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

Diff of /Sprout/CustomAttributes.pm

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

revision 1.11, Wed Nov 29 20:28:52 2006 UTC revision 1.24, Fri Apr 27 22:17:39 2007 UTC
# Line 8  Line 8 
8      use strict;      use strict;
9      use Tracer;      use Tracer;
10      use ERDBLoad;      use ERDBLoad;
11        use Stats;
12    
13  =head1 Custom SEED Attribute Manager  =head1 Custom SEED Attribute Manager
14    
# Line 27  Line 28 
28  The actual attribute values are stored as a relationship between the attribute  The actual attribute values are stored as a relationship between the attribute
29  keys and the objects. There can be multiple values for a single key/object pair.  keys and the objects. There can be multiple values for a single key/object pair.
30    
31    =head3 Object IDs
32    
33    The object ID is normally represented as
34    
35        I<type>:I<id>
36    
37    where I<type> is the object type (C<Role>, C<Coupling>, etc.) and I<id> is
38    the actual object ID. Note that the object type must consist of only upper- and
39    lower-case letters! Thus, C<GenomeGroup> is a valid object type, but
40    C<genome_group> is not. Given that restriction, the object ID
41    
42        Family:aclame|cluster10
43    
44    would represent the FIG family C<aclame|cluster10>. For historical reasons,
45    there are three exceptions: subsystems, genomes, and features do not need
46    a type. So, for PEG 3361 of Streptomyces coelicolor A3(2), you simply code
47    
48        fig|100226.1.peg.3361
49    
50    The methods L</ParseID> and L</FormID> can be used to make this all seem
51    more consistent. Given any object ID string, L</ParseID> will convert it to an
52    object type and ID, and given any object type and ID, L</FormID> will
53    convert it to an object ID string. The attribute database is pretty
54    freewheeling about what it will allow for an ID; however, for best
55    results, the type should match an entity type from a Sprout genetics
56    database. If this rule is followed, then the database object
57    corresponding to an ID in the attribute database could be retrieved using
58    L</GetTargetObject> method.
59    
60        my $object = CustomAttributes::GetTargetObject($sprout, $idValue);
61    
62    =head3 Retrieval and Logging
63    
64  The full suite of ERDB retrieval capabilities is provided. In addition,  The full suite of ERDB retrieval capabilities is provided. In addition,
65  custom methods are provided specific to this application. To get all  custom methods are provided specific to this application. To get all
66  the values of the attribute C<essential> in a specified B<Feature>, you  the values of the attribute C<essential> in a specified B<Feature>, you
# Line 36  Line 70 
70    
71  where I<$fid> contains the ID of the desired feature.  where I<$fid> contains the ID of the desired feature.
72    
73  New attribute keys must be defined before they can be used. A web interface  Keys can be split into two pieces using the splitter value defined in the
74  is provided for this purpose.  constructor (the default is C<::>). The first piece of the key is called
75    the I<real key>. This portion of the key must be defined using the
76    web interface (C<Attributes.cgi>). The second portion of the key is called
77    the I<sub key>, and can take any value.
78    
79    Major attribute activity is recorded in a log (C<attributes.log>) in the
80    C<$FIG_Config::var> directory. The log reports the user name, time, and
81    the details of the operation. The user name will almost always be unknown,
82    the exception being when it is specified in this object's constructor
83    (see L</new>).
84    
85  =head2 FIG_Config Parameters  =head2 FIG_Config Parameters
86    
# Line 87  Line 130 
130    
131  =head3 new  =head3 new
132    
133  C<< my $attrDB = CustomAttributes->new($splitter); >>  C<< my $attrDB = CustomAttributes->new(%options); >>
134    
135  Construct a new CustomAttributes object.  Construct a new CustomAttributes object. The following options are
136    supported.
137    
138  =over 4  =over 4
139    
140  =item splitter  =item splitter
141    
142  Value to be used to split attribute values into sections in the  Value to be used to split attribute values into sections in the
143  L</Fig Replacement Methods>. The default is a double colon C<::>.  L</Fig Replacement Methods>. The default is a double colon C<::>,
144  If you do not use the replacement methods, you do not need to  and should only be overridden in extreme circumstances.
145  worry about this parameter.  
146    =item user
147    
148    Name of the current user. This will appear in the attribute log.
149    
150  =back  =back
151    
# Line 106  Line 153 
153    
154  sub new {  sub new {
155      # Get the parameters.      # Get the parameters.
156      my ($class, $splitter) = @_;      my ($class, %options) = @_;
157      # Connect to the database.      # Connect to the database.
158      my $dbh = DBKernel->new($FIG_Config::attrDbms, $FIG_Config::attrDbName,      my $dbh = DBKernel->new($FIG_Config::attrDbms, $FIG_Config::attrDbName,
159                              $FIG_Config::attrUser, $FIG_Config::attrPass,                              $FIG_Config::attrUser, $FIG_Config::attrPass,
# Line 116  Line 163 
163      my $xmlFileName = $FIG_Config::attrDBD;      my $xmlFileName = $FIG_Config::attrDBD;
164      my $retVal = ERDB::new($class, $dbh, $xmlFileName);      my $retVal = ERDB::new($class, $dbh, $xmlFileName);
165      # Store the splitter value.      # Store the splitter value.
166      $retVal->{splitter} = (defined($splitter) ? $splitter : '::');      $retVal->{splitter} = $options{splitter} || '::';
167        # Store the user name.
168        $retVal->{user} = $options{user} || '<unknown>';
169        Trace("User $retVal->{user} selected for attribute object.") if T(3);
170      # Return the result.      # Return the result.
171      return $retVal;      return $retVal;
172  }  }
# Line 131  Line 181 
181    
182  =item attributeName  =item attributeName
183    
184  Name of the attribute. It must be a valid ERDB field name, consisting entirely of  Name of the attribute (the real key). If it does not exist already, it will be created.
 letters, digits, and hyphens, with a letter at the beginning. If it does not  
 exist already, it will be created.  
185    
186  =item type  =item type
187    
# Line 160  Line 208 
208      # Get the data type hash.      # Get the data type hash.
209      my %types = ERDB::GetDataTypes();      my %types = ERDB::GetDataTypes();
210      # Validate the initial input values.      # Validate the initial input values.
211      if (! ERDB::ValidateFieldName($attributeName)) {      if ($attributeName =~ /$self->{splitter}/) {
212          Confess("Invalid attribute name \"$attributeName\" specified.");          Confess("Invalid attribute name \"$attributeName\" specified.");
213      } elsif (! $notes || length($notes) < 25) {      } elsif (! $notes || length($notes) < 25) {
214          Confess("Missing or incomplete description for $attributeName.");          Confess("Missing or incomplete description for $attributeName.");
215      } elsif (! exists $types{$type}) {      } elsif (! exists $types{$type}) {
216          Confess("Invalid data type \"$type\" for $attributeName.");          Confess("Invalid data type \"$type\" for $attributeName.");
217      } else {      } else {
218            # Create a variable to hold the action to be displayed for the log (Add or Update).
219            my $action;
220          # Okay, we're ready to begin. See if this key exists.          # Okay, we're ready to begin. See if this key exists.
221          my $attribute = $self->GetEntity('AttributeKey', $attributeName);          my $attribute = $self->GetEntity('AttributeKey', $attributeName);
222          if (defined($attribute)) {          if (defined($attribute)) {
223              # It does, so we do an update.              # It does, so we do an update.
224                $action = "Update Key";
225              $self->UpdateEntity('AttributeKey', $attributeName,              $self->UpdateEntity('AttributeKey', $attributeName,
226                                  { description => $notes, 'data-type' => $type });                                  { description => $notes, 'data-type' => $type });
227              # Detach the key from its current groups.              # Detach the key from its current groups.
228              $self->Disconnect('IsInGroup', 'AttributeKey', $attributeName);              $self->Disconnect('IsInGroup', 'AttributeKey', $attributeName);
229          } else {          } else {
230              # It doesn't, so we do an insert.              # It doesn't, so we do an insert.
231                $action = "Insert Key";
232              $self->InsertObject('AttributeKey', { id => $attributeName,              $self->InsertObject('AttributeKey', { id => $attributeName,
233                                  description => $notes, 'data-type' => $type });                                  description => $notes, 'data-type' => $type });
234          }          }
# Line 186  Line 238 
238              $self->InsertObject('IsInGroup', { 'from-link' => $attributeName,              $self->InsertObject('IsInGroup', { 'from-link' => $attributeName,
239                                                 'to-link'   => $group });                                                 'to-link'   => $group });
240          }          }
241            # Log the operation.
242            $self->LogOperation($action, $attributeName, "Group list is " . join(" ", @{$groups}));
243      }      }
244  }  }
245    
 =head3 LoadAttributeKey  
   
