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

Diff of /Sprout/ERDB.pm

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

revision 1.5, Tue Apr 5 05:17:01 2005 UTC revision 1.83, Mon Jan 22 20:23:58 2007 UTC
# Line 1  Line 1 
1  package ERDB;  package ERDB;
2    
3          use strict;          use strict;
         use Carp;  
4          use Tracer;          use Tracer;
5          use DBKernel;      use DBrtns;
6          use Data::Dumper;          use Data::Dumper;
7          use XML::Simple;          use XML::Simple;
8          use DBQuery;          use DBQuery;
9          use DBObject;          use DBObject;
10          use Stats;          use Stats;
11          use Time::HiRes qw(gettimeofday);          use Time::HiRes qw(gettimeofday);
12        use Digest::MD5 qw(md5_base64);
13        use FIG;
14        use CGI;
15    
16  =head1 Entity-Relationship Database Package  =head1 Entity-Relationship Database Package
17    
# Line 33  Line 35 
35  relation that contains two fields-- the feature ID (C<id>) and the alias name (C<alias>).  relation that contains two fields-- the feature ID (C<id>) and the alias name (C<alias>).
36  The B<FEATURE> entity also contains an optional virulence number. This is implemented  The B<FEATURE> entity also contains an optional virulence number. This is implemented
37  as a separate relation C<FeatureVirulence> which contains an ID (C<id>) and a virulence number  as a separate relation C<FeatureVirulence> which contains an ID (C<id>) and a virulence number
38  (C<virulence>). If the virulence of a feature I<ABC> is known to be 6, there will be one row in the  (C<virulence>). If the virulence of a feature I<ABC> is known to be 6, there will be one row in
39  C<FeatureVirulence> relation possessing the value I<ABC> as its ID and 6 as its virulence number.  the C<FeatureVirulence> relation possessing the value I<ABC> as its ID and 6 as its virulence
40  If the virulence of I<ABC> is not known, there will not be any rows for it in C<FeatureVirulence>.  number. If the virulence of I<ABC> is not known, there will not be any rows for it in
41    C<FeatureVirulence>.
42    
43  Entities are connected by binary relationships implemented using single relations possessing the  Entities are connected by binary relationships implemented using single relations possessing the
44  same name as the relationship itself and that has an I<arity> of 1-to-1 (C<11>), 1-to-many (C<1M>),  same name as the relationship itself and that has an I<arity> of 1-to-1 (C<11>), 1-to-many (C<1M>),
# Line 57  Line 60 
60  B<start-position>, which indicates where in the contig that the sequence begins. This attribute  B<start-position>, which indicates where in the contig that the sequence begins. This attribute
61  is implemented as the C<start_position> field in the C<IsMadeUpOf> relation.  is implemented as the C<start_position> field in the C<IsMadeUpOf> relation.
62    
63  The database itself is described by an XML file using the F<ERDatabase.xsd> schema. In addition to  The database itself is described by an XML file. In addition to all the data required to define
64  all the data required to define the entities, relationships, and attributes, the schema provides  the entities, relationships, and attributes, the schema provides space for notes describing
65  space for notes describing the data and what it means. These notes are used by L</ShowMetaData>  the data and what it means. These notes are used by L</ShowMetaData> to generate documentation
66  to generate documentation for the database.  for the database.
67    
68    Special support is provided for text searching. An entity field can be marked as <em>searchable</em>,
69    in which case it will be used to generate a text search index in which the user searches for words
70    in the field instead of a particular field value.
71    
72  Finally, every entity and relationship object has a flag indicating if it is new or old. The object  Finally, every entity and relationship object has a flag indicating if it is new or old. The object
73  is considered I<old> if it was loaded by the L</LoadTables> method. It is considered I<new> if it  is considered I<old> if it was loaded by the L</LoadTables> method. It is considered I<new> if it
74  was inserted by the L</InsertObject> method.  was inserted by the L</InsertObject> method.
75    
76  To facilitate testing, the ERDB module supports automatic generation of test data. This process  =head2 XML Database Description
77  is described in the L</GenerateEntity> and L</GenerateConnection> methods, though it is not yet  
78  fully implemented.  =head3 Data Types
79    
80    The ERDB system supports the following data types. Note that there are numerous string
81    types depending on the maximum length. Some database packages limit the total number of
82    characters you have in an index key; to insure the database works in all environments,
83    the type of string should be the shortest one possible that supports all the known values.
84    
85    =over 4
86    
87    =item char
88    
89    single ASCII character
90    
91    =item int
92    
93    32-bit signed integer
94    
95    =item counter
96    
97    32-bit unsigned integer
98    
99    =item date
100    
101    64-bit unsigned integer, representing a PERL date/time value
102    
103    =item text
104    
105    long string; Text fields cannot be used in indexes or sorting and do not support the
106    normal syntax of filter clauses, but can be up to a billion character in length
107    
108    =item float
109    
110    double-precision floating-point number
111    
112    =item boolean
113    
114    single-bit numeric value; The value is stored as a 16-bit signed integer (for
115    compatability with certain database packages), but the only values supported are
116    0 and 1.
117    
118    =item id-string
119    
120    variable-length string, maximum 25 characters
121    
122    =item key-string
123    
124    variable-length string, maximum 40 characters
125    
126    =item name-string
127    
128    variable-length string, maximum 80 characters
129    
130    =item medium-string
131    
132    variable-length string, maximum 160 characters
133    
134    =item string
135    
136    variable-length string, maximum 255 characters
137    
138    =item hash-string
139    
140    variable-length string, maximum 22 characters
141    
142    =back
143    
144    The hash-string data type has a special meaning. The actual key passed into the loader will
145    be a string, but it will be digested into a 22-character MD5 code to save space. Although the
146    MD5 algorithm is not perfect, it is extremely unlikely two strings will have the same
147    digest. Therefore, it is presumed the keys will be unique. When the database is actually
148    in use, the hashed keys will be presented rather than the original values. For this reason,
149    they should not be used for entities where the key is meaningful.
150    
151    =head3 Global Tags
152    
153    The entire database definition must be inside a B<Database> tag. The display name of
154    the database is given by the text associated with the B<Title> tag. The display name
155    is only used in the automated documentation. It has no other effect. The entities and
156    relationships are listed inside the B<Entities> and B<Relationships> tags,
157    respectively. None of these tags have attributes.
158    
159        <Database>
160            <Title>... display title here...</Title>
161            <Entities>
162                ... entity definitions here ...
163            </Entities>
164            <Relationships>
165                ... relationship definitions here...
166            </Relationships>
167        </Database>
168    
169    Entities, relationships, indexes, and fields all allow a text tag called B<Notes>.
170    The text inside the B<Notes> tag contains comments that will appear when the database
171    documentation is generated. Within a B<Notes> tag, you may use C<[i]> and C<[/i]> for
172    italics, C<[b]> and C<[/b]> for bold, and C<[p]> for a new paragraph.
173    
174    =head3 Fields
175    
176    Both entities and relationships have fields described by B<Field> tags. A B<Field>
177    tag can have B<Notes> associated with it. The complete set of B<Field> tags for an
178    object mus be inside B<Fields> tags.
179    
180        <Entity ... >
181            <Fields>
182                ... Field tags ...
183            </Fields>
184        </Entity>
185    
186    The attributes for the B<Field> tag are as follows.
187    
188    =over 4
189    
190    =item name
191    
192    Name of the field. The field name should contain only letters, digits, and hyphens (C<->),
193    and the first character should be a letter. Most underlying databases are case-insensitive
194    with the respect to field names, so a best practice is to use lower-case letters only. Finally,
195    the name C<search-relevance> has special meaning for full-text searches and should not be
196    used as a field name.
197    
198    =item type
199    
200    Data type of the field. The legal data types are given above.
201    
202    =item relation
203    
204    Name of the relation containing the field. This should only be specified for entity
205    fields. The ERDB system does not support optional fields or multi-occurring fields
206    in the primary relation of an entity. Instead, they are put into secondary relations.
207    So, for example, in the C<Genome> entity, the C<group-name> field indicates a special
208    grouping used to select a subset of the genomes. A given genome may not be in any
209    groups or may be in multiple groups. Therefore, C<group-name> specifies a relation
210    value. The relation name specified must be a valid table name. By convention, it is
211    usually the entity name followed by a qualifying word (e.g. C<GenomeGroup>). In an
212    entity, the fields without a relation attribute are said to belong to the
213    I<primary relation>. This relation has the same name as the entity itself.
214    
215    =item searchable
216    
217    If specified, then the field is a candidate for full-text searching. A single full-text
218    index will be created for each relation with at least one searchable field in it.
219    For best results, this option should only be used for string or text fields.
220    
221    =item special
222    
223    This attribute allows the subclass to assign special meaning for certain fields.
224    The interpretation is up to the subclass itself. Currently, only entity fields
225    can have this attribute.
226    
227    =back
228    
229    =head3 Indexes
230    
231    An entity can have multiple alternate indexes associated with it. The fields must
232    all be from the same relation. The alternate indexes assist in ordering results
233    from a query. A relationship can have up to two indexes-- a I<to-index> and a
234    I<from-index>. These order the results when crossing the relationship. For
235    example, in the relationship C<HasContig> from C<Genome> to C<Contig>, the
236    from-index would order the contigs of a ganome, and the to-index would order
237    the genomes of a contig. A relationship's index must specify only fields in
238    the relationship.
239    
240    The indexes for an entity must be listed inside the B<Indexes> tag. The from-index
241    of a relationship is specified using the B<FromIndex> tag; the to-index is specified
242    using the B<ToIndex> tag.
243    
244    Each index can contain a B<Notes> tag. In addition, it will have an B<IndexFields>
245    tag containing the B<IndexField> tags. These specify, in order, the fields used in
246    the index. The attributes of an B<IndexField> tag are as follows.
247    
248    =over 4
249    
250    =item name
251    
252    Name of the field.
253    
254    =item order
255    
256    Sort order of the field-- C<ascending> or C<descending>.
257    
258    =back
259    
260    The B<FromIndex>, and B<ToIndex> tags have no attributes. The B<Index> tag can
261    have a B<Unique> attribute. If specified, the index will be generated as a unique
262    index.
263    
264    =head3 Object and Field Names
265    
266    By convention entity and relationship names use capital casing (e.g. C<Genome> or
267    C<HasRegionsIn>. Most underlying databases, however, are aggressively case-insensitive
268    with respect to relation names, converting them internally to all-upper case or
269    all-lower case.
270    
271    If syntax or parsing errors occur when you try to load or use an ERDB database, the
272    most likely reason is that one of your objects has an SQL reserved word as its name.
273    The list of SQL reserved words keeps increasing; however, most are unlikely to show
274    up as a noun or declarative verb phrase. The exceptions are C<Group>, C<User>,
275    C<Table>, C<Index>, C<Object>, C<Date>, C<Number>, C<Update>, C<Time>, C<Percent>,
276    C<Memo>, C<Order>, and C<Sum>. This problem can crop up in field names as well.
277    
278    Every entity has a field called C<id> that acts as its primary key. Every relationship
279    has fields called C<from-link> and C<to-link> that contain copies of the relevant
280    entity IDs. These are essentially ERDB's reserved words, and should not be used
281    for user-defined field names.
282    
283    =head3 Entities
284    
285    An entity is described by the B<Entity> tag. The entity can contain B<Notes>, an
286    B<Indexes> tag containing one or more secondary indexes, and a B<Fields> tag
287    containing one or more fields. The attributes of the B<Entity> tag are as follows.
288    
289    =over 4
290    
291    =item name
292    
293    Name of the entity. The entity name, by convention, uses capital casing (e.g. C<Genome>
294    or C<GroupBlock>) and should be a noun or noun phrase.
295    
296    =item keyType
297    
298    Data type of the primary key. The primary key is always named C<id>.
299    
300    =back
301    
302    =head3 Relationships
303    
304    A relationship is described by the C<Relationship> tag. Within a relationship,
305    there can be a C<Notes> tag, a C<Fields> tag containing the intersection data
306    fields, a C<FromIndex> tag containing the from-index, and a C<ToIndex> tag containing
307    the to-index.
308    
309    The C<Relationship> tag has the following attributes.
310    
311    =over 4
312    
313    =item name
314    
315    Name of the relationship. The relationship name, by convention, uses capital casing
316    (e.g. C<ContainsRegionIn> or C<HasContig>), and should be a declarative verb
317    phrase, designed to fit between the from-entity and the to-entity (e.g.
318    Block C<ContainsRegionIn> Genome).
319    
320    =item from
321    
322    Name of the entity from which the relationship starts.
323    
324    =item to
325    
326    Name of the entity to which the relationship proceeds.
327    
328    =item arity
329    
330    Relationship type: C<1M> for one-to-many and C<MM> for many-to-many.
331    
332    =back
333    
334  =cut  =cut
335    
# Line 76  Line 337 
337    
338  # Table of information about our datatypes. "sqlType" is the corresponding SQL datatype string.  # Table of information about our datatypes. "sqlType" is the corresponding SQL datatype string.
339  # "maxLen" is the maximum permissible length of the incoming string data used to populate a field  # "maxLen" is the maximum permissible length of the incoming string data used to populate a field
340  # of the specified type. "dataGen" is PERL string that will be evaluated if no test data generation  # of the specified type. "avgLen" is the average byte length for estimating
341   #string is specified in the field definition.  # record sizes. "sort" is the key modifier for the sort command, "notes" is a type description,
342  my %TypeTable = ( char =>        { sqlType => 'CHAR(1)',                        maxLen => 1,                    dataGen => "StringGen('A')" },  # and "indexMod", if non-zero, is the number of characters to use when the field is specified in an
343                                    int =>         { sqlType => 'INTEGER',                        maxLen => 20,                   dataGen => "IntGen(0, 99999999)" },  # index
344                                    string =>  { sqlType => 'VARCHAR(255)',               maxLen => 255,                  dataGen => "StringGen(IntGen(10,250))" },  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",
345                                    text =>        { sqlType => 'TEXT',                           maxLen => 1000000000,   dataGen => "StringGen(IntGen(80,1000))" },                                 indexMod =>   0, notes => "single ASCII character"},
346                                    date =>        { sqlType => 'BIGINT',                         maxLen => 80,                   dataGen => "DateGen(-7, 7, IntGen(0,1400))" },                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n",
347                                    float =>       { sqlType => 'DOUBLE PRECISION',       maxLen => 40,                   dataGen => "FloatGen(0.0, 100.0)" },                                 indexMod =>   0, notes => "signed 32-bit integer"},
348                                    boolean => { sqlType => 'SMALLINT',                   maxLen => 1,                    dataGen => "IntGen(0, 1)" },                    counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n",
349                                   indexMod =>   0, notes => "unsigned 32-bit integer"},
350                      string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, sort => "",
351                                   indexMod =>   0, notes => "character string, 0 to 255 characters"},
352                      text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, sort => "",
353                                   indexMod => 255, notes => "character string, nearly unlimited length, only first 255 characters are indexed"},
354                      date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, sort => "n",
355                                   indexMod =>   0, notes => "signed, 64-bit integer"},
356                      float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, sort => "g",
357                                   indexMod =>   0, notes => "64-bit double precision floating-point number"},
358                      boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, sort => "n",
359                                   indexMod =>   0, notes => "boolean value: 0 if false, 1 if true"},
360                     'hash-string' =>
361                                 { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, sort => "",
362                                   indexMod =>   0, notes => "string stored in digested form, used for certain types of key fields"},
363                     'id-string' =>
364                                 { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, sort => "",
365                                   indexMod =>   0, notes => "character string, 0 to 25 characters"},
366                               'key-string' =>                               'key-string' =>
367                                                           { sqlType => 'VARCHAR(40)',            maxLen => 40,                   dataGen => "StringGen(IntGen(10,40))" },                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, sort => "",
368                                   indexMod =>   0, notes => "character string, 0 to 40 characters"},
369                                   'name-string' =>                                   'name-string' =>
370                                                           { sqlType => 'VARCHAR(80)',            maxLen => 80,                   dataGen => "StringGen(IntGen(10,80))" },                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, sort => "",
371                                   indexMod =>   0, notes => "character string, 0 to 80 characters"},
372                                   'medium-string' =>                                   'medium-string' =>
373                                                           { sqlType => 'VARCHAR(160)',           maxLen => 160,                  dataGen => "StringGen(IntGen(10,160))" },                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",
374                                   indexMod =>   0, notes => "character string, 0 to 160 characters"},
375                                  );                                  );
376    
377  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 99  Line 380 
380                                     'MM' => 'many-to-many'                                     'MM' => 'many-to-many'
381                                   );                                   );
382    
383  # Table for interpreting string patterns.  # Options for XML input and output.
