[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 1.97, Wed May 7 23:08:19 2008 UTC
# Line 2  Line 2 
2    
3          use strict;          use strict;
4          use Tracer;          use Tracer;
5          use DBKernel;      use DBrtns;
6          use Data::Dumper;          use Data::Dumper;
7          use XML::Simple;          use XML::Simple;
8          use DBQuery;          use DBQuery;
9          use DBObject;      use ERDBObject;
10          use Stats;          use Stats;
11          use Time::HiRes qw(gettimeofday);          use Time::HiRes qw(gettimeofday);
12        use Digest::MD5 qw(md5_base64);
13        use CGI;
14        use WikiTools;
15    
16  =head1 Entity-Relationship Database Package  =head1 Entity-Relationship Database Package
17    
# Line 32  Line 35 
35  relation that contains two fields-- the feature ID (C<id>) and the alias name (C<alias>).  relation that contains two fields-- the feature ID (C<id>) and the alias name (C<alias>).
36  The B<FEATURE> entity also contains an optional virulence number. This is implemented  The B<FEATURE> entity also contains an optional virulence number. This is implemented
37  as a separate relation C<FeatureVirulence> which contains an ID (C<id>) and a virulence number  as a separate relation C<FeatureVirulence> which contains an ID (C<id>) and a virulence number
38  (C<virulence>). If the virulence of a feature I<ABC> is known to be 6, there will be one row in the  (C<virulence>). If the virulence of a feature I<ABC> is known to be 6, there will be one row in
39  C<FeatureVirulence> relation possessing the value I<ABC> as its ID and 6 as its virulence number.  the C<FeatureVirulence> relation possessing the value I<ABC> as its ID and 6 as its virulence
40  If the virulence of I<ABC> is not known, there will not be any rows for it in C<FeatureVirulence>.  number. If the virulence of I<ABC> is not known, there will not be any rows for it in
41    C<FeatureVirulence>.
42    
43  Entities are connected by binary relationships implemented using single relations possessing the  Entities are connected by binary relationships implemented using single relations possessing the
44  same name as the relationship itself and that has an I<arity> of 1-to-1 (C<11>), 1-to-many (C<1M>),  same name as the relationship itself and that has an I<arity> of 1-to-1 (C<11>), 1-to-many (C<1M>),
# Line 56  Line 60 
60  B<start-position>, which indicates where in the contig that the sequence begins. This attribute  B<start-position>, which indicates where in the contig that the sequence begins. This attribute
61  is implemented as the C<start_position> field in the C<IsMadeUpOf> relation.  is implemented as the C<start_position> field in the C<IsMadeUpOf> relation.
62    
63  The database itself is described by an XML file using the F<ERDatabase.xsd> schema. In addition to  The database itself is described by an XML file. In addition to all the data required to define
64  all the data required to define the entities, relationships, and attributes, the schema provides  the entities, relationships, and attributes, the schema provides space for notes describing
65  space for notes describing the data and what it means. These notes are used by L</ShowMetaData>  the data and what it means. These notes are used by L</ShowMetaData> to generate documentation
66  to generate documentation for the database.  for the database.
67    
68    Special support is provided for text searching. An entity field can be marked as <em>searchable</em>,
69    in which case it will be used to generate a text search index in which the user searches for words
70    in the field instead of a particular field value.
71    
72  Finally, every entity and relationship object has a flag indicating if it is new or old. The object  Finally, every entity and relationship object has a flag indicating if it is new or old. The object
73  is considered I<old> if it was loaded by the L</LoadTables> method. It is considered I<new> if it  is considered I<old> if it was loaded by the L</LoadTables> method. It is considered I<new> if it
74  was inserted by the L</InsertObject> method.  was inserted by the L</InsertObject> method.
75    
76  To facilitate testing, the ERDB module supports automatic generation of test data. This process  =head2 XML Database Description
77  is described in the L</GenerateEntity> and L</GenerateConnection> methods, though it is not yet  
78  fully implemented.  =head3 Data Types
79    
80    The ERDB system supports the following data types. Note that there are numerous string
81    types depending on the maximum length. Some database packages limit the total number of
82    characters you have in an index key; to insure the database works in all environments,
83    the type of string should be the shortest one possible that supports all the known values.
84    
85    =over 4
86    
87    =item char
88    
89    single ASCII character
90    
91    =item int
92    
93    32-bit signed integer
94    
95    =item counter
96    
97    32-bit unsigned integer
98    
99    =item date
100    
101    64-bit unsigned integer, representing a PERL date/time value
102    
103    =item text
104    
105    long string; Text fields cannot be used in indexes or sorting and do not support the
106    normal syntax of filter clauses, but can be up to a billion character in length
107    
108    =item float
109    
110    double-precision floating-point number
111    
112    =item boolean
113    
114    single-bit numeric value; The value is stored as a 16-bit signed integer (for
115    compatability with certain database packages), but the only values supported are
116    0 and 1.
117    
118    =item id-string
119    
120    variable-length string, maximum 25 characters
121    
122    =item key-string
123    
124    variable-length string, maximum 40 characters
125    
126    =item name-string
127    
128    variable-length string, maximum 80 characters
129    
130    =item medium-string
131    
132    variable-length string, maximum 160 characters
133    
134    =item string
135    
136    variable-length string, maximum 255 characters
137    
138    =item hash-string
139    
140    variable-length string, maximum 22 characters
141    
142    =back
143    
144    The hash-string data type has a special meaning. The actual key passed into the loader will
145    be a string, but it will be digested into a 22-character MD5 code to save space. Although the
146    MD5 algorithm is not perfect, it is extremely unlikely two strings will have the same
147    digest. Therefore, it is presumed the keys will be unique. When the database is actually
148    in use, the hashed keys will be presented rather than the original values. For this reason,
149    they should not be used for entities where the key is meaningful.
150    
151    =head3 Global Tags
152    
153    The entire database definition must be inside a B<Database> tag. The display name of
154    the database is given by the text associated with the B<Title> tag. The display name
155    is only used in the automated documentation. It has no other effect. The entities and
156    relationships are listed inside the B<Entities> and B<Relationships> tags,
157    respectively. None of these tags have attributes.
158    
159        <Database>
160            <Title>... display title here...</Title>
161            <Entities>
162                ... entity definitions here ...
163            </Entities>
164            <Relationships>
165                ... relationship definitions here...
166            </Relationships>
167        </Database>
168    
169    Entities, relationships, indexes, and fields all allow a text tag called B<Notes>.
170    The text inside the B<Notes> tag contains comments that will appear when the database
171    documentation is generated. Within a B<Notes> tag, you may use C<[i]> and C<[/i]> for
172    italics, C<[b]> and C<[/b]> for bold, and C<[p]> for a new paragraph.
173    
174    =head3 Fields
175    
176    Both entities and relationships have fields described by B<Field> tags. A B<Field>
177    tag can have B<Notes> associated with it. The complete set of B<Field> tags for an
178    object mus be inside B<Fields> tags.
179    
180        <Entity ... >
181            <Fields>
182                ... Field tags ...
183            </Fields>
184        </Entity>
185    
186    The attributes for the B<Field> tag are as follows.
187    
188    =over 4
189    
190    =item name
191    
192    Name of the field. The field name should contain only letters, digits, and hyphens (C<->),
193    and the first character should be a letter. Most underlying databases are case-insensitive
194    with the respect to field names, so a best practice is to use lower-case letters only. Finally,
195    the name C<search-relevance> has special meaning for full-text searches and should not be
196    used as a field name.
197    
198    =item type
199    
200    Data type of the field. The legal data types are given above.
201    
202    =item relation
203    
204    Name of the relation containing the field. This should only be specified for entity
205    fields. The ERDB system does not support optional fields or multi-occurring fields
206    in the primary relation of an entity. Instead, they are put into secondary relations.
207    So, for example, in the C<Genome> entity, the C<group-name> field indicates a special
208    grouping used to select a subset of the genomes. A given genome may not be in any
209    groups or may be in multiple groups. Therefore, C<group-name> specifies a relation
210    value. The relation name specified must be a valid table name. By convention, it is
211    usually the entity name followed by a qualifying word (e.g. C<GenomeGroup>). In an
212    entity, the fields without a relation attribute are said to belong to the
213    I<primary relation>. This relation has the same name as the entity itself.
214    
215    =item searchable
216    
217    If specified, then the field is a candidate for full-text searching. A single full-text
218    index will be created for each relation with at least one searchable field in it.
219    For best results, this option should only be used for string or text fields.
220    
221    =item special
222    
223    This attribute allows the subclass to assign special meaning for certain fields.
224    The interpretation is up to the subclass itself. Currently, only entity fields
225    can have this attribute.
226    
227    =back
228    
229    =head3 Indexes
230    
231    An entity can have multiple alternate indexes associated with it. The fields in an
232    index must all be from the same relation. The alternate indexes assist in searching
233    on fields other than the entity ID. A relationship has at least two indexes-- a I<to-index> and a
234    I<from-index> that order the results when crossing the relationship. For
235    example, in the relationship C<HasContig> from C<Genome> to C<Contig>, the
236    from-index would order the contigs of a ganome, and the to-index would order
237    the genomes of a contig. In addition, it can have zero or more alternate
238    indexes. A relationship's index must specify only fields in
239    the relationship.
240    
241    The alternate indexes for an entity or relationship must be listed inside the B<Indexes> tag.
242    The from-index of a relationship is specified using the B<FromIndex> tag; the to-index is
243    specified using the B<ToIndex> tag.
244    
245    Each index can contain a B<Notes> tag. In addition, it will have an B<IndexFields>
246    tag containing the B<IndexField> tags. These specify, in order, the fields used in
247    the index. The attributes of an B<IndexField> tag are as follows.
248    
249    =over 4
250    
251    =item name
252    
253    Name of the field.
254    
255    =item order
256    
257    Sort order of the field-- C<ascending> or C<descending>.
258    
259    =back
260    
261    The B<FromIndex>, and B<ToIndex> tags have no attributes. The B<Index> tag can
262    have a B<Unique> attribute. If specified, the index will be generated as a unique
263    index.
264    
265    =head3 Object and Field Names
266    
267    By convention entity and relationship names use capital casing (e.g. C<Genome> or
268    C<HasRegionsIn>. Most underlying databases, however, are aggressively case-insensitive
269    with respect to relation names, converting them internally to all-upper case or
270    all-lower case.
271    
272    If syntax or parsing errors occur when you try to load or use an ERDB database, the
273    most likely reason is that one of your objects has an SQL reserved word as its name.
274    The list of SQL reserved words keeps increasing; however, most are unlikely to show
275    up as a noun or declarative verb phrase. The exceptions are C<Group>, C<User>,
276    C<Table>, C<Index>, C<Object>, C<Date>, C<Number>, C<Update>, C<Time>, C<Percent>,
277    C<Memo>, C<Order>, and C<Sum>. This problem can crop up in field names as well.
278    
279    Every entity has a field called C<id> that acts as its primary key. Every relationship
280    has fields called C<from-link> and C<to-link> that contain copies of the relevant
281    entity IDs. These are essentially ERDB's reserved words, and should not be used
282    for user-defined field names.
283    
284    =head3 Entities
285    
286    An entity is described by the B<Entity> tag. The entity can contain B<Notes>, an
287    B<Indexes> tag containing one or more secondary indexes, and a B<Fields> tag
288    containing one or more fields. The attributes of the B<Entity> tag are as follows.
289    
290    =over 4
291    
292    =item name
293    
294    Name of the entity. The entity name, by convention, uses capital casing (e.g. C<Genome>
295    or C<GroupBlock>) and should be a noun or noun phrase.
296    
297    =item keyType
298    
299    Data type of the primary key. The primary key is always named C<id>.
300    
301    =back
302    
303    =head3 Relationships
304    
305    A relationship is described by the C<Relationship> tag. Within a relationship,
306    there can be a C<Notes> tag, a C<Fields> tag containing the intersection data
307    fields, a C<FromIndex> tag containing the from-index, a C<ToIndex> tag containing
308    the to-index, and an C<Indexes> tag containing the alternate indexes.
309    
310    The C<Relationship> tag has the following attributes.
311    
312    =over 4
313    
314    =item name
315    
316    Name of the relationship. The relationship name, by convention, uses capital casing
317    (e.g. C<ContainsRegionIn> or C<HasContig>), and should be a declarative verb
318    phrase, designed to fit between the from-entity and the to-entity (e.g.
319    Block C<ContainsRegionIn> Genome).
320    
321    =item from
322    
323    Name of the entity from which the relationship starts.
324    
325    =item to
326    
327    Name of the entity to which the relationship proceeds.
328    
329    =item arity
330    
331    Relationship type: C<1M> for one-to-many and C<MM> for many-to-many.
332    
333    =back
334    
335  =cut  =cut
336    
# Line 75  Line 338 
338    
339  # Table of information about our datatypes. "sqlType" is the corresponding SQL datatype string.  # Table of information about our datatypes. "sqlType" is the corresponding SQL datatype string.
340  # "maxLen" is the maximum permissible length of the incoming string data used to populate a field  # "maxLen" is the maximum permissible length of the incoming string data used to populate a field
341  # of the specified type. "dataGen" is PERL string that will be evaluated if no test data generation  # of the specified type. "avgLen" is the average byte length for estimating
342   #string is specified in the field definition.  # record sizes. "sort" is the key modifier for the sort command, "notes" is a type description,
343  my %TypeTable = ( char =>        { sqlType => 'CHAR(1)',                        maxLen => 1,                    dataGen => "StringGen('A')" },  # and "indexMod", if non-zero, is the number of characters to use when the field is specified in an
344                                    int =>         { sqlType => 'INTEGER',                        maxLen => 20,                   dataGen => "IntGen(0, 99999999)" },  # index
345                                    string =>  { sqlType => 'VARCHAR(255)',               maxLen => 255,                  dataGen => "StringGen(IntGen(10,250))" },  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",
346                                    text =>        { sqlType => 'TEXT',                           maxLen => 1000000000,   dataGen => "StringGen(IntGen(80,1000))" },                                 indexMod =>   0, notes => "single ASCII character"},
347                                    date =>        { sqlType => 'BIGINT',                         maxLen => 80,                   dataGen => "DateGen(-7, 7, IntGen(0,1400))" },                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n",
348                                    float =>       { sqlType => 'DOUBLE PRECISION',       maxLen => 40,                   dataGen => "FloatGen(0.0, 100.0)" },                                 indexMod =>   0, notes => "signed 32-bit integer"},
349                                    boolean => { sqlType => 'SMALLINT',                   maxLen => 1,                    dataGen => "IntGen(0, 1)" },                    counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n",
350                                   indexMod =>   0, notes => "unsigned 32-bit integer"},
351                      string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, sort => "",
352                                   indexMod =>   0, notes => "character string, 0 to 255 characters"},
353                      text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, sort => "",
354                                   indexMod => 255, notes => "character string, nearly unlimited length, only first 255 characters are indexed"},
355                      date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, sort => "n",
356                                   indexMod =>   0, notes => "signed, 64-bit integer"},
357                      float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, sort => "g",
358                                   indexMod =>   0, notes => "64-bit double precision floating-point number"},
359                      boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, sort => "n",
360                                   indexMod =>   0, notes => "boolean value: 0 if false, 1 if true"},
361                     'hash-string' =>
362                                 { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, sort => "",
363                                   indexMod =>   0, notes => "string stored in digested form, used for certain types of key fields"},
364                     'id-string' =>
365                                 { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, sort => "",
366                                   indexMod =>   0, notes => "character string, 0 to 25 characters"},
367                               'key-string' =>                               'key-string' =>
368                                                           { sqlType => 'VARCHAR(40)',            maxLen => 40,                   dataGen => "StringGen(IntGen(10,40))" },                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, sort => "",
369                                   indexMod =>   0, notes => "character string, 0 to 40 characters"},
370                                   'name-string' =>                                   'name-string' =>
371                                                           { sqlType => 'VARCHAR(80)',            maxLen => 80,                   dataGen => "StringGen(IntGen(10,80))" },                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, sort => "",
372                                   indexMod =>   0, notes => "character string, 0 to 80 characters"},
373                                   'medium-string' =>                                   'medium-string' =>
374                                                           { sqlType => 'VARCHAR(160)',           maxLen => 160,                  dataGen => "StringGen(IntGen(10,160))" },                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",
375                                   indexMod =>   0, notes => "character string, 0 to 160 characters"},
376                     'long-string' =>
377                                 { sqlType => 'VARCHAR(500)',       maxLen => 500,          avglen => 255, sort => "",
378                                   indexMod =>   0, notes => "character string, 0 to 500 characters"},
379                                  );                                  );
380    
381  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 98  Line 384 
384                                     'MM' => 'many-to-many'                                     'MM' => 'many-to-many'
385                                   );                                   );
386    
387  # Table for interpreting string patterns.  # Options for XML input and output.
388    
389    my %XmlOptions = (GroupTags =>  { Relationships => 'Relationship',
390                                      Entities => 'Entity',
391                                      Fields => 'Field',
392                                      Indexes => 'Index',
393                                      IndexFields => 'IndexField'
394                                    },
395                      KeyAttr =>    { Relationship => 'name',
396                                      Entity => 'name',
397                                      Field => 'name'
398                                    },
399                      SuppressEmpty => 1,
400                     );
401    
402  my %PictureTable = ( 'A' => "abcdefghijklmnopqrstuvwxyz",  my %XmlInOpts  = (
403                                           '9' => "0123456789",                    ForceArray => ['Field', 'Index', 'IndexField', 'Relationship', 'Entity'],
404                                           'X' => "abcdefghijklmnopqrstuvwxyz0123456789",                    ForceContent => 1,
405                                           'V' => "aeiou",                    NormalizeSpace => 2,
406                                           'K' => "bcdfghjklmnoprstvwxyz"                   );
407    my %XmlOutOpts = (
408                      RootName => 'Database',
409                      XMLDecl => 1,
410                                     );                                     );
411    
412  =head2 Public Methods  =head2 Public Methods
413    
414  =head3 new  =head3 new
415    
416  C<< my $database = ERDB->new($dbh, $metaFileName); >>      my $database = ERDB->new($dbh, $metaFileName);
417    
418  Create a new ERDB object.  Create a new ERDB object.
419    
# Line 131  Line 433 
433    
434  sub new {  sub new {
435          # Get the parameters.          # Get the parameters.
