###########################################################################
#
# mgbuildproc.pm -- 
# A component of the Greenstone digital library software
# from the New Zealand Digital Library Project at the 
# University of Waikato, New Zealand.
#
# Copyright (C) 1999 New Zealand Digital Library Project
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
#
###########################################################################

package niupepabuildproc;

use mgbuildproc;
use unicode;

BEGIN {
    @ISA = ('mgbuildproc');
}


sub new {
    my ($class, $collection, $source_dir, $build_dir,
	$verbosity, $outhandle) = @_;
    my $self = new mgbuildproc ();

    return bless $self, $class;
}

# We want to strip out the macrons if we're indexing the text - we then
# strip any macrons from search terms at runtime so that we'll hit all
# versions of a word, with or without macrons.

# Note that this behaviour may not be best in all cases with Maori text as
# there are examples of completely different words being spelt the same
# except for their respective macrons. For this collection it seems like
# the best solution though.
sub filter_text {
    my $self = shift(@_);
    
    if ($self->{'indexing_text'}) {
	my $unicode_array = &unicode::utf82unicode($_[1]);
	foreach my $c (@$unicode_array) {
	    if ($c == 256) {$c = ord("A");}
	    elsif ($c == 257) {$c = ord("a");}
	    elsif ($c == 274) {$c = ord("E");}
	    elsif ($c == 275) {$c = ord("e");}
	    elsif ($c == 298) {$c = ord("I");}
	    elsif ($c == 299) {$c = ord("i");}
	    elsif ($c == 332) {$c = ord("O");}
	    elsif ($c == 333) {$c = ord("o");}
	    elsif ($c == 362) {$c = ord("U");}
	    elsif ($c == 363) {$c = ord("u");}
	}
	$_[1] = &unicode::unicode2utf8($unicode_array);
    }
}

# all documents are "paged" for this collection
sub get_document_type {
    return ("Invisible", "Paged");
}

1;