view release on metacpan or  search on metacpan

lib/PBib/Document/OpenOffice.pm  view on Meta::CPAN

# --*-Perl-*-- coding: utf-8
# $Id: OpenOffice.pm 13 2004-11-27 08:58:44Z tandler $
#

=head1 NAME

PBib::Document::OpenOffice - Base Class for OpenOffice documents

=head1 SYNOPSIS

	use PBib::Document;
	my $doc = new PBib::Document(
		'filename' => 'test.sxw',
		'mode' => 'r',
		);
	print $doc->filename();
	my @paragraphs = $doc->paragraphs();
	$doc->close();

=head1 DESCRIPTION

Base class for OpenOffice documents.

All OpenOffice documents have a similar structure: They are a zip archive that contains a content.xml file with the content.

=cut

package PBib::Document::OpenOffice;
use 5.008; # for Unicode / utf-8 support
use strict;
use warnings;
use charnames ':full';	# enable \N{unicode char name} in strings
#  use English;

# for debug:
use Data::Dumper;

BEGIN {
    use vars qw($Revision $VERSION);
	my $major = 1; q$Revision: 13 $ =~ /: (\d+)/; my ($minor) = ($1); $VERSION = "$major." . ($minor<10 ? '0' : '') . $minor;
}

# superclass
use base qw(PBib::Document::XML);

# used modules
use Carp::Assert;
use Archive::Zip qw( :ERROR_CODES :CONSTANTS );

# used own modules


# module variables
#use vars qw(mmmm);

use constant {
	CONTENTNAME => 'content.xml',
	};
	
# Unicode chars, see http://www.unicode.org/charts/
my $EM_DASH = "\N{EM DASH}";				# = \x{2014}
my $EN_DASH = "\N{EN DASH}";				# = \x{2013}
my $FIG_DASH = "\N{FIGURE DASH}";			# 20 12
my $NB_HYPHEN = "\N{NON-BREAKING HYPHEN}";	# 20 11
my $HYPHEN = "\N{HYPHEN}";					# 20 10 (difference to "hypen-minus"?)
my $OPT_HYPHEN = "\N{SOFT HYPHEN}";			# 00 AD

my $LDBLQUOTE_EN = "\N{LEFT DOUBLE QUOTATION MARK}";	# 20 1C
my $RDBLQUOTE_EN = "\N{RIGHT DOUBLE QUOTATION MARK}";	# 20 1D
my $LQUOTE_EN = "\N{LEFT SINGLE QUOTATION MARK}";		# 20 18
my $RQUOTE_EN = "\N{RIGHT SINGLE QUOTATION MARK}";		# 20 19
my $LDBLQUOTE_DE = "\N{DOUBLE LOW-9 QUOTATION MARK}";	# 20 1E
# "\N{DOUBLE HIGH-REVERSED-9 QUOTATION MARK}";	# 20 1F
my $RDBLQUOTE_DE = "\N{LEFT DOUBLE QUOTATION MARK}";	# 20 1C
my $LQUOTE_DE = "\N{SINGLE LOW-9 QUOTATION MARK}";		# 20 1A
my $RQUOTE_DE = "\N{LEFT SINGLE QUOTATION MARK}";		# 20 18
# \N{SINGLE HIGH-REVERSED-9 QUOTATION MARK}		# 20 1B

my $NB_SPACE = "\N{NO-BREAK SPACE}";	# 00 A0 = \N{NBSP}
my $EM_SPACE = "\N{EM SPACE}";	# 20 03
my $EN_SPACE = "\N{EN SPACE}";	# 20 02

my $ELLIPSIS = "\{HORIZONTAL ELLIPSIS}";	# 20 26


=head1 METHODS

=cut

=head1 File Handling Methods

=over

=cut

=item $doc->zip()

Handle to Archive::Zip, used to (de)compress the OpenOffice file.

=cut

sub zip {
	my $self = shift;
	my $zip = $self->{'zip'};
	unless( $zip ) {
		my $filename = $self->filename() or return undef;
		$zip = Archive::Zip->new() or return undef;
		$self->{'zip'} = $zip;
	}
	return $zip;
}

=item $doc->close();

Close the file. Does nothing?

=cut

sub close {
# close file ... must the zip be closed???