 C<< my $stats = $attrDB->LoadAttributeKey($keyName, $fh, $keyCol, $dataCol, %options); >>  
   
 Load the specified attribute from the specified file. The file should be a  
 tab-delimited file with internal tab and new-line characters escaped. This is  
 the typical TBL-style file used by most FIG applications. One of the columns  
 in the input file must contain the appropriate object id value and the other the  
 corresponding attribute value.  
   
 =over 4  
   
 =item keyName  
   
 Key of the attribute to load.  
   
 =item fh  
   
 Open file handle for the input file.  
   
 =item idCol  
   
 Index (0-based) of the column containing the ID field. The ID field should  
 contain the ID of an instance of the named entity.  
   
 =item dataCol  
   
 Index (0-based) of the column containing the data value field.  
   
 =item options  
   
 Hash specifying the options for this load.  
   
 =item RETURN  
   
 Returns a statistics object for the load process.  
   
 =back  
   
 The available options are as follows.  
   
 =over 4  
   
 =item erase  
   
 If TRUE, the key's values will all be erased before loading. (Doing so  
 makes for a faster load.)  
   
 =back  
   
 =cut  
   
 sub LoadAttributeKey {  
     # Get the parameters.  
     my ($self, $keyName, $fh, $idCol, $dataCol, %options) = @_;  
     # Create the return variable.  
     my $retVal = Stats->new("lineIn", "shortLine", "newObject");  
     # Compute the minimum number of fields required in each input line.  
     my $minCols = ($idCol < $dataCol ? $idCol : $idCol) + 1;  
     # Insure the attribute key exists.  
     my $found = $self->GetEntity('AttributeKey', $keyName);  
     if (! defined $found) {  
         Confess("Attribute key \"$keyName\" not found in database.");  
     } else {  
         # Erase the key's current values.  
         $self->EraseAttribute($keyName);  
         # Save a list of the object IDs we need to add.  
         my %objectIDs = ();  
         # Loop through the input file.  
         while (! eof $fh) {  
             # Get the next line of the file.  
             my @fields = Tracer::GetLine($fh);  
             $retVal->Add(lineIn => 1);  
             # Now we need to validate the line.  
             if (scalar(@fields) < $minCols) {  
                 $retVal->Add(shortLine => 1);  
             } else {  
                 # It's valid, so get the ID and value.  
                 my ($id, $value) = ($fields[$idCol], $fields[$dataCol]);  
                 # Denote we're using this input line.  
                 $retVal->Add(lineUsed => 1);  
                 # Now the fun begins. Find out if we need to create a target object record for this object ID.  
                 if (! exists $objectIDs{$id}) {  
                     my $found = $self->Exists('TargetObject', $id);  
                     if (! $found) {  
                         $self->InsertObject('TargetObject', { id => $id });  
                     }  
                     $objectIDs{$id} = 1;  
                     $retVal->Add(newObject => 1);  
                 }  
                 # Now we insert the attribute.  
                 $self->InsertObject('HasValueFor', { from => $keyName, to => $id, value => $value });  
                 $retVal->Add(newValue => 1);  
             }  
         }  
     }  
     # Return the statistics.  
     return $retVal;  
 }  
   
