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

Diff of /Sprout/ERDB.pm

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

revision 1.6, Wed May 4 03:24:43 2005 UTC revision 1.89, Thu Apr 12 05:59:41 2007 UTC
# Line 2  Line 2 
2    
3          use strict;          use strict;
4          use Tracer;          use Tracer;
5          use DBKernel;      use DBrtns;
6          use Data::Dumper;          use Data::Dumper;
7          use XML::Simple;          use XML::Simple;
8          use DBQuery;          use DBQuery;
9          use DBObject;      use ERDBObject;
10          use Stats;          use Stats;
11          use Time::HiRes qw(gettimeofday);          use Time::HiRes qw(gettimeofday);
12        use Digest::MD5 qw(md5_base64);
13        use FIG;
14        use CGI;
15    
16  =head1 Entity-Relationship Database Package  =head1 Entity-Relationship Database Package
17    
# Line 32  Line 35 
35  relation that contains two fields-- the feature ID (C<id>) and the alias name (C<alias>).  relation that contains two fields-- the feature ID (C<id>) and the alias name (C<alias>).
36  The B<FEATURE> entity also contains an optional virulence number. This is implemented  The B<FEATURE> entity also contains an optional virulence number. This is implemented
37  as a separate relation C<FeatureVirulence> which contains an ID (C<id>) and a virulence number  as a separate relation C<FeatureVirulence> which contains an ID (C<id>) and a virulence number
38  (C<virulence>). If the virulence of a feature I<ABC> is known to be 6, there will be one row in the  (C<virulence>). If the virulence of a feature I<ABC> is known to be 6, there will be one row in
39  C<FeatureVirulence> relation possessing the value I<ABC> as its ID and 6 as its virulence number.  the C<FeatureVirulence> relation possessing the value I<ABC> as its ID and 6 as its virulence
40  If the virulence of I<ABC> is not known, there will not be any rows for it in C<FeatureVirulence>.  number. If the virulence of I<ABC> is not known, there will not be any rows for it in
41    C<FeatureVirulence>.
42    
43  Entities are connected by binary relationships implemented using single relations possessing the  Entities are connected by binary relationships implemented using single relations possessing the
44  same name as the relationship itself and that has an I<arity> of 1-to-1 (C<11>), 1-to-many (C<1M>),  same name as the relationship itself and that has an I<arity> of 1-to-1 (C<11>), 1-to-many (C<1M>),
# Line 56  Line 60 
60  B<start-position>, which indicates where in the contig that the sequence begins. This attribute  B<start-position>, which indicates where in the contig that the sequence begins. This attribute
61  is implemented as the C<start_position> field in the C<IsMadeUpOf> relation.  is implemented as the C<start_position> field in the C<IsMadeUpOf> relation.
62    
63  The database itself is described by an XML file using the F<ERDatabase.xsd> schema. In addition to  The database itself is described by an XML file. In addition to all the data required to define
64  all the data required to define the entities, relationships, and attributes, the schema provides  the entities, relationships, and attributes, the schema provides space for notes describing
65  space for notes describing the data and what it means. These notes are used by L</ShowMetaData>  the data and what it means. These notes are used by L</ShowMetaData> to generate documentation
66  to generate documentation for the database.  for the database.
67    
68    Special support is provided for text searching. An entity field can be marked as <em>searchable</em>,
69    in which case it will be used to generate a text search index in which the user searches for words
70    in the field instead of a particular field value.
71    
72  Finally, every entity and relationship object has a flag indicating if it is new or old. The object  Finally, every entity and relationship object has a flag indicating if it is new or old. The object
73  is considered I<old> if it was loaded by the L</LoadTables> method. It is considered I<new> if it  is considered I<old> if it was loaded by the L</LoadTables> method. It is considered I<new> if it
74  was inserted by the L</InsertObject> method.  was inserted by the L</InsertObject> method.
75    
76  To facilitate testing, the ERDB module supports automatic generation of test data. This process  =head2 XML Database Description
77  is described in the L</GenerateEntity> and L</GenerateConnection> methods, though it is not yet  
78  fully implemented.  =head3 Data Types
79    
80    The ERDB system supports the following data types. Note that there are numerous string
81    types depending on the maximum length. Some database packages limit the total number of
82    characters you have in an index key; to insure the database works in all environments,
83    the type of string should be the shortest one possible that supports all the known values.
84    
85    =over 4
86    
87    =item char
88    
89    single ASCII character
90    
91    =item int
92    
93    32-bit signed integer
94    
95    =item counter
96    
97    32-bit unsigned integer
98    
99    =item date
100    
101    64-bit unsigned integer, representing a PERL date/time value
102    
103    =item text
104    
105    long string; Text fields cannot be used in indexes or sorting and do not support the
106    normal syntax of filter clauses, but can be up to a billion character in length
107    
108    =item float
109    
110    double-precision floating-point number
111    
112    =item boolean
113    
114    single-bit numeric value; The value is stored as a 16-bit signed integer (for
115    compatability with certain database packages), but the only values supported are
116    0 and 1.
117    
118    =item id-string
119    
120    variable-length string, maximum 25 characters
121    
122    =item key-string
123    
124    variable-length string, maximum 40 characters
125    
126    =item name-string
127    
128    variable-length string, maximum 80 characters
129    
130    =item medium-string
131    
132    variable-length string, maximum 160 characters
133    
134    =item string
135    
136    variable-length string, maximum 255 characters
137    
138    =item hash-string
139    
140    variable-length string, maximum 22 characters
141    
142    =back
143    
144    The hash-string data type has a special meaning. The actual key passed into the loader will
145    be a string, but it will be digested into a 22-character MD5 code to save space. Although the
146    MD5 algorithm is not perfect, it is extremely unlikely two strings will have the same
147    digest. Therefore, it is presumed the keys will be unique. When the database is actually
148    in use, the hashed keys will be presented rather than the original values. For this reason,
149    they should not be used for entities where the key is meaningful.
150    
151    =head3 Global Tags
152    
153    The entire database definition must be inside a B<Database> tag. The display name of
154    the database is given by the text associated with the B<Title> tag. The display name
155    is only used in the automated documentation. It has no other effect. The entities and
156    relationships are listed inside the B<Entities> and B<Relationships> tags,
157    respectively. None of these tags have attributes.
158    
159        <Database>
160            <Title>... display title here...</Title>
161            <Entities>
162                ... entity definitions here ...
163            </Entities>
164            <Relationships>
165                ... relationship definitions here...
166            </Relationships>
167        </Database>
168    
169    Entities, relationships, indexes, and fields all allow a text tag called B<Notes>.
170    The text inside the B<Notes> tag contains comments that will appear when the database
171    documentation is generated. Within a B<Notes> tag, you may use C<[i]> and C<[/i]> for
172    italics, C<[b]> and C<[/b]> for bold, and C<[p]> for a new paragraph.
173    
174    =head3 Fields
175    
176    Both entities and relationships have fields described by B<Field> tags. A B<Field>
177    tag can have B<Notes> associated with it. The complete set of B<Field> tags for an
178    object mus be inside B<Fields> tags.
179    
180        <Entity ... >
181            <Fields>
182                ... Field tags ...
183            </Fields>
184        </Entity>
185    
186    The attributes for the B<Field> tag are as follows.
187    
188    =over 4
189    
190    =item name
191    
192    Name of the field. The field name should contain only letters, digits, and hyphens (C<->),
193    and the first character should be a letter. Most underlying databases are case-insensitive
194    with the respect to field names, so a best practice is to use lower-case letters only. Finally,
195    the name C<search-relevance> has special meaning for full-text searches and should not be
196    used as a field name.
197    
198    =item type
199    
200    Data type of the field. The legal data types are given above.
201    
202    =item relation
203    
204    Name of the relation containing the field. This should only be specified for entity
205    fields. The ERDB system does not support optional fields or multi-occurring fields
206    in the primary relation of an entity. Instead, they are put into secondary relations.
207    So, for example, in the C<Genome> entity, the C<group-name> field indicates a special
208    grouping used to select a subset of the genomes. A given genome may not be in any
209    groups or may be in multiple groups. Therefore, C<group-name> specifies a relation
210    value. The relation name specified must be a valid table name. By convention, it is
211    usually the entity name followed by a qualifying word (e.g. C<GenomeGroup>). In an
212    entity, the fields without a relation attribute are said to belong to the
213    I<primary relation>. This relation has the same name as the entity itself.
214    
215    =item searchable
216    
217    If specified, then the field is a candidate for full-text searching. A single full-text
218    index will be created for each relation with at least one searchable field in it.
219    For best results, this option should only be used for string or text fields.
220    
221    =item special
222    
223    This attribute allows the subclass to assign special meaning for certain fields.
224    The interpretation is up to the subclass itself. Currently, only entity fields
225    can have this attribute.
226    
227    =back
228    
229    =head3 Indexes
230    
231    An entity can have multiple alternate indexes associated with it. The fields in an
232    index must all be from the same relation. The alternate indexes assist in searching
233    on fields other than the entity ID. A relationship has at least two indexes-- a I<to-index> and a
234    I<from-index> that order the results when crossing the relationship. For
235    example, in the relationship C<HasContig> from C<Genome> to C<Contig>, the
236    from-index would order the contigs of a ganome, and the to-index would order
237    the genomes of a contig. In addition, it can have zero or more alternate
238    indexes. A relationship's index must specify only fields in
239    the relationship.
240    
241    The alternate indexes for an entity or relationship must be listed inside the B<Indexes> tag.
242    The from-index of a relationship is specified using the B<FromIndex> tag; the to-index is
243    specified using the B<ToIndex> tag.
244    
245    Each index can contain a B<Notes> tag. In addition, it will have an B<IndexFields>
246    tag containing the B<IndexField> tags. These specify, in order, the fields used in
247    the index. The attributes of an B<IndexField> tag are as follows.
248    
249    =over 4
250    
251    =item name
252    
253    Name of the field.
254    
255    =item order
256    
257    Sort order of the field-- C<ascending> or C<descending>.
258    
259    =back
260    
261    The B<FromIndex>, and B<ToIndex> tags have no attributes. The B<Index> tag can
262    have a B<Unique> attribute. If specified, the index will be generated as a unique
263    index.
264    
265    =head3 Object and Field Names
266    
267    By convention entity and relationship names use capital casing (e.g. C<Genome> or
268    C<HasRegionsIn>. Most underlying databases, however, are aggressively case-insensitive
269    with respect to relation names, converting them internally to all-upper case or
270    all-lower case.
271    
272    If syntax or parsing errors occur when you try to load or use an ERDB database, the
273    most likely reason is that one of your objects has an SQL reserved word as its name.
274    The list of SQL reserved words keeps increasing; however, most are unlikely to show
275    up as a noun or declarative verb phrase. The exceptions are C<Group>, C<User>,
276    C<Table>, C<Index>, C<Object>, C<Date>, C<Number>, C<Update>, C<Time>, C<Percent>,
277    C<Memo>, C<Order>, and C<Sum>. This problem can crop up in field names as well.
278    
279    Every entity has a field called C<id> that acts as its primary key. Every relationship
280    has fields called C<from-link> and C<to-link> that contain copies of the relevant
281    entity IDs. These are essentially ERDB's reserved words, and should not be used
282    for user-defined field names.
283    
284    =head3 Entities
285    
286    An entity is described by the B<Entity> tag. The entity can contain B<Notes>, an
287    B<Indexes> tag containing one or more secondary indexes, and a B<Fields> tag
288    containing one or more fields. The attributes of the B<Entity> tag are as follows.
289    
290    =over 4
291    
292    =item name
293    
294    Name of the entity. The entity name, by convention, uses capital casing (e.g. C<Genome>
295    or C<GroupBlock>) and should be a noun or noun phrase.
296    
297    =item keyType
298    
299    Data type of the primary key. The primary key is always named C<id>.
300    
301    =back
302    
303    =head3 Relationships
304    
305    A relationship is described by the C<Relationship> tag. Within a relationship,
306    there can be a C<Notes> tag, a C<Fields> tag containing the intersection data
307    fields, a C<FromIndex> tag containing the from-index, a C<ToIndex> tag containing
308    the to-index, and an C<Indexes> tag containing the alternate indexes.
309    
310    The C<Relationship> tag has the following attributes.
311    
312    =over 4
313    
314    =item name
315    
316    Name of the relationship. The relationship name, by convention, uses capital casing
317    (e.g. C<ContainsRegionIn> or C<HasContig>), and should be a declarative verb
318    phrase, designed to fit between the from-entity and the to-entity (e.g.
319    Block C<ContainsRegionIn> Genome).
320    
321    =item from
322    
323    Name of the entity from which the relationship starts.
324    
325    =item to
326    
327    Name of the entity to which the relationship proceeds.
328    
329    =item arity
330    
331    Relationship type: C<1M> for one-to-many and C<MM> for many-to-many.
332    
333    =back
334    
335  =cut  =cut
336    
# Line 75  Line 338 
338    
339  # Table of information about our datatypes. "sqlType" is the corresponding SQL datatype string.  # Table of information about our datatypes. "sqlType" is the corresponding SQL datatype string.
340  # "maxLen" is the maximum permissible length of the incoming string data used to populate a field  # "maxLen" is the maximum permissible length of the incoming string data used to populate a field
341  # of the specified type. "dataGen" is PERL string that will be evaluated if no test data generation  # of the specified type. "avgLen" is the average byte length for estimating
342   #string is specified in the field definition.  # record sizes. "sort" is the key modifier for the sort command, "notes" is a type description,
343  my %TypeTable = ( char =>        { sqlType => 'CHAR(1)',                        maxLen => 1,                    dataGen => "StringGen('A')" },  # and "indexMod", if non-zero, is the number of characters to use when the field is specified in an
344                                    int =>         { sqlType => 'INTEGER',                        maxLen => 20,                   dataGen => "IntGen(0, 99999999)" },  # index
345                                    string =>  { sqlType => 'VARCHAR(255)',               maxLen => 255,                  dataGen => "StringGen(IntGen(10,250))" },  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",
346                                    text =>        { sqlType => 'TEXT',                           maxLen => 1000000000,   dataGen => "StringGen(IntGen(80,1000))" },                                 indexMod =>   0, notes => "single ASCII character"},
347                                    date =>        { sqlType => 'BIGINT',                         maxLen => 80,                   dataGen => "DateGen(-7, 7, IntGen(0,1400))" },                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n",
348                                    float =>       { sqlType => 'DOUBLE PRECISION',       maxLen => 40,                   dataGen => "FloatGen(0.0, 100.0)" },                                 indexMod =>   0, notes => "signed 32-bit integer"},
349                                    boolean => { sqlType => 'SMALLINT',                   maxLen => 1,                    dataGen => "IntGen(0, 1)" },                    counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n",
350                                   indexMod =>   0, notes => "unsigned 32-bit integer"},
351                      string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, sort => "",
352                                   indexMod =>   0, notes => "character string, 0 to 255 characters"},
353                      text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, sort => "",
354                                   indexMod => 255, notes => "character string, nearly unlimited length, only first 255 characters are indexed"},
355                      date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, sort => "n",
356                                   indexMod =>   0, notes => "signed, 64-bit integer"},
357                      float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, sort => "g",
358                                   indexMod =>   0, notes => "64-bit double precision floating-point number"},
359                      boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, sort => "n",
360                                   indexMod =>   0, notes => "boolean value: 0 if false, 1 if true"},
361                     'hash-string' =>
362                                 { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, sort => "",
363                                   indexMod =>   0, notes => "string stored in digested form, used for certain types of key fields"},
364                     'id-string' =>
365                                 { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, sort => "",
366                                   indexMod =>   0, notes => "character string, 0 to 25 characters"},
367                               'key-string' =>                               'key-string' =>
368                                                           { sqlType => 'VARCHAR(40)',            maxLen => 40,                   dataGen => "StringGen(IntGen(10,40))" },                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, sort => "",
369                                   indexMod =>   0, notes => "character string, 0 to 40 characters"},
370                                   'name-string' =>                                   'name-string' =>
371                                                           { sqlType => 'VARCHAR(80)',            maxLen => 80,                   dataGen => "StringGen(IntGen(10,80))" },                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, sort => "",
372                                   indexMod =>   0, notes => "character string, 0 to 80 characters"},
373                                   'medium-string' =>                                   'medium-string' =>
374                                                           { sqlType => 'VARCHAR(160)',           maxLen => 160,                  dataGen => "StringGen(IntGen(10,160))" },                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",
375                                   indexMod =>   0, notes => "character string, 0 to 160 characters"},
376                                  );                                  );
377    
378  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 98  Line 381 
381                                     'MM' => 'many-to-many'                                     'MM' => 'many-to-many'
382                                   );                                   );
383    
384  # Table for interpreting string patterns.  # Options for XML input and output.
385    
386    my %XmlOptions = (GroupTags =>  { Relationships => 'Relationship',
387                                      Entities => 'Entity',
388                                      Fields => 'Field',
389                                      Indexes => 'Index',
390                                      IndexFields => 'IndexField'
391                                    },
392                      KeyAttr =>    { Relationship => 'name',
393                                      Entity => 'name',
394                                      Field => 'name'
395                                    },
396                      SuppressEmpty => 1,
397                     );
398    
399  my %PictureTable = ( 'A' => "abcdefghijklmnopqrstuvwxyz",  my %XmlInOpts  = (
400                                           '9' => "0123456789",                    ForceArray => ['Field', 'Index', 'IndexField', 'Relationship', 'Entity'],
401                                           'X' => "abcdefghijklmnopqrstuvwxyz0123456789",                    ForceContent => 1,
402                                           'V' => "aeiou",                    NormalizeSpace => 2,
403                                           'K' => "bcdfghjklmnoprstvwxyz"                   );
404    my %XmlOutOpts = (
405                      RootName => 'Database',
406                      XMLDecl => 1,
407                                     );                                     );
408    
409    
410  =head2 Public Methods  =head2 Public Methods
411    
412  =head3 new  =head3 new
# Line 145  Line 445 
445    
446  =head3 ShowMetaData  =head3 ShowMetaData
447    
448  C<< $database->ShowMetaData($fileName); >>  C<< $erdb->ShowMetaData($fileName); >>
449    
450  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
451  the data to be loaded into the relations.  the data to be loaded into the relations.
# Line 176  Line 476 
476          # Write the HTML heading stuff.          # Write the HTML heading stuff.
477          print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";          print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";
478          print HTMLOUT "</head>\n<body>\n";          print HTMLOUT "</head>\n<body>\n";
479        # Write the documentation.
480        print HTMLOUT $self->DisplayMetaData();
481        # Close the document.
