# BioMirror/Swiss.pm

=head1 NAME

BioMirror::Swiss -- BioMirror::Data packages for SwissProt/ExPASY databanks

=cut

package BioMirror::SwissProt;
 @ISA = qw( BioMirror::Data ); 

sub new {
	my $class= shift;
	my $self = $class->SUPER::new( 
		srsdb => 'SWISSPROT',
		name => 'SWISS-PROT',
		makeflags => $BioMirror::Data::kFromArchive|$BioMirror::Data::kDoSrsIndex,

		mirror_dir =>	'$zpath/swissprot/',
		expanded_dir =>	'$dpath/swissprot/',

		dosummary => 1, 
   	source => {
   		home => 'ExPASy',
   		comment => 'Annotated protein sequence database',
   		url => 'ftp://expasy.hcuge.ch/databases/swiss-prot/release_compressed/',
   		web => 'http://www.expasy.ch/sprot/',
     	get_patt => '(README|sprot.*\.dat\.Z$|userman\.txt\.Z|relnotes\.txt\.Z)',
			local_ignore => '+Readme|update|new-seq.dat|log$',
		  recursive => 'false',
			},

		data => [
			## ? need data_pat => or such for data file regex patterns ?
			'(sprot[0-9]+.dat)=seq.dat',
			],

		docs => [ ## don't confuse w/ seq data - do we need these unexpanded?
			'relnotes.txt',
			'userman.txt',
			],

		@_ );
	return $self;
}


sub getRelease {
			# SWISS-PROT RELEASE 36.0 RELEASE NOTES   
	my $self= shift;
	my $rel= undef;
	my $df= BioMirror::replaceVars( $self->expanded_dir . 'relnotes.txt');
	# my @df= $self->getDataPathnames();
	# my $df= $df[0] . $df[1];
	my $buf= $self->readChunk($df);
	if ($buf =~ m/SWISS-PROT RELEASE ([0-9\.]+)/) {
		$rel= "$1";
		}
	return $rel;
}


#-------------

package BioMirror::SwissProtNew;
 @ISA = qw( BioMirror::SwissProt ); 

sub new {
	my $class= shift;
	my $self = $class->SUPER::new( 
		srsdb => 'SWISSNEW',
		name => 'SwissProt New data',
		makeflags => $BioMirror::Data::kFromArchive|$BioMirror::Data::kDoSrsIndex,
		mirror_dir =>	'$zpath/swissprot/updates/',
		expanded_dir =>	'$dpath/swissnew/',

		dosummary => 0, 
   	source => {
   		comment => 'SwissProt new data from ExPASy',
   		url => 'ftp://expasy.hcuge.ch/databases/swiss-prot/updates_compressed/',
   		web => 'http://www.expasy.ch/sprot/',
     	get_patt => '(new_seq\.dat\.Z$)',
     	local_ignore => '+Readme|update|new-seq.dat|log$',
		  recursive => 'false',
			},

		data => [ 'new_seq.dat', ],
		docs => [],
		@_ );
	return $self;
}
#-------------

