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

Diff of /Sprout/ERDB.pm

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

revision 1.47, Sun Jun 18 05:14:56 2006 UTC revision 1.78, Tue Nov 28 01:02:42 2006 UTC
# Line 11  Line 11 
11      use Time::HiRes qw(gettimeofday);      use Time::HiRes qw(gettimeofday);
12      use Digest::MD5 qw(md5_base64);      use Digest::MD5 qw(md5_base64);
13      use FIG;      use FIG;
14        use CGI;
15    
16  =head1 Entity-Relationship Database Package  =head1 Entity-Relationship Database Package
17    
# Line 59  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    
 To facilitate testing, the ERDB module supports automatic generation of test data. This process  
 is described in the L</GenerateEntity> and L</GenerateConnection> methods, though it is not yet  
 fully implemented.  
   
76  =head2 XML Database Description  =head2 XML Database Description
77    
78  =head3 Data Types  =head3 Data Types
# Line 91  Line 92 
92    
93  32-bit signed integer  32-bit signed integer
94    
95    =item counter
96    
97    32-bit unsigned integer
98    
99  =item date  =item date
100    
101  64-bit unsigned integer, representing a PERL date/time value  64-bit unsigned integer, representing a PERL date/time value
# Line 186  Line 191 
191    
192  Name of the field. The field name should contain only letters, digits, and hyphens (C<->),  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  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.  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  =item type
199    
# Line 205  Line 212 
212  entity, the fields without a relation attribute are said to belong to the  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.  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  =back
228    
229  =head3 Indexes  =head3 Indexes
230    
231  An entity can have multiple alternate indexes associated with it. The fields must  An entity can have multiple alternate indexes associated with it. The fields must
232  be from the primary relation. The alternate indexes assist in ordering results  all be from the same relation. The alternate indexes assist in ordering results
233  from a query. A relationship can have up to two indexes-- a I<to-index> and a  from a query. A relationship can have up to two indexes-- a I<to-index> and a
234  I<from-index>. These order the results when crossing the relationship. For  I<from-index>. These order the results when crossing the relationship. For
235  example, in the relationship C<HasContig> from C<Genome> to C<Contig>, the  example, in the relationship C<HasContig> from C<Genome> to C<Contig>, the
# Line 238  Line 257 
257    
258  =back  =back
259    
260  The B<Index>, B<FromIndex>, and B<ToIndex> tags themselves have no attributes.  The B<FromIndex>, and B<ToIndex> tags have no attributes. The B<Index> tag can
261    have a B<Unique> attribute. If specified, the index will be generated as a unique
262    index.
263    
264  =head3 Object and Field Names  =head3 Object and Field Names
265    
# Line 316  Line 337 
337    
338  # Table of information about our datatypes. "sqlType" is the corresponding SQL datatype string.  # Table of information about our datatypes. "sqlType" is the corresponding SQL datatype string.
339  # "maxLen" is the maximum permissible length of the incoming string data used to populate a field  # "maxLen" is the maximum permissible length of the incoming string data used to populate a field
340  # of the specified type. "dataGen" is PERL string that will be evaluated if no test data generation  # of the specified type. "avgLen" is the average byte length for estimating
341  # string is specified in the field definition. "avgLen" is the average byte length for estimating  # record sizes. "sort" is the key modifier for the sort command, "notes" is a type description,
342  # record sizes.  # and "indexMod", if non-zero, is the number of characters to use when the field is specified in an
343  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, dataGen => "StringGen('A')" },  # index
344                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, dataGen => "IntGen(0, 99999999)" },  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",
345                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, dataGen => "StringGen(IntGen(10,250))" },                                 indexMod =>   0, notes => "single ASCII character"},
346                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, dataGen => "StringGen(IntGen(80,1000))" },                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n",
347                    date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, dataGen => "DateGen(-7, 7, IntGen(0,1400))" },                                 indexMod =>   0, notes => "signed 32-bit integer"},
348                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, dataGen => "FloatGen(0.0, 100.0)" },                    counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n",
349                    boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, dataGen => "IntGen(0, 1)" },                                 indexMod =>   0, notes => "unsigned 32-bit integer"},
350                      string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, sort => "",
351                                   indexMod =>   0, notes => "character string, 0 to 255 characters"},
352                      text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, sort => "",
353                                   indexMod => 255, notes => "character string, nearly unlimited length, only first 255 characters are indexed"},
354                      date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, sort => "n",
355                                   indexMod =>   0, notes => "signed, 64-bit integer"},
356                      float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, sort => "g",
357                                   indexMod =>   0, notes => "64-bit double precision floating-point number"},
358                      boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, sort => "n",
359                                   indexMod =>   0, notes => "boolean value: 0 if false, 1 if true"},
360                   'hash-string' =>                   'hash-string' =>
361                               { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, dataGen => "SringGen(22)" },                               { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, sort => "",
362                                   indexMod =>   0, notes => "string stored in digested form, used for certain types of key fields"},
363                   'id-string' =>                   'id-string' =>
364                               { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, dataGen => "SringGen(22)" },                               { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, sort => "",
365                                   indexMod =>   0, notes => "character string, 0 to 25 characters"},
366                   'key-string' =>                   'key-string' =>
367                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, dataGen => "StringGen(IntGen(10,40))" },                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, sort => "",
368                                   indexMod =>   0, notes => "character string, 0 to 40 characters"},
369                   'name-string' =>                   'name-string' =>
370                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, dataGen => "StringGen(IntGen(10,80))" },                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, sort => "",
371                                   indexMod =>   0, notes => "character string, 0 to 80 characters"},
372                   'medium-string' =>                   'medium-string' =>
373                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, dataGen => "StringGen(IntGen(10,160))" },                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",
374                                   indexMod =>   0, notes => "character string, 0 to 160 characters"},
375                  );                  );
376    
377  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 344  Line 380 
380                     'MM' => 'many-to-many'                     'MM' => 'many-to-many'
381                   );                   );
382    
383  # Table for interpreting string patterns.  # Options for XML input and output.
384    
385    my %XmlOptions = (GroupTags =>  { Relationships => 'Relationship',
386                                      Entities => 'Entity',
387                                      Fields => 'Field',
388                                      Indexes => 'Index',
389                                      IndexFields => 'IndexField'
390                                    },
391                      KeyAttr =>    { Relationship => 'name',
392                                      Entity => 'name',
393                                      Field => 'name'
394                                    },
395                      SuppressEmpty => 1,
396                     );
397    
398  my %PictureTable = ( 'A' => "abcdefghijklmnopqrstuvwxyz",  my %XmlInOpts  = (
399                       '9' => "0123456789",                    ForceArray => ['Field', 'Index', 'IndexField', 'Relationship', 'Entity'],
400                       'X' => "abcdefghijklmnopqrstuvwxyz0123456789",                    ForceContent => 1,
401                       'V' => "aeiou",                    NormalizeSpace => 2,
402                       'K' => "bcdfghjklmnoprstvwxyz"                   );
403    my %XmlOutOpts = (
404                      RootName => 'Database',
405                      XMLDecl => 1,
406                     );                     );
407    
408    
409  =head2 Public Methods  =head2 Public Methods
410    
411  =head3 new  =head3 new
# Line 493  Line 546 
546          my $entityData = $entityList->{$key};          my $entityData = $entityList->{$key};
547          # If there's descriptive text, display it.          # If there's descriptive text, display it.
548          if (my $notes = $entityData->{Notes}) {          if (my $notes = $entityData->{Notes}) {
549              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
550          }          }
551          # Now we want a list of the entity's relationships. First, we set up the relationship subsection.          # Now we want a list of the entity's relationships. First, we set up the relationship subsection.
552          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
# Line 550  Line 603 
603          $retVal .= "</p>\n";          $retVal .= "</p>\n";
604          # If there are notes on this relationship, display them.          # If there are notes on this relationship, display them.
605          if (my $notes = $relationshipStructure->{Notes}) {          if (my $notes = $relationshipStructure->{Notes}) {
606              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
607          }          }
608          # Generate the relationship's relation table.          # Generate the relationship's relation table.
609          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
# Line 597  Line 650 
650      return Data::Dumper::Dumper($self->{_metaData});      return Data::Dumper::Dumper($self->{_metaData});
651  }  }
652    
653    =head3 FindIndexForEntity
654    
655    C<< my $indexFound = ERDB::FindIndexForEntity($xml, $entityName, $attributeName); >>
656    
657    This method locates the entry in an entity's index list that begins with the
658    specified attribute name. If the entity has no index list, one will be
659    created. This method works on raw XML, not a live ERDB object.
660    
661    =over 4
662    
663    =item xml
664    
665    The raw XML structure defining the database.
666    
667    =item entityName
668    
669    The name of the relevant entity.
670    
671    =item attributeName
672    
673    The name of the attribute relevant to the search.
674    
675    =item RETURN
676    
677    The numerical index in the index list of the index entry for the specified entity and
678    attribute, or C<undef> if no such index exists.
679    
680    =back
681    
682    =cut
683    
684    sub FindIndexForEntity {
685        # Get the parameters.
686        my ($xml, $entityName, $attributeName) = @_;
687        # Declare the return variable.
688        my $retVal;
689        # Get the named entity.
690        my $entityData = $xml->{Entities}->{$entityName};
691        if (! $entityData) {
692            Confess("Entity $entityName not found in DBD structure.");
693        } else {
694            # Insure it has an index list.
695            if (! exists $entityData->{Indexes}) {
696                $entityData->{Indexes} = [];
697            } else {
698                # Search for the desired index.
699                my $indexList = $entityData->{Indexes};
700                my $n = scalar @{$indexList};
701                Trace("Searching $n indexes in index list for $entityName.") if T(2);
702                # We use an indexed FOR here because we're returning an
703                # index number instead of an object. We do THAT so we can
704                # delete the index from the list if needed.
705                for (my $i = 0; $i < $n && !defined($retVal); $i++) {
706                    my $index = $indexList->[$i];
707                    my $fields = $index->{IndexFields};
708                    # Technically this IF should be safe (that is, we are guaranteed
709                    # the existence of a "$fields->[0]"), because when we load the XML
710                    # we have SuppressEmpty specified.
711                    if ($fields->[0]->{name} eq $attributeName) {
712                        $retVal = $i;
713                    }
714                }
715            }
716        }
717        Trace("Index for $attributeName of $entityName found at position $retVal.") if defined($retVal) && T(3);
718        Trace("Index for $attributeName not found in $entityName.") if !defined($retVal) && T(3);
719        # Return the result.
720        return $retVal;
721    }
722    
723  =head3 CreateTables  =head3 CreateTables
724    
725  C<< $erdb->CreateTables(); >>  C<< $erdb->CreateTables(); >>
# Line 684  Line 807 
807      Trace("Creating table $relationName: $fieldThing") if T(2);      Trace("Creating table $relationName: $fieldThing") if T(2);
808      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);
809      Trace("Relation $relationName created in database.") if T(2);      Trace("Relation $relationName created in database.") if T(2);
810      # If we want to build the indexes, we do it here.      # If we want to build the indexes, we do it here. Note that the full-text search
811        # index will not be built until the table has been loaded.
812      if ($indexFlag) {      if ($indexFlag) {
813          $self->CreateIndex($relationName);          $self->CreateIndex($relationName);
814      }      }
# Line 841  Line 965 
965      for my $indexName (keys %{$indexHash}) {      for my $indexName (keys %{$indexHash}) {
966          my $indexData = $indexHash->{$indexName};          my $indexData = $indexHash->{$indexName};
967          # Get the index's field list.          # Get the index's field list.
968          my @fieldList = _FixNames(@{$indexData->{IndexFields}});          my @rawFields = @{$indexData->{IndexFields}};
969            # Get a hash of the relation's field types.
970            my %types = map { $_->{name} => $_->{type} } @{$relationData->{Fields}};
971            # We need to check for text fields so we can append a length limitation for them. To do
972            # that, we need the relation's field list.
973            my $relFields = $relationData->{Fields};
974            for (my $i = 0; $i <= $#rawFields; $i++) {
975                # Get the field type.
976                my $field = $rawFields[$i];
977                my $type = $types{$field};
978                # Ask if it requires using prefix notation for the index.
979                my $mod = $TypeTable{$type}->{indexMod};
980                Trace("Field $field ($i) in $relationName has type $type and indexMod $mod.") if T(3);
981                if ($mod) {
982                    # Append the prefix length to the field name,
983                    $rawFields[$i] .= "($mod)";
984                }
985            }
986            my @fieldList = _FixNames(@rawFields);
987          my $flds = join(', ', @fieldList);          my $flds = join(', ', @fieldList);
988          # Get the index's uniqueness flag.          # Get the index's uniqueness flag.
989          my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');          my $unique = (exists $indexData->{Unique} ? 'unique' : undef);
990          # Create the index.          # Create the index.
991          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
992                                      flds => $flds, unique => $unique);                                      flds => $flds, kind => $unique);
993          if ($rv) {          if ($rv) {
994              Trace("Index created: $indexName for $relationName ($flds)") if T(1);              Trace("Index created: $indexName for $relationName ($flds)") if T(1);
995          } else {          } else {
# Line 856  Line 998 
998      }      }
999  }  }
1000    
1001    =head3 GetSecondaryFields
1002    
1003    C<< my %fieldTuples = $erdb->GetSecondaryFields($entityName); >>
1004    
1005    This method will return a list of the name and type of each of the secondary
1006    fields for a specified entity. Secondary fields are stored in two-column tables
1007    in addition to the primary entity table. This enables the field to have no value
1008    or to have multiple values.
1009    
1010    =over 4
1011    
1012    =item entityName
1013    
1014    Name of the entity whose secondary fields are desired.
1015    
1016    =item RETURN
1017    
1018    Returns a hash mapping the field names to their field types.
1019    
1020    =back
1021    
1022    =cut
1023    
1024    sub GetSecondaryFields {
1025        # Get the parameters.
1026        my ($self, $entityName) = @_;
1027        # Declare the return variable.
1028        my %retVal = ();
1029        # Look for the entity.
1030        my $table = $self->GetFieldTable($entityName);
1031        # Loop through the fields, pulling out the secondaries.
1032        for my $field (sort keys %{$table}) {
1033            if ($table->{$field}->{relation} ne $entityName) {
1034                # Here we have a secondary field.
1035                $retVal{$field} = $table->{$field}->{type};
1036            }
1037        }
1038        # Return the result.
1039        return %retVal;
1040    }
1041    
1042    =head3 GetFieldRelationName
1043    
1044    C<< my $name = $erdb->GetFieldRelationName($objectName, $fieldName); >>
1045    
1046    Return the name of the relation containing a specified field.
1047    
1048    =over 4
1049    
1050    =item objectName
1051    
1052    Name of the entity or relationship containing the field.
1053    
1054    =item fieldName
1055    
1056    Name of the relevant field in that entity or relationship.
1057    
1058    =item RETURN
1059    
1060    Returns the name of the database relation containing the field, or C<undef> if
1061    the field does not exist.
1062    
1063    =back
1064    
1065    =cut
1066    
1067    sub GetFieldRelationName {
1068        # Get the parameters.
1069        my ($self, $objectName, $fieldName) = @_;
1070        # Declare the return variable.
1071        my $retVal;
1072        # Get the object field table.
1073        my $table = $self->GetFieldTable($objectName);
1074        # Only proceed if the field exists.
1075        if (exists $table->{$fieldName}) {
1076            # Determine the name of the relation that contains this field.
1077            $retVal = $table->{$fieldName}->{relation};
1078        }
1079        # Return the result.
1080        return $retVal;
1081    }
1082    
1083    =head3 DeleteValue
1084    
1085    C<< my $numDeleted = $erdb->DeleteValue($entityName, $id, $fieldName, $fieldValue); >>
1086    
1087    Delete secondary field values from the database. This method can be used to delete all