246    
247  =head3 DeleteAttributeKey  =head3 DeleteAttributeKey
248    
# Line 315  Line 269 
269      my ($self, $attributeName) = @_;      my ($self, $attributeName) = @_;
270      # Delete the attribute key.      # Delete the attribute key.
271      my $retVal = $self->Delete('AttributeKey', $attributeName);      my $retVal = $self->Delete('AttributeKey', $attributeName);
272        # Log this operation.
273        $self->LogOperation("Delete Key", $attributeName, "Key will no longer be available for use by anyone.");
274      # Return the result.      # Return the result.
275      return $retVal;      return $retVal;
276    
# Line 413  Line 369 
369                             $cgi->td($cgi->checkbox_group(-name=>'groups',                             $cgi->td($cgi->checkbox_group(-name=>'groups',
370                                      -values=> \@groups))                                      -values=> \@groups))
371                            );                            );
372      # If the user wants to upload new values for the field, then we have      # Now the four buttons: STORE, SHOW, ERASE, and DELETE.
     # an upload file name and column indicators.  
     push @retVal, $cgi->Tr($cgi->th("Upload Values"),  
                            $cgi->td($cgi->filefield(-name => 'newValueFile',  
                                                     -size => 20) .  
                                     " Key&nbsp;" .  
                                     $cgi->textfield(-name => 'keyCol',  
                                                     -size => 3,  
                                                     -default => 0) .  
                                     " Value&nbsp;" .  
                                     $cgi->textfield(-name => 'valueCol',  
                                                     -size => 3,  
                                                     -default => 1)  
                                    ),  
                           );  
     # Now the three buttons: STORE, SHOW, and DELETE.  
373      push @retVal, $cgi->Tr($cgi->th("&nbsp;"),      push @retVal, $cgi->Tr($cgi->th("&nbsp;"),
374                             $cgi->td({align => 'center'},                             $cgi->td({align => 'center'}, join(" ",
375                                      $cgi->submit(-name => 'Delete', -value => 'DELETE') . " " .                                      $cgi->submit(-name => 'Delete', -value => 'DELETE'),
376                                      $cgi->submit(-name => 'Store',  -value => 'STORE') . " " .                                      $cgi->submit(-name => 'Store',  -value => 'STORE'),
377                                        $cgi->submit(-name => 'Erase',  -value => 'ERASE'),
378                                      $cgi->submit(-name => 'Show',   -value => 'SHOW')                                      $cgi->submit(-name => 'Show',   -value => 'SHOW')
379                                     )                                     ))
380                            );                            );
381      # Close the table and the form.      # Close the table and the form.
382      push @retVal, $cgi->end_table();      push @retVal, $cgi->end_table();
# Line 445  Line 387 
387  =head3 LoadAttributesFrom  =head3 LoadAttributesFrom
388    
389  C<< my $stats = $attrDB->LoadAttributesFrom($fileName, %options); >>  C<< my $stats = $attrDB->LoadAttributesFrom($fileName, %options); >>
390    s
391  Load attributes from the specified tab-delimited file. Each line of the file must  Load attributes from the specified tab-delimited file. Each line of the file must
392  contain an object ID in the first column, an attribute key name in the second  contain an object ID in the first column, an attribute key name in the second
393  column, and attribute values in the remaining columns. The attribute values will  column, and attribute values in the remaining columns. The attribute values will
394  be assembled into a single value using the splitter code.  be assembled into a single value using the splitter code. In addition, the key names may
395    contain a splitter. If this is the case, the portion of the key after the splitter is
396    treated as a subkey.
397    
398  =over 4  =over 4
399    
400  =item fileName  =item fileName
401    
402  Name of the file from which to load the attributes.  Name of the file from which to load the attributes, or an open handle for the file.
403    (This last enables the method to be used in conjunction with the CGI form upload
404    control.)
405    
406  =item options  =item options
407    
# Line 476  Line 422 
422  If TRUE, then the attributes will be appended to existing data; otherwise, the  If TRUE, then the attributes will be appended to existing data; otherwise, the
423  first time a key name is encountered, it will be erased.  first time a key name is encountered, it will be erased.
424    
425    =item archive
426    
427    If specified, the name of a file into which the incoming data file should be saved.
428    
429    =item objectType
430    
431    If specified, the specified object type will be prefixed to each object ID.
432    
433  =back  =back
434    
435  =cut  =cut
# Line 489  Line 443 
443      my $append = ($options{append} ? 1 : 0);      my $append = ($options{append} ? 1 : 0);
444      # Create a hash of key names found.      # Create a hash of key names found.
445      my %keyHash = ();      my %keyHash = ();
446      # Open the file for input.      # Open the file for input. Note we must anticipate the possibility of an
447      my $fh = Open(undef, "<$fileName");      # open filehandle being passed in.
448        my $fh;
449        if (ref $fileName) {
450            Trace("Using file opened by caller.") if T(3);
451            $fh = $fileName;
452        } else {
453            Trace("Attributes will be loaded from $fileName.") if T(3);
454            $fh = Open(undef, "<$fileName");
455        }
456        # Now check to see if we need to archive.
457        my $ah;
458        if ($options{archive}) {
459            $ah = Open(undef, ">$options{archive}");
460            Trace("Load file will be archived to $options{archive}.") if T(3);
461        }
462        # Finally, open a database transaction.
463        $self->BeginTran();
464        # Insure we recover from errors. If an error occurs, we will delete the archive file and
465        # roll back the updates.
466        eval {
467      # Loop through the file.      # Loop through the file.
468      while (! eof $fh) {      while (! eof $fh) {
469                # Read the current line.
470          my ($id, $key, @values) = Tracer::GetLine($fh);          my ($id, $key, @values) = Tracer::GetLine($fh);
471          $retVal->Add(linesIn => 1);          $retVal->Add(linesIn => 1);
472                # Check to see if we need to fix up the object ID.
473                if ($options{objectType}) {
474                    $id = "$options{objectType}:$id";
475                }
476                # Archive the line (if necessary).
477                if (defined $ah) {
478                    Tracer::PutLine($ah, [$id, $key, @values]);
479                }
480          # Do some validation.          # Do some validation.
481          if (! defined($id)) {              if (! $id) {
482              # We ignore blank lines.              # We ignore blank lines.
483              $retVal->Add(blankLines => 1);              $retVal->Add(blankLines => 1);
484                } elsif (substr($id, 0, 1) eq '#') {
485                    # A line beginning with a pound sign is a comment.
486                    $retVal->Add(comments => 1);
487          } elsif (! defined($key)) {          } elsif (! defined($key)) {
488              # An ID without a key is a serious error.              # An ID without a key is a serious error.
489              my $lines = $retVal->Ask('linesIn');              my $lines = $retVal->Ask('linesIn');
490              Confess("Line $lines in $fileName has no attribute key.");              Confess("Line $lines in $fileName has no attribute key.");
491                } elsif (! @values) {
492                    # A line with no values is not allowed.
493                    my $lines = $retVal->Ask('linesIn');
494                    Trace("Line $lines for key $key has no attribute values.") if T(1);
495                    $retVal->Add(skipped => 1);
496          } else {          } else {
497                    # The key contains a real part and an optional sub-part. We need the real part.
498                    my ($realKey, $subKey) = $self->SplitKey($key);
499              # Now we need to check for a new key.              # Now we need to check for a new key.
500              if (! exists $keyHash{$key}) {                  if (! exists $keyHash{$realKey}) {
501                  # This is a new key. Verify that it exists.                      if (! $self->Exists('AttributeKey', $realKey)) {
                 if (! $self->Exists('AttributeKey', $key)) {  
502                      my $line = $retVal->Ask('linesIn');                      my $line = $retVal->Ask('linesIn');
503                      Confess("Attribute \"$key\" on line $line of $fileName not found in database.");                          Confess("Attribute \"$realKey\" on line $line of $fileName not found in database.");
504                  } else {                  } else {
505                      # Make sure we know this is no longer a new key.                      # Make sure we know this is no longer a new key.