482        print HTMLOUT "</body>\n</html>\n";
483        # Close the file.
484        close HTMLOUT;
485    }
486    
487    =head3 DisplayMetaData
488    
489    C<< my $html = $erdb->DisplayMetaData(); >>
490    
491    Return an HTML description of the database. This description can be used to help users create
492    the data to be loaded into the relations and form queries. The output is raw includable HTML
493    without any HEAD or BODY tags.
494    
495    =over 4
496    
497    =item filename
498    
499    The name of the output file.
500    
501    =back
502    
503    =cut
504    
505    sub DisplayMetaData {
506        # Get the parameters.
507        my ($self) = @_;
508        # Get the metadata and the title string.
509        my $metadata = $self->{_metaData};
510        # Get the title string.
511        my $title = $metadata->{Title};
512        # Get the entity and relationship lists.
513        my $entityList = $metadata->{Entities};
514        my $relationshipList = $metadata->{Relationships};
515        # Declare the return variable.
516        my $retVal = "";
517        # Open the output file.
518        Trace("Building MetaData table of contents.") if T(4);
519          # 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
520          # section contains an ordered list of entity or relationship subsections.          # section contains an ordered list of entity or relationship subsections.
521          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";
522          # Loop through the Entities, displaying a list item for each.          # Loop through the Entities, displaying a list item for each.
523          foreach my $key (sort keys %{$entityList}) {          foreach my $key (sort keys %{$entityList}) {
524                  # Display this item.                  # Display this item.
525                  print HTMLOUT "<li><a href=\"#$key\">$key</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$key</a></li>\n";
526          }          }
527          # Close off the entity section and start the relationship section.          # Close off the entity section and start the relationship section.
528          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";
529          # Loop through the Relationships.          # Loop through the Relationships.
530          foreach my $key (sort keys %{$relationshipList}) {          foreach my $key (sort keys %{$relationshipList}) {
531                  # Display this item.                  # Display this item.
532                  my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});                  my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});
533                  print HTMLOUT "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";
534          }          }
535          # Close off the relationship section and list the join table section.          # Close off the relationship section and list the join table section.
536          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";
537          # Close off the table of contents itself.          # Close off the table of contents itself.
538          print HTMLOUT "</ul>\n";      $retVal .=  "</ul>\n";
539          # 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.
540          print HTMLOUT "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";      $retVal .= "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";
541          # Loop through the entities.          # Loop through the entities.
542          for my $key (sort keys %{$entityList}) {          for my $key (sort keys %{$entityList}) {
543                  Trace("Building MetaData entry for $key entity.") if T(4);                  Trace("Building MetaData entry for $key entity.") if T(4);
544                  # Create the entity header. It contains a bookmark and the entity name.                  # Create the entity header. It contains a bookmark and the entity name.
545                  print HTMLOUT "<a name=\"$key\"></a><h3>$key</h3>\n";          $retVal .= "<a name=\"$key\"></a><h3>$key</h3>\n";
546                  # Get the entity data.                  # Get the entity data.
547                  my $entityData = $entityList->{$key};                  my $entityData = $entityList->{$key};
548                  # If there's descriptive text, display it.                  # If there's descriptive text, display it.
549                  if (my $notes = $entityData->{Notes}) {                  if (my $notes = $entityData->{Notes}) {
550                          print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
551                  }                  }
552                  # 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.
553                  print HTMLOUT "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          my $relCount = keys %{$relationshipList};
554            if ($relCount > 0) {
555                # First, we set up the relationship subsection.
556                $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
557                  # Loop through the relationships.                  # Loop through the relationships.
558                  for my $relationship (sort keys %{$relationshipList}) {                  for my $relationship (sort keys %{$relationshipList}) {
559                          # Get the relationship data.                          # Get the relationship data.
# Line 220  Line 563 
563                                  # Get the relationship sentence and append the arity.                                  # Get the relationship sentence and append the arity.
564                                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);                                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);
565                                  # Display the relationship data.                                  # Display the relationship data.
566                                  print HTMLOUT "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";                      $retVal .= "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";
567                          }                          }
568                  }                  }
569                  # Close off the relationship list.                  # Close off the relationship list.
570                  print HTMLOUT "</ul>\n";              $retVal .= "</ul>\n";
571            }
572                  # Get the entity's relations.                  # Get the entity's relations.
573                  my $relationList = $entityData->{Relations};                  my $relationList = $entityData->{Relations};
574                  # Create a header for the relation subsection.                  # Create a header for the relation subsection.
575                  print HTMLOUT "<h4>Relations for <b>$key</b></h4>\n";          $retVal .= "<h4>Relations for <b>$key</b></h4>\n";
576                  # Loop through the relations, displaying them.                  # Loop through the relations, displaying them.
577                  for my $relation (sort keys %{$relationList}) {                  for my $relation (sort keys %{$relationList}) {
578                          my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});                          my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});
579                          print HTMLOUT $htmlString;              $retVal .= $htmlString;
580                  }                  }
581          }          }
582          # Denote we're starting the relationship section.          # Denote we're starting the relationship section.
583          print HTMLOUT "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";      $retVal .= "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";
584          # Loop through the relationships.          # Loop through the relationships.
585          for my $key (sort keys %{$relationshipList}) {          for my $key (sort keys %{$relationshipList}) {
586                  Trace("Building MetaData entry for $key relationship.") if T(4);                  Trace("Building MetaData entry for $key relationship.") if T(4);
# Line 244  Line 588 
588                  my $relationshipStructure = $relationshipList->{$key};                  my $relationshipStructure = $relationshipList->{$key};
589                  # Create the relationship header.                  # Create the relationship header.
590                  my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);                  my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);
591                  print HTMLOUT "<h3><a name=\"$key\"></a>$headerText</h3>\n";          $retVal .= "<h3><a name=\"$key\"></a>$headerText</h3>\n";
592                  # Get the entity names.                  # Get the entity names.
593                  my $fromEntity = $relationshipStructure->{from};                  my $fromEntity = $relationshipStructure->{from};
594                  my $toEntity = $relationshipStructure->{to};                  my $toEntity = $relationshipStructure->{to};
# Line 254  Line 598 
598                  # since both sentences will say the same thing.                  # since both sentences will say the same thing.
599                  my $arity = $relationshipStructure->{arity};                  my $arity = $relationshipStructure->{arity};
600                  if ($arity eq "11") {                  if ($arity eq "11") {
601                          print HTMLOUT "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";
602                  } else {                  } else {
603                          print HTMLOUT "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";
604                          if ($arity eq "MM" && $fromEntity ne $toEntity) {                          if ($arity eq "MM" && $fromEntity ne $toEntity) {
605                                  print HTMLOUT "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";                  $retVal .= "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";
606                          }                          }
607                  }                  }
608                  print HTMLOUT "</p>\n";          $retVal .= "</p>\n";
609                  # If there are notes on this relationship, display them.                  # If there are notes on this relationship, display them.
610                  if (my $notes = $relationshipStructure->{Notes}) {                  if (my $notes = $relationshipStructure->{Notes}) {
611                          print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
612                  }                  }
613                  # Generate the relationship's relation table.                  # Generate the relationship's relation table.
614                  my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});                  my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
615                  print HTMLOUT $htmlString;          $retVal .= $htmlString;
616          }          }
617          Trace("Building MetaData join table.") if T(4);          Trace("Building MetaData join table.") if T(4);
618          # Denote we're starting the join table.          # Denote we're starting the join table.
619          print HTMLOUT "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";      $retVal .= "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";
620          # Create a table header.          # Create a table header.
621          print HTMLOUT _OpenTable("Join Table", "Source", "Target", "Join Condition");      $retVal .= _OpenTable("Join Table", "Source", "Target", "Join Condition");
622          # Loop through the joins.          # Loop through the joins.
623          my $joinTable = $metadata->{Joins};          my $joinTable = $metadata->{Joins};
624          my @joinKeys = keys %{$joinTable};          my @joinKeys = keys %{$joinTable};
# Line 282  Line 626 
626                  # Separate out the source, the target, and the join clause.                  # Separate out the source, the target, and the join clause.
627                  $joinKey =~ m!^([^/]+)/(.+)$!;                  $joinKey =~ m!^([^/]+)/(.+)$!;
628                  my ($sourceRelation, $targetRelation) = ($1, $2);                  my ($sourceRelation, $targetRelation) = ($1, $2);
629                  Trace("Join with key $joinKey is from $sourceRelation to $targetRelation.") if T(4);          Trace("Join with key $joinKey is from $sourceRelation to $targetRelation.") if T(Joins => 4);
630                  my $source = $self->ComputeObjectSentence($sourceRelation);                  my $source = $self->ComputeObjectSentence($sourceRelation);
631                  my $target = $self->ComputeObjectSentence($targetRelation);                  my $target = $self->ComputeObjectSentence($targetRelation);
632                  my $clause = $joinTable->{$joinKey};                  my $clause = $joinTable->{$joinKey};
633                  # Display them in a table row.                  # Display them in a table row.
634                  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";
635          }          }
636          # Close the table.          # Close the table.
637          print HTMLOUT _CloseTable();      $retVal .= _CloseTable();
638          # Close the document.      Trace("Built MetaData HTML.") if T(3);
639          print HTMLOUT "</body>\n</html>\n";      # Return the HTML.
640          # Close the file.      return $retVal;
         close HTMLOUT;  
         Trace("Built MetaData web page.") if T(3);  
641  }  }
642    
643  =head3 DumpMetaData  =head3 DumpMetaData
644    
645  C<< $database->DumpMetaData(); >>  C<< $erdb->DumpMetaData(); >>
646    
647  Return a dump of the metadata structure.  Return a dump of the metadata structure.
648    
# Line 313  Line 655 
655          return Data::Dumper::Dumper($self->{_metaData});          return Data::Dumper::Dumper($self->{_metaData});
656  }  }
657    
658    =head3 CreatePPO
659    
660    C<< ERDB::CreatePPO($erdbXMLFile, $ppoXMLFile); >>
661    
662    Create a PPO XML file from an ERDB data definition XML file. At the
663    current time, the PPO XML file can be used to create a database with
664    similar functionality. Eventually, the PPO will be able to use the
665    created XML to access the live ERDB database.
666    
667    =over 4
668    
669    =item erdbXMLFile
670    
671    Name of the XML data definition file for the ERDB database. This
672    file must exist.
673    
674    =item ppoXMLFile
675    
676    Output file for the PPO XML definition. If this file exists, it
677    will be overwritten.
678    
679    =back
680    
681    =cut
682    
683    sub CreatePPO {
684        # Get the parameters.
685        my ($erdbXMLFile, $ppoXMLFile) = @_;
686        # First, we want to slurp in the ERDB XML file in its raw form.
687        my $xml = ReadMetaXML($erdbXMLFile);
688        # Create a variable to hold all of the objects in the PPO project.
689        my @objects = ();
690        # Get the relationship hash.
691        my $relationships = $xml->{Relationships};
692        # Loop through the entities.
693        my $entities = $xml->{Entities};
694        for my $entityName (keys %{$entities}) {
695            # Get the entity's data structures.
696            my $entityObject = $entities->{$entityName};
697            # We put the object's fields in here, according to their type.
698            my (@object_refs, @scalars, @indexes, @arrays);
699            # Create the ID field for the entity. We get the key type from the
700            # entity object and compute the corresponding SQL type.
701            my $type = $TypeTable{$entityObject->{keyType}}->{sqlType};
702            push @scalars, { label => 'id', type => $type };
703            # Loop through the entity fields.
704            for my $fieldName ( keys %{$entityObject->{Fields}} ) {
705                # Get the field object.
706                my $fieldObject = $entityObject->{Fields}->{$fieldName};
707                # Convert it to a scalar tag.
708                my $scalar = _CreatePPOField($fieldName, $fieldObject);
709                # If we have a relation, this field is stored in an array.
710                # otherwise, it is a scalar. The array tag has scalars
711                # stored as an XML array. In ERDB, there is only ever one,
712                # but PPO can have more.
713                my $relation = $fieldObject->{relation};
714                if ($relation) {
715                    push @arrays, { scalar => [$scalar] };
716                } else {
717                    push @scalars, $scalar;
718                }
719            }
720            # Loop through the relationships. If this entity is the to-entity
721            # on a relationship of 1M arity, then it is implemented as a PPO
722            # object reference.
723            for my $relationshipName (keys %{$relationships}) {
724                # Get the relationship data.
725                my $relationshipData = $relationships->{$relationshipName};
726                # If we have a from for this entity and an arity of 1M, we
727                # have an object reference.
728                if ($relationshipData->{to} eq $entityName &&
729                    $relationshipData->{arity} eq '1M') {
730                    # Build the object reference tag.
731                    push @object_refs, { label => $relationshipName,
732                                         type => $relationshipData->{from} };
733                }
734            }
735            # Create the indexes.
736            my $indexList = $entityObject->{Indexes};
737            push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
738            # Build the object XML tree.
739            my $object = { label => $entityName,
740                           object_ref => \@object_refs,
741                           scalar => \@scalars,
742                           index => \@indexes,
743                           array => \@arrays
744                          };
745            # Push the object onto the objects list.
746            push @objects, $object;
747        }
748        # Loop through the relationships, searching for MMs. The 1Ms were
749        # already handled by the entity search above.
750        for my $relationshipName (keys %{$relationships}) {
751            # Get this relationship's object.
752            my $relationshipObject = $relationships->{$relationshipName};
753            # Only proceed if it's many-to-many.
754            if ($relationshipObject->{arity} eq 'MM') {
755                # Create the tag lists for the relationship object.
756                my (@object_refs, @scalars, @indexes);
757                # The relationship will be created as an object with object
758                # references for its links to the participating entities.
759                my %links = ( from => $relationshipObject->{from},
760                              to => $relationshipObject->{to} );
761                for my $link (keys %links) {
762                    # Create an object_ref tag for this piece of the
763                    # relationship (from or to).
764                    my $object_ref = { label => $link,
765                                       type => $links{$link} };
766                    push @object_refs, $object_ref;
767                }
768                # Loop through the intersection data fields, creating scalar tags.
769                # There are no fancy array tags in a relationship.
770                for my $fieldName (keys %{$relationshipObject->{Fields}}) {
771                    my $fieldObject = $relationshipObject->{Fields}->{$fieldName};
772                    push @scalars, _CreatePPOField($fieldName, $fieldObject);
773                }
774                # Finally, the indexes: currently we cannot support the to-index and
775                # from-index in PPO, so we just process the alternate indexes.
776                my $indexList = $relationshipObject->{Indexes};
777                push @indexes, map { _CreatePPOIndex($_) } @{$indexList};
778                # Wrap up all the stuff about this relationship.
779                my $object = { label => $relationshipName,
780                               scalar => \@scalars,
781                               object_ref => \@object_refs,
782                               index => \@indexes
783                             };
784                # Push it into the object list.
785                push @objects, $object;
786            }
787        }
788        # Compute a title.
789        my $title;
790        if ($erdbXMLFile =~ /\/([^\/]+)DBD\.xml/) {
791            # Here we have a standard file name we can use for a title.
792            $title = $1;
793        } else {
794            # Here the file name is non-standard, so we carve up the
795            # database title.
796            $title = $xml->{Title}->{content};
797            $title =~ s/\s\.,//g;
798        }
799        # Wrap up the XML as a project.
800        my $ppoXML = { project => { label => $title,
801                                    object => \@objects }};
802        # Write out the results.
803        my $ppoString = XML::Simple::XMLout($ppoXML,
804                                            AttrIndent => 1,
805                                            KeepRoot => 1);
806        Tracer::PutFile($ppoXMLFile, [ $ppoString ]);
807    }
808    
809    
810    
811    =head3 FindIndexForEntity
812    
813    C<< my $indexFound = ERDB::FindIndexForEntity($xml, $entityName, $attributeName); >>
814    
815    This method locates the entry in an entity's index list that begins with the
816    specified attribute name. If the entity has no index list, one will be
817    created. This method works on raw XML, not a live ERDB object.
818    
819    =over 4
820    
821    =item xml
822    
823    The raw XML structure defining the database.
824    
825    =item entityName
826    
827    The name of the relevant entity.
828    
829    =item attributeName
830    
831    The name of the attribute relevant to the search.
832    
833    =item RETURN
834    
835    The numerical index in the index list of the index entry for the specified entity and
836    attribute, or C<undef> if no such index exists.
837    
838    =back
839    
840    =cut
841    
842    sub FindIndexForEntity {
843        # Get the parameters.
844        my ($xml, $entityName, $attributeName) = @_;
845        # Declare the return variable.
846        my $retVal;
847        # Get the named entity.
848        my $entityData = $xml->{Entities}->{$entityName};
849        if (! $entityData) {
850            Confess("Entity $entityName not found in DBD structure.");
851        } else {
852            # Insure it has an index list.
853            if (! exists $entityData->{Indexes}) {
854                $entityData->{Indexes} = [];
855            } else {
856                # Search for the desired index.
857                my $indexList = $entityData->{Indexes};
858                my $n = scalar @{$indexList};
859                Trace("Searching $n indexes in index list for $entityName.") if T(2);
860                # We use an indexed FOR here because we're returning an
861                # index number instead of an object. We do THAT so we can
862                # delete the index from the list if needed.
863                for (my $i = 0; $i < $n && !defined($retVal); $i++) {
864                    my $index = $indexList->[$i];
865                    my $fields = $index->{IndexFields};
866                    # Technically this IF should be safe (that is, we are guaranteed
867                    # the existence of a "$fields->[0]"), because when we load the XML
868                    # we have SuppressEmpty specified.
869                    if ($fields->[0]->{name} eq $attributeName) {
870                        $retVal = $i;
871                    }
872                }
873            }
874        }
875        Trace("Index for $attributeName of $entityName found at position $retVal.") if defined($retVal) && T(3);
876        Trace("Index for $attributeName not found in $entityName.") if !defined($retVal) && T(3);
877        # Return the result.
878        return $retVal;
879    }
880    
881  =head3 CreateTables  =head3 CreateTables
882    
883  C<< $datanase->CreateTables(); >>  C<< $erdb->CreateTables(); >>
884    
885  This method creates the tables for the database from the metadata structure loaded by the  This method creates the tables for the database from the metadata structure loaded by the
886  constructor. It is expected this function will only be used on rare occasions, when the  constructor. It is expected this function will only be used on rare occasions, when the
# Line 327  Line 892 
892  sub CreateTables {  sub CreateTables {
893          # Get the parameters.          # Get the parameters.