1088    values of a specified field for a particular entity instance, or only a single value.
1089    
1090    Secondary fields are stored in two-column relations separate from an entity's primary
1091    table, and as a result a secondary field can legitimately have no value or multiple
1092    values. Therefore, it makes sense to talk about deleting secondary fields where it
1093    would not make sense for primary fields.
1094    
1095    =over 4
1096    
1097    =item entityName
1098    
1099    Name of the entity from which the fields are to be deleted.
1100    
1101    =item id
1102    
1103    ID of the entity instance to be processed. If the instance is not found, this
1104    method will have no effect. If C<undef> is specified, all values for all of
1105    the entity instances will be deleted.
1106    
1107    =item fieldName
1108    
1109    Name of the field whose values are to be deleted.
1110    
1111    =item fieldValue (optional)
1112    
1113    Value to be deleted. If not specified, then all values of the specified field
1114    will be deleted for the entity instance. If specified, then only the values which
1115    match this parameter will be deleted.
1116    
1117    =item RETURN
1118    
1119    Returns the number of rows deleted.
1120    
1121    =back
1122    
1123    =cut
1124    
1125    sub DeleteValue {
1126        # Get the parameters.
1127        my ($self, $entityName, $id, $fieldName, $fieldValue) = @_;
1128        # Declare the return value.
1129        my $retVal = 0;
1130        # We need to set up an SQL command to do the deletion. First, we
1131        # find the name of the field's relation.
1132        my $table = $self->GetFieldTable($entityName);
1133        my $field = $table->{$fieldName};
1134        my $relation = $field->{relation};
1135        # Make sure this is a secondary field.
1136        if ($relation eq $entityName) {
1137            Confess("Cannot delete values of $fieldName for $entityName.");
1138        } else {
1139            # Set up the SQL command to delete all values.
1140            my $sql = "DELETE FROM $relation";
1141            # Build the filter.
1142            my @filters = ();
1143            my @parms = ();
1144            # Check for a filter by ID.
1145            if (defined $id) {
1146                push @filters, "id = ?";
1147                push @parms, $id;
1148            }
1149            # Check for a filter by value.
1150            if (defined $fieldValue) {
1151                push @filters, "$fieldName = ?";
1152                push @parms, $fieldValue;
1153            }
1154            # Append the filters to the command.
1155            if (@filters) {
1156                $sql .= " WHERE " . join(" AND ", @filters);
1157            }
1158            # Execute the command.
1159            my $dbh = $self->{_dbh};
1160            $retVal = $dbh->SQL($sql, 0, @parms);
1161        }
1162        # Return the result.
1163        return $retVal;
1164    }
1165    
1166  =head3 LoadTables  =head3 LoadTables
1167    
1168  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>
# Line 950  Line 1257 
1257      return sort keys %{$entityList};      return sort keys %{$entityList};
1258  }  }
1259    
1260    =head3 GetDataTypes
1261    
1262    C<< my %types = ERDB::GetDataTypes(); >>
1263    
1264    Return a table of ERDB data types. The table returned is a hash of hashes.
1265    The keys of the big hash are the datatypes. Each smaller hash has several
1266    values used to manage the data. The most interesting is the SQL type (key
1267    C<sqlType>) and the descriptive node (key C<notes>).
1268    
1269    Note that changing the values in the smaller hashes will seriously break
1270    things, so this data should be treated as read-only.
1271    
1272    =cut
1273    
1274    sub GetDataTypes {
1275        return %TypeTable;
1276    }
1277    
1278    
1279  =head3 IsEntity  =head3 IsEntity
1280    
1281  C<< my $flag = $erdb->IsEntity($entityName); >>  C<< my $flag = $erdb->IsEntity($entityName); >>
# Line 1094  Line 1420 
1420      return $retVal;      return $retVal;
1421  }  }
1422    
1423    
1424    
1425    =head3 Search
1426    
1427    C<< my $query = $erdb->Search($searchExpression, $idx, \@objectNames, $filterClause, \@params); >>
1428    
1429    Perform a full text search with filtering. The search will be against a specified object
1430    in the object name list. That object will get an extra field containing the search
1431    relevance. Note that except for the search expression, the parameters of this method are
1432    the same as those for L</Get> and follow the same rules.
1433    
1434    =over 4
1435    
1436    =item searchExpression
1437    
1438    Boolean search expression for the text fields of the target object. The default mode for
1439    a Boolean search expression is OR, but we want the default to be AND, so we will
1440    add a C<+> operator to each word with no other operator before it.
1441    
1442    =item idx
1443    
1444    Index in the I<$objectNames> list of the table to be searched in full-text mode.
1445    
1446    =item objectNames
1447    
1448    List containing the names of the entity and relationship objects to be retrieved.
1449    
1450    =item filterClause
1451    
1452    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1453    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
1454    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
1455    in the filter clause should be added to the parameter list as additional parameters. The
1456    fields in a filter clause can come from primary entity relations, relationship relations,
1457    or secondary entity relations; however, all of the entities and relationships involved must
1458    be included in the list of object names.
1459    
1460    =item params
1461    
1462    Reference to a list of parameter values to be substituted into the filter clause.
1463    
1464    =item RETURN
1465    
1466    Returns a query object for the specified search.
1467    
1468    =back
1469    
1470    =cut
1471    
1472    sub Search {
1473        # Get the parameters.
1474        my ($self, $searchExpression, $idx, $objectNames, $filterClause, $params) = @_;
1475        # Declare the return variable.
1476        my $retVal;
1477        # Create a safety copy of the parameter list. Note we have to be careful to insure
1478        # a parameter list exists before we copy it.
1479        my @myParams = ();
1480        if (defined $params) {
1481            @myParams = @{$params};
1482        }
1483        # Get the first object's structure so we have access to the searchable fields.
1484        my $object1Name = $objectNames->[$idx];
1485        my $object1Structure = $self->_GetStructure($object1Name);
1486        # Get the field list.
1487        if (! exists $object1Structure->{searchFields}) {
1488            Confess("No searchable index for $object1Name.");
1489        } else {
1490            # Get the field list.
1491            my @fields = @{$object1Structure->{searchFields}};
1492            # Clean the search expression.
1493            my $actualKeywords = $self->CleanKeywords($searchExpression);
1494            # Prefix a "+" to each uncontrolled word. This converts the default
1495            # search mode from OR to AND.
1496            $actualKeywords =~ s/(^|\s)(\w)/$1\+$2/g;
1497            Trace("Actual keywords for search are\n$actualKeywords") if T(3);
1498            # We need two match expressions, one for the filter clause and one in the
1499            # query itself. Both will use a parameter mark, so we need to push the
1500            # search expression onto the front of the parameter list twice.
1501            unshift @myParams, $actualKeywords, $actualKeywords;
1502            # Build the match expression.
1503            my @matchFilterFields = map { "$object1Name." . _FixName($_) } @fields;
1504            my $matchClause = "MATCH (" . join(", ", @matchFilterFields) . ") AGAINST (? IN BOOLEAN MODE)";
1505            # Process the SQL stuff.
1506            my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1507                $self->_SetupSQL($objectNames, $filterClause, $matchClause);
1508            # Create the query. Note that the match clause is inserted at the front of
1509            # the select fields.
1510            my $command = "SELECT DISTINCT $matchClause, " . join(".*, ", @{$mappedNameListRef}) .
1511                ".* $suffix";
1512            my $sth = $self->_GetStatementHandle($command, \@myParams);
1513            # Now we create the relation map, which enables DBQuery to determine the order, name
1514            # and mapped name for each object in the query.
1515            my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef);
1516            # Return the statement object.
1517            $retVal = DBQuery::_new($self, $sth, \@relationMap, $object1Name);
1518        }
1519        return $retVal;
1520    }
1521    
1522  =head3 GetFlat  =head3 GetFlat
1523    
1524  C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>  C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>
# Line 1147  Line 1572 
1572      return @retVal;      return @retVal;
1573  }  }
1574    
1575    =head3 SpecialFields
1576    
1577    C<< my %specials = $erdb->SpecialFields($entityName); >>
1578    
1579    Return a hash mapping special fields in the specified entity to the value of their
1580    C<special> attribute. This enables the subclass to get access to the special field
1581    attributes without needed to plumb the internal ERDB data structures.
1582    
1583    =over 4
1584    
1585    =item entityName
1586    
1587    Name of the entity whose special fields are desired.
1588    
1589    =item RETURN
1590    
1591    Returns a hash. The keys of the hash are the special field names, and the values
1592    are the values from each special field's C<special> attribute.
1593    
1594    =back
1595    
1596    =cut
1597    
1598    sub SpecialFields {
1599        # Get the parameters.
1600        my ($self, $entityName) = @_;
1601        # Declare the return variable.
1602        my %retVal = ();
1603        # Find the entity's data structure.
1604        my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1605        # Loop through its fields, adding each special field to the return hash.
1606        my $fieldHash = $entityData->{Fields};
1607        for my $fieldName (keys %{$fieldHash}) {
1608            my $fieldData = $fieldHash->{$fieldName};
1609            if (exists $fieldData->{special}) {
1610                $retVal{$fieldName} = $fieldData->{special};
1611            }
1612        }
1613        # Return the result.
1614        return %retVal;
1615    }
1616    
1617  =head3 Delete  =head3 Delete
1618    
1619  C<< my $stats = $erdb->Delete($entityName, $objectID); >>  C<< my $stats = $erdb->Delete($entityName, $objectID, %options); >>
1620    
1621  Delete an entity instance from the database. The instance is deleted along with all entity and  Delete an entity instance from the database. The instance is deleted along with all entity and
1622  relationship instances dependent on it. The idea of dependence here is recursive. An object is  relationship instances dependent on it. The definition of I<dependence> is recursive.
1623  always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many  
1624  relationship connected to a dependent entity or the "to" entity connected to a 1-to-many  An object is always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many
1625    relationship connected to a dependent entity or if it is the "to" entity connected to a 1-to-many
1626  dependent relationship.  dependent relationship.
1627    
1628  =over 4  =over 4
# Line 1168  Line 1636 
1636  ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),  ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),
1637  then it is presumed to by a LIKE pattern.  then it is presumed to by a LIKE pattern.
1638    
1639  =item testFlag  =item options
1640    
1641  If TRUE, the delete statements will be traced without being executed.  A hash detailing the options for this delete operation.
1642    
1643  =item RETURN  =item RETURN
1644    
# Line 1179  Line 1647 
1647    
1648  =back  =back
1649    
1650    The permissible options for this method are as follows.
1651    
1652    =over 4
1653    
1654    =item testMode
1655    
1656    If TRUE, then the delete statements will be traced, but no changes will be made to the database.
1657    
1658    =item keepRoot
1659    
1660    If TRUE, then the entity instances will not be deleted, only the dependent records.
1661    
1662    =back
1663    
1664  =cut  =cut
1665  #: Return Type $%;  #: Return Type $%;
1666  sub Delete {  sub Delete {
1667      # Get the parameters.      # Get the parameters.
1668      my ($self, $entityName, $objectID, $testFlag) = @_;      my ($self, $entityName, $objectID, %options) = @_;
1669      # Declare the return variable.      # Declare the return variable.
1670      my $retVal = Stats->new();      my $retVal = Stats->new();
1671      # Get the DBKernel object.      # Get the DBKernel object.
# Line 1200  Line 1682 
1682      # FROM-relationships and entities.      # FROM-relationships and entities.
1683      my @fromPathList = ();      my @fromPathList = ();
1684      my @toPathList = ();      my @toPathList = ();
1685      # This final hash is used to remember what work still needs to be done. We push paths      # This final list is used to remember what work still needs to be done. We push paths
1686      # onto the list, then pop them off to extend the paths. We prime it with the starting      # onto the list, then pop them off to extend the paths. We prime it with the starting
1687      # point. Note that we will work hard to insure that the last item on a path in the      # point. Note that we will work hard to insure that the last item on a path in the
1688      # TODO list is always an entity.      # to-do list is always an entity.
1689      my @todoList = ([$entityName]);      my @todoList = ([$entityName]);
1690      while (@todoList) {      while (@todoList) {
1691          # Get the current path.          # Get the current path.
# Line 1211  Line 1693 
1693          # Copy it into a list.          # Copy it into a list.
1694          my @stackedPath = @{$current};          my @stackedPath = @{$current};
1695          # Pull off the last item on the path. It will always be an entity.          # Pull off the last item on the path. It will always be an entity.
1696          my $entityName = pop @stackedPath;          my $myEntityName = pop @stackedPath;
1697          # Add it to the alreadyFound list.          # Add it to the alreadyFound list.
1698          $alreadyFound{$entityName} = 1;          $alreadyFound{$myEntityName} = 1;
1699            # Figure out if we need to delete this entity.
1700            if ($myEntityName ne $entityName || ! $options{keepRoot}) {
1701          # Get the entity data.          # Get the entity data.
1702          my $entityData = $self->_GetStructure($entityName);              my $entityData = $self->_GetStructure($myEntityName);
1703          # The first task is to loop through the entity's relation. A DELETE command will              # Loop through the entity's relations. A DELETE command will be needed for each of them.
         # be needed for each of them.  
1704          my $relations = $entityData->{Relations};          my $relations = $entityData->{Relations};
1705          for my $relation (keys %{$relations}) {          for my $relation (keys %{$relations}) {
1706              my @augmentedList = (@stackedPath, $relation);              my @augmentedList = (@stackedPath, $relation);
1707              push @fromPathList, \@augmentedList;              push @fromPathList, \@augmentedList;
1708          }          }
1709            }
1710          # Now we need to look for relationships connected to this entity.          # Now we need to look for relationships connected to this entity.
1711          my $relationshipList = $self->{_metaData}->{Relationships};          my $relationshipList = $self->{_metaData}->{Relationships};
1712          for my $relationshipName (keys %{$relationshipList}) {          for my $relationshipName (keys %{$relationshipList}) {
1713              my $relationship = $relationshipList->{$relationshipName};              my $relationship = $relationshipList->{$relationshipName};
1714              # Check the FROM field. We're only interested if it's us.              # Check the FROM field. We're only interested if it's us.
1715              if ($relationship->{from} eq $entityName) {              if ($relationship->{from} eq $myEntityName) {
1716                  # Add the path to this relationship.                  # Add the path to this relationship.
1717                  my @augmentedList = (@stackedPath, $entityName, $relationshipName);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1718                  push @fromPathList, \@augmentedList;                  push @fromPathList, \@augmentedList;
1719                  # Check the arity. If it's MM we're done. If it's 1M                  # Check the arity. If it's MM we're done. If it's 1M
1720                  # and the target hasn't been seen yet, we want to                  # and the target hasn't been seen yet, we want to
# Line 1249  Line 1733 
1733              }              }
1734              # Now check the TO field. In this case only the relationship needs              # Now check the TO field. In this case only the relationship needs
1735              # deletion.              # deletion.
1736              if ($relationship->{to} eq $entityName) {              if ($relationship->{to} eq $myEntityName) {
1737                  my @augmentedList = (@stackedPath, $entityName, $relationshipName);                  my @augmentedList = (@stackedPath, $myEntityName, $relationshipName);
1738                  push @toPathList, \@augmentedList;                  push @toPathList, \@augmentedList;
1739              }              }
1740          }          }
1741      }      }
1742      # Create the first qualifier for the WHERE clause. This selects the      # Create the first qualifier for the WHERE clause. This selects the
1743      # keys of the primary entity records to be deleted. When we're deleting      # keys of the primary entity records to be deleted. When we're deleting
1744      # from a dependent table, we construct a join page from the first qualifier      # from a dependent table, we construct a join path from the first qualifier
1745      # to the table containing the dependent records to delete.      # to the table containing the dependent records to delete.
1746      my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");      my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
1747      # We need to make two passes. The first is through the to-list, and      # We need to make two passes. The first is through the to-list, and
# Line 1296  Line 1780 
1780                  }                  }
1781              }              }
1782              # Now we have our desired DELETE statement.              # Now we have our desired DELETE statement.
1783              if ($testFlag) {              if ($options{testMode}) {
1784                  # Here the user wants to trace without executing.                  # Here the user wants to trace without executing.
1785                  Trace($stmt) if T(0);                  Trace($stmt) if T(0);
1786              } else {              } else {
1787                  # Here we can delete. Note that the SQL method dies with a confessing                  # Here we can delete. Note that the SQL method dies with a confession
1788                  # if an error occurs, so we just go ahead and do it.                  # if an error occurs, so we just go ahead and do it.
1789                  Trace("Executing delete from $target using '$objectID'.") if T(3);                  Trace("Executing delete from $target using '$objectID'.") if T(3);
1790                  my $rv = $db->SQL($stmt, 0, $objectID);                  my $rv = $db->SQL($stmt, 0, $objectID);
# Line 1315  Line 1799 
1799      return $retVal;      return $retVal;
1800  }  }
1801    
1802  =head3 GetList  =head3 Disconnect
   