506                      $keyHash{$key} = 1;                          $keyHash{$realKey} = 1;
507                      $retVal->Add(keys => 1);                      $retVal->Add(keys => 1);
508                      # If this is NOT append mode, erase the key.                      # If this is NOT append mode, erase the key.
509                      if (! $append) {                      if (! $append) {
510                          $self->EraseAttribute($key);                              $self->EraseAttribute($realKey);
511                      }                      }
512                  }                  }
513                  Trace("Key $key found.") if T(3);                      Trace("Key $realKey found.") if T(3);
514              }              }
515              # Now we know the key is valid. Add this value.                  # Everything is all set up, so add the value.
516              $self->AddAttribute($id, $key, @values);              $self->AddAttribute($id, $key, @values);
517              my $progress = $retVal->Add(values => 1);              my $progress = $retVal->Add(values => 1);
518              Trace("$progress values loaded.") if T(3) && ($progress % 1000 == 0);              Trace("$progress values loaded.") if T(3) && ($progress % 1000 == 0);
519                }
520            }
521        };
522        # Check for an error.
523        if ($@) {
524            # Here we have an error. Roll back the transaction and delete the archive file.
525            my $message = $@;
526            Trace("Rolling back attribute updates due to error.") if T(1);
527            $self->RollbackTran();
528            if (defined $ah) {
529                Trace("Deleting archive file $options{archive}.") if T(1);
530                close $ah;
531                unlink $options{archive};
532            }
533            Confess("Error during attribute load: $message");
534        } else {
535            # Here the load worked. Commit the transaction and close the archive file.
536            Trace("Committing attribute upload.") if T(2);
537            $self->CommitTran();
538            if (defined $ah) {
539                Trace("Closing archive file $options{archive}.") if T(2);
540                close $ah;
541            }
542        }
543        # Return the result.
544        return $retVal;
545    }
546    
547    =head3 BackupKeys
548    
549    C<< my $stats = $attrDB->BackupKeys($fileName, %options); >>
550    
551    Backup the attribute key information from the attribute database.
552    
553    =over 4
554    
555    =item fileName
556    
557    Name of the output file.
558    
559    =item options
560    
561    Options for modifying the backup process.
562    
563    =item RETURN
564    
565    Returns a statistics object for the backup.
566    
567    =back
568    
569    Currently there are no options. The backup is straight to a text file in
570    tab-delimited format. Each key is backup up to two lines. The first line
571    is all of the data from the B<AttributeKey> table. The second is a
572    tab-delimited list of all the groups.
573    
574    =cut
575    
576    sub BackupKeys {
577        # Get the parameters.
578        my ($self, $fileName, %options) = @_;
579        # Declare the return variable.
580        my $retVal = Stats->new();
581        # Open the output file.
582        my $fh = Open(undef, ">$fileName");
583        # Set up to read the keys.
584        my $keyQuery = $self->Get(['AttributeKey'], "", []);
585        # Loop through the keys.
586        while (my $keyData = $keyQuery->Fetch()) {
587            $retVal->Add(key => 1);
588            # Get the fields.
589            my ($id, $type, $description) = $keyData->Values(['AttributeKey(id)', 'AttributeKey(data-type)',
590                                                              'AttributeKey(description)']);
591            # Escape any tabs or new-lines in the description.
592            my $escapedDescription = Tracer::Escape($description);
593            # Write the key data to the output.
594            Tracer::PutLine($fh, [$id, $type, $escapedDescription]);
595            # Get the key's groups.
596            my @groups = $self->GetFlat(['IsInGroup'], "IsInGroup(from-link) = ?", [$id],
597                                        'IsInGroup(to-link)');
598            $retVal->Add(memberships => scalar(@groups));
599            # Write them to the output. Note we put a marker at the beginning to insure the line
600            # is nonempty.
601            Tracer::PutLine($fh, ['#GROUPS', @groups]);
602        }
603        # Log the operation.
604        $self->LogOperation("Backup Keys", $fileName, $retVal->Display());
605        # Return the result.
606        return $retVal;
607    }
608    
609    =head3 RestoreKeys
610    
611    C<< my $stats = $attrDB->RestoreKeys($fileName, %options); >>
612    
613    Restore the attribute keys and groups from a backup file.
614    
615    =over 4
616    
617    =item fileName
618    
619    Name of the file containing the backed-up keys. Each key has a pair of lines,
620    one containing the key data and one listing its groups.
621    
622    =back
623    
624    =cut
625    
626    sub RestoreKeys {
627        # Get the parameters.
628        my ($self, $fileName, %options) = @_;
629        # Declare the return variable.
630        my $retVal = Stats->new();
631        # Set up a hash to hold the group IDs.
632        my %groups = ();
633        # Open the file.
634        my $fh = Open(undef, "<$fileName");
635        # Loop until we're done.
636        while (! eof $fh) {
637            # Get a key record.
638            my ($id, $dataType, $description) = Tracer::GetLine($fh);
639            if ($id eq '#GROUPS') {
640                Confess("Group record found when key record expected.");
641            } elsif (! defined($description)) {
642                Confess("Invalid format found for key record.");
643            } else {
644                $retVal->Add("keyIn" => 1);
645                # Add this key to the database.
646                $self->InsertObject('AttributeKey', { id => $id, 'data-type' => $dataType,
647                                                      description => Tracer::UnEscape($description) });
648                Trace("Attribute $id stored.") if T(3);
649                # Get the group line.
650                my ($marker, @groups) = Tracer::GetLine($fh);
651                if (! defined($marker)) {
652                    Confess("End of file found where group record expected.");
653                } elsif ($marker ne '#GROUPS') {
654                    Confess("Group record not found after key record.");
655                } else {
656                    $retVal->Add(memberships => scalar(@groups));
657                    # Connect the groups.
658                    for my $group (@groups) {
659                        # Find out if this is a new group.
660                        if (! $groups{$group}) {
661                            $retVal->Add(newGroup => 1);
662                            # Add the group.
663                            $self->InsertObject('AttributeGroup', { id => $group });
664                            Trace("Group $group created.") if T(3);
665                            # Make sure we know it's not new.
666                            $groups{$group} = 1;
667                        }
668                        # Connect the group to our key.
669                        $self->InsertObject('IsInGroup', { 'from-link' => $id, 'to-link' => $group });
670                    }
671                    Trace("$id added to " . scalar(@groups) . " groups.") if T(3);
672                }
673            }
674          }          }
675        # Log the operation.
676        $self->LogOperation("Backup Keys", $fileName, $retVal->Display());
677        # Return the result.
678        return $retVal;
679      }      }
680    
681    =head3 ArchiveFileName
682    
683    C<< my $fileName = $ca->ArchiveFileName(); >>
684    
685    Compute a file name for archiving attribute input data. The file will be in the attribute log directory
686    
687    =cut
688    
689    sub ArchiveFileName {
690        # Get the parameters.
691        my ($self) = @_;
692        # Declare the return variable.
693        my $retVal;
694        # We start by turning the timestamp into something usable as a file name.
695        my $now = Tracer::Now();
696        $now =~ tr/ :\//___/;
697        # Next we get the directory name.
698        my $dir = "$FIG_Config::var/attributes";
699        if (! -e $dir) {
700            Trace("Creating attribute file directory $dir.") if T(1);
701            mkdir $dir;
702        }
703        # Put it together with the field name and the time stamp.
704        $retVal = "$dir/upload.$now";
705        # Modify the file name to insure it's unique.
706        my $seq = 0;
707        while (-e "$retVal.$seq.tbl") { $seq++ }
708        # Use the computed sequence number to get the correct file name.
709        $retVal .= ".$seq.tbl";
710      # Return the result.      # Return the result.
711      return $retVal;      return $retVal;
712  }  }
# Line 568  Line 747 
747      my @keys = $self->GetFlat(['AttributeKey'], "", [], 'AttributeKey(id)');      my @keys = $self->GetFlat(['AttributeKey'], "", [], 'AttributeKey(id)');
748      Trace(scalar(@keys) . " keys found during backup.") if T(2);      Trace(scalar(@keys) . " keys found during backup.") if T(2);