436          my ($class, $dbh, $metaFileName, $options) = @_;      my ($class, $dbh, $metaFileName, %options) = @_;
437          # Load the meta-data.          # Load the meta-data.
438          my $metaData = _LoadMetaData($metaFileName);          my $metaData = _LoadMetaData($metaFileName);
439          # Create the object.          # Create the object.
# Line 145  Line 447 
447    
448  =head3 ShowMetaData  =head3 ShowMetaData
449    
450  C<< $database->ShowMetaData($fileName); >>      $erdb->ShowMetaData($fileName);
451    
452  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
453  the data to be loaded into the relations.  the data to be loaded into the relations.
# Line 176  Line 478 
478          # Write the HTML heading stuff.          # Write the HTML heading stuff.
479          print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";          print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";
480          print HTMLOUT "</head>\n<body>\n";          print HTMLOUT "</head>\n<body>\n";
481        # Write the documentation.
482        print HTMLOUT $self->DisplayMetaData();
483        # Close the document.
484        print HTMLOUT "</body>\n</html>\n";
485        # Close the file.
486        close HTMLOUT;
487    }
488    
489    =head3 DisplayMetaData
490    
491        my $html = $erdb->DisplayMetaData();
492    
493    Return an HTML description of the database. This description can be used to help users create
494    the data to be loaded into the relations and form queries. The output is raw includable HTML
495    without any HEAD or BODY tags.
496    
497    =over 4
498    
499    =item filename
500    
501    The name of the output file.
502    
503    =back
504    
505    =cut
506    
507    sub DisplayMetaData {
508        # Get the parameters.
509        my ($self) = @_;
510        # Get the metadata and the title string.
511        my $metadata = $self->{_metaData};
512        # Get the title string.
513        my $title = $metadata->{Title};
514        # Get the entity and relationship lists.
515        my $entityList = $metadata->{Entities};
516        my $relationshipList = $metadata->{Relationships};
517        # Declare the return variable.
518        my $retVal = "";
519        # Open the output file.
520        Trace("Building MetaData table of contents.") if T(4);
521          # 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
522          # section contains an ordered list of entity or relationship subsections.          # section contains an ordered list of entity or relationship subsections.
523          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";
524          # Loop through the Entities, displaying a list item for each.          # Loop through the Entities, displaying a list item for each.
525          foreach my $key (sort keys %{$entityList}) {          foreach my $key (sort keys %{$entityList}) {
526                  # Display this item.                  # Display this item.
527                  print HTMLOUT "<li><a href=\"#$key\">$key</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$key</a></li>\n";
528          }          }
529          # Close off the entity section and start the relationship section.          # Close off the entity section and start the relationship section.
530          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";
531          # Loop through the Relationships.          # Loop through the Relationships.
532          foreach my $key (sort keys %{$relationshipList}) {          foreach my $key (sort keys %{$relationshipList}) {
533                  # Display this item.                  # Display this item.
534                  my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});                  my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});
535                  print HTMLOUT "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";
536          }          }
537          # Close off the relationship section and list the join table section.          # Close off the relationship section and list the join table section.
538          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";
539          # Close off the table of contents itself.          # Close off the table of contents itself.
540          print HTMLOUT "</ul>\n";      $retVal .=  "</ul>\n";
541          # 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.
542          print HTMLOUT "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";      $retVal .= "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";
543          # Loop through the entities.          # Loop through the entities.
544          for my $key (sort keys %{$entityList}) {          for my $key (sort keys %{$entityList}) {
545                  Trace("Building MetaData entry for $key entity.") if T(4);                  Trace("Building MetaData entry for $key entity.") if T(4);
546                  # Create the entity header. It contains a bookmark and the entity name.                  # Create the entity header. It contains a bookmark and the entity name.
547                  print HTMLOUT "<a name=\"$key\"></a><h3>$key</h3>\n";          $retVal .= "<a name=\"$key\"></a><h3>$key</h3>\n";
548                  # Get the entity data.                  # Get the entity data.
549                  my $entityData = $entityList->{$key};                  my $entityData = $entityList->{$key};
550                  # If there's descriptive text, display it.                  # If there's descriptive text, display it.
551                  if (my $notes = $entityData->{Notes}) {                  if (my $notes = $entityData->{Notes}) {
552                          print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
553                  }                  }
554                  # Now we want a list of the entity's relationships. First, we set up the relationship subsection.          # See if we need a list of the entity's relationships.
555                  print HTMLOUT "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          my $relCount = keys %{$relationshipList};
556            if ($relCount > 0) {
557                # First, we set up the relationship subsection.
558                $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
559                  # Loop through the relationships.                  # Loop through the relationships.
560                  for my $relationship (sort keys %{$relationshipList}) {                  for my $relationship (sort keys %{$relationshipList}) {
561                          # Get the relationship data.                          # Get the relationship data.
# Line 220  Line 565 
565                                  # Get the relationship sentence and append the arity.                                  # Get the relationship sentence and append the arity.
566                                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);                                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);
567                                  # Display the relationship data.                                  # Display the relationship data.
568                                  print HTMLOUT "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";                      $retVal .= "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";
569                          }                          }
570                  }                  }
571                  # Close off the relationship list.                  # Close off the relationship list.
572                  print HTMLOUT "</ul>\n";              $retVal .= "</ul>\n";
573            }
574                  # Get the entity's relations.                  # Get the entity's relations.
575                  my $relationList = $entityData->{Relations};                  my $relationList = $entityData->{Relations};
576                  # Create a header for the relation subsection.                  # Create a header for the relation subsection.
577                  print HTMLOUT "<h4>Relations for <b>$key</b></h4>\n";          $retVal .= "<h4>Relations for <b>$key</b></h4>\n";
578                  # Loop through the relations, displaying them.                  # Loop through the relations, displaying them.
579                  for my $relation (sort keys %{$relationList}) {                  for my $relation (sort keys %{$relationList}) {
580                          my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});                          my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});
581                          print HTMLOUT $htmlString;              $retVal .= $htmlString;
582                  }                  }
583          }          }
584          # Denote we're starting the relationship section.          # Denote we're starting the relationship section.
585          print HTMLOUT "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";      $retVal .= "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";
586          # Loop through the relationships.          # Loop through the relationships.
587          for my $key (sort keys %{$relationshipList}) {          for my $key (sort keys %{$relationshipList}) {
588                  Trace("Building MetaData entry for $key relationship.") if T(4);                  Trace("Building MetaData entry for $key relationship.") if T(4);
# Line 244  Line 590 
590                  my $relationshipStructure = $relationshipList->{$key};                  my $relationshipStructure = $relationshipList->{$key};
591                  # Create the relationship header.                  # Create the relationship header.
592                  my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);                  my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);
593                  print HTMLOUT "<h3><a name=\"$key\"></a>$headerText</h3>\n";          $retVal .= "<h3><a name=\"$key\"></a>$headerText</h3>\n";
594                  # Get the entity names.                  # Get the entity names.
595                  my $fromEntity = $relationshipStructure->{from};                  my $fromEntity = $relationshipStructure->{from};
596                  my $toEntity = $relationshipStructure->{to};                  my $toEntity = $relationshipStructure->{to};
# Line 254  Line 600 
600                  # since both sentences will say the same thing.                  # since both sentences will say the same thing.
601                  my $arity = $relationshipStructure->{arity};                  my $arity = $relationshipStructure->{arity};
602                  if ($arity eq "11") {                  if ($arity eq "11") {
603                          print HTMLOUT "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";
604                  } else {                  } else {
605                          print HTMLOUT "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";
606                          if ($arity eq "MM" && $fromEntity ne $toEntity) {                          if ($arity eq "MM" && $fromEntity ne $toEntity) {
607                                  print HTMLOUT "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";                  $retVal .= "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";
608                          }                          }
609                  }                  }
610                  print HTMLOUT "</p>\n";          $retVal .= "</p>\n";
611                  # If there are notes on this relationship, display them.                  # If there are notes on this relationship, display them.
612                  if (my $notes = $relationshipStructure->{Notes}) {                  if (my $notes = $relationshipStructure->{Notes}) {
613                          print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
614                  }                  }
615                  # Generate the relationship's relation table.                  # Generate the relationship's relation table.
616                  my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});                  my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
617                  print HTMLOUT $htmlString;          $retVal .= $htmlString;
618          }          }
619          Trace("Building MetaData join table.") if T(4);          Trace("Building MetaData join table.") if T(4);
620          # Denote we're starting the join table.          # Denote we're starting the join table.
621          print HTMLOUT "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";      $retVal .= "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";
622          # Create a table header.          # Create a table header.
623          print HTMLOUT _OpenTable("Join Table", "Source", "Target", "Join Condition");      $retVal .= _OpenTable("Join Table", "Source", "Target", "Join Condition");
624          # Loop through the joins.          # Loop through the joins.
625          my $joinTable = $metadata->{Joins};          my $joinTable = $metadata->{Joins};
626          my @joinKeys = keys %{$joinTable};          my @joinKeys = keys %{$joinTable};
# Line 282  Line 628 
628                  # Separate out the source, the target, and the join clause.                  # Separate out the source, the target, and the join clause.
629                  $joinKey =~ m!^([^/]+)/(.+)$!;                  $joinKey =~ m!^([^/]+)/(.+)$!;
630                  my ($sourceRelation, $targetRelation) = ($1, $2);                  my ($sourceRelation, $targetRelation) = ($1, $2);
631                  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);
632                  my $source = $self->ComputeObjectSentence($sourceRelation);                  my $source = $self->ComputeObjectSentence($sourceRelation);
633                  my $target = $self->ComputeObjectSentence($targetRelation);                  my $target = $self->ComputeObjectSentence($targetRelation);
634                  my $clause = $joinTable->{$joinKey};                  my $clause = $joinTable->{$joinKey};
635                  # Display them in a table row.                  # Display them in a table row.
636                  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";
637          }          }
638          # Close the table.          # Close the table.
639          print HTMLOUT _CloseTable();      $retVal .= _CloseTable();
640          # Close the document.      Trace("Built MetaData HTML.") if T(3);
641          print HTMLOUT "</body>\n</html>\n";      # Return the HTML.
642          # Close the file.      return $retVal;
         close HTMLOUT;  
         Trace("Built MetaData web page.") if T(3);  
643  }  }
644    
645  =head3 DumpMetaData  =head3 DumpMetaData
646    
647  C<< $database->DumpMetaData(); >>      $erdb->DumpMetaData();
648    
649  Return a dump of the metadata structure.  Return a dump of the metadata structure.
650    
# Line 313  Line 657 
657          return Data::Dumper::Dumper($self->{_metaData});          return Data::Dumper::Dumper($self->{_metaData});
658  }  }
659    
660    =head3 GenerateWikiData
661    
662        my @wikiLines = $erdb->GenerateWikiData();
663    
664    Build a description of the database for the wiki. The database will be
665    organized into a single page, with sections for each entity and relationship.
666    The return value is a list of text lines.
667    
668    =cut
669    
670    sub GenerateWikiData {
671        # Get the parameters.
672        my ($self) = @_;
673        # We'll build the wiki text in here.
674        my @retVal = ();
675        # Get the metadata object.
676        my $metadata = $self->{_metaData};
677        # Get the title string. This will become the page name.
678        my $title = $metadata->{Title}->{content};
679        # Get the entity and relationship lists.
680        my $entityList = $metadata->{Entities};
681        my $relationshipList = $metadata->{Relationships};
682        # Start with the introductory text.
683        push @retVal, WikiTools::Heading(2, "Introduction");
684        if (my $notes = $metadata->{Notes}) {
685            push @retVal, WikiNote($notes->{content});
686        }
687        # Start the entity section.
688        push @retVal, WikiTools::Heading(2, "Entities");
689        # Loop through the entities. Note that unlike the situation with HTML, we
690        # don't need to generate the table of contents manually, just the data
691        # itself.
692        for my $key (sort keys %$entityList) {
693            # Create a header for this entity.
694            push @retVal, "", WikiTools::Heading(3, $key);
695            # Get the entity data.
696            my $entityData = $entityList->{$key};
697            # Plant the notes here, if there are any.
698            if (my $notes = $entityData->{Notes}) {
699                push @retVal, "", WikiNote($notes->{content});
700            }
701            # Get the entity's relations.
702            my $relationList = $entityData->{Relations};
703            # Loop through the relations, displaying them.
704            for my $relation (sort keys %{$relationList}) {
705                my $wikiString = _WikiRelationTable($relation, $relationList->{$relation});
706                push @retVal, $wikiString;
707            }
708            # Now we list the entity's relationships (if any). First, we build a list
709            # of the relationships relevant to this entity.
710            my @rels = ();
711            for my $rel (sort keys %$relationshipList) {
712                my $relStructure = $relationshipList->{$rel};
713                if ($relStructure->{from} eq $key || $relStructure->{to} eq $key) {
714                    # Get the relationship sentence.
715                    my $relSentence = _ComputeRelationshipSentence($rel, $relStructure);
716                    # Linkify it.
717                    my $linkedRel = WikiTools::LinkMarkup("#$rel", $rel);
718                    $relSentence =~ s/$rel/$linkedRel/;
719                    push @rels, $relSentence;
720                }
721            }
722            # Add the relationships as a Wiki list.
723            push @retVal, WikiTools::List(@rels);
724        }
725        # Now the entities are documented. Next we do the relationships.
726        push @retVal, WikiTools::Heading(2, "Relationships");
727        for my $key (sort keys %$relationshipList) {
728            my $relationshipData = $relationshipList->{$key};
729            # Create the relationship heading.
730            push @retVal, WikiTools::Heading(3, $key);
731            # Describe the relationship arity. Note there's a bit of trickiness involving recursive
732            # many-to-many relationships. In a normal many-to-many we use two sentences to describe
733            # the arity (one for each direction). This is a bad idea for a recursive relationship,
734            # since both sentences will say the same thing.
735            my $arity = $relationshipData->{arity};
736            my $fromEntity = $relationshipData->{from};
737            my $toEntity = $relationshipData->{to};
738            my @listElements = ();
739            my $boldCode = WikiTools::BoldCode();
740            if ($arity eq "11") {
741                push @listElements, "Each $boldCode$fromEntity$boldCode relates to at most one $boldCode$toEntity$boldCode.";
742            } else {
743                push @listElements, "Each $boldCode$fromEntity$boldCode relates to multiple $boldCode${toEntity}s$boldCode.\n";
744                if ($arity eq "MM" && $fromEntity ne $toEntity) {
745                    push @listElements, "Each $boldCode$toEntity$boldCode relates to multiple $boldCode${fromEntity}s$boldCode.\n";
746                }
747            }
748            push @retVal, WikiTools::List(@listElements);
749            # Plant the notes here, if there are any.
750            if (my $notes = $relationshipData->{Notes}) {
751                push @retVal, "", WikiNote($notes->{content});
752            }
753            # Finally, the relationship table.
754            my $wikiString = _WikiRelationTable($key, $relationshipData->{Relations}->{$key});
755            push @retVal, $wikiString;
756        }
757        # All done. Return the lines.
758        return @retVal;
759    }
760    
761    
762    =head3 CreatePPO
763    
764        ERDB::CreatePPO($erdbXMLFile, $ppoXMLFile);
765    
766    Create a PPO XML file from an ERDB data definition XML file. At the
767    current time, the PPO XML file can be used to create a database with
768    similar functionality. Eventually, the PPO will be able to use the
769    created XML to access the live ERDB database.
770    
771    =over 4
772    
773    =item erdbXMLFile
774    
775    Name of the XML data definition file for the ERDB database. This
776    file must exist.
777    
778    =item ppoXMLFile
779    
780    Output file for the PPO XML definition. If this file exists, it
781    will be overwritten.
782    
783    =back
784    
785    =cut
786    
787    sub CreatePPO {
788        # Get the parameters.
789        my ($erdbXMLFile, $ppoXMLFile) = @_;
790        # First, we want to slurp in the ERDB XML file in its raw form.
791        my $xml = ReadMetaXML($erdbXMLFile);
792        # Create a variable to hold all of the objects in the PPO project.
793        my @objects = ();
794        # Get the relationship hash.
795        my $relationships = $xml->{Relationships};
796        # Loop through the entities.
797        my $entities = $xml->{Entities};
798        for my $entityName (keys %{$entities}) {
799            # Get the entity's data structures.
800            my $entityObject = $entities->{$entityName};
801            # We put the object's fields in here, according to their type.
802            my (@object_refs, @scalars, @indexes, @arrays);
803            # Create the ID field for the entity. We get the key type from the
804            # entity object and compute the corresponding SQL type.
805            my $type = $TypeTable{$entityObject->{keyType}}->{sqlType};
806            push @scalars, { label => 'id', type => $type };
807            # Loop through the entity fields.
808            for my $fieldName ( keys %{$entityObject->{Fields}} ) {
809                # Get the field object.
810                my $fieldObject = $entityObject->{Fields}->{$fieldName};
811                # Convert it to a scalar tag.
812                my $scalar = _CreatePPOField($fieldName, $fieldObject);
813                # If we have a relation, this field is stored in an array.