 C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>  
1803    
1804  Return a list of object descriptors for the specified objects as determined by the  C<< $erdb->Disconnect($relationshipName, $originEntityName, $originEntityID); >>
 specified filter clause.  
1805    
1806  This method is essentially the same as L</Get> except it returns a list of objects rather  Disconnect an entity instance from all the objects to which it is related. This
1807  than a query object that can be used to get the results one record at a time.  will delete each relationship instance that connects to the specified entity.
1808    
1809  =over 4  =over 4
1810    
1811  =item objectNames  =item relationshipName
1812    
1813  List containing the names of the entity and relationship objects to be retrieved.  Name of the relationship whose instances are to be deleted.
1814    
1815  =item filterClause  =item originEntityName
1816    
1817  WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  Name of the entity that is to be disconnected.
 be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be  
 specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified  
 in the filter clause should be added to the parameter list as additional parameters. The  
 fields in a filter clause can come from primary entity relations, relationship relations,  
 or secondary entity relations; however, all of the entities and relationships involved must  
 be included in the list of object names.  
1818    
1819  The filter clause can also specify a sort order. To do this, simply follow the filter string  =item originEntityID
 with an ORDER BY clause. For example, the following filter string gets all genomes for a  
 particular genus and sorts them by species name.  
1820    
1821  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>  ID of the entity that is to be disconnected.
1822    
1823  The rules for field references in a sort order are the same as those for field references in the  =back
 filter clause in general; however, odd things may happen if a sort field is from a secondary  
 relation.  
1824    
1825  =item params  =cut
1826    
1827    sub Disconnect {
1828        # Get the parameters.
1829        my ($self, $relationshipName, $originEntityName, $originEntityID) = @_;
1830        # Get the relationship descriptor.
1831        my $structure = $self->_GetStructure($relationshipName);
1832        # Insure we have a relationship.
1833        if (! exists $structure->{from}) {
1834            Confess("$relationshipName is not a relationship in the database.");
1835        } else {
1836            # Get the database handle.
1837            my $dbh = $self->{_dbh};
1838            # We'll set this value to 1 if we find our entity.
1839            my $found = 0;
1840            # Loop through the ends of the relationship.
1841            for my $dir ('from', 'to') {
1842                if ($structure->{$dir} eq $originEntityName) {
1843                    # Delete all relationship instances on this side of the entity instance.
1844                    $dbh->SQL("DELETE FROM $relationshipName WHERE ${dir}_link = ?", 0, $originEntityID);
1845                    $found = 1;
1846                }
1847            }
1848            # Insure we found the entity on at least one end.
1849            if (! $found) {
1850                Confess("Entity \"$originEntityName\" does not use $relationshipName.");
1851            }
1852        }
1853    }
1854    
1855    =head3 SortNeeded
1856    
1857    C<< my $parms = $erdb->SortNeeded($relationName); >>
1858    
1859    Return the pipe command for the sort that should be applied to the specified
1860    relation when creating the load file.
1861    
1862    For example, if the load file should be sorted ascending by the first
1863    field, this method would return
1864    
1865        sort -k1 -t"\t"
1866    
1867    If the first field is numeric, the method would return
1868    
1869        sort -k1n -t"\t"
1870    
1871    Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate
1872    keys using a sort.
1873    
1874    =over 4
1875    
1876    =item relationName
1877    
1878    Name of the relation to be examined.
1879    
1880    =item
1881    
1882    Returns the sort command to use for sorting the relation, suitable for piping.
1883    
1884    =back
1885    
1886    =cut
1887    #: Return Type $;
1888    sub SortNeeded {
1889        # Get the parameters.
1890        my ($self, $relationName) = @_;
1891        # Declare a descriptor to hold the names of the key fields.
1892        my @keyNames = ();
1893        # Get the relation structure.
1894        my $relationData = $self->_FindRelation($relationName);
1895        # Find out if the relation is a primary entity relation,
1896        # a relationship relation, or a secondary entity relation.
1897        my $entityTable = $self->{_metaData}->{Entities};
1898        my $relationshipTable = $self->{_metaData}->{Relationships};
1899        if (exists $entityTable->{$relationName}) {
1900            # Here we have a primary entity relation.
1901            push @keyNames, "id";
1902        } elsif (exists $relationshipTable->{$relationName}) {
1903            # Here we have a relationship. We sort using the FROM index.
1904            my $relationshipData = $relationshipTable->{$relationName};
1905            my $index = $relationData->{Indexes}->{idxFrom};
1906            push @keyNames, @{$index->{IndexFields}};
1907        } else {
1908            # Here we have a secondary entity relation, so we have a sort on the ID field.
1909            push @keyNames, "id";
1910        }
1911        # Now we parse the key names into sort parameters. First, we prime the return
1912        # string.
1913        my $retVal = "sort -t\"\t\" ";
1914        # Get the relation's field list.
1915        my @fields = @{$relationData->{Fields}};
1916        # Loop through the keys.
1917        for my $keyData (@keyNames) {
1918            # Get the key and the ordering.
1919            my ($keyName, $ordering);
1920            if ($keyData =~ /^([^ ]+) DESC/) {
1921                ($keyName, $ordering) = ($1, "descending");
1922            } else {
1923                ($keyName, $ordering) = ($keyData, "ascending");
1924            }
1925            # Find the key's position and type.
1926            my $fieldSpec;
1927            for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {
1928                my $thisField = $fields[$i];
1929                if ($thisField->{name} eq $keyName) {
1930                    # Get the sort modifier for this field type. The modifier
1931                    # decides whether we're using a character, numeric, or
1932                    # floating-point sort.
1933                    my $modifier = $TypeTable{$thisField->{type}}->{sort};
1934                    # If the index is descending for this field, denote we want
1935                    # to reverse the sort order on this field.
1936                    if ($ordering eq 'descending') {
1937                        $modifier .= "r";
1938                    }
1939                    # Store the position and modifier into the field spec, which
1940                    # will stop the inner loop. Note that the field number is
1941                    # 1-based in the sort command, so we have to increment the
1942                    # index.
1943                    $fieldSpec = ($i + 1) . $modifier;
1944                }
1945            }
1946            # Add this field to the sort command.
1947            $retVal .= " -k$fieldSpec";
1948        }
1949        # Return the result.
1950        return $retVal;
1951    }
1952    
1953    =head3 GetList
1954    
1955    C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>
1956    
1957    Return a list of object descriptors for the specified objects as determined by the
1958    specified filter clause.
1959    
1960    This method is essentially the same as L</Get> except it returns a list of objects rather
1961    than a query object that can be used to get the results one record at a time.
1962    
1963    =over 4
1964    
1965    =item objectNames
1966    
1967    List containing the names of the entity and relationship objects to be retrieved.
1968    
1969    =item filterClause
1970    
1971    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1972    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
1973    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
1974    in the filter clause should be added to the parameter list as additional parameters. The
1975    fields in a filter clause can come from primary entity relations, relationship relations,
1976    or secondary entity relations; however, all of the entities and relationships involved must
1977    be included in the list of object names.
1978    
1979    The filter clause can also specify a sort order. To do this, simply follow the filter string
1980    with an ORDER BY clause. For example, the following filter string gets all genomes for a
1981    particular genus and sorts them by species name.
1982    
1983    C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
1984    
1985    The rules for field references in a sort order are the same as those for field references in the
1986    filter clause in general; however, odd things may happen if a sort field is from a secondary
1987    relation.
1988    
1989    =item params
1990    
1991  Reference to a list of parameter values to be substituted into the filter clause.  Reference to a list of parameter values to be substituted into the filter clause.
1992    
# Line 1431  Line 2066 
2066  sub GetCount {  sub GetCount {
2067      # Get the parameters.      # Get the parameters.
2068      my ($self, $objectNames, $filter, $params) = @_;      my ($self, $objectNames, $filter, $params) = @_;
2069        # Insure the params argument is an array reference if the caller left it off.
2070        if (! defined($params)) {
2071            $params = [];
2072        }
2073      # Declare the return variable.      # Declare the return variable.
2074      my $retVal;      my $retVal;
2075      # Find out if we're counting an entity or a relationship.      # Find out if we're counting an entity or a relationship.
# Line 1544  Line 2183 
2183      }      }
2184  }  }
2185    
2186    =head3 InsertValue
2187    
2188    C<< $erdb->InsertValue($entityID, $fieldName, $value); >>
2189    
2190    This method will insert a new value into the database. The value must be one
2191    associated with a secondary relation, since primary values cannot be inserted:
2192    they occur exactly once. Secondary values, on the other hand, can be missing
2193    or multiply-occurring.
2194    
2195    =over 4
2196    
2197    =item entityID
2198    
2199    ID of the object that is to receive the new value.
2200    
2201    =item fieldName
2202    
2203    Field name for the new value-- this includes the entity name, since
2204    field names are of the format I<objectName>C<(>I<fieldName>C<)>.
2205    
2206    =item value
2207    
2208    New value to be put in the field.
2209    
2210    =back
2211    
2212    =cut
2213    
2214    sub InsertValue {
2215        # Get the parameters.
2216        my ($self, $entityID, $fieldName, $value) = @_;
2217        # Parse the entity name and the real field name.
2218        if ($fieldName =~ /^([^(]+)\(([^)]+)\)/) {
2219            my $entityName = $1;
2220            my $fieldTitle = $2;
2221            # Get its descriptor.
2222            if (!$self->IsEntity($entityName)) {
2223                Confess("$entityName is not a valid entity.");
2224            } else {
2225                my $entityData = $self->{_metaData}->{Entities}->{$entityName};
2226                # Find the relation containing this field.
2227                my $fieldHash = $entityData->{Fields};
2228                if (! exists $fieldHash->{$fieldTitle}) {
2229                    Confess("$fieldTitle not found in $entityName.");
2230                } else {
2231                    my $relation = $fieldHash->{$fieldTitle}->{relation};
2232                    if ($relation eq $entityName) {
2233                        Confess("Cannot do InsertValue on primary field $fieldTitle of $entityName.");
2234                    } else {
2235                        # Now we can create an INSERT statement.
2236                        my $dbh = $self->{_dbh};
2237                        my $fixedName = _FixName($fieldTitle);
2238                        my $statement = "INSERT INTO $relation (id, $fixedName) VALUES(?, ?)";
2239                        # Execute the command.
2240                        $dbh->SQL($statement, 0, $entityID, $value);
2241                    }
2242                }
2243            }
2244        } else {
2245            Confess("$fieldName is not a valid field name.");
2246        }
2247    }
2248    
2249  =head3 InsertObject  =head3 InsertObject
2250    
2251  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>  C<< $erdb->InsertObject($objectType, \%fieldHash); >>
2252    
2253  Insert an object into the database. The object is defined by a type name and then a hash  Insert an object into the database. The object is defined by a type name and then a hash
2254  of field names to values. Field values in the primary relation are represented by scalars.  of field names to values. Field values in the primary relation are represented by scalars.
# Line 1560  Line 2262 
2262  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
2263  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
2264    
2265  C<< $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>  C<< $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>
2266    
2267  =over 4  =over 4
2268    
# Line 1572  Line 2274 
2274    
2275  Hash of field names to values.  Hash of field names to values.
2276    
 =item RETURN  
   