894          my ($self) = @_;          my ($self) = @_;
895          my $metadata = $self->{_metaData};      # Get the relation names.
896          my $dbh = $self->{_dbh};      my @relNames = $self->GetTableNames();
897          # Loop through the entities.      # Loop through the relations.
898          my $entityHash = $metadata->{Entities};      for my $relationName (@relNames) {
         for my $entityName (keys %{$entityHash}) {  
                 my $entityData = $entityHash->{$entityName};  
                 # Tell the user what we're doing.  
                 Trace("Creating relations for entity $entityName.") if T(1);  
                 # Loop through the entity's relations.  
                 for my $relationName (keys %{$entityData->{Relations}}) {  
899                          # Create a table for this relation.                          # Create a table for this relation.
900                          $self->CreateTable($relationName);          $self->CreateTable($relationName, 1);
901                          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);  
902          }          }
903  }  }
904    
905  =head3 CreateTable  =head3 CreateTable
906    
907  C<< $database->CreateTable($tableName, $indexFlag); >>  C<< $erdb->CreateTable($tableName, $indexFlag, $estimatedRows); >>
908    
909  Create the table for a relation and optionally create its indexes.  Create the table for a relation and optionally create its indexes.
910    
# Line 363  Line 914 
914    
915  Name of the relation (which will also be the table name).  Name of the relation (which will also be the table name).
916    
917  =item $indexFlag  =item indexFlag
918    
919  TRUE if the indexes for the relation should be created, else FALSE. If FALSE,  TRUE if the indexes for the relation should be created, else FALSE. If FALSE,
920  L</CreateIndexes> must be called later to bring the indexes into existence.  L</CreateIndexes> must be called later to bring the indexes into existence.
921    
922    =item estimatedRows (optional)
923    
924    If specified, the estimated maximum number of rows for the relation. This
925    information allows the creation of tables using storage engines that are
926    faster but require size estimates, such as MyISAM.
927    
928  =back  =back
929    
930  =cut  =cut
931    
932  sub CreateTable {  sub CreateTable {
933          # Get the parameters.          # Get the parameters.
934          my ($self, $relationName, $indexFlag) = @_;      my ($self, $relationName, $indexFlag, $estimatedRows) = @_;
935          # Get the database handle.          # Get the database handle.
936          my $dbh = $self->{_dbh};          my $dbh = $self->{_dbh};
937          # Get the relation data and determine whether or not the relation is primary.          # Get the relation data and determine whether or not the relation is primary.
# Line 398  Line 955 
955          # Insure the table is not already there.          # Insure the table is not already there.
956          $dbh->drop_table(tbl => $relationName);          $dbh->drop_table(tbl => $relationName);
957          Trace("Table $relationName dropped.") if T(2);          Trace("Table $relationName dropped.") if T(2);
958        # If there are estimated rows, create an estimate so we can take advantage of
959        # faster DB technologies.
960        my $estimation = undef;
961        if ($estimatedRows) {
962            $estimation = [$self->EstimateRowSize($relationName), $estimatedRows];
963        }
964          # Create the table.          # Create the table.
965          Trace("Creating table $relationName: $fieldThing") if T(2);          Trace("Creating table $relationName: $fieldThing") if T(2);
966          $dbh->create_table(tbl => $relationName, flds => $fieldThing);      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);
967          Trace("Relation $relationName created in database.") if T(2);          Trace("Relation $relationName created in database.") if T(2);
968          # If we want to build the indexes, we do it here.      # If we want to build the indexes, we do it here. Note that the full-text search
969        # index will not be built until the table has been loaded.
970          if ($indexFlag) {          if ($indexFlag) {
971                  $self->CreateIndex($relationName);                  $self->CreateIndex($relationName);
972          }          }
973  }  }
974    
975  =head3 CreateIndex  =head3 VerifyFields
976    
977  C<< $database->CreateIndex($relationName); >>  C<< my $count = $erdb->VerifyFields($relName, \@fieldList); >>
978    
979  Create the indexes for a relation. If a table is being loaded from a large source file (as  Run through the list of proposed field values, insuring that all the character fields are
980  is the case in L</LoadTable>), it is best to create the indexes after the load. If that is  below the maximum length. If any fields are too long, they will be truncated in place.
981  the case, then L</CreateTable> should be called with the index flag set to FALSE, and this  
982  method used after the load to create the indexes for the table.  =over 4
983    
984    =item relName
985    
986    Name of the relation for which the specified fields are destined.
987    
988    =item fieldList
989    
990    Reference to a list, in order, of the fields to be put into the relation.
991    
992    =item RETURN
993    
994    Returns the number of fields truncated.
995    
996    =back
997    
998  =cut  =cut
999    
1000  sub CreateIndex {  sub VerifyFields {
1001          # Get the parameters.          # Get the parameters.
1002          my ($self, $relationName) = @_;      my ($self, $relName, $fieldList) = @_;
1003          # Get the relation's descriptor.      # Initialize the return value.
1004          my $relationData = $self->_FindRelation($relationName);      my $retVal = 0;
1005          # Get the database handle.      # Get the relation definition.
1006          my $dbh = $self->{_dbh};      my $relData = $self->_FindRelation($relName);
1007          # Now we need to create this relation's indexes. We do this by looping through its index table.      # Get the list of field descriptors.
1008          my $indexHash = $relationData->{Indexes};      my $fieldTypes = $relData->{Fields};
1009          for my $indexName (keys %{$indexHash}) {      my $fieldCount = scalar @{$fieldTypes};
1010                  my $indexData = $indexHash->{$indexName};      # Loop through the two lists.
1011                  # Get the index's field list.      for (my $i = 0; $i < $fieldCount; $i++) {
1012                  my @fieldList = _FixNames(@{$indexData->{IndexFields}});          # Get the type of the current field.
1013                  my $flds = join(', ', @fieldList);          my $fieldType = $fieldTypes->[$i]->{type};
1014                  # Get the index's uniqueness flag.          # If it's a character field, verify the length.
1015                  my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');          if ($fieldType =~ /string/) {
1016                  # Create the index.              my $maxLen = $TypeTable{$fieldType}->{maxLen};
1017                  $dbh->create_index(idx => $indexName, tbl => $relationName, flds => $flds, unique => $unique);              my $oldString = $fieldList->[$i];
1018                  Trace("Index created: $indexName for $relationName ($flds)") if T(1);              if (length($oldString) > $maxLen) {
1019                    # Here it's too big, so we truncate it.
1020                    Trace("Truncating field $i in relation $relName to $maxLen characters from \"$oldString\".") if T(1);
1021                    $fieldList->[$i] = substr $oldString, 0, $maxLen;
1022                    $retVal++;
1023                }
1024            }
1025          }          }
1026        # Return the truncation count.
1027        return $retVal;
1028  }  }
1029    
1030  =head3 LoadTables  =head3 DigestFields
1031    
1032  C<< my $stats = $database->LoadTables($directoryName, $rebuild); >>  C<< $erdb->DigestFields($relName, $fieldList); >>
1033    
1034  This method will load the database tables from a directory. The tables must already have been created  Digest the strings in the field list that correspond to data type C<hash-string> in the
1035  in the database. (This can be done by calling L</CreateTables>.) The caller passes in a directory name;  specified relation.
1036    
1037    =over 4
1038    
1039    =item relName
1040    
1041    Name of the relation to which the fields belong.
1042    
1043    =item fieldList
1044    
1045    List of field contents to be loaded into the relation.
1046    
1047    =back
1048    
1049    =cut
1050    #: Return Type ;
1051    sub DigestFields {
1052        # Get the parameters.
1053        my ($self, $relName, $fieldList) = @_;
1054        # Get the relation definition.
1055        my $relData = $self->_FindRelation($relName);
1056        # Get the list of field descriptors.
1057        my $fieldTypes = $relData->{Fields};
1058        my $fieldCount = scalar @{$fieldTypes};
1059        # Loop through the two lists.
1060        for (my $i = 0; $i < $fieldCount; $i++) {
1061            # Get the type of the current field.
1062            my $fieldType = $fieldTypes->[$i]->{type};
1063            # If it's a hash string, digest it in place.
1064            if ($fieldType eq 'hash-string') {
1065                $fieldList->[$i] = $self->DigestKey($fieldList->[$i]);
1066            }
1067        }
1068    }
1069    
1070    =head3 DigestKey
1071    
1072    C<< my $digested = $erdb->DigestKey($keyValue); >>
1073    
1074    Return the digested value of a symbolic key. The digested value can then be plugged into a
1075    key-based search into a table with key-type hash-string.
1076    
1077    Currently the digesting process is independent of the database structure, but that may not
1078    always be the case, so this is an instance method instead of a static method.
1079    
1080    =over 4
1081    
1082    =item keyValue
1083    
1084    Key value to digest.
1085    
1086    =item RETURN
1087    
1088    Digested value of the key.
1089    
1090    =back
1091    
1092    =cut
1093    
1094    sub DigestKey {
1095        # Get the parameters.
1096        my ($self, $keyValue) = @_;
1097        # Compute the digest.
1098        my $retVal = md5_base64($keyValue);
1099        # Return the result.
1100        return $retVal;
1101    }
1102    
1103    =head3 CreateIndex
1104    
1105    C<< $erdb->CreateIndex($relationName); >>
1106    
1107    Create the indexes for a relation. If a table is being loaded from a large source file (as
1108    is the case in L</LoadTable>), it is sometimes best to create the indexes after the load.
1109    If that is the case, then L</CreateTable> should be called with the index flag set to
1110    FALSE, and this method used after the load to create the indexes for the table.
1111    
1112    =cut
1113    
1114    sub CreateIndex {
1115        # Get the parameters.
1116        my ($self, $relationName) = @_;
1117        # Get the relation's descriptor.
1118        my $relationData = $self->_FindRelation($relationName);
1119        # Get the database handle.
1120        my $dbh = $self->{_dbh};
1121        # Now we need to create this relation's indexes. We do this by looping through its index table.
1122        my $indexHash = $relationData->{Indexes};
1123        for my $indexName (keys %{$indexHash}) {
1124            my $indexData = $indexHash->{$indexName};
1125            # Get the index's field list.
1126            my @rawFields = @{$indexData->{IndexFields}};
1127            # Get a hash of the relation's field types.
1128            my %types = map { $_->{name} => $_->{type} } @{$relationData->{Fields}};
1129            # We need to check for text fields so we can append a length limitation for them. To do
1130            # that, we need the relation's field list.
1131            my $relFields = $relationData->{Fields};
1132            for (my $i = 0; $i <= $#rawFields; $i++) {
1133                # Get the field type.
1134                my $field = $rawFields[$i];
1135                my $type = $types{$field};
1136                # Ask if it requires using prefix notation for the index.
1137                my $mod = $TypeTable{$type}->{indexMod};
1138                Trace("Field $field ($i) in $relationName has type $type and indexMod $mod.") if T(3);
1139                if ($mod) {
1140                    # Append the prefix length to the field name,
1141                    $rawFields[$i] .= "($mod)";
1142                }
1143            }
1144            my @fieldList = _FixNames(@rawFields);
1145            my $flds = join(', ', @fieldList);
1146            # Get the index's uniqueness flag.
1147            my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
1148            # Create the index.
1149            my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
1150                                        flds => $flds, kind => $unique);
1151            if ($rv) {
1152                Trace("Index created: $indexName for $relationName ($flds)") if T(1);
1153            } else {
1154                Confess("Error creating index $indexName for $relationName using ($flds): " . $dbh->error_message());
1155            }
1156        }
1157    }
1158    
1159    =head3 GetSecondaryFields
1160    
1161    C<< my %fieldTuples = $erdb->GetSecondaryFields($entityName); >>
1162    
1163    This method will return a list of the name and type of each of the secondary
1164    fields for a specified entity. Secondary fields are stored in two-column tables
1165    in addition to the primary entity table. This enables the field to have no value
1166    or to have multiple values.
1167    
1168    =over 4
1169    
1170    =item entityName
1171    
1172    Name of the entity whose secondary fields are desired.
1173    
1174    =item RETURN
1175    
1176    Returns a hash mapping the field names to their field types.
1177    
1178    =back
1179    
1180    =cut
1181    
1182    sub GetSecondaryFields {
1183        # Get the parameters.
1184        my ($self, $entityName) = @_;
1185        # Declare the return variable.
1186        my %retVal = ();
1187        # Look for the entity.
1188        my $table = $self->GetFieldTable($entityName);
1189        # Loop through the fields, pulling out the secondaries.
1190        for my $field (sort keys %{$table}) {
1191            if ($table->{$field}->{relation} ne $entityName) {
1192                # Here we have a secondary field.
1193                $retVal{$field} = $table->{$field}->{type};
1194            }
1195        }
1196        # Return the result.
1197        return %retVal;
1198    }
1199    
1200    =head3 GetFieldRelationName
1201    
1202    C<< my $name = $erdb->GetFieldRelationName($objectName, $fieldName); >>
1203    
1204    Return the name of the relation containing a specified field.
1205    
1206    =over 4
1207    
1208    =item objectName
1209    
1210    Name of the entity or relationship containing the field.
1211    
1212    =item fieldName
1213    
1214    Name of the relevant field in that entity or relationship.
1215    
1216    =item RETURN
1217    
1218    Returns the name of the database relation containing the field, or C<undef> if
1219    the field does not exist.
1220    
1221    =back
1222    
1223    =cut
1224    
1225    sub GetFieldRelationName {
1226        # Get the parameters.
1227        my ($self, $objectName, $fieldName) = @_;
1228        # Declare the return variable.
1229        my $retVal;
1230        # Get the object field table.
1231        my $table = $self->GetFieldTable($objectName);
1232        # Only proceed if the field exists.
1233        if (exists $table->{$fieldName}) {
1234            # Determine the name of the relation that contains this field.
1235            $retVal = $table->{$fieldName}->{relation};
1236        }
1237        # Return the result.
1238        return $retVal;
1239    }
1240    
1241    =head3 DeleteValue
1242    
1243    C<< my $numDeleted = $erdb->DeleteValue($entityName, $id, $fieldName, $fieldValue); >>
1244    
1245    Delete secondary field values from the database. This method can be used to delete all
1246    values of a specified field for a particular entity instance, or only a single value.
1247    
1248    Secondary fields are stored in two-column relations separate from an entity's primary
1249    table, and as a result a secondary field can legitimately have no value or multiple
1250    values. Therefore, it makes sense to talk about deleting secondary fields where it
1251    would not make sense for primary fields.
1252    
1253    =over 4
1254    
1255    =item entityName
1256    
1257    Name of the entity from which the fields are to be deleted.
1258    
1259    =item id
1260    
1261    ID of the entity instance to be processed. If the instance is not found, this
1262    method will have no effect. If C<undef> is specified, all values for all of
1263    the entity instances will be deleted.
1264    
1265    =item fieldName
1266    
1267    Name of the field whose values are to be deleted.
1268    
1269    =item fieldValue (optional)
1270    
1271    Value to be deleted. If not specified, then all values of the specified field
1272    will be deleted for the entity instance. If specified, then only the values which
1273    match this parameter will be deleted.
1274    
1275    =item RETURN
1276    
1277    Returns the number of rows deleted.
1278    
1279    =back
1280    
1281    =cut
1282    
1283    sub DeleteValue {
1284        # Get the parameters.
1285        my ($self, $entityName, $id, $fieldName, $fieldValue) = @_;
1286        # Declare the return value.
1287        my $retVal = 0;
1288        # We need to set up an SQL command to do the deletion. First, we
1289        # find the name of the field's relation.
1290        my $table = $self->GetFieldTable($entityName);
1291        my $field = $table->{$fieldName};
1292        my $relation = $field->{relation};
1293        # Make sure this is a secondary field.
1294        if ($relation eq $entityName) {
1295            Confess("Cannot delete values of $fieldName for $entityName.");
1296        } else {
1297            # Set up the SQL command to delete all values.
1298            my $sql = "DELETE FROM $relation";
1299            # Build the filter.
1300            my @filters = ();
1301            my @parms = ();
1302            # Check for a filter by ID.
1303            if (defined $id) {
1304                push @filters, "id = ?";
1305                push @parms, $id;
1306            }
1307            # Check for a filter by value.
1308            if (defined $fieldValue) {
1309                push @filters, "$fieldName = ?";
1310                push @parms, $fieldValue;
1311            }
1312            # Append the filters to the command.
1313            if (@filters) {
1314                $sql .= " WHERE " . join(" AND ", @filters);
1315            }
1316            # Execute the command.
1317            my $dbh = $self->{_dbh};
1318            $retVal = $dbh->SQL($sql, 0, @parms);
1319        }
1320        # Return the result.
1321        return $retVal;
1322    }
1323    
1324    =head3 LoadTables
1325    
1326    C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>
1327    
1328    This method will load the database tables from a directory. The tables must already have been created
1329    in the database. (This can be done by calling L</CreateTables>.) The caller passes in a directory name;
1330  all of the relations to be loaded must have a file in the directory with the same name as the relation  all of the relations to be loaded must have a file in the directory with the same name as the relation
1331  (optionally with a suffix of C<.dtx>). Each file must be a tab-delimited table of field values. Each  (optionally with a suffix of C<.dtx>). Each file must be a tab-delimited table of field values. Each
1332  line of the file will be loaded as a row of the target relation table. The field values should be in  line of the file will be loaded as a row of the target relation table. The field values should be in
# Line 486  Line 1366 
1366          $directoryName =~ s!/\\$!!;          $directoryName =~ s!/\\$!!;
1367          # Declare the return variable.          # Declare the return variable.
1368          my $retVal = Stats->new();          my $retVal = Stats->new();
1369          # Get the metadata structure.      # Get the relation names.
1370          my $metaData = $self->{_metaData};      my @relNames = $self->GetTableNames();
1371          # Loop through the entities.      for my $relationName (@relNames) {
         for my $entity (values %{$metaData->{Entities}}) {  
                 # Loop through the entity's relations.  
                 for my $relationName (keys %{$entity->{Relations}}) {  
1372                          # Try to load this relation.                          # Try to load this relation.
1373                          my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);                          my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);
1374                          # Accumulate the statistics.                          # Accumulate the statistics.
1375                          $retVal->Accumulate($result);                          $retVal->Accumulate($result);
1376                  }                  }
         }  
         # 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);  
         }  
1377          # Add the duration of the load to the statistical object.          # Add the duration of the load to the statistical object.
1378          $retVal->Add('duration', gettimeofday - $startTime);          $retVal->Add('duration', gettimeofday - $startTime);
1379          # Return the accumulated statistics.          # Return the accumulated statistics.