384    
385    my %XmlOptions = (GroupTags =>  { Relationships => 'Relationship',
386                                      Entities => 'Entity',
387                                      Fields => 'Field',
388                                      Indexes => 'Index',
389                                      IndexFields => 'IndexField'
390                                    },
391                      KeyAttr =>    { Relationship => 'name',
392                                      Entity => 'name',
393                                      Field => 'name'
394                                    },
395                      SuppressEmpty => 1,
396                     );
397    
398  my %PictureTable = ( 'A' => "abcdefghijklmnopqrstuvwxyz",  my %XmlInOpts  = (
399                                           '9' => "0123456789",                    ForceArray => ['Field', 'Index', 'IndexField', 'Relationship', 'Entity'],
400                                           'X' => "abcdefghijklmnopqrstuvwxyz0123456789",                    ForceContent => 1,
401                                           'V' => "aeiou",                    NormalizeSpace => 2,
402                                           'K' => "bcdfghjklmnoprstvwxyz"                   );
403    my %XmlOutOpts = (
404                      RootName => 'Database',
405                      XMLDecl => 1,
406                                     );                                     );
407    
408    
409  =head2 Public Methods  =head2 Public Methods
410    
411  =head3 new  =head3 new
# Line 140  Line 438 
438                                   _metaData => $metaData                                   _metaData => $metaData
439                             };                             };
440          # Bless and return it.          # Bless and return it.
441          bless $self;      bless $self, $class;
442          return $self;          return $self;
443  }  }
444    
445  =head3 ShowMetaData  =head3 ShowMetaData
446    
447  C<< $database->ShowMetaData($fileName); >>  C<< $erdb->ShowMetaData($fileName); >>
448    
449  This method outputs a description of the database. This description can be used to help users create  This method outputs a description of the database. This description can be used to help users create
450  the data to be loaded into the relations.  the data to be loaded into the relations.
# Line 177  Line 475 
475          # Write the HTML heading stuff.          # Write the HTML heading stuff.
476          print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";          print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";
477          print HTMLOUT "</head>\n<body>\n";          print HTMLOUT "</head>\n<body>\n";
478        # Write the documentation.
479        print HTMLOUT $self->DisplayMetaData();
480        # Close the document.
481        print HTMLOUT "</body>\n</html>\n";
482        # Close the file.
483        close HTMLOUT;
484    }
485    
486    =head3 DisplayMetaData
487    
488    C<< my $html = $erdb->DisplayMetaData(); >>
489    
490    Return an HTML description of the database. This description can be used to help users create
491    the data to be loaded into the relations and form queries. The output is raw includable HTML
492    without any HEAD or BODY tags.
493    
494    =over 4
495    
496    =item filename
497    
498    The name of the output file.
499    
500    =back
501    
502    =cut
503    
504    sub DisplayMetaData {
505        # Get the parameters.
506        my ($self) = @_;
507        # Get the metadata and the title string.
508        my $metadata = $self->{_metaData};
509        # Get the title string.
510        my $title = $metadata->{Title};
511        # Get the entity and relationship lists.
512        my $entityList = $metadata->{Entities};
513        my $relationshipList = $metadata->{Relationships};
514        # Declare the return variable.
515        my $retVal = "";
516        # Open the output file.
517        Trace("Building MetaData table of contents.") if T(4);
518          # Here we do the table of contents. It starts as an unordered list of section names. Each          # Here we do the table of contents. It starts as an unordered list of section names. Each
519          # section contains an ordered list of entity or relationship subsections.          # section contains an ordered list of entity or relationship subsections.
520          print HTMLOUT "<ul>\n<li><a href=\"#EntitiesSection\">Entities</a>\n<ol>\n";      $retVal .= "<ul>\n<li><a href=\"#EntitiesSection\">Entities</a>\n<ol>\n";
521          # Loop through the Entities, displaying a list item for each.          # Loop through the Entities, displaying a list item for each.
522          foreach my $key (sort keys %{$entityList}) {          foreach my $key (sort keys %{$entityList}) {
523                  # Display this item.                  # Display this item.
524                  print HTMLOUT "<li><a href=\"#$key\">$key</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$key</a></li>\n";
525          }          }
526          # Close off the entity section and start the relationship section.          # Close off the entity section and start the relationship section.
527          print HTMLOUT "</ol></li>\n<li><a href=\"#RelationshipsSection\">Relationships</a>\n<ol>\n";      $retVal .= "</ol></li>\n<li><a href=\"#RelationshipsSection\">Relationships</a>\n<ol>\n";
528          # Loop through the Relationships.          # Loop through the Relationships.
529          foreach my $key (sort keys %{$relationshipList}) {          foreach my $key (sort keys %{$relationshipList}) {
530                  # Display this item.                  # Display this item.
531                  my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});                  my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});
532                  print HTMLOUT "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";
533          }          }
534          # Close off the relationship section and list the join table section.          # Close off the relationship section and list the join table section.
535          print HTMLOUT "</ol></li>\n<li><a href=\"#JoinTable\">Join Table</a></li>\n";      $retVal .= "</ol></li>\n<li><a href=\"#JoinTable\">Join Table</a></li>\n";
536          # Close off the table of contents itself.          # Close off the table of contents itself.
537          print HTMLOUT "</ul>\n";      $retVal .=  "</ul>\n";
538          # Now we start with the actual data. Denote we're starting the entity section.          # Now we start with the actual data. Denote we're starting the entity section.
539          print HTMLOUT "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";      $retVal .= "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";
540          # Loop through the entities.          # Loop through the entities.
541          for my $key (sort keys %{$entityList}) {          for my $key (sort keys %{$entityList}) {
542                  Trace("Building MetaData entry for $key entity.") if T(4);                  Trace("Building MetaData entry for $key entity.") if T(4);
543                  # Create the entity header. It contains a bookmark and the entity name.                  # Create the entity header. It contains a bookmark and the entity name.
544                  print HTMLOUT "<a name=\"$key\"></a><h3>$key</h3>\n";          $retVal .= "<a name=\"$key\"></a><h3>$key</h3>\n";
545                  # Get the entity data.                  # Get the entity data.
546                  my $entityData = $entityList->{$key};                  my $entityData = $entityList->{$key};
547                  # If there's descriptive text, display it.                  # If there's descriptive text, display it.
548                  if (my $notes = $entityData->{Notes}) {                  if (my $notes = $entityData->{Notes}) {
549                          print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
550                  }                  }
551                  # Now we want a list of the entity's relationships. First, we set up the relationship subsection.          # See if we need a list of the entity's relationships.
552                  print HTMLOUT "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          my $relCount = keys %{$relationshipList};
553            if ($relCount > 0) {
554                # First, we set up the relationship subsection.
555                $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
556                  # Loop through the relationships.                  # Loop through the relationships.
557                  for my $relationship (sort keys %{$relationshipList}) {                  for my $relationship (sort keys %{$relationshipList}) {
558                          # Get the relationship data.                          # Get the relationship data.
# Line 221  Line 562 
562                                  # Get the relationship sentence and append the arity.                                  # Get the relationship sentence and append the arity.
563                                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);                                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);
564                                  # Display the relationship data.                                  # Display the relationship data.
565                                  print HTMLOUT "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";                      $retVal .= "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";
566                          }                          }
567                  }                  }
568                  # Close off the relationship list.                  # Close off the relationship list.
569                  print HTMLOUT "</ul>\n";              $retVal .= "</ul>\n";
570            }
571                  # Get the entity's relations.                  # Get the entity's relations.
572                  my $relationList = $entityData->{Relations};                  my $relationList = $entityData->{Relations};
573                  # Create a header for the relation subsection.                  # Create a header for the relation subsection.
574                  print HTMLOUT "<h4>Relations for <b>$key</b></h4>\n";          $retVal .= "<h4>Relations for <b>$key</b></h4>\n";
575                  # Loop through the relations, displaying them.                  # Loop through the relations, displaying them.
576                  for my $relation (sort keys %{$relationList}) {                  for my $relation (sort keys %{$relationList}) {
577                          my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});                          my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});
578                          print HTMLOUT $htmlString;              $retVal .= $htmlString;
579                  }                  }
580          }          }
581          # Denote we're starting the relationship section.          # Denote we're starting the relationship section.
582          print HTMLOUT "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";      $retVal .= "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";
583          # Loop through the relationships.          # Loop through the relationships.
584          for my $key (sort keys %{$relationshipList}) {          for my $key (sort keys %{$relationshipList}) {
585                  Trace("Building MetaData entry for $key relationship.") if T(4);                  Trace("Building MetaData entry for $key relationship.") if T(4);
# Line 245  Line 587 
587                  my $relationshipStructure = $relationshipList->{$key};                  my $relationshipStructure = $relationshipList->{$key};
588                  # Create the relationship header.                  # Create the relationship header.
589                  my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);                  my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);
590                  print HTMLOUT "<h3><a name=\"$key\"></a>$headerText</h3>\n";          $retVal .= "<h3><a name=\"$key\"></a>$headerText</h3>\n";
591                  # Get the entity names.                  # Get the entity names.
592                  my $fromEntity = $relationshipStructure->{from};                  my $fromEntity = $relationshipStructure->{from};
593                  my $toEntity = $relationshipStructure->{to};                  my $toEntity = $relationshipStructure->{to};
# Line 255  Line 597 
597                  # since both sentences will say the same thing.                  # since both sentences will say the same thing.
598                  my $arity = $relationshipStructure->{arity};                  my $arity = $relationshipStructure->{arity};
599                  if ($arity eq "11") {                  if ($arity eq "11") {
600                          print HTMLOUT "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";
601                  } else {                  } else {
602                          print HTMLOUT "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";
603                          if ($arity eq "MM" && $fromEntity ne $toEntity) {                          if ($arity eq "MM" && $fromEntity ne $toEntity) {
604                                  print HTMLOUT "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";                  $retVal .= "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";
605                          }                          }
606                  }                  }
607                  print HTMLOUT "</p>\n";          $retVal .= "</p>\n";
608                  # If there are notes on this relationship, display them.                  # If there are notes on this relationship, display them.
609                  if (my $notes = $relationshipStructure->{Notes}) {                  if (my $notes = $relationshipStructure->{Notes}) {
610                          print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
611                  }                  }
612                  # Generate the relationship's relation table.                  # Generate the relationship's relation table.
613                  my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});                  my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
614                  print HTMLOUT $htmlString;          $retVal .= $htmlString;
615          }          }
616          Trace("Building MetaData join table.") if T(4);          Trace("Building MetaData join table.") if T(4);
617          # Denote we're starting the join table.          # Denote we're starting the join table.
618          print HTMLOUT "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";      $retVal .= "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";
619          # Create a table header.          # Create a table header.
620          print HTMLOUT _OpenTable("Join Table", "Source", "Target", "Join Condition");      $retVal .= _OpenTable("Join Table", "Source", "Target", "Join Condition");
621          # Loop through the joins.          # Loop through the joins.
622          my $joinTable = $metadata->{Joins};          my $joinTable = $metadata->{Joins};
623          for my $joinKey (sort keys %{$joinTable}) {      my @joinKeys = keys %{$joinTable};
624        for my $joinKey (sort @joinKeys) {
625                  # Separate out the source, the target, and the join clause.                  # Separate out the source, the target, and the join clause.
626                  $joinKey =~ m!([^/]*)/(.*)$!;          $joinKey =~ m!^([^/]+)/(.+)$!;
627                  my ($source, $target, $clause) = ($self->ComputeObjectSentence($1),          my ($sourceRelation, $targetRelation) = ($1, $2);
628                                                                                    $self->ComputeObjectSentence($2),          Trace("Join with key $joinKey is from $sourceRelation to $targetRelation.") if T(Joins => 4);
629                                                                                    $joinTable->{$joinKey});          my $source = $self->ComputeObjectSentence($sourceRelation);
630            my $target = $self->ComputeObjectSentence($targetRelation);
631            my $clause = $joinTable->{$joinKey};
632                  # Display them in a table row.                  # Display them in a table row.
633                  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";
634          }          }
635          # Close the table.          # Close the table.
636          print HTMLOUT _CloseTable();      $retVal .= _CloseTable();
637          # Close the document.      Trace("Built MetaData HTML.") if T(3);
638          print HTMLOUT "</body>\n</html>\n";      # Return the HTML.
639          # Close the file.      return $retVal;
         close HTMLOUT;  
         Trace("Built MetaData web page.") if T(3);  
640  }  }
641    
642  =head3 DumpMetaData  =head3 DumpMetaData
643    
644  C<< $database->DumpMetaData(); >>  C<< $erdb->DumpMetaData(); >>
645    
646  Return a dump of the metadata structure.  Return a dump of the metadata structure.
647    
# Line 311  Line 654 
654          return Data::Dumper::Dumper($self->{_metaData});          return Data::Dumper::Dumper($self->{_metaData});
655  }  }
656    
657    =head3 FindIndexForEntity
658    
659    C<< my $indexFound = ERDB::FindIndexForEntity($xml, $entityName, $attributeName); >>
660    
661    This method locates the entry in an entity's index list that begins with the
662    specified attribute name. If the entity has no index list, one will be
663    created. This method works on raw XML, not a live ERDB object.
664    
665    =over 4
666    
667    =item xml
668    
669    The raw XML structure defining the database.
670    
671    =item entityName
672    
673    The name of the relevant entity.
674    
675    =item attributeName
676    
677    The name of the attribute relevant to the search.
678    
679    =item RETURN
680    
681    The numerical index in the index list of the index entry for the specified entity and
682    attribute, or C<undef> if no such index exists.
683    
684    =back
685    
686    =cut
687    
688    sub FindIndexForEntity {
689        # Get the parameters.
690        my ($xml, $entityName, $attributeName) = @_;
691        # Declare the return variable.
692        my $retVal;
693        # Get the named entity.
694        my $entityData = $xml->{Entities}->{$entityName};
695        if (! $entityData) {
696            Confess("Entity $entityName not found in DBD structure.");
697        } else {
698            # Insure it has an index list.
699            if (! exists $entityData->{Indexes}) {
700                $entityData->{Indexes} = [];
701            } else {
702                # Search for the desired index.
703                my $indexList = $entityData->{Indexes};
704                my $n = scalar @{$indexList};
705                Trace("Searching $n indexes in index list for $entityName.") if T(2);
706                # We use an indexed FOR here because we're returning an
707                # index number instead of an object. We do THAT so we can
708                # delete the index from the list if needed.
709                for (my $i = 0; $i < $n && !defined($retVal); $i++) {
710                    my $index = $indexList->[$i];
711                    my $fields = $index->{IndexFields};
712                    # Technically this IF should be safe (that is, we are guaranteed
713                    # the existence of a "$fields->[0]"), because when we load the XML
714                    # we have SuppressEmpty specified.
715                    if ($fields->[0]->{name} eq $attributeName) {
716                        $retVal = $i;
717                    }
718                }
719            }
720        }
721        Trace("Index for $attributeName of $entityName found at position $retVal.") if defined($retVal) && T(3);
722        Trace("Index for $attributeName not found in $entityName.") if !defined($retVal) && T(3);
723        # Return the result.
724        return $retVal;
725    }
726    
727  =head3 CreateTables  =head3 CreateTables
728    
729  C<< $datanase->CreateTables(); >>  C<< $erdb->CreateTables(); >>
730    
731  This method creates the tables for the database from the metadata structure loaded by the  This method creates the tables for the database from the metadata structure loaded by the
732  constructor. It is expected this function will only be used on rare occasions, when the  constructor. It is expected this function will only be used on rare occasions, when the
# Line 325  Line 738 
738  sub CreateTables {  sub CreateTables {
739          # Get the parameters.          # Get the parameters.
740          my ($self) = @_;          my ($self) = @_;
741          my $metadata = $self->{_metaData};      # Get the relation names.
742          my $dbh = $self->{_dbh};      my @relNames = $self->GetTableNames();
743          # Loop through the entities.      # Loop through the relations.
744          while (my ($entityName, $entityData) = each %{$metadata->{Entities}}) {      for my $relationName (@relNames) {
                 # Tell the user what we're doing.  
                 Trace("Creating relations for entity $entityName.") if T(1);  
                 # Loop through the entity's relations.  
                 for my $relationName (keys %{$entityData->{Relations}}) {  
745                          # Create a table for this relation.                          # Create a table for this relation.