814                # otherwise, it is a scalar. The array tag has scalars
815                # stored as an XML array. In ERDB, there is only ever one,
816                # but PPO can have more.
817                my $relation = $fieldObject->{relation};
818                if ($relation) {
819                    push @arrays, { scalar => [$scalar] };
820                } else {
821                    push @scalars, $scalar;
822                }
823            }
824            # Loop through the relationships. If this entity is the to-entity
825            # on a relationship of 1M arity, then it is implemented as a PPO
826            # object reference.
827            for my $relationshipName (keys %{$relationships}) {
828                # Get the relationship data.
829                my $relationshipData = $relationships->{$relationshipName};
830                # If we have a from for this entity and an arity of 1M, we
831                # have an object reference.
832                if ($relationshipData->{to} eq $entityName &&
833                    $relationshipData->{arity} eq '1M') {
834                    # Build the object reference tag.
835                    push @object_refs, { label => $relationshipName,
836                                         type => $relationshipData->{from} };
837                }
838            }
839            # Create the indexes.
840            my $indexList = $entityObject->{Indexes};
841            push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
842            # Build the object XML tree.
843            my $object = { label => $entityName,
844                           object_ref => \@object_refs,
845                           scalar => \@scalars,
846                           index => \@indexes,
847                           array => \@arrays
848                          };
849            # Push the object onto the objects list.
850            push @objects, $object;
851        }
852        # Loop through the relationships, searching for MMs. The 1Ms were
853        # already handled by the entity search above.
854        for my $relationshipName (keys %{$relationships}) {
855            # Get this relationship's object.
856            my $relationshipObject = $relationships->{$relationshipName};
857            # Only proceed if it's many-to-many.
858            if ($relationshipObject->{arity} eq 'MM') {
859                # Create the tag lists for the relationship object.
860                my (@object_refs, @scalars, @indexes);
861                # The relationship will be created as an object with object
862                # references for its links to the participating entities.
863                my %links = ( from_link => $relationshipObject->{from},
864                              to_link => $relationshipObject->{to} );
865                for my $link (keys %links) {
866                    # Create an object_ref tag for this piece of the
867                    # relationship (from or to).
868                    my $object_ref = { label => $link,
869                                       type => $links{$link} };
870                    push @object_refs, $object_ref;
871                }
872                # Loop through the intersection data fields, creating scalar tags.
873                # There are no fancy array tags in a relationship.
874                for my $fieldName (keys %{$relationshipObject->{Fields}}) {
875                    my $fieldObject = $relationshipObject->{Fields}->{$fieldName};
876                    push @scalars, _CreatePPOField($fieldName, $fieldObject);
877                }
878                # Finally, the indexes: currently we cannot support the to-index and
879                # from-index in PPO, so we just process the alternate indexes.
880                my $indexList = $relationshipObject->{Indexes};
881                push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
882                # Wrap up all the stuff about this relationship.
883                my $object = { label => $relationshipName,
884                               scalar => \@scalars,
885                               object_ref => \@object_refs,
886                               index => \@indexes
887                             };
888                # Push it into the object list.
889                push @objects, $object;
890            }
891        }
892        # Compute a title.
893        my $title;
894        if ($erdbXMLFile =~ /(\/|^)([^\/]+)DBD\.xml/) {
895            # Here we have a standard file name we can use for a title.
896            $title = $2;
897        } else {
898            # Here the file name is non-standard, so we carve up the
899            # database title.
900            $title = $xml->{Title}->{content};
901            $title =~ s/\s\.,//g;
902        }
903        # Wrap up the XML as a project.
904        my $ppoXML = { project => { label => $title,
905                                    object => \@objects }};
906        # Write out the results.
907        my $ppoString = XML::Simple::XMLout($ppoXML,
908                                            AttrIndent => 1,
909                                            KeepRoot => 1);
910        Tracer::PutFile($ppoXMLFile, [ $ppoString ]);
911    }
912    
913    =head3 FindIndexForEntity
914    
915        my $indexFound = ERDB::FindIndexForEntity($xml, $entityName, $attributeName);
916    
917    This method locates the entry in an entity's index list that begins with the
918    specified attribute name. If the entity has no index list, one will be
919    created. This method works on raw XML, not a live ERDB object.
920    
921    =over 4
922    
923    =item xml
924    
925    The raw XML structure defining the database.
926    
927    =item entityName
928    
929    The name of the relevant entity.
930    
931    =item attributeName
932    
933    The name of the attribute relevant to the search.
934    
935    =item RETURN
936    
937    The numerical index in the index list of the index entry for the specified entity and
938    attribute, or C<undef> if no such index exists.
939    
940    =back
941    
942    =cut
943    
944    sub FindIndexForEntity {
945        # Get the parameters.
946        my ($xml, $entityName, $attributeName) = @_;
947        # Declare the return variable.
948        my $retVal;
949        # Get the named entity.
950        my $entityData = $xml->{Entities}->{$entityName};
951        if (! $entityData) {
952            Confess("Entity $entityName not found in DBD structure.");
953        } else {
954            # Insure it has an index list.
955            if (! exists $entityData->{Indexes}) {
956                $entityData->{Indexes} = [];
957            } else {
958                # Search for the desired index.
959                my $indexList = $entityData->{Indexes};
960                my $n = scalar @{$indexList};
961                Trace("Searching $n indexes in index list for $entityName.") if T(2);
962                # We use an indexed FOR here because we're returning an
963                # index number instead of an object. We do THAT so we can
964                # delete the index from the list if needed.
965                for (my $i = 0; $i < $n && !defined($retVal); $i++) {
966                    my $index = $indexList->[$i];
967                    my $fields = $index->{IndexFields};
968                    # Technically this IF should be safe (that is, we are guaranteed
969                    # the existence of a "$fields->[0]"), because when we load the XML
970                    # we have SuppressEmpty specified.
971                    if ($fields->[0]->{name} eq $attributeName) {
972                        $retVal = $i;
973                    }
974                }
975            }
976        }
977        Trace("Index for $attributeName of $entityName found at position $retVal.") if defined($retVal) && T(3);
978        Trace("Index for $attributeName not found in $entityName.") if !defined($retVal) && T(3);
979        # Return the result.
980        return $retVal;
981    }
982    
983  =head3 CreateTables  =head3 CreateTables
984    
985  C<< $datanase->CreateTables(); >>      $erdb->CreateTables();
986    
987  This method creates the tables for the database from the metadata structure loaded by the  This method creates the tables for the database from the metadata structure loaded by the
988  constructor. It is expected this function will only be used on rare occasions, when the  constructor. It is expected this function will only be used on rare occasions, when the
# Line 327  Line 994 
994  sub CreateTables {  sub CreateTables {
995          # Get the parameters.          # Get the parameters.
996          my ($self) = @_;          my ($self) = @_;
997          my $metadata = $self->{_metaData};      # Get the relation names.
998          my $dbh = $self->{_dbh};      my @relNames = $self->GetTableNames();
999          # Loop through the entities.      # Loop through the relations.
1000          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}}) {  
1001                          # Create a table for this relation.                          # Create a table for this relation.
1002                          $self->CreateTable($relationName);          $self->CreateTable($relationName, 1);
1003                          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);  
1004          }          }
1005  }  }
1006    
1007  =head3 CreateTable  =head3 CreateTable
1008    
1009  C<< $database->CreateTable($tableName, $indexFlag); >>      $erdb->CreateTable($tableName, $indexFlag, $estimatedRows);
1010    
1011  Create the table for a relation and optionally create its indexes.  Create the table for a relation and optionally create its indexes.
1012    
# Line 363  Line 1016 
1016    
1017  Name of the relation (which will also be the table name).  Name of the relation (which will also be the table name).
1018    
1019  =item $indexFlag  =item indexFlag
1020    
1021  TRUE if the indexes for the relation should be created, else FALSE. If FALSE,  TRUE if the indexes for the relation should be created, else FALSE. If FALSE,
1022  L</CreateIndexes> must be called later to bring the indexes into existence.  L</CreateIndexes> must be called later to bring the indexes into existence.
1023    
1024    =item estimatedRows (optional)
1025    
1026    If specified, the estimated maximum number of rows for the relation. This
1027    information allows the creation of tables using storage engines that are
1028    faster but require size estimates, such as MyISAM.
1029    
1030  =back  =back
1031    
1032  =cut  =cut
1033    
1034  sub CreateTable {  sub CreateTable {
1035          # Get the parameters.          # Get the parameters.
1036          my ($self, $relationName, $indexFlag) = @_;      my ($self, $relationName, $indexFlag, $estimatedRows) = @_;
1037          # Get the database handle.          # Get the database handle.
1038          my $dbh = $self->{_dbh};          my $dbh = $self->{_dbh};
1039          # 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 1057 
1057          # Insure the table is not already there.          # Insure the table is not already there.
1058          $dbh->drop_table(tbl => $relationName);          $dbh->drop_table(tbl => $relationName);
1059          Trace("Table $relationName dropped.") if T(2);          Trace("Table $relationName dropped.") if T(2);
1060        # If there are estimated rows, create an estimate so we can take advantage of
1061        # faster DB technologies.
1062        my $estimation = undef;
1063        if ($estimatedRows) {
1064            $estimation = [$self->EstimateRowSize($relationName), $estimatedRows];
1065            Trace("$estimation->[1] rows of $estimation->[0] bytes each.") if T(3);
1066        }
1067          # Create the table.          # Create the table.
1068          Trace("Creating table $relationName: $fieldThing") if T(2);          Trace("Creating table $relationName: $fieldThing") if T(2);
1069          $dbh->create_table(tbl => $relationName, flds => $fieldThing);      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);
1070          Trace("Relation $relationName created in database.") if T(2);          Trace("Relation $relationName created in database.") if T(2);
1071          # If we want to build the indexes, we do it here.      # If we want to build the indexes, we do it here. Note that the full-text search
1072        # index will not be built until the table has been loaded.
1073          if ($indexFlag) {          if ($indexFlag) {
1074                  $self->CreateIndex($relationName);                  $self->CreateIndex($relationName);
1075          }          }
1076  }  }
1077    
1078    =head3 VerifyFields
1079    
1080        my $count = $erdb->VerifyFields($relName, \@fieldList);
1081    
1082    Run through the list of proposed field values, insuring that all the character fields are
1083    below the maximum length. If any fields are too long, they will be truncated in place.
1084    
1085    =over 4
1086    
1087    =item relName
1088    
1089    Name of the relation for which the specified fields are destined.
1090    
1091    =item fieldList
1092    
1093    Reference to a list, in order, of the fields to be put into the relation.
1094    
1095    =item RETURN
1096    
1097    Returns the number of fields truncated.
1098    
1099    =back
1100    
1101    =cut
1102    
1103    sub VerifyFields {
1104        # Get the parameters.
1105        my ($self, $relName, $fieldList) = @_;
1106        # Initialize the return value.
1107        my $retVal = 0;
1108        # Get the relation definition.
1109        my $relData = $self->_FindRelation($relName);
1110        # Get the list of field descriptors.
1111        my $fieldTypes = $relData->{Fields};
1112        my $fieldCount = scalar @{$fieldTypes};
1113        # Loop through the two lists.
1114        for (my $i = 0; $i < $fieldCount; $i++) {
1115            # Get the type of the current field.
1116            my $fieldType = $fieldTypes->[$i]->{type};
1117            # If it's a character field, verify the length.
1118            if ($fieldType =~ /string/) {
1119                my $maxLen = $TypeTable{$fieldType}->{maxLen};
1120                my $oldString = $fieldList->[$i];
1121                if (length($oldString) > $maxLen) {
1122                    # Here it's too big, so we truncate it.
1123                    Trace("Truncating field $i ($fieldTypes->[$i]->{name}) in relation $relName to $maxLen characters from \"$oldString\".") if T(1);
1124                    $fieldList->[$i] = substr $oldString, 0, $maxLen;
1125                    $retVal++;
1126                }
1127            }
1128        }
1129        # Return the truncation count.
1130        return $retVal;
1131    }
1132    
1133    =head3 DigestFields
1134    
1135        $erdb->DigestFields($relName, $fieldList);
1136    
1137    Digest the strings in the field list that correspond to data type C<hash-string> in the
1138    specified relation.
1139    
1140    =over 4
1141    
1142    =item relName
1143    
1144    Name of the relation to which the fields belong.
1145    
1146    =item fieldList
1147    
1148    List of field contents to be loaded into the relation.
1149    
1150    =back
1151    
1152    =cut
1153    #: Return Type ;
1154    sub DigestFields {
1155        # Get the parameters.
1156        my ($self, $relName, $fieldList) = @_;
1157        # Get the relation definition.
1158        my $relData = $self->_FindRelation($relName);
1159        # Get the list of field descriptors.
1160        my $fieldTypes = $relData->{Fields};
1161        my $fieldCount = scalar @{$fieldTypes};
1162        # Loop through the two lists.
1163        for (my $i = 0; $i < $fieldCount; $i++) {
1164            # Get the type of the current field.
1165            my $fieldType = $fieldTypes->[$i]->{type};
1166            # If it's a hash string, digest it in place.
1167            if ($fieldType eq 'hash-string') {
1168                $fieldList->[$i] = $self->DigestKey($fieldList->[$i]);
1169            }
1170        }
1171    }
1172    
1173    =head3 DigestKey
1174    
1175        my $digested = $erdb->DigestKey($keyValue);
1176    
1177    Return the digested value of a symbolic key. The digested value can then be plugged into a
1178    key-based search into a table with key-type hash-string.
1179    
1180    Currently the digesting process is independent of the database structure, but that may not
1181    always be the case, so this is an instance method instead of a static method.
1182    
1183    =over 4
1184    
1185    =item keyValue
1186    
1187    Key value to digest.
1188    
1189    =item RETURN
1190    
1191    Digested value of the key.
1192    
1193    =back
1194    
1195    =cut
1196    
1197    sub DigestKey {
1198        # Get the parameters.
1199        my ($self, $keyValue) = @_;
1200        # Compute the digest.
1201        my $retVal = md5_base64($keyValue);
1202        # Return the result.
1203        return $retVal;
1204    }
1205    
1206  =head3 CreateIndex  =head3 CreateIndex
1207    
1208  C<< $database->CreateIndex($relationName); >>      $erdb->CreateIndex($relationName);
1209    
1210  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
1211  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.
1212  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
1213  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.
1214    
1215  =cut  =cut
1216    
# Line 431  Line 1226 
1226          for my $indexName (keys %{$indexHash}) {          for my $indexName (keys %{$indexHash}) {
1227                  my $indexData = $indexHash->{$indexName};                  my $indexData = $indexHash->{$indexName};
1228                  # Get the index's field list.                  # Get the index's field list.
1229                  my @fieldList = _FixNames(@{$indexData->{IndexFields}});          my @rawFields = @{$indexData->{IndexFields}};
1230            # Get a hash of the relation's field types.
1231            my %types = map { $_->{name} => $_->{type} } @{$relationData->{Fields}};
1232            # We need to check for text fields so we can append a length limitation for them. To do
1233            # that, we need the relation's field list.
1234            my $relFields = $relationData->{Fields};
1235            for (my $i = 0; $i <= $#rawFields; $i++) {
1236                # Get the field type.
1237                my $field = $rawFields[$i];
1238                my $type = $types{$field};
1239                # Ask if it requires using prefix notation for the index.
1240                my $mod = $TypeTable{$type}->{indexMod};
1241                Trace("Field $field ($i) in $relationName has type $type and indexMod $mod.") if T(3);
1242                if ($mod) {
1243                    # Append the prefix length to the field name,
1244                    $rawFields[$i] .= "($mod)";
1245                }
1246            }
1247            my @fieldList = _FixNames(@rawFields);
1248                  my $flds = join(', ', @fieldList);                  my $flds = join(', ', @fieldList);
1249                  # Get the index's uniqueness flag.                  # Get the index's uniqueness flag.
1250                  my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
1251                  # Create the index.                  # Create the index.
1252                  $dbh->create_index(idx => $indexName, tbl => $relationName, flds => $flds, unique => $unique);          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
1253                                        flds => $flds, kind => $unique);
1254            if ($rv) {
1255                  Trace("Index created: $indexName for $relationName ($flds)") if T(1);                  Trace("Index created: $indexName for $relationName ($flds)") if T(1);
1256            } else {
1257                Confess("Error creating index $indexName for $relationName using ($flds): " . $dbh->error_message());
1258            }
1259        }
1260    }
1261    
1262    =head3 GetSecondaryFields
1263    
1264        my %fieldTuples = $erdb->GetSecondaryFields($entityName);
1265    
1266    This method will return a list of the name and type of each of the secondary
1267    fields for a specified entity. Secondary fields are stored in two-column tables
1268    in addition to the primary entity table. This enables the field to have no value
1269    or to have multiple values.
1270    
1271    =over 4
1272    
1273    =item entityName
1274    
1275    Name of the entity whose secondary fields are desired.
1276    
1277    =item RETURN
1278    
1279    Returns a hash mapping the field names to their field types.
1280    
1281    =back
1282    
1283    =cut
1284    
1285    sub GetSecondaryFields {
1286        # Get the parameters.
1287        my ($self, $entityName) = @_;
1288        # Declare the return variable.
1289        my %retVal = ();
1290        # Look for the entity.
1291        my $table = $self->GetFieldTable($entityName);
1292        # Loop through the fields, pulling out the secondaries.
1293        for my $field (sort keys %{$table}) {
1294            if ($table->{$field}->{relation} ne $entityName) {
1295                # Here we have a secondary field.
1296                $retVal{$field} = $table->{$field}->{type};
1297            }
1298        }
1299        # Return the result.