 Returns 1 if successful, 0 if an error occurred.  
   
2277  =back  =back
2278    
2279  =cut  =cut
# Line 1674  Line 2372 
2372                  $retVal = $sth->execute(@parameterList);                  $retVal = $sth->execute(@parameterList);
2373                  if (!$retVal) {                  if (!$retVal) {
2374                      my $errorString = $sth->errstr();                      my $errorString = $sth->errstr();
2375                      Trace("Insert error: $errorString.") if T(0);                      Confess("Error inserting into $relationName: $errorString");
2376                  }                  }
2377              }              }
2378          }          }
2379      }      }
2380      # Return the success indicator.      # Return a 1 for backward compatability.
2381      return $retVal;      return 1;
2382    }
2383    
2384    =head3 UpdateEntity
2385    
2386    C<< $erdb->UpdateEntity($entityName, $id, \%fields); >>
2387    
2388    Update the values of an entity. This is an unprotected update, so it should only be
2389    done if the database resides on a database server.
2390    
2391    =over 4
2392    
2393    =item entityName
2394    
2395    Name of the entity to update. (This is the entity type.)
2396    
2397    =item id
2398    
2399    ID of the entity to update. If no entity exists with this ID, an error will be thrown.
2400    
2401    =item fields
2402    
2403    Reference to a hash mapping field names to their new values. All of the fields named
2404    must be in the entity's primary relation, and they cannot any of them be the ID field.
2405    
2406    =back
2407    
2408    =cut
2409    
2410    sub UpdateEntity {
2411        # Get the parameters.
2412        my ($self, $entityName, $id, $fields) = @_;
2413        # Get a list of the field names being updated.
2414        my @fieldList = keys %{$fields};
2415        # Verify that the fields exist.
2416        my $checker = $self->GetFieldTable($entityName);
2417        for my $field (@fieldList) {
2418            if ($field eq 'id') {
2419                Confess("Cannot update the ID field for entity $entityName.");
2420            } elsif ($checker->{$field}->{relation} ne $entityName) {
2421                Confess("Cannot find $field in primary relation of $entityName.");
2422            }
2423        }
2424        # Build the SQL statement.
2425        my @sets = ();
2426        my @valueList = ();
2427        for my $field (@fieldList) {
2428            push @sets, _FixName($field) . " = ?";
2429            push @valueList, $fields->{$field};
2430        }
2431        my $command = "UPDATE $entityName SET " . join(", ", @sets) . " WHERE id = ?";
2432        # Add the ID to the list of binding values.
2433        push @valueList, $id;
2434        # Call SQL to do the work.
2435        my $rows = $self->{_dbh}->SQL($command, 0, @valueList);
2436        # Check for errors.
2437        if ($rows == 0) {
2438            Confess("Entity $id of type $entityName not found.");
2439        }
2440  }  }
2441    
2442  =head3 LoadTable  =head3 LoadTable
2443    
2444  C<< my %results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>  C<< my $results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>
2445    
2446  Load data from a tab-delimited file into a specified table, optionally re-creating the table  Load data from a tab-delimited file into a specified table, optionally re-creating the table
2447  first.  first.
# Line 1752  Line 2508 
2508      };      };
2509      if (!defined $rv) {      if (!defined $rv) {
2510          $retVal->AddMessage($@) if ($@);          $retVal->AddMessage($@) if ($@);
2511          $retVal->AddMessage("Table load failed for $relationName using $fileName.");          $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2512          Trace("Table load failed for $relationName.") if T(1);          Trace("Table load failed for $relationName.") if T(1);
2513      } else {      } else {
2514          # Here we successfully loaded the table.          # Here we successfully loaded the table.
# Line 1760  Line 2516 
2516          my $size = -s $fileName;          my $size = -s $fileName;
2517          Trace("$size bytes loaded into $relationName.") if T(2);          Trace("$size bytes loaded into $relationName.") if T(2);
2518          # If we're rebuilding, we need to create the table indexes.          # If we're rebuilding, we need to create the table indexes.
2519          if ($truncateFlag && ! $dbh->{_preIndex}) {          if ($truncateFlag) {
2520                # Indexes are created here for PostGres. For PostGres, indexes are
2521                # best built at the end. For MySQL, the reverse is true.
2522                if (! $dbh->{_preIndex}) {
2523              eval {              eval {
2524                  $self->CreateIndex($relationName);                  $self->CreateIndex($relationName);
2525              };              };
# Line 1768  Line 2527 
2527                  $retVal->AddMessage($@);                  $retVal->AddMessage($@);
2528              }              }
2529          }          }
2530                # The full-text index (if any) is always built last, even for MySQL.
2531                # First we need to see if this table has a full-text index. Only
2532                # primary relations are allowed that privilege.
2533                if ($self->_IsPrimary($relationName)) {
2534                    # Get the relation's entity/relationship structure.
2535                    my $structure = $self->_GetStructure($relationName);
2536                    # Check for a searchable fields list.
2537                    if (exists $structure->{searchFields}) {
2538                        # Here we know that we need to create a full-text search index.
2539                        # Get an SQL-formatted field name list.
2540                        my $fields = join(", ", $self->_FixNames(@{$structure->{searchFields}}));
2541                        # Create the index.
2542                        $dbh->create_index(tbl => $relationName, idx => "search_idx",
2543                                           flds => $fields, kind => 'fulltext');
2544                    }
2545                }
2546            }
2547      }      }
2548      # Analyze the table to improve performance.      # Analyze the table to improve performance.
2549        Trace("Analyzing and compacting $relationName.") if T(3);
2550      $dbh->vacuum_it($relationName);      $dbh->vacuum_it($relationName);
2551        Trace("$relationName load completed.") if T(3);
2552      # Return the statistics.      # Return the statistics.
2553      return $retVal;      return $retVal;
2554  }  }
2555    
2556  =head3 GenerateEntity  =head3 DropRelation
2557    
2558  C<< my $fieldHash = $erdb->GenerateEntity($id, $type, \%values); >>  C<< $erdb->DropRelation($relationName); >>
2559    
2560  Generate the data for a new entity instance. This method creates a field hash suitable for  Physically drop a relation from the database.
 passing as a parameter to L</InsertObject>. The ID is specified by the callr, but the rest  
 of the fields are generated using information in the database schema.  
   