749      # Open the file for output.      # Open the file for output.
750      my $fh = Open(undef, $fileName);      my $fh = Open(undef, ">$fileName");
751      # Loop through the keys.      # Loop through the keys.
752      for my $key (@keys) {      for my $key (@keys) {
753          Trace("Backing up attribute $key.") if T(3);          Trace("Backing up attribute $key.") if T(3);
754          $retVal->Add(keys => 1);          $retVal->Add(keys => 1);
755          # Loop through this key's values.          # Loop through this key's values.
756          my $query = $self->Get(['HasValueFor'], "HasValueFor(to-link) = ?", [$key]);          my $query = $self->Get(['HasValueFor'], "HasValueFor(from-link) = ?", [$key]);
757          my $valuesFound = 0;          my $valuesFound = 0;
758          while (my $line = $query->Fetch()) {          while (my $line = $query->Fetch()) {
759              $valuesFound++;              $valuesFound++;
760              # Get this row's data.              # Get this row's data.
761              my @row = $line->Values(['HasValueFor(from-link)', 'HasValueFor(to-link)',              my ($id, $key, $subKey, $value) = $line->Values(['HasValueFor(to-link)',
762                                                                 'HasValueFor(from-link)',
763                                                                 'HasValueFor(subkey)',
764                                       'HasValueFor(value)']);                                       'HasValueFor(value)']);
765                # Check for a subkey.
766                if ($subKey ne '') {
767                    $key = "$key$self->{splitter}$subKey";
768                }
769              # Write it to the file.              # Write it to the file.
770              Tracer::PutLine($fh, \@row);              Tracer::PutLine($fh, [$id, $key, $value]);
771          }          }
772          Trace("$valuesFound values backed up for key $key.") if T(3);          Trace("$valuesFound values backed up for key $key.") if T(3);
773          $retVal->Add(values => $valuesFound);          $retVal->Add(values => $valuesFound);
774      }      }
775        # Log the operation.
776        $self->LogOperation("Backup Data", $fileName, $retVal->Display());
777      # Return the result.      # Return the result.
778      return $retVal;      return $retVal;
779  }  }
# Line 851  Line 1038 
1038      return %retVal;      return %retVal;
1039  }  }
1040    
1041    =head3 LogOperation
1042    
1043    C<< $ca->LogOperation($action, $target, $description); >>
1044    
1045    Write an operation description to the attribute activity log (C<$FIG_Config::var/attributes.log>).
1046    
1047    =over 4
1048    
1049    =item action
1050    
1051    Action being logged (e.g. C<Delete Group> or C<Load Key>).
1052    
1053    =item target
1054    
1055    ID of the key or group affected.
1056    
1057    =item description
1058    
1059    Short description of the action.
1060    
1061    =back
1062    
1063    =cut
1064    
1065    sub LogOperation {
1066        # Get the parameters.
1067        my ($self, $action, $target, $description) = @_;
1068        # Get the user ID.
1069        my $user = $self->{user};
1070        # Get a timestamp.
1071        my $timeString = Tracer::Now();
1072        # Open the log file for appending.
1073        my $oh = Open(undef, ">>$FIG_Config::var/attributes.log");
1074        # Write the data to it.
1075        Tracer::PutLine($oh, [$timeString, $user, $action, $target, $description]);
1076        # Close the log file.
1077        close $oh;
1078    }
1079    
1080    =head2 Internal Utility Methods
1081    
1082    =head3 _KeywordString
1083    
1084    C<< my $keywordString = $ca->_KeywordString($key, $value); >>
1085    
1086    Compute the keyword string for a specified key/value pair. This consists of the
1087    key name and value converted to lower case with underscores translated to spaces.
1088    
1089    This method is for internal use only. It is called whenever we need to update or
1090    insert a B<HasValueFor> record.
1091    
1092    =over 4
1093    
1094    =item key
1095    
1096    Name of the relevant attribute key.
1097    
1098    =item target
1099    
1100    ID of the target object to which this key/value pair will be associated.
1101    
1102    =item value
1103    
1104    The value to store for this key/object combination.
1105    
1106    =item RETURN
1107    
1108    Returns the value that should be stored as the keyword string for the specified
1109    key/value pair.
1110    
1111    =back
1112    
1113    =cut
1114    
1115    sub _KeywordString {
1116        # Get the parameters.
1117        my ($self, $key, $value) = @_;
1118        # Get a copy of the key name and convert underscores to spaces.
1119        my $keywordString = $key;
1120        $keywordString =~ s/_/ /g;
1121        # Add the value convert it all to lower case.
1122        my $retVal = lc "$keywordString $value";
1123        # Return the result.
1124        return $retVal;
1125    }
1126    
1127    =head3 _QueryResults
1128    
1129    C<< my @attributeList = $attrDB->_QueryResults($query, @values); >>
1130    
1131    Match the results of a B<HasValueFor> query against value criteria and return
1132    the results. This is an internal method that splits the values coming back
1133    and matches the sections against the specified section patterns. It serves
1134    as the back end to L</GetAttributes> and L</FindAttributes>.
1135    
1136    =over 4
1137    
1138    =item query
1139    
1140    A query object that will return the desired B<HasValueFor> records.
1141    
1142    =item values
1143    
1144    List of the desired attribute values, section by section. If C<undef>
1145    or an empty string is specified, all values in that section will match. A
1146    generic match can be requested by placing a percent sign (C<%>) at the end.
1147    In that case, all values that match up to and not including the percent sign
1148    will match. You may also specify a regular expression enclosed
1149    in slashes. All values that match the regular expression will be returned. For
1150    performance reasons, only values have this extra capability.
1151    
1152    =item RETURN
1153    
1154    Returns a list of tuples. The first element in the tuple is an object ID, the
1155    second is an attribute key, and the remaining elements are the sections of
1156    the attribute value. All of the tuples will match the criteria set forth in
1157    the parameter list.
1158    
1159    =back
1160    
1161    =cut
1162    
1163    sub _QueryResults {
1164        # Get the parameters.
1165        my ($self, $query, @values) = @_;
1166        # Declare the return value.
1167        my @retVal = ();
1168        # Get the number of value sections we have to match.
1169        my $sectionCount = scalar(@values);
1170        # Loop through the assignments found.
1171        while (my $row = $query->Fetch()) {
1172            # Get the current row's data.
1173            my ($id, $realKey, $subKey, $valueString) = $row->Values(['HasValueFor(to-link)',
1174                                                                      'HasValueFor(from-link)',
1175                                                                      'HasValueFor(subkey)',
1176                                                                      'HasValueFor(value)'
1177                                                                    ]);
1178            # Form the key from the real key and the sub key.
1179            my $key = $self->JoinKey($realKey, $subKey);
1180            # Break the value into sections.
1181            my @sections = split($self->{splitter}, $valueString);
1182            # Match each section against the incoming values. We'll assume we're
1183            # okay unless we learn otherwise.
1184            my $matching = 1;
1185            for (my $i = 0; $i < $sectionCount && $matching; $i++) {
1186                # We need to check to see if this section is generic.
1187                my $value = $values[$i];
1188                Trace("Current value pattern is \"$value\".") if T(4);
1189                if (substr($value, -1, 1) eq '%') {
1190                    Trace("Generic match used.") if T(4);
1191                    # Here we have a generic match.
1192                    my $matchLen = length($values[$i]) - 1;
1193                    $matching = substr($sections[$i], 0, $matchLen) eq
1194                                substr($values[$i], 0, $matchLen);
1195                } elsif ($value =~ m#^/(.+)/[a-z]*$#) {
1196                    Trace("Regular expression detected.") if T(4);
1197                    # Here we have a regular expression match.
1198                    my $section = $sections[$i];
1199                    $matching = eval("\$section =~ $value");
1200                } else {
1201                    # Here we have a strict match.
1202                    Trace("Strict match used.") if T(4);
1203                    $matching = ($sections[$i] eq $values[$i]);
1204                }
1205            }
1206            # If we match, output this row to the return list.
1207            if ($matching) {
1208                push @retVal, [$id, $key, @sections];
1209            }
1210        }
1211        # Return the rows found.
1212        return @retVal;
1213    }
1214    
1215  =head2 FIG Method Replacements  =head2 FIG Method Replacements
1216    