746                          $self->CreateTable($relationName);                          $self->CreateTable($relationName);
747                          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);  
748          }          }
749  }  }
750    
751  =head3 CreateTable  =head3 CreateTable
752    
753  C<< $database->CreateTable($tableName, $indexFlag); >>  C<< $erdb->CreateTable($tableName, $indexFlag, $estimatedRows); >>
754    
755  Create the table for a relation and optionally create its indexes.  Create the table for a relation and optionally create its indexes.
756    
# Line 359  Line 760 
760    
761  Name of the relation (which will also be the table name).  Name of the relation (which will also be the table name).
762    
763  =item $indexFlag  =item indexFlag
764    
765  TRUE if the indexes for the relation should be created, else FALSE. If FALSE,  TRUE if the indexes for the relation should be created, else FALSE. If FALSE,
766  L</CreateIndexes> must be called later to bring the indexes into existence.  L</CreateIndexes> must be called later to bring the indexes into existence.
767    
768    =item estimatedRows (optional)
769    
770    If specified, the estimated maximum number of rows for the relation. This
771    information allows the creation of tables using storage engines that are
772    faster but require size estimates, such as MyISAM.
773    
774  =back  =back
775    
776  =cut  =cut
777    
778  sub CreateTable {  sub CreateTable {
779          # Get the parameters.          # Get the parameters.
780          my ($self, $relationName, $indexFlag) = @_;      my ($self, $relationName, $indexFlag, $estimatedRows) = @_;
781          # Get the database handle.          # Get the database handle.
782          my $dbh = $self->{_dbh};          my $dbh = $self->{_dbh};
783          # Get the relation data and determine whether or not the relation is primary.          # Get the relation data and determine whether or not the relation is primary.
# Line 394  Line 801 
801          # Insure the table is not already there.          # Insure the table is not already there.
802          $dbh->drop_table(tbl => $relationName);          $dbh->drop_table(tbl => $relationName);
803          Trace("Table $relationName dropped.") if T(2);          Trace("Table $relationName dropped.") if T(2);
804        # If there are estimated rows, create an estimate so we can take advantage of
805        # faster DB technologies.
806        my $estimation = undef;
807        if ($estimatedRows) {
808            $estimation = [$self->EstimateRowSize($relationName), $estimatedRows];
809        }
810          # Create the table.          # Create the table.
811          Trace("Creating table $relationName: $fieldThing") if T(2);          Trace("Creating table $relationName: $fieldThing") if T(2);
812          $dbh->create_table(tbl => $relationName, flds => $fieldThing);      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);
813          Trace("Relation $relationName created in database.") if T(2);          Trace("Relation $relationName created in database.") if T(2);
814          # If we want to build the indexes, we do it here.      # If we want to build the indexes, we do it here. Note that the full-text search
815        # index will not be built until the table has been loaded.
816          if ($indexFlag) {          if ($indexFlag) {
817                  $self->CreateIndex($relationName);                  $self->CreateIndex($relationName);
818          }          }
819  }  }
820    
821  =head3 CreateIndex  =head3 VerifyFields
   
 C<< $database->CreateIndex($relationName); >>  
   
 Create the indexes for a relation. If a table is being loaded from a large source file (as  
 is the case in L</LoadTable>), it is best to create the indexes after the load. If that is  
 the case, then L</CreateTable> should be called with the index flag set to FALSE, and this  
 method used after the load to create the indexes for the table.  
   
 =cut  
   
 sub CreateIndex {  
         # Get the parameters.  
         my ($self, $relationName) = @_;  
         # Get the relation's descriptor.  
         my $relationData = $self->_FindRelation($relationName);  
         # Get the database handle.  
         my $dbh = $self->{_dbh};  
         # Now we need to create this relation's indexes. We do this by looping through its index table.  
         while (my ($indexName, $indexData) = each %{$relationData->{Indexes}}) {  
                 # Get the index's field list.  
                 my @fieldList = _FixNames(@{$indexData->{IndexFields}});  
                 my $flds = join(', ', @fieldList);  
                 # Get the index's uniqueness flag.  
                 my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');  
                 # Create the index.  
                 $dbh->create_index(idx => $indexName, tbl => $relationName, flds => $flds, unique => $unique);  
                 Trace("Index created: $indexName for $relationName ($flds)") if T(1);  
         }  
 }  
   
 =head3 LoadTables  
   
 C<< my $stats = $database->LoadTables($directoryName, $rebuild); >>  
822    
823  This method will load the database tables from a directory. The tables must already have been created  C<< my $count = $erdb->VerifyFields($relName, \@fieldList); >>
 in the database. (This can be done by calling L</CreateTables>.) The caller passes in a directory name;  
 all of the relations to be loaded must have a file in the directory with the same name as the relation  
 (optionally with a suffix of C<.dtx>). Each file must be a tab-delimited table of field values. Each  
 line of the file will be loaded as a row of the target relation table. The field values should be in  
 the same order as the fields in the relation tables generated by L</ShowMetaData>. The old data is  
 erased before the new data is loaded in.  
824    
825  A certain amount of translation automatically takes place. Ctrl-M characters are deleted, and  Run through the list of proposed field values, insuring that all the character fields are
826  tab and new-line characters inside a field are escaped as C<\t> and C<\n>, respectively. Dates must  below the maximum length. If any fields are too long, they will be truncated in place.
 be entered as a Unix timestamp, that is, as an integer number of seconds since the base epoch.  
827    
828  =over 4  =over 4
829    
830  =item directoryName  =item relName
831    
832  Name of the directory containing the relation files to be loaded.  Name of the relation for which the specified fields are destined.
833    
834  =item rebuild  =item fieldList
835    
836  TRUE if the tables should be dropped and rebuilt, else FALSE. This is, unfortunately, the  Reference to a list, in order, of the fields to be put into the relation.
 only way to erase existing data in the tables, since the TRUNCATE command is not supported  
 by all of the DB engines we use.  
837    
838  =item RETURN  =item RETURN
839    
840  Returns a statistical object describing the number of records read and a list of the error messages.  Returns the number of fields truncated.
841    
842  =back  =back
843    
844  =cut  =cut
845    
846  sub LoadTables {  sub VerifyFields {
847          # Get the parameters.          # Get the parameters.
848          my ($self, $directoryName, $rebuild) = @_;      my ($self, $relName, $fieldList) = @_;
849          # Start the timer.      # Initialize the return value.
850          my $startTime = gettimeofday;      my $retVal = 0;
851          # Clean any trailing slash from the directory name.      # Get the relation definition.
852          $directoryName =~ s!/\\$!!;      my $relData = $self->_FindRelation($relName);
853          # Declare the return variable.      # Get the list of field descriptors.
854          my $retVal = Stats->new();      my $fieldTypes = $relData->{Fields};
855          # Get the metadata structure.      my $fieldCount = scalar @{$fieldTypes};
856          my $metaData = $self->{_metaData};      # Loop through the two lists.
857          # Loop through the entities.      for (my $i = 0; $i < $fieldCount; $i++) {
858          for my $entity (values %{$metaData->{Entities}}) {          # Get the type of the current field.
859                  # Loop through the entity's relations.          my $fieldType = $fieldTypes->[$i]->{type};
860                  for my $relationName (keys %{$entity->{Relations}}) {          # If it's a character field, verify the length.
861                          # Try to load this relation.          if ($fieldType =~ /string/) {
862                          my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);              my $maxLen = $TypeTable{$fieldType}->{maxLen};
863                          # Accumulate the statistics.              my $oldString = $fieldList->[$i];
864                          $retVal->Accumulate($result);              if (length($oldString) > $maxLen) {
865                    # Here it's too big, so we truncate it.
866                    Trace("Truncating field $i in relation $relName to $maxLen characters from \"$oldString\".") if T(1);
867                    $fieldList->[$i] = substr $oldString, 0, $maxLen;
868                    $retVal++;
869                  }                  }
870          }          }
         # 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);  
871          }          }
872          # Add the duration of the load to the statistical object.      # Return the truncation count.
         $retVal->Add('duration', gettimeofday - $startTime);  
         # Return the accumulated statistics.  
873          return $retVal;          return $retVal;
874  }  }
875    
876  =head3 GetTableNames  =head3 DigestFields
877    
878  C<< my @names = $database->GetTableNames; >>  C<< $erdb->DigestFields($relName, $fieldList); >>
879    
880  Return a list of the relations required to implement this database.  Digest the strings in the field list that correspond to data type C<hash-string> in the
881    specified relation.
882    
883  =cut  =over 4
884    
885  sub GetTableNames {  =item relName
886    
887    Name of the relation to which the fields belong.
888    
889    =item fieldList
890    
891    List of field contents to be loaded into the relation.
892    
893    =back
894    
895    =cut
896    #: Return Type ;
897    sub DigestFields {
898        # Get the parameters.
899        my ($self, $relName, $fieldList) = @_;
900        # Get the relation definition.
901        my $relData = $self->_FindRelation($relName);
902        # Get the list of field descriptors.
903        my $fieldTypes = $relData->{Fields};
904        my $fieldCount = scalar @{$fieldTypes};
905        # Loop through the two lists.
906        for (my $i = 0; $i < $fieldCount; $i++) {
907            # Get the type of the current field.
908            my $fieldType = $fieldTypes->[$i]->{type};
909            # If it's a hash string, digest it in place.
910            if ($fieldType eq 'hash-string') {
911                $fieldList->[$i] = $self->DigestKey($fieldList->[$i]);
912            }
913        }
914    }
915    
916    =head3 DigestKey
917    
918    C<< my $digested = $erdb->DigestKey($keyValue); >>
919    
920    Return the digested value of a symbolic key. The digested value can then be plugged into a
921    key-based search into a table with key-type hash-string.
922    
923    Currently the digesting process is independent of the database structure, but that may not
924    always be the case, so this is an instance method instead of a static method.
925    
926    =over 4
927    
928    =item keyValue
929    
930    Key value to digest.
931    
932    =item RETURN
933    
934    Digested value of the key.
935    
936    =back
937    
938    =cut
939    
940    sub DigestKey {
941        # Get the parameters.
942        my ($self, $keyValue) = @_;
943        # Compute the digest.
944        my $retVal = md5_base64($keyValue);
945        # Return the result.
946        return $retVal;
947    }
948    
949    =head3 CreateIndex
950    
951    C<< $erdb->CreateIndex($relationName); >>
952    
953    Create the indexes for a relation. If a table is being loaded from a large source file (as
954    is the case in L</LoadTable>), it is sometimes best to create the indexes after the load.
955    If that is the case, then L</CreateTable> should be called with the index flag set to
956    FALSE, and this method used after the load to create the indexes for the table.
957    
958    =cut
959    
960    sub CreateIndex {
961        # Get the parameters.
962        my ($self, $relationName) = @_;
963        # Get the relation's descriptor.
964        my $relationData = $self->_FindRelation($relationName);
965        # Get the database handle.
966        my $dbh = $self->{_dbh};
967        # Now we need to create this relation's indexes. We do this by looping through its index table.
968        my $indexHash = $relationData->{Indexes};
969        for my $indexName (keys %{$indexHash}) {
970            my $indexData = $indexHash->{$indexName};
971            # Get the index's field list.
972            my @rawFields = @{$indexData->{IndexFields}};
973            # Get a hash of the relation's field types.
974            my %types = map { $_->{name} => $_->{type} } @{$relationData->{Fields}};
975            # We need to check for text fields so we can append a length limitation for them. To do
976            # that, we need the relation's field list.
977            my $relFields = $relationData->{Fields};
978            for (my $i = 0; $i <= $#rawFields; $i++) {
979                # Get the field type.
980                my $field = $rawFields[$i];
981                my $type = $types{$field};
982                # Ask if it requires using prefix notation for the index.
983                my $mod = $TypeTable{$type}->{indexMod};
984                Trace("Field $field ($i) in $relationName has type $type and indexMod $mod.") if T(3);
985                if ($mod) {
986                    # Append the prefix length to the field name,
987                    $rawFields[$i] .= "($mod)";
988                }
989            }
990            my @fieldList = _FixNames(@rawFields);
991            my $flds = join(', ', @fieldList);
992            # Get the index's uniqueness flag.
993            my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
994            # Create the index.
995            my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
996                                        flds => $flds, kind => $unique);
997            if ($rv) {
998                Trace("Index created: $indexName for $relationName ($flds)") if T(1);
999            } else {
1000                Confess("Error creating index $indexName for $relationName using ($flds): " . $dbh->error_message());
1001            }
1002        }
1003    }
1004    
1005    =head3 GetSecondaryFields
1006    
1007    C<< my %fieldTuples = $erdb->GetSecondaryFields($entityName); >>
1008    
1009    This method will return a list of the name and type of each of the secondary
1010    fields for a specified entity. Secondary fields are stored in two-column tables
1011    in addition to the primary entity table. This enables the field to have no value
1012    or to have multiple values.
1013    
1014    =over 4
1015    
1016    =item entityName
1017    
1018    Name of the entity whose secondary fields are desired.
1019    
1020    =item RETURN
1021    
1022    Returns a hash mapping the field names to their field types.
1023    
1024    =back
1025    
1026    =cut
1027    
1028    sub GetSecondaryFields {
1029        # Get the parameters.
1030        my ($self, $entityName) = @_;
1031        # Declare the return variable.
1032        my %retVal = ();
1033        # Look for the entity.
1034        my $table = $self->GetFieldTable($entityName);
1035        # Loop through the fields, pulling out the secondaries.
1036        for my $field (sort keys %{$table}) {
1037            if ($table->{$field}->{relation} ne $entityName) {
1038                # Here we have a secondary field.
1039                $retVal{$field} = $table->{$field}->{type};
1040            }
1041        }
1042        # Return the result.
1043        return %retVal;
1044    }
1045    
1046    =head3 GetFieldRelationName
1047    
1048    C<< my $name = $erdb->GetFieldRelationName($objectName, $fieldName); >>
1049    
1050    Return the name of the relation containing a specified field.
1051    
1052    =over 4
1053    
1054    =item objectName
1055    
1056    Name of the entity or relationship containing the field.
1057    
1058    =item fieldName
1059    
1060    Name of the relevant field in that entity or relationship.
1061    
1062    =item RETURN
1063    
1064    Returns the name of the database relation containing the field, or C<undef> if
1065    the field does not exist.
1066    
1067    =back
1068    
1069    =cut
1070    
1071    sub GetFieldRelationName {
1072        # Get the parameters.
1073        my ($self, $objectName, $fieldName) = @_;
1074        # Declare the return variable.
1075        my $retVal;
1076        # Get the object field table.
1077        my $table = $self->GetFieldTable($objectName);
1078        # Only proceed if the field exists.
1079        if (exists $table->{$fieldName}) {
1080            # Determine the name of the relation that contains this field.
1081            $retVal = $table->{$fieldName}->{relation};
1082        }
1083        # Return the result.
1084        return $retVal;
1085    }
1086    
1087    =head3 DeleteValue
1088    
1089    C<< my $numDeleted = $erdb->DeleteValue($entityName, $id, $fieldName, $fieldValue); >>
1090    
1091    Delete secondary field values from the database. This method can be used to delete all
1092    values of a specified field for a particular entity instance, or only a single value.
1093    
1094    Secondary fields are stored in two-column relations separate from an entity's primary
1095    table, and as a result a secondary field can legitimately have no value or multiple
1096    values. Therefore, it makes sense to talk about deleting secondary fields where it
1097    would not make sense for primary fields.
1098    
1099    =over 4
1100    
1101    =item entityName
1102    
1103    Name of the entity from which the fields are to be deleted.
1104    
1105    =item id
1106    
1107    ID of the entity instance to be processed. If the instance is not found, this
1108    method will have no effect. If C<undef> is specified, all values for all of
1109    the entity instances will be deleted.
1110    
1111    =item fieldName
1112    
1113    Name of the field whose values are to be deleted.
1114    
1115    =item fieldValue (optional)
1116    
1117    Value to be deleted. If not specified, then all values of the specified field
1118    will be deleted for the entity instance. If specified, then only the values which
1119    match this parameter will be deleted.
1120    
1121    =item RETURN
1122    
1123    Returns the number of rows deleted.
1124    
1125    =back
1126    
1127    =cut
1128    
1129    sub DeleteValue {
1130        # Get the parameters.
1131        my ($self, $entityName, $id, $fieldName, $fieldValue) = @_;
1132        # Declare the return value.
1133        my $retVal = 0;
1134        # We need to set up an SQL command to do the deletion. First, we
1135        # find the name of the field's relation.
1136        my $table = $self->GetFieldTable($entityName);
1137        my $field = $table->{$fieldName};
1138        my $relation = $field->{relation};
1139        # Make sure this is a secondary field.