1300        return %retVal;
1301    }
1302    
1303    =head3 GetFieldRelationName
1304    
1305        my $name = $erdb->GetFieldRelationName($objectName, $fieldName);
1306    
1307    Return the name of the relation containing a specified field.
1308    
1309    =over 4
1310    
1311    =item objectName
1312    
1313    Name of the entity or relationship containing the field.
1314    
1315    =item fieldName
1316    
1317    Name of the relevant field in that entity or relationship.
1318    
1319    =item RETURN
1320    
1321    Returns the name of the database relation containing the field, or C<undef> if
1322    the field does not exist.
1323    
1324    =back
1325    
1326    =cut
1327    
1328    sub GetFieldRelationName {
1329        # Get the parameters.
1330        my ($self, $objectName, $fieldName) = @_;
1331        # Declare the return variable.
1332        my $retVal;
1333        # Get the object field table.
1334        my $table = $self->GetFieldTable($objectName);
1335        # Only proceed if the field exists.
1336        if (exists $table->{$fieldName}) {
1337            # Determine the name of the relation that contains this field.
1338            $retVal = $table->{$fieldName}->{relation};
1339        }
1340        # Return the result.
1341        return $retVal;
1342    }
1343    
1344    =head3 DeleteValue
1345    
1346        my $numDeleted = $erdb->DeleteValue($entityName, $id, $fieldName, $fieldValue);
1347    
1348    Delete secondary field values from the database. This method can be used to delete all
1349    values of a specified field for a particular entity instance, or only a single value.
1350    
1351    Secondary fields are stored in two-column relations separate from an entity's primary
1352    table, and as a result a secondary field can legitimately have no value or multiple
1353    values. Therefore, it makes sense to talk about deleting secondary fields where it
1354    would not make sense for primary fields.
1355    
1356    =over 4
1357    
1358    =item entityName
1359    
1360    Name of the entity from which the fields are to be deleted.
1361    
1362    =item id
1363    
1364    ID of the entity instance to be processed. If the instance is not found, this
1365    method will have no effect. If C<undef> is specified, all values for all of
1366    the entity instances will be deleted.
1367    
1368    =item fieldName
1369    
1370    Name of the field whose values are to be deleted.
1371    
1372    =item fieldValue (optional)
1373    
1374    Value to be deleted. If not specified, then all values of the specified field
1375    will be deleted for the entity instance. If specified, then only the values which
1376    match this parameter will be deleted.
1377    
1378    =item RETURN
1379    
1380    Returns the number of rows deleted.
1381    
1382    =back
1383    
1384    =cut
1385    
1386    sub DeleteValue {
1387        # Get the parameters.
1388        my ($self, $entityName, $id, $fieldName, $fieldValue) = @_;
1389        # Declare the return value.
1390        my $retVal = 0;
1391        # We need to set up an SQL command to do the deletion. First, we
1392        # find the name of the field's relation.
1393        my $table = $self->GetFieldTable($entityName);
1394        my $field = $table->{$fieldName};
1395        my $relation = $field->{relation};
1396        # Make sure this is a secondary field.
1397        if ($relation eq $entityName) {
1398            Confess("Cannot delete values of $fieldName for $entityName.");
1399        } else {
1400            # Set up the SQL command to delete all values.
1401            my $sql = "DELETE FROM $relation";
1402            # Build the filter.
1403            my @filters = ();
1404            my @parms = ();
1405            # Check for a filter by ID.
1406            if (defined $id) {
1407                push @filters, "id = ?";
1408                push @parms, $id;
1409            }
1410            # Check for a filter by value.
1411            if (defined $fieldValue) {
1412                push @filters, "$fieldName = ?";
1413                push @parms, $fieldValue;
1414            }
1415            # Append the filters to the command.
1416            if (@filters) {
1417                $sql .= " WHERE " . join(" AND ", @filters);
1418          }          }
1419            # Execute the command.
1420            my $dbh = $self->{_dbh};
1421            $retVal = $dbh->SQL($sql, 0, @parms);
1422        }
1423        # Return the result.
1424        return $retVal;
1425  }  }
1426    
1427  =head3 LoadTables  =head3 LoadTables
1428    
1429  C<< my $stats = $database->LoadTables($directoryName, $rebuild); >>      my $stats = $erdb->LoadTables($directoryName, $rebuild);
1430    
1431  This method will load the database tables from a directory. The tables must already have been created  This method will load the database tables from a directory. The tables must already have been created
1432  in the database. (This can be done by calling L</CreateTables>.) The caller passes in a directory name;  in the database. (This can be done by calling L</CreateTables>.) The caller passes in a directory name;
# Line 486  Line 1469 
1469          $directoryName =~ s!/\\$!!;          $directoryName =~ s!/\\$!!;
1470          # Declare the return variable.          # Declare the return variable.
1471          my $retVal = Stats->new();          my $retVal = Stats->new();
1472          # Get the metadata structure.      # Get the relation names.
1473          my $metaData = $self->{_metaData};      my @relNames = $self->GetTableNames();
1474          # 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}}) {  
1475                          # Try to load this relation.                          # Try to load this relation.
1476                          my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);                          my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);
1477                          # Accumulate the statistics.                          # Accumulate the statistics.
1478                          $retVal->Accumulate($result);                          $retVal->Accumulate($result);
1479                  }                  }
         }  
         # 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);  
         }  
1480          # Add the duration of the load to the statistical object.          # Add the duration of the load to the statistical object.
1481          $retVal->Add('duration', gettimeofday - $startTime);          $retVal->Add('duration', gettimeofday - $startTime);
1482          # Return the accumulated statistics.          # Return the accumulated statistics.
1483          return $retVal;          return $retVal;
1484  }  }
1485    
1486    
1487  =head3 GetTableNames  =head3 GetTableNames
1488    
1489  C<< my @names = $database->GetTableNames; >>      my @names = $erdb->GetTableNames;
1490    
1491  Return a list of the relations required to implement this database.  Return a list of the relations required to implement this database.
1492    
# Line 530  Line 1503 
1503    
1504  =head3 GetEntityTypes  =head3 GetEntityTypes
1505    
1506  C<< my @names = $database->GetEntityTypes; >>      my @names = $erdb->GetEntityTypes;
1507    
1508  Return a list of the entity type names.  Return a list of the entity type names.
1509    
# Line 545  Line 1518 
1518          return sort keys %{$entityList};          return sort keys %{$entityList};
1519  }  }
1520    
1521    =head3 GetDataTypes
1522    
1523        my %types = ERDB::GetDataTypes();
1524    
1525    Return a table of ERDB data types. The table returned is a hash of hashes.
1526    The keys of the big hash are the datatypes. Each smaller hash has several
1527    values used to manage the data. The most interesting is the SQL type (key
1528    C<sqlType>) and the descriptive node (key C<notes>).
1529    
1530    Note that changing the values in the smaller hashes will seriously break
1531    things, so this data should be treated as read-only.
1532    
1533    =cut
1534    
1535    sub GetDataTypes {
1536        return %TypeTable;
1537    }
1538    
1539    
1540    =head3 IsEntity
1541    
1542        my $flag = $erdb->IsEntity($entityName);
1543    
1544    Return TRUE if the parameter is an entity name, else FALSE.
1545    
1546    =over 4
1547    
1548    =item entityName
1549    
1550    Object name to be tested.
1551    
1552    =item RETURN
1553    
1554    Returns TRUE if the specified string is an entity name, else FALSE.
1555    
1556    =back
1557    
1558    =cut
1559    
1560    sub IsEntity {
1561        # Get the parameters.
1562        my ($self, $entityName) = @_;
1563        # Test to see if it's an entity.
1564        return exists $self->{_metaData}->{Entities}->{$entityName};
1565    }
1566    
1567  =head3 Get  =head3 Get
1568    
1569  C<< my $query = $database->Get(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>      my $query = $erdb->Get(\@objectNames, $filterClause, \@params);
1570    
1571  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.
1572  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 1574 
1574  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
1575  $genus.  $genus.
1576    
1577  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = ?", $genus); >>      $query = $erdb->Get(['Genome'], "Genome(genus) = ?", [$genus]);
1578    
1579  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
1580  parameter representing the parameter value. It would also be possible to code  parameter representing the parameter value. It would also be possible to code
1581    
1582  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>      $query = $erdb->Get(['Genome'], "Genome(genus) = \'$genus\'");
1583    
1584  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
1585  characters inside the variable C<$genus>.  characters inside the variable C<$genus>.
# Line 572  Line 1591 
1591  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
1592  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,
1593    
1594  C<< $query = $sprout->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", $genus); >>      $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]);
1595    
1596  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
1597  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.
1598  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
1599  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
1600  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  
1601  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,
1602  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.
1603    
1604    If an entity or relationship is mentioned twice, the name for the second occurrence will
1605    be suffixed with C<2>, the third occurrence will be suffixed with C<3>, and so forth. So,
1606    for example, if we have C<['Feature', 'HasContig', 'Contig', 'HasContig']>, then the
1607    B<to-link> field of the first B<HasContig> is specified as C<HasContig(to-link)>, while
1608    the B<to-link> field of the second B<HasContig> is specified as C<HasContig2(to-link)>.
1609    
1610  =over 4  =over 4
1611    
1612  =item objectNames  =item objectNames
# Line 603  Line 1627 
1627  with an ORDER BY clause. For example, the following filter string gets all genomes for a  with an ORDER BY clause. For example, the following filter string gets all genomes for a
1628  particular genus and sorts them by species name.  particular genus and sorts them by species name.
1629    
1630  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>      "Genome(genus) = ? ORDER BY Genome(species)"
1631    
1632    Note that the case is important. Only an uppercase "ORDER BY" with a single space will
1633    be processed. The idea is to make it less likely to find the verb by accident.
1634    
1635  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
1636  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
1637  relation.  relation.
1638    
1639  =item param1, param2, ..., paramN  Finally, you can limit the number of rows returned by adding a LIMIT clause. The LIMIT must
1640    be the last thing in the filter clause, and it contains only the word "LIMIT" followed by
1641    a positive number. So, for example
1642    
1643        "Genome(genus) = ? ORDER BY Genome(species) LIMIT 10"
1644    
1645    will only return the first ten genomes for the specified genus. The ORDER BY clause is not
1646    required. For example, to just get the first 10 genomes in the B<Genome> table, you could
1647    use
1648    
1649        "LIMIT 10"
1650    
1651  Parameter values to be substituted into the filter clause.  =item params
1652    
1653    Reference to a list of parameter values to be substituted into the filter clause.
1654    
1655  =item RETURN  =item RETURN
1656    
# Line 623  Line 1662 
1662    
1663  sub Get {  sub Get {
1664          # Get the parameters.          # Get the parameters.
1665          my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $objectNames, $filterClause, $params) = @_;
1666          # Construct the SELECT statement. The general pattern is      # Process the SQL stuff.
1667          #      my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1668          # SELECT name1.*, name2.*, ... nameN.* FROM name1, name2, ... nameN          $self->_SetupSQL($objectNames, $filterClause);
1669          #      # Create the query.
1670          my $dbh = $self->{_dbh};      my $command = "SELECT " . join(".*, ", @{$mappedNameListRef}) .
1671          my $command = "SELECT DISTINCT " . join('.*, ', @{$objectNames}) . ".* FROM " .          ".* $suffix";
1672                                  join(', ', @{$objectNames});      my $sth = $self->_GetStatementHandle($command, $params);
1673          # Check for a filter clause.      # Now we create the relation map, which enables DBQuery to determine the order, name
1674          if ($filterClause) {      # and mapped name for each object in the query.
1675                  # Here we have one, so we convert its field names and add it to the query. First,      my @relationMap = ();
1676                  # We create a copy of the filter string we can work with.      for my $mappedName (@{$mappedNameListRef}) {
1677                  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 = $1;  
1678                  }                  }
1679                  # Add the filter and the join clauses (if any) to the SELECT command.      # Return the statement object.
1680                  if ($filterString) {      my $retVal = DBQuery::_new($self, $sth, \@relationMap);
1681                          push @joinWhere, "($filterString)";      return $retVal;
                 }  
                 if (@joinWhere) {  
                         $command .= " WHERE " . join(' AND ', @joinWhere);  
                 }  
                 # Add the sort clause (if any) to the SELECT command.  
                 if ($orderClause) {  
                         $command .= " ORDER BY $orderClause";  
                 }  
         }  
         Trace("SQL query: $command") if T(2);  
         Trace("PARMS: '" . (join "', '", @params) . "'") if (T(3) && (@params > 0));  
         my $sth = $dbh->prepare_command($command);  
         # Execute it with the parameters bound in.  
         $sth->execute(@params) || Confess("SELECT error" . $sth->errstr());  
         # Return the statement object.  
         my $retVal = DBQuery::_new($self, $sth, @{$objectNames});  
         return $retVal;  
1682  }  }
1683    
 =head3 GetList  
1684    
 C<< my @dbObjects = $database->GetList(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  
1685    
1686  Return a list of object descriptors for the specified objects as determined by the  =head3 Search
 specified filter clause.  
1687    
1688  This method is essentially the same as L</Get> except it returns a list of objects rather      my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params);
 that a query object that can be used to get the results one record at a time.  
1689    
1690  =over 4  Perform a full text search with filtering. The search will be against a specified object
1691    in the object name list. That object will get an extra field containing the search
1692    relevance. Note that except for the search expression, the parameters of this method are
1693    the same as those for L</Get> and follow the same rules.
1694    
1695  =over 4  =over 4
1696    
1697    =item searchExpression
1698    
1699    Boolean search expression for the text fields of the target object. The default mode for
1700    a Boolean search expression is OR, but we want the default to be AND, so we will
1701    add a C<+> operator to each word with no other operator before it.
1702    
1703    =item idx
1704    
1705    Index in the I<$objectNames> list of the table to be searched in full-text mode.
1706    
1707  =item objectNames  =item objectNames
1708    
1709  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 1718 
1718  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
1719  be included in the list of object names.  be included in the list of object names.
1720    
1721  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  
1722    
1723  Parameter values to be substituted into the filter clause.  Reference to a list of parameter values to be substituted into the filter clause.
1724    
1725  =item RETURN  =item RETURN
1726    
1727  Returns a list of B<DBObject>s that satisfy the query conditions.  Returns a query object for the specified search.
1728    
1729  =back  =back
1730    
1731  =cut  =cut
1732  #: Return Type @%  
1733  sub GetList {  sub Search {
1734      # Get the parameters.      # Get the parameters.
1735      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1736          # Declare the return variable.          # Declare the return variable.
1737          my @retVal = ();      my $retVal;
1738          # Perform the query.      # Create a safety copy of the parameter list. Note we have to be careful to insure
1739          my $query = $self->Get($objectNames, $filterClause, @params);      # a parameter list exists before we copy it.
1740          # Loop through the results.      my @myParams = ();
1741          while (my $object = $query->Fetch) {      if (defined $params) {
1742                  push @retVal, $object;          @myParams = @{$params};
1743        }
1744        # Get the first object's structure so we have access to the searchable fields.
1745        my $object1Name = $objectNames->[$idx];
1746        my $object1Structure = $self->_GetStructure($object1Name);
1747        # Get the field list.
1748        if (! exists $object1Structure->{searchFields}) {
1749            Confess("No searchable index for $object1Name.");
1750        } else {
1751            # Get the field list.
1752            my @fields = @{$object1Structure->{searchFields}};
1753            # Clean the search expression.
1754            my $actualKeywords = $self->CleanKeywords($searchExpression);
1755            # Prefix a "+" to each uncontrolled word. This converts the default
1756            # search mode from OR to AND.
1757            $actualKeywords =~ s/(^|\s)(\w|")/$1\+$2/g;
1758            Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1759            # We need two match expressions, one for the filter clause and one in the
1760            # query itself. Both will use a parameter mark, so we need to push the
1761            # search expression onto the front of the parameter list twice.
1762            unshift @myParams, $actualKeywords, $actualKeywords;
1763            # Build the match expression.
1764            my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
1765            my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
1766            # Process the SQL stuff.
1767            my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1768                $self->_SetupSQL($objectNames, $filterClause, $matchClause);
1769            # Create the query. Note that the match clause is inserted at the front of
1770            # the select fields.
1771            my $command = "SELECT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .
1772                ".* $suffix";
1773            my $sth = $self->_GetStatementHandle($command, \@myParams);
1774            # Now we create the relation map, which enables DBQuery to determine the order, name
1775            # and mapped name for each object in the query.
1776            my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
1777            # Return the statement object.
1778            $retVal = DBQuery::_new($self, $sth, \@relationMap, $object1Name);
1779          }          }
1780      # Return the result.      return $retVal;
     return @retVal;  
1781  }  }
1782    
1783  =head3 ComputeObjectSentence  =head3 GetFlat
1784    
1785  C<< my $sentence = $database->ComputeObjectSentence($objectName); >>      my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field);
1786    
1787  Check an object name, and if it is a relationship convert it to a relationship sentence.  This is a variation of L</GetAll> that asks for only a single field per record and
1788    returns a single flattened list.
1789    
1790  =over 4  =over 4
1791    
1792  =item objectName  =item objectNames
1793    
1794  Name of the entity or relationship.  List containing the names of the entity and relationship objects to be retrieved.
1795    
1796    =item filterClause
1797    
1798    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1799    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
1800    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
1801    parameter list as additional parameters. The fields in a filter clause can come from primary
1802    entity relations, relationship relations, or secondary entity relations; however, all of the
1803    entities and relationships involved must be included in the list of object names.
1804    
1805    =item parameterList
1806    
1807    List of the parameters to be substituted in for the parameters marks in the filter clause.
1808    
1809    =item field
1810    
1811    Name of the field to be used to get the elements of the list returned.
1812    
1813  =item RETURN  =item RETURN
1814    
1815  Returns a string containing the entity name or a relationship sentence.  Returns a list of values.
1816    
1817  =back  =back
1818    
1819  =cut  =cut
1820    #: Return Type @;
1821  sub ComputeObjectSentence {  sub GetFlat {
1822          # Get the parameters.          # Get the parameters.