1217  The following methods are used by B<FIG.pm> to replace the previous attribute functionality.  The following methods are used by B<FIG.pm> to replace the previous attribute functionality.
# Line 862  Line 1223 
1223  The idea is that these methods represent attribute manipulation allowed by all users, while  The idea is that these methods represent attribute manipulation allowed by all users, while
1224  the others are only for privileged users with access to the attribute server.  the others are only for privileged users with access to the attribute server.
1225    
1226  In the previous implementation, an attribute had a value and a URL. In the new implementation,  In the previous implementation, an attribute had a value and a URL. In this implementation,
1227  there is only a value. In this implementation, each attribute has only a value. These  each attribute has only a value. These methods will treat the value as a list with the individual
1228  methods will treat the value as a list with the individual elements separated by the  elements separated by the value of the splitter parameter on the constructor (L</new>). The default
1229  value of the splitter parameter on the constructor (L</new>). The default is double  is double colons C<::>.
 colons C<::>.  
1230    
1231  So, for example, an old-style keyword with a value of C<essential> and a URL of  So, for example, an old-style keyword with a value of C<essential> and a URL of
1232  C<http://www.sciencemag.org/cgi/content/abstract/293/5538/2266> using the default  C<http://www.sciencemag.org/cgi/content/abstract/293/5538/2266> using the default
# Line 918  Line 1278 
1278  which has no wildcard in the key or the object ID, may return multiple tuples.  which has no wildcard in the key or the object ID, may return multiple tuples.
1279    
1280  Value matching in this system works very poorly, because of the way multiple values are  Value matching in this system works very poorly, because of the way multiple values are
1281  stored. For the object ID and key name, we create queries that filter for the desired  stored. For the object ID, key name, and first value, we create queries that filter for the
1282  results. For the values, we do a comparison after the attributes are retrieved from the  desired results. On any filtering by value, we must do a comparison after the attributes are
1283  database. As a result, queries in which filter only on value end up reading the entire  retrieved from the database, since the database has no notion of the multiple values, which
1284  attribute table to find the desired results.  are stored in a single string. As a result, queries in which filter only on value end up
1285    reading a lot more than they need to.
1286    
1287  =over 4  =over 4
1288    
# Line 945  Line 1306 
1306  or an empty string is specified, all values in that section will match. A  or an empty string is specified, all values in that section will match. A
1307  generic match can be requested by placing a percent sign (C<%>) at the end.  generic match can be requested by placing a percent sign (C<%>) at the end.
1308  In that case, all values that match up to and not including the percent sign  In that case, all values that match up to and not including the percent sign
1309  will match.  will match. You may also specify a regular expression enclosed
1310    in slashes. All values that match the regular expression will be returned. For
1311    performance reasons, only values have this extra capability.
1312    
1313  =item RETURN  =item RETURN
1314    
# Line 961  Line 1324 
1324  sub GetAttributes {  sub GetAttributes {
1325      # Get the parameters.      # Get the parameters.
1326      my ($self, $objectID, $key, @values) = @_;      my ($self, $objectID, $key, @values) = @_;
1327      # We will create one big honking query. The following hash will build the filter      # This hash will map "HasValueFor" fields to patterns. We use it to build the
1328      # clause and a parameter list.      # SQL statement.
1329      my %data = ('HasValueFor(from-link)' => $key, 'HasValueFor(to-link)' => $objectID);      my %data;
1330        # Before we do anything else, we must parse the key. The key is treated by the
1331        # user as a single field, but to us it's actually a real key and a subkey.
1332        # If the key has no splitter and is exact, the real key is the original key
1333        # and the subkey is an empty string. If the key has a splitter, it is
1334        # split into two pieces and each piece is processed separately. If the key has
1335        # no splitter and is generic, the real key is the incoming key and the subkey
1336        # is allowed to be wild. Of course, this only matters if an actual key has
1337        # been specified.
1338        if (defined $key) {
1339            if ($key =~ /$self->{splitter}/) {
1340                # Here we have a two-part key, so we split it normally.
1341                my ($realKey, $subKey) = $self->SplitKey($key);
1342                $data{'HasValueFor(from-link)'} = $realKey;
1343                $data{'HasValueFor(subkey)'} = $subKey;
1344            } elsif (substr($key, -1, 1) eq '%') {
1345                $data{'HasValueFor(from-link)'} = $key;
1346            } else {
1347                $data{'HasValueFor(from-link)'} = $key;
1348                $data{'HasValueFor(subkey)'} = '';
1349            }
1350        }
1351        # Add the object ID to the key information.
1352        $data{'HasValueFor(to-link)'} = $objectID;
1353        # The first value represents a problem, because we can search it using SQL, but not
1354        # in the normal way. If the user specifies a generic search or exact match for
1355        # every alternative value (remember, the values may be specified as a list),
1356        # then we can create SQL filtering for it. If any of the values are specified
1357        # as a regular expression, however, that's a problem, because we need to read
1358        # every value to verify a match.
1359        if (@values > 0) {
1360            # Get the first value and put its alternatives in an array.
1361            my $valueParm = $values[0];
1362            my @valueList;
1363            if (ref $valueParm eq 'ARRAY') {
1364                @valueList = @{$valueParm};
1365            } else {
1366                @valueList = ($valueParm);
1367            }
1368            # Okay, now we have all the possible criteria for the first value in the list
1369            # @valueList. We'll copy the values to a new array in which they have been
1370            # converted to generic requests. If we find a regular-expression match
1371            # anywhere in the list, we toss the whole thing.
1372            my @valuePatterns = ();
1373            my $okValues = 1;
1374            for my $valuePattern (@valueList) {
1375                # Check the pattern type.
1376                if (substr($valuePattern, 0, 1) eq '/') {
1377                    # Regular expressions invalidate the entire process.
1378                    $okValues = 0;
1379                } elsif (substr($valuePattern, -1, 1) eq '%') {
1380                    # A Generic pattern is passed in unmodified.
1381                    push @valuePatterns, $valuePattern;
1382                } else {
1383                    # An exact match is converted to generic.
1384                    push @valuePatterns, "$valuePattern%";
1385                }
1386            }
1387            # If everything works, add the value data to the filtering hash.
1388            if ($okValues) {
1389                $data{'HasValueFor(value)'} = \@valuePatterns;
1390            }
1391        }
1392        # Create some lists to contain the filter fragments and parameter values.
1393      my @filter = ();      my @filter = ();
1394      my @parms = ();      my @parms = ();
1395      # This next loop goes through the different fields that can be specified in the      # This next loop goes through the different fields that can be specified in the
1396      # parameter list and generates filters for each.      # parameter list and generates filters for each. The %data hash that we built above
1397        # contains all the necessary information to do this.
1398      for my $field (keys %data) {      for my $field (keys %data) {
1399          # Accumulate filter information for this field. We will OR together all the          # Accumulate filter information for this field. We will OR together all the
1400          # elements accumulated to create the final result.          # elements accumulated to create the final result.
# Line 995  Line 1422 
1422                          push @fieldFilter, "$field = ?";                          push @fieldFilter, "$field = ?";
1423                          push @parms, $pattern;                          push @parms, $pattern;
1424                      } else {                      } else {
1425                          # Here we have a generate request, so we will use the LIKE operator to                          # Here we have a generic request, so we will use the LIKE operator to
1426                          # filter the field to this value pattern.                          # filter the field to this value pattern.
1427                          push @fieldFilter, "$field LIKE ?";                          push @fieldFilter, "$field LIKE ?";
1428                          # We must convert the pattern value to an SQL match pattern. First                          # We must convert the pattern value to an SQL match pattern. First
