM " . join(', ', @fromList);
3582        # Now for the WHERE. First, we need a place for the filter string.
3583        my $filterString = "";
3584        # We will also keep a list of conditions to add to the WHERE clause in order to link
3585        # entities and relationships as well as primary relations to secondary ones.
3586        my @joinWhere = ();
3587        # Check for a filter clause.
3588        if ($filterClause) {
3589            # Here we have one, so we convert its field names and add it to the query. First,
3590            # We create a copy of the filter string we can work with.
3591            $filterString = $filterClause;
3592            # Next, we sort the object names by length. This helps protect us from finding
3593            # object names inside other object names when we're doing our search and replace.
3594            my @sortedNames = sort { length($b) - length($a) } @mappedNameList;
3595            # The final preparatory step is to create a hash table of relation names. The
3596            # table begins with the relation names already in the SELECT command. We may
3597            # need to add relations later if there is filtering on a field in a secondary
3598            # relation. The secondary relations are the ones that contain multiply-
3599            # occurring or optional fields.
3600            my %fromNames = map { $_ => 1 } @sortedNames;
3601            # We are ready to begin. We loop through the object names, replacing each
3602            # object name's field references by the corresponding SQL field reference.
3603            # Along the way, if we find a secondary relation, we will need to add it
3604            # to the FROM clause.
3605            for my $mappedName (@sortedNames) {
3606                # Get the length of the object name plus 2. This is the value we add to the
3607                # size of the field name to determine the size of the field reference as a
3608                # whole.
3609                my $nameLength = 2 + length $mappedName;
3610                # Get the real object name for this mapped name.
3611                my $objectName = $mappedNameHash{$mappedName};
3612                Trace("Processing $mappedName for object $objectName.") if T(4);
3613                # Get the object's field list.
3614                my $fieldList = $self->GetFieldTable($objectName);
3615                # Find the field references for this object.
3616                while ($filterString =~ m/$mappedName\(([^)]*)\)/g) {
3617                    # At this point, $1 contains the field name, and the current position
3618                    # is set immediately after the final parenthesis. We pull out the name of
3619                    # the field and the position and length of the field reference as a whole.
3620                    my $fieldName = $1;
3621                    my $len = $nameLength + length $fieldName;
3622                    my $pos = pos($filterString) - $len;
3623                    # Insure the field exists.
3624                    if (!exists $fieldList->{$fieldName}) {
3625                        Confess("Field $fieldName not found for object $objectName.");
3626                    } else {
3627                        Trace("Processing $fieldName at position $pos.") if T(4);
3628                        # Get the field's relation.
3629                        my $relationName = $fieldList->{$fieldName}->{relation};
3630                        # Now we have a secondary relation. We need to insure it matches the
3631                        # mapped name of the primary relation. First we peel off the suffix
3632                        # from the mapped name.
3633                        my $mappingSuffix = substr $mappedName, length($objectName);
3634                        # Put the mapping suffix onto the relation name to get the
3635                        # mapped relation name.
3636                        my $mappedRelationName = "$relationName$mappingSuffix";
3637                        # Insure the relation is in the FROM clause.
3638