1823          my ($self, $objectName) = @_;      my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
1824          # Set the default return value.      # Construct the query.
1825          my $retVal = $objectName;      my $query = $self->Get($objectNames, $filterClause, $parameterList);
1826          # Look for the object as a relationship.      # Create the result list.
1827          my $relTable = $self->{_metaData}->{Relationships};      my @retVal = ();
1828          if (exists $relTable->{$objectName}) {      # Loop through the records, adding the field values found to the result list.
1829                  # Get the relationship sentence.      while (my $row = $query->Fetch()) {
1830                  $retVal = _ComputeRelationshipSentence($objectName, $relTable->{$objectName});          push @retVal, $row->Value($field);
1831          }          }
1832          # Return the result.      # Return the list created.
1833          return $retVal;      return @retVal;
1834  }  }
1835    
1836  =head3 DumpRelations  =head3 SpecialFields
1837    
1838  C<< $database->DumpRelations($outputDirectory); >>      my %specials = $erdb->SpecialFields($entityName);
1839    
1840  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
1841  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
1842    attributes without needed to plumb the internal ERDB data structures.
1843    
1844  =over 4  =over 4
1845    
1846  =item outputDirectory  =item entityName
1847    
1848  Name of the directory into which the relation files should be dumped.  Name of the entity whose special fields are desired.
1849    
1850    =item RETURN
1851    
1852    Returns a hash. The keys of the hash are the special field names, and the values
1853    are the values from each special field's C<special> attribute.
1854    
1855  =back  =back
1856    
1857  =cut  =cut
1858    
1859  sub DumpRelations {  sub SpecialFields {
1860          # Get the parameters.          # Get the parameters.
1861          my ($self, $outputDirectory) = @_;      my ($self, $entityName) = @_;
1862          # Now we need to run through all the relations. First, we loop through the entities.      # Declare the return variable.
1863          my $metaData = $self->{_metaData};      my %retVal = ();
1864          my $entities = $metaData->{Entities};      # Find the entity's data structure.
1865          for my $entityName (keys %{$entities}) {      my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1866                  my $entityStructure = $entities->{$entityName};      # Loop through its fields, adding each special field to the return hash.
1867                  # Get the entity's relations.      my $fieldHash = $entityData->{Fields};
1868                  my $relationList = $entityStructure->{Relations};      for my $fieldName (keys %{$fieldHash}) {
1869                  # Loop through the relations, dumping them.          my $fieldData = $fieldHash->{$fieldName};
1870                  for my $relationName (keys %{$relationList}) {          if (exists $fieldData->{special}) {
1871                          my $relation = $relationList->{$relationName};              $retVal{$fieldName} = $fieldData->{special};
                         $self->_DumpRelation($outputDirectory, $relationName, $relation);  
                 }  
1872          }          }
         # 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});  
1873          }          }
1874        # Return the result.
1875        return %retVal;
1876  }  }
1877    
1878  =head3 InsertObject  =head3 Delete
1879    
1880  C<< my $ok = $database->InsertObject($objectType, \%fieldHash); >>      my $stats = $erdb->Delete($entityName, $objectID, %options);
1881    
1882  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
1883  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>.  
1884    
1885  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
1886    relationship connected to a dependent entity or if it is the "to" entity connected to a 1-to-many
1887    dependent relationship.
1888    
1889  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>.  
1890    
1891  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
1892    
1893  =over 4  Name of the entity type for the instance being deleted.
1894    
1895  =item newObjectType  =item objectID
1896    
1897  Type name of the object to insert.  ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),
1898    then it is presumed to by a LIKE pattern.
1899    
1900  =item fieldHash  =item options
1901    
1902  Hash of field names to values.  A hash detailing the options for this delete operation.
1903    
1904  =item RETURN  =item RETURN
1905    
1906  Returns 1 if successful, 0 if an error occurred.  Returns a statistics object indicating how many records of each particular table were
1907    deleted.
1908    
1909  =back  =back
1910    
1911  =cut  The permissible options for this method are as follows.
1912    
1913  sub InsertObject {  =over 4
1914    
1915    =item testMode
1916    
1917    If TRUE, then the delete statements will be traced, but no changes will be made to the database.
1918    
1919    =item keepRoot
1920    
1921    If TRUE, then the entity instances will not be deleted, only the dependent records.
1922    
1923    =back
1924    
1925    =cut
1926    #: Return Type $%;
1927    sub Delete {
1928          # Get the parameters.          # Get the parameters.
1929          my ($self, $newObjectType, $fieldHash) = @_;      my ($self, $entityName, $objectID, %options) = @_;
1930          # Denote that so far we appear successful.      # Declare the return variable.
1931          my $retVal = 1;      my $retVal = Stats->new();
1932          # Get the database handle.      # Get the DBKernel object.
1933          my $dbh = $self->{_dbh};      my $db = $self->{_dbh};
1934          # Get the relation list.      # We're going to generate all the paths branching out from the starting entity. One of
1935          my $relationTable = $self->_GetRelationTable($newObjectType);      # the things we have to be careful about is preventing loops. We'll use a hash to
1936          # Loop through the relations. We'll build insert statements for each one. If a relation is      # determine if we've hit a loop.
1937          # secondary, we may end up generating multiple insert statements. If an error occurs, we      my %alreadyFound = ();
1938          # stop the loop.      # These next lists will serve as our result stack. We start by pushing object lists onto
1939          my @relationList = keys %{$relationTable};      # the stack, and then popping them off to do the deletes. This means the deletes will
1940          for (my $i = 0; $retVal && $i <= $#relationList; $i++) {      # start with the longer paths before getting to the shorter ones. That, in turn, makes
1941                  my $relationName = $relationList[$i];      # sure we don't delete records that might be needed to forge relationships back to the
1942                  my $relationDefinition = $relationTable->{$relationName};      # original item. We have two lists-- one for TO-relationships, and one for
1943                  # Get the relation's fields. For each field we will collect a value in the corresponding      # FROM-relationships and entities.
1944                  # position of the @valueList array. If one of the fields is missing, we will add it to the      my @fromPathList = ();
1945                  # @missing list.      my @toPathList = ();
1946                  my @fieldList = @{$relationDefinition->{Fields}};      # This final list is used to remember what work still needs to be done. We push paths
1947                  my @fieldNameList = ();      # onto the list, then pop them off to extend the paths. We prime it with the starting
1948                  my @valueList = ();      # point. Note that we will work hard to insure that the last item on a path in the
1949                  my @missing = ();      # to-do list is always an entity.
1950                  my $recordCount = 1;      my @todoList = ([$entityName]);
1951                  for my $fieldDescriptor (@fieldList) {      while (@todoList) {
1952                          # Get the field name and save it. Note we need to fix it up so the hyphens          # Get the current path.
1953                          # are converted to underscores.          my $current = pop @todoList;
1954                          my $fieldName = $fieldDescriptor->{name};          # Copy it into a list.
1955                          push @fieldNameList, _FixName($fieldName);          my @stackedPath = @{$current};
1956                          # Look for the named field in the incoming structure. Note that we are looking          # Pull off the last item on the path. It will always be an entity.
1957                          # for the real field name, not the fixed-up one!          my $myEntityName = pop @stackedPath;
1958                          if (exists $fieldHash->{$fieldName}) {          # Add it to the alreadyFound list.
1959                                  # Here we found the field. Stash it in the value list.          $alreadyFound{$myEntityName} = 1;
1960                                  my $value = $fieldHash->{$fieldName};          # Figure out if we need to delete this entity.
1961                                  push @valueList, $value;          if ($myEntityName ne $entityName || ! $options{keepRoot}) {
1962                                  # If the value is a list, we may need to increment the record count.              # Get the entity data.
1963                                  if (ref $value eq "ARRAY") {              my $entityData = $self->_GetStructure($myEntityName);
1964                                          my $thisCount = @{$value};              # Loop through the entity's relations. A DELETE command will be needed for each of them.
1965                                          if ($recordCount == 1) {              my $relations = $entityData->{Relations};
1966                                                  # Here we have our first list, so we save its count.              for my $relation (keys %{$relations}) {
1967                                                  $recordCount = $thisCount;                  my @augmentedList = (@stackedPath, $relation);
1968                                          } elsif ($recordCount != $thisCount) {                  push @fromPathList, \@augmentedList;
                                                 # Here we have a second list, so its length has to match the  
                                                 # previous lists.  
                                                 Trace("Field $value in new $newObjectType object has an invalid list length $thisCount. Expected $recordCount.") if T(0);  
                                                 $retVal = 0;  
1969                                          }                                          }
1970                                  }                                  }
1971            # Now we need to look for relationships connected to this entity.
1972            my $relationshipList = $self->{_metaData}->{Relationships};
1973            for my $relationshipName (keys %{$relationshipList}) {
1974                my $relationship = $relationshipList->{$relationshipName};
1975                # Check the FROM field. We're only interested if it's us.
1976                if ($relationship->{from} eq $myEntityName) {
1977                    # Add the path to this relationship.
1978                    my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1979                    push @fromPathList, \@augmentedList;
1980                    # Check the arity. If it's MM we're done. If it's 1M
1981                    # and the target hasn't been seen yet, we want to
1982                    # stack the entity for future processing.
1983                    if ($relationship->{arity} eq '1M') {
1984                        my $toEntity = $relationship->{to};
1985                        if (! exists $alreadyFound{$toEntity}) {
1986                            # Here we have a new entity that's dependent on
1987                            # the current entity, so we need to stack it.
1988                            my @stackList = (@augmentedList, $toEntity);
1989                            push @fromPathList, \@stackList;
1990                          } else {                          } else {
1991                                  # Here the field is not present. Flag it as missing.                          Trace("$toEntity ignored because it occurred previously.") if T(4);
                                 push @missing, $fieldName;  
1992                          }                          }
1993                  }                  }
                 # If we are the primary relation, add the new-record flag.  
                 if ($relationName eq $newObjectType) {  
                         push @valueList, 1;  
                         push @fieldNameList, "new_record";  
1994                  }                  }
1995                  # Only proceed if there are no missing fields.              # Now check the TO field. In this case only the relationship needs
1996                  if (@missing > 0) {              # deletion.
1997                          Trace("Relation $relationName for $newObjectType skipped due to missing fields: " .              if ($relationship->{to} eq $myEntityName) {
1998                                  join(' ', @missing)) if T(1);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1999                  } else {                  push @toPathList, \@augmentedList;
                         # Build the INSERT statement.  
                         my $statement = "INSERT INTO $relationName (" . join (', ', @fieldNameList) .  
                                 ") VALUES (";  
                         # Create a marker list of the proper size and put it in the statement.  
                         my @markers = ();  
                         while (@markers < @fieldNameList) { push @markers, '?'; }  
                         $statement .= join(', ', @markers) . ")";  
                         # We have the insert statement, so prepare it.  
                         my $sth = $dbh->prepare_command($statement);  
                         Trace("Insert statement prepared: $statement") if T(3);  
                         # Now we loop through the values. If a value is scalar, we use it unmodified. If it's  
                         # a list, we use the current element. The values are stored in the @parameterList array.  
                         my $done = 0;  
                         for (my $i = 0; $i < $recordCount; $i++) {  
                                 # Clear the parameter list array.  
                                 my @parameterList = ();  
                                 # Loop through the values.  
                                 for my $value (@valueList) {  
                                         # Check to see if this is a scalar value.  
                                         if (ref $value eq "ARRAY") {  
                                                 # Here we have a list value. Pull the current entry.  
                                                 push @parameterList, $value->[$i];  
                                         } else {  
                                                 # Here we have a scalar value. Use it unmodified.  
                                                 push @parameterList, $value;  
2000                                          }                                          }
2001                                  }                                  }
                                 # Execute the INSERT statement with the specified parameter list.  
                                 $retVal = $sth->execute(@parameterList);  
                                 if (!$retVal) {  
                                         my $errorString = $sth->errstr();  
                                         Trace("Insert error: $errorString.") if T(0);  
2002                                  }                                  }
2003        # Create the first qualifier for the WHERE clause. This selects the
2004        # keys of the primary entity records to be deleted. When we're deleting
2005        # from a dependent table, we construct a join path from the first qualifier
2006        # to the table containing the dependent records to delete.
2007        my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
2008        # We need to make two passes. The first is through the to-list, and
2009        # the second through the from-list. The from-list is second because
2010        # the to-list may need to pass through some of the entities the
2011        # from-list would delete.
2012        my %stackList = ( from_link => \@fromPathList, to_link => \@toPathList );
2013        # Now it's time to do the deletes. We do it in two passes.
2014        for my $keyName ('to_link', 'from_link') {
2015            # Get the list for this key.
2016            my @pathList = @{$stackList{$keyName}};
2017            Trace(scalar(@pathList) . " entries in path list for $keyName.") if T(3);
2018            # Loop through this list.
2019            while (my $path = pop @pathList) {
2020                # Get the table whose rows are to be deleted.
2021                my @pathTables = @{$path};
2022                # Start the DELETE statement. We need to call DBKernel because the
2023                # syntax of a DELETE-USING varies among DBMSs.
2024                my $target = $pathTables[$#pathTables];
2025                my $stmt = $db->SetUsing(@pathTables);
2026                # Now start the WHERE. The first thing is the ID field from the starting table. That
2027                # starting table will either be the entity relation or one of the entity's
2028                # sub-relations.
2029                $stmt .= " WHERE $pathTables[0].id $qualifier";
2030                # Now we run through the remaining entities in the path, connecting them up.
2031                for (my $i = 1; $i <= $#pathTables; $i += 2) {
2032                    # Connect the current relationship to the preceding entity.
2033                    my ($entity, $rel) = @pathTables[$i-1,$i];
2034                    # The style of connection depends on the direction of the relationship.
2035                    $stmt .= " AND $entity.id = $rel.$keyName";
2036                    if ($i + 1 <= $#pathTables) {
2037                        # Here there's a next entity, so connect that to the relationship's
2038                        # to-link.
2039                        my $entity2 = $pathTables[$i+1];
2040                        $stmt .= " AND $rel.to_link = $entity2.id";
2041                    }
2042                }
2043                # Now we have our desired DELETE statement.
2044                if ($options{testMode}) {
2045                    # Here the user wants to trace without executing.
2046                    Trace($stmt) if T(0);
2047                } else {
2048                    # Here we can delete. Note that the SQL method dies with a confession
2049                    # if an error occurs, so we just go ahead and do it.
2050                    Trace("Executing delete from $target using '$objectID'.") if T(3);
2051                    my $rv = $db->SQL($stmt, 0, $objectID);
2052                    # Accumulate the statistics for this delete. The only rows deleted
2053                    # are from the target table, so we use its name to record the
2054                    # statistic.
2055                    $retVal->Add($target, $rv);
2056                          }                          }
2057                  }                  }
2058          }          }
2059          # Return the success indicator.      # Return the result.
2060          return $retVal;          return $retVal;
2061  }  }
2062    
2063  =head3 LoadTable  =head3 Disconnect
2064    
2065  C<< my %results = $database->LoadTable($fileName, $relationName, $truncateFlag); >>      $erdb->Disconnect($relationshipName, $originEntityName, $originEntityID);
2066    
2067  Load data from a tab-delimited file into a specified table, optionally re-creating the table first.  Disconnect an entity instance from all the objects to which it is related. This
2068    will delete each relationship instance that connects to the specified entity.
2069    
2070  =over 4  =over 4
2071    
2072  =item fileName  =item relationshipName
   
 Name of the file from which the table data should be loaded.  
   
 =item relationName  
2073    
2074  Name of the relation to be loaded. This is the same as the table name.  Name of the relationship whose instances are to be deleted.
2075    
2076  =item truncateFlag  =item originEntityName
2077    
2078  TRUE if the table should be dropped and re-created, else FALSE  Name of the entity that is to be disconnected.
2079    
2080  =item RETURN  =item originEntityID
2081    
2082  Returns a statistical object containing the number of records read and a list of the error messages.  ID of the entity that is to be disconnected.
2083    
2084  =back  =back
2085    
2086  =cut  =cut
2087  sub LoadTable {  
2088    sub Disconnect {
2089          # Get the parameters.          # Get the parameters.
2090          my ($self, $fileName, $relationName, $truncateFlag) = @_;      my ($self, $relationshipName, $originEntityName, $originEntityID) = @_;
2091          # Create the statistical return object.      # Get the relationship descriptor.
2092          my $retVal = _GetLoadStats();      my $structure = $self->_GetStructure($relationshipName);
2093          # Trace the fact of the load.      # Insure we have a relationship.
2094          Trace("Loading table $relationName from $fileName") if T(1);      if (! exists $structure->{from}) {
2095            Confess("$relationshipName is not a relationship in the database.");
2096        } else {
2097          # Get the database handle.          # Get the database handle.
2098          my $dbh = $self->{_dbh};          my $dbh = $self->{_dbh};
2099          # Get the relation data.          # We'll set this value to 1 if we find our entity.
2100          my $relation = $self->_FindRelation($relationName);          my $found = 0;
2101          # Check the truncation flag.          # Loop through the ends of the relationship.
2102          if ($truncateFlag) {          for my $dir ('from', 'to') {
2103                  Trace("Creating table $relationName") if T(1);              if ($structure->{$dir} eq $originEntityName) {
2104                  # Re-create the table without its index.                  $found = 1;
2105                  $self->CreateTable($relationName, 0);                  # Here we want to delete all relationship instances on this side of the
2106                    # entity instance.
2107                    Trace("Disconnecting in $dir direction with ID \"$originEntityID\".");
2108                    # We do this delete in batches to keep it from dragging down the
2109                    # server.