1380          return $retVal;          return $retVal;
1381  }  }
1382    
1383    
1384  =head3 GetTableNames  =head3 GetTableNames
1385    
1386  C<< my @names = $database->GetTableNames; >>  C<< my @names = $erdb->GetTableNames; >>
1387    
1388  Return a list of the relations required to implement this database.  Return a list of the relations required to implement this database.
1389    
# Line 530  Line 1400 
1400    
1401  =head3 GetEntityTypes  =head3 GetEntityTypes
1402    
1403  C<< my @names = $database->GetEntityTypes; >>  C<< my @names = $erdb->GetEntityTypes; >>
1404    
1405  Return a list of the entity type names.  Return a list of the entity type names.
1406    
# Line 545  Line 1415 
1415          return sort keys %{$entityList};          return sort keys %{$entityList};
1416  }  }
1417    
1418    =head3 GetDataTypes
1419    
1420    C<< my %types = ERDB::GetDataTypes(); >>
1421    
1422    Return a table of ERDB data types. The table returned is a hash of hashes.
1423    The keys of the big hash are the datatypes. Each smaller hash has several
1424    values used to manage the data. The most interesting is the SQL type (key
1425    C<sqlType>) and the descriptive node (key C<notes>).
1426    
1427    Note that changing the values in the smaller hashes will seriously break
1428    things, so this data should be treated as read-only.
1429    
1430    =cut
1431    
1432    sub GetDataTypes {
1433        return %TypeTable;
1434    }
1435    
1436    
1437    =head3 IsEntity
1438    
1439    C<< my $flag = $erdb->IsEntity($entityName); >>
1440    
1441    Return TRUE if the parameter is an entity name, else FALSE.
1442    
1443    =over 4
1444    
1445    =item entityName
1446    
1447    Object name to be tested.
1448    
1449    =item RETURN
1450    
1451    Returns TRUE if the specified string is an entity name, else FALSE.
1452    
1453    =back
1454    
1455    =cut
1456    
1457    sub IsEntity {
1458        # Get the parameters.
1459        my ($self, $entityName) = @_;
1460        # Test to see if it's an entity.
1461        return exists $self->{_metaData}->{Entities}->{$entityName};
1462    }
1463    
1464  =head3 Get  =head3 Get
1465    
1466  C<< my $query = $database->Get(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  C<< my $query = $erdb->Get(\@objectNames, $filterClause, \@params); >>
1467    
1468  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.
1469  The filter is a standard WHERE/ORDER BY clause with question marks as parameter markers and each  The filter is a standard WHERE/ORDER BY clause with question marks as parameter markers and each
# Line 555  Line 1471 
1471  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
1472  $genus.  $genus.
1473    
1474  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", [$genus]); >>
1475    
1476  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
1477  parameter representing the parameter value. It would also be possible to code  parameter representing the parameter value. It would also be possible to code
1478    
1479  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>
1480    
1481  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
1482  characters inside the variable C<$genus>.  characters inside the variable C<$genus>.
# Line 572  Line 1488 
1488  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
1489  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,
1490    
1491  C<< $query = $sprout->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]); >>
1492    
1493  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
1494  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.
1495  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
1496  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
1497  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  
1498  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,
1499  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.
1500    
1501    If an entity or relationship is mentioned twice, the name for the second occurrence will
1502    be suffixed with C<2>, the third occurrence will be suffixed with C<3>, and so forth. So,
1503    for example, if we have C<['Feature', 'HasContig', 'Contig', 'HasContig']>, then the
1504    B<to-link> field of the first B<HasContig> is specified as C<HasContig(to-link)>, while
1505    the B<to-link> field of the second B<HasContig> is specified as C<HasContig2(to-link)>.
1506    
1507  =over 4  =over 4
1508    
1509  =item objectNames  =item objectNames
# Line 605  Line 1526 
1526    
1527  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
1528    
1529    Note that the case is important. Only an uppercase "ORDER BY" with a single space will
1530    be processed. The idea is to make it less likely to find the verb by accident.
1531    
1532  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
1533  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
1534  relation.  relation.
1535    
1536  =item param1, param2, ..., paramN  Finally, you can limit the number of rows returned by adding a LIMIT clause. The LIMIT must
1537    be the last thing in the filter clause, and it contains only the word "LIMIT" followed by
1538    a positive number. So, for example
1539    
1540    C<< "Genome(genus) = ? ORDER BY Genome(species) LIMIT 10" >>
1541    
1542  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
1543    required. For example, to just get the first 10 genomes in the B<Genome> table, you could
1544    use
1545    
1546    C<< "LIMIT 10" >>
1547    
1548    =item params
1549    
1550    Reference to a list of parameter values to be substituted into the filter clause.
1551    
1552  =item RETURN  =item RETURN
1553    
# Line 623  Line 1559 
1559    
1560  sub Get {  sub Get {
1561          # Get the parameters.          # Get the parameters.
1562          my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $objectNames, $filterClause, $params) = @_;
1563          # Construct the SELECT statement. The general pattern is      # Process the SQL stuff.
1564          #      my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1565          # SELECT name1.*, name2.*, ... nameN.* FROM name1, name2, ... nameN          $self->_SetupSQL($objectNames, $filterClause);
1566          #      # Create the query.
1567          my $dbh = $self->{_dbh};      my $command = "SELECT DISTINCT " . join(".*, ", @{$mappedNameListRef}) .
1568          my $command = "SELECT DISTINCT " . join('.*, ', @{$objectNames}) . ".* FROM " .          ".* $suffix";
1569                                  join(', ', @{$objectNames});      my $sth = $self->_GetStatementHandle($command, $params);
1570          # Check for a filter clause.      # Now we create the relation map, which enables DBQuery to determine the order, name
1571          if ($filterClause) {      # and mapped name for each object in the query.
1572                  # Here we have one, so we convert its field names and add it to the query. First,      my @relationMap = ();
1573                  # We create a copy of the filter string we can work with.      for my $mappedName (@{$mappedNameListRef}) {
1574                  my $filterString = $filterClause;          push @relationMap, [$mappedName, $mappedNameHashRef->{$mappedName}];
                 # Next, we sort the object names by length. This helps protect us from finding  
                 # object names inside other object names when we're doing our search and replace.  
                 my @sortedNames = sort { length($b) - length($a) } @{$objectNames};  
                 # We will also keep a list of conditions to add to the WHERE clause in order to link  
                 # entities and relationships as well as primary relations to secondary ones.  
                 my @joinWhere = ();  
                 # The final preparatory step is to create a hash table of relation names. The  
                 # table begins with the relation names already in the SELECT command.  
                 my %fromNames = ();  
                 for my $objectName (@sortedNames) {  
                         $fromNames{$objectName} = 1;  
                 }  
                 # We are ready to begin. We loop through the object names, replacing each  
                 # object name's field references by the corresponding SQL field reference.  
                 # Along the way, if we find a secondary relation, we will need to add it  
                 # to the FROM clause.  
                 for my $objectName (@sortedNames) {  
                         # Get the length of the object name plus 2. This is the value we add to the  
                         # size of the field name to determine the size of the field reference as a  
                         # whole.  
                         my $nameLength = 2 + length $objectName;  
                         # Get the object's field list.  
                         my $fieldList = $self->_GetFieldTable($objectName);  
                         # Find the field references for this object.  
                         while ($filterString =~ m/$objectName\(([^)]*)\)/g) {  
                                 # At this point, $1 contains the field name, and the current position  
                                 # is set immediately after the final parenthesis. We pull out the name of  
                                 # the field and the position and length of the field reference as a whole.  
                                 my $fieldName = $1;  
                                 my $len = $nameLength + length $fieldName;  
                                 my $pos = pos($filterString) - $len;  
                                 # Insure the field exists.  
                                 if (!exists $fieldList->{$fieldName}) {  
                                         Confess("Field $fieldName not found for object $objectName.");  
                                 } else {  
                                         # Get the field's relation.  
                                         my $relationName = $fieldList->{$fieldName}->{relation};  
                                         # Insure the relation is in the FROM clause.  
                                         if (!exists $fromNames{$relationName}) {  
                                                 # Add the relation to the FROM clause.  
                                                 $command .= ", $relationName";  
                                                 # Create its join sub-clause.  
                                                 push @joinWhere, "$objectName.id = $relationName.id";  
                                                 # Denote we have it available for future fields.  
                                                 $fromNames{$relationName} = 1;  
                                         }  
                                         # Form an SQL field reference from the relation name and the field name.  
                                         my $sqlReference = "$relationName." . _FixName($fieldName);  
                                         # Put it into the filter string in place of the old value.  
                                         substr($filterString, $pos, $len) = $sqlReference;  
                                         # Reposition the search.  
                                         pos $filterString = $pos + length $sqlReference;  
                                 }  
                         }  
                 }  
                 # The next step is to join the objects together. We only need to do this if there  
                 # is more than one object in the object list. We start with the first object and  
                 # run through the objects after it. Note also that we make a safety copy of the  
                 # list before running through it.  
                 my @objectList = @{$objectNames};  
                 my $lastObject = shift @objectList;  
                 # Get the join table.  
                 my $joinTable = $self->{_metaData}->{Joins};  
                 # Loop through the object list.  
                 for my $thisObject (@objectList) {  
                         # Look for a join.  
                         my $joinKey = "$lastObject/$thisObject";  
                         if (!exists $joinTable->{$joinKey}) {  
                                 # Here there's no join, so we throw an error.  
                                 Confess("No join exists to connect from $lastObject to $thisObject.");  
                         } else {  
                                 # Get the join clause and add it to the WHERE list.  
                                 push @joinWhere, $joinTable->{$joinKey};  
                                 # Save this object as the last object for the next iteration.  
                                 $lastObject = $thisObject;  
                         }  
1575                  }                  }
1576                  # Now we need to handle the whole ORDER BY thing. We'll put the order by clause      # Return the statement object.
1577                  # in the following variable.      my $retVal = DBQuery::_new($self, $sth, \@relationMap);
1578                  my $orderClause = "";      return $retVal;
                 # Locate the ORDER BY verb (if any).  
                 if ($filterString =~ m/^(.*)ORDER BY/g) {  
                         # Here we have an ORDER BY verb. Split it off of the filter string.  
                         my $pos = pos $filterString;  
                         $orderClause = substr($filterString, $pos);  
                         $filterString = $1;  
                 }  
                 # Add the filter and the join clauses (if any) to the SELECT command.  
                 if ($filterString) {  
                         push @joinWhere, "($filterString)";  
                 }  
                 if (@joinWhere) {  
                         $command .= " WHERE " . join(' AND ', @joinWhere);  
                 }  
                 # Add the sort clause (if any) to the SELECT command.  
                 if ($orderClause) {  
                         $command .= " ORDER BY $orderClause";  
                 }  
         }  
         Trace("SQL query: $command") if T(2);  
         Trace("PARMS: '" . (join "', '", @params) . "'") if (T(3) && (@params > 0));  
         my $sth = $dbh->prepare_command($command);  
         # Execute it with the parameters bound in.  
         $sth->execute(@params) || Confess("SELECT error" . $sth->errstr());  
         # Return the statement object.  
         my $retVal = DBQuery::_new($self, $sth, @{$objectNames});  
         return $retVal;  
1579  }  }
1580    
 =head3 GetList  
1581    
 C<< my @dbObjects = $database->GetList(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  
1582    
1583  Return a list of object descriptors for the specified objects as determined by the  =head3 Search
 specified filter clause.  
1584    
1585  This method is essentially the same as L</Get> except it returns a list of objects rather  C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>
 that a query object that can be used to get the results one record at a time.  
1586    
1587  =over 4  Perform a full text search with filtering. The search will be against a specified object
1588    in the object name list. That object will get an extra field containing the search
1589    relevance. Note that except for the search expression, the parameters of this method are
1590    the same as those for L</Get> and follow the same rules.
1591    
1592  =over 4  =over 4
1593    
1594    =item searchExpression
1595    
1596    Boolean search expression for the text fields of the target object. The default mode for
1597    a Boolean search expression is OR, but we want the default to be AND, so we will
1598    add a C<+> operator to each word with no other operator before it.
1599    
1600    =item idx
1601    
1602    Index in the I<$objectNames> list of the table to be searched in full-text mode.
1603    
1604  =item objectNames  =item objectNames
1605    
1606  List containing the names of the entity and relationship objects to be retrieved.  List containing the names of the entity and relationship objects to be retrieved.
# Line 773  Line 1615 
1615  or secondary entity relations; however, all of the entities and relationships involved must  or secondary entity relations; however, all of the entities and relationships involved must
1616  be included in the list of object names.  be included in the list of object names.
1617    
1618  The filter clause can also specify a sort order. To do this, simply follow the filter string  =item params
 with an ORDER BY clause. For example, the following filter string gets all genomes for a  
 particular genus and sorts them by species name.  
   
 C<< "Genome(genus) = ? ORDER BY Genome(species)" >>  
   
 The rules for field references in a sort order are the same as those for field references in the  
 filter clause in general; however, odd things may happen if a sort field is from a secondary  
 relation.  
   
 =item param1, param2, ..., paramN  
1619    
1620  Parameter values to be substituted into the filter clause.  Reference to a list of parameter values to be substituted into the filter clause.
1621    
1622  =item RETURN  =item RETURN
1623    
1624  Returns a list of B<DBObject>s that satisfy the query conditions.  Returns a query object for the specified search.
1625    
1626  =back  =back
1627    
1628  =cut  =cut
1629  #: Return Type @%  
1630  sub GetList {  sub Search {
1631      # Get the parameters.      # Get the parameters.
1632      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1633          # Declare the return variable.          # Declare the return variable.
1634          my @retVal = ();      my $retVal;
1635          # Perform the query.      # Create a safety copy of the parameter list. Note we have to be careful to insure
1636          my $query = $self->Get($objectNames, $filterClause, @params);      # a parameter list exists before we copy it.
1637          # Loop through the results.      my @myParams = ();
1638          while (my $object = $query->Fetch) {      if (defined $params) {
1639                  push @retVal, $object;          @myParams = @{$params};
1640        }
1641        # Get the first object's structure so we have access to the searchable fields.
1642        my $object1Name = $objectNames->[$idx];
1643        my $object1Structure = $self->_GetStructure($object1Name);
1644        # Get the field list.
1645        if (! exists $object1Structure->{searchFields}) {
1646            Confess("No searchable index for $object1Name.");
1647        } else {
1648            # Get the field list.
1649            my @fields = @{$object1Structure->{searchFields}};
1650            # Clean the search expression.
1651            my $actualKeywords = $self->CleanKeywords($searchExpression);
1652            # Prefix a "+" to each uncontrolled word. This converts the default
1653            # search mode from OR to AND.
1654            $actualKeywords =~ s/(^|\s)(\w|")/$1\+$2/g;
1655            Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1656            # We need two match expressions, one for the filter clause and one in the
1657            # query itself. Both will use a parameter mark, so we need to push the
1658            # search expression onto the front of the parameter list twice.
1659            unshift @myParams, $actualKeywords, $actualKeywords;
1660            # Build the match expression.
1661            my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
1662            my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
1663            # Process the SQL stuff.
1664            my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1665                $self->_SetupSQL($objectNames, $filterClause, $matchClause);
1666            # Create the query. Note that the match clause is inserted at the front of
1667            # the select fields.
1668            my $command = "SELECT DISTINCT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .
1669                ".* $suffix";
1670            my $sth = $self->_GetStatementHandle($command, \@myParams);
1671            # Now we create the relation map, which enables DBQuery to determine the order, name
1672            # and mapped name for each object in the query.
1673            my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
1674            # Return the statement object.
1675            $retVal = DBQuery::_new($self, $sth, \@relationMap, $object1Name);
1676          }          }
1677      # Return the result.      return $retVal;
     return @retVal;  
1678  }  }
1679    
1680  =head3 ComputeObjectSentence  =head3 GetFlat
1681    
1682  C<< my $sentence = $database->ComputeObjectSentence($objectName); >>  C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>
1683    
1684  Check an object name, and if it is a relationship convert it to a relationship sentence.  This is a variation of L</GetAll> that asks for only a single field per record and
1685    returns a single flattened list.
1686    
1687  =over 4  =over 4
1688    
1689  =item objectName  =item objectNames
1690    
1691  Name of the entity or relationship.  List containing the names of the entity and relationship objects to be retrieved.
1692    
1693    =item filterClause
1694    
1695    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1696    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
1697    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
1698    parameter list as additional parameters. The fields in a filter clause can come from primary
1699    entity relations, relationship relations, or secondary entity relations; however, all of the
1700    entities and relationships involved must be included in the list of object names.
1701    
1702    =item parameterList
1703    
1704    List of the parameters to be substituted in for the parameters marks in the filter clause.
1705    
1706    =item field
1707    
1708    Name of the field to be used to get the elements of the list returned.
1709    
1710  =item RETURN  =item RETURN
1711    
1712  Returns a string containing the entity name or a relationship sentence.  Returns a list of values.
1713    
1714  =back  =back
1715    
1716  =cut  =cut
1717    #: Return Type @;
1718  sub ComputeObjectSentence {  sub GetFlat {
1719          # Get the parameters.          # Get the parameters.
1720          my ($self, $objectName) = @_;      my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
1721          # Set the default return value.      # Construct the query.
1722          my $retVal = $objectName;      my $query = $self->Get($objectNames, $filterClause, $parameterList);
1723          # Look for the object as a relationship.      # Create the result list.
1724          my $relTable = $self->{_metaData}->{Relationships};      my @retVal = ();
1725          if (exists $relTable->{$objectName}) {      # Loop through the records, adding the field values found to the result list.
1726                  # Get the relationship sentence.      while (my $row = $query->Fetch()) {
1727                  $retVal = _ComputeRelationshipSentence($objectName, $relTable->{$objectName});          push @retVal, $row->Value($field);
1728          }          }
1729          # Return the result.      # Return the list created.
1730          return $retVal;      return @retVal;
1731  }  }
1732    
1733  =head3 DumpRelations  =head3 SpecialFields
1734    
1735  C<< $database->DumpRelations($outputDirectory); >>  C<< my %specials = $erdb->SpecialFields($entityName); >>
1736    
1737  Write the contents of all the relations to tab-delimited files in the specified directory.  Return a hash mapping special fields in the specified entity to the value of their
1738  Each file will have the same name as the relation dumped, with an extension of DTX.  C<special> attribute. This enables the subclass to get access to the special field
1739    attributes without needed to plumb the internal ERDB data structures.
1740    
1741  =over 4  =over 4
1742    
1743  =item outputDirectory  =item entityName
1744    
1745  Name of the directory into which the relation files should be dumped.  Name of the entity whose special fields are desired.
