1 | ###########################################################################
|
---|
2 | #
|
---|
3 | # ProtemixPlug.pm --
|
---|
4 | #
|
---|
5 | # A component of the Greenstone digital library software
|
---|
6 | # from the New Zealand Digital Library Project at the
|
---|
7 | # University of Waikato, New Zealand.
|
---|
8 | #
|
---|
9 | # Copyright (C) 2002 New Zealand Digital Library Project
|
---|
10 | #
|
---|
11 | # This program is free software; you can redistribute it and/or modify
|
---|
12 | # it under the terms of the GNU General Public License as published by
|
---|
13 | # the Free Software Foundation; either version 2 of the License, or
|
---|
14 | # (at your option) any later version.
|
---|
15 | #
|
---|
16 | # This program is distributed in the hope that it will be useful,
|
---|
17 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
18 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
19 | # GNU General Public License for more details.
|
---|
20 | #
|
---|
21 | # You should have received a copy of the GNU General Public License
|
---|
22 | # along with this program; if not, write to the Free Software
|
---|
23 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
24 | #
|
---|
25 | ###########################################################################
|
---|
26 |
|
---|
27 | package ProtemixPlug;
|
---|
28 |
|
---|
29 | use HTMLPlug;
|
---|
30 | use util;
|
---|
31 |
|
---|
32 | sub BEGIN {
|
---|
33 | @ISA = ('HTMLPlug');
|
---|
34 | }
|
---|
35 |
|
---|
36 | use XML::Parser;
|
---|
37 |
|
---|
38 | sub new {
|
---|
39 | my $class = shift (@_);
|
---|
40 |
|
---|
41 | # $self must be global for XML parser routines
|
---|
42 | $self = new HTMLPlug ($class, @_);
|
---|
43 |
|
---|
44 | $self->{'no_metadata'} = 1;
|
---|
45 | $self->{'nolinks'} = 1;
|
---|
46 | $self->{'section_metadata'} = {};
|
---|
47 | $self->{'Page'} = "TopLevel";
|
---|
48 | $self->{'metadata_name'} = "";
|
---|
49 |
|
---|
50 | return bless $self, $class;
|
---|
51 | }
|
---|
52 |
|
---|
53 | sub read {
|
---|
54 | my $self = shift (@_);
|
---|
55 | my ($pluginfo, $base_dir, $file, $metadata, $processor, $maxdocs) = @_;
|
---|
56 |
|
---|
57 | my $filename = $file;
|
---|
58 | $filename = &util::filename_cat ($base_dir, $file) if $base_dir =~ /\w/;
|
---|
59 |
|
---|
60 | my $basename = File::Basename::basename($filename);
|
---|
61 | return 0 if $basename =~ /^\d+(-(all|\d+))?\.(html?|pdf)/;
|
---|
62 | return undef unless $filename =~ /meta\.xml$/;
|
---|
63 |
|
---|
64 | # create a new document
|
---|
65 | my $doc_obj = new doc ($filename, "indexed_doc");
|
---|
66 | $doc_obj->set_OIDtype ($processor->{'OIDtype'});
|
---|
67 | my $topsection = $doc_obj->get_top_section();
|
---|
68 |
|
---|
69 | # process the meta.xml file and set top level metadata
|
---|
70 | my $parser = new XML::Parser('Style' => 'Stream');
|
---|
71 | $self->{'section_metadata'} = {};
|
---|
72 | $self->{'Page'} = "TopLevel";
|
---|
73 | $parser->parsefile($filename);
|
---|
74 | foreach my $key (keys %{$self->{'section_metadata'}->{'TopLevel'}}) {
|
---|
75 | $doc_obj->add_utf8_metadata ($topsection, $key, $self->{'section_metadata'}->{'TopLevel'}->{$key});
|
---|
76 | }
|
---|
77 |
|
---|
78 | my $dir = File::Basename::dirname($filename);
|
---|
79 |
|
---|
80 | my $outhandle = $self->{'outhandle'};
|
---|
81 | print $outhandle "ProtemixPlug: processing $dir\n";
|
---|
82 |
|
---|
83 |
|
---|
84 | # associate article level pdf file
|
---|
85 | my ($pdffile) = $dir =~ /([^\/\\]+)$/;
|
---|
86 | $pdffile = &util::filename_cat($dir, $pdffile);
|
---|
87 | $pdffile .= "-all.pdf";
|
---|
88 | if (-e $pdffile) {
|
---|
89 | $doc_obj->associate_file($pdffile, "article.pdf", undef, $topsection);
|
---|
90 | $doc_obj->add_utf8_metadata ($cursection, "pdf", "article.pdf");
|
---|
91 | } else {
|
---|
92 | print STDERR "ProtemixPlug: Error: $pdffile does not exist\n";
|
---|
93 | }
|
---|
94 |
|
---|
95 | # read in directory and process individual files
|
---|
96 | opendir(DIR, $dir) || die;
|
---|
97 | my @files = readdir DIR;
|
---|
98 | closedir DIR;
|
---|
99 |
|
---|