2110                    my $limitClause = ($FIG_Config::delete_limit ? "LIMIT $FIG_Config::delete_limit" : "");
2111                    my $done = 0;
2112                    while (! $done) {
2113                        # Do the delete.
2114                        my $rows = $dbh->SQL("DELETE FROM $relationshipName WHERE ${dir}_link = ? $limitClause", 0, $originEntityID);
2115                        # See if we're done. We're done if no rows were found or the delete is unlimited.
2116                        $done = ($rows == 0 || ! $limitClause);
2117          }          }
         # 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 $relationName.") if T(1);  
         } else {  
                 # Here we successfully loaded the table. Trace the number of records loaded.  
                 Trace("$retVal->{records} records read for $relationName.") if T(1);  
                 # If we're rebuilding, we need to create the table indexes.  
                 if ($truncateFlag) {  
                         eval {  
                                 $self->CreateIndex($relationName);  
                         };  
                         if ($@) {  
                                 $retVal->AddMessage($@);  
2118                          }                          }
2119                  }                  }
2120            # Insure we found the entity on at least one end.
2121            if (! $found) {
2122                Confess("Entity \"$originEntityName\" does not use $relationshipName.");
2123          }          }
2124          # Commit the database changes.      }
2125          $dbh->commit_tran;  }
2126          # Delete the temporary file.  
2127          unlink $tempName;  =head3 DeleteRow
2128          # Return the statistics.  
2129        $erdb->DeleteRow($relationshipName, $fromLink, $toLink, \%values);
2130    
2131    Delete a row from a relationship. In most cases, only the from-link and to-link are
2132    needed; however, for relationships with intersection data values can be specified
2133    for the other fields using a hash.
2134    
2135    =over 4
2136    
2137    =item relationshipName
2138    
2139    Name of the relationship from which the row is to be deleted.
2140    
2141    =item fromLink
2142    
2143    ID of the entity instance in the From direction.
2144    
2145    =item toLink
2146    
2147    ID of the entity instance in the To direction.
2148    
2149    =item values
2150    
2151    Reference to a hash of other values to be used for filtering the delete.
2152    
2153    =back
2154    
2155    =cut
2156    
2157    sub DeleteRow {
2158        # Get the parameters.
2159        my ($self, $relationshipName, $fromLink, $toLink, $values) = @_;
2160        # Create a hash of all the filter information.
2161        my %filter = ('from-link' => $fromLink, 'to-link' => $toLink);
2162        if (defined $values) {
2163            for my $key (keys %{$values}) {
2164                $filter{$key} = $values->{$key};
2165            }
2166        }
2167        # Build an SQL statement out of the hash.
2168        my @filters = ();
2169        my @parms = ();
2170        for my $key (keys %filter) {
2171            push @filters, _FixName($key) . " = ?";
2172            push @parms, $filter{$key};
2173        }
2174        Trace("Parms for delete row are " . join(", ", map { "\"$_\"" } @parms) . ".") if T(SQL => 4);
2175        my $command = "DELETE FROM $relationshipName WHERE " .
2176                      join(" AND ", @filters);
2177        # Execute it.
2178        my $dbh = $self->{_dbh};
2179        $dbh->SQL($command, undef, @parms);
2180    }
2181    
2182    =head3 DeleteLike
2183    
2184        my $deleteCount = $erdb->DeleteLike($relName, $filter, \@parms);
2185    
2186    Delete all the relationship rows that satisfy a particular filter condition. Unlike a normal
2187    filter, only fields from the relationship itself can be used.
2188    
2189    =over 4
2190    
2191    =item relName
2192    
2193    Name of the relationship whose records are to be deleted.
2194    
2195    =item filter
2196    
2197    A filter clause (L</Get>-style) for the delete query.
2198    
2199    =item parms
2200    
2201    Reference to a list of parameters for the filter clause.
2202    
2203    =item RETURN
2204    
2205    Returns a count of the number of rows deleted.
2206    
2207    =back
2208    
2209    =cut
2210    
2211    sub DeleteLike {
2212        # Get the parameters.
2213        my ($self, $objectName, $filter, $parms) = @_;
2214        # Declare the return variable.
2215        my $retVal;
2216        # Insure the parms argument is an array reference if the caller left it off.
2217        if (! defined($parms)) {
2218            $parms = [];
2219        }
2220        # Insure we have a relationship. The main reason for this is if we delete an entity
2221        # instance we have to yank out a bunch of other stuff with it.
2222        if ($self->IsEntity($objectName)) {
2223            Confess("Cannot use DeleteLike on $objectName, because it is not a relationship.");
2224        } else {
2225            # Create the SQL command suffix to get the desierd records.
2226            my ($suffix) = $self->_SetupSQL([$objectName], $filter);
2227            # Convert it to a DELETE command.
2228            my $command = "DELETE $suffix";
2229            # Execute the command.
2230            my $dbh = $self->{_dbh};
2231            my $result = $dbh->SQL($command, 0, @{$parms});
2232            # Check the results. Note we convert the "0D0" result to a real zero.
2233            # A failure causes an abnormal termination, so the caller isn't going to
2234            # worry about it.
2235            if (! defined $result) {
2236                Confess("Error deleting from $objectName: " . $dbh->errstr());
2237            } elsif ($result == 0) {
2238                $retVal = 0;
2239            } else {
2240                $retVal = $result;
2241            }
2242        }
2243        # Return the result count.
2244        return $retVal;
2245    }
2246    
2247    =head3 SortNeeded
2248    
2249        my $parms = $erdb->SortNeeded($relationName);
2250    
2251    Return the pipe command for the sort that should be applied to the specified
2252    relation when creating the load file.
2253    
2254    For example, if the load file should be sorted ascending by the first
2255    field, this method would return
2256    
2257        sort -k1 -t"\t"
2258    
2259    If the first field is numeric, the method would return
2260    
2261        sort -k1n -t"\t"
2262    
2263    Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate
2264    keys using a sort.
2265    
2266    =over 4
2267    
2268    =item relationName
2269    
2270    Name of the relation to be examined.
2271    
2272    =item
2273    
2274    Returns the sort command to use for sorting the relation, suitable for piping.
2275    
2276    =back
2277    
2278    =cut
2279    #: Return Type $;
2280    sub SortNeeded {
2281        # Get the parameters.
2282        my ($self, $relationName) = @_;
2283        # Declare a descriptor to hold the names of the key fields.
2284        my @keyNames = ();
2285        # Get the relation structure.
2286        my $relationData = $self->_FindRelation($relationName);
2287        # Find out if the relation is a primary entity relation,
2288        # a relationship relation, or a secondary entity relation.
2289        my $entityTable = $self->{_metaData}->{Entities};
2290        my $relationshipTable = $self->{_metaData}->{Relationships};
2291        if (exists $entityTable->{$relationName}) {
2292            # Here we have a primary entity relation.
2293            push @keyNames, "id";
2294        } elsif (exists $relationshipTable->{$relationName}) {
2295            # Here we have a relationship. We sort using the FROM index.
2296            my $relationshipData = $relationshipTable->{$relationName};
2297            my $index = $relationData->{Indexes}->{idxFrom};
2298            push @keyNames, @{$index->{IndexFields}};
2299        } else {
2300            # Here we have a secondary entity relation, so we have a sort on the ID field.
2301            push @keyNames, "id";
2302        }
2303        # Now we parse the key names into sort parameters. First, we prime the return
2304        # string.
2305        my $retVal = "sort -t\"\t\" ";
2306        # Get the relation's field list.
2307        my @fields = @{$relationData->{Fields}};
2308        # Loop through the keys.
2309        for my $keyData (@keyNames) {
2310            # Get the key and the ordering.
2311            my ($keyName, $ordering);
2312            if ($keyData =~ /^([^ ]+) DESC/) {
2313                ($keyName, $ordering) = ($1, "descending");
2314            } else {
2315                ($keyName, $ordering) = ($keyData, "ascending");
2316            }
2317            # Find the key's position and type.
2318            my $fieldSpec;
2319            for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {
2320                my $thisField = $fields[$i];
2321                if ($thisField->{name} eq $keyName) {
2322                    # Get the sort modifier for this field type. The modifier
2323                    # decides whether we're using a character, numeric, or
2324                    # floating-point sort.
2325                    my $modifier = $TypeTable{$thisField->{type}}->{sort};
2326                    # If the index is descending for this field, denote we want
2327                    # to reverse the sort order on this field.
2328                    if ($ordering eq 'descending') {
2329                        $modifier .= "r";
2330                    }
2331                    # Store the position and modifier into the field spec, which
2332                    # will stop the inner loop. Note that the field number is
2333                    # 1-based in the sort command, so we have to increment the
2334                    # index.
2335                    $fieldSpec = ($i + 1) . $modifier;
2336                }
2337            }
2338            # Add this field to the sort command.
2339            $retVal .= " -k$fieldSpec";
2340        }
2341        # Return the result.
2342        return $retVal;
2343    }
2344    
2345    =head3 GetList
2346    
2347        my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params);
2348    
2349    Return a list of object descriptors for the specified objects as determined by the
2350    specified filter clause.
2351    
2352    This method is essentially the same as L</Get> except it returns a list of objects rather
2353    than a query object that can be used to get the results one record at a time.
2354    
2355    =over 4
2356    
2357    =item objectNames
2358    
2359    List containing the names of the entity and relationship objects to be retrieved.
2360    
2361    =item filterClause
2362    
2363    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
2364    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
2365    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
2366    in the filter clause should be added to the parameter list as additional parameters. The
2367    fields in a filter clause can come from primary entity relations, relationship relations,
2368    or secondary entity relations; however, all of the entities and relationships involved must
2369    be included in the list of object names.
2370    
2371    The filter clause can also specify a sort order. To do this, simply follow the filter string
2372    with an ORDER BY clause. For example, the following filter string gets all genomes for a
2373    particular genus and sorts them by species name.
2374    
2375        "Genome(genus) = ? ORDER BY Genome(species)"
2376    
2377    The rules for field references in a sort order are the same as those for field references in the
2378    filter clause in general; however, odd things may happen if a sort field is from a secondary
2379    relation.
2380    
2381    =item params
2382    
2383    Reference to a list of parameter values to be substituted into the filter clause.
2384    
2385    =item RETURN
2386    
2387    Returns a list of B<ERDBObject>s that satisfy the query conditions.
2388    
2389    =back
2390    
2391    =cut
2392    #: Return Type @%
2393    sub GetList {
2394        # Get the parameters.
2395        my ($self, $objectNames, $filterClause, $params) = @_;
2396        # Declare the return variable.
2397        my @retVal = ();
2398        # Perform the query.
2399        my $query = $self->Get($objectNames, $filterClause, $params);
2400        # Loop through the results.
2401        while (my $object = $query->Fetch) {
2402            push @retVal, $object;
2403        }
2404        # Return the result.
2405        return @retVal;
2406    }
2407    
2408    =head3 GetCount
2409    
2410        my $count = $erdb->GetCount(\@objectNames, $filter, \@params);
2411    
2412    Return the number of rows found by a specified query. This method would
2413    normally be used to count the records in a single table. For example, in a
2414    genetics database
2415    
2416        my $count = $erdb->GetCount(['Genome'], 'Genome(genus-species) LIKE ?', ['homo %']);
2417    
2418    would return the number of genomes for the genus I<homo>. It is conceivable, however,
2419    to use it to return records based on a join. For example,
2420    
2421        my $count = $erdb->GetCount(['HasFeature', 'Genome'], 'Genome(genus-species) LIKE ?',
2422                                    ['homo %']);
2423    
2424    would return the number of features for genomes in the genus I<homo>. Note that
2425    only the rows from the first table are counted. If the above command were
2426    
2427        my $count = $erdb->GetCount(['Genome', 'Feature'], 'Genome(genus-species) LIKE ?',
2428                                    ['homo %']);
2429    
2430    it would return the number of genomes, not the number of genome/feature pairs.
2431    
2432    =over 4
2433    
2434    =item objectNames
2435    
2436    Reference to a list of the objects (entities and relationships) included in the
2437    query.
2438    
2439    =item filter
2440    
2441    A filter clause for restricting the query. The rules are the same as for the L</Get>
2442    method.
2443    
2444    =item params
2445    
2446    Reference to a list of the parameter values to be substituted for the parameter marks
2447    in the filter.
2448    
2449    =item RETURN
2450    
2451    Returns a count of the number of records in the first table that would satisfy
2452    the query.
2453    
2454    =back
2455    
2456    =cut
2457    
2458    sub GetCount {
2459        # Get the parameters.
2460        my ($self, $objectNames, $filter, $params) = @_;
2461        # Insure the params argument is an array reference if the caller left it off.
2462        if (! defined($params)) {
2463            $params = [];
2464        }
2465        # Declare the return variable.
2466        my $retVal;
2467        # Find out if we're counting an entity or a relationship.
2468        my $countedField;
2469        if ($self->IsEntity($objectNames->[0])) {
2470            $countedField = "id";
2471        } else {
2472            # For a relationship we count the to-link because it's usually more
2473            # numerous. Note we're automatically converting to the SQL form
2474            # of the field name (to_link vs. to-link).
2475            $countedField = "to_link";
2476        }
2477        # Create the SQL command suffix to get the desired records.
2478        my ($suffix, $mappedNameListRef, $mappedNameHashRef) = $self->_SetupSQL($objectNames,
2479                                                                                $filter);
2480        # Prefix it with text telling it we want a record count.
2481        my $firstObject = $mappedNameListRef->[0];
2482        my $command = "SELECT COUNT($firstObject.$countedField) $suffix";
2483        # Prepare and execute the command.
2484        my $sth = $self->_GetStatementHandle($command, $params);
2485        # Get the count value.
2486        ($retVal) = $sth->fetchrow_array();
2487        # Check for a problem.
2488        if (! defined($retVal)) {
2489            if ($sth->err) {
2490                # Here we had an SQL error.
2491                Confess("Error retrieving row count: " . $sth->errstr());
2492            } else {
2493                # Here we have no result.
2494                Confess("No result attempting to retrieve row count.");
2495            }
2496        }
2497        # Return the result.
2498        return $retVal;
2499    }
2500    
2501    =head3 ComputeObjectSentence
2502    
2503        my $sentence = $erdb->ComputeObjectSentence($objectName);
2504    
2505    Check an object name, and if it is a relationship convert it to a relationship sentence.
2506    
2507    =over 4
2508    
2509    =item objectName
2510    
2511    Name of the entity or relationship.
2512    
2513    =item RETURN
2514    
2515    Returns a string containing the entity name or a relationship sentence.
2516    
2517    =back
2518    
2519    =cut
2520    
2521    sub ComputeObjectSentence {
2522        # Get the parameters.
2523        my ($self, $objectName) = @_;
2524        # Set the default return value.
2525        my $retVal = $objectName;
2526        # Look for the object as a relationship.
2527        my $relTable = $self->{_metaData}->{Relationships};
2528        if (exists $relTable->{$objectName}) {
2529            # Get the relationship sentence.
2530            $retVal = _ComputeRelationshipSentence($objectName, $relTable->{$objectName});
2531        }
2532        # Return the result.
2533        return $retVal;
2534    }
2535    
2536    =head3 DumpRelations
2537    
2538        $erdb->DumpRelations($outputDirectory);
2539    
2540    Write the contents of all the relations to tab-delimited files in the specified directory.
2541    Each file will have the same name as the relation dumped, with an extension of DTX.
2542    
2543    =over 4
2544    
2545    =item outputDirectory
2546    
2547    Name of the directory into which the relation files should be dumped.
2548    
2549    =back
2550    
2551    =cut
2552    
2553    sub DumpRelations {
2554        # Get the parameters.
2555        my ($self, $outputDirectory) = @_;
2556        # Now we need to run through all the relations. First, we loop through the entities.
2557        my $metaData = $self->{_metaData};
2558        my $entities = $metaData->{Entities};
2559        for my $entityName (keys %{$entities}) {
2560            my $entityStructure = $entities->{$entityName};
2561            # Get the entity's relations.
2562            my $relationList = $entityStructure->{Relations};
2563            # Loop through the relations, dumping them.
2564            for my $relationName (keys %{$relationList}) {
2565                my $relation = $relationList->{$relationName};
2566                $self->_DumpRelation($outputDirectory, $relationName, $relation);
2567            }
2568        }
2569        # Next, we loop through the relationships.
2570        my $relationships = $metaData->{Relationships};
2571        for my $relationshipName (keys %{$relationships}) {
2572            my $relationshipStructure = $relationships->{$relationshipName};
2573            # Dump this relationship's relation.
2574            $self->_DumpRelation($outputDirectory, $relationshipName, $relationshipStructure->{Relations}->{$relationshipName});
2575        }
2576    }
2577    
2578    =head3 InsertValue
2579    
2580        $erdb->InsertValue($entityID, $fieldName, $value);
2581    
2582    This method will insert a new value into the database. The value must be one
2583    associated with a secondary relation, since primary values cannot be inserted:
2584    they occur exactly once. Secondary values, on the other hand, can be missing
2585    or multiply-occurring.
2586    
2587    =over 4
2588    
2589    =item entityID
2590    
2591    ID of the object that is to receive the new value.
2592    
2593    =item fieldName
2594    
2595    Field name for the new value-- this includes the entity name, since
2596    field names are of the format I<objectName>C<(>I<fieldName>C<)>.
2597    
2598    =item value
2599    
2600    New value to be put in the field.
2601    
2602    =back
2603    
2604    =cut
2605    
2606    sub InsertValue {
2607        # Get the parameters.
2608        my ($self, $entityID, $fieldName, $value) = @_;
2609        # Parse the entity name and the real field name.
2610        if ($fieldName =~ /^([^(]+)\(([^)]+)\)/) {
2611            my $entityName = $1;
2612            my $fieldTitle = $2;
2613            # Get its descriptor.