1746    
1747    =item RETURN
1748    
1749    Returns a hash. The keys of the hash are the special field names, and the values
1750    are the values from each special field's C<special> attribute.
1751    
1752  =back  =back
1753    
1754  =cut  =cut
1755    
1756  sub DumpRelations {  sub SpecialFields {
1757          # Get the parameters.          # Get the parameters.
1758          my ($self, $outputDirectory) = @_;      my ($self, $entityName) = @_;
1759          # Now we need to run through all the relations. First, we loop through the entities.      # Declare the return variable.
1760          my $metaData = $self->{_metaData};      my %retVal = ();
1761          my $entities = $metaData->{Entities};      # Find the entity's data structure.
1762          for my $entityName (keys %{$entities}) {      my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1763                  my $entityStructure = $entities->{$entityName};      # Loop through its fields, adding each special field to the return hash.
1764                  # Get the entity's relations.      my $fieldHash = $entityData->{Fields};
1765                  my $relationList = $entityStructure->{Relations};      for my $fieldName (keys %{$fieldHash}) {
1766                  # Loop through the relations, dumping them.          my $fieldData = $fieldHash->{$fieldName};
1767                  for my $relationName (keys %{$relationList}) {          if (exists $fieldData->{special}) {
1768                          my $relation = $relationList->{$relationName};              $retVal{$fieldName} = $fieldData->{special};
                         $self->_DumpRelation($outputDirectory, $relationName, $relation);  
                 }  
1769          }          }
         # Next, we loop through the relationships.  
         my $relationships = $metaData->{Relationships};  
         for my $relationshipName (keys %{$relationships}) {  
                 my $relationshipStructure = $relationships->{$relationshipName};  
                 # Dump this relationship's relation.  
                 $self->_DumpRelation($outputDirectory, $relationshipName, $relationshipStructure->{Relations}->{$relationshipName});  
1770          }          }
1771        # Return the result.
1772        return %retVal;
1773  }  }
1774    
1775  =head3 InsertObject  =head3 Delete
1776    
1777  C<< my $ok = $database->InsertObject($objectType, \%fieldHash); >>  C<< my $stats = $erdb->Delete($entityName, $objectID, %options); >>
1778    
1779  Insert an object into the database. The object is defined by a type name and then a hash  Delete an entity instance from the database. The instance is deleted along with all entity and
1780  of field names to values. Field values in the primary relation are represented by scalars.  relationship instances dependent on it. The definition of I<dependence> is recursive.
 (Note that for relationships, the primary relation is the B<only> relation.)  
 Field values for the other relations comprising the entity are always list references. For  
 example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases  
 C<ZP_00210270.1> and C<gi|46206278>.  
1781    
1782  C<< $database->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>  An object is always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many
1783    relationship connected to a dependent entity or if it is the "to" entity connected to a 1-to-many
1784    dependent relationship.
1785    
1786  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and  =over 4
 property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.  
1787    
1788  C<< $database->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>  =item entityName
1789    
1790  =over 4  Name of the entity type for the instance being deleted.
1791    
1792  =item newObjectType  =item objectID
1793    
1794  Type name of the object to insert.  ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),
1795    then it is presumed to by a LIKE pattern.
1796    
1797  =item fieldHash  =item options
1798    
1799  Hash of field names to values.  A hash detailing the options for this delete operation.
1800    
1801  =item RETURN  =item RETURN
1802    
1803  Returns 1 if successful, 0 if an error occurred.  Returns a statistics object indicating how many records of each particular table were
1804    deleted.
1805    
1806  =back  =back
1807    
1808  =cut  The permissible options for this method are as follows.
1809    
1810  sub InsertObject {  =over 4
1811    
1812    =item testMode
1813    
1814    If TRUE, then the delete statements will be traced, but no changes will be made to the database.
1815    
1816    =item keepRoot
1817    
1818    If TRUE, then the entity instances will not be deleted, only the dependent records.
1819    
1820    =back
1821    
1822    =cut
1823    #: Return Type $%;
1824    sub Delete {
1825          # Get the parameters.          # Get the parameters.
1826          my ($self, $newObjectType, $fieldHash) = @_;      my ($self, $entityName, $objectID, %options) = @_;
1827          # Denote that so far we appear successful.      # Declare the return variable.
1828          my $retVal = 1;      my $retVal = Stats->new();
1829          # Get the database handle.      # Get the DBKernel object.
1830          my $dbh = $self->{_dbh};      my $db = $self->{_dbh};
1831          # Get the relation list.      # We're going to generate all the paths branching out from the starting entity. One of
1832          my $relationTable = $self->_GetRelationTable($newObjectType);      # the things we have to be careful about is preventing loops. We'll use a hash to
1833          # Loop through the relations. We'll build insert statements for each one. If a relation is      # determine if we've hit a loop.
1834          # secondary, we may end up generating multiple insert statements. If an error occurs, we      my %alreadyFound = ();
1835          # stop the loop.      # These next lists will serve as our result stack. We start by pushing object lists onto
1836          my @relationList = keys %{$relationTable};      # the stack, and then popping them off to do the deletes. This means the deletes will
1837          for (my $i = 0; $retVal && $i <= $#relationList; $i++) {      # start with the longer paths before getting to the shorter ones. That, in turn, makes
1838                  my $relationName = $relationList[$i];      # sure we don't delete records that might be needed to forge relationships back to the
1839                  my $relationDefinition = $relationTable->{$relationName};      # original item. We have two lists-- one for TO-relationships, and one for
1840                  # Get the relation's fields. For each field we will collect a value in the corresponding      # FROM-relationships and entities.
1841                  # position of the @valueList array. If one of the fields is missing, we will add it to the      my @fromPathList = ();
1842                  # @missing list.      my @toPathList = ();
1843                  my @fieldList = @{$relationDefinition->{Fields}};      # This final list is used to remember what work still needs to be done. We push paths
1844                  my @fieldNameList = ();      # onto the list, then pop them off to extend the paths. We prime it with the starting
1845                  my @valueList = ();      # point. Note that we will work hard to insure that the last item on a path in the
1846                  my @missing = ();      # to-do list is always an entity.
1847                  my $recordCount = 1;      my @todoList = ([$entityName]);
1848                  for my $fieldDescriptor (@fieldList) {      while (@todoList) {
1849                          # Get the field name and save it. Note we need to fix it up so the hyphens          # Get the current path.
1850                          # are converted to underscores.          my $current = pop @todoList;
1851                          my $fieldName = $fieldDescriptor->{name};          # Copy it into a list.
1852                          push @fieldNameList, _FixName($fieldName);          my @stackedPath = @{$current};
1853                          # Look for the named field in the incoming structure. Note that we are looking          # Pull off the last item on the path. It will always be an entity.
1854                          # for the real field name, not the fixed-up one!          my $myEntityName = pop @stackedPath;
1855                          if (exists $fieldHash->{$fieldName}) {          # Add it to the alreadyFound list.
1856                                  # Here we found the field. Stash it in the value list.          $alreadyFound{$myEntityName} = 1;
1857                                  my $value = $fieldHash->{$fieldName};          # Figure out if we need to delete this entity.
1858                                  push @valueList, $value;          if ($myEntityName ne $entityName || ! $options{keepRoot}) {
1859                                  # If the value is a list, we may need to increment the record count.              # Get the entity data.
1860                                  if (ref $value eq "ARRAY") {              my $entityData = $self->_GetStructure($myEntityName);
1861                                          my $thisCount = @{$value};              # Loop through the entity's relations. A DELETE command will be needed for each of them.
1862                                          if ($recordCount == 1) {              my $relations = $entityData->{Relations};
1863                                                  # Here we have our first list, so we save its count.              for my $relation (keys %{$relations}) {
1864                                                  $recordCount = $thisCount;                  my @augmentedList = (@stackedPath, $relation);
1865                                          } elsif ($recordCount != $thisCount) {                  push @fromPathList, \@augmentedList;
                                                 # Here we have a second list, so its length has to match the  
                                                 # previous lists.  
                                                 Trace("Field $value in new $newObjectType object has an invalid list length $thisCount. Expected $recordCount.") if T(0);  
                                                 $retVal = 0;  
1866                                          }                                          }
1867                                  }                                  }
1868            # Now we need to look for relationships connected to this entity.
1869            my $relationshipList = $self->{_metaData}->{Relationships};
1870            for my $relationshipName (keys %{$relationshipList}) {
1871                my $relationship = $relationshipList->{$relationshipName};
1872                # Check the FROM field. We're only interested if it's us.
1873                if ($relationship->{from} eq $myEntityName) {
1874                    # Add the path to this relationship.
1875                    my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1876                    push @fromPathList, \@augmentedList;
1877                    # Check the arity. If it's MM we're done. If it's 1M
1878                    # and the target hasn't been seen yet, we want to
1879                    # stack the entity for future processing.
1880                    if ($relationship->{arity} eq '1M') {
1881                        my $toEntity = $relationship->{to};
1882                        if (! exists $alreadyFound{$toEntity}) {
1883                            # Here we have a new entity that's dependent on
1884                            # the current entity, so we need to stack it.
1885                            my @stackList = (@augmentedList, $toEntity);
1886                            push @fromPathList, \@stackList;
1887                          } else {                          } else {
1888                                  # Here the field is not present. Flag it as missing.                          Trace("$toEntity ignored because it occurred previously.") if T(4);
                                 push @missing, $fieldName;  
1889                          }                          }
1890                  }                  }
                 # If we are the primary relation, add the new-record flag.  
                 if ($relationName eq $newObjectType) {  
                         push @valueList, 1;  
                         push @fieldNameList, "new_record";  
1891                  }                  }
1892                  # Only proceed if there are no missing fields.              # Now check the TO field. In this case only the relationship needs
1893                  if (@missing > 0) {              # deletion.
1894                          Trace("Relation $relationName for $newObjectType skipped due to missing fields: " .              if ($relationship->{to} eq $myEntityName) {
1895                                  join(' ', @missing)) if T(1);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1896                  } else {                  push @toPathList, \@augmentedList;
                         # Build the INSERT statement.  
                         my $statement = "INSERT INTO $relationName (" . join (', ', @fieldNameList) .  
                                 ") VALUES (";  
                         # Create a marker list of the proper size and put it in the statement.  
                         my @markers = ();  
                         while (@markers < @fieldNameList) { push @markers, '?'; }  
                         $statement .= join(', ', @markers) . ")";  
                         # We have the insert statement, so prepare it.  
                         my $sth = $dbh->prepare_command($statement);  
                         Trace("Insert statement prepared: $statement") if T(3);  
                         # Now we loop through the values. If a value is scalar, we use it unmodified. If it's  
                         # a list, we use the current element. The values are stored in the @parameterList array.  
                         my $done = 0;  
                         for (my $i = 0; $i < $recordCount; $i++) {  
                                 # Clear the parameter list array.  
                                 my @parameterList = ();  
                                 # Loop through the values.  
                                 for my $value (@valueList) {  
                                         # Check to see if this is a scalar value.  
                                         if (ref $value eq "ARRAY") {  
                                                 # Here we have a list value. Pull the current entry.  
                                                 push @parameterList, $value->[$i];  
                                         } else {  
                                                 # Here we have a scalar value. Use it unmodified.  
                                                 push @parameterList, $value;  
1897                                          }                                          }
1898                                  }                                  }
                                 # Execute the INSERT statement with the specified parameter list.  
                                 $retVal = $sth->execute(@parameterList);  
                                 if (!$retVal) {  
                                         my $errorString = $sth->errstr();  
                                         Trace("Insert error: $errorString.") if T(0);  
1899                                  }                                  }
1900        # Create the first qualifier for the WHERE clause. This selects the
1901        # keys of the primary entity records to be deleted. When we're deleting
1902        # from a dependent table, we construct a join path from the first qualifier
1903        # to the table containing the dependent records to delete.
1904        my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
1905        # We need to make two passes. The first is through the to-list, and
1906        # the second through the from-list. The from-list is second because
1907        # the to-list may need to pass through some of the entities the
1908        # from-list would delete.
1909        my %stackList = ( from_link => \@fromPathList, to_link => \@toPathList );
1910        # Now it's time to do the deletes. We do it in two passes.
1911        for my $keyName ('to_link', 'from_link') {
1912            # Get the list for this key.
1913            my @pathList = @{$stackList{$keyName}};
1914            Trace(scalar(@pathList) . " entries in path list for $keyName.") if T(3);
1915            # Loop through this list.
1916            while (my $path = pop @pathList) {
1917                # Get the table whose rows are to be deleted.
1918                my @pathTables = @{$path};
1919                # Start the DELETE statement. We need to call DBKernel because the
1920                # syntax of a DELETE-USING varies among DBMSs.
1921                my $target = $pathTables[$#pathTables];
1922                my $stmt = $db->SetUsing(@pathTables);
1923                # Now start the WHERE. The first thing is the ID field from the starting table. That
1924                # starting table will either be the entity relation or one of the entity's
1925                # sub-relations.
1926                $stmt .= " WHERE $pathTables[0].id $qualifier";
1927                # Now we run through the remaining entities in the path, connecting them up.
1928                for (my $i = 1; $i <= $#pathTables; $i += 2) {
1929                    # Connect the current relationship to the preceding entity.
1930                    my ($entity, $rel) = @pathTables[$i-1,$i];
1931                    # The style of connection depends on the direction of the relationship.
1932                    $stmt .= " AND $entity.id = $rel.$keyName";
1933                    if ($i + 1 <= $#pathTables) {
1934                        # Here there's a next entity, so connect that to the relationship's
1935                        # to-link.
1936                        my $entity2 = $pathTables[$i+1];
1937                        $stmt .= " AND $rel.to_link = $entity2.id";
1938                    }
1939                }
1940                # Now we have our desired DELETE statement.
1941                if ($options{testMode}) {
1942                    # Here the user wants to trace without executing.
1943                    Trace($stmt) if T(0);
1944                } else {
1945                    # Here we can delete. Note that the SQL method dies with a confession
1946                    # if an error occurs, so we just go ahead and do it.
1947                    Trace("Executing delete from $target using '$objectID'.") if T(3);
1948                    my $rv = $db->SQL($stmt, 0, $objectID);
1949                    # Accumulate the statistics for this delete. The only rows deleted
1950                    # are from the target table, so we use its name to record the
1951                    # statistic.
1952                    $retVal->Add($target, $rv);
1953                          }                          }
1954                  }                  }
1955          }          }
1956          # Return the success indicator.      # Return the result.
1957          return $retVal;          return $retVal;
1958  }  }
1959    
1960  =head3 LoadTable  =head3 Disconnect
1961    
1962    C<< $erdb->Disconnect($relationshipName, $originEntityName, $originEntityID); >>
1963    
1964  C<< my %results = $database->LoadTable($fileName, $relationName, $truncateFlag); >>  Disconnect an entity instance from all the objects to which it is related. This
1965    will delete each relationship instance that connects to the specified entity.
1966    
1967  Load data from a tab-delimited file into a specified table, optionally re-creating the table first.  =over 4
1968    
1969    =item relationshipName
1970    
1971    Name of the relationship whose instances are to be deleted.
1972    
1973    =item originEntityName
1974    
1975    Name of the entity that is to be disconnected.
1976    
1977    =item originEntityID
1978    
1979    ID of the entity that is to be disconnected.
1980    
1981    =back
1982    
1983    =cut
1984    
1985    sub Disconnect {
1986        # Get the parameters.
1987        my ($self, $relationshipName, $originEntityName, $originEntityID) = @_;
1988        # Get the relationship descriptor.
1989        my $structure = $self->_GetStructure($relationshipName);
1990        # Insure we have a relationship.
1991        if (! exists $structure->{from}) {
1992            Confess("$relationshipName is not a relationship in the database.");
1993        } else {
1994            # Get the database handle.
1995            my $dbh = $self->{_dbh};
1996            # We'll set this value to 1 if we find our entity.
1997            my $found = 0;
1998            # Loop through the ends of the relationship.
1999            for my $dir ('from', 'to') {
2000                if ($structure->{$dir} eq $originEntityName) {
2001                    # Delete all relationship instances on this side of the entity instance.
2002                    Trace("Disconnecting in $dir direction with ID \"$originEntityID\".");
2003                    $dbh->SQL("DELETE FROM $relationshipName WHERE ${dir}_link = ?", 0, $originEntityID);
2004                    $found = 1;
2005                }
2006            }
2007            # Insure we found the entity on at least one end.
2008            if (! $found) {
2009                Confess("Entity \"$originEntityName\" does not use $relationshipName.");
2010            }
2011        }
2012    }
2013    
2014    =head3 DeleteRow
2015    
2016    C<< $erdb->DeleteRow($relationshipName, $fromLink, $toLink, \%values); >>
2017    
2018    Delete a row from a relationship. In most cases, only the from-link and to-link are
2019    needed; however, for relationships with intersection data values can be specified
2020    for the other fields using a hash.
2021    
2022  =over 4  =over 4
2023    
2024  =item fileName  =item relationshipName
2025    
2026    Name of the relationship from which the row is to be deleted.
2027    
2028    =item fromLink
2029    
2030    ID of the entity instance in the From direction.
2031    
2032    =item toLink
2033    
2034    ID of the entity instance in the To direction.
2035    
2036    =item values
2037    
2038    Reference to a hash of other values to be used for filtering the delete.
2039    
2040    =back
2041    
2042    =cut
2043    
2044    sub DeleteRow {
2045        # Get the parameters.
2046        my ($self, $relationshipName, $fromLink, $toLink, $values) = @_;
2047        # Create a hash of all the filter information.
2048        my %filter = ('from-link' => $fromLink, 'to-link' => $toLink);
2049        if (defined $values) {
2050            for my $key (keys %{$values}) {
2051                $filter{$key} = $values->{$key};
2052            }
2053        }
2054        # Build an SQL statement out of the hash.
2055        my @filters = ();
2056        my @parms = ();
2057        for my $key (keys %filter) {
2058            push @filters, _FixName($key) . " = ?";
2059            push @parms, $filter{$key};
2060        }
2061        Trace("Parms for delete row are " . join(", ", map { "\"$_\"" } @parms) . ".") if T(SQL => 4);
2062        my $command = "DELETE FROM $relationshipName WHERE " .
2063                      join(" AND ", @filters);
2064        # Execute it.
2065        my $dbh = $self->{_dbh};
2066        $dbh->SQL($command, undef, @parms);
2067    }
2068    
2069    =head3 SortNeeded
2070    
2071    C<< my $parms = $erdb->SortNeeded($relationName); >>
2072    
2073    Return the pipe command for the sort that should be applied to the specified
2074    relation when creating the load file.