100 |
|
---|
101 | # we rely on the files being named in such a way that they'll be read
|
---|
102 | # in the correct order
|
---|
103 | my $count = 1;
|
---|
104 | foreach my $thisfile (@files) {
|
---|
105 | if ($thisfile =~ /^(.*?)\.html?$/i) {
|
---|
106 | my $filesuf = $1;
|
---|
107 | $thisfile = &util::filename_cat($dir, $thisfile);
|
---|
108 | my ($language, $encoding) = $self->textcat_get_language_encoding ($thisfile);
|
---|
109 | # read in file ($text will be in utf8)
|
---|
110 | my $text = "";
|
---|
111 | $self->read_file ($thisfile, $encoding, $language, \$text);
|
---|
112 | if (!length ($text)) {
|
---|
113 | print STDERR "ProtemixPlug: Warning: $thisfile has no text\n";
|
---|
114 | }
|
---|
115 |
|
---|
116 | my $cursection = $doc_obj->insert_section($doc_obj->get_end_child($topsection));
|
---|
117 |
|
---|
118 | # process HTML file with HTMLPlug
|
---|
119 | $self->process_section (\$text, '', $thisfile, $doc_obj, $cursection);
|
---|
120 |
|
---|
121 | # associate PDF page level pdf file
|
---|
122 | my $pdffile = $thisfile;
|
---|
123 | $pdffile =~ s/\.html?$/\.pdf/;
|
---|
124 | if (-e $pdffile) {
|
---|
125 | $doc_obj->associate_file($pdffile, "page$count.pdf", undef, $cursection);
|
---|
126 | $doc_obj->add_utf8_metadata ($cursection, "pdf", "page$count.pdf");
|
---|
127 | } else {
|
---|
128 | print STDERR "ProtemixPlug: Warning: no pdf file for $thisfile\n";
|
---|
129 | }
|
---|
130 | $doc_obj->add_utf8_metadata ($cursection, "Title", $count);
|
---|
131 |
|
---|
132 | # add any section level metadata we have for this page (set from within the meta.xml file)
|
---|
133 |
|
---|
134 | # currently commented out as we're not using Class1, Class2, and Class3 metadata yet
|
---|
135 | # if (defined ($self->{'section_metadata'}->{$filesuf})) {
|
---|
136 | # foreach my $key (keys %{$self->{'section_metadata'}->{$filesuf}}) {
|
---|
137 | # $doc_obj->add_utf8_metadata ($cursection, $key, $self->{'section_metadata'}->{$filesuf}->{$key});
|
---|
138 | # }
|
---|
139 | # }
|
---|
140 |
|
---|
141 | $count ++;
|
---|
142 | }
|
---|
143 | }
|
---|
144 |
|
---|
145 | # add an OID
|
---|
146 | $doc_obj->set_OID();
|
---|
147 |
|
---|
148 | # process the document
|
---|
149 | $processor->process($doc_obj);
|
---|
150 |
|
---|
151 | $self->{'num_processed'} ++;
|
---|
152 |
|
---|
153 | return 1; # processed the file
|
---|
154 | }
|
---|
155 |
|
---|
156 |
|
---|
157 | sub StartTag {
|
---|
158 | my ($expat, $element) = @_;
|
---|
159 |
|
---|
160 | if ($element eq "Page") {
|
---|
161 | $self->{'Page'} = $_{'filename'};
|
---|
162 |
|
---|
163 | } elsif ($element eq "Metadata") {
|
---|
164 | if (!defined $self->{'section_metadata'}->{$self->{'Page'}}) {
|
---|
165 | $self->{'section_metadata'}->{$self->{'Page'}} = {};
|
---|
166 | }
|
---|
167 | $self->{'metadata_name'} = $_{'name'};
|
---|
168 | $self->{'section_metadata'}->{$self->{'Page'}}->{$_{'name'}} = "";
|
---|
169 | }
|
---|
170 | }
|
---|
171 |
|
---|
172 | sub EndTag {
|
---|
173 | my ($expat, $element) = @_;
|
---|
174 |
|
---|
175 | if ($element eq "Page") {
|
---|
176 | $self->{'Page'} eq "TopLevel";
|
---|
177 |
|
---|
178 | } elsif ($element eq "Metadata") {
|
---|
179 | $self->{'metadata_name'} = "";
|
---|
180 | }
|
---|
181 | }
|
---|
182 |
|
---|
183 | sub Text {
|
---|
184 | if ($self->{'metadata_name'} ne "") {
|
---|
185 | $self->{'section_metadata'}->{$self->{'Page'}}->{$self->{'metadata_name'}} .= $_;
|
---|
186 | }
|
---|
187 | }
|
---|
188 |
|
---|
189 | # don't want to convert character entities for now as mgpp appears to be broken
|
---|
190 | sub read_file {
|
---|
191 | my ($self, $filename, $encoding, $language, $textref) = @_;
|
---|
192 |
|
---|
193 | &BasPlug::read_file($self, $filename, $encoding, $language, $textref);
|
---|
194 |
|
---|
195 | # Convert entities to their UTF8 equivalents
|
---|
196 | # $$textref =~ s/&(lt|gt|amp|quot);/&z$1;/go;
|
---|
197 | # $$textref =~ s/&([^;]+);/&ghtml::getcharequiv($1,1)/gseo;
|
---|
198 | # $$textref =~ s/&z(lt|gt|amp|quot);/&$1;/go;
|
---|
199 | }
|
---|
200 |
|
---|
201 |
|
---|
202 | 1;
|
---|