# Line 1017  Line 1444 
1444      # Now @filter contains one or more filter strings and @parms contains the parameter      # Now @filter contains one or more filter strings and @parms contains the parameter
1445      # values to bind to them.      # values to bind to them.
1446      my $actualFilter = join(" AND ", @filter);      my $actualFilter = join(" AND ", @filter);
     # Declare the return variable.  
     my @retVal = ();  
     # Get the number of value sections we have to match.  
     my $sectionCount = scalar(@values);  
1447      # Now we're ready to make our query.      # Now we're ready to make our query.
1448      my $query = $self->Get(['HasValueFor'], $actualFilter, \@parms);      my $query = $self->Get(['HasValueFor'], $actualFilter, \@parms);
1449      # Loop through the assignments found.      # Format the results.
1450      while (my $row = $query->Fetch()) {      my @retVal = $self->_QueryResults($query, @values);
         # Get the current row's data.  
         my ($id, $key, $valueString) = $row->Values(['HasValueFor(to-link)', 'HasValueFor(from-link)',  
                                                       'HasValueFor(value)']);  
         # Break the value into sections.  
         my @sections = split($self->{splitter}, $valueString);  
         # Match each section against the incoming values. We'll assume we're  
         # okay unless we learn otherwise.  
         my $matching = 1;  
         for (my $i = 0; $i < $sectionCount && $matching; $i++) {  
             # We need to check to see if this section is generic.  
             if (substr($values[$i], -1, 1) eq '%') {  
                 my $matchLen = length($values[$i] - 1);  
                 $matching = substr($sections[$i], 0, $matchLen) eq  
                             substr($values[$i], 0, $matchLen);  
             } else {  
                 $matching = ($sections[$i] eq $values[$i]);  
             }  
         }  
         # If we match, output this row to the return list.  
         if ($matching) {  
             push @retVal, [$id, $key, @sections];  
         }  
     }  
1451      # Return the rows found.      # Return the rows found.
1452      return @retVal;      return @retVal;
1453  }  }
# Line 1093  Line 1493 
1493          # Okay, now we have some reason to believe we can do this. Form the values          # Okay, now we have some reason to believe we can do this. Form the values
1494          # into a scalar.          # into a scalar.
1495          my $valueString = join($self->{splitter}, @values);          my $valueString = join($self->{splitter}, @values);
1496            # Split up the key.
1497            my ($realKey, $subKey) = $self->SplitKey($key);
1498          # Connect the object to the key.          # Connect the object to the key.
1499          $self->InsertObject('HasValueFor', { 'from-link' => $key,          $self->InsertObject('HasValueFor', { 'from-link' => $realKey,
1500                                               'to-link'   => $objectID,                                               'to-link'   => $objectID,
1501                                                 'subkey'    => $subKey,
1502                                               'value'     => $valueString,                                               'value'     => $valueString,
1503                                         });                                         });
1504      }      }
# Line 1136  Line 1539 
1539          Confess("No object ID specified for DeleteAttribute call.");          Confess("No object ID specified for DeleteAttribute call.");
1540      } elsif (! defined($key)) {      } elsif (! defined($key)) {
1541          Confess("No attribute key specified for DeleteAttribute call.");          Confess("No attribute key specified for DeleteAttribute call.");
1542      } elsif (scalar(@values) == 0) {      } else {
1543          # Here we erase the entire key.          # Split the key into the real key and the subkey.
1544          $self->EraseAttribute($key);          my ($realKey, $subKey) = $self->SplitKey($key);
1545            if ($subKey eq '' && scalar(@values) == 0) {
1546                # Here we erase the entire key for this object.
1547                $self->DeleteRow('HasValueFor', $key, $objectID);
1548      } else {      } else {
1549          # Here we erase the matching values.          # Here we erase the matching values.
1550          my $valueString = join($self->{splitter}, @values);          my $valueString = join($self->{splitter}, @values);
1551          $self->DeleteRow('HasValueFor', $key, $objectID, { value => $valueString });              $self->DeleteRow('HasValueFor', $realKey, $objectID,
1552                                 { subkey => $subKey, value => $valueString });
1553            }
1554      }      }
1555      # Return a one. This is for backward compatability.      # Return a one. This is for backward compatability.
1556      return 1;      return 1;
1557  }  }
1558    
1559    =head3 DeleteMatchingAttributes
1560    
1561    C<< my @deleted = $attrDB->DeleteMatchingAttributes($objectID, $key, @values); >>
1562    
1563    Delete all attributes that match the specified criteria. This is equivalent to
1564    calling L</GetAttributes> and then invoking L</DeleteAttribute> for each
1565    row found.
1566    
1567    =over 4
1568    
1569    =item objectID
1570    
1571    ID of object whose attributes are to be deleted. If the attributes for multiple
1572    objects are to be deleted, this parameter can be specified as a list reference. If
1573    attributes are to be deleted for all objects, specify C<undef> or an empty string.
1574    Finally, you can delete attributes for a range of object IDs by putting a percent
1575    sign (C<%>) at the end.
1576    
1577    =item key
1578    
1579    Attribute key name. A value of C<undef> or an empty string will match all
1580    attribute keys. If the values are to be deletedfor multiple keys, this parameter can be
1581    specified as a list reference. Finally, you can delete attributes for a range of
1582    keys by putting a percent sign (C<%>) at the end.
1583    
1584    =item values
1585    
1586    List of the desired attribute values, section by section. If C<undef>
1587    or an empty string is specified, all values in that section will match. A
1588    generic match can be requested by placing a percent sign (C<%>) at the end.
1589    In that case, all values that match up to and not including the percent sign
1590    will match. You may also specify a regular expression enclosed
1591    in slashes. All values that match the regular expression will be deleted. For
1592    performance reasons, only values have this extra capability.
1593    
1594    =item RETURN
1595    
1596    Returns a list of tuples for the attributes that were deleted, in the
1597    same form as L</GetAttributes>.
1598    
1599    =back
1600    
1601    =cut
1602    
1603    sub DeleteMatchingAttributes {
1604        # Get the parameters.
1605        my ($self, $objectID, $key, @values) = @_;
1606        # Get the matching attributes.
1607        my @retVal = $self->GetAttributes($objectID, $key, @values);
1608        # Loop through the attributes, deleting them.
1609        for my $tuple (@retVal) {
1610            $self->DeleteAttribute(@{$tuple});
1611        }
1612        # Log this operation.
1613        my $count = @retVal;
1614        $self->LogOperation("Mass Delete", $key, "$count matching attributes deleted.");
1615        # Return the deleted attributes.
1616        return @retVal;
1617    }
1618    
1619  =head3 ChangeAttribute  =head3 ChangeAttribute
1620    
1621  C<< $attrDB->ChangeAttribute($objectID, $key, \@oldValues, \@newValues); >>  C<< $attrDB->ChangeAttribute($objectID, $key, \@oldValues, \@newValues); >>
# Line 1211  Line 1679 
1679    
1680  =item key  =item key
1681    
1682  Key to erase.  Key to erase. This must be a real key; that is, it cannot have a subkey
1683    component.
1684    
1685  =back  =back
1686    
# Line 1220  Line 1689 
1689  sub EraseAttribute {  sub EraseAttribute {
1690      # Get the parameters.      # Get the parameters.
1691      my ($self, $key) = @_;      my ($self, $key) = @_;
1692      # Delete everything connected to the key. The "keepRoot" option keeps the key in the      # Delete everything connected to the key.
1693      # datanase while deleting everything attached to it.      $self->Disconnect('HasValueFor', 'AttributeKey', $key);
1694      $self->Delete('AttributeKey', $key, keepRoot => 1);      # Log the operation.
1695        $self->LogOperation("Erase Data", $key);
1696      # Return a 1, for backward compatability.      # Return a 1, for backward compatability.
1697      return 1;      return 1;
1698  }  }
# Line 1257  Line 1727 
1727      return sort @groups;      return sort @groups;
1728  }  }
1729    
1730    =head3 QueryAttributes
1731    
1732    C<< my @attributeData = $ca->QueryAttributes($filter, $filterParms); >>
1733    
1734    Return the attribute data based on an SQL filter clause. In the filter clause,
1735    the name C<$object> should be used for the object ID, C<$key> should be used for
1736    the key name, C<$subkey> for the subkey value, and C<$value> for the value field.
1737    
1738    =over 4
1739    
1740    =item filter
1741    
1742    Filter clause in the standard ERDB format, except that the field names are C<$object> for
1743    the object ID field, C<$key> for the key name field, C<$subkey> for the subkey field,