1140        if ($relation eq $entityName) {
1141            Confess("Cannot delete values of $fieldName for $entityName.");
1142        } else {
1143            # Set up the SQL command to delete all values.
1144            my $sql = "DELETE FROM $relation";
1145            # Build the filter.
1146            my @filters = ();
1147            my @parms = ();
1148            # Check for a filter by ID.
1149            if (defined $id) {
1150                push @filters, "id = ?";
1151                push @parms, $id;
1152            }
1153            # Check for a filter by value.
1154            if (defined $fieldValue) {
1155                push @filters, "$fieldName = ?";
1156                push @parms, $fieldValue;
1157            }
1158            # Append the filters to the command.
1159            if (@filters) {
1160                $sql .= " WHERE " . join(" AND ", @filters);
1161            }
1162            # Execute the command.
1163            my $dbh = $self->{_dbh};
1164            $retVal = $dbh->SQL($sql, 0, @parms);
1165        }
1166        # Return the result.
1167        return $retVal;
1168    }
1169    
1170    =head3 LoadTables
1171    
1172    C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>
1173    
1174    This method will load the database tables from a directory. The tables must already have been created
1175    in the database. (This can be done by calling L</CreateTables>.) The caller passes in a directory name;
1176    all of the relations to be loaded must have a file in the directory with the same name as the relation
1177    (optionally with a suffix of C<.dtx>). Each file must be a tab-delimited table of field values. Each
1178    line of the file will be loaded as a row of the target relation table. The field values should be in
1179    the same order as the fields in the relation tables generated by L</ShowMetaData>. The old data is
1180    erased before the new data is loaded in.
1181    
1182    A certain amount of translation automatically takes place. Ctrl-M characters are deleted, and
1183    tab and new-line characters inside a field are escaped as C<\t> and C<\n>, respectively. Dates must
1184    be entered as a Unix timestamp, that is, as an integer number of seconds since the base epoch.
1185    
1186    =over 4
1187    
1188    =item directoryName
1189    
1190    Name of the directory containing the relation files to be loaded.
1191    
1192    =item rebuild
1193    
1194    TRUE if the tables should be dropped and rebuilt, else FALSE. This is, unfortunately, the
1195    only way to erase existing data in the tables, since the TRUNCATE command is not supported
1196    by all of the DB engines we use.
1197    
1198    =item RETURN
1199    
1200    Returns a statistical object describing the number of records read and a list of the error messages.
1201    
1202    =back
1203    
1204    =cut
1205    
1206    sub LoadTables {
1207        # Get the parameters.
1208        my ($self, $directoryName, $rebuild) = @_;
1209        # Start the timer.
1210        my $startTime = gettimeofday;
1211        # Clean any trailing slash from the directory name.
1212        $directoryName =~ s!/\\$!!;
1213        # Declare the return variable.
1214        my $retVal = Stats->new();
1215        # Get the relation names.
1216        my @relNames = $self->GetTableNames();
1217        for my $relationName (@relNames) {
1218            # Try to load this relation.
1219            my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);
1220            # Accumulate the statistics.
1221            $retVal->Accumulate($result);
1222        }
1223        # Add the duration of the load to the statistical object.
1224        $retVal->Add('duration', gettimeofday - $startTime);
1225        # Return the accumulated statistics.
1226        return $retVal;
1227    }
1228    
1229    
1230    =head3 GetTableNames
1231    
1232    C<< my @names = $erdb->GetTableNames; >>
1233    
1234    Return a list of the relations required to implement this database.
1235    
1236    =cut
1237    
1238    sub GetTableNames {
1239          # Get the parameters.          # Get the parameters.
1240          my ($self) = @_;          my ($self) = @_;
1241          # Get the relation list from the metadata.          # Get the relation list from the metadata.
# Line 524  Line 1246 
1246    
1247  =head3 GetEntityTypes  =head3 GetEntityTypes
1248    
1249  C<< my @names = $database->GetEntityTypes; >>  C<< my @names = $erdb->GetEntityTypes; >>
1250    
1251  Return a list of the entity type names.  Return a list of the entity type names.
1252    
# Line 539  Line 1261 
1261          return sort keys %{$entityList};          return sort keys %{$entityList};
1262  }  }
1263    
1264    =head3 GetDataTypes
1265    
1266    C<< my %types = ERDB::GetDataTypes(); >>
1267    
1268    Return a table of ERDB data types. The table returned is a hash of hashes.
1269    The keys of the big hash are the datatypes. Each smaller hash has several
1270    values used to manage the data. The most interesting is the SQL type (key
1271    C<sqlType>) and the descriptive node (key C<notes>).
1272    
1273    Note that changing the values in the smaller hashes will seriously break
1274    things, so this data should be treated as read-only.
1275    
1276    =cut
1277    
1278    sub GetDataTypes {
1279        return %TypeTable;
1280    }
1281    
1282    
1283    =head3 IsEntity
1284    
1285    C<< my $flag = $erdb->IsEntity($entityName); >>
1286    
1287    Return TRUE if the parameter is an entity name, else FALSE.
1288    
1289    =over 4
1290    
1291    =item entityName
1292    
1293    Object name to be tested.
1294    
1295    =item RETURN
1296    
1297    Returns TRUE if the specified string is an entity name, else FALSE.
1298    
1299    =back
1300    
1301    =cut
1302    
1303    sub IsEntity {
1304        # Get the parameters.
1305        my ($self, $entityName) = @_;
1306        # Test to see if it's an entity.
1307        return exists $self->{_metaData}->{Entities}->{$entityName};
1308    }
1309    
1310  =head3 Get  =head3 Get
1311    
1312  C<< my $query = $database->Get(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  C<< my $query = $erdb->Get(\@objectNames, $filterClause, \@params); >>
1313    
1314  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.
1315  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 549  Line 1317 
1317  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
1318  $genus.  $genus.
1319    
1320  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", [$genus]); >>
1321    
1322  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
1323  parameter representing the parameter value. It would also be possible to code  parameter representing the parameter value. It would also be possible to code
1324    
1325  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>
1326    
1327  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
1328  characters inside the variable C<$genus>.  characters inside the variable C<$genus>.
# Line 566  Line 1334 
1334  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
1335  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,
1336    
1337  C<< $query = $sprout->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]); >>
1338    
1339  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
1340  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.
1341  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
1342  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
1343  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  
1344  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,
1345  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.
1346    
1347    If an entity or relationship is mentioned twice, the name for the second occurrence will
1348    be suffixed with C<2>, the third occurrence will be suffixed with C<3>, and so forth. So,
1349    for example, if we have C<['Feature', 'HasContig', 'Contig', 'HasContig']>, then the
1350    B<to-link> field of the first B<HasContig> is specified as C<HasContig(to-link)>, while
1351    the B<to-link> field of the second B<HasContig> is specified as C<HasContig2(to-link)>.
1352    
1353  =over 4  =over 4
1354    
1355  =item objectNames  =item objectNames
# Line 599  Line 1372 
1372    
1373  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
1374    
1375    Note that the case is important. Only an uppercase "ORDER BY" with a single space will
1376    be processed. The idea is to make it less likely to find the verb by accident.
1377    
1378  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
1379  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
1380  relation.  relation.
1381    
1382  =item param1, param2, ..., paramN  Finally, you can limit the number of rows returned by adding a LIMIT clause. The LIMIT must
1383    be the last thing in the filter clause, and it contains only the word "LIMIT" followed by
1384    a positive number. So, for example
1385    
1386    C<< "Genome(genus) = ? ORDER BY Genome(species) LIMIT 10" >>
1387    
1388  Parameter values to be substituted into the filter clause.  will only return the first ten genomes for the specified genus. The ORDER BY clause is not
1389    required. For example, to just get the first 10 genomes in the B<Genome> table, you could
1390    use
1391    
1392    C<< "LIMIT 10" >>
1393    
1394    =item params
1395    
1396    Reference to a list of parameter values to be substituted into the filter clause.
1397    
1398  =item RETURN  =item RETURN
1399    
# Line 617  Line 1405 
1405    
1406  sub Get {  sub Get {
1407          # Get the parameters.          # Get the parameters.
1408          my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $objectNames, $filterClause, $params) = @_;
1409          # Construct the SELECT statement. The general pattern is      # Process the SQL stuff.
1410          #      my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1411          # SELECT name1.*, name2.*, ... nameN.* FROM name1, name2, ... nameN          $self->_SetupSQL($objectNames, $filterClause);
1412          #      # Create the query.
1413          my $dbh = $self->{_dbh};      my $command = "SELECT DISTINCT " . join(".*, ", @{$mappedNameListRef}) .
1414          my $command = "SELECT DISTINCT " . join('.*, ', @{$objectNames}) . ".* FROM " .          ".* $suffix";
1415                                  join(', ', @{$objectNames});      my $sth = $self->_GetStatementHandle($command, $params);
1416          # Check for a filter clause.      # Now we create the relation map, which enables DBQuery to determine the order, name
1417          if ($filterClause) {      # and mapped name for each object in the query.
1418                  # Here we have one, so we convert its field names and add it to the query. First,      my @relationMap = ();
1419                  # We create a copy of the filter string we can work with.      for my $mappedName (@{$mappedNameListRef}) {
1420                  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;  
1421                  }                  }
1422                  # We are ready to begin. We loop through the object names, replacing each      # Return the statement object.
1423                  # object name's field references by the corresponding SQL field reference.      my $retVal = DBQuery::_new($self, $sth, \@relationMap);
1424                  # Along the way, if we find a secondary relation, we will need to add it      return $retVal;
1425                  # to the FROM clause.  }
1426                  for my $objectName (@sortedNames) {  
1427                          # Get the length of the object name plus 2. This is the value we add to the  
1428                          # size of the field name to determine the size of the field reference as a  
1429                          # whole.  =head3 Search
1430                          my $nameLength = 2 + length $objectName;  
1431                          # Get the object's field list.  C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>
1432                          my $fieldList = $self->_GetFieldTable($objectName);  
1433                          # Find the field references for this object.  Perform a full text search with filtering. The search will be against a specified object
1434                          while ($filterString =~ m/$objectName\(([^)]*)\)/g) {  in the object name list. That object will get an extra field containing the search
1435                                  # At this point, $1 contains the field name, and the current position  relevance. Note that except for the search expression, the parameters of this method are
1436                                  # is set immediately after the final parenthesis. We pull out the name of  the same as those for L</Get> and follow the same rules.
1437                                  # the field and the position and length of the field reference as a whole.  
1438                                  my $fieldName = $1;  =over 4
1439                                  my $len = $nameLength + length $fieldName;  
1440                                  my $pos = pos($filterString) - $len;  =item searchExpression
1441                                  # Insure the field exists.  
1442                                  if (!exists $fieldList->{$fieldName}) {  Boolean search expression for the text fields of the target object. The default mode for
1443                                          Confess("Field $fieldName not found for object $objectName.");  a Boolean search expression is OR, but we want the default to be AND, so we will
1444    add a C<+> operator to each word with no other operator before it.
1445    
1446    =item idx
1447    
1448    Index in the I<$objectNames> list of the table to be searched in full-text mode.
1449    
1450    =item objectNames
1451    
1452    List containing the names of the entity and relationship objects to be retrieved.
1453    
1454    =item filterClause
1455    
1456    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1457    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
1458    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
1459    in the filter clause should be added to the parameter list as additional parameters. The
1460    fields in a filter clause can come from primary entity relations, relationship relations,
1461    or secondary entity relations; however, all of the entities and relationships involved must
1462    be included in the list of object names.
1463    
1464    =item params
1465    
1466    Reference to a list of parameter values to be substituted into the filter clause.
1467    
1468    =item RETURN
1469    
1470    Returns a query object for the specified search.
1471    
1472    =back
1473    
1474    =cut
1475    
1476    sub Search {
1477        # Get the parameters.
1478        my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1479        # Declare the return variable.
1480        my $retVal;
1481        # Create a safety copy of the parameter list. Note we have to be careful to insure
1482        # a parameter list exists before we copy it.
1483        my @myParams = ();
1484        if (defined $params) {
1485            @myParams = @{$params};
1486        }
1487        # Get the first object's structure so we have access to the searchable fields.
1488        my $object1Name = $objectNames->[$idx];
1489        my $object1Structure = $self->_GetStructure($object1Name);
1490        # Get the field list.
1491        if (! exists $object1Structure->{searchFields}) {
1492            Confess("No searchable index for $object1Name.");
1493        } else {
1494            # Get the field list.
1495            my @fields = @{$object1Structure->{searchFields}};
1496            # Clean the search expression.
1497            my $actualKeywords = $self->CleanKeywords($searchExpression);
1498            # Prefix a "+" to each uncontrolled word. This converts the default
1499            # search mode from OR to AND.
1500            $actualKeywords =~ s/(^|\s)(\w|")/$1\+$2/g;
1501            Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1502            # We need two match expressions, one for the filter clause and one in the
1503            # query itself. Both will use a parameter mark, so we need to push the
1504            # search expression onto the front of the parameter list twice.
1505            unshift @myParams, $actualKeywords, $actualKeywords;
1506            # Build the match expression.
1507            my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
1508            my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
1509            # Process the SQL stuff.
1510            my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1511                $self->_SetupSQL($objectNames, $filterClause, $matchClause);
1512            # Create the query. Note that the match clause is inserted at the front of
1513            # the select fields.
1514            my $command = "SELECT DISTINCT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .
1515                ".* $suffix";
1516            my $sth = $self->_GetStatementHandle($command, \@myParams);
1517            # Now we create the relation map, which enables DBQuery to determine the order, name
1518            # and mapped name for each object in the query.
1519            my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
1520            # Return the statement object.
1521            $retVal = DBQuery::_new($self, $sth, \@relationMap, $object1Name);
1522        }
1523        return $retVal;
1524    }
1525    
1526    =head3 GetFlat
1527    
1528    C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>
1529    
1530    This is a variation of L</GetAll> that asks for only a single field per record and
1531    returns a single flattened list.
1532    
1533    =over 4
1534    
1535    =item objectNames
1536    
1537    List containing the names of the entity and relationship objects to be retrieved.
1538    
1539    =item filterClause
1540    
1541    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1542    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
1543    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
1544    parameter list as additional parameters. The fields in a filter clause can come from primary
1545    entity relations, relationship relations, or secondary entity relations; however, all of the
1546    entities and relationships involved must be included in the list of object names.
1547    
1548    =item parameterList
1549    
1550    List of the parameters to be substituted in for the parameters marks in the filter clause.
1551    
1552    =item field
1553    
1554    Name of the field to be used to get the elements of the list returned.
1555    
1556    =item RETURN
1557    
1558    Returns a list of values.
1559    
1560    =back
1561    
1562    =cut
1563    #: Return Type @;
1564    sub GetFlat {
1565        # Get the parameters.
1566        my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
1567        # Construct the query.
1568        my $query = $self->Get($objectNames, $filterClause, $parameterList);
1569        # Create the result list.
1570        my @retVal = ();
1571        # Loop through the records, adding the field values found to the result list.
1572        while (my $row = $query->Fetch()) {
1573            push @retVal, $row->Value($field);
1574        }
1575        # Return the list created.
1576        return @retVal;
1577    }
1578    
1579    =head3 SpecialFields
1580    
1581    C<< my %specials = $erdb->SpecialFields($entityName); >>
1582    
1583    Return a hash mapping special fields in the specified entity to the value of their
1584    C<special> attribute. This enables the subclass to get access to the special field
1585    attributes without needed to plumb the internal ERDB data structures.
1586    
1587    =over 4
1588    
1589    =item entityName
1590    
1591    Name of the entity whose special fields are desired.
1592    
1593    =item RETURN
1594    
1595    Returns a hash. The keys of the hash are the special field names, and the values
1596    are the values from each special field's C<special> attribute.
1597    
1598    =back
1599    
1600    =cut
1601    
1602    sub SpecialFields {
1603        # Get the parameters.
1604        my ($self, $entityName) = @_;
1605        # Declare the return variable.
1606        my %retVal = ();
1607        # Find the entity's data structure.
1608        my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1609        # Loop through its fields, adding each special field to the return hash.
1610        my $fieldHash = $entityData->{Fields};
1611        for my $fieldName (keys %{$fieldHash}) {
1612            my $fieldData = $fieldHash->{$fieldName};
1613            if (exists $fieldData->{special}) {
1614                $retVal{$fieldName} = $fieldData->{special};
1615            }
1616        }
1617        # Return the result.