 Each data type has a default algorithm for generating random test data. This can be overridden  
 by including a B<DataGen> element in the field. If this happens, the content of the element is  
 executed as a PERL program in the context of this module. The element may make use of a C<$this>  
 variable which contains the field hash as it has been built up to the current point. If any  
 fields are dependent on other fields, the C<pass> attribute can be used to control the order  
 in which the fields are generated. A field with a high data pass number will be generated after  
 a field with a lower one. If any external values are needed, they should be passed in via the  
 optional third parameter, which will be available to the data generation script under the name  
 C<$value>. Several useful utility methods are provided for generating random values, including  
 L</IntGen>, L</StringGen>, L</FloatGen>, and L</DateGen>. Note that dates are stored and generated  
 in the form of a timestamp number rather than a string.  
2561    
2562  =over 4  =over 4
2563    
2564  =item id  =item relationName
2565    
2566  ID to assign to the new entity.  Name of the relation to drop. If it does not exist, this method will have
2567    no effect.
2568    
2569  =item type  =back
2570    
2571    =cut
2572    
2573  Type name for the new entity.  sub DropRelation {
2574        # Get the parameters.
2575        my ($self, $relationName) = @_;
2576        # Get the database handle.
2577        my $dbh = $self->{_dbh};
2578        # Drop the relation. The method used here has no effect if the relation
2579        # does not exist.
2580        Trace("Invoking DB Kernel to drop $relationName.") if T(3);
2581        $dbh->drop_table(tbl => $relationName);
2582    }
2583    
2584    =head3 MatchSqlPattern
2585    
2586    C<< my $matched = ERDB::MatchSqlPattern($value, $pattern); >>
2587    
2588    Determine whether or not a specified value matches an SQL pattern. An SQL
2589    pattern has two wild card characters: C<%> that matches multiple characters,
2590    and C<_> that matches a single character. These can be escaped using a
2591    backslash (C<\>). We pull this off by converting the SQL pattern to a
2592    PERL regular expression. As per SQL rules, the match is case-insensitive.
2593    
2594    =over 4
2595    
2596    =item value
2597    
2598    Value to be matched against the pattern. Note that an undefined or empty
2599    value will not match anything.
2600    
2601    =item pattern
2602    
2603    SQL pattern against which to match the value. An undefined or empty pattern will
2604    match everything.
2605    
2606  =item values  =item RETURN
2607    
2608  Hash containing additional values that might be needed by the data generation methods (optional).  Returns TRUE if the value and pattern match, else FALSE.
2609    
2610  =back  =back
2611    
2612  =cut  =cut
2613    
2614  sub GenerateEntity {  sub MatchSqlPattern {
2615      # Get the parameters.      # Get the parameters.
2616      my ($self, $id, $type, $values) = @_;      my ($value, $pattern) = @_;
2617      # Create the return hash.      # Declare the return variable.
2618      my $this = { id => $id };      my $retVal;
2619      # Get the metadata structure.      # Insure we have a pattern.
2620      my $metadata = $self->{_metaData};      if (! defined($pattern) || $pattern eq "") {
2621      # Get this entity's list of fields.          $retVal = 1;
2622      if (!exists $metadata->{Entities}->{$type}) {      } else {
2623          Confess("Unrecognized entity type $type in GenerateEntity.");          # Break the pattern into pieces around the wildcard characters. Because we
2624      } else {          # use parentheses in the split function's delimiter expression, we'll get
2625          my $entity = $metadata->{Entities}->{$type};          # list elements for the delimiters as well as the rest of the string.
2626          my $fields = $entity->{Fields};          my @pieces = split /([_%]|\\[_%])/, $pattern;
2627          # Generate data from the fields.          # Check some fast special cases.
2628          _GenerateFields($this, $fields, $type, $values);          if ($pattern eq '%') {
2629                # A null pattern matches everything.
2630                $retVal = 1;
2631            } elsif (@pieces == 1) {
2632                # No wildcards, so we have a literal comparison. Note we're case-insensitive.
2633                $retVal = (lc($value) eq lc($pattern));
2634            } elsif (@pieces == 2 && $pieces[1] eq '%') {
2635                # A wildcard at the end, so we have a substring match. This is also case-insensitive.
2636                $retVal = (lc(substr($value, 0, length($pieces[0]))) eq lc($pieces[0]));
2637            } else {
2638                # Okay, we have to do it the hard way. Convert each piece to a PERL pattern.
2639                my $realPattern = "";
2640                for my $piece (@pieces) {
2641                    # Determine the type of piece.
2642                    if ($piece eq "") {
2643                        # Empty pieces are ignored.
2644                    } elsif ($piece eq "%") {
2645                        # Here we have a multi-character wildcard. Note that it can match
2646                        # zero or more characters.
2647                        $realPattern .= ".*"
2648                    } elsif ($piece eq "_") {
2649                        # Here we have a single-character wildcard.
2650                        $realPattern .= ".";
2651                    } elsif ($piece eq "\\%" || $piece eq "\\_") {
2652                        # This is an escape sequence (which is a rare thing, actually).
2653                        $realPattern .= substr($piece, 1, 1);
2654                    } else {
2655                        # Here we have raw text.
2656                        $realPattern .= quotemeta($piece);
2657                    }
2658                }
2659                # Do the match.
2660                $retVal = ($value =~ /^$realPattern$/i ? 1 : 0);
2661      }      }
2662      # Return the hash created.      }
2663      return $this;      # Return the result.
2664        return $retVal;
2665  }  }
2666    
2667  =head3 GetEntity  =head3 GetEntity
# Line 1869  Line 2700 
2700      return $retVal;      return $retVal;
2701  }  }
2702    
2703    =head3 GetChoices
2704    
2705    C<< my @values = $erdb->GetChoices($entityName, $fieldName); >>
2706    
2707    Return a list of all the values for the specified field that are represented in the
2708    specified entity.
2709    
2710    Note that if the field is not indexed, then this will be a very slow operation.
2711    
2712    =over 4
2713    
2714    =item entityName
2715    
2716    Name of an entity in the database.
2717    
2718    =item fieldName
2719    
2720    Name of a field belonging to the entity. This is a raw field name without
2721    the standard parenthesized notation used in most calls.
2722    
2723    =item RETURN
2724    
2725    Returns a list of the distinct values for the specified field in the database.
2726    
2727    =back
2728    
2729    =cut
2730    
2731    sub GetChoices {
2732        # Get the parameters.
2733        my ($self, $entityName, $fieldName) = @_;
2734        # Declare the return variable.
2735        my @retVal;
2736        # Get the entity data structure.
2737        my $entityData = $self->_GetStructure($entityName);
2738        # Get the field.
2739        my $fieldHash = $entityData->{Fields};
2740        if (! exists $fieldHash->{$fieldName}) {
2741            Confess("$fieldName not found in $entityName.");
2742        } else {
2743            # Get the name of the relation containing the field.
2744            my $relation = $fieldHash->{$fieldName}->{relation};
2745            # Fix up the field name.
2746            my $realName = _FixName($fieldName);
2747            # Get the database handle.
2748            my $dbh = $self->{_dbh};
2749            # Query the database.
2750            my $results = $dbh->SQL("SELECT DISTINCT $realName FROM $relation");
2751            # Clean the results. They are stored as a list of lists, and we just want the one list.
2752            @retVal = sort map { $_->[0] } @{$results};
2753        }
2754        # Return the result.
2755        return @retVal;
2756    }
2757    
2758  =head3 GetEntityValues  =head3 GetEntityValues
2759    
2760  C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>  C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>
2761    
2762  Return a list of values from a specified entity instance.  Return a list of values from a specified entity instance. If the entity instance
2763    does not exist, an empty list is returned.
2764    
2765  =over 4  =over 4
2766    
# Line 1930  Line 2817 
2817  spreadsheet cell, and each feature will be represented by a list containing the  spreadsheet cell, and each feature will be represented by a list containing the
2818  feature ID followed by all of its aliases.  feature ID followed by all of its aliases.
2819    
2820  C<< $query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>  C<< @query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>
2821    
2822  =over 4  =over 4
2823    
# Line 2001  Line 2888 
2888          push @retVal, \@rowData;          push @retVal, \@rowData;
2889          $fetched++;          $fetched++;
2890      }      }
2891        Trace("$fetched rows returned in GetAll.") if T(SQL => 4);
2892      # Return the resulting list.      # Return the resulting list.
2893      return @retVal;      return @retVal;
2894  }  }
2895    
2896    =head3 Exists
2897    
2898    C<< my $found = $sprout->Exists($entityName, $entityID); >>
2899    
2900    Return TRUE if an entity exists, else FALSE.
2901    
2902    =over 4
2903    
2904    =item entityName
2905    
2906    Name of the entity type (e.g. C<Feature>) relevant to the existence check.
2907    
2908    =item entityID
2909    
2910    ID of the entity instance whose existence is to be checked.
2911    
2912    =item RETURN
2913    
2914    Returns TRUE if the entity instance exists, else FALSE.
2915    
2916    =back
2917    
2918    =cut
2919    #: Return Type $;
2920    sub Exists {
2921        # Get the parameters.
2922        my ($self, $entityName, $entityID) = @_;
2923        # Check for the entity instance.
2924        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
2925        my $testInstance = $self->GetEntity($entityName, $entityID);
2926        # Return an existence indicator.
2927        my $retVal = ($testInstance ? 1 : 0);
2928        return $retVal;
2929    }
2930    
2931  =head3 EstimateRowSize  =head3 EstimateRowSize
2932    
2933  C<< my $rowSize = $erdb->EstimateRowSize($relName); >>  C<< my $rowSize = $erdb->EstimateRowSize($relName); >>
# Line 2072  Line 2995 
2995      return $objectData->{Fields};      return $objectData->{Fields};
2996  }  }
2997    
2998  =head3 GetUsefulCrossValues  =head3 SplitKeywords
2999    
3000  C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>  C<< my @keywords = ERDB::SplitKeywords($keywordString); >>
3001    
3002  Return a list of the useful attributes that would be returned by a B<Cross> call  This method returns a list of the positive keywords in the specified
3003  from an entity of the source entity type through the specified relationship. This  keyword string. All of the operators will have been stripped off,
3004  means it will return the fields of the target entity type and the intersection data  and if the keyword is preceded by a minus operator (C<->), it will
3005  fields in the relationship. Only primary table fields are returned. In other words,  not be in the list returned. The idea here is to get a list of the
3006  the field names returned will be for fields where there is always one and only one  keywords the user wants to see. The list will be processed to remove
3007  value.  duplicates.
3008    
3009  =over 4  It is possible to create a string that confuses this method. For example
3010    
3011  =item sourceEntity      frog toad -frog
3012    
3013  Name of the entity from which the relationship crossing will start.  would return both C<frog> and C<toad>. If this is a problem we can deal
3014    with it later.
3015    
3016  =item relationship  =over 4
3017    
3018  Name of the relationship being crossed.  =item keywordString
3019    
3020    The keyword string to be parsed.
3021    
3022    =item RETURN
3023    
3024    Returns a list of the words in the keyword string the user wants to
3025    see.
3026    
3027    =back
3028    
3029    =cut
3030    
3031    sub SplitKeywords {
3032        # Get the parameters.
3033        my ($keywordString) = @_;
3034        # Make a safety copy of the string. (This helps during debugging.)
3035        my $workString = $keywordString;
3036        # Convert operators we don't care about to spaces.
3037        $workString =~ tr/+"()<>/ /;
3038        # Split the rest of the string along space boundaries. Note that we
3039        # eliminate any words that are zero length or begin with a minus sign.
3040        my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
3041        # Use a hash to remove duplicates.
3042        my %words = map { $_ => 1 } @wordList;
3043        # Return the result.
3044        return sort keys %words;
3045    }
3046    
3047    =head3 ValidateFieldName
3048    
3049    C<< my $okFlag = ERDB::ValidateFieldName($fieldName); >>
3050    
3051    Return TRUE if the specified field name is valid, else FALSE. Valid field names must
3052    be hyphenated words subject to certain restrictions.
3053    
3054    =over 4
3055    
3056    =item fieldName
3057    
3058    Field name to be validated.
3059    
3060    =item RETURN
3061    
3062    Returns TRUE if the field name is valid, else FALSE.
3063    
3064    =back
3065    
3066    =cut
3067    
3068    sub ValidateFieldName {
3069        # Get the parameters.
3070        my ($fieldName) = @_;
3071        # Declare the return variable. The field name is valid until we hear
3072        # differently.
3073        my $retVal = 1;
3074        # Compute the maximum name length.
3075        my $maxLen = $TypeTable{'name-string'}->{maxLen};
3076        # Look for bad stuff in the name.
3077        if ($fieldName =~ /--/) {
3078            # Here we have a doubled minus sign.
3079            Trace("Field name $fieldName has a doubled hyphen.") if T(1);
3080            $retVal = 0;
3081        } elsif ($fieldName !~ /^[A-Za-z]/) {
3082            # Here the field name is missing the initial letter.
3083            Trace("Field name $fieldName does not begin with a letter.") if T(1);
3084            $retVal = 0;
3085        } elsif (length($fieldName) > $maxLen) {
3086            # Here the field name is too long.
3087            Trace("Maximum field name length is $maxLen. Field name must be truncated to " . substr($fieldName,0, $maxLen) . ".");
3088        } else {
3089            # Strip out the minus signs. Everything remaining must be a letter,
3090            # underscore, or digit.
3091            my $strippedName = $fieldName;
3092            $strippedName =~ s/-//g;
3093            if ($strippedName !~ /^(\w|\d)+$/) {
3094                Trace("Field name $fieldName contains illegal characters.") if T(1);
3095                $retVal = 0;
3096            }
3097        }
3098        # Return the result.
3099        return $retVal;
3100    }
3101    
3102    =head3 ReadMetaXML
3103    
3104    C<< my $rawMetaData = ERDB::ReadDBD($fileName); >>
3105    
3106    This method reads a raw database definition XML file and returns it.
3107    Normally, the metadata used by the ERDB system has been processed and
3108    modified to make it easier to load and retrieve the data; however,
3109    this method can be used to get the data in its raw form.
3110    
3111    =over 4
3112    
3113    =item fileName
3114    
3115    Name of the XML file to read.
3116    
3117    =item RETURN
3118    
3119    Returns a hash reference containing the raw XML data from the specified file.
3120    
3121    =back
3122    
3123    =cut
3124    
3125    sub ReadMetaXML {
3126        # Get the parameters.
3127        my ($fileName) = @_;
3128        # Read the XML.
3129        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
3130        Trace("XML metadata loaded from file $fileName.") if T(1);
3131        # Return the result.
3132        return $retVal;
3133    }
3134    
3135    =head3 GetEntityFieldHash
3136    
3137    C<< my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName); >>
3138    
3139    Get the field hash of the named entity in the specified raw XML structure.
3140    The field hash may not exist, in which case we need to create it.
3141    
3142    =over 4
3143    
3144    =item structure
3145    
3146    Raw XML structure defininng the database. This is not the run-time XML used by
3147    an ERDB object, since that has all sorts of optimizations built-in.
3148    
3149    =item entityName
3150    
3151    Name of the entity whose field structure is desired.
3152    
3153    =item RETURN
3154    
3155    Returns the field hash used to define the entity's fields.
3156    
3157    =back
3158    
3159    =cut
3160    
3161    sub GetEntityFieldHash {
3162        # Get the parameters.
3163        my ($structure, $entityName) = @_;
3164        # Get the entity structure.
3165        my $entityData = $structure->{Entities}->{$entityName};
3166        # Look for a field structure.
3167        my $retVal = $entityData->{Fields};
3168        # If it doesn't exist, create it.
3169        if (! defined($retVal)) {
3170            $entityData->{Fields} = {};
3171            $retVal = $entityData->{Fields};
3172        }
3173        # Return the result.
3174        return $retVal;
3175    }
3176    
3177    =head3 WriteMetaXML
3178    
3179    C<< ERDB::WriteMetaXML($structure, $fileName); >>
3180    
3181    Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
3182    used to update the database definition. It must be used with care, however, since it
3183    will only work on a raw structure, not on the processed structure created by an ERDB
3184    constructor.
3185    
3186    =over 4
3187    
3188    =item structure
3189    
3190    XML structure to be written to the file.
3191    
3192    =item fileName
3193    
3194    Name of the output file to which the updated XML should be stored.
3195    
3196    =back
3197    
3198    =cut
3199    
