1 | ###########################################################################
|
---|
2 | #
|
---|
3 | # docprint.pm --
|
---|
4 | # A component of the Greenstone digital library software
|
---|
5 | # from the New Zealand Digital Library Project at the
|
---|
6 | # University of Waikato, New Zealand.
|
---|
7 | #
|
---|
8 | # Copyright (C) 2006 New Zealand Digital Library Project
|
---|
9 | #
|
---|
10 | # This program is free software; you can redistribute it and/or modify
|
---|
11 | # it under the terms of the GNU General Public License as published by
|
---|
12 | # the Free Software Foundation; either version 2 of the License, or
|
---|
13 | # (at your option) any later version.
|
---|
14 | #
|
---|
15 | # This program is distributed in the hope that it will be useful,
|
---|
16 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
17 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
18 | # GNU General Public License for more details.
|
---|
19 | #
|
---|
20 | # You should have received a copy of the GNU General Public License
|
---|
21 | # along with this program; if not, write to the Free Software
|
---|
22 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
23 | #
|
---|
24 | ###########################################################################
|
---|
25 |
|
---|
26 | # This is used to output an XML representation of a doc_obj - this will be
|
---|
27 | # Greenstone XML format.
|
---|
28 | # This is used by GreenstoneXMLPlugout and doc.pm
|
---|
29 |
|
---|
30 | package docprint;
|
---|
31 |
|
---|
32 | use strict;
|
---|
33 |
|
---|
34 | sub get_section_xml {
|
---|
35 |
|
---|
36 | my ($doc_obj, $section) = @_;
|
---|
37 |
|
---|
38 | my $section_ptr = $doc_obj->_lookup_section ($section);
|
---|
39 | return "" unless defined $section_ptr;
|
---|
40 |
|
---|
41 | my $all_text = "<Section>\n";
|
---|
42 | $all_text .= " <Description>\n";
|
---|
43 |
|
---|
44 | # output metadata
|
---|
45 | foreach my $data (@{$section_ptr->{'metadata'}}) {
|
---|
46 | my $escaped_value = &escape_text($data->[1]);
|
---|
47 | $all_text .= ' <Metadata name="' . $data->[0] . '">' . $escaped_value . "</Metadata>\n";
|
---|
48 | }
|
---|
49 |
|
---|
50 | $all_text .= " </Description>\n";
|
---|
51 |
|
---|
52 | # output the text
|
---|
53 | $all_text .= " <Content>";
|
---|
54 | $all_text .= &escape_text($section_ptr->{'text'});
|
---|
55 | $all_text .= "</Content>\n";
|
---|
56 |
|
---|
57 | # output all the subsections
|
---|
58 | foreach my $subsection (@{$section_ptr->{'subsection_order'}}) {
|
---|
59 | $all_text .= &get_section_xml($doc_obj, "$section.$subsection");
|
---|
60 | }
|
---|
61 |
|
---|
62 | $all_text .= "</Section>\n";
|
---|
63 |
|
---|
64 | # make sure no nasty control characters have snuck through
|
---|
65 | # (XML::Parser will barf on anything it doesn't consider to be
|
---|
66 | # valid UTF-8 text, including things like \c@, \cC etc.)
|
---|
67 | $all_text =~ s/[\x00-\x09\x0B\x0C\x0E-\x1F]//g;
|
---|
68 |
|
---|
69 | return $all_text;
|
---|
70 | }
|
---|
71 |
|
---|
72 | sub escape_text {
|
---|
73 | my ($text) = @_;
|
---|
74 | # special characters in the xml encoding
|
---|
75 | $text =~ s/&&/& &/g;
|
---|
76 | $text =~ s/&/&/g; # this has to be first...
|
---|
77 | $text =~ s/</</g;
|
---|
78 | $text =~ s/>/>/g;
|
---|
79 | $text =~ s/\"/"/g;
|
---|
80 |
|
---|
81 | return $text;
|
---|
82 | }
|
---|
83 |
|
---|
84 | 1;
|
---|