1 | ###########################################################################
|
---|
2 | #
|
---|
3 | # PDFPlug.pm -- reasonably with-it pdf plugin
|
---|
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) 1999-2001 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 | package PDFPlug;
|
---|
27 |
|
---|
28 | use ConvertToPlug;
|
---|
29 |
|
---|
30 | sub BEGIN {
|
---|
31 | @ISA = ('ConvertToPlug');
|
---|
32 | }
|
---|
33 |
|
---|
34 | sub new {
|
---|
35 | my $class = shift (@_);
|
---|
36 |
|
---|
37 | # following title_sub removes "Page 1" added by pdftohtml, and a leading
|
---|
38 | # "1", which is often the page number at the top of the page. Bad Luck
|
---|
39 | # if your document title actually starts with "1 " - is there a better way?
|
---|
40 |
|
---|
41 | my $self = new ConvertToPlug ($class, @_, "-title_sub", '^(Page\s+\d+)?(\s*1\s+)?');
|
---|
42 |
|
---|
43 | return bless $self, $class;
|
---|
44 | }
|
---|
45 |
|
---|
46 |
|
---|
47 |
|
---|
48 | sub get_default_process_exp {
|
---|
49 | my $self = shift (@_);
|
---|
50 |
|
---|
51 | return q^(?i)\.pdf$^;
|
---|
52 | }
|
---|
53 |
|
---|
54 | # so we don't inherit HTMLPlug's block exp...
|
---|
55 | sub get_default_block_exp {
|
---|
56 | return "";
|
---|
57 | }
|
---|
58 |
|
---|
59 |
|
---|
60 | # do plugin specific processing of doc_obj for HTML type
|
---|
61 | sub process {
|
---|
62 | my $self = shift (@_);
|
---|
63 |
|
---|
64 | my $outhandle = $self->{'outhandle'};
|
---|
65 | print $outhandle "PDFPlug: passing $_[3] on to $self->{'convert_to'}Plug\n"
|
---|
66 | if $self->{'verbosity'} > 1;
|
---|
67 |
|
---|
68 | return ConvertToPlug::process_type($self,"pdf",@_);
|
---|
69 | }
|
---|
70 |
|
---|
71 | 1;
|
---|