1618        return %retVal;
1619    }
1620    
1621    =head3 Delete
1622    
1623    C<< my $stats = $erdb->Delete($entityName, $objectID, %options); >>
1624    
1625    Delete an entity instance from the database. The instance is deleted along with all entity and
1626    relationship instances dependent on it. The definition of I<dependence> is recursive.
1627    
1628    An object is always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many
1629    relationship connected to a dependent entity or if it is the "to" entity connected to a 1-to-many
1630    dependent relationship.
1631    
1632    =over 4
1633    
1634    =item entityName
1635    
1636    Name of the entity type for the instance being deleted.
1637    
1638    =item objectID
1639    
1640    ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),
1641    then it is presumed to by a LIKE pattern.
1642    
1643    =item options
1644    
1645    A hash detailing the options for this delete operation.
1646    
1647    =item RETURN
1648    
1649    Returns a statistics object indicating how many records of each particular table were
1650    deleted.
1651    
1652    =back
1653    
1654    The permissible options for this method are as follows.
1655    
1656    =over 4
1657    
1658    =item testMode
1659    
1660    If TRUE, then the delete statements will be traced, but no changes will be made to the database.
1661    
1662    =item keepRoot
1663    
1664    If TRUE, then the entity instances will not be deleted, only the dependent records.
1665    
1666    =back
1667    
1668    =cut
1669    #: Return Type $%;
1670    sub Delete {
1671        # Get the parameters.
1672        my ($self, $entityName, $objectID, %options) = @_;
1673        # Declare the return variable.
1674        my $retVal = Stats->new();
1675        # Get the DBKernel object.
1676        my $db = $self->{_dbh};
1677        # We're going to generate all the paths branching out from the starting entity. One of
1678        # the things we have to be careful about is preventing loops. We'll use a hash to
1679        # determine if we've hit a loop.
1680        my %alreadyFound = ();
1681        # These next lists will serve as our result stack. We start by pushing object lists onto
1682        # the stack, and then popping them off to do the deletes. This means the deletes will
1683        # start with the longer paths before getting to the shorter ones. That, in turn, makes
1684        # sure we don't delete records that might be needed to forge relationships back to the
1685        # original item. We have two lists-- one for TO-relationships, and one for
1686        # FROM-relationships and entities.
1687        my @fromPathList = ();
1688        my @toPathList = ();
1689        # This final list is used to remember what work still needs to be done. We push paths
1690        # onto the list, then pop them off to extend the paths. We prime it with the starting
1691        # point. Note that we will work hard to insure that the last item on a path in the
1692        # to-do list is always an entity.
1693        my @todoList = ([$entityName]);
1694        while (@todoList) {
1695            # Get the current path.
1696            my $current = pop @todoList;
1697            # Copy it into a list.
1698            my @stackedPath = @{$current};
1699            # Pull off the last item on the path. It will always be an entity.
1700            my $myEntityName = pop @stackedPath;
1701            # Add it to the alreadyFound list.
1702            $alreadyFound{$myEntityName} = 1;
1703            # Figure out if we need to delete this entity.
1704            if ($myEntityName ne $entityName || ! $options{keepRoot}) {
1705                # Get the entity data.
1706                my $entityData = $self->_GetStructure($myEntityName);
1707                # Loop through the entity's relations. A DELETE command will be needed for each of them.
1708                my $relations = $entityData->{Relations};
1709                for my $relation (keys %{$relations}) {
1710                    my @augmentedList = (@stackedPath, $relation);
1711                    push @fromPathList, \@augmentedList;
1712                }
1713            }
1714            # Now we need to look for relationships connected to this entity.
1715            my $relationshipList = $self->{_metaData}->{Relationships};
1716            for my $relationshipName (keys %{$relationshipList}) {
1717                my $relationship = $relationshipList->{$relationshipName};
1718                # Check the FROM field. We're only interested if it's us.
1719                if ($relationship->{from} eq $myEntityName) {
1720                    # Add the path to this relationship.
1721                    my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1722                    push @fromPathList, \@augmentedList;
1723                    # Check the arity. If it's MM we're done. If it's 1M
1724                    # and the target hasn't been seen yet, we want to
1725                    # stack the entity for future processing.
1726                    if ($relationship->{arity} eq '1M') {
1727                        my $toEntity = $relationship->{to};
1728                        if (! exists $alreadyFound{$toEntity}) {
1729                            # Here we have a new entity that's dependent on
1730                            # the current entity, so we need to stack it.
1731                            my @stackList = (@augmentedList, $toEntity);
1732                            push @fromPathList, \@stackList;
1733                        } else {
1734                            Trace("$toEntity ignored because it occurred previously.") if T(4);
1735                        }
1736                    }
1737                }
1738                # Now check the TO field. In this case only the relationship needs
1739                # deletion.
1740                if ($relationship->{to} eq $myEntityName) {
1741                    my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1742                    push @toPathList, \@augmentedList;
1743                }
1744            }
1745        }
1746        # Create the first qualifier for the WHERE clause. This selects the
1747        # keys of the primary entity records to be deleted. When we're deleting
1748        # from a dependent table, we construct a join path from the first qualifier
1749        # to the table containing the dependent records to delete.
1750        my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
1751        # We need to make two passes. The first is through the to-list, and
1752        # the second through the from-list. The from-list is second because
1753        # the to-list may need to pass through some of the entities the
1754        # from-list would delete.
1755        my %stackList = ( from_link => \@fromPathList, to_link => \@toPathList );
1756        # Now it's time to do the deletes. We do it in two passes.
1757        for my $keyName ('to_link', 'from_link') {
1758            # Get the list for this key.
1759            my @pathList = @{$stackList{$keyName}};
1760            Trace(scalar(@pathList) . " entries in path list for $keyName.") if T(3);
1761            # Loop through this list.
1762            while (my $path = pop @pathList) {
1763                # Get the table whose rows are to be deleted.
1764                my @pathTables = @{$path};
1765                # Start the DELETE statement. We need to call DBKernel because the
1766                # syntax of a DELETE-USING varies among DBMSs.
1767                my $target = $pathTables[$#pathTables];
1768                my $stmt = $db->SetUsing(@pathTables);
1769                # Now start the WHERE. The first thing is the ID field from the starting table. That
1770                # starting table will either be the entity relation or one of the entity's
1771                # sub-relations.
1772                $stmt .= " WHERE $pathTables[0].id $qualifier";
1773                # Now we run through the remaining entities in the path, connecting them up.
1774                for (my $i = 1; $i <= $#pathTables; $i += 2) {
1775                    # Connect the current relationship to the preceding entity.
1776                    my ($entity, $rel) = @pathTables[$i-1,$i];
1777                    # The style of connection depends on the direction of the relationship.
1778                    $stmt .= " AND $entity.id = $rel.$keyName";
1779                    if ($i + 1 <= $#pathTables) {
1780                        # Here there's a next entity, so connect that to the relationship's
1781                        # to-link.
1782                        my $entity2 = $pathTables[$i+1];
1783                        $stmt .= " AND $rel.to_link = $entity2.id";
1784                    }
1785                }
1786                # Now we have our desired DELETE statement.
1787                if ($options{testMode}) {
1788                    # Here the user wants to trace without executing.
1789                    Trace($stmt) if T(0);
1790                } else {
1791                    # Here we can delete. Note that the SQL method dies with a confession
1792                    # if an error occurs, so we just go ahead and do it.
1793                    Trace("Executing delete from $target using '$objectID'.") if T(3);
1794                    my $rv = $db->SQL($stmt, 0, $objectID);
1795                    # Accumulate the statistics for this delete. The only rows deleted
1796                    # are from the target table, so we use its name to record the
1797                    # statistic.
1798                    $retVal->Add($target, $rv);
1799                }
1800            }
1801        }
1802        # Return the result.
1803        return $retVal;
1804    }
1805    
1806    =head3 Disconnect
1807    
1808    C<< $erdb->Disconnect($relationshipName, $originEntityName, $originEntityID); >>
1809    
1810    Disconnect an entity instance from all the objects to which it is related. This
1811    will delete each relationship instance that connects to the specified entity.
1812    
1813    =over 4
1814    
1815    =item relationshipName
1816    
1817    Name of the relationship whose instances are to be deleted.
1818    
1819    =item originEntityName
1820    
1821    Name of the entity that is to be disconnected.
1822    
1823    =item originEntityID
1824    
1825    ID of the entity that is to be disconnected.
1826    
1827    =back
1828    
1829    =cut
1830    
1831    sub Disconnect {
1832        # Get the parameters.
1833        my ($self, $relationshipName, $originEntityName, $originEntityID) = @_;
1834        # Get the relationship descriptor.
1835        my $structure = $self->_GetStructure($relationshipName);
1836        # Insure we have a relationship.
1837        if (! exists $structure->{from}) {
1838            Confess("$relationshipName is not a relationship in the database.");
1839        } else {
1840            # Get the database handle.
1841            my $dbh = $self->{_dbh};
1842            # We'll set this value to 1 if we find our entity.
1843            my $found = 0;
1844            # Loop through the ends of the relationship.
1845            for my $dir ('from', 'to') {
1846                if ($structure->{$dir} eq $originEntityName) {
1847                    # Delete all relationship instances on this side of the entity instance.
1848                    $dbh->SQL("DELETE FROM $relationshipName WHERE ${dir}_link = ?", 0, $originEntityID);
1849                    $found = 1;
1850                }
1851            }
1852            # Insure we found the entity on at least one end.
1853            if (! $found) {
1854                Confess("Entity \"$originEntityName\" does not use $relationshipName.");
1855            }
1856        }
1857    }
1858    
1859    =head3 DeleteRow
1860    
1861    C<< $erdb->DeleteRow($relationshipName, $fromLink, $toLink, \%values); >>
1862    
1863    Delete a row from a relationship. In most cases, only the from-link and to-link are
1864    needed; however, for relationships with intersection data values can be specified
1865    for the other fields using a hash.
1866    
1867    =over 4
1868    
1869    =item relationshipName
1870    
1871    Name of the relationship from which the row is to be deleted.
1872    
1873    =item fromLink
1874    
1875    ID of the entity instance in the From direction.
1876    
1877    =item toLink
1878    
1879    ID of the entity instance in the To direction.
1880    
1881    =item values
1882    
1883    Reference to a hash of other values to be used for filtering the delete.
1884    
1885    =back
1886    
1887    =cut
1888    
1889    sub DeleteRow {
1890        # Get the parameters.
1891        my ($self, $relationshipName, $fromLink, $toLink, $values) = @_;
1892        # Create a hash of all the filter information.
1893        my %filter = ('from-link' => $fromLink, 'to-link' => $toLink);
1894        if (defined $values) {
1895            for my $key (keys %{$values}) {
1896                $filter{$key} = $values->{$key};
1897            }
1898        }
1899        # Build an SQL statement out of the hash.
1900        my @filters = ();
1901        my @parms = ();
1902        for my $key (keys %filter) {
1903            push @filters, _FixName($key) . " = ?";
1904            push @parms, $filter{$key};
1905        }
1906        Trace("Parms for delete row are " . join(", ", map { "\"$_\"" } @parms) . ".") if T(SQL => 4);
1907        my $command = "DELETE FROM $relationshipName WHERE " .
1908                      join(" AND ", @filters);
1909        # Execute it.
1910        my $dbh = $self->{_dbh};
1911        $dbh->SQL($command, undef, @parms);
1912    }
1913    
1914    =head3 SortNeeded
1915    
1916    C<< my $parms = $erdb->SortNeeded($relationName); >>
1917    
1918    Return the pipe command for the sort that should be applied to the specified
1919    relation when creating the load file.
1920    
1921    For example, if the load file should be sorted ascending by the first
1922    field, this method would return
1923    
1924        sort -k1 -t"\t"
1925    
1926    If the first field is numeric, the method would return
1927    
1928        sort -k1n -t"\t"
1929    
1930    Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate
1931    keys using a sort.
1932    
1933    =over 4
1934    
1935    =item relationName
1936    
1937    Name of the relation to be examined.
1938    
1939    =item
1940    
1941    Returns the sort command to use for sorting the relation, suitable for piping.
1942    
1943    =back
1944    
1945    =cut
1946    #: Return Type $;
1947    sub SortNeeded {
1948        # Get the parameters.
1949        my ($self, $relationName) = @_;
1950        # Declare a descriptor to hold the names of the key fields.
1951        my @keyNames = ();
1952        # Get the relation structure.
1953        my $relationData = $self->_FindRelation($relationName);
1954        # Find out if the relation is a primary entity relation,
1955        # a relationship relation, or a secondary entity relation.
1956        my $entityTable = $self->{_metaData}->{Entities};
1957        my $relationshipTable = $self->{_metaData}->{Relationships};
1958        if (exists $entityTable->{$relationName}) {
1959            # Here we have a primary entity relation.
1960            push @keyNames, "id";
1961        } elsif (exists $relationshipTable->{$relationName}) {
1962            # Here we have a relationship. We sort using the FROM index.
1963            my $relationshipData = $relationshipTable->{$relationName};
1964            my $index = $relationData->{Indexes}->{idxFrom};
1965            push @keyNames, @{$index->{IndexFields}};
1966        } else {
1967            # Here we have a secondary entity relation, so we have a sort on the ID field.
1968            push @keyNames, "id";
1969        }
1970        # Now we parse the key names into sort parameters. First, we prime the return
1971        # string.
1972        my $retVal = "sort -t\"\t\" ";
1973        # Get the relation's field list.
1974        my @fields = @{$relationData->{Fields}};
1975        # Loop through the keys.
1976        for my $keyData (@keyNames) {
1977            # Get the key and the ordering.
1978            my ($keyName, $ordering);
1979            if ($keyData =~ /^([^ ]+) DESC/) {
1980                ($keyName, $ordering) = ($1, "descending");
1981            } else {
1982                ($keyName, $ordering) = ($keyData, "ascending");
1983            }
1984            # Find the key's position and type.
1985            my $fieldSpec;
1986            for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {
1987                my $thisField = $fields[$i];
1988                if ($thisField->{name} eq $keyName) {
1989                    # Get the sort modifier for this field type. The modifier
1990                    # decides whether we're using a character, numeric, or
1991                    # floating-point sort.
1992                    my $modifier = $TypeTable{$thisField->{type}}->{sort};
1993                    # If the index is descending for this field, denote we want
1994                    # to reverse the sort order on this field.
1995                    if ($ordering eq 'descending') {
1996                        $modifier .= "r";
1997                    }
1998                    # Store the position and modifier into the field spec, which
1999                    # will stop the inner loop. Note that the field number is
2000                    # 1-based in the sort command, so we have to increment the
2001                    # index.
2002                    $fieldSpec = ($i + 1) . $modifier;
2003                }
2004            }
2005            # Add this field to the sort command.
2006            $retVal .= " -k$fieldSpec";
2007        }
2008        # Return the result.
2009        return $retVal;
2010    }
2011    
2012    =head3 GetList
2013    
2014    C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>
2015    
2016    Return a list of object descriptors for the specified objects as determined by the
2017    specified filter clause.
2018    
2019    This method is essentially the same as L</Get> except it returns a list of objects rather
2020    than a query object that can be used to get the results one record at a time.
2021    
2022    =over 4
2023    
2024    =item objectNames
2025    
2026    List containing the names of the entity and relationship objects to be retrieved.
2027    
2028    =item filterClause
2029    
2030    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
2031    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
2032    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
2033    in the filter clause should be added to the parameter list as additional parameters. The
2034    fields in a filter clause can come from primary entity relations, relationship relations,
2035    or secondary entity relations; however, all of the entities and relationships involved must
2036    be included in the list of object names.
2037    
2038    The filter clause can also specify a sort order. To do this, simply follow the filter string
2039    with an ORDER BY clause. For example, the following filter string gets all genomes for a
2040    particular genus and sorts them by species name.
2041    
2042    C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
2043    
2044    The rules for field references in a sort order are the same as those for field references in the
2045    filter clause in general; however, odd things may happen if a sort field is from a secondary
2046    relation.
2047    
2048    =item params
2049    
2050    Reference to a list of parameter values to be substituted into the filter clause.
2051    
2052    =item RETURN
2053    
2054    Returns a list of B<DBObject>s that satisfy the query conditions.
2055    
2056    =back
2057    
2058    =cut
2059    #: Return Type @%
2060    sub GetList {
2061        # Get the parameters.
2062        my ($self, $objectNames, $filterClause, $params) = @_;
2063        # Declare the return variable.
2064        my @retVal = ();
2065        # Perform the query.
2066        my $query = $self->Get($objectNames, $filterClause, $params);
2067        # Loop through the results.