2075    
2076    For example, if the load file should be sorted ascending by the first
2077    field, this method would return
2078    
2079        sort -k1 -t"\t"
2080    
2081    If the first field is numeric, the method would return
2082    
2083        sort -k1n -t"\t"
2084    
2085    Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate
2086    keys using a sort.
2087    
2088    =over 4
2089    
2090    =item relationName
2091    
2092    Name of the relation to be examined.
2093    
2094    =item
2095    
2096    Returns the sort command to use for sorting the relation, suitable for piping.
2097    
2098    =back
2099    
2100    =cut
2101    #: Return Type $;
2102    sub SortNeeded {
2103        # Get the parameters.
2104        my ($self, $relationName) = @_;
2105        # Declare a descriptor to hold the names of the key fields.
2106        my @keyNames = ();
2107        # Get the relation structure.
2108        my $relationData = $self->_FindRelation($relationName);
2109        # Find out if the relation is a primary entity relation,
2110        # a relationship relation, or a secondary entity relation.
2111        my $entityTable = $self->{_metaData}->{Entities};
2112        my $relationshipTable = $self->{_metaData}->{Relationships};
2113        if (exists $entityTable->{$relationName}) {
2114            # Here we have a primary entity relation.
2115            push @keyNames, "id";
2116        } elsif (exists $relationshipTable->{$relationName}) {
2117            # Here we have a relationship. We sort using the FROM index.
2118            my $relationshipData = $relationshipTable->{$relationName};
2119            my $index = $relationData->{Indexes}->{idxFrom};
2120            push @keyNames, @{$index->{IndexFields}};
2121        } else {
2122            # Here we have a secondary entity relation, so we have a sort on the ID field.
2123            push @keyNames, "id";
2124        }
2125        # Now we parse the key names into sort parameters. First, we prime the return
2126        # string.
2127        my $retVal = "sort -t\"\t\" ";
2128        # Get the relation's field list.
2129        my @fields = @{$relationData->{Fields}};
2130        # Loop through the keys.
2131        for my $keyData (@keyNames) {
2132            # Get the key and the ordering.
2133            my ($keyName, $ordering);
2134            if ($keyData =~ /^([^ ]+) DESC/) {
2135                ($keyName, $ordering) = ($1, "descending");
2136            } else {
2137                ($keyName, $ordering) = ($keyData, "ascending");
2138            }
2139            # Find the key's position and type.
2140            my $fieldSpec;
2141            for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {
2142                my $thisField = $fields[$i];
2143                if ($thisField->{name} eq $keyName) {
2144                    # Get the sort modifier for this field type. The modifier
2145                    # decides whether we're using a character, numeric, or
2146                    # floating-point sort.
2147                    my $modifier = $TypeTable{$thisField->{type}}->{sort};
2148                    # If the index is descending for this field, denote we want
2149                    # to reverse the sort order on this field.
2150                    if ($ordering eq 'descending') {
2151                        $modifier .= "r";
2152                    }
2153                    # Store the position and modifier into the field spec, which
2154                    # will stop the inner loop. Note that the field number is
2155                    # 1-based in the sort command, so we have to increment the
2156                    # index.
2157                    $fieldSpec = ($i + 1) . $modifier;
2158                }
2159            }
2160            # Add this field to the sort command.
2161            $retVal .= " -k$fieldSpec";
2162        }
2163        # Return the result.
2164        return $retVal;
2165    }
2166    
2167    =head3 GetList
2168    
2169    C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>
2170    
2171    Return a list of object descriptors for the specified objects as determined by the
2172    specified filter clause.
2173    
2174    This method is essentially the same as L</Get> except it returns a list of objects rather
2175    than a query object that can be used to get the results one record at a time.
2176    
2177    =over 4
2178    
2179    =item objectNames
2180    
2181    List containing the names of the entity and relationship objects to be retrieved.
2182    
2183    =item filterClause
2184    
2185    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
2186    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
2187    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
2188    in the filter clause should be added to the parameter list as additional parameters. The
2189    fields in a filter clause can come from primary entity relations, relationship relations,
2190    or secondary entity relations; however, all of the entities and relationships involved must
2191    be included in the list of object names.
2192    
2193    The filter clause can also specify a sort order. To do this, simply follow the filter string
2194    with an ORDER BY clause. For example, the following filter string gets all genomes for a
2195    particular genus and sorts them by species name.
2196    
2197    C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
2198    
2199    The rules for field references in a sort order are the same as those for field references in the
2200    filter clause in general; however, odd things may happen if a sort field is from a secondary
2201    relation.
2202    
2203    =item params
2204    
2205    Reference to a list of parameter values to be substituted into the filter clause.
2206    
2207    =item RETURN
2208    
2209    Returns a list of B<ERDBObject>s that satisfy the query conditions.
2210    
2211    =back
2212    
2213    =cut
2214    #: Return Type @%
2215    sub GetList {
2216        # Get the parameters.
2217        my ($self, $objectNames, $filterClause, $params) = @_;
2218        # Declare the return variable.
2219        my @retVal = ();
2220        # Perform the query.
2221        my $query = $self->Get($objectNames, $filterClause, $params);
2222        # Loop through the results.
2223        while (my $object = $query->Fetch) {
2224            push @retVal, $object;
2225        }
2226        # Return the result.
2227        return @retVal;
2228    }
2229    
2230    =head3 GetCount
2231    
2232    C<< my $count = $erdb->GetCount(\@objectNames, $filter, \@params); >>
2233    
2234    Return the number of rows found by a specified query. This method would
2235    normally be used to count the records in a single table. For example, in a
2236    genetics database
2237    
2238        my $count = $erdb->GetCount(['Genome'], 'Genome(genus-species) LIKE ?', ['homo %']);
2239    
2240    would return the number of genomes for the genus I<homo>. It is conceivable, however,
2241    to use it to return records based on a join. For example,
2242    
2243        my $count = $erdb->GetCount(['HasFeature', 'Genome'], 'Genome(genus-species) LIKE ?',
2244                                    ['homo %']);
2245    
2246    would return the number of features for genomes in the genus I<homo>. Note that
2247    only the rows from the first table are counted. If the above command were
2248    
2249        my $count = $erdb->GetCount(['Genome', 'Feature'], 'Genome(genus-species) LIKE ?',
2250                                    ['homo %']);
2251    
2252    it would return the number of genomes, not the number of genome/feature pairs.
2253    
2254    =over 4
2255    
2256    =item objectNames
2257    
2258    Reference to a list of the objects (entities and relationships) included in the
2259    query.
2260    
2261    =item filter
2262    
2263    A filter clause for restricting the query. The rules are the same as for the L</Get>
2264    method.
2265    
2266    =item params
2267    
2268    Reference to a list of the parameter values to be substituted for the parameter marks
2269    in the filter.
2270    
2271    =item RETURN
2272    
2273    Returns a count of the number of records in the first table that would satisfy
2274    the query.
2275    
2276    =back
2277    
2278    =cut
2279    
2280    sub GetCount {
2281        # Get the parameters.
2282        my ($self, $objectNames, $filter, $params) = @_;
2283        # Insure the params argument is an array reference if the caller left it off.
2284        if (! defined($params)) {
2285            $params = [];
2286        }
2287        # Declare the return variable.
2288        my $retVal;
2289        # Find out if we're counting an entity or a relationship.
2290        my $countedField;
2291        if ($self->IsEntity($objectNames->[0])) {
2292            $countedField = "id";
2293        } else {
2294            # For a relationship we count the to-link because it's usually more
2295            # numerous. Note we're automatically converting to the SQL form
2296            # of the field name (to_link vs. to-link).
2297            $countedField = "to_link";
2298        }
2299        # Create the SQL command suffix to get the desired records.
2300        my ($suffix, $mappedNameListRef, $mappedNameHashRef) = $self->_SetupSQL($objectNames,
2301                                                                                $filter);
2302        # Prefix it with text telling it we want a record count.
2303        my $firstObject = $mappedNameListRef->[0];
2304        my $command = "SELECT COUNT($firstObject.$countedField) $suffix";
2305        # Prepare and execute the command.
2306        my $sth = $self->_GetStatementHandle($command, $params);
2307        # Get the count value.
2308        ($retVal) = $sth->fetchrow_array();
2309        # Check for a problem.
2310        if (! defined($retVal)) {
2311            if ($sth->err) {
2312                # Here we had an SQL error.
2313                Confess("Error retrieving row count: " . $sth->errstr());
2314            } else {
2315                # Here we have no result.
2316                Confess("No result attempting to retrieve row count.");
2317            }
2318        }
2319        # Return the result.
2320        return $retVal;
2321    }
2322    
2323    =head3 ComputeObjectSentence
2324    
2325    C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>
2326    
2327    Check an object name, and if it is a relationship convert it to a relationship sentence.
2328    
2329    =over 4
2330    
2331    =item objectName
2332    
2333    Name of the entity or relationship.
2334    
2335    =item RETURN
2336    
2337    Returns a string containing the entity name or a relationship sentence.
2338    
2339    =back
2340    
2341    =cut
2342    
2343    sub ComputeObjectSentence {
2344        # Get the parameters.
2345        my ($self, $objectName) = @_;
2346        # Set the default return value.
2347        my $retVal = $objectName;
2348        # Look for the object as a relationship.
2349        my $relTable = $self->{_metaData}->{Relationships};
2350        if (exists $relTable->{$objectName}) {
2351            # Get the relationship sentence.
2352            $retVal = _ComputeRelationshipSentence($objectName, $relTable->{$objectName});
2353        }
2354        # Return the result.
2355        return $retVal;
2356    }
2357    
2358    =head3 DumpRelations
2359    
2360    C<< $erdb->DumpRelations($outputDirectory); >>
2361    
2362    Write the contents of all the relations to tab-delimited files in the specified directory.
2363    Each file will have the same name as the relation dumped, with an extension of DTX.
2364    
2365    =over 4
2366    
2367    =item outputDirectory
2368    
2369    Name of the directory into which the relation files should be dumped.
2370    
2371    =back
2372    
2373    =cut
2374    
2375    sub DumpRelations {
2376        # Get the parameters.
2377        my ($self, $outputDirectory) = @_;
2378        # Now we need to run through all the relations. First, we loop through the entities.
2379        my $metaData = $self->{_metaData};
2380        my $entities = $metaData->{Entities};
2381        for my $entityName (keys %{$entities}) {
2382            my $entityStructure = $entities->{$entityName};
2383            # Get the entity's relations.
2384            my $relationList = $entityStructure->{Relations};
2385            # Loop through the relations, dumping them.
2386            for my $relationName (keys %{$relationList}) {
2387                my $relation = $relationList->{$relationName};
2388                $self->_DumpRelation($outputDirectory, $relationName, $relation);
2389            }
2390        }
2391        # Next, we loop through the relationships.
2392        my $relationships = $metaData->{Relationships};
2393        for my $relationshipName (keys %{$relationships}) {
2394            my $relationshipStructure = $relationships->{$relationshipName};
2395            # Dump this relationship's relation.
2396            $self->_DumpRelation($outputDirectory, $relationshipName, $relationshipStructure->{Relations}->{$relationshipName});
2397        }
2398    }
2399    
2400    =head3 InsertValue
2401    
2402    C<< $erdb->InsertValue($entityID, $fieldName, $value); >>
2403    
2404    This method will insert a new value into the database. The value must be one
2405    associated with a secondary relation, since primary values cannot be inserted:
2406    they occur exactly once. Secondary values, on the other hand, can be missing
2407    or multiply-occurring.
2408    
2409    =over 4
2410    
2411    =item entityID
2412    
2413    ID of the object that is to receive the new value.
2414    
2415    =item fieldName
2416    
2417    Field name for the new value-- this includes the entity name, since
2418    field names are of the format I<objectName>C<(>I<fieldName>C<)>.
2419    
2420    =item value
2421    
2422    New value to be put in the field.
2423    
2424    =back
2425    
2426    =cut
2427    
2428    sub InsertValue {
2429        # Get the parameters.
2430        my ($self, $entityID, $fieldName, $value) = @_;
2431        # Parse the entity name and the real field name.
2432        if ($fieldName =~ /^([^(]+)\(([^)]+)\)/) {
2433            my $entityName = $1;
2434            my $fieldTitle = $2;
2435            # Get its descriptor.
2436            if (!$self->IsEntity($entityName)) {
2437                Confess("$entityName is not a valid entity.");
2438            } else {
2439                my $entityData = $self->{_metaData}->{Entities}->{$entityName};
2440                # Find the relation containing this field.
2441                my $fieldHash = $entityData->{Fields};
2442                if (! exists $fieldHash->{$fieldTitle}) {
2443                    Confess("$fieldTitle not found in $entityName.");
2444                } else {
2445                    my $relation = $fieldHash->{$fieldTitle}->{relation};
2446                    if ($relation eq $entityName) {
2447                        Confess("Cannot do InsertValue on primary field $fieldTitle of $entityName.");
2448                    } else {
2449                        # Now we can create an INSERT statement.
2450                        my $dbh = $self->{_dbh};
2451                        my $fixedName = _FixName($fieldTitle);
2452                        my $statement = "INSERT INTO $relation (id, $fixedName) VALUES(?, ?)";
2453                        # Execute the command.
2454                        $dbh->SQL($statement, 0, $entityID, $value);
2455                    }
2456                }
2457            }
2458        } else {
2459            Confess("$fieldName is not a valid field name.");
2460        }
2461    }
2462    
2463    =head3 InsertObject
2464    
2465    C<< $erdb->InsertObject($objectType, \%fieldHash); >>
2466    
2467    Insert an object into the database. The object is defined by a type name and then a hash
2468    of field names to values. Field values in the primary relation are represented by scalars.
2469    (Note that for relationships, the primary relation is the B<only> relation.)
2470    Field values for the other relations comprising the entity are always list references. For
2471    example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases
2472    C<ZP_00210270.1> and C<gi|46206278>.
2473    
2474    C<< $erdb->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>
2475    
2476    The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
2477    property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
2478    
2479    C<< $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>
2480    
2481    =over 4
2482    
2483    =item newObjectType
2484    
2485    Type name of the object to insert.
2486    
2487    =item fieldHash
2488    
2489    Hash of field names to values.
2490    
2491    =back
2492    
2493    =cut
2494    
2495    sub InsertObject {
2496        # Get the parameters.
2497        my ($self, $newObjectType, $fieldHash) = @_;
2498        # Denote that so far we appear successful.
2499        my $retVal = 1;
2500        # Get the database handle.
2501        my $dbh = $self->{_dbh};
2502        # Get the relation list.
2503        my $relationTable = $self->_GetRelationTable($newObjectType);
2504        # Loop through the relations. We'll build insert statements for each one. If a relation is
2505        # secondary, we may end up generating multiple insert statements. If an error occurs, we
2506        # stop the loop.
2507        my @relationList = keys %{$relationTable};
2508        for (my $i = 0; $retVal && $i <= $#relationList; $i++) {
2509            my $relationName = $relationList[$i];
2510            my $relationDefinition = $relationTable->{$relationName};
2511            # Get the relation's fields. For each field we will collect a value in the corresponding
2512            # position of the @valueList array. If one of the fields is missing, we will add it to the
2513            # @missing list.
2514            my @fieldList = @{$relationDefinition->{Fields}};
2515            my @fieldNameList = ();
2516            my @valueList = ();
2517            my @missing = ();
2518            my $recordCount = 1;
2519            for my $fieldDescriptor (@fieldList) {
2520                # Get the field name and save it. Note we need to fix it up so the hyphens
2521                # are converted to underscores.
2522                my $fieldName = $fieldDescriptor->{name};
2523                push @fieldNameList, _FixName($fieldName);
2524                # Look for the named field in the incoming structure. Note that we are looking
2525                # for the real field name, not the fixed-up one!
2526                if (exists $fieldHash->{$fieldName}) {
2527                    # Here we found the field. Stash it in the value list.
2528                    my $value = $fieldHash->{$fieldName};
2529                    push @valueList, $value;
2530                    # If the value is a list, we may need to increment the record count.
2531                    if (ref $value eq "ARRAY") {
2532                        my $thisCount = @{$value};
2533                        if ($recordCount == 1) {
2534                            # Here we have our first list, so we save its count.
2535                            $recordCount = $thisCount;
2536                        } elsif ($recordCount != $thisCount) {
2537                            # Here we have a second list, so its length has to match the
2538                            # previous lists.
2539                            Trace("Field $value in new $newObjectType object has an invalid list length $thisCount. Expected $recordCount.") if T(0);
2540                            $retVal = 0;
2541                        }
2542                    }
2543                } else {
2544                    # Here the field is not present. Flag it as missing.
2545                    push @missing, $fieldName;
2546                }
2547            }
2548            # If we are the primary relation, add the new-record flag.
2549            if ($relationName eq $newObjectType) {
2550                push @valueList, 1;
2551                push @fieldNameList, "new_record";
2552            }
2553            # Only proceed if there are no missing fields.
2554            if (@missing > 0) {
2555                Trace("Relation $relationName for $newObjectType skipped due to missing fields: " .
2556                    join(' ', @missing)) if T(1);
2557            } else {
2558                # Build the INSERT statement.
2559                my $statement = "INSERT INTO $relationName (" . join (', ', @fieldNameList) .
2560                    ") VALUES (";
2561                # Create a marker list of the proper size and put it in the statement.
2562                my @markers = ();
2563                while (@markers < @fieldNameList) { push @markers, '?'; }
2564                $statement .= join(', ', @markers) . ")";
2565                # We have the insert statement, so prepare it.
2566                my $sth = $dbh->prepare_command($statement);
2567                Trace("Insert statement prepared: $statement") if T(3);
2568                # Now we loop through the values. If a value is scalar, we use it unmodified. If it's
2569                # a list, we use the current element. The values are stored in the @parameterList array.
2570                my $done = 0;
2571                for (my $i = 0; $i < $recordCount; $i++) {
2572                    # Clear the parameter list array.
2573                    my @parameterList = ();
2574                    # Loop through the values.
2575                    for my $value (@valueList) {
2576                        # Check to see if this is a scalar value.
2577                        if (ref $value eq "ARRAY") {
2578                            # Here we have a list value. Pull the current entry.
2579                            push @parameterList, $value->[$i];
2580                        } else {
2581                            # Here we have a scalar value. Use it unmodified.
2582                            push @parameterList, $value;
2583                        }
2584                    }
2585                    # Execute the INSERT statement with the specified parameter list.