2614            if (!$self->IsEntity($entityName)) {
2615                Confess("$entityName is not a valid entity.");
2616            } else {
2617                my $entityData = $self->{_metaData}->{Entities}->{$entityName};
2618                # Find the relation containing this field.
2619                my $fieldHash = $entityData->{Fields};
2620                if (! exists $fieldHash->{$fieldTitle}) {
2621                    Confess("$fieldTitle not found in $entityName.");
2622                } else {
2623                    my $relation = $fieldHash->{$fieldTitle}->{relation};
2624                    if ($relation eq $entityName) {
2625                        Confess("Cannot do InsertValue on primary field $fieldTitle of $entityName.");
2626                    } else {
2627                        # Now we can create an INSERT statement.
2628                        my $dbh = $self->{_dbh};
2629                        my $fixedName = _FixName($fieldTitle);
2630                        my $statement = "INSERT INTO $relation (id, $fixedName) VALUES(?, ?)";
2631                        # Execute the command.
2632                        $dbh->SQL($statement, 0, $entityID, $value);
2633                    }
2634                }
2635            }
2636        } else {
2637            Confess("$fieldName is not a valid field name.");
2638        }
2639    }
2640    
2641    =head3 InsertObject
2642    
2643        $erdb->InsertObject($objectType, \%fieldHash);
2644    
2645    Insert an object into the database. The object is defined by a type name and then a hash
2646    of field names to values. Field values in the primary relation are represented by scalars.
2647    (Note that for relationships, the primary relation is the B<only> relation.)
2648    Field values for the other relations comprising the entity are always list references. For
2649    example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases
2650    C<ZP_00210270.1> and C<gi|46206278>.
2651    
2652        $erdb->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']});
2653    
2654    The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
2655    property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
2656    
2657        $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'});
2658    
2659    =over 4
2660    
2661    =item newObjectType
2662    
2663    Type name of the object to insert.
2664    
2665    =item fieldHash
2666    
2667    Hash of field names to values.
2668    
2669    =back
2670    
2671    =cut
2672    
2673    sub InsertObject {
2674        # Get the parameters.
2675        my ($self, $newObjectType, $fieldHash) = @_;
2676        # Denote that so far we appear successful.
2677        my $retVal = 1;
2678        # Get the database handle.
2679        my $dbh = $self->{_dbh};
2680        # Get the relation list.
2681        my $relationTable = $self->_GetRelationTable($newObjectType);
2682        # Loop through the relations. We'll build insert statements for each one. If a relation is
2683        # secondary, we may end up generating multiple insert statements. If an error occurs, we
2684        # stop the loop.
2685        my @relationList = keys %{$relationTable};
2686        for (my $i = 0; $retVal && $i <= $#relationList; $i++) {
2687            my $relationName = $relationList[$i];
2688            my $relationDefinition = $relationTable->{$relationName};
2689            # Get the relation's fields. For each field we will collect a value in the corresponding
2690            # position of the @valueList array. If one of the fields is missing, we will add it to the
2691            # @missing list.
2692            my @fieldList = @{$relationDefinition->{Fields}};
2693            my @fieldNameList = ();
2694            my @valueList = ();
2695            my @missing = ();
2696            my $recordCount = 1;
2697            for my $fieldDescriptor (@fieldList) {
2698                # Get the field name and save it. Note we need to fix it up so the hyphens
2699                # are converted to underscores.
2700                my $fieldName = $fieldDescriptor->{name};
2701                push @fieldNameList, _FixName($fieldName);
2702                # Look for the named field in the incoming structure. Note that we are looking
2703                # for the real field name, not the fixed-up one!
2704                if (exists $fieldHash->{$fieldName}) {
2705                    # Here we found the field. Stash it in the value list.
2706                    my $value = $fieldHash->{$fieldName};
2707                    push @valueList, $value;
2708                    # If the value is a list, we may need to increment the record count.
2709                    if (ref $value eq "ARRAY") {
2710                        my $thisCount = @{$value};
2711                        if ($recordCount == 1) {
2712                            # Here we have our first list, so we save its count.
2713                            $recordCount = $thisCount;
2714                        } elsif ($recordCount != $thisCount) {
2715                            # Here we have a second list, so its length has to match the
2716                            # previous lists.
2717                            Trace("Field $value in new $newObjectType object has an invalid list length $thisCount. Expected $recordCount.") if T(0);
2718                            $retVal = 0;
2719                        }
2720                    }
2721                } else {
2722                    # Here the field is not present. Flag it as missing.
2723                    push @missing, $fieldName;
2724                }
2725            }
2726            # If we are the primary relation, add the new-record flag.
2727            if ($relationName eq $newObjectType) {
2728                push @valueList, 1;
2729                push @fieldNameList, "new_record";
2730            }
2731            # Only proceed if there are no missing fields.
2732            if (@missing > 0) {
2733                Trace("Relation $relationName for $newObjectType skipped due to missing fields: " .
2734                    join(' ', @missing)) if T(1);
2735            } else {
2736                # Build the INSERT statement.
2737                my $statement = "INSERT INTO $relationName (" . join (', ', @fieldNameList) .
2738                    ") VALUES (";
2739                # Create a marker list of the proper size and put it in the statement.
2740                my @markers = ();
2741                while (@markers < @fieldNameList) { push @markers, '?'; }
2742                $statement .= join(', ', @markers) . ")";
2743                # We have the insert statement, so prepare it.
2744                my $sth = $dbh->prepare_command($statement);
2745                Trace("Insert statement prepared: $statement") if T(3);
2746                # Now we loop through the values. If a value is scalar, we use it unmodified. If it's
2747                # a list, we use the current element. The values are stored in the @parameterList array.
2748                my $done = 0;
2749                for (my $i = 0; $i < $recordCount; $i++) {
2750                    # Clear the parameter list array.
2751                    my @parameterList = ();
2752                    # Loop through the values.
2753                    for my $value (@valueList) {
2754                        # Check to see if this is a scalar value.
2755                        if (ref $value eq "ARRAY") {
2756                            # Here we have a list value. Pull the current entry.
2757                            push @parameterList, $value->[$i];
2758                        } else {
2759                            # Here we have a scalar value. Use it unmodified.
2760                            push @parameterList, $value;
2761                        }
2762                    }
2763                    # Execute the INSERT statement with the specified parameter list.
2764                    $retVal = $sth->execute(@parameterList);
2765                    if (!$retVal) {
2766                        my $errorString = $sth->errstr();
2767                        Confess("Error inserting into $relationName: $errorString");
2768                    } else {
2769                        Trace("Insert successful using $parameterList[0].") if T(3);
2770                    }
2771                }
2772            }
2773        }
2774        # Return a 1 for backward compatability.
2775        return 1;
2776    }
2777    
2778    =head3 UpdateEntity
2779    
2780        $erdb->UpdateEntity($entityName, $id, \%fields);
2781    
2782    Update the values of an entity. This is an unprotected update, so it should only be
2783    done if the database resides on a database server.
2784    
2785    =over 4
2786    
2787    =item entityName
2788    
2789    Name of the entity to update. (This is the entity type.)
2790    
2791    =item id
2792    
2793    ID of the entity to update. If no entity exists with this ID, an error will be thrown.
2794    
2795    =item fields
2796    
2797    Reference to a hash mapping field names to their new values. All of the fields named
2798    must be in the entity's primary relation, and they cannot any of them be the ID field.
2799    
2800    =back
2801    
2802    =cut
2803    
2804    sub UpdateEntity {
2805        # Get the parameters.
2806        my ($self, $entityName, $id, $fields) = @_;
2807        # Get a list of the field names being updated.
2808        my @fieldList = keys %{$fields};
2809        # Verify that the fields exist.
2810        my $checker = $self->GetFieldTable($entityName);
2811        for my $field (@fieldList) {
2812            if ($field eq 'id') {
2813                Confess("Cannot update the ID field for entity $entityName.");
2814            } elsif ($checker->{$field}->{relation} ne $entityName) {
2815                Confess("Cannot find $field in primary relation of $entityName.");
2816            }
2817        }
2818        # Build the SQL statement.
2819        my @sets = ();
2820        my @valueList = ();
2821        for my $field (@fieldList) {
2822            push @sets, _FixName($field) . " = ?";
2823            push @valueList, $fields->{$field};
2824        }
2825        my $command = "UPDATE $entityName SET " . join(", ", @sets) . " WHERE id = ?";
2826        # Add the ID to the list of binding values.
2827        push @valueList, $id;
2828        # Call SQL to do the work.
2829        my $rows = $self->{_dbh}->SQL($command, 0, @valueList);
2830        # Check for errors.
2831        if ($rows == 0) {
2832            Confess("Entity $id of type $entityName not found.");
2833        }
2834    }
2835    
2836    =head3 LoadTable
2837    
2838        my $results = $erdb->LoadTable($fileName, $relationName, %options);
2839    
2840    Load data from a tab-delimited file into a specified table, optionally re-creating the table
2841    first.
2842    
2843    =over 4
2844    
2845    =item fileName
2846    
2847    Name of the file from which the table data should be loaded.
2848    
2849    =item relationName
2850    
2851    Name of the relation to be loaded. This is the same as the table name.
2852    
2853    =item options
2854    
2855    A hash of load options.
2856    
2857    =item RETURN
2858    
2859    Returns a statistical object containing a list of the error messages.
2860    
2861    =back
2862    
2863    The permissible options are as follows.
2864    
2865    =over 4
2866    
2867    =item truncate
2868    
2869    If TRUE, then the table will be erased before loading.
2870    
2871    =item mode
2872    
2873    Mode in which the load should operate, either C<low_priority> or C<concurrent>.
2874    This option is only applicable to a MySQL database.
2875    
2876    =item partial
2877    
2878    If TRUE, then it is assumed that this is a partial load, and the table will not
2879    be analyzed and compacted at the end.
2880    
2881    =back
2882    
2883    =cut
2884    sub LoadTable {
2885        # Get the parameters.
2886        my ($self, $fileName, $relationName, %options) = @_;
2887        # Create the statistical return object.
2888        my $retVal = _GetLoadStats();
2889        # Trace the fact of the load.
2890        Trace("Loading table $relationName from $fileName") if T(2);
2891        # Get the database handle.
2892        my $dbh = $self->{_dbh};
2893        # Get the input file size.
2894        my $fileSize = -s $fileName;
2895        # Get the relation data.
2896        my $relation = $self->_FindRelation($relationName);
2897        # Check the truncation flag.
2898        if ($options{truncate}) {
2899            Trace("Creating table $relationName") if T(2);
2900            # Compute the row count estimate. We take the size of the load file,
2901            # divide it by the estimated row size, and then multiply by 2 to
2902            # leave extra room. We postulate a minimum row count of 1000 to
2903            # prevent problems with incoming empty load files.
2904            my $rowSize = $self->EstimateRowSize($relationName);
2905            my $estimate = $fileSize * 8 / $rowSize;
2906            if ($estimate < 1000) {
2907                $estimate = 1000;
2908            }
2909            # Re-create the table without its index.
2910            $self->CreateTable($relationName, 0, $estimate);
2911            # If this is a pre-index DBMS, create the index here.
2912            if ($dbh->{_preIndex}) {
2913                eval {
2914                    $self->CreateIndex($relationName);
2915                };
2916                if ($@) {
2917                    $retVal->AddMessage($@);
2918                }
2919            }
2920        }
2921        # Load the table.
2922        my $rv;
2923        eval {
2924            $rv = $dbh->load_table(file => $fileName, tbl => $relationName, style => $options{mode});
2925        };
2926        if (!defined $rv) {
2927            $retVal->AddMessage($@) if ($@);
2928            $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2929            Trace("Table load failed for $relationName.") if T(1);
2930        } else {
2931            # Here we successfully loaded the table.
2932            $retVal->Add("tables");
2933            my $size = -s $fileName;
2934            Trace("$size bytes loaded into $relationName.") if T(2);
2935            $retVal->Add("bytes", $size);
2936            # If we're rebuilding, we need to create the table indexes.
2937            if ($options{truncate}) {
2938                # Indexes are created here for PostGres. For PostGres, indexes are
2939                # best built at the end. For MySQL, the reverse is true.
2940                if (! $dbh->{_preIndex}) {
2941                    eval {
2942                        $self->CreateIndex($relationName);
2943                    };
2944                    if ($@) {
2945                        $retVal->AddMessage($@);
2946                    }
2947                }
2948                # The full-text index (if any) is always built last, even for MySQL.
2949                # First we need to see if this table has a full-text index. Only
2950                # primary relations are allowed that privilege.
2951                Trace("Checking for full-text index on $relationName.") if T(2);
2952                if ($self->_IsPrimary($relationName)) {
2953                    $self->CreateSearchIndex($relationName);
2954                }
2955            }
2956        }
2957        # Analyze the table to improve performance.
2958        if (! $options{partial}) {
2959            Trace("Analyzing and compacting $relationName.") if T(3);
2960            $dbh->vacuum_it($relationName);
2961        }
2962        Trace("$relationName load completed.") if T(3);
2963        # Return the statistics.
2964        return $retVal;
2965    }
2966    
2967    =head3 CreateSearchIndex
2968    
2969        $erdb->CreateSearchIndex($objectName);
2970    
2971    Check for a full-text search index on the specified entity or relationship object, and
2972    if one is required, rebuild it.
2973    
2974    =over 4
2975    
2976    =item objectName
2977    
2978    Name of the entity or relationship to be indexed.
2979    
2980    =back
2981    
2982    =cut
2983    
2984    sub CreateSearchIndex {
2985        # Get the parameters.
2986        my ($self, $objectName) = @_;
2987        # Get the relation's entity/relationship structure.
2988        my $structure = $self->_GetStructure($objectName);
2989        # Get the database handle.
2990        my $dbh = $self->{_dbh};
2991        Trace("Checking for search fields in $objectName.") if T(3);
2992        # Check for a searchable fields list.
2993        if (exists $structure->{searchFields}) {
2994            # Here we know that we need to create a full-text search index.
2995            # Get an SQL-formatted field name list.
2996            my $fields = join(", ", _FixNames(@{$structure->{searchFields}}));
2997            # Create the index. If it already exists, it will be dropped.
2998            $dbh->create_index(tbl => $objectName, idx => "search_idx",
2999                               flds => $fields, kind => 'fulltext');
3000            Trace("Index created for $fields in $objectName.") if T(2);
3001        }
3002    }
3003    
3004    =head3 DropRelation
3005    
3006        $erdb->DropRelation($relationName);
3007    
3008    Physically drop a relation from the database.
3009    
3010    =over 4
3011    
3012    =item relationName
3013    
3014    Name of the relation to drop. If it does not exist, this method will have
3015    no effect.
3016    
3017    =back
3018    
3019    =cut
3020    
3021    sub DropRelation {
3022        # Get the parameters.
3023        my ($self, $relationName) = @_;
3024        # Get the database handle.
3025        my $dbh = $self->{_dbh};
3026        # Drop the relation. The method used here has no effect if the relation
3027        # does not exist.
3028        Trace("Invoking DB Kernel to drop $relationName.") if T(3);
3029        $dbh->drop_table(tbl => $relationName);
3030    }
3031    
3032    =head3 MatchSqlPattern
3033    
3034        my $matched = ERDB::MatchSqlPattern($value, $pattern);
3035    
3036    Determine whether or not a specified value matches an SQL pattern. An SQL
3037    pattern has two wild card characters: C<%> that matches multiple characters,
3038    and C<_> that matches a single character. These can be escaped using a
3039    backslash (C<\>). We pull this off by converting the SQL pattern to a
3040    PERL regular expression. As per SQL rules, the match is case-insensitive.
3041    
3042    =over 4
3043    
3044    =item value
3045    
3046    Value to be matched against the pattern. Note that an undefined or empty
3047    value will not match anything.
3048    
3049    =item pattern
3050    
3051    SQL pattern against which to match the value. An undefined or empty pattern will
3052    match everything.
3053    
3054    =item RETURN
3055    
3056    Returns TRUE if the value and pattern match, else FALSE.
3057    
3058    =back
3059    
3060    =cut
3061    
3062    sub MatchSqlPattern {
3063        # Get the parameters.
3064        my ($value, $pattern) = @_;
3065        # Declare the return variable.
3066        my $retVal;
3067        # Insure we have a pattern.
3068        if (! defined($pattern) || $pattern eq "") {
3069            $retVal = 1;
3070        } else {
3071            # Break the pattern into pieces around the wildcard characters. Because we
3072            # use parentheses in the split function's delimiter expression, we'll get
3073            # list elements for the delimiters as well as the rest of the string.
3074            my @pieces = split /([_%]|\\[_%])/, $pattern;
3075            # Check some fast special cases.
3076            if ($pattern eq '%') {
3077                # A null pattern matches everything.
3078                $retVal = 1;
3079            } elsif (@pieces == 1) {
3080                # No wildcards, so we have a literal comparison. Note we're case-insensitive.
3081                $retVal = (lc($value) eq lc($pattern));
3082            } elsif (@pieces == 2 && $pieces[1] eq '%') {
3083                # A wildcard at the end, so we have a substring match. This is also case-insensitive.
3084                $retVal = (lc(substr($value, 0, length($pieces[0]))) eq lc($pieces[0]));
3085            } else {
3086                # Okay, we have to do it the hard way. Convert each piece to a PERL pattern.
3087                my $realPattern = "";
3088                for my $piece (@pieces) {
3089                    # Determine the type of piece.
3090                    if ($piece eq "") {
3091                        # Empty pieces are ignored.
3092                    } elsif ($piece eq "%") {
3093                        # Here we have a multi-character wildcard. Note that it can match
3094                        # zero or more characters.