2068        while (my $object = $query->Fetch) {
2069            push @retVal, $object;
2070        }
2071        # Return the result.
2072        return @retVal;
2073    }
2074    
2075    =head3 GetCount
2076    
2077    C<< my $count = $erdb->GetCount(\@objectNames, $filter, \@params); >>
2078    
2079    Return the number of rows found by a specified query. This method would
2080    normally be used to count the records in a single table. For example, in a
2081    genetics database
2082    
2083        my $count = $erdb->GetCount(['Genome'], 'Genome(genus-species) LIKE ?', ['homo %']);
2084    
2085    would return the number of genomes for the genus I<homo>. It is conceivable, however,
2086    to use it to return records based on a join. For example,
2087    
2088        my $count = $erdb->GetCount(['HasFeature', 'Genome'], 'Genome(genus-species) LIKE ?',
2089                                    ['homo %']);
2090    
2091    would return the number of features for genomes in the genus I<homo>. Note that
2092    only the rows from the first table are counted. If the above command were
2093    
2094        my $count = $erdb->GetCount(['Genome', 'Feature'], 'Genome(genus-species) LIKE ?',
2095                                    ['homo %']);
2096    
2097    it would return the number of genomes, not the number of genome/feature pairs.
2098    
2099    =over 4
2100    
2101    =item objectNames
2102    
2103    Reference to a list of the objects (entities and relationships) included in the
2104    query.
2105    
2106    =item filter
2107    
2108    A filter clause for restricting the query. The rules are the same as for the L</Get>
2109    method.
2110    
2111    =item params
2112    
2113    Reference to a list of the parameter values to be substituted for the parameter marks
2114    in the filter.
2115    
2116    =item RETURN
2117    
2118    Returns a count of the number of records in the first table that would satisfy
2119    the query.
2120    
2121    =back
2122    
2123    =cut
2124    
2125    sub GetCount {
2126        # Get the parameters.
2127        my ($self, $objectNames, $filter, $params) = @_;
2128        # Insure the params argument is an array reference if the caller left it off.
2129        if (! defined($params)) {
2130            $params = [];
2131        }
2132        # Declare the return variable.
2133        my $retVal;
2134        # Find out if we're counting an entity or a relationship.
2135        my $countedField;
2136        if ($self->IsEntity($objectNames->[0])) {
2137            $countedField = "id";
2138        } else {
2139            # For a relationship we count the to-link because it's usually more
2140            # numerous. Note we're automatically converting to the SQL form
2141            # of the field name (to_link vs. to-link).
2142            $countedField = "to_link";
2143        }
2144        # Create the SQL command suffix to get the desired records.
2145        my ($suffix, $mappedNameListRef, $mappedNameHashRef) = $self->_SetupSQL($objectNames,
2146                                                                                $filter);
2147        # Prefix it with text telling it we want a record count.
2148        my $firstObject = $mappedNameListRef->[0];
2149        my $command = "SELECT COUNT($firstObject.$countedField) $suffix";
2150        # Prepare and execute the command.
2151        my $sth = $self->_GetStatementHandle($command, $params);
2152        # Get the count value.
2153        ($retVal) = $sth->fetchrow_array();
2154        # Check for a problem.
2155        if (! defined($retVal)) {
2156            if ($sth->err) {
2157                # Here we had an SQL error.
2158                Confess("Error retrieving row count: " . $sth->errstr());
2159            } else {
2160                # Here we have no result.
2161                Confess("No result attempting to retrieve row count.");
2162            }
2163        }
2164        # Return the result.
2165        return $retVal;
2166    }
2167    
2168    =head3 ComputeObjectSentence
2169    
2170    C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>
2171    
2172    Check an object name, and if it is a relationship convert it to a relationship sentence.
2173    
2174    =over 4
2175    
2176    =item objectName
2177    
2178    Name of the entity or relationship.
2179    
2180    =item RETURN
2181    
2182    Returns a string containing the entity name or a relationship sentence.
2183    
2184    =back
2185    
2186    =cut
2187    
2188    sub ComputeObjectSentence {
2189        # Get the parameters.
2190        my ($self, $objectName) = @_;
2191        # Set the default return value.
2192        my $retVal = $objectName;
2193        # Look for the object as a relationship.
2194        my $relTable = $self->{_metaData}->{Relationships};
2195        if (exists $relTable->{$objectName}) {
2196            # Get the relationship sentence.
2197            $retVal = _ComputeRelationshipSentence($objectName, $relTable->{$objectName});
2198        }
2199        # Return the result.
2200        return $retVal;
2201    }
2202    
2203    =head3 DumpRelations
2204    
2205    C<< $erdb->DumpRelations($outputDirectory); >>
2206    
2207    Write the contents of all the relations to tab-delimited files in the specified directory.
2208    Each file will have the same name as the relation dumped, with an extension of DTX.
2209    
2210    =over 4
2211    
2212    =item outputDirectory
2213    
2214    Name of the directory into which the relation files should be dumped.
2215    
2216    =back
2217    
2218    =cut
2219    
2220    sub DumpRelations {
2221        # Get the parameters.
2222        my ($self, $outputDirectory) = @_;
2223        # Now we need to run through all the relations. First, we loop through the entities.
2224        my $metaData = $self->{_metaData};
2225        my $entities = $metaData->{Entities};
2226        for my $entityName (keys %{$entities}) {
2227            my $entityStructure = $entities->{$entityName};
2228            # Get the entity's relations.
2229            my $relationList = $entityStructure->{Relations};
2230            # Loop through the relations, dumping them.
2231            for my $relationName (keys %{$relationList}) {
2232                my $relation = $relationList->{$relationName};
2233                $self->_DumpRelation($outputDirectory, $relationName, $relation);
2234            }
2235        }
2236        # Next, we loop through the relationships.
2237        my $relationships = $metaData->{Relationships};
2238        for my $relationshipName (keys %{$relationships}) {
2239            my $relationshipStructure = $relationships->{$relationshipName};
2240            # Dump this relationship's relation.
2241            $self->_DumpRelation($outputDirectory, $relationshipName, $relationshipStructure->{Relations}->{$relationshipName});
2242        }
2243    }
2244    
2245    =head3 InsertValue
2246    
2247    C<< $erdb->InsertValue($entityID, $fieldName, $value); >>
2248    
2249    This method will insert a new value into the database. The value must be one
2250    associated with a secondary relation, since primary values cannot be inserted:
2251    they occur exactly once. Secondary values, on the other hand, can be missing
2252    or multiply-occurring.
2253    
2254    =over 4
2255    
2256    =item entityID
2257    
2258    ID of the object that is to receive the new value.
2259    
2260    =item fieldName
2261    
2262    Field name for the new value-- this includes the entity name, since
2263    field names are of the format I<objectName>C<(>I<fieldName>C<)>.
2264    
2265    =item value
2266    
2267    New value to be put in the field.
2268    
2269    =back
2270    
2271    =cut
2272    
2273    sub InsertValue {
2274        # Get the parameters.
2275        my ($self, $entityID, $fieldName, $value) = @_;
2276        # Parse the entity name and the real field name.
2277        if ($fieldName =~ /^([^(]+)\(([^)]+)\)/) {
2278            my $entityName = $1;
2279            my $fieldTitle = $2;
2280            # Get its descriptor.
2281            if (!$self->IsEntity($entityName)) {
2282                Confess("$entityName is not a valid entity.");
2283            } else {
2284                my $entityData = $self->{_metaData}->{Entities}->{$entityName};
2285                # Find the relation containing this field.
2286                my $fieldHash = $entityData->{Fields};
2287                if (! exists $fieldHash->{$fieldTitle}) {
2288                    Confess("$fieldTitle not found in $entityName.");
2289                } else {
2290                    my $relation = $fieldHash->{$fieldTitle}->{relation};
2291                    if ($relation eq $entityName) {
2292                        Confess("Cannot do InsertValue on primary field $fieldTitle of $entityName.");
2293                    } else {
2294                        # Now we can create an INSERT statement.
2295                        my $dbh = $self->{_dbh};
2296                        my $fixedName = _FixName($fieldTitle);
2297                        my $statement = "INSERT INTO $relation (id, $fixedName) VALUES(?, ?)";
2298                        # Execute the command.
2299                        $dbh->SQL($statement, 0, $entityID, $value);
2300                    }
2301                }
2302            }
2303        } else {
2304            Confess("$fieldName is not a valid field name.");
2305        }
2306    }
2307    
2308    =head3 InsertObject
2309    
2310    C<< $erdb->InsertObject($objectType, \%fieldHash); >>
2311    
2312    Insert an object into the database. The object is defined by a type name and then a hash
2313    of field names to values. Field values in the primary relation are represented by scalars.
2314    (Note that for relationships, the primary relation is the B<only> relation.)
2315    Field values for the other relations comprising the entity are always list references. For
2316    example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases
2317    C<ZP_00210270.1> and C<gi|46206278>.
2318    
2319    C<< $erdb->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>
2320    
2321    The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
2322    property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
2323    
2324    C<< $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>
2325    
2326    =over 4
2327    
2328    =item newObjectType
2329    
2330    Type name of the object to insert.
2331    
2332    =item fieldHash
2333    
2334    Hash of field names to values.
2335    
2336    =back
2337    
2338    =cut
2339    
2340    sub InsertObject {
2341        # Get the parameters.
2342        my ($self, $newObjectType, $fieldHash) = @_;
2343        # Denote that so far we appear successful.
2344        my $retVal = 1;
2345        # Get the database handle.
2346        my $dbh = $self->{_dbh};
2347        # Get the relation list.
2348        my $relationTable = $self->_GetRelationTable($newObjectType);
2349        # Loop through the relations. We'll build insert statements for each one. If a relation is
2350        # secondary, we may end up generating multiple insert statements. If an error occurs, we
2351        # stop the loop.
2352        my @relationList = keys %{$relationTable};
2353        for (my $i = 0; $retVal && $i <= $#relationList; $i++) {
2354            my $relationName = $relationList[$i];
2355            my $relationDefinition = $relationTable->{$relationName};
2356            # Get the relation's fields. For each field we will collect a value in the corresponding
2357            # position of the @valueList array. If one of the fields is missing, we will add it to the
2358            # @missing list.
2359            my @fieldList = @{$relationDefinition->{Fields}};
2360            my @fieldNameList = ();
2361            my @valueList = ();
2362            my @missing = ();
2363            my $recordCount = 1;
2364            for my $fieldDescriptor (@fieldList) {
2365                # Get the field name and save it. Note we need to fix it up so the hyphens
2366                # are converted to underscores.
2367                my $fieldName = $fieldDescriptor->{name};
2368                push @fieldNameList, _FixName($fieldName);
2369                # Look for the named field in the incoming structure. Note that we are looking
2370                # for the real field name, not the fixed-up one!
2371                if (exists $fieldHash->{$fieldName}) {
2372                    # Here we found the field. Stash it in the value list.
2373                    my $value = $fieldHash->{$fieldName};
2374                    push @valueList, $value;
2375                    # If the value is a list, we may need to increment the record count.
2376                    if (ref $value eq "ARRAY") {
2377                        my $thisCount = @{$value};
2378                        if ($recordCount == 1) {
2379                            # Here we have our first list, so we save its count.
2380                            $recordCount = $thisCount;
2381                        } elsif ($recordCount != $thisCount) {
2382                            # Here we have a second list, so its length has to match the
2383                            # previous lists.
2384                            Trace("Field $value in new $newObjectType object has an invalid list length $thisCount. Expected $recordCount.") if T(0);
2385                            $retVal = 0;
2386                        }
2387                    }
2388                } else {
2389                    # Here the field is not present. Flag it as missing.
2390                    push @missing, $fieldName;
2391                }
2392            }
2393            # If we are the primary relation, add the new-record flag.
2394            if ($relationName eq $newObjectType) {
2395                push @valueList, 1;
2396                push @fieldNameList, "new_record";
2397            }
2398            # Only proceed if there are no missing fields.
2399            if (@missing > 0) {
2400                Trace("Relation $relationName for $newObjectType skipped due to missing fields: " .
2401                    join(' ', @missing)) if T(1);
2402            } else {
2403                # Build the INSERT statement.
2404                my $statement = "INSERT INTO $relationName (" . join (', ', @fieldNameList) .
2405                    ") VALUES (";
2406                # Create a marker list of the proper size and put it in the statement.
2407                my @markers = ();
2408                while (@markers < @fieldNameList) { push @markers, '?'; }
2409                $statement .= join(', ', @markers) . ")";
2410                # We have the insert statement, so prepare it.
2411                my $sth = $dbh->prepare_command($statement);
2412                Trace("Insert statement prepared: $statement") if T(3);
2413                # Now we loop through the values. If a value is scalar, we use it unmodified. If it's
2414                # a list, we use the current element. The values are stored in the @parameterList array.
2415                my $done = 0;
2416                for (my $i = 0; $i < $recordCount; $i++) {
2417                    # Clear the parameter list array.
2418                    my @parameterList = ();
2419                    # Loop through the values.
2420                    for my $value (@valueList) {
2421                        # Check to see if this is a scalar value.
2422                        if (ref $value eq "ARRAY") {
2423                            # Here we have a list value. Pull the current entry.
2424                            push @parameterList, $value->[$i];
2425                        } else {
2426                            # Here we have a scalar value. Use it unmodified.
2427                            push @parameterList, $value;
2428                        }
2429                    }
2430                    # Execute the INSERT statement with the specified parameter list.
2431                    $retVal = $sth->execute(@parameterList);
2432                    if (!$retVal) {
2433                        my $errorString = $sth->errstr();
2434                        Confess("Error inserting into $relationName: $errorString");
2435                    }
2436                }
2437            }
2438        }
2439        # Return a 1 for backward compatability.
2440        return 1;
2441    }
2442    
2443    =head3 UpdateEntity
2444    
2445    C<< $erdb->UpdateEntity($entityName, $id, \%fields); >>
2446    
2447    Update the values of an entity. This is an unprotected update, so it should only be
2448    done if the database resides on a database server.
2449    
2450    =over 4
2451    
2452    =item entityName
2453    
2454    Name of the entity to update. (This is the entity type.)
2455    
2456    =item id
2457    
2458    ID of the entity to update. If no entity exists with this ID, an error will be thrown.
2459    
2460    =item fields
2461    
2462    Reference to a hash mapping field names to their new values. All of the fields named
2463    must be in the entity's primary relation, and they cannot any of them be the ID field.
2464    
2465    =back
2466    
2467    =cut
2468    
2469    sub UpdateEntity {
2470        # Get the parameters.
2471        my ($self, $entityName, $id, $fields) = @_;
2472        # Get a list of the field names being updated.
2473        my @fieldList = keys %{$fields};
2474        # Verify that the fields exist.
2475        my $checker = $self->GetFieldTable($entityName);
2476        for my $field (@fieldList) {
2477            if ($field eq 'id') {
2478                Confess("Cannot update the ID field for entity $entityName.");
2479            } elsif ($checker->{$field}->{relation} ne $entityName) {
2480                Confess("Cannot find $field in primary relation of $entityName.");
2481            }
2482        }
2483        # Build the SQL statement.
2484        my @sets = ();
2485        my @valueList = ();
2486        for my $field (@fieldList) {
2487            push @sets, _FixName($field) . " = ?";
2488            push @valueList, $fields->{$field};
2489        }
2490        my $command = "UPDATE $entityName SET " . join(", ", @sets) . " WHERE id = ?";
2491        # Add the ID to the list of binding values.
2492        push @valueList, $id;
2493        # Call SQL to do the work.
2494        my $rows = $self->{_dbh}->SQL($command, 0, @valueList);
2495        # Check for errors.
2496        if ($rows == 0) {
2497            Confess("Entity $id of type $entityName not found.");
2498        }
2499    }
2500    
2501    =head3 LoadTable
2502    
2503    C<< my $results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>
2504    
2505    Load data from a tab-delimited file into a specified table, optionally re-creating the table
2506    first.
2507    
2508    =over 4
2509    
2510    =item fileName
2511    
2512    Name of the file from which the table data should be loaded.
2513    
2514    =item relationName
2515    
2516    Name of the relation to be loaded. This is the same as the table name.
2517    
2518    =item truncateFlag
2519    
2520    TRUE if the table should be dropped and re-created, else FALSE
2521    
2522    =item RETURN
2523    
2524    Returns a statistical object containing a list of the error messages.
2525    
2526    =back
2527    
2528    =cut
2529    sub LoadTable {
2530        # Get the parameters.
2531        my ($self, $fileName, $relationName, $truncateFlag) = @_;
2532        # Create the statistical return object.