2586                    $retVal = $sth->execute(@parameterList);
2587                    if (!$retVal) {
2588                        my $errorString = $sth->errstr();
2589                        Confess("Error inserting into $relationName: $errorString");
2590                    } else {
2591                        Trace("Insert successful using $parameterList[0].") if T(3);
2592                    }
2593                }
2594            }
2595        }
2596        # Return a 1 for backward compatability.
2597        return 1;
2598    }
2599    
2600    =head3 UpdateEntity
2601    
2602    C<< $erdb->UpdateEntity($entityName, $id, \%fields); >>
2603    
2604    Update the values of an entity. This is an unprotected update, so it should only be
2605    done if the database resides on a database server.
2606    
2607    =over 4
2608    
2609    =item entityName
2610    
2611    Name of the entity to update. (This is the entity type.)
2612    
2613    =item id
2614    
2615    ID of the entity to update. If no entity exists with this ID, an error will be thrown.
2616    
2617    =item fields
2618    
2619    Reference to a hash mapping field names to their new values. All of the fields named
2620    must be in the entity's primary relation, and they cannot any of them be the ID field.
2621    
2622    =back
2623    
2624    =cut
2625    
2626    sub UpdateEntity {
2627        # Get the parameters.
2628        my ($self, $entityName, $id, $fields) = @_;
2629        # Get a list of the field names being updated.
2630        my @fieldList = keys %{$fields};
2631        # Verify that the fields exist.
2632        my $checker = $self->GetFieldTable($entityName);
2633        for my $field (@fieldList) {
2634            if ($field eq 'id') {
2635                Confess("Cannot update the ID field for entity $entityName.");
2636            } elsif ($checker->{$field}->{relation} ne $entityName) {
2637                Confess("Cannot find $field in primary relation of $entityName.");
2638            }
2639        }
2640        # Build the SQL statement.
2641        my @sets = ();
2642        my @valueList = ();
2643        for my $field (@fieldList) {
2644            push @sets, _FixName($field) . " = ?";
2645            push @valueList, $fields->{$field};
2646        }
2647        my $command = "UPDATE $entityName SET " . join(", ", @sets) . " WHERE id = ?";
2648        # Add the ID to the list of binding values.
2649        push @valueList, $id;
2650        # Call SQL to do the work.
2651        my $rows = $self->{_dbh}->SQL($command, 0, @valueList);
2652        # Check for errors.
2653        if ($rows == 0) {
2654            Confess("Entity $id of type $entityName not found.");
2655        }
2656    }
2657    
2658    =head3 LoadTable
2659    
2660    C<< my $results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>
2661    
2662    Load data from a tab-delimited file into a specified table, optionally re-creating the table
2663    first.
2664    
2665    =over 4
2666    
2667    =item fileName
2668    
2669    Name of the file from which the table data should be loaded.
2670    
2671    =item relationName
2672    
2673    Name of the relation to be loaded. This is the same as the table name.
2674    
2675    =item truncateFlag
2676    
2677    TRUE if the table should be dropped and re-created, else FALSE
2678    
2679    =item RETURN
2680    
2681    Returns a statistical object containing a list of the error messages.
2682    
2683    =back
2684    
2685    =cut
2686    sub LoadTable {
2687        # Get the parameters.
2688        my ($self, $fileName, $relationName, $truncateFlag) = @_;
2689        # Create the statistical return object.
2690        my $retVal = _GetLoadStats();
2691        # Trace the fact of the load.
2692        Trace("Loading table $relationName from $fileName") if T(2);
2693        # Get the database handle.
2694        my $dbh = $self->{_dbh};
2695        # Get the input file size.
2696        my $fileSize = -s $fileName;
2697        # Get the relation data.
2698        my $relation = $self->_FindRelation($relationName);
2699        # Check the truncation flag.
2700        if ($truncateFlag) {
2701            Trace("Creating table $relationName") if T(2);
2702            # Compute the row count estimate. We take the size of the load file,
2703            # divide it by the estimated row size, and then multiply by 1.5 to
2704            # leave extra room. We postulate a minimum row count of 1000 to
2705            # prevent problems with incoming empty load files.
2706            my $rowSize = $self->EstimateRowSize($relationName);
2707            my $estimate = FIG::max($fileSize * 1.5 / $rowSize, 1000);
2708            # Re-create the table without its index.
2709            $self->CreateTable($relationName, 0, $estimate);
2710            # If this is a pre-index DBMS, create the index here.
2711            if ($dbh->{_preIndex}) {
2712                eval {
2713                    $self->CreateIndex($relationName);
2714                };
2715                if ($@) {
2716                    $retVal->AddMessage($@);
2717                }
2718            }
2719        }
2720        # Load the table.
2721        my $rv;
2722        eval {
2723            $rv = $dbh->load_table(file => $fileName, tbl => $relationName);
2724        };
2725        if (!defined $rv) {
2726            $retVal->AddMessage($@) if ($@);
2727            $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2728            Trace("Table load failed for $relationName.") if T(1);
2729        } else {
2730            # Here we successfully loaded the table.
2731            $retVal->Add("tables");
2732            my $size = -s $fileName;
2733            Trace("$size bytes loaded into $relationName.") if T(2);
2734            # If we're rebuilding, we need to create the table indexes.
2735            if ($truncateFlag) {
2736                # Indexes are created here for PostGres. For PostGres, indexes are
2737                # best built at the end. For MySQL, the reverse is true.
2738                if (! $dbh->{_preIndex}) {
2739                    eval {
2740                        $self->CreateIndex($relationName);
2741                    };
2742                    if ($@) {
2743                        $retVal->AddMessage($@);
2744                    }
2745                }
2746                # The full-text index (if any) is always built last, even for MySQL.
2747                # First we need to see if this table has a full-text index. Only
2748                # primary relations are allowed that privilege.
2749                Trace("Checking for full-text index on $relationName.") if T(2);
2750                if ($self->_IsPrimary($relationName)) {
2751                    $self->CreateSearchIndex($relationName);
2752                }
2753            }
2754        }
2755        # Analyze the table to improve performance.
2756        Trace("Analyzing and compacting $relationName.") if T(3);
2757        $dbh->vacuum_it($relationName);
2758        Trace("$relationName load completed.") if T(3);
2759        # Return the statistics.
2760        return $retVal;
2761    }
2762    
2763    =head3 CreateSearchIndex
2764    
2765    C<< $erdb->CreateSearchIndex($objectName); >>
2766    
2767    Check for a full-text search index on the specified entity or relationship object, and
2768    if one is required, rebuild it.
2769    
2770    =over 4
2771    
2772    =item objectName
2773    
2774    Name of the entity or relationship to be indexed.
2775    
2776    =back
2777    
2778    =cut
2779    
2780    sub CreateSearchIndex {
2781        # Get the parameters.
2782        my ($self, $objectName) = @_;
2783        # Get the relation's entity/relationship structure.
2784        my $structure = $self->_GetStructure($objectName);
2785        # Get the database handle.
2786        my $dbh = $self->{_dbh};
2787        Trace("Checking for search fields in $objectName.") if T(3);
2788        # Check for a searchable fields list.
2789        if (exists $structure->{searchFields}) {
2790            # Here we know that we need to create a full-text search index.
2791            # Get an SQL-formatted field name list.
2792            my $fields = join(", ", _FixNames(@{$structure->{searchFields}}));
2793            # Create the index. If it already exists, it will be dropped.
2794            $dbh->create_index(tbl => $objectName, idx => "search_idx",
2795                               flds => $fields, kind => 'fulltext');
2796            Trace("Index created for $fields in $objectName.") if T(2);
2797        }
2798    }
2799    
2800    =head3 DropRelation
2801    
2802    C<< $erdb->DropRelation($relationName); >>
2803    
2804    Physically drop a relation from the database.
2805    
2806    =over 4
2807    
2808    =item relationName
2809    
2810    Name of the relation to drop. If it does not exist, this method will have
2811    no effect.
2812    
2813    =back
2814    
2815    =cut
2816    
2817    sub DropRelation {
2818        # Get the parameters.
2819        my ($self, $relationName) = @_;
2820        # Get the database handle.
2821        my $dbh = $self->{_dbh};
2822        # Drop the relation. The method used here has no effect if the relation
2823        # does not exist.
2824        Trace("Invoking DB Kernel to drop $relationName.") if T(3);
2825        $dbh->drop_table(tbl => $relationName);
2826    }
2827    
2828    =head3 MatchSqlPattern
2829    
2830    C<< my $matched = ERDB::MatchSqlPattern($value, $pattern); >>
2831    
2832    Determine whether or not a specified value matches an SQL pattern. An SQL
2833    pattern has two wild card characters: C<%> that matches multiple characters,
2834    and C<_> that matches a single character. These can be escaped using a
2835    backslash (C<\>). We pull this off by converting the SQL pattern to a
2836    PERL regular expression. As per SQL rules, the match is case-insensitive.
2837    
2838    =over 4
2839    
2840    =item value
2841    
2842    Value to be matched against the pattern. Note that an undefined or empty
2843    value will not match anything.
2844    
2845    =item pattern
2846    
2847    SQL pattern against which to match the value. An undefined or empty pattern will
2848    match everything.
2849    
2850    =item RETURN
2851    
2852    Returns TRUE if the value and pattern match, else FALSE.
2853    
2854    =back
2855    
2856    =cut
2857    
2858    sub MatchSqlPattern {
2859        # Get the parameters.
2860        my ($value, $pattern) = @_;
2861        # Declare the return variable.
2862        my $retVal;
2863        # Insure we have a pattern.
2864        if (! defined($pattern) || $pattern eq "") {
2865            $retVal = 1;
2866        } else {
2867            # Break the pattern into pieces around the wildcard characters. Because we
2868            # use parentheses in the split function's delimiter expression, we'll get
2869            # list elements for the delimiters as well as the rest of the string.
2870            my @pieces = split /([_%]|\\[_%])/, $pattern;
2871            # Check some fast special cases.
2872            if ($pattern eq '%') {
2873                # A null pattern matches everything.
2874                $retVal = 1;
2875            } elsif (@pieces == 1) {
2876                # No wildcards, so we have a literal comparison. Note we're case-insensitive.
2877                $retVal = (lc($value) eq lc($pattern));
2878            } elsif (@pieces == 2 && $pieces[1] eq '%') {
2879                # A wildcard at the end, so we have a substring match. This is also case-insensitive.
2880                $retVal = (lc(substr($value, 0, length($pieces[0]))) eq lc($pieces[0]));
2881            } else {
2882                # Okay, we have to do it the hard way. Convert each piece to a PERL pattern.
2883                my $realPattern = "";
2884                for my $piece (@pieces) {
2885                    # Determine the type of piece.
2886                    if ($piece eq "") {
2887                        # Empty pieces are ignored.
2888                    } elsif ($piece eq "%") {
2889                        # Here we have a multi-character wildcard. Note that it can match
2890                        # zero or more characters.
2891                        $realPattern .= ".*"
2892                    } elsif ($piece eq "_") {
2893                        # Here we have a single-character wildcard.
2894                        $realPattern .= ".";
2895                    } elsif ($piece eq "\\%" || $piece eq "\\_") {
2896                        # This is an escape sequence (which is a rare thing, actually).
2897                        $realPattern .= substr($piece, 1, 1);
2898                    } else {
2899                        # Here we have raw text.
2900                        $realPattern .= quotemeta($piece);
2901                    }
2902                }
2903                # Do the match.
2904                $retVal = ($value =~ /^$realPattern$/i ? 1 : 0);
2905            }
2906        }
2907        # Return the result.
2908        return $retVal;
2909    }
2910    
2911    =head3 GetEntity
2912    
2913    C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>
2914    
2915    Return an object describing the entity instance with a specified ID.
2916    
2917    =over 4
2918    
2919    =item entityType
2920    
2921    Entity type name.
2922    
2923    =item ID
2924    
2925    ID of the desired entity.
2926    
2927    =item RETURN
2928    
2929    Returns a B<ERDBObject> representing the desired entity instance, or an undefined value if no
2930    instance is found with the specified key.
2931    
2932    =back
2933    
2934    =cut
2935    
2936    sub GetEntity {
2937        # Get the parameters.
2938        my ($self, $entityType, $ID) = @_;
2939        # Create a query.
2940        my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);
2941        # Get the first (and only) object.
2942        my $retVal = $query->Fetch();
2943        # Return the result.
2944        return $retVal;
2945    }
2946    
2947    =head3 GetChoices
2948    
2949    C<< my @values = $erdb->GetChoices($entityName, $fieldName); >>
2950    
2951    Return a list of all the values for the specified field that are represented in the
2952    specified entity.
2953    
2954    Note that if the field is not indexed, then this will be a very slow operation.
2955    
2956    =over 4
2957    
2958    =item entityName
2959    
2960    Name of an entity in the database.
2961    
2962    =item fieldName
2963    
2964    Name of a field belonging to the entity. This is a raw field name without
2965    the standard parenthesized notation used in most calls.
2966    
2967    =item RETURN
2968    
2969    Returns a list of the distinct values for the specified field in the database.
2970    
2971    =back
2972    
2973    =cut
2974    
2975    sub GetChoices {
2976        # Get the parameters.
2977        my ($self, $entityName, $fieldName) = @_;
2978        # Declare the return variable.
2979        my @retVal;
2980        # Get the entity data structure.
2981        my $entityData = $self->_GetStructure($entityName);
2982        # Get the field.
2983        my $fieldHash = $entityData->{Fields};
2984        if (! exists $fieldHash->{$fieldName}) {
2985            Confess("$fieldName not found in $entityName.");
2986        } else {
2987            # Get the name of the relation containing the field.
2988            my $relation = $fieldHash->{$fieldName}->{relation};
2989            # Fix up the field name.
2990            my $realName = _FixName($fieldName);
2991            # Get the database handle.
2992            my $dbh = $self->{_dbh};
2993            # Query the database.
2994            my $results = $dbh->SQL("SELECT DISTINCT $realName FROM $relation");
2995            # Clean the results. They are stored as a list of lists, and we just want the one list.
2996            @retVal = sort map { $_->[0] } @{$results};
2997        }
2998        # Return the result.
2999        return @retVal;
3000    }
3001    
3002    =head3 GetEntityValues
3003    
3004    C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>
3005    
3006    Return a list of values from a specified entity instance. If the entity instance
3007    does not exist, an empty list is returned.
3008    
3009    =over 4
3010    
3011    =item entityType
3012    
3013    Entity type name.
3014    
3015    =item ID
3016    
3017    ID of the desired entity.
3018    
3019    =item fields
3020    
3021    List of field names, each of the form I<objectName>C<(>I<fieldName>C<)>.
3022    
3023    =item RETURN
3024    
3025    Returns a flattened list of the values of the specified fields for the specified entity.
3026    
3027    =back
3028    
3029    =cut
3030    
3031    sub GetEntityValues {
3032        # Get the parameters.
3033        my ($self, $entityType, $ID, $fields) = @_;
3034        # Get the specified entity.
3035        my $entity = $self->GetEntity($entityType, $ID);
3036        # Declare the return list.
3037        my @retVal = ();
3038        # If we found the entity, push the values into the return list.
3039        if ($entity) {
3040            push @retVal, $entity->Values($fields);
3041        }
3042        # Return the result.
3043        return @retVal;
3044    }
3045    
3046    =head3 GetAll
3047    
3048    C<< my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>
3049    
3050    Return a list of values taken from the objects returned by a query. The first three
3051    parameters correspond to the parameters of the L</Get> method. The final parameter is
3052    a list of the fields desired from each record found by the query. The field name
3053    syntax is the standard syntax used for fields in the B<ERDB> system--
3054    B<I<objectName>(I<fieldName>)>-- where I<objectName> is the name of the relevant entity
3055    or relationship and I<fieldName> is the name of the field.
3056    
3057    The list returned will be a list of lists. Each element of the list will contain
3058    the values returned for the fields specified in the fourth parameter. If one of the
3059    fields specified returns multiple values, they are flattened in with the rest. For
3060    example, the following call will return a list of the features in a particular
3061    spreadsheet cell, and each feature will be represented by a list containing the
3062    feature ID followed by all of its aliases.
3063    
3064    C<< @query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>
3065    
3066    =over 4
3067    
3068    =item objectNames
3069    
3070    List containing the names of the entity and relationship objects to be retrieved.
3071    
3072    =item filterClause
3073    
3074    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
3075    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
3076    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
3077    parameter list as additional parameters. The fields in a filter clause can come from primary
3078    entity relations, relationship relations, or secondary entity relations; however, all of the
3079    entities and relationships involved must be included in the list of object names.
3080    
3081    =item parameterList
3082    
3083    List of the parameters to be substituted in for the parameters marks in the filter clause.
3084    
3085    =item fields
3086    
3087    List of the fields to be returned in each element of the list returned.
3088    
3089    =item count
3090    
3091    Maximum number of records to return. If omitted or 0, all available records will be returned.
3092    
3093    =item RETURN
3094    
3095    Returns a list of list references. Each element of the return list contains the values for the
3096    fields specified in the B<fields> parameter.
3097    
3098    =back
3099    
3100    =cut
3101    #: Return Type @@;
3102    sub GetAll {
3103        # Get the parameters.
3104        my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
3105        # Translate the parameters from a list reference to a list. If the parameter
3106        # list is a scalar we convert it into a singleton list.
3107        my @parmList = ();
3108        if (ref $parameterList eq "ARRAY") {
3109            Trace("GetAll parm list is an array.") if T(4);
3110            @parmList = @{$parameterList};
3111        } else {
3112            Trace("GetAll parm list is a scalar: $parameterList.") if T(4);
3113            push @parmList, $parameterList;
3114        }
3115        # Insure the counter has a value.
3116        if (!defined $count) {
3117            $count = 0;
3118        }
3119        # Add the row limit to the filter clause.
3120        if ($count > 0) {
3121            $filterClause .= " LIMIT $count";
3122        }
3123        # Create the query.
3124        my $query = $self->Get($objectNames, $filterClause, \@parmList);
3125        # Set up a counter of the number of records read.
3126        my $fetched = 0;
3127        # Loop through the records returned, extracting the fields. Note that if the
3128        # counter is non-zero, we stop when the number of records read hits the count.
3129        my @retVal = ();
3130        while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {
3131            my @rowData = $row->Values($fields);
3132            push @retVal, \@rowData;
3133            $fetched++;
3134        }
3135        Trace("$fetched rows returned in GetAll.") if T(SQL => 4);
3136        # Return the resulting list.