# ## moved to EBI package to get their version of sp_tr_nrdb
# package BioMirror::TrEMBL;
#  @ISA = qw( BioMirror::SwissProt ); 
# 
# sub new {
# 	my $class= shift;
# 	my $self = $class->SUPER::new( 
# 		srsdb => 'TREMBL',
# 		name => 'TrEMBL',
# 		makeflags => $BioMirror::Data::kFromArchive|$BioMirror::Data::kDoSrsIndex,
# 		mirror_dir =>	'$zpath/trembl/',
# 		expanded_dir =>	'$dpath/trembl/',
# 
#    	source => {
#    		comment => 'TrEMBL from ExPASy',
#    		url => 'ftp://expasy.hcuge.ch/databases/sp_tr_nrdb/',
#       web => 'http://www.expasy.ch/sprot/',
#     	get_patt => '(README|trembl.*\.dat\.Z$|nrdb.txt|userman.txt.Z|relnotes.txt.Z)',
#      	local_ignore => '+Readme|update|log$',
#      	exclude_patt => '+|fasta',
# 		  recursive => 'false',
# 			},
# 
# 		data => [ 'trembl.dat', ],
# 		docs => [],
# 		@_ );
# 	return $self;
# }
# 
# 
# sub getRelease {
# 			# ???
# 	my $self= shift;
# 	my $rel= undef;
# 	my $df= BioMirror::replaceVars( $self->expanded_dir . ${$self->data}[0]);
# 	# my @df= $self->getDataPathnames(1);
# 	# my $df= $df[0] . $df[1];
# 	my $buf= $self->readChunk($df);
# 
# 	#if ($buf =~ m/SWISS-PROT RELEASE ([0-9\.]+)/) {
# 	#	$rel= "$1";
# 	#	}
# 	return $rel;
# }
# 
# #-------------
# 
# package BioMirror::TrEMBLNew;
#  @ISA = qw( BioMirror::TrEMBL ); 
# 
# sub new {
# 	my $class= shift;
# 	my $self = $class->SUPER::new( 
# 		srsdb => 'TREMBLNEW',
# 		name => 'TrEMBL new data',
# 		makeflags => $BioMirror::Data::kFromArchive|$BioMirror::Data::kDoSrsIndex,
# 
# 		sourceflags => $BioMirror::Data::kSuperSource,
# 		data => [ 'trembl_new.dat', ],
# 		@_ );
# 	return $self;
# }

#-------------

package BioMirror::Enzyme;
 @ISA = qw( BioMirror::Data ); 

sub new {
	my $class= shift;
	my $self = $class->SUPER::new( 
		srsdb => 'ENZYME',
		name => 'Enzyme',
		makeflags => $BioMirror::Data::kFromArchive|$BioMirror::Data::kDoSrsIndex,

		dosummary => 1, 
   	source => {
   		home => 'ExPASy',
   		comment => 'Enzyme nomenclature database',
   		url => 'ftp://expasy.hcuge.ch/databases/enzyme/',
   		web => 'http://www.expasy.ch/enzyme/',
			},
			
		mirror_dir =>	'$zpath/enzyme/',
		expanded_dir =>	'$dpath/enzyme/',
		data => [ 'enzyme.dat' 	],
			
		@_ );
	return $self;
}

	 ## for enzyme|prosite|prositedoc
sub getRelease { 
		##CC   Release 24.0 of January 1999
	  ##CC   Release 15.0 of July 1998 		
		## Release  : 15.0 of July 1998  		
	my $self= shift;
	my $rel= undef;
	my $df= BioMirror::replaceVars( $self->expanded_dir . ${$self->data}[0]);
	my $buf= $self->readChunk($df);
	if ($buf =~ m/Release[\s:]+([0-9\.]+) of ([0-9A-z ]+)/) {
		$rel= "$1, $2";
		}
	return $rel;
}


#-------------


package BioMirror::Prosite;
 @ISA = qw( BioMirror::Enzyme ); 

sub new {
	my $class= shift;
	my $self = $class->SUPER::new( 
		srsdb => 'PROSITE',
		name => 'Prosite',
		makeflags => $BioMirror::Data::kFromArchive|$BioMirror::Data::kDoSrsIndex,

 		dosummary => 1, 
  	source => {
  		home => 'ExPASy',
   		comment => 'Database of protein families and domains',
   		url => 'ftp://expasy.hcuge.ch/databases/prosite/',
   		web => 'http://www.expasy.ch/prosite/',
			},
			
		mirror_dir =>	'$zpath/prosite/release_with_updates',
		expanded_dir =>	'$dpath/prosite/',
		data => [ 'prosite.dat', ],
			
		@_ );
	return $self;
}

#----------------

package BioMirror::PrositeDoc;
 @ISA = qw( BioMirror::Prosite ); 

sub new {
	my $class= shift;
	my $self = $class->SUPER::new( 
		srsdb => 'PROSITEDOC',
		name => 'PrositeDoc',
		makeflags => $BioMirror::Data::kFromArchive|$BioMirror::Data::kDoSrsIndex,
 		dosummary => 0, 

		## no need to ftp source separate from Prosite...
		sourceflags => $BioMirror::Data::kSuperSource,
		
		data => [ 'prosite.doc', ],
			
		@_ );
	return $self;
}

#----------------
1;