3200    sub WriteMetaXML {
3201        # Get the parameters.
3202        my ($structure, $fileName) = @_;
3203        # Compute the output.
3204        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
3205        # Write it to the file.
3206        my $xmlOut = Open(undef, ">$fileName");
3207        print $xmlOut $fileString;
3208    }
3209    
3210    
3211    =head3 HTMLNote
3212    
3213    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
3214    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
3215    Except for C<[p]>, all the codes are closed by slash-codes. So, for
3216    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
3217    
3218    C<< my $realHtml = ERDB::HTMLNote($dataString); >>
3219    
3220    =over 4
3221    
3222    =item dataString
3223    
3224    String to convert to HTML.
3225    
3226    =item RETURN
3227    
3228    An HTML string derived from the input string.
3229    
3230    =back
3231    
3232    =cut
3233    
3234    sub HTMLNote {
3235        # Get the parameter.
3236        my ($dataString) = @_;
3237        # HTML-escape the text.
3238        my $retVal = CGI::escapeHTML($dataString);
3239        # Substitute the bulletin board codes.
3240        $retVal =~ s!\[(/?[bi])\]!<$1>!g;
3241        $retVal =~ s!\[p\]!</p><p>!g;
3242        # Return the result.
3243        return $retVal;
3244    }
3245    
3246    
3247    =head2 Data Mining Methods
3248    
3249    =head3 GetUsefulCrossValues
3250    
3251    C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>
3252    
3253    Return a list of the useful attributes that would be returned by a B<Cross> call
3254    from an entity of the source entity type through the specified relationship. This
3255    means it will return the fields of the target entity type and the intersection data
3256    fields in the relationship. Only primary table fields are returned. In other words,
3257    the field names returned will be for fields where there is always one and only one
3258    value.
3259    
3260    =over 4
3261    
3262    =item sourceEntity
3263    
3264    Name of the entity from which the relationship crossing will start.
3265    
3266    =item relationship
3267    
3268    Name of the relationship being crossed.
3269    
3270  =item RETURN  =item RETURN
3271    
# Line 2133  Line 3307 
3307      return @retVal;      return @retVal;
3308  }  }
3309    
3310    =head3 FindColumn
3311    
3312    C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>
3313    
3314    Return the location a desired column in a data mining header line. The data
3315    mining header line is a tab-separated list of column names. The column
3316    identifier is either the numerical index of a column or the actual column
3317    name.
3318    
3319    =over 4
3320    
3321    =item headerLine
3322    
3323    The header line from a data mining command, which consists of a tab-separated
3324    list of column names.
3325    
3326    =item columnIdentifier
3327    
3328    Either the ordinal number of the desired column (1-based), or the name of the
3329    desired column.
3330    
3331    =item RETURN
3332    
3333    Returns the array index (0-based) of the desired column.
3334    
3335    =back
3336    
3337    =cut
3338    
3339    sub FindColumn {
3340        # Get the parameters.
3341        my ($headerLine, $columnIdentifier) = @_;
3342        # Declare the return variable.
3343        my $retVal;
3344        # Split the header line into column names.
3345        my @headers = ParseColumns($headerLine);
3346        # Determine whether we have a number or a name.
3347        if ($columnIdentifier =~ /^\d+$/) {
3348            # Here we have a number. Subtract 1 and validate the result.
3349            $retVal = $columnIdentifier - 1;
3350            if ($retVal < 0 || $retVal > $#headers) {
3351                Confess("Invalid column identifer \"$columnIdentifier\": value out of range.");
3352            }
3353        } else {
3354            # Here we have a name. We need to find it in the list.
3355            for (my $i = 0; $i <= $#headers && ! defined($retVal); $i++) {
3356                if ($headers[$i] eq $columnIdentifier) {
3357                    $retVal = $i;
3358                }
3359            }
3360            if (! defined($retVal)) {
3361                Confess("Invalid column identifier \"$columnIdentifier\": value not found.");
3362            }
3363        }
3364        # Return the result.
3365        return $retVal;
3366    }
3367    
3368    =head3 ParseColumns
3369    
3370    C<< my @columns = ERDB::ParseColumns($line); >>
3371    
3372    Convert the specified data line to a list of columns.
3373    
3374    =over 4
3375    
3376    =item line
3377    
3378    A data mining input, consisting of a tab-separated list of columns terminated by a
3379    new-line.
3380    
3381    =item RETURN
3382    
3383    Returns a list consisting of the column values.
3384    
3385    =back
3386    
3387    =cut
3388    
3389    sub ParseColumns {
3390        # Get the parameters.
3391        my ($line) = @_;
3392        # Chop off the line-end.
3393        chomp $line;
3394        # Split it into a list.
3395        my @retVal = split(/\t/, $line);
3396        # Return the result.
3397        return @retVal;
3398    }
3399    
3400    =head2 Virtual Methods
3401    
3402    =head3 CleanKeywords
3403    
3404    C<< my $cleanedString = $erdb->CleanKeywords($searchExpression); >>
3405    
3406    Clean up a search expression or keyword list. This is a virtual method that may
3407    be overridden by the subclass. The base-class method removes extra spaces
3408    and converts everything to lower case.
3409    
3410    =over 4
3411    
3412    =item searchExpression
3413    
3414    Search expression or keyword list to clean. Note that a search expression may
3415    contain boolean operators which need to be preserved. This includes leading
3416    minus signs.
3417    
3418    =item RETURN
3419    
3420    Cleaned expression or keyword list.
3421    
3422    =back
3423    
3424    =cut
3425    
3426    sub CleanKeywords {
3427        # Get the parameters.
3428        my ($self, $searchExpression) = @_;
3429        # Lower-case the expression and copy it into the return variable. Note that we insure we
3430        # don't accidentally end up with an undefined value.
3431        my $retVal = lc($searchExpression || "");
3432        # Remove extra spaces.
3433        $retVal =~ s/\s+/ /g;
3434        $retVal =~ s/(^\s+)|(\s+$)//g;
3435        # Return the result.
3436        return $retVal;
3437    }
3438    
3439    =head3 GetSourceObject
3440    
3441    C<< my $source = $erdb->GetSourceObject($entityName); >>
3442    
3443    Return the object to be used in loading special attributes of the specified entity. The
3444    algorithm for loading special attributes is stored in the C<DataGen> elements of the
3445    XML
3446    
3447  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3448    
3449  =head3 SetupSQL  =head3 _RelationMap
3450    
3451    C<< my @relationMap = _RelationMap($mappedNameHashRef, $mappedNameListRef); >>
3452    
3453    Create the relation map for an SQL query. The relation map is used by B<DBObject>
3454    to determine how to interpret the results of the query.
3455    
3456    =over 4
3457    
3458    =item mappedNameHashRef
3459    
3460    Reference to a hash that maps modified object names to real object names.
3461    
3462    =item mappedNameListRef
3463    
3464    Reference to a list of modified object names in the order they appear in the
3465    SELECT list.
3466    
3467    =item RETURN
3468    
3469    Returns a list of 2-tuples. Each tuple consists of an object name as used in the
3470    query followed by the actual name of that object. This enables the B<DBObject> to
3471    determine the order of the tables in the query and which object name belongs to each
3472    mapped object name. Most of the time these two values are the same; however, if a
3473    relation occurs twice in the query, the relation name in the field list and WHERE
3474    clause will use a mapped name (generally the actual relation name with a numeric
3475    suffix) that does not match the actual relation name.
3476    
3477    =back
3478    
3479    =cut
3480    
3481    sub _RelationMap {
3482        # Get the parameters.
3483        my ($mappedNameHashRef, $mappedNameListRef) = @_;
3484        # Declare the return variable.
3485        my @retVal = ();
3486        # Build the map.
3487        for my $mappedName (@{$mappedNameListRef}) {
3488            push @retVal, [$mappedName, $mappedNameHashRef->{$mappedName}];
3489        }
3490        # Return it.
3491        return @retVal;
3492    }
3493    
3494    
3495    =head3 _SetupSQL
3496    
3497  Process a list of object names and a filter clause so that they can be used to  Process a list of object names and a filter clause so that they can be used to
3498  build an SQL statement. This method takes in a reference to a list of object names  build an SQL statement. This method takes in a reference to a list of object names
# Line 2155  Line 3512 
3512  A string containing the WHERE clause for the query (without the C<WHERE>) and also  A string containing the WHERE clause for the query (without the C<WHERE>) and also
3513  optionally the C<ORDER BY> and C<LIMIT> clauses.  optionally the C<ORDER BY> and C<LIMIT> clauses.
3514    
3515    =item matchClause
3516    
3517    An optional full-text search clause. If specified, it will be inserted at the
3518    front of the WHERE clause. It should already be SQL-formatted; that is, the
3519    field names should be in the form I<table>C<.>I<fieldName>.
3520    
3521  =item RETURN  =item RETURN
3522    
3523  Returns a three-element list. The first element is the SQL statement suffix, beginning  Returns a three-element list. The first element is the SQL statement suffix, beginning
# Line 2167  Line 3530 
3530  =cut  =cut
3531    
3532  sub _SetupSQL {  sub _SetupSQL {
3533      my ($self, $objectNames, $filterClause) = @_;      my ($self, $objectNames, $filterClause, $matchClause) = @_;
3534      # Adjust the list of object names to account for multiple occurrences of the      # Adjust the list of object names to account for multiple occurrences of the
3535      # same object. We start with a hash table keyed on object name that will      # same object. We start with a hash table keyed on object name that will
3536      # return the object suffix. The first time an object is encountered it will      # return the object suffix. The first time an object is encountered it will
# Line 2216  Line 3579 
3579      # FROM name1, name2, ... nameN      # FROM name1, name2, ... nameN
3580      #      #
3581      my $suffix = "FROM " . join(', ', @fromList);      my $suffix = "FROM " . join(', ', @fromList);
3582        # Now for the WHERE. First, we need a place for the filter string.
3583        my $filterString = "";
3584        # We will also keep a list of conditions to add to the WHERE clause in order to link
3585        # entities and relationships as well as primary relations to secondary ones.
3586        my @joinWhere = ();
3587      # Check for a filter clause.      # Check for a filter clause.
3588      if ($filterClause) {      if ($filterClause) {
3589          # Here we have one, so we convert its field names and add it to the query. First,          # Here we have one, so we convert its field names and add it to the query. First,
3590          # We create a copy of the filter string we can work with.          # We create a copy of the filter string we can work with.
3591          my $filterString = $filterClause;          $filterString = $filterClause;
3592          # Next, we sort the object names by length. This helps protect us from finding          # Next, we sort the object names by length. This helps protect us from finding
3593          # object names inside other object names when we're doing our search and replace.          # object names inside other object names when we're doing our search and replace.
3594          my @sortedNames = sort { length($b) - length($a) } @mappedNameList;          my @sortedNames = sort { length($b) - length($a) } @mappedNameList;
         # 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 = ();  
3595          # The final preparatory step is to create a hash table of relation names. The          # The final preparatory step is to create a hash table of relation names. The
3596          # table begins with the relation names already in the SELECT command. We may          # table begins with the relation names already in the SELECT command. We may
3597          # need to add relations later if there is filtering on a field in a secondary          # need to add relations later if there is filtering on a field in a secondary
# Line 2294  Line 3659 
3659                  }                  }
3660              }              }
3661          }          }
3662        }
3663          # The next step is to join the objects together. We only need to do this if there          # The next step is to join the objects together. We only need to do this if there
3664          # is more than one object in the object list. We start with the first object and          # is more than one object in the object list. We start with the first object and
3665          # run through the objects after it. Note also that we make a safety copy of the          # run through the objects after it. Note also that we make a safety copy of the
3666          # list before running through it.      # list before running through it, because we shift off the first object before
3667        # processing the rest.
3668          my @mappedObjectList = @mappedNameList;          my @mappedObjectList = @mappedNameList;
3669          my $lastMappedObject = shift @mappedObjectList;          my $lastMappedObject = shift @mappedObjectList;
3670          # Get the join table.          # Get the join table.
# Line 2326  Line 3693 
3693          # here is we want the filter clause to be empty if there's no WHERE filter.          # here is we want the filter clause to be empty if there's no WHERE filter.
3694          # We'll put the ORDER BY / LIMIT clauses in the following variable.          # We'll put the ORDER BY / LIMIT clauses in the following variable.
3695          my $orderClause = "";          my $orderClause = "";
3696        # This is only necessary if we have a filter string in which the ORDER BY
3697        # and LIMIT clauses can live.
3698        if ($filterString) {
3699          # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy          # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy
3700          # operator so that we find the first occurrence of either verb.          # operator so that we find the first occurrence of either verb.
3701          if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {          if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {
# Line 2334  Line 3704 
3704              $orderClause = $2 . substr($filterString, $pos);              $orderClause = $2 . substr($filterString, $pos);
3705              $filterString = $1;              $filterString = $1;
3706          }          }
3707          # Add the filter and the join clauses (if any) to the SELECT command.      }
3708        # All the things that are supposed to be in the WHERE clause of the
3709        # SELECT command need to be put into @joinWhere so we can string them
3710        # together. We begin with the match clause. This is important,
3711        # because the match clause's parameter mark must precede any parameter
3712        # marks in the filter string.
3713        if ($matchClause) {
3714            push @joinWhere, $matchClause;
3715        }
3716        # Add the filter string. We put it in parentheses to avoid operator
3717        # precedence problems with the match clause or the joins.
3718          if ($filterString) {          if ($filterString) {
3719              Trace("Filter string is \"$filterString\".") if T(4);              Trace("Filter string is \"$filterString\".") if T(4);
3720              push @joinWhere, "($filterString)";              push @joinWhere, "($filterString)";
3721          }          }
3722        # String it all together into a big filter clause.
3723          if (@joinWhere) {          if (@joinWhere) {
3724              $suffix .= " WHERE " . join(' AND ', @joinWhere);              $suffix .= " WHERE " . join(' AND ', @joinWhere);
3725          }          }
3726          # Add the sort or limit clause (if any) to the SELECT command.      # Add the sort or limit clause (if any).
3727          if ($orderClause) {          if ($orderClause) {
3728              $suffix .= " $orderClause";              $suffix .= " $orderClause";
3729          }          }
     }  
3730      # Return the suffix, the mapped name list, and the mapped name hash.      # Return the suffix, the mapped name list, and the mapped name hash.
3731      return ($suffix, \@mappedNameList, \%mappedNameHash);      return ($suffix, \@mappedNameList, \%mappedNameHash);
3732  }  }
3733    
3734  =head3 GetStatementHandle  =head3 _GetStatementHandle
3735    
3736  This method will prepare and execute an SQL query, returning the statement handle.  This method will prepare and execute an SQL query, returning the statement handle.
3737  The main reason for doing this here is so that everybody who does SQL queries gets  The main reason for doing this here is so that everybody who does SQL queries gets
# Line 2389  Line 3769 
3769      # Prepare the command.      # Prepare the command.
3770      my $sth = $dbh->prepare_command($command);      my $sth = $dbh->prepare_command($command);
3771      # Execute it with the parameters bound in.      # Execute it with the parameters bound in.
3772      $sth->execute(@{$params}) || Confess("SELECT error" . $sth->errstr());      $sth->execute(@{$params}) || Confess("SELECT error:  " . $sth->errstr());
3773      # Return the statement handle.      # Return the statement handle.
3774      return $sth;      return $sth;
3775  }  }
3776    
3777  =head3 GetLoadStats  =head3 _GetLoadStats
3778    
3779  Return a blank statistics object for use by the load methods.  Return a blank statistics object for use by the load methods.
3780    
# Line 2406  Line 3786 
3786      return Stats->new();      return Stats->new();
3787  }  }
3788    
3789  =head3 GenerateFields  =head3 _DumpRelation
   
