1 | ###########################################################################
|
---|
2 | #
|
---|
3 | # PSPlug.pm -- this might look VERY similar to the 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 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 PSPlug;
|
---|
27 |
|
---|
28 | use ConvertToPlug;
|
---|
29 | use sorttools;
|
---|
30 |
|
---|
31 | sub BEGIN {
|
---|
32 | @ISA = ('ConvertToPlug');
|
---|
33 | }
|
---|
34 |
|
---|
35 | use strict;
|
---|
36 |
|
---|
37 |
|
---|
38 | sub new {
|
---|
39 | my $class = shift (@_);
|
---|
40 |
|
---|
41 | my $self = new ConvertToPlug ($class, ("-convert_to","text",@_), "--", "-title_sub", 'Page\s+\d+');
|
---|
42 |
|
---|
43 | if (!parsargv::parse(\@_,
|
---|
44 | q^extract_date^, \$self->{'extract_date'},
|
---|
45 | q^extract_pages^, \$self->{'extract_pages'},
|
---|
46 | q^extract_title^, \$self->{'extract_title'},
|
---|
47 | "allow_extra_options")) {
|
---|
48 | print STDERR "\nIncorrect options passed to HTMLPlug, check your collect.cfg configuration file\n";
|
---|
49 | &print_usage();
|
---|
50 | die "\n";
|
---|
51 | }
|
---|
52 |
|
---|
53 | return bless $self, $class;
|
---|
54 | }
|
---|
55 |
|
---|
56 | sub print_usage {
|
---|
57 | print STDERR "\n usage: plugin PSPlug [options]\n\n";
|
---|
58 | print STDERR " options:\n";
|
---|
59 | print STDERR " -extract_date Extract date from PS header\n";
|
---|
60 | print STDERR " -extract_pages Extract pages from PS header\n";
|
---|
61 | print STDERR " -extract_title Extract title from PS header\n";
|
---|
62 | print STDERR "\n\nNote! This is a \"poor man's\" ps to text converter. If you are serious, consider\n";
|
---|
63 | print STDERR "using the PRESCRIPT package, which is available for download at\n http://www.nzdl.org/html/software.html\n\n";
|
---|
64 | }
|
---|
65 |
|
---|
66 |
|
---|
67 | sub get_default_block_exp {
|
---|
68 | my $self = shift (@_);
|
---|
69 |
|
---|
70 | return q^(?i)\.(eps)$^;
|
---|
71 | }
|
---|
72 |
|
---|
73 | sub get_default_process_exp {
|
---|
74 | my $self = shift (@_);
|
---|
75 |
|
---|
76 | return q^(?i)\.ps$^;
|
---|
77 | }
|
---|
78 |
|
---|
79 | sub extract_metadata_from_postscript {
|
---|
80 | my $self = shift (@_);
|
---|
81 | my $filename = shift (@_);
|
---|
82 | my $doc = shift (@_);
|
---|
83 | my $section = $doc->get_top_section();
|
---|
84 |
|
---|
85 | my $title_found = 0;
|
---|
86 | my $pages_found = 0;
|
---|
87 | my $date_found = 0;
|
---|
88 |
|
---|
89 | print STDERR "PSPlug: extracting PostScript metadata from \"$filename\"\n"
|
---|
90 | if $self->{'verbosity'} > 1;
|
---|
91 |
|
---|
92 | open(INPUT, "<$filename");
|
---|
93 | my $date;
|
---|
94 |
|
---|
95 | while(my $line =<INPUT>) {
|
---|
96 | if ($self->{'extract_title'} && !$title_found) {
|
---|
97 | foreach my $word ($line =~ m|Title: ([-A-Za-z0-9@/\/\(\):,. ]*)|g) {
|
---|
98 | my $new_word = $word;
|
---|
99 | $new_word =~ s/\(Untitled\)//i;
|
---|
100 | $new_word =~ s/\(Microsoft Word\)//i;
|
---|
101 | $new_word =~ s/Microsoft Word//i;
|
---|
102 | $new_word =~ s/^\(//i;
|
---|
103 | $new_word =~ s/\)$//i;
|
---|
104 | $new_word =~ s/^ - //i;
|
---|
105 | if ($new_word ne "") {
|
---|
106 | $doc->add_utf8_metadata($section, "Title", $new_word );
|
---|
107 | $title_found = 1;
|
---|
108 | }
|
---|
109 | }
|
---|
110 | }
|
---|
111 | if ($self->{'extract_date'} && !$date_found) {
|
---|
112 | foreach my $word ($line =~ m/(Creation[-A-Za-z0-9@\/\(\):,. ]*)/g) {
|
---|
113 | if ($word =~ m/ ([A-Za-z][A-Za-z][A-Za-z]) ([0-9 ][0-9]) ?[0-9: ]+ ([0-9]{4})/) {
|
---|
114 | $date = &sorttools::format_date($2,$1,$3);
|
---|
115 | if (defined $date) {
|
---|
116 | $doc->add_utf8_metadata($section, "Date", $date );
|
---|
117 | }
|
---|
118 | }
|
---|
119 | if ($word =~ m/D:([0-9]{4})([0-9]{2})([0-9]{2})[0-9]{6}\)/) {
|
---|
120 | $date = &sorttools::format_date($3,$2,$1);
|
---|
121 | if (defined $date) {
|
---|
122 | $doc->add_utf8_metadata($section, "Date", $date );
|
---|
123 | }
|
---|
124 | }
|
---|
125 | if ($word =~ m/CreationDate: ([0-9]{4}) ([A-Za-z][A-Za-z][A-Za-z]) ([0-9 ][0-9]) [0-9:]*/) {
|
---|
126 | $date = &sorttools::format_date($3,$2,$1);
|
---|
127 | if (defined $date) {
|
---|
128 | $doc->add_utf8_metadata($section, "Date", $date );
|
---|
129 | }
|
---|
130 | }
|
---|
131 | $date_found = 1;
|
---|
132 | }
|
---|
133 | }
|
---|
134 | if ($self->{'extract_pages'} && !$pages_found) {
|
---|
135 | foreach my $word ($line =~ m/(Pages: [0-9]*)/g) {
|
---|
136 | my $digits = $word;
|
---|
137 | $digits =~ s/[^0-9]//g;
|
---|
138 | if ($digits ne "" && $digits ne "0") {
|
---|
139 | $doc->add_utf8_metadata($section, "Pages", $digits );
|
---|
140 | $pages_found = 1;
|
---|
141 | }
|
---|
142 | }
|
---|
143 | }
|
---|
144 | }
|
---|
145 | }
|
---|
146 |
|
---|
147 |
|
---|
148 | # do plugin specific processing of doc_obj for HTML type
|
---|
149 | sub process {
|
---|
150 | my $self = shift (@_);
|
---|
151 | my ($trash, $trash2, $path, $file, $trash3, $doc) = @_;
|
---|
152 |
|
---|
153 | print STDERR "PSPlug: passing $_[3] onto $self->{'convert_to'} Plug\n"
|
---|
154 | if $self->{'verbosity'} > 1;
|
---|
155 |
|
---|
156 | &extract_metadata_from_postscript($self,"$path/$file", $doc);
|
---|
157 |
|
---|
158 | return ConvertToPlug::process_type($self,"ps",@_);
|
---|
159 | }
|
---|
160 |
|
---|
161 |
|
---|
162 | 1;
|
---|
163 |
|
---|