3095                        $realPattern .= ".*"
3096                    } elsif ($piece eq "_") {
3097                        # Here we have a single-character wildcard.
3098                        $realPattern .= ".";
3099                    } elsif ($piece eq "\\%" || $piece eq "\\_") {
3100                        # This is an escape sequence (which is a rare thing, actually).
3101                        $realPattern .= substr($piece, 1, 1);
3102                    } else {
3103                        # Here we have raw text.
3104                        $realPattern .= quotemeta($piece);
3105                    }
3106                }
3107                # Do the match.
3108                $retVal = ($value =~ /^$realPattern$/i ? 1 : 0);
3109            }
3110        }
3111        # Return the result.
3112        return $retVal;
3113    }
3114    
3115    =head3 GetEntity
3116    
3117        my $entityObject = $erdb->GetEntity($entityType, $ID);
3118    
3119    Return an object describing the entity instance with a specified ID.
3120    
3121    =over 4
3122    
3123    =item entityType
3124    
3125    Entity type name.
3126    
3127    =item ID
3128    
3129    ID of the desired entity.
3130    
3131    =item RETURN
3132    
3133    Returns a B<ERDBObject> representing the desired entity instance, or an undefined value if no
3134    instance is found with the specified key.
3135    
3136    =back
3137    
3138    =cut
3139    
3140    sub GetEntity {
3141        # Get the parameters.
3142        my ($self, $entityType, $ID) = @_;
3143        # Create a query.
3144        my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);
3145        # Get the first (and only) object.
3146        my $retVal = $query->Fetch();
3147        # Return the result.
3148        return $retVal;
3149    }
3150    
3151    =head3 GetChoices
3152    
3153        my @values = $erdb->GetChoices($entityName, $fieldName);
3154    
3155    Return a list of all the values for the specified field that are represented in the
3156    specified entity.
3157    
3158    Note that if the field is not indexed, then this will be a very slow operation.
3159    
3160    =over 4
3161    
3162    =item entityName
3163    
3164    Name of an entity in the database.
3165    
3166    =item fieldName
3167    
3168    Name of a field belonging to the entity. This is a raw field name without
3169    the standard parenthesized notation used in most calls.
3170    
3171    =item RETURN
3172    
3173    Returns a list of the distinct values for the specified field in the database.
3174    
3175    =back
3176    
3177    =cut
3178    
3179    sub GetChoices {
3180        # Get the parameters.
3181        my ($self, $entityName, $fieldName) = @_;
3182        # Declare the return variable.
3183        my @retVal;
3184        # Get the entity data structure.
3185        my $entityData = $self->_GetStructure($entityName);
3186        # Get the field.
3187        my $fieldHash = $entityData->{Fields};
3188        if (! exists $fieldHash->{$fieldName}) {
3189            Confess("$fieldName not found in $entityName.");
3190        } else {
3191            # Get the name of the relation containing the field.
3192            my $relation = $fieldHash->{$fieldName}->{relation};
3193            # Fix up the field name.
3194            my $realName = _FixName($fieldName);
3195            # Get the database handle.
3196            my $dbh = $self->{_dbh};
3197            # Query the database.
3198            my $results = $dbh->SQL("SELECT DISTINCT $realName FROM $relation");
3199            # Clean the results. They are stored as a list of lists, and we just want the one list.
3200            @retVal = sort map { $_->[0] } @{$results};
3201        }
3202        # Return the result.
3203        return @retVal;
3204    }
3205    
3206    =head3 GetEntityValues
3207    
3208        my @values = $erdb->GetEntityValues($entityType, $ID, \@fields);
3209    
3210    Return a list of values from a specified entity instance. If the entity instance
3211    does not exist, an empty list is returned.
3212    
3213    =over 4
3214    
3215    =item entityType
3216    
3217    Entity type name.
3218    
3219    =item ID
3220    
3221    ID of the desired entity.
3222    
3223    =item fields
3224    
3225    List of field names, each of the form I<objectName>C<(>I<fieldName>C<)>.
3226    
3227    =item RETURN
3228    
3229    Returns a flattened list of the values of the specified fields for the specified entity.
3230    
3231    =back
3232    
3233    =cut
3234    
3235    sub GetEntityValues {
3236        # Get the parameters.
3237        my ($self, $entityType, $ID, $fields) = @_;
3238        # Get the specified entity.
3239        my $entity = $self->GetEntity($entityType, $ID);
3240        # Declare the return list.
3241        my @retVal = ();
3242        # If we found the entity, push the values into the return list.
3243        if ($entity) {
3244            push @retVal, $entity->Values($fields);
3245        }
3246        # Return the result.
3247        return @retVal;
3248    }
3249    
3250    =head3 GetAll
3251    
3252        my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count);
3253    
3254    Return a list of values taken from the objects returned by a query. The first three
3255    parameters correspond to the parameters of the L</Get> method. The final parameter is
3256    a list of the fields desired from each record found by the query. The field name
3257    syntax is the standard syntax used for fields in the B<ERDB> system--
3258    B<I<objectName>(I<fieldName>)>-- where I<objectName> is the name of the relevant entity
3259    or relationship and I<fieldName> is the name of the field.
3260    
3261    The list returned will be a list of lists. Each element of the list will contain
3262    the values returned for the fields specified in the fourth parameter. If one of the
3263    fields specified returns multiple values, they are flattened in with the rest. For
3264    example, the following call will return a list of the features in a particular
3265    spreadsheet cell, and each feature will be represented by a list containing the
3266    feature ID followed by all of its essentiality determinations.
3267    
3268        @query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(essential)']);
3269    
3270    =over 4
3271    
3272    =item objectNames
3273    
3274    List containing the names of the entity and relationship objects to be retrieved.
3275    
3276    =item filterClause
3277    
3278    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
3279    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
3280    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
3281    parameter list as additional parameters. The fields in a filter clause can come from primary
3282    entity relations, relationship relations, or secondary entity relations; however, all of the
3283    entities and relationships involved must be included in the list of object names.
3284    
3285    =item parameterList
3286    
3287    List of the parameters to be substituted in for the parameters marks in the filter clause.
3288    
3289    =item fields
3290    
3291    List of the fields to be returned in each element of the list returned.
3292    
3293    =item count
3294    
3295    Maximum number of records to return. If omitted or 0, all available records will be returned.
3296    
3297    =item RETURN
3298    
3299    Returns a list of list references. Each element of the return list contains the values for the
3300    fields specified in the B<fields> parameter.
3301    
3302    =back
3303    
3304    =cut
3305    #: Return Type @@;
3306    sub GetAll {
3307        # Get the parameters.
3308        my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
3309        # Translate the parameters from a list reference to a list. If the parameter
3310        # list is a scalar we convert it into a singleton list.
3311        my @parmList = ();
3312        if (ref $parameterList eq "ARRAY") {
3313            Trace("GetAll parm list is an array.") if T(4);
3314            @parmList = @{$parameterList};
3315        } else {
3316            Trace("GetAll parm list is a scalar: $parameterList.") if T(4);
3317            push @parmList, $parameterList;
3318        }
3319        # Insure the counter has a value.
3320        if (!defined $count) {
3321            $count = 0;
3322        }
3323        # Add the row limit to the filter clause.
3324        if ($count > 0) {
3325            $filterClause .= " LIMIT $count";
3326        }
3327        # Create the query.
3328        my $query = $self->Get($objectNames, $filterClause, \@parmList);
3329        # Set up a counter of the number of records read.
3330        my $fetched = 0;
3331        # Loop through the records returned, extracting the fields. Note that if the
3332        # counter is non-zero, we stop when the number of records read hits the count.
3333        my @retVal = ();
3334        while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {
3335            my @rowData = $row->Values($fields);
3336            push @retVal, \@rowData;
3337            $fetched++;
3338        }
3339        Trace("$fetched rows returned in GetAll.") if T(SQL => 4);
3340        # Return the resulting list.
3341        return @retVal;
3342    }
3343    
3344    =head3 Exists
3345    
3346        my $found = $sprout->Exists($entityName, $entityID);
3347    
3348    Return TRUE if an entity exists, else FALSE.
3349    
3350    =over 4
3351    
3352    =item entityName
3353    
3354    Name of the entity type (e.g. C<Feature>) relevant to the existence check.
3355    
3356    =item entityID
3357    
3358    ID of the entity instance whose existence is to be checked.
3359    
3360    =item RETURN
3361    
3362    Returns TRUE if the entity instance exists, else FALSE.
3363    
3364    =back
3365    
3366    =cut
3367    #: Return Type $;
3368    sub Exists {
3369        # Get the parameters.
3370        my ($self, $entityName, $entityID) = @_;
3371        # Check for the entity instance.
3372        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
3373        my $testInstance = $self->GetEntity($entityName, $entityID);
3374        # Return an existence indicator.
3375        my $retVal = ($testInstance ? 1 : 0);
3376        return $retVal;
3377    }
3378    
3379    =head3 EstimateRowSize
3380    
3381        my $rowSize = $erdb->EstimateRowSize($relName);
3382    
3383    Estimate the row size of the specified relation. The estimated row size is computed by adding
3384    up the average length for each data type.
3385    
3386    =over 4
3387    
3388    =item relName
3389    
3390    Name of the relation whose estimated row size is desired.
3391    
3392    =item RETURN
3393    
3394    Returns an estimate of the row size for the specified relation.
3395    
3396    =back
3397    
3398    =cut
3399    #: Return Type $;
3400    sub EstimateRowSize {
3401        # Get the parameters.
3402        my ($self, $relName) = @_;
3403        # Declare the return variable.
3404        my $retVal = 0;
3405        # Find the relation descriptor.
3406        my $relation = $self->_FindRelation($relName);
3407        # Get the list of fields.
3408        for my $fieldData (@{$relation->{Fields}}) {
3409            # Get the field type and add its length.
3410            my $fieldLen = $TypeTable{$fieldData->{type}}->{avgLen};
3411            $retVal += $fieldLen;
3412        }
3413        # Return the result.
3414        return $retVal;
3415    }
3416    
3417    =head3 GetFieldTable
3418    
3419        my $fieldHash = $self->GetFieldTable($objectnName);
3420    
3421    Get the field structure for a specified entity or relationship.
3422    
3423    =over 4
3424    
3425    =item objectName
3426    
3427    Name of the desired entity or relationship.
3428    
3429    =item RETURN
3430    
3431    The table containing the field descriptors for the specified object.
3432    
3433    =back
3434    
3435    =cut
3436    
3437    sub GetFieldTable {
3438        # Get the parameters.
3439        my ($self, $objectName) = @_;
3440        # Get the descriptor from the metadata.
3441        my $objectData = $self->_GetStructure($objectName);
3442        # Return the object's field table.
3443        return $objectData->{Fields};
3444    }
3445    
3446    =head3 SplitKeywords
3447    
3448        my @keywords = ERDB::SplitKeywords($keywordString);
3449    
3450    This method returns a list of the positive keywords in the specified
3451    keyword string. All of the operators will have been stripped off,
3452    and if the keyword is preceded by a minus operator (C<->), it will
3453    not be in the list returned. The idea here is to get a list of the
3454    keywords the user wants to see. The list will be processed to remove
3455    duplicates.
3456    
3457    It is possible to create a string that confuses this method. For example
3458    
3459        frog toad -frog
3460    
3461    would return both C<frog> and C<toad>. If this is a problem we can deal
3462    with it later.
3463    
3464    =over 4
3465    
3466    =item keywordString
3467    
3468    The keyword string to be parsed.
3469    
3470    =item RETURN
3471    
3472    Returns a list of the words in the keyword string the user wants to
3473    see.
3474    
3475    =back
3476    
3477    =cut
3478    
3479    sub SplitKeywords {
3480        # Get the parameters.
3481        my ($keywordString) = @_;
3482        # Make a safety copy of the string. (This helps during debugging.)
3483        my $workString = $keywordString;
3484        # Convert operators we don't care about to spaces.
3485        $workString =~ tr/+"()<>/ /;
3486        # Split the rest of the string along space boundaries. Note that we
3487        # eliminate any words that are zero length or begin with a minus sign.
3488        my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
3489        # Use a hash to remove duplicates.
3490        my %words = map { $_ => 1 } @wordList;
3491        # Return the result.
3492        return sort keys %words;
3493    }
3494    
3495    =head3 ValidateFieldName
3496    
3497        my $okFlag = ERDB::ValidateFieldName($fieldName);
3498    
3499    Return TRUE if the specified field name is valid, else FALSE. Valid field names must
3500    be hyphenated words subject to certain restrictions.
3501    
3502    =over 4
3503    
3504    =item fieldName
3505    
3506    Field name to be validated.
3507    
3508    =item RETURN
3509    
3510    Returns TRUE if the field name is valid, else FALSE.
3511    
3512    =back
3513    
3514    =cut
3515    
3516    sub ValidateFieldName {
3517        # Get the parameters.
3518        my ($fieldName) = @_;
3519        # Declare the return variable. The field name is valid until we hear
3520        # differently.
3521        my $retVal = 1;
3522        # Compute the maximum name length.
3523        my $maxLen = $TypeTable{'name-string'}->{maxLen};
3524        # Look for bad stuff in the name.
3525        if ($fieldName =~ /--/) {
3526            # Here we have a doubled minus sign.
3527            Trace("Field name $fieldName has a doubled hyphen.") if T(1);
3528            $retVal = 0;
3529        } elsif ($fieldName !~ /^[A-Za-z]/) {
3530            # Here the field name is missing the initial letter.
3531            Trace("Field name $fieldName does not begin with a letter.") if T(1);
3532            $retVal = 0;
3533        } elsif (length($fieldName) > $maxLen) {
3534            # Here the field name is too long.
3535            Trace("Maximum field name length is $maxLen. Field name must be truncated to " . substr($fieldName,0, $maxLen) . ".");
3536        } else {
3537            # Strip out the minus signs. Everything remaining must be a letter,
3538            # underscore, or digit.
3539            my $strippedName = $fieldName;
3540            $strippedName =~ s/-//g;
3541            if ($strippedName !~ /^(\w|\d)+$/) {
3542                Trace("Field name $fieldName contains illegal characters.") if T(1);
3543                $retVal = 0;
3544            }
3545        }
3546        # Return the result.
3547        return $retVal;
3548    }
3549    
3550    =head3 ReadMetaXML
3551    
3552        my $rawMetaData = ERDB::ReadDBD($fileName);
3553    
3554    This method reads a raw database definition XML file and returns it.
3555    Normally, the metadata used by the ERDB system has been processed and
3556    modified to make it easier to load and retrieve the data; however,
3557    this method can be used to get the data in its raw form.
3558    
3559    =over 4
3560    
3561    =item fileName
3562    
3563    Name of the XML file to read.
3564    
3565    =item RETURN
3566    
3567    Returns a hash reference containing the raw XML data from the specified file.
3568    
3569    =back
3570    
3571    =cut
3572    
3573    sub ReadMetaXML {
3574        # Get the parameters.
3575        my ($fileName) = @_;
3576        # Read the XML.
3577        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
3578        Trace("XML metadata loaded from file $fileName.") if T(1);
3579        # Return the result.
3580        return $retVal;
3581    }
3582    
3583    =head3 GetEntityFieldHash
3584    
3585        my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName);
3586    
3587    Get the field hash of the named entity in the specified raw XML structure.
3588    The field hash may not exist, in which case we need to create it.
3589    
3590    =over 4
3591    
3592    =item structure
3593    
3594    Raw XML structure defininng the database. This is not the run-time XML used by
3595    an ERDB object, since that has all sorts of optimizations built-in.
3596    
3597    =item entityName
3598    
3599    Name of the entity whose field structure is desired.
3600    
3601    =item RETURN
3602    
3603    Returns the field hash used to define the entity's fields.
3604    
3605    =back
3606    
3607    =cut
3608    
3609    sub GetEntityFieldHash {
3610        # Get the parameters.
3611        my ($structure, $entityName) = @_;
3612        # Get the entity structure.
3613        my $entityData = $structure->{Entities}->{$entityName};
3614        # Look for a field structure.
3615        my $retVal = $entityData->{Fields};
3616        # If it doesn't exist, create it.
3617        if (! defined($retVal)) {
3618            $entityData->{Fields} = {};
3619            $retVal = $entityData->{Fields};
3620        }
3621        # Return the result.
3622        return $retVal;
3623    }
3624    
3625    =head3 WriteMetaXML
3626    
3627        ERDB::WriteMetaXML($structure, $fileName);
3628    
3629    Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
3630    used to update the database definition. It must be used with care, however, since it
3631    will only work on a raw structure, not on the processed structure created by an ERDB
3632    constructor.
3633    
3634    =over 4
3635    
3636    =item structure
3637    
3638    XML structure to be written to the file.
3639    
3640    =item fileName
3641    
3642    Name of the output file to which the updated XML should be stored.
3643    
3644    =back
3645    
3646    =cut
3647    
3648    sub WriteMetaXML {
3649        # Get the parameters.
3650        my ($structure, $fileName) = @_;
3651        # Compute the output.
3652        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
3653        # Write it to the file.
3654        my $xmlOut = Open(undef, ">$fileName");
3655        print $xmlOut $fileString;
3656    }
3657    
3658    
3659    =head3 HTMLNote
3660    
3661    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
3662    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
3663    Except for C<[p]>, all the codes are closed by slash-codes. So, for
3664    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
3665    
3666        my $realHtml = ERDB::HTMLNote($dataString);
3667    
3668    =over 4
3669    
3670    =item dataString
3671    
3672    String to convert to HTML.
3673    
3674    =item RETURN
3675    
3676    An HTML string derived from the input string.
3677    
3678    =back
3679    
3680    =cut
3681    
3682    sub HTMLNote {
3683        # Get the parameter.
3684        my ($dataString) = @_;
3685        # HTML-escape the text.
3686