2533        my $retVal = _GetLoadStats();
2534        # Trace the fact of the load.
2535        Trace("Loading table $relationName from $fileName") if T(2);
2536        # Get the database handle.
2537        my $dbh = $self->{_dbh};
2538        # Get the input file size.
2539        my $fileSize = -s $fileName;
2540        # Get the relation data.
2541        my $relation = $self->_FindRelation($relationName);
2542        # Check the truncation flag.
2543        if ($truncateFlag) {
2544            Trace("Creating table $relationName") if T(2);
2545            # Compute the row count estimate. We take the size of the load file,
2546            # divide it by the estimated row size, and then multiply by 1.5 to
2547            # leave extra room. We postulate a minimum row count of 1000 to
2548            # prevent problems with incoming empty load files.
2549            my $rowSize = $self->EstimateRowSize($relationName);
2550            my $estimate = FIG::max($fileSize * 1.5 / $rowSize, 1000);
2551            # Re-create the table without its index.
2552            $self->CreateTable($relationName, 0, $estimate);
2553            # If this is a pre-index DBMS, create the index here.
2554            if ($dbh->{_preIndex}) {
2555                eval {
2556                    $self->CreateIndex($relationName);
2557                };
2558                if ($@) {
2559                    $retVal->AddMessage($@);
2560                }
2561            }
2562        }
2563        # Load the table.
2564        my $rv;
2565        eval {
2566            $rv = $dbh->load_table(file => $fileName, tbl => $relationName);
2567        };
2568        if (!defined $rv) {
2569            $retVal->AddMessage($@) if ($@);
2570            $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2571            Trace("Table load failed for $relationName.") if T(1);
2572                                  } else {                                  } else {
2573                                          # Get the field's relation.          # Here we successfully loaded the table.
2574                                          my $relationName = $fieldList->{$fieldName}->{relation};          $retVal->Add("tables");
2575                                          # Insure the relation is in the FROM clause.          my $size = -s $fileName;
2576                                          if (!exists $fromNames{$relationName}) {          Trace("$size bytes loaded into $relationName.") if T(2);
2577                                                  # Add the relation to the FROM clause.          # If we're rebuilding, we need to create the table indexes.
2578                                                  $command .= ", $relationName";          if ($truncateFlag) {
2579                                                  # Create its join sub-clause.              # Indexes are created here for PostGres. For PostGres, indexes are
2580                                                  push @joinWhere, "$objectName.id = $relationName.id";              # best built at the end. For MySQL, the reverse is true.
2581                                                  # Denote we have it available for future fields.              if (! $dbh->{_preIndex}) {
2582                                                  $fromNames{$relationName} = 1;                  eval {
2583                        $self->CreateIndex($relationName);
2584                    };
2585                    if ($@) {
2586                        $retVal->AddMessage($@);
2587                                          }                                          }
                                         # 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;  
2588                                  }                                  }
2589                # The full-text index (if any) is always built last, even for MySQL.
2590                # First we need to see if this table has a full-text index. Only
2591                # primary relations are allowed that privilege.
2592                Trace("Checking for full-text index on $relationName.") if T(2);
2593                if ($self->_IsPrimary($relationName)) {
2594                    $self->CreateSearchIndex($relationName);
2595                          }                          }
2596                  }                  }
2597                  # The next step is to join the objects together. We only need to do this if there      }
2598                  # is more than one object in the object list. We start with the first object and      # Analyze the table to improve performance.
2599                  # run through the objects after it. Note also that we make a safety copy of the      Trace("Analyzing and compacting $relationName.") if T(3);
2600                  # list before running through it.      $dbh->vacuum_it($relationName);
2601                  my @objectList = @{$objectNames};      Trace("$relationName load completed.") if T(3);
2602                  my $lastObject = shift @objectList;      # Return the statistics.
2603                  # Get the join table.      return $retVal;
2604                  my $joinTable = $self->{_metaData}->{Joins};  }
2605                  # Loop through the object list.  
2606                  for my $thisObject (@objectList) {  =head3 CreateSearchIndex
2607                          # Look for a join.  
2608                          my $joinKey = "$lastObject/$thisObject";  C<< $erdb->CreateSearchIndex($objectName); >>
2609                          if (!exists $joinTable->{$joinKey}) {  
2610                                  # Here there's no join, so we throw an error.  Check for a full-text search index on the specified entity or relationship object, and
2611                                  Confess("No join exists to connect from $lastObject to $thisObject.");  if one is required, rebuild it.
2612    
2613    =over 4
2614    
2615    =item objectName
2616    
2617    Name of the entity or relationship to be indexed.
2618    
2619    =back
2620    
2621    =cut
2622    
2623    sub CreateSearchIndex {
2624        # Get the parameters.
2625        my ($self, $objectName) = @_;
2626        # Get the relation's entity/relationship structure.
2627        my $structure = $self->_GetStructure($objectName);
2628        # Get the database handle.
2629        my $dbh = $self->{_dbh};
2630        Trace("Checking for search fields in $objectName.") if T(3);
2631        # Check for a searchable fields list.
2632        if (exists $structure->{searchFields}) {
2633            # Here we know that we need to create a full-text search index.
2634            # Get an SQL-formatted field name list.
2635            my $fields = join(", ", _FixNames(@{$structure->{searchFields}}));
2636            # Create the index. If it already exists, it will be dropped.
2637            $dbh->create_index(tbl => $objectName, idx => "search_idx",
2638                               flds => $fields, kind => 'fulltext');
2639            Trace("Index created for $fields in $objectName.") if T(2);
2640        }
2641    }
2642    
2643    =head3 DropRelation
2644    
2645    C<< $erdb->DropRelation($relationName); >>
2646    
2647    Physically drop a relation from the database.
2648    
2649    =over 4
2650    
2651    =item relationName
2652    
2653    Name of the relation to drop. If it does not exist, this method will have
2654    no effect.
2655    
2656    =back
2657    
2658    =cut
2659    
2660    sub DropRelation {
2661        # Get the parameters.
2662        my ($self, $relationName) = @_;
2663        # Get the database handle.
2664        my $dbh = $self->{_dbh};
2665        # Drop the relation. The method used here has no effect if the relation
2666        # does not exist.
2667        Trace("Invoking DB Kernel to drop $relationName.") if T(3);
2668        $dbh->drop_table(tbl => $relationName);
2669    }
2670    
2671    =head3 MatchSqlPattern
2672    
2673    C<< my $matched = ERDB::MatchSqlPattern($value, $pattern); >>
2674    
2675    Determine whether or not a specified value matches an SQL pattern. An SQL
2676    pattern has two wild card characters: C<%> that matches multiple characters,
2677    and C<_> that matches a single character. These can be escaped using a
2678    backslash (C<\>). We pull this off by converting the SQL pattern to a
2679    PERL regular expression. As per SQL rules, the match is case-insensitive.
2680    
2681    =over 4
2682    
2683    =item value
2684    
2685    Value to be matched against the pattern. Note that an undefined or empty
2686    value will not match anything.
2687    
2688    =item pattern
2689    
2690    SQL pattern against which to match the value. An undefined or empty pattern will
2691    match everything.
2692    
2693    =item RETURN
2694    
2695    Returns TRUE if the value and pattern match, else FALSE.
2696    
2697    =back
2698    
2699    =cut
2700    
2701    sub MatchSqlPattern {
2702        # Get the parameters.
2703        my ($value, $pattern) = @_;
2704        # Declare the return variable.
2705        my $retVal;
2706        # Insure we have a pattern.
2707        if (! defined($pattern) || $pattern eq "") {
2708            $retVal = 1;
2709                          } else {                          } else {
2710                                  # Get the join clause and add it to the WHERE list.          # Break the pattern into pieces around the wildcard characters. Because we
2711                                  push @joinWhere, $joinTable->{$joinKey};          # use parentheses in the split function's delimiter expression, we'll get
2712                                  # Save this object as the last object for the next iteration.          # list elements for the delimiters as well as the rest of the string.
2713                                  $lastObject = $thisObject;          my @pieces = split /([_%]|\\[_%])/, $pattern;
2714            # Check some fast special cases.
2715            if ($pattern eq '%') {
2716                # A null pattern matches everything.
2717                $retVal = 1;
2718            } elsif (@pieces == 1) {
2719                # No wildcards, so we have a literal comparison. Note we're case-insensitive.
2720                $retVal = (lc($value) eq lc($pattern));
2721            } elsif (@pieces == 2 && $pieces[1] eq '%') {
2722                # A wildcard at the end, so we have a substring match. This is also case-insensitive.
2723                $retVal = (lc(substr($value, 0, length($pieces[0]))) eq lc($pieces[0]));
2724            } else {
2725                # Okay, we have to do it the hard way. Convert each piece to a PERL pattern.
2726                my $realPattern = "";
2727                for my $piece (@pieces) {
2728                    # Determine the type of piece.
2729                    if ($piece eq "") {
2730                        # Empty pieces are ignored.
2731                    } elsif ($piece eq "%") {
2732                        # Here we have a multi-character wildcard. Note that it can match
2733                        # zero or more characters.
2734                        $realPattern .= ".*"
2735                    } elsif ($piece eq "_") {
2736                        # Here we have a single-character wildcard.
2737                        $realPattern .= ".";
2738                    } elsif ($piece eq "\\%" || $piece eq "\\_") {
2739                        # This is an escape sequence (which is a rare thing, actually).
2740                        $realPattern .= substr($piece, 1, 1);
2741                    } else {
2742                        # Here we have raw text.
2743                        $realPattern .= quotemeta($piece);
2744                          }                          }
2745                  }                  }
2746                  # Now we need to handle the whole ORDER BY thing. We'll put the order by clause              # Do the match.
2747                  # in the following variable.              $retVal = ($value =~ /^$realPattern$/i ? 1 : 0);
                 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 = $1;  
2748                  }                  }
                 # Add the filter and the join clauses (if any) to the SELECT command.  
                 if ($filterString) {  
                         push @joinWhere, "($filterString)";  
2749                  }                  }
2750                  if (@joinWhere) {      # Return the result.
2751                          $command .= " WHERE " . join(' AND ', @joinWhere);      return $retVal;
2752    }
2753    
2754    =head3 GetEntity
2755    
2756    C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>
2757    
2758    Return an object describing the entity instance with a specified ID.
2759    
2760    =over 4
2761    
2762    =item entityType
2763    
2764    Entity type name.
2765    
2766    =item ID
2767    
2768    ID of the desired entity.
2769    
2770    =item RETURN
2771    
2772    Returns a B<DBObject> representing the desired entity instance, or an undefined value if no
2773    instance is found with the specified key.
2774    
2775    =back
2776    
2777    =cut
2778    
2779    sub GetEntity {
2780        # Get the parameters.
2781        my ($self, $entityType, $ID) = @_;
2782        # Create a query.
2783        my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);
2784        # Get the first (and only) object.
2785        my $retVal = $query->Fetch();
2786        # Return the result.
2787        return $retVal;
2788    }
2789    
2790    =head3 GetChoices
2791    
2792    C<< my @values = $erdb->GetChoices($entityName, $fieldName); >>
2793    
2794    Return a list of all the values for the specified field that are represented in the
2795    specified entity.
2796    
2797    Note that if the field is not indexed, then this will be a very slow operation.
2798    
2799    =over 4
2800    
2801    =item entityName
2802    
2803    Name of an entity in the database.
2804    
2805    =item fieldName
2806    
2807    Name of a field belonging to the entity. This is a raw field name without
2808    the standard parenthesized notation used in most calls.
2809    
2810    =item RETURN
2811    
2812    Returns a list of the distinct values for the specified field in the database.
2813    
2814    =back
2815    
2816    =cut
2817    
2818    sub GetChoices {
2819        # Get the parameters.
2820        my ($self, $entityName, $fieldName) = @_;
2821        # Declare the return variable.
2822        my @retVal;
2823        # Get the entity data structure.
2824        my $entityData = $self->_GetStructure($entityName);
2825        # Get the field.
2826        my $fieldHash = $entityData->{Fields};
2827        if (! exists $fieldHash->{$fieldName}) {
2828            Confess("$fieldName not found in $entityName.");
2829        } else {
2830            # Get the name of the relation containing the field.
2831            my $relation = $fieldHash->{$fieldName}->{relation};
2832            # Fix up the field name.
2833            my $realName = _FixName($fieldName);
2834            # Get the database handle.
2835            my $dbh = $self->{_dbh};
2836            # Query the database.
2837            my $results = $dbh->SQL("SELECT DISTINCT $realName FROM $relation");
2838            # Clean the results. They are stored as a list of lists, and we just want the one list.
2839            @retVal = sort map { $_->[0] } @{$results};
2840        }
2841        # Return the result.
2842        return @retVal;
2843    }
2844    
2845    =head3 GetEntityValues
2846    
2847    C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>
2848    
2849    Return a list of values from a specified entity instance. If the entity instance
2850    does not exist, an empty list is returned.
2851    
2852    =over 4
2853    
2854    =item entityType
2855    
2856    Entity type name.
2857    
2858    =item ID
2859    
2860    ID of the desired entity.
2861    
2862    =item fields
2863    
2864    List of field names, each of the form I<objectName>C<(>I<fieldName>C<)>.
2865    
2866    =item RETURN
2867    
2868    Returns a flattened list of the values of the specified fields for the specified entity.
2869    
2870    =back
2871    
2872    =cut
2873    
2874    sub GetEntityValues {
2875        # Get the parameters.
2876        my ($self, $entityType, $ID, $fields) = @_;
2877        # Get the specified entity.
2878        my $entity = $self->GetEntity($entityType, $ID);
2879        # Declare the return list.
2880        my @retVal = ();
2881        # If we found the entity, push the values into the return list.
2882        if ($entity) {
2883            push @retVal, $entity->Values($fields);
2884        }
2885        # Return the result.
2886        return @retVal;
2887    }
2888    
2889    =head3 GetAll
2890    
2891    C<< my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>
2892    
2893    Return a list of values taken from the objects returned by a query. The first three
2894    parameters correspond to the parameters of the L</Get> method. The final parameter is
2895    a list of the fields desired from each record found by the query. The field name
2896    syntax is the standard syntax used for fields in the B<ERDB> system--
2897    B<I<objectName>(I<fieldName>)>-- where I<objectName> is the name of the relevant entity
2898    or relationship and I<fieldName> is the name of the field.
2899    
2900    The list returned will be a list of lists. Each element of the list will contain
2901    the values returned for the fields specified in the fourth parameter. If one of the
2902    fields specified returns multiple values, they are flattened in with the rest. For
2903    example, the following call will return a list of the features in a particular
2904    spreadsheet cell, and each feature will be represented by a list containing the
2905    feature ID followed by all of its aliases.
2906    
2907    C<< @query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>
2908    
2909    =over 4
2910    
2911    =item objectNames
2912    
2913    List containing the names of the entity and relationship objects to be retrieved.
2914    
2915    =item filterClause
2916    
2917    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
2918    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
2919    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
2920    parameter list as additional parameters. The fields in a filter clause can come from primary
2921    entity relations, relationship relations, or secondary entity relations; however, all of the
2922    entities and relationships involved must be included in the list of object names.
2923    
2924    =item parameterList
2925    
2926    List of the parameters to be substituted in for the parameters marks in the filter clause.
2927    
2928    =item fields
2929    
2930    List of the fields to be returned in each element of the list returned.
2931    
2932    =item count
2933    
2934    Maximum number of records to return. If omitted or 0, all available records will be returned.
2935    
2936    =item RETURN
2937    
2938    Returns a list of list references. Each element of the return list contains the values for the
2939    fields specified in the B<fields> parameter.
2940    
2941    =back
2942    
2943    =cut
2944    #: Return Type @@;
2945    sub GetAll {
2946        # Get the parameters.
2947        my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
2948        # Translate the parameters from a list reference to a list. If the parameter
2949        # list is a scalar we convert it into a singleton list.
2950        my @parmList = ();
2951        if (ref $parameterList eq "ARRAY") {
2952            Trace("GetAll parm list is an array.") if T(4);
2953            @parmList = @{$parameterList};
2954        } else {
2955            Trace("GetAll parm list is a scalar: $parameterList.") if T(4);
2956            push @parmList, $parameterList;
2957                  }                  }
2958                  # Add the sort clause (if any) to the SELECT command.      # Insure the counter has a value.
2959                  if ($orderClause) {      if (!defined $count) {
2960                          $command .= " ORDER BY $orderClause";          $count = 0;
2961        }
2962        # Add the row limit to the filter clause.