 Generate field values from a field structure and store in a specified table. The field names  
 are first sorted by pass count, certain pre-defined fields are removed from the list, and  
 then we rip through them evaluation the data generation string. Fields in the primary relation  
 are stored as scalars; fields in secondary relations are stored as value lists.  
   
 This is a static method.  
   
 =over 4  
   
 =item this  
   
 Hash table into which the field values should be placed.  
   
 =item fields  
   
 Field structure from which the field descriptors should be taken.  
   
 =item type  
   
 Type name of the object whose fields are being generated.  
   
 =item values (optional)  
   
 Reference to a value structure from which additional values can be taken.  
   
 =item from (optiona)  
   
 Reference to the source entity instance if relationship data is being generated.  
   
 =item to (optional)  
   
 Reference to the target entity instance if relationship data is being generated.  
   
 =back  
   
 =cut  
   
 sub _GenerateFields {  
     # Get the parameters.  
     my ($this, $fields, $type, $values, $from, $to) = @_;  
     # Sort the field names by pass number.  
     my @fieldNames = sort { $fields->{$a}->{DataGen}->{pass} <=> $fields->{$b}->{DataGen}->{pass} } keys %{$fields};  
     # Loop through the field names, generating data.  
     for my $name (@fieldNames) {  
         # Only proceed if this field needs to be generated.  
         if (!exists $this->{$name}) {  
             # Get this field's data generation descriptor.  
             my $fieldDescriptor = $fields->{$name};  
             my $data = $fieldDescriptor->{DataGen};  
             # Get the code to generate the field value.  
             my $codeString = $data->{content};  
             # Determine whether or not this field is in the primary relation.  
             if ($fieldDescriptor->{relation} eq $type) {  
                 # Here we have a primary relation field. Store the field value as  
                 # a scalar.  
                 $this->{$name} = eval($codeString);  
             } else {  
                 # Here we have a secondary relation field. Create a null list  
                 # and push the desired number of field values onto it.  
                 my @fieldValues = ();  
                 my $count = IntGen(0,$data->{testCount});  
                 for (my $i = 0; $i < $count; $i++) {  
                     my $newValue = eval($codeString);  
                     push @fieldValues, $newValue;  
                 }  
                 # Store the value list in the main hash.  
                 $this->{$name} = \@fieldValues;  
             }  
         }  
     }  
 }  
   
 =head3 DumpRelation  
3790    
3791  Dump the specified relation's to the specified output file in tab-delimited format.  Dump the specified relation to the specified output file in tab-delimited format.
3792    
3793  This is an instance method.  This is an instance method.
3794    
# Line 2530  Line 3836 
3836      close DTXOUT;      close DTXOUT;
3837  }  }
3838    
3839  =head3 GetStructure  =head3 _GetStructure
3840    
3841  Get the data structure for a specified entity or relationship.  Get the data structure for a specified entity or relationship.
3842    
# Line 2569  Line 3875 
3875      return $retVal;      return $retVal;
3876  }  }
3877    
3878  =head3 GetRelationTable  
3879    
3880    =head3 _GetRelationTable
3881    
3882  Get the list of relations for a specified entity or relationship.  Get the list of relations for a specified entity or relationship.
3883    
# Line 2598  Line 3906 
3906      return $objectData->{Relations};      return $objectData->{Relations};
3907  }  }
3908    
3909  =head3 ValidateFieldNames  =head3 _ValidateFieldNames
3910    
3911  Determine whether or not the field names are valid. A description of the problems with the names  Determine whether or not the field names are valid. A description of the problems with the names
3912  will be written to the standard error output. If there is an error, this method will abort. This is  will be written to the standard error output. If there is an error, this method will abort. This is
# Line 2625  Line 3933 
3933          for my $object (values %{$metadata->{$section}}) {          for my $object (values %{$metadata->{$section}}) {
3934              # Loop through the object's fields.              # Loop through the object's fields.
3935              for my $fieldName (keys %{$object->{Fields}}) {              for my $fieldName (keys %{$object->{Fields}}) {
3936                  # Now we make some initial validations.                  # If this field name is invalid, set the return value to zero
3937                  if ($fieldName =~ /--/) {                  # so we know we encountered an error.
3938                      # Here we have a doubled minus sign.                  if (! ValidateFieldName($fieldName)) {
                     print STDERR "Field name $fieldName has a doubled hyphen.\n";  
                     $retVal = 0;  
                 } elsif ($fieldName !~ /^[A-Za-z]/) {  
                     # Here the field name is missing the initial letter.  
                     print STDERR "Field name $fieldName does not begin with a letter.\n";  
                     $retVal = 0;  
                 } else {  
                     # Strip out the minus signs. Everything remaining must be a letter  
                     # or digit.  
                     my $strippedName = $fieldName;  
                     $strippedName =~ s/-//g;  
                     if ($strippedName !~ /^[A-Za-z0-9]+$/) {  
                         print STDERR "Field name $fieldName contains illegal characters.\n";  
3939                          $retVal = 0;                          $retVal = 0;
3940                      }                      }
3941                  }                  }
3942              }              }
3943          }          }
     }  
3944      # If an error was found, fail.      # If an error was found, fail.
3945      if ($retVal  == 0) {      if ($retVal  == 0) {
3946          Confess("Errors found in field names.");          Confess("Errors found in field names.");
3947      }      }
3948  }  }
3949    
3950  =head3 LoadRelation  =head3 _LoadRelation
3951    
3952  Load a relation from the data in a tab-delimited disk file. The load will only take place if a disk  Load a relation from the data in a tab-delimited disk file. The load will only take place if a disk
3953  file with the same name as the relation exists in the specified directory.  file with the same name as the relation exists in the specified directory.
# Line 2713  Line 4007 
4007      return $retVal;      return $retVal;
4008  }  }
4009    
4010  =head3 LoadMetaData  
4011    =head3 _LoadMetaData
4012    
4013  This method loads the data describing this database from an XML file into a metadata structure.  This method loads the data describing this database from an XML file into a metadata structure.
4014  The resulting structure is a set of nested hash tables containing all the information needed to  The resulting structure is a set of nested hash tables containing all the information needed to
# Line 2738  Line 4033 
4033  sub _LoadMetaData {  sub _LoadMetaData {
4034      # Get the parameters.      # Get the parameters.
4035      my ($filename) = @_;      my ($filename) = @_;
4036      Trace("Reading Sprout DBD from $filename.") if T(2);      Trace("Reading DBD from $filename.") if T(2);
4037      # Slurp the XML file into a variable. Extensive use of options is used to insure we      # Slurp the XML file into a variable. Extensive use of options is used to insure we
4038      # get the exact structure we want.      # get the exact structure we want.
4039      my $metadata = XML::Simple::XMLin($filename,      my $metadata = ReadMetaXML($filename);
                                       GroupTags => { Relationships => 'Relationship',  
                                                      Entities => 'Entity',  
                                                      Fields => 'Field',  
                                                      Indexes => 'Index',  
                                                      IndexFields => 'IndexField'},  
                                       KeyAttr => { Relationship => 'name',  
                                                    Entity => 'name',  
                                                    Field => 'name'},  
                                       ForceArray => ['Field', 'Index', 'IndexField'],  
                                       ForceContent => 1,  
                                       NormalizeSpace => 2  
                                       );  
     Trace("XML metadata loaded from file $filename.") if T(1);  
4040      # Before we go any farther, we need to validate the field and object names. If an error is found,      # Before we go any farther, we need to validate the field and object names. If an error is found,
4041      # the method below will fail.      # the method below will fail.
4042      _ValidateFieldNames($metadata);      _ValidateFieldNames($metadata);
# Line 2884  Line 4166 
4166              my $count = 0;              my $count = 0;
4167              for my $index (@{$indexList}) {              for my $index (@{$indexList}) {
4168                  # Add this index to the index table.                  # Add this index to the index table.
4169                  _AddIndex("idx$relationName$count", $relation, $index);                  _AddIndex("idx$count", $relation, $index);
4170                  # Increment the counter so that the next index has a different name.                  # Increment the counter so that the next index has a different name.
4171                  $count++;                  $count++;
4172              }              }
# Line 3040  Line 4322 
4322      return $metadata;      return $metadata;
4323  }  }
4324    
4325  =head3 SortNeeded  =head3 _CreateRelationshipIndex
   
 C<< my $flag = $erdb->SortNeeded($relationName); >>  
   
 Return TRUE if the specified relation should be sorted during loading to remove duplicate keys,  
 else FALSE.  
   
 =over 4  
   
 =item relationName  
   
 Name of the relation to be examined.  
   
 =item RETURN  
   
 Returns TRUE if the relation needs a sort, else FALSE.  
   
 =back  
   
 =cut  
 #: Return Type $;  
 sub SortNeeded {  
     # Get the parameters.  
     my ($self, $relationName) = @_;  
     # Declare the return variable.  
     my $retVal = 0;  
     # Find out if the relation is a primary entity relation.  
     my $entityTable = $self->{_metaData}->{Entities};  
     if (exists $entityTable->{$relationName}) {  
         my $keyType = $entityTable->{$relationName}->{keyType};  
         Trace("Relation $relationName found in entity table with key type $keyType.") if T(3);  
         # If the key is not a hash string, we must do the sort.  
         if ($keyType ne 'hash-string') {  
             $retVal = 1;  
         }  
     }  
     # Return the result.  
     return $retVal;  
 }  
   
 =head3 CreateRelationshipIndex  
4326    
4327  Create an index for a relationship's relation.  Create an index for a relationship's relation.
4328    
# Line 3122  Line 4364 
4364          $newIndex->{Unique} = 'true';          $newIndex->{Unique} = 'true';
4365      }      }
4366      # Add the index to the relation.      # Add the index to the relation.
4367      _AddIndex("idx$relationshipName$indexKey", $relationStructure, $newIndex);      _AddIndex("idx$indexKey", $relationStructure, $newIndex);
4368  }  }
4369    
4370  =head3 AddIndex  =head3 _AddIndex
4371    
4372  Add an index to a relation structure.  Add an index to a relation structure.
4373    
# Line 3171  Line 4413 
4413      $relationStructure->{Indexes}->{$indexName} = $newIndex;      $relationStructure->{Indexes}->{$indexName} = $newIndex;
4414  }  }
4415    
4416  =head3 FixupFields  =head3 _FixupFields
4417    
4418  This method fixes the field list for an entity or relationship. It will add the caller-specified  This method fixes the field list for an entity or relationship. It will add the caller-specified
4419  relation name to fields that do not have a name and set the C<PrettySort> value as specified.  relation name to fields that do not have a name and set the C<PrettySort> value as specified.
# Line 3209  Line 4451 
4451          # Here it doesn't, so we create a new one.          # Here it doesn't, so we create a new one.
4452          $structure->{Fields} = { };          $structure->{Fields} = { };
4453      } else {      } else {
4454          # Here we have a field list. Loop through its fields.          # Here we have a field list. We need to track the searchable fields, so we
4455            # create a list for stashing them.
4456            my @textFields = ();
4457            # Loop through the fields.
4458          my $fieldStructures = $structure->{Fields};          my $fieldStructures = $structure->{Fields};
4459          for my $fieldName (keys %{$fieldStructures}) {          for my $fieldName (keys %{$fieldStructures}) {
4460              Trace("Processing field $fieldName of $defaultRelationName.") if T(4);              Trace("Processing field $fieldName of $defaultRelationName.") if T(4);
# Line 3218  Line 4463 
4463              my $type = $fieldData->{type};              my $type = $fieldData->{type};
4464              # Plug in a relation name if it is needed.              # Plug in a relation name if it is needed.
4465              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });
4466              # Plug in a data generator if we need one.              # Check for searchability.
4467              if (!exists $fieldData->{DataGen}) {              if ($fieldData->{searchable}) {
4468                  # The data generator will use the default for the field's type.                  # Only allow this for a primary relation.
4469                  $fieldData->{DataGen} = { content => $TypeTable{$type}->{dataGen} };                  if ($fieldData->{relation} ne $defaultRelationName) {
4470                        Confess("Field $fieldName of $defaultRelationName is in secondary relations and cannot be searchable.");
4471                    } else {
4472                        push @textFields, $fieldName;
4473                    }
4474              }              }
             # Plug in the defaults for the optional data generation parameters.  
             Tracer::MergeOptions($fieldData->{DataGen}, { testCount => 1, pass => 0 });  
4475              # Add the PrettySortValue.              # Add the PrettySortValue.
4476              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);
4477          }          }
4478            # If there are searchable fields, remember the fact.
4479            if (@textFields) {
4480                $structure->{searchFields} = \@textFields;
4481            }
4482      }      }
4483  }  }
4484    
4485  =head3 FixName  =head3 _FixName
4486    
4487  Fix the incoming field name so that it is a legal SQL column name.  Fix the incoming field name so that it is a legal SQL column name.
4488    
# Line 3260  Line 4511 
4511      return $fieldName;      return $fieldName;
4512  }  }
4513    
4514  =head3 FixNames  =head3 _FixNames
4515    
4516  Fix all the field names in a list.  Fix all the field names in a list.
4517    
# Line 3291  Line 4542 
4542      return @result;      return @result;
4543  }  }
4544    
4545  =head3 AddField  =head3 _AddField
4546    
4547  Add a field to a field list.  Add a field to a field list.
4548    
# Line 3326  Line 4577 
4577      $fieldList->{$fieldName} = $fieldStructure;      $fieldList->{$fieldName} = $fieldStructure;
4578  }  }
4579    
4580  =head3 ReOrderRelationTable  =head3 _ReOrderRelationTable
4581    
4582  This method will take a relation table and re-sort it according to the implicit ordering of the  This method will take a relation table and re-sort it according to the implicit ordering of the
4583  C<PrettySort> property. Instead of a hash based on field names, it will return a list of fields.  C<PrettySort> property. Instead of a hash based on field names, it will return a list of fields.
# Line 3387  Line 4638 
4638    
4639  }  }
4640    
4641  =head3 IsPrimary  =head3 _IsPrimary
4642    
4643  Return TRUE if a specified relation is a primary relation, else FALSE. A relation is primary  Return TRUE if a specified relation is a primary relation, else FALSE. A relation is primary
4644  if it has the same name as an entity or relationship.  if it has the same name as an entity or relationship.
# Line 3423  Line 4674 
4674      return $retVal;      return $retVal;
4675  }  }
4676    
4677  =head3 FindRelation  =head3 _FindRelation
4678    
4679  Return the descriptor for the specified relation.  Return the descriptor for the specified relation.
4680    
# Line 3454  Line 4705 
4705    
4706  =head2 HTML Documentation Utility Methods  =head2 HTML Documentation Utility Methods
4707    
4708  =head3 ComputeRelationshipSentence  =head3 _ComputeRelationshipSentence
4709    
4710  The relationship sentence consists of the relationship name between the names of the  The relationship sentence consists of the relationship name between the names of the
4711  two related entities and an arity indicator.  two related entities and an arity indicator.
# Line 3492  Line 4743 
4743      return $result;      return $result;
4744  }  }
4745    
4746  =head3 ComputeRelationshipHeading  =head3 _ComputeRelationshipHeading
4747    
4748  The relationship heading is the L<relationship sentence|/ComputeRelationshipSentence> with the entity  The relationship heading is the L<relationship sentence|/ComputeRelationshipSentence> with the entity
4749  names hyperlinked to the appropriate entity sections of the document.  names hyperlinked to the appropriate entity sections of the document.
# Line 3529  Line 4780 
4780      return $result;      return $result;
4781  }  }
4782    
4783  =head3 ShowRelationTable  =head3 _ShowRelationTable
4784    
4785  Generate the HTML string for a particular relation. The relation's data will be formatted as an HTML  Generate the HTML string for a particular relation. The relation's data will be formatted as an HTML
4786  table with three columns-- the field name, the field type, and the field description.  table with three columns-- the field name, the field type, and the field description.
# Line 3579  Line 4830 
4830          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";
4831          # Add any note text.          # Add any note text.
4832          if (my $note = $indexData->{Notes}) {          if (my $note = $indexData->{Notes}) {
4833              $htmlString .= "<li>" . _HTMLNote($note->{content}) . "</li>\n";              $htmlString .= "<li>" . HTMLNote($note->{content}) . "</li>\n";
4834          }          }
4835          # Add the fiield list.          # Add the fiield list.
4836          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";
# Line 3590  Line 4841 
4841      $htmlString .= "</ul>\n";      $htmlString .= "</ul>\n";
4842  }  }
4843    
4844  =head3 OpenFieldTable  =head3 _OpenFieldTable
4845    
4846  This method creates the header string for the field table generated by L</ShowMetaData>.  This method creates the header string for the field table generated by L</ShowMetaData>.
4847    
# Line 3615  Line 4866 
4866      return _OpenTable($tablename, 'Field', 'Type', 'Description');      return _OpenTable($tablename, 'Field', 'Type', 'Description');
4867  }  }
4868    
4869  =head3 OpenTable  =head3 _OpenTable
4870    
4871  This method creates the header string for an HTML table.  This method creates the header string for an HTML table.
4872    
# Line 3655  Line 4906 
4906      return $htmlString;      return $htmlString;
4907  }  }
4908    
4909  =head3 CloseTable  =head3 _CloseTable
4910    
4911  This method returns the HTML for closing a table.  This method returns the HTML for closing a table.
4912    
# Line 3667  Line 4918 
4918      return "</table></p>\n";      return "</table></p>\n";
4919  }  }
4920    
4921  =head3 ShowField  =head3 _ShowField
4922    
4923  This method returns the HTML for displaying a row of field information in a field table.  This method returns the HTML for displaying a row of field information in a field table.
4924    
# Line 3694  Line 4945 
4945      my $htmlString = "<tr><th align=\"left\">$fieldData->{name}</th><td>$fieldData->{type}</td>";      my $htmlString = "<tr><th align=\"left\">$fieldData->{name}</th><td>$fieldData->{type}</td>";
4946      # If we have content, add it as a third column.      # If we have content, add it as a third column.
4947      if (exists $fieldData->{Notes}) {      if (exists $fieldData->{Notes}) {
4948          $htmlString .= "<td>" . _HTMLNote($fieldData->{Notes}->{content}) . "</td>";          $htmlString .= "<td>" . HTMLNote($fieldData->{Notes}->{content}) . "</td>";
4949      }      }
4950      # Close off the row.      # Close off the row.
4951      $htmlString .= "</tr>\n";      $htmlString .= "</tr>\n";
# Line 3702  Line 4953 
4953      return $htmlString;      return $htmlString;
4954  }  }
4955    
 =head3 HTMLNote  
   
 Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes  
 supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.  
 Except for C<[p]>, all the codes are closed by slash-codes. So, for  
 example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.  
   
 This is a static method.  
   
 =over 4  
   
 =item dataString  
   
 String to convert to HTML.  
   
 =item RETURN  
   
 An HTML string derived from the input string.  
   
 =back  
   
 =cut  
   
 sub _HTMLNote {  
     # Get the parameter.  
     my ($dataString) = @_;  
     # Substitute the codes.  
     $dataString =~ s!\[(/?[bi])\]!<$1>!g;  
     $dataString =~ s!\[p\]!</p><p>!g;  
     # Return the result.  
     return $dataString;  
 }  
   
 =head2 Data Generation Utilities  
   
 =head3 IntGen  
   
 C<< my $integer = IntGen($min, $max); >>  
   
 Returns a random number between the specified minimum and maximum (inclusive).  
   
 =over 4  
   
 =item min  
   
 Minimum permissible return value.  
   
 =item max  
   
 Maximum permissible return value.  
   
 =item RETURN  
   
 Returns a value no lower than the minimum and no greater than the maximum.  
   
 =back  
   
 =cut  
   
 sub IntGen {  
     # Get the parameters.  
     my ($min, $max) = @_;  
     # Determine the range of possible values. Note we put some space well above the  
     # maximum value to give it a fighting chance of apppearing in the list.  
     my $span = $max + 0.99 - $min;  
     # Create an integer in the range.  
     my $retVal = $min + int(rand($span));  
     # Return the result.  
     return $retVal;  
 }  
   
 =head3 RandChar  
   
 C<< my $char = RandChar($sourceString); >>  
   
 Select a random character from a string.  
   
 =over 4  
   
 =item sourceString  
   
 String from which the random character should be selected.  
   
 =item RETURN  
   
 Returns a single character from the incoming string.  
   
 =back  
   
 =cut  
   
 sub RandChar {  
     # Get the parameter.  
     my ($sourceString) = @_;  
     # Select a random character.  
     my $retVal = IntGen(0, (length $sourceString) - 1);  
     # Return it.  
     return substr($sourceString, $retVal, 1);  
 }  
   
 =head3 RandChars  
   
 C<< my $string = RandChars($sourceString, $length); >>  
   
 Create a string from characters taken from a source string.  
   
 =over 4  
   
 =item sourceString  
   
 String from which the random characters should be selected.  
   
 =item length  
   
 Number of characters to put in the output string.  
   
 =item RETURN  
   
 Returns a string of the specified length consisting of characters taken from the  
 source string.  
   
 =back  
   
 =cut  
   
 sub RandChars {  
     # Get the parameters.  
     my ($sourceString, $length) = @_;  
     # Call RandChar repeatedly to generate the string.  
     my $retVal = "";  
     for (my $i = 0; $i < $length; $i++) {  
         $retVal .= RandChar($sourceString);  
     }  
     # Return the result.  
     return $retVal;  
 }  
   
 =head3 RandParam  
   
 C<< my $value = RandParam($parm1, $parm2, ... $parmN); >>  
   
 Return a randomly-selected value from the parameter list.  
   
 =over 4  
   
 =item parm1, parm2, ... parmN  
   
 List of values of which one will be selected.  
   
 =item RETURN  
   
 Returns a randomly-chosen value from the specified list.  
   
 =back  
   
 =cut  
   
 sub RandParam {  
     # Get the parameter.  
     my @parms = @_;  
     # Choose a random parameter from the list.  
     my $chosenIndex = IntGen(0, $#parms);  
     return $parms[$chosenIndex];  
 }  
   
 =head3 StringGen  
   
 C<< my $string = StringGen($pattern1, $pattern2, ... $patternN); >>  
   
 Returns a random string derived from a randomly-chosen format pattern. The pattern  
 can either be a number (indicating the number of characters desired, or the letter  
 C<P> followed by a picture. The picture should contain C<A> when a letter is desired,  
 C<9> when a digit is desired, C<V> when a vowel is desired, C<K> when a consonant is  
 desired, and C<X> when a letter or a digit is desired. Any other character will be  
 translated as a literal.  
   
 =over 4  
   
 =item pattern1, pattern2, ... patternN  
   
 List of patterns to be used to generate string values.  
   
 =item RETURN  
   
 A single string generated from a pattern.  
   
 =back  
   
 =cut  
   
 sub StringGen {  
     # Get the parameters.  
     my @patterns = @_;  
     # Choose the appropriate pattern.  
     my $chosenPattern = RandParam(@patterns);  
     # Declare the return variable.  
     my $retVal = "";  
     # Determine whether this is a count or a picture pattern.  
     if ($chosenPattern =~ m/^\d+/) {  
         # Here we have a count. Get the string of source characters.  
         my $letterString = $PictureTable{'X'};  
         my $stringLen = length $letterString;  
         # Save the number of characters we have to generate.  
         my $charsLeft = $chosenPattern;  
         # Loop until the return variable is full.  
         while ($charsLeft > 0) {  
             # Generate a random position in the soruce string.  
             my $stringIndex = IntGen(0, $stringLen - 1);  
             # Compute the number of characters to pull out of the source string.  
             my $chunkSize = $stringLen - $stringIndex;  
             if ($chunkSize > $charsLeft) { $chunkSize = $charsLeft; }  
             # Stuff this chunk into the return value.  
             $retVal .= substr($letterString, $stringIndex, $chunkSize);  
             # Record the data moved.  
             $charsLeft -= $chunkSize;  
         }  
     } elsif ($chosenPattern =~ m/^P/) {  
         # Here we have a picture string. We will move through the picture one  
         # character at a time generating data.  
         for (my $i = 1; $i < length $chosenPattern; $i++) {  
             # Get this picture character.  
             my $chr = substr($chosenPattern, $i, 1);  
             # Check to see if the picture char is one we recognize.  
             if (exists $PictureTable{$chr}) {  
                 # Choose a random character from the available values for this  
                 # picture character.  
                 $retVal .= RandChar($PictureTable{$chr});  
             } else {  
                 # Copy in the picture character as a literal.  
                 $retVal .= $chr;  
             }  
         }  
     } else {  
         # Here we have neither a picture string or a letter count, so we treat  
         # the string as a literal.  
         $retVal = $chosenPattern;  
     }  
     # Return the string formed.  
     return $retVal;  
 }  
   
 =head3 DateGen  
   
 C<< my $date = DateGen($startDayOffset, $endDayOffset, $minutes); >>  
   
 Return a numeric timestamp within the specified range of days with the specified minute  
 value. The range of days is specified relevant to the current day. Thus, the call  
   
 C<< my $date = DateGen(-1, 5, 720); >>  
   
 will return a timestamp at noon (72 minutes past midnight) sometime during the week that  
 began on the preceding day. If you want a random minute of the day, simply combine with  
 a call to L</IntGen>, as follows.  
   
 C<< my $date = DateGen(-1, 5, IntGen(0, 1439)); >>  
   
 =over 4  
   
 =item startDayOffset  
   
 The earliest day that can be returned, relative to the current day.  
   
 =item endDayOffset  
   
 The latest day that can be returned, related to the current day.  
   
 =item minutes  
   
 Number of minutes into the selected day that should be used.  
   
 =back  
   
 =cut  
   
 sub DateGen {  
     # Get the parameters.  
     my ($startDayOffset, $endDayOffset, $minutes) = @_;  
     # Get midnight of the current day.  
     my $now = time();  
     my ($sec, $min, $hour) = localtime($now);  
     my $today = $now - (($hour * 60 + $min) * 60 + $sec);  
     # Compute the day we want.  
     my $newDay = IntGen($startDayOffset, $endDayOffset) * 86400 + $today;  
     # Add the minutes.  
     my $retVal = $newDay + $minutes * 60;  
     # Return the result.  
     return $retVal;  
 }  
   
 =head3 FloatGen  
   
 C<< my $number = FloatGen($min, $max); >>  
   
 Return a random floating-point number greater than or equal to the specified minimum and  
 less than the specified maximum.  
   
 =over 4  
   
 =item min  
   
 Minimum permissible value for the number returned.  
   
 =item max  
   
 Maximum permissible value for the number returned.  
   
 =item RETURN  
   
 Returns a floating-point number anywhere in the specified range.  
   
 =back  
   
 =cut  
   
 sub FloatGen {  
     # Get the parameters.  
     my ($min, $max) = @_;  
     # Generate the result.  
     my $retVal = rand($max - $min) + $min;  
     return $retVal;  
 }  
   
 =head3 ListGen  
   
 C<< my @list = ListGen($pattern, $count); >>  
   
 Return a list containing a fixed number of randomly-generated strings.  
   
 =over 4  
   
 =item pattern  
   
 A pattern (in the form expected by L</StringGen>) that should be used to generate the  
 strings in the list.  
   
 =item count  
   
 The number of list entries to generate.  
   
 =item RETURN  
   
 Returns a list consisting of the specified number of strings.  
   
 =back  
   
 =cut  
   
 sub ListGen {  
     # Get the parameters.  
     my ($pattern, $count) = @_;  
     # Generate the list.  
     my @retVal = ();  
     for (my $i = 0; $i < $count; $i++) {  
         push @retVal, StringGen($pattern);  
     }  
     # Return it.  
     return @retVal;  
 }  
   
4956  1;  1;

Legend:
Removed from v.1.47  
changed lines
  Added in v.1.78

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3