1744    and C<$value> for the value field. This abstraction enables us to hide the details of
1745    the database construction from the user.
1746    
1747    =item filterParms
1748    
1749    Parameters for the filter clause.
1750    
1751    =item RETURN
1752    
1753    Returns a list of tuples. Each tuple consists of an object ID, a key (with optional subkey), and
1754    one or more attribute values.
1755    
1756    =back
1757    
1758    =cut
1759    
1760    # This hash is used to drive the substitution process.
1761    my %AttributeParms = (object => 'HasValueFor(to-link)',
1762                          key    => 'HasValueFor(from-link)',
1763                          subkey => 'HasValueFor(subkey)',
1764                          value  => 'HasValueFor(value)');
1765    
1766    sub QueryAttributes {
1767        # Get the parameters.
1768        my ($self, $filter, $filterParms) = @_;
1769        # Declare the return variable.
1770        my @retVal = ();
1771        # Make sue we have filter parameters.
1772        my $realParms = (defined($filterParms) ? $filterParms : []);
1773        # Create the query by converting the filter.
1774        my $realFilter = $filter;
1775        for my $name (keys %AttributeParms) {
1776            $realFilter =~ s/\$$name/$AttributeParms{$name}/g;
1777        }
1778        my $query = $self->Get(['HasValueFor'], $realFilter, $realParms);
1779        # Loop through the results, forming the output attribute tuples.
1780        while (my $result = $query->Fetch()) {
1781            # Get the four values from this query result row.
1782            my ($objectID, $key, $subkey, $value) = $result->Values([$AttributeParms{object},
1783                                                                    $AttributeParms{key},
1784                                                                    $AttributeParms{subkey},
1785                                                                    $AttributeParms{value}]);
1786            # Combine the key and the subkey.
1787            my $realKey = ($subkey ? $key . $self->{splitter} . $subkey : $key);
1788            # Split the value.
1789            my @values = split $self->{splitter}, $value;
1790            # Output the result.
1791            push @retVal, [$objectID, $realKey, @values];
1792        }
1793        # Return the result.
1794        return @retVal;
1795    }
1796    
1797    =head2 Key and ID Manipulation Methods
1798    
1799    =head3 ParseID
1800    
1801    C<< my ($type, $id) = CustomAttributes::ParseID($idValue); >>
1802    
1803    Determine the type and object ID corresponding to an ID value from the attribute database.
1804    Most ID values consist of a type name and an ID, separated by a colon (e.g. C<Family:aclame|cluster10>);
1805    however, Genomes, Features, and Subsystems are not stored with a type name, so we need to
1806    deduce the type from the ID value structure.
1807    
1808    The theory here is that you can plug the ID and type directly into a Sprout database method, as
1809    follows
1810    
1811        my ($type, $id) = CustomAttributes::ParseID($attrList[$num]->[0]);
1812        my $target = $sprout->GetEntity($type, $id);
1813    
1814    =over 4
1815    
1816    =item idValue
1817    
1818    ID value taken from the attribute database.
1819    
1820    =item RETURN
1821    
1822    Returns a two-element list. The first element is the type of object indicated by the ID value,
1823    and the second element is the actual object ID.
1824    
1825    =back
1826    
1827    =cut
1828    
1829    sub ParseID {
1830        # Get the parameters.
1831        my ($idValue) = @_;
1832        # Declare the return variables.
1833        my ($type, $id);
1834        # Parse the incoming ID. We first check for the presence of an entity name. Entity names
1835        # can only contain letters, which helps to insure typed object IDs don't collide with
1836        # subsystem names (which are untyped).
1837        if ($idValue =~ /^([A-Za-z]+):(.+)/) {
1838            # Here we have a typed ID.
1839            ($type, $id) = ($1, $2);
1840        } elsif ($idValue =~ /fig\|/) {
1841            # Here we have a feature ID.
1842            ($type, $id) = (Feature => $idValue);
1843        } elsif ($idValue =~ /\d+\.\d+/) {
1844            # Here we have a genome ID.
1845            ($type, $id) = (Genome => $idValue);
1846        } else {
1847            # The default is a subsystem ID.
1848            ($type, $id) = (Subsystem => $idValue);
1849        }
1850        # Return the results.
1851        return ($type, $id);
1852    }
1853    
1854    =head3 FormID
1855    
1856    C<< my $idValue = CustomAttributes::FormID($type, $id); >>
1857    
1858    Convert an object type and ID pair into an object ID string for the attribute system. Subsystems,
1859    genomes, and features are stored in the database without type information, but all other object IDs
1860    must be prefixed with the object type.
1861    
1862    =over 4
1863    
1864    =item type
1865    
1866    Relevant object type.
1867    
1868    =item id
1869    
1870    ID of the object in question.
1871    
1872    =item RETURN
1873    
1874    Returns a string that will be recognized as an object ID in the attribute database.
1875    
1876    =back
1877    
1878    =cut
1879    
1880    sub FormID {
1881        # Get the parameters.
1882        my ($type, $id) = @_;
1883        # Declare the return variable.
1884        my $retVal;
1885        # Compute the ID string from the type.
1886        if (grep { $type eq $_ } qw(Feature Genome Subsystem)) {
1887            $retVal = $id;
1888        } else {
1889            $retVal = "$type:$id";
1890        }
1891        # Return the result.
1892        return $retVal;
1893    }
1894    
1895    =head3 GetTargetObject
1896    
1897    C<< my $object = CustomAttributes::GetTargetObject($erdb, $idValue); >>
1898    
1899    Return the database object corresponding to the specified attribute object ID. The
1900    object type associated with the ID value must correspond to an entity name in the
1901    specified database.
1902    
1903    =over 4
1904    
1905    =item erdb
1906    
1907    B<ERDB> object for accessing the target database.
1908    
1909    =item idValue
1910    
1911    ID value retrieved from the attribute database.
1912    
1913    =item RETURN
1914    
1915    Returns a B<ERDBObject> for the attribute value's target object.
1916    
1917    =back
1918    
1919    =cut
1920    
1921    sub GetTargetObject {
1922        # Get the parameters.
1923        my ($erdb, $idValue) = @_;
1924        # Declare the return variable.
1925        my $retVal;
1926        # Get the type and ID for the target object.
1927        my ($type, $id) = ParseID($idValue);
1928        # Plug them into the GetEntity method.
1929        $retVal = $erdb->GetEntity($type, $id);
1930        # Return the resulting object.
1931        return $retVal;
1932    }
1933    
1934    =head3 SplitKey
1935    
1936    C<< my ($realKey, $subKey) = $ca->SplitKey($key); >>
1937    
1938    Split an external key (that is, one passed in by a caller) into the real key and the sub key.
1939    The real and sub keys are separated by a splitter value (usually C<::>). If there is no splitter,
1940    then the sub key is presumed to be an empty string.
1941    
1942    =over 4
1943    
1944    =item key
1945    
1946    Incoming key to be split.
1947    
1948    =item RETURN
1949    
1950    Returns a two-element list, the first element of which is the real key and the second element of
1951    which is the sub key.
1952    
1953    =back
1954    
1955    =cut
1956    
1957    sub SplitKey {
1958        # Get the parameters.
1959        my ($self, $key) = @_;
1960        # Do the split.
1961        my ($realKey, $subKey) = split($self->{splitter}, $key, 2);
1962        # Insure the subkey has a value.
1963        if (! defined $subKey) {
1964            $subKey = '';
1965        }
1966        # Return the results.
1967        return ($realKey, $subKey);
1968    }
1969    
1970    =head3 JoinKey
1971    
1972    C<< my $key = $ca->JoinKey($realKey, $subKey); >>
1973    
1974    Join a real key and a subkey together to make an external key. The external key is the attribute key
1975    used by the caller. The real key and the subkey are how the keys are represented in the database. The
1976    real key is the key to the B<AttributeKey> entity. The subkey is an attribute of the B<HasValueFor>
1977    relationship.
1978    
1979    =over 4
1980    
1981    =item realKey
1982    
1983    The real attribute key.
1984    
1985    =item subKey
1986    
1987    The subordinate portion of the attribute key.
1988    
1989    =item RETURN
1990    
1991    Returns a single string representing both keys.
1992    
1993    =back
1994    
1995    =cut
1996    
1997    sub JoinKey {
1998        # Get the parameters.
1999        my ($self, $realKey, $subKey) = @_;
2000        # Declare the return variable.
2001        my $retVal;
2002        # Check for a subkey.
2003        if ($subKey eq '') {
2004            # No subkey, so the real key is the key.
2005            $retVal = $realKey;
2006        } else {
2007            # Subkey found, so the two pieces must be joined by a splitter.
2008            $retVal = "$realKey$self->{splitter}$subKey";
2009        }
2010        # Return the result.
2011        return $retVal;
2012    }
2013    
2014  1;  1;

Legend:
Removed from v.1.11  
changed lines
  Added in v.1.24

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3