3137        return @retVal;
3138    }
3139    
3140    =head3 Exists
3141    
3142    C<< my $found = $sprout->Exists($entityName, $entityID); >>
3143    
3144    Return TRUE if an entity exists, else FALSE.
3145    
3146    =over 4
3147    
3148    =item entityName
3149    
3150    Name of the entity type (e.g. C<Feature>) relevant to the existence check.
3151    
3152    =item entityID
3153    
3154    ID of the entity instance whose existence is to be checked.
3155    
3156    =item RETURN
3157    
3158    Returns TRUE if the entity instance exists, else FALSE.
3159    
3160    =back
3161    
3162    =cut
3163    #: Return Type $;
3164    sub Exists {
3165        # Get the parameters.
3166        my ($self, $entityName, $entityID) = @_;
3167        # Check for the entity instance.
3168        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
3169        my $testInstance = $self->GetEntity($entityName, $entityID);
3170        # Return an existence indicator.
3171        my $retVal = ($testInstance ? 1 : 0);
3172        return $retVal;
3173    }
3174    
3175    =head3 EstimateRowSize
3176    
3177    C<< my $rowSize = $erdb->EstimateRowSize($relName); >>
3178    
3179    Estimate the row size of the specified relation. The estimated row size is computed by adding
3180    up the average length for each data type.
3181    
3182    =over 4
3183    
3184    =item relName
3185    
3186    Name of the relation whose estimated row size is desired.
3187    
3188    =item RETURN
3189    
3190    Returns an estimate of the row size for the specified relation.
3191    
3192    =back
3193    
3194    =cut
3195    #: Return Type $;
3196    sub EstimateRowSize {
3197        # Get the parameters.
3198        my ($self, $relName) = @_;
3199        # Declare the return variable.
3200        my $retVal = 0;
3201        # Find the relation descriptor.
3202        my $relation = $self->_FindRelation($relName);
3203        # Get the list of fields.
3204        for my $fieldData (@{$relation->{Fields}}) {
3205            # Get the field type and add its length.
3206            my $fieldLen = $TypeTable{$fieldData->{type}}->{avgLen};
3207            $retVal += $fieldLen;
3208        }
3209        # Return the result.
3210        return $retVal;
3211    }
3212    
3213    =head3 GetFieldTable
3214    
3215    C<< my $fieldHash = $self->GetFieldTable($objectnName); >>
3216    
3217    Get the field structure for a specified entity or relationship.
3218    
3219    =over 4
3220    
3221    =item objectName
3222    
3223    Name of the desired entity or relationship.
3224    
3225    =item RETURN
3226    
3227    The table containing the field descriptors for the specified object.
3228    
3229    =back
3230    
3231    =cut
3232    
3233    sub GetFieldTable {
3234        # Get the parameters.
3235        my ($self, $objectName) = @_;
3236        # Get the descriptor from the metadata.
3237        my $objectData = $self->_GetStructure($objectName);
3238        # Return the object's field table.
3239        return $objectData->{Fields};
3240    }
3241    
3242    =head3 SplitKeywords
3243    
3244    C<< my @keywords = ERDB::SplitKeywords($keywordString); >>
3245    
3246    This method returns a list of the positive keywords in the specified
3247    keyword string. All of the operators will have been stripped off,
3248    and if the keyword is preceded by a minus operator (C<->), it will
3249    not be in the list returned. The idea here is to get a list of the
3250    keywords the user wants to see. The list will be processed to remove
3251    duplicates.
3252    
3253    It is possible to create a string that confuses this method. For example
3254    
3255        frog toad -frog
3256    
3257    would return both C<frog> and C<toad>. If this is a problem we can deal
3258    with it later.
3259    
3260    =over 4
3261    
3262    =item keywordString
3263    
3264    The keyword string to be parsed.
3265    
3266    =item RETURN
3267    
3268    Returns a list of the words in the keyword string the user wants to
3269    see.
3270    
3271    =back
3272    
3273    =cut
3274    
3275    sub SplitKeywords {
3276        # Get the parameters.
3277        my ($keywordString) = @_;
3278        # Make a safety copy of the string. (This helps during debugging.)
3279        my $workString = $keywordString;
3280        # Convert operators we don't care about to spaces.
3281        $workString =~ tr/+"()<>/ /;
3282        # Split the rest of the string along space boundaries. Note that we
3283        # eliminate any words that are zero length or begin with a minus sign.
3284        my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
3285        # Use a hash to remove duplicates.
3286        my %words = map { $_ => 1 } @wordList;
3287        # Return the result.
3288        return sort keys %words;
3289    }
3290    
3291    =head3 ValidateFieldName
3292    
3293    C<< my $okFlag = ERDB::ValidateFieldName($fieldName); >>
3294    
3295    Return TRUE if the specified field name is valid, else FALSE. Valid field names must
3296    be hyphenated words subject to certain restrictions.
3297    
3298    =over 4
3299    
3300    =item fieldName
3301    
3302    Field name to be validated.
3303    
3304    =item RETURN
3305    
3306    Returns TRUE if the field name is valid, else FALSE.
3307    
3308    =back
3309    
3310    =cut
3311    
3312    sub ValidateFieldName {
3313        # Get the parameters.
3314        my ($fieldName) = @_;
3315        # Declare the return variable. The field name is valid until we hear
3316        # differently.
3317        my $retVal = 1;
3318        # Compute the maximum name length.
3319        my $maxLen = $TypeTable{'name-string'}->{maxLen};
3320        # Look for bad stuff in the name.
3321        if ($fieldName =~ /--/) {
3322            # Here we have a doubled minus sign.
3323            Trace("Field name $fieldName has a doubled hyphen.") if T(1);
3324            $retVal = 0;
3325        } elsif ($fieldName !~ /^[A-Za-z]/) {
3326            # Here the field name is missing the initial letter.
3327            Trace("Field name $fieldName does not begin with a letter.") if T(1);
3328            $retVal = 0;
3329        } elsif (length($fieldName) > $maxLen) {
3330            # Here the field name is too long.
3331            Trace("Maximum field name length is $maxLen. Field name must be truncated to " . substr($fieldName,0, $maxLen) . ".");
3332        } else {
3333            # Strip out the minus signs. Everything remaining must be a letter,
3334            # underscore, or digit.
3335            my $strippedName = $fieldName;
3336            $strippedName =~ s/-//g;
3337            if ($strippedName !~ /^(\w|\d)+$/) {
3338                Trace("Field name $fieldName contains illegal characters.") if T(1);
3339                $retVal = 0;
3340            }
3341        }
3342        # Return the result.
3343        return $retVal;
3344    }
3345    
3346    =head3 ReadMetaXML
3347    
3348    C<< my $rawMetaData = ERDB::ReadDBD($fileName); >>
3349    
3350    This method reads a raw database definition XML file and returns it.
3351    Normally, the metadata used by the ERDB system has been processed and
3352    modified to make it easier to load and retrieve the data; however,
3353    this method can be used to get the data in its raw form.
3354    
3355    =over 4
3356    
3357    =item fileName
3358    
3359    Name of the XML file to read.
3360    
3361    =item RETURN
3362    
3363    Returns a hash reference containing the raw XML data from the specified file.
3364    
3365    =back
3366    
3367    =cut
3368    
3369    sub ReadMetaXML {
3370        # Get the parameters.
3371        my ($fileName) = @_;
3372        # Read the XML.
3373        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
3374        Trace("XML metadata loaded from file $fileName.") if T(1);
3375        # Return the result.
3376        return $retVal;
3377    }
3378    
3379    =head3 GetEntityFieldHash
3380    
3381    C<< my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName); >>
3382    
3383    Get the field hash of the named entity in the specified raw XML structure.
3384    The field hash may not exist, in which case we need to create it.
3385    
3386    =over 4
3387    
3388    =item structure
3389    
3390    Raw XML structure defininng the database. This is not the run-time XML used by
3391    an ERDB object, since that has all sorts of optimizations built-in.
3392    
3393    =item entityName
3394    
3395    Name of the entity whose field structure is desired.
3396    
3397    =item RETURN
3398    
3399    Returns the field hash used to define the entity's fields.
3400    
3401    =back
3402    
3403    =cut
3404    
3405    sub GetEntityFieldHash {
3406        # Get the parameters.
3407        my ($structure, $entityName) = @_;
3408        # Get the entity structure.
3409        my $entityData = $structure->{Entities}->{$entityName};
3410        # Look for a field structure.
3411        my $retVal = $entityData->{Fields};
3412        # If it doesn't exist, create it.
3413        if (! defined($retVal)) {
3414            $entityData->{Fields} = {};
3415            $retVal = $entityData->{Fields};
3416        }
3417        # Return the result.
3418        return $retVal;
3419    }
3420    
3421    =head3 WriteMetaXML
3422    
3423    C<< ERDB::WriteMetaXML($structure, $fileName); >>
3424    
3425    Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
3426    used to update the database definition. It must be used with care, however, since it
3427    will only work on a raw structure, not on the processed structure created by an ERDB
3428    constructor.
3429    
3430    =over 4
3431    
3432    =item structure
3433    
3434    XML structure to be written to the file.
3435    
3436    =item fileName
3437    
3438    Name of the output file to which the updated XML should be stored.
3439    
3440    =back
3441    
3442    =cut
3443    
3444    sub WriteMetaXML {
3445        # Get the parameters.
3446        my ($structure, $fileName) = @_;
3447        # Compute the output.
3448        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
3449        # Write it to the file.
3450        my $xmlOut = Open(undef, ">$fileName");
3451        print $xmlOut $fileString;
3452    }
3453    
3454    
3455    =head3 HTMLNote
3456    
3457    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
3458    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
3459    Except for C<[p]>, all the codes are closed by slash-codes. So, for
3460    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
3461    
3462    C<< my $realHtml = ERDB::HTMLNote($dataString); >>
3463    
3464    =over 4
3465    
3466    =item dataString
3467    
3468    String to convert to HTML.
3469    
3470    =item RETURN
3471    
3472    An HTML string derived from the input string.
3473    
3474    =back
3475    
3476    =cut
3477    
3478    sub HTMLNote {
3479        # Get the parameter.
3480        my ($dataString) = @_;
3481        # HTML-escape the text.
3482        my $retVal = CGI::escapeHTML($dataString);
3483        # Substitute the bulletin board codes.
3484        $retVal =~ s!\[(/?[bi])\]!<$1>!g;
3485        $retVal =~ s!\[p\]!</p><p>!g;
3486        $retVal =~ s!\[link\s+([^\]]+)\]!<a href="$1">!g;
3487        $retVal =~ s!\[/link\]!</a>!g;
3488        # Return the result.
3489        return $retVal;
3490    }
3491    
3492    =head3 BeginTran
3493    
3494    C<< $erdb->BeginTran(); >>
3495    
3496    Start a database transaction.
3497    
3498    =cut
3499    
3500    sub BeginTran {
3501        my ($self) = @_;
3502        $self->{_dbh}->begin_tran();
3503    
3504    }
3505    
3506    =head3 CommitTran
3507    
3508    C<< $erdb->CommitTran(); >>
3509    
3510    Commit an active database transaction.
3511    
3512    =cut
3513    
3514    sub CommitTran {
3515        my ($self) = @_;
3516        $self->{_dbh}->commit_tran();
3517    }
3518    
3519    =head3 RollbackTran
3520    
3521    C<< $erdb->RollbackTran(); >>
3522    
3523    Roll back an active database transaction.
3524    
3525    =cut
3526    
3527    sub RollbackTran {
3528        my ($self) = @_;
3529        $self->{_dbh}->roll_tran();
3530    }
3531    
3532    
3533    =head2 Data Mining Methods
3534    
3535    =head3 GetUsefulCrossValues
3536    
3537    C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>
3538    
3539    Return a list of the useful attributes that would be returned by a B<Cross> call
3540    from an entity of the source entity type through the specified relationship. This
3541    means it will return the fields of the target entity type and the intersection data
3542    fields in the relationship. Only primary table fields are returned. In other words,
3543    the field names returned will be for fields where there is always one and only one
3544    value.
3545    
3546    =over 4
3547    
3548    =item sourceEntity
3549    
3550    Name of the entity from which the relationship crossing will start.
3551    
3552    =item relationship
3553    
3554    Name of the relationship being crossed.
3555    
3556    =item RETURN
3557    
3558    Returns a list of field names in Sprout field format (I<objectName>C<(>I<fieldName>C<)>.
3559    
3560    =back
3561    
3562    =cut
3563    #: Return Type @;
3564    sub GetUsefulCrossValues {
3565        # Get the parameters.
3566        my ($self, $sourceEntity, $relationship) = @_;
3567        # Declare the return variable.
3568        my @retVal = ();
3569        # Determine the target entity for the relationship. This is whichever entity is not
3570        # the source entity. So, if the source entity is the FROM, we'll get the name of
3571        # the TO, and vice versa.
3572        my $relStructure = $self->_GetStructure($relationship);
3573        my $targetEntityType = ($relStructure->{from} eq $sourceEntity ? "to" : "from");
3574        my $targetEntity = $relStructure->{$targetEntityType};
3575        # Get the field table for the entity.
3576        my $entityFields = $self->GetFieldTable($targetEntity);
3577        # The field table is a hash. The hash key is the field name. The hash value is a structure.
3578        # For the entity fields, the key aspect of the target structure is that the {relation} value
3579        # must match the entity name.
3580        my @fieldList = map { "$targetEntity($_)" } grep { $entityFields->{$_}->{relation} eq $targetEntity }
3581                            keys %{$entityFields};
3582        # Push the fields found onto the return variable.
3583        push @retVal, sort @fieldList;
3584        # Get the field table for the relationship.
3585        my $relationshipFields = $self->GetFieldTable($relationship);
3586        # Here we have a different rule. We want all the fields other than "from-link" and "to-link".
3587        # This may end up being an empty set.
3588        my @fieldList2 = map { "$relationship($_)" } grep { $_ ne "from-link" && $_ ne "to-link" }
3589                            keys %{$relationshipFields};
3590        # Push these onto the return list.
3591        push @retVal, sort @fieldList2;
3592        # Return the result.
3593        return @retVal;
3594    }
3595    
3596    =head3 FindColumn
3597    
3598    C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>
3599    
3600    Return the location a desired column in a data mining header line. The data
3601    mining header line is a tab-separated list of column names. The column
3602    identifier is either the numerical index of a column or the actual column
3603    name.
3604    
3605    =over 4
3606    
3607    =item headerLine
3608    
3609    The header line from a data mining command, which consists of a tab-separated
3610    list of column names.
3611    
3612    =item columnIdentifier
3613    
3614    Either the ordinal number of the desired column (1-based), or the name of the
3615    desired column.
3616    
3617    =item RETURN
3618    
3619    Returns the array index (0-based) of the desired column.
3620    
3621    =back
3622    
3623    =cut
3624    
3625    sub FindColumn {
3626        # Get the parameters.
3627        my ($headerLine, $columnIdentifier) = @_;
3628        # Declare the return variable.
3629        my $retVal;
3630        # Split the header line into column names.
3631        my @headers = ParseColumns($headerLine);
3632        # Determine whether we have a number or a name.
3633        if ($columnIdentifier =~ /^\d+$/) {
3634            # Here we have a number. Subtract 1 and validate the result.
3635            $retVal = $columnIdentifier - 1;
3636            if ($retVal < 0 || $retVal > $#headers) {
3637                Confess("Invalid column identifer \"$columnIdentifier\": value out of range.");
3638            }
3639        } else {
3640            # Here we have a name. We need to find it in the list.
3641            for (my $i = 0; $i <= $#headers && ! defined($retVal); $i++) {
3642                if ($headers[$i] eq $columnIdentifier) {
3643                    $retVal = $i;
3644                }
3645            }
3646            if (! defined($retVal)) {
3647                Confess("Invalid column identifier \"$columnIdentifier\": value not found.");
3648            }
3649        }
3650        # Return the result.
3651        return $retVal;
3652    }
3653    
3654    =head3 ParseColumns
3655    
3656    C<< my @columns = ERDB::ParseColumns($line); >>
3657    
3658    Convert the specified data line to a list of columns.
3659    
3660    =over 4
3661    
3662    =item line
3663    
3664    A data mining input, consisting of a tab-separated list of columns terminated by a
3665    new-line.
3666    
3667    =item RETURN
3668    
3669    Returns a list consisting of the column values.
3670    
3671    =back
3672    
3673    =cut
3674    
3675    sub ParseColumns {
3676        # Get the parameters.
3677        my ($line) = @_;
3678        # Chop off the line-end.
3679        chomp $line;
3680        # Split it into a list.
3681        my @retVal = split(/\t/, $line);
3682        # Return the result.
3683        return @retVal;
3684    }
3685    
3686    =head2 Virtual Methods
3687    
3688  Name of the file from which the table data should be loaded.  =head3 _CreatePPOIndex
3689    
3690  =item relationName  C<< my $index = ERDB::_CreatePPOIndex($indexObject); >>
3691    
3692  Name of the relation to be loaded. This is the same as the table name.  Convert the XML for an ERDB index to the XML structure for a PPO
3693    index.
3694    
3695  =item truncateFlag  =over 4
3696    
3697  TRUE if the table should be dropped and re-created, else FALSE  ERDB XML structure for an index.
3698    
3699  =item RETURN  =item RETURN
3700    
3701  Returns a statistical object containing the number of records read and a list of the error messages.  PPO XML structure for the same index.
3702    
3703  =back  =back
3704    
3705  =cut  =cut
3706  sub LoadTable {  
3707    sub _CreatePPOIndex {
3708          # Get the parameters.          # Get the parameters.
3709          my ($self, $fileName, $relationName, $truncateFlag) = @_;      my ($indexObject) = @_;
3710          # Create the statistical return object.      # The incoming index contains a list of the index fields in the IndexFields
3711          my $retVal = _GetLoadStats();      # member. We loop through it to create the index tags.
3712          # Trace the fact of the load.      my @fields = map { { label => _FixName($_->{name}) } } @{$indexObject->{IndexFields}};
3713          Trace("Loading table $relationName from $fileName") if T(1);      # Wrap the fields in attribute tags.
3714          # Get the database handle.      my $retVal = { attribute => \@fields };
3715          my $dbh = $self->{_dbh};      # Return the result.
         # Get the relation data.  
         my $relation = $self->_FindRelation($relationName);  
         # Check the truncation flag.  
         if ($truncateFlag) {  
                 Trace("Creating table $relationName") if T(1);  
                 # Re-create the table without its index.  
                 $self->CreateTable($relationName, 0);  
         }  
         # Determine whether or not this is a primary relation. Primary relations have an extra