2963        if ($count > 0) {
2964            $filterClause .= " LIMIT $count";
2965        }
2966        # Create the query.
2967        my $query = $self->Get($objectNames, $filterClause, \@parmList);
2968        # Set up a counter of the number of records read.
2969        my $fetched = 0;
2970        # Loop through the records returned, extracting the fields. Note that if the
2971        # counter is non-zero, we stop when the number of records read hits the count.
2972        my @retVal = ();
2973        while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {
2974            my @rowData = $row->Values($fields);
2975            push @retVal, \@rowData;
2976            $fetched++;
2977                  }                  }
2978        Trace("$fetched rows returned in GetAll.") if T(SQL => 4);
2979        # Return the resulting list.
2980        return @retVal;
2981          }          }
2982          Trace("SQL query: $command") if T(2);  
2983          Trace("PARMS: '" . (join "', '", @params) . "'") if (T(3) && (@params > 0));  =head3 Exists
2984          my $sth = $dbh->prepare_command($command);  
2985          # Execute it with the parameters bound in.  C<< my $found = $sprout->Exists($entityName, $entityID); >>
2986          $sth->execute(@params) || Confess("SELECT error" . $sth->errstr());  
2987          # Return the statement object.  Return TRUE if an entity exists, else FALSE.
2988          my $retVal = DBQuery::_new($self, $sth, @{$objectNames});  
2989    =over 4
2990    
2991    =item entityName
2992    
2993    Name of the entity type (e.g. C<Feature>) relevant to the existence check.
2994    
2995    =item entityID
2996    
2997    ID of the entity instance whose existence is to be checked.
2998    
2999    =item RETURN
3000    
3001    Returns TRUE if the entity instance exists, else FALSE.
3002    
3003    =back
3004    
3005    =cut
3006    #: Return Type $;
3007    sub Exists {
3008        # Get the parameters.
3009        my ($self, $entityName, $entityID) = @_;
3010        # Check for the entity instance.
3011        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
3012        my $testInstance = $self->GetEntity($entityName, $entityID);
3013        # Return an existence indicator.
3014        my $retVal = ($testInstance ? 1 : 0);
3015          return $retVal;          return $retVal;
3016  }  }
3017    
3018  =head3 ComputeObjectSentence  =head3 EstimateRowSize
3019    
3020  C<< my $sentence = $database->ComputeObjectSentence($objectName); >>  C<< my $rowSize = $erdb->EstimateRowSize($relName); >>
3021    
3022  Check an object name, and if it is a relationship convert it to a relationship sentence.  Estimate the row size of the specified relation. The estimated row size is computed by adding
3023    up the average length for each data type.
3024    
3025  =over 4  =over 4
3026    
3027  =item objectName  =item relName
3028    
3029  Name of the entity or relationship.  Name of the relation whose estimated row size is desired.
3030    
3031  =item RETURN  =item RETURN
3032    
3033  Returns a string containing the entity name or a relationship sentence.  Returns an estimate of the row size for the specified relation.
3034    
3035  =back  =back
3036    
3037  =cut  =cut
3038    #: Return Type $;
3039  sub ComputeObjectSentence {  sub EstimateRowSize {
3040          # Get the parameters.          # Get the parameters.
3041          my ($self, $objectName) = @_;      my ($self, $relName) = @_;
3042          # Set the default return value.      # Declare the return variable.
3043          my $retVal = $objectName;      my $retVal = 0;
3044          # Look for the object as a relationship.      # Find the relation descriptor.
3045          my $relTable = $self->{_metaData}->{Relationships};      my $relation = $self->_FindRelation($relName);
3046          if (exists $relTable->{$objectName}) {      # Get the list of fields.
3047                  # Get the relationship sentence.      for my $fieldData (@{$relation->{Fields}}) {
3048                  $retVal = _ComputeRelationshipSentence($objectName, $relTable->{$objectName});          # Get the field type and add its length.
3049            my $fieldLen = $TypeTable{$fieldData->{type}}->{avgLen};
3050            $retVal += $fieldLen;
3051          }          }
3052          # Return the result.          # Return the result.
3053          return $retVal;          return $retVal;
3054  }  }
3055    
3056  =head3 DumpRelations  =head3 GetFieldTable
3057    
3058  C<< $database->DumpRelations($outputDirectory); >>  C<< my $fieldHash = $self->GetFieldTable($objectnName); >>
3059    
3060  Write the contents of all the relations to tab-delimited files in the specified directory.  Get the field structure for a specified entity or relationship.
 Each file will have the same name as the relation dumped, with an extension of DTX.  
3061    
3062  =over 4  =over 4
3063    
3064  =item outputDirectory  =item objectName
3065    
3066  Name of the directory into which the relation files should be dumped.  Name of the desired entity or relationship.
3067    
3068    =item RETURN
3069    
3070    The table containing the field descriptors for the specified object.
3071    
3072  =back  =back
3073    
3074  =cut  =cut
3075    
3076  sub DumpRelations {  sub GetFieldTable {
3077          # Get the parameters.          # Get the parameters.
3078          my ($self, $outputDirectory) = @_;      my ($self, $objectName) = @_;
3079          # Now we need to run through all the relations. First, we loop through the entities.      # Get the descriptor from the metadata.
3080          my $metaData = $self->{_metaData};      my $objectData = $self->_GetStructure($objectName);
3081          my $entities = $metaData->{Entities};      # Return the object's field table.
3082          while (my ($entityName, $entityStructure) = each %{$entities}) {      return $objectData->{Fields};
                 # Get the entity's relations.  
                 my $relationList = $entityStructure->{Relations};  
                 # Loop through the relations, dumping them.  
                 while (my ($relationName, $relation) = each %{$relationList}) {  
                         $self->_DumpRelation($outputDirectory, $relationName, $relation);  
                 }  
         }  
         # Next, we loop through the relationships.  
         my $relationships = $metaData->{Relationships};  
         while (my ($relationshipName, $relationshipStructure) = each %{$relationships}) {  
                 # Dump this relationship's relation.  
                 $self->_DumpRelation($outputDirectory, $relationshipName, $relationshipStructure->{Relations}->{$relationshipName});  
         }  
3083  }  }
3084    
3085  =head3 InsertObject  =head3 SplitKeywords
3086    
3087  C<< my $ok = $database->InsertObject($objectType, \%fieldHash); >>  C<< my @keywords = ERDB::SplitKeywords($keywordString); >>
3088    
3089  Insert an object into the database. The object is defined by a type name and then a hash  This method returns a list of the positive keywords in the specified
3090  of field names to values. Field values in the primary relation are represented by scalars.  keyword string. All of the operators will have been stripped off,
3091  (Note that for relationships, the primary relation is the B<only> relation.)  and if the keyword is preceded by a minus operator (C<->), it will
3092  Field values for the other relations comprising the entity are always list references. For  not be in the list returned. The idea here is to get a list of the
3093  example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases  keywords the user wants to see. The list will be processed to remove
3094  C<ZP_00210270.1> and C<gi|46206278>.  duplicates.
3095    
3096  C<< $database->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>  It is possible to create a string that confuses this method. For example
3097    
3098  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and      frog toad -frog
 property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.  
3099    
3100  C<< $database->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>  would return both C<frog> and C<toad>. If this is a problem we can deal
3101    with it later.
3102    
3103  =over 4  =over 4
3104    
3105  =item newObjectType  =item keywordString
3106    
3107  Type name of the object to insert.  The keyword string to be parsed.
3108    
3109  =item fieldHash  =item RETURN
3110    
3111  Hash of field names to values.  Returns a list of the words in the keyword string the user wants to
3112    see.
3113    
3114    =back
3115    
3116    =cut
3117    
3118    sub SplitKeywords {
3119        # Get the parameters.
3120        my ($keywordString) = @_;
3121        # Make a safety copy of the string. (This helps during debugging.)
3122        my $workString = $keywordString;
3123        # Convert operators we don't care about to spaces.
3124        $workString =~ tr/+"()<>/ /;
3125        # Split the rest of the string along space boundaries. Note that we
3126        # eliminate any words that are zero length or begin with a minus sign.
3127        my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
3128        # Use a hash to remove duplicates.
3129        my %words = map { $_ => 1 } @wordList;
3130        # Return the result.
3131        return sort keys %words;
3132    }
3133    
3134    =head3 ValidateFieldName
3135    
3136    C<< my $okFlag = ERDB::ValidateFieldName($fieldName); >>
3137    
3138    Return TRUE if the specified field name is valid, else FALSE. Valid field names must
3139    be hyphenated words subject to certain restrictions.
3140    
3141    =over 4
3142    
3143    =item fieldName
3144    
3145    Field name to be validated.
3146    
3147  =item RETURN  =item RETURN
3148    
3149  Returns 1 if successful, 0 if an error occurred.  Returns TRUE if the field name is valid, else FALSE.
3150    
3151  =back  =back
3152    
3153  =cut  =cut
3154    
3155  sub InsertObject {  sub ValidateFieldName {
3156          # Get the parameters.          # Get the parameters.
3157          my ($self, $newObjectType, $fieldHash) = @_;      my ($fieldName) = @_;
3158          # Denote that so far we appear successful.      # Declare the return variable. The field name is valid until we hear
3159        # differently.
3160          my $retVal = 1;          my $retVal = 1;
3161          # Get the database handle.      # Compute the maximum name length.
3162          my $dbh = $self->{_dbh};      my $maxLen = $TypeTable{'name-string'}->{maxLen};
3163          # Get the relation list.      # Look for bad stuff in the name.
3164          my $relationTable = $self->_GetRelationTable($newObjectType);      if ($fieldName =~ /--/) {
3165          # Loop through the relations. We'll build insert statements for each one. If a relation is          # Here we have a doubled minus sign.
3166          # secondary, we may end up generating multiple insert statements. If an error occurs, we          Trace("Field name $fieldName has a doubled hyphen.") if T(1);
         # stop the loop.  
         while ($retVal && (my ($relationName, $relationDefinition) = each %{$relationTable})) {  
                 # Get the relation's fields. For each field we will collect a value in the corresponding  
                 # position of the @valueList array. If one of the fields is missing, we will add it to the  
                 # @missing list.  
                 my @fieldList = @{$relationDefinition->{Fields}};  
                 my @fieldNameList = ();  
                 my @valueList = ();  
                 my @missing = ();  
                 my $recordCount = 1;  
                 for my $fieldDescriptor (@fieldList) {  
                         # Get the field name and save it. Note we need to fix it up so the hyphens  
                         # are converted to underscores.  
                         my $fieldName = $fieldDescriptor->{name};  
                         push @fieldNameList, _FixName($fieldName);  
                         # Look for the named field in the incoming structure. Note that we are looking  
                         # for the real field name, not the fixed-up one!  
                         if (exists $fieldHash->{$fieldName}) {  
                                 # Here we found the field. Stash it in the value list.  
                                 my $value = $fieldHash->{$fieldName};  
                                 push @valueList, $value;  
                                 # If the value is a list, we may need to increment the record count.  
                                 if (ref $value eq "ARRAY") {  
                                         my $thisCount = @{$value};  
                                         if ($recordCount == 1) {  
                                                 # Here we have our first list, so we save its count.  
                                                 $recordCount = $thisCount;  
                                         } elsif ($recordCount != $thisCount) {  
                                                 # Here we have a second list, so its length has to match the  
                                                 # previous lists.  
                                                 Trace("Field $value in new $newObjectType object has an invalid list length $thisCount. Expected $recordCount.") if T(0);  
3167                                                  $retVal = 0;                                                  $retVal = 0;
3168                                          }      } elsif ($fieldName !~ /^[A-Za-z]/) {
3169                                  }          # Here the field name is missing the initial letter.
3170            Trace("Field name $fieldName does not begin with a letter.") if T(1);
3171            $retVal = 0;
3172        } elsif (length($fieldName) > $maxLen) {
3173            # Here the field name is too long.
3174            Trace("Maximum field name length is $maxLen. Field name must be truncated to " . substr($fieldName,0, $maxLen) . ".");
3175                          } else {                          } else {
3176                                  # Here the field is not present. Flag it as missing.          # Strip out the minus signs. Everything remaining must be a letter,
3177                                  push @missing, $fieldName;          # underscore, or digit.
3178                          }          my $strippedName = $fieldName;
3179                  }          $strippedName =~ s/-//g;
3180                  # If we are the primary relation, add the new-record flag.          if ($strippedName !~ /^(\w|\d)+$/) {
3181                  if ($relationName eq $newObjectType) {              Trace("Field name $fieldName contains illegal characters.") if T(1);
3182                          push @valueList, 1;              $retVal = 0;
                         push @fieldNameList, "new_record";  
3183                  }                  }
                 # Only proceed if there are no missing fields.  
                 if (@missing > 0) {  
                         Trace("Relation $relationName for $newObjectType skipped due to missing fields: " .  
                                 join(' ', @missing)) if T(1);  
                 } else {  
                         # 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;  
3184                                          }                                          }
3185        # Return the result.
3186        return $retVal;
3187                                  }                                  }
3188                                  # Execute the INSERT statement with the specified parameter list.  
3189                                  $retVal = $sth->execute(@parameterList);  =head3 ReadMetaXML
3190                                  if (!$retVal) {  
3191                                          my $errorString = $sth->errstr();  C<< my $rawMetaData = ERDB::ReadDBD($fileName); >>
3192                                          Trace("Insert error: $errorString.") if T(0);  
3193    This method reads a raw database definition XML file and returns it.
3194    Normally, the metadata used by the ERDB system has been processed and
3195    modified to make it easier to load and retrieve the data; however,
3196    this method can be used to get the data in its raw form.
3197    
3198    =over 4
3199    
3200    =item fileName
3201    
3202    Name of the XML file to read.
3203    
3204    =item RETURN
3205    
3206    Returns a hash reference containing the raw XML data from the specified file.
3207    
3208    =back
3209    
3210    =cut
3211    
3212    sub ReadMetaXML {
3213        # Get the parameters.
3214        my ($fileName) = @_;
3215        # Read the XML.
3216        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
3217        Trace("XML metadata loaded from file $fileName.") if T(1);
3218        # Return the result.
3219        return $retVal;
3220                                  }                                  }
3221    
3222    =head3 GetEntityFieldHash
3223    
3224    C<< my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName); >>
3225    
3226    Get the field hash of the named entity in the specified raw XML structure.
3227    The field hash may not exist, in which case we need to create it.
3228    
3229    =over 4
3230    
3231    =item structure
3232    
3233    Raw XML structure defininng the database. This is not the run-time XML used by
3234    an ERDB object, since that has all sorts of optimizations built-in.
3235    
3236    =item entityName
3237    
3238    Name of the entity whose field structure is desired.
3239    
3240    =item RETURN
3241    
3242    Returns the field hash used to define the entity's fields.
3243    
3244    =back
3245    
3246    =cut
3247    
3248    sub GetEntityFieldHash {
3249        # Get the parameters.
3250        my ($structure, $entityName) = @_;
3251        # Get the entity structure.
3252        my $entityData = $structure->{Entities}->{$entityName};
3253        # Look for a field structure.
3254        my $retVal = $entityData->{Fields};
3255        # If it doesn't exist, create it.
3256        if (! defined($retVal)) {
3257            $entityData->{Fields} = {};
3258            $retVal = $entityData->{Fields};
3259                          }                          }
3260        # Return the result.
3261        return $retVal;
3262                  }                  }
3263    
3264    =head3 WriteMetaXML
3265    
3266    C<< ERDB::WriteMetaXML($structure, $fileName); >>
3267    
3268    Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
3269    used to update the database definition. It must be used with care, however, since it
3270    will only work on a raw structure, not on the processed structure created by an ERDB
3271    constructor.
3272    
3273    =over 4
3274    
3275    =item structure
3276    
3277    XML structure to be written to the file.
3278    
3279    =item fileName
3280    
3281    Name of the output file to which the updated XML should be stored.
3282    
3283    =back
3284    
3285    =cut
3286    
3287    sub WriteMetaXML {
3288        # Get the parameters.
3289        my ($structure, $fileName) = @_;
3290        # Compute the output.
3291        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
3292        # Write it to the file.
3293        my $xmlOut = Open(undef, ">$fileName");
3294        print $xmlOut $fileString;
3295          }          }
3296          # Return the success indicator.  
3297    
3298    =head3 HTMLNote
3299    
3300    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
3301    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
3302    Except for C<[p]>, all the codes are closed by slash-codes. So, for
3303    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
3304    
3305    C<< my $realHtml = ERDB::HTMLNote($dataString); >>
3306    
3307    =over 4
3308    
3309    =item dataString