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 | # 12/05/02 Added usage datastructure - John Thompson
|
---|
27 |
|
---|
28 | package PSPlug;
|
---|
29 |
|
---|
30 | use ConvertToPlug;
|
---|
31 | use sorttools;
|
---|
32 |
|
---|
33 | sub BEGIN {
|
---|
34 | @ISA = ('ConvertToPlug');
|
---|
35 | }
|
---|
36 |
|
---|
37 | my $arguments =
|
---|
38 | [ { 'name' => "process_exp",
|
---|
39 | 'desc' => "{BasPlug.process_exp}",
|
---|
40 | 'type' => "regexp",
|
---|
41 | 'deft' => &get_default_process_exp(),
|
---|
42 | 'reqd' => "no" },
|
---|
43 | { 'name' => "block_exp",
|
---|
44 | 'desc' => "{BasPlug.block_exp}",
|
---|
45 | 'type' => 'regexp',
|
---|
46 | 'deft' => &get_default_block_exp() },
|
---|
47 | { 'name' => "extract_date",
|
---|
48 | 'desc' => "{PSPlug.extract_date}",
|
---|
49 | 'type' => "flag" },
|
---|
50 | { 'name' => "extract_pages",
|
---|
51 | 'desc' => "{PSPlug.extract_pages}",
|
---|
52 | 'type' => "flag" },
|
---|
53 | { 'name' => "extract_title",
|
---|
54 | 'desc' => "{PSPlug.extract_title}",
|
---|
55 | 'type' => "flag" } ];
|
---|
56 |
|
---|
57 | my $options = { 'name' => "PSPlug",
|
---|
58 | 'desc' => "{PSPlug.desc}",
|
---|
59 | 'abstract' => "no",
|
---|
60 | 'inherits' => "yes",
|
---|
61 | 'args' => $arguments };
|
---|
62 |
|
---|
63 | sub new {
|
---|
64 | my ($class) = shift (@_);
|
---|
65 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
---|
66 | push(@$pluginlist, $class);
|
---|
67 |
|
---|
68 | push(@$inputargs,"-convert_to");
|
---|
69 | push(@$inputargs,"text");
|
---|
70 | push(@$inputargs,"-title_sub");
|
---|
71 | push(@$inputargs,'^(Page\s+\d+)?(\s*1\s+)?');
|
---|
72 |
|
---|
73 | if(defined $arguments){ push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});}
|
---|
74 | if(defined $options) { push(@{$hashArgOptLists->{"OptList"}},$options)};
|
---|
75 |
|
---|
76 | my $self = (defined $hashArgOptLists)? new ConvertToPlug($pluginlist,$inputargs,$hashArgOptLists): new ConvertToPlug($pluginlist,$inputargs);
|
---|
77 |
|
---|
78 | return bless $self, $class;
|
---|
79 | }
|
---|
80 |
|
---|
81 |
|
---|
82 | sub get_default_block_exp {
|
---|
83 | my $self = shift (@_);
|
---|
84 |
|
---|
85 | return q^(?i)\.(eps)$^;
|
---|
86 | }
|
---|
87 |
|
---|
88 | sub get_default_process_exp {
|
---|
89 | my $self = shift (@_);
|
---|
90 |
|
---|
91 | return q^(?i)\.ps$^;
|
---|
92 | }
|
---|
93 |
|
---|
94 | sub extract_metadata_from_postscript {
|
---|
95 | my $self = shift (@_);
|
---|
96 | my $filename = shift (@_);
|
---|
97 | my $doc = shift (@_);
|
---|
98 | my $section = $doc->get_top_section();
|
---|
99 |
|
---|
100 | my $title_found = 0;
|
---|
101 | my $pages_found = 0;
|
---|
102 | my $date_found = 0;
|
---|
103 |
|
---|
104 | print STDERR "PSPlug: extracting PostScript metadata from \"$filename\"\n"
|
---|
105 | if $self->{'verbosity'} > 1;
|
---|
106 |
|
---|
107 | open(INPUT, "<$filename");
|
---|
108 | my $date;
|
---|
109 |
|
---|
110 | while(my $line =<INPUT>) {
|
---|
111 | if ($self->{'extract_title'} && !$title_found) {
|
---|
112 | foreach my $word ($line =~ m|Title: ([-A-Za-z0-9@/\/\(\):,. ]*)|g) {
|
---|
113 | my $new_word = $word;
|
---|
114 | $new_word =~ s/\(Untitled\)//i;
|
---|
115 | $new_word =~ s/\(Microsoft Word\)//i;
|
---|
116 | $new_word =~ s/Microsoft Word//i;
|
---|
117 | $new_word =~ s/^\(//i;
|
---|
118 | $new_word =~ s/\)$//i;
|
---|
119 | $new_word =~ s/^ - //i;
|
---|
120 | if ($new_word ne "") {
|
---|
121 | $doc->add_utf8_metadata($section, "Title", $new_word );
|
---|
122 | $title_found = 1;
|
---|
123 | }
|
---|
124 | }
|
---|
125 | }
|
---|
126 | if ($self->{'extract_date'} && !$date_found) {
|
---|
127 | foreach my $word ($line =~ m/(Creation[-A-Za-z0-9@\/\(\):,. ]*)/g) {
|
---|
128 | if ($word =~ m/ ([A-Za-z][A-Za-z][A-Za-z]) ([0-9 ][0-9]) ?[0-9: ]+ ([0-9]{4})/) {
|
---|
129 | $date = &sorttools::format_date($2,$1,$3);
|
---|
130 | if (defined $date) {
|
---|
131 | $doc->add_utf8_metadata($section, "Date", $date );
|
---|
132 | }
|
---|
133 | }
|
---|
134 | if ($word =~ m/D:([0-9]{4})([0-9]{2})([0-9]{2})[0-9]{6}\)/) {
|
---|
135 | $date = &sorttools::format_date($3,$2,$1);
|
---|
136 | if (defined $date) {
|
---|
137 | $doc->add_utf8_metadata($section, "Date", $date );
|
---|
138 | }
|
---|
139 | }
|
---|
140 | if ($word =~ m/CreationDate: ([0-9]{4}) ([A-Za-z][A-Za-z][A-Za-z]) ([0-9 ][0-9]) [0-9:]*/) {
|
---|
141 | $date = &sorttools::format_date($3,$2,$1);
|
---|
142 | if (defined $date) {
|
---|
143 | $doc->add_utf8_metadata($section, "Date", $date );
|
---|
144 | }
|
---|
145 | }
|
---|
146 | $date_found = 1;
|
---|
147 | }
|
---|
148 | }
|
---|
149 | if ($self->{'extract_pages'} && !$pages_found) {
|
---|
150 | foreach my $word ($line =~ m/(Pages: [0-9]*)/g) {
|
---|
151 | my $digits = $word;
|
---|
152 | $digits =~ s/[^0-9]//g;
|
---|
153 | if ($digits ne "" && $digits ne "0") {
|
---|
154 | $doc->add_utf8_metadata($section, "Pages", $digits );
|
---|
155 | $pages_found = 1;
|
---|
156 | }
|
---|
157 | }
|
---|
158 | }
|
---|
159 | }
|
---|
160 | }
|
---|
161 |
|
---|
162 | # do plugin specific processing of doc_obj for HTML type
|
---|
163 | sub process {
|
---|
164 | my $self = shift (@_);
|
---|
165 | my ($trash, $trash2, $path, $file, $trash3, $doc, $gli) = @_;
|
---|
166 |
|
---|
167 | my $outhandle = $self->{'outhandle'};
|
---|
168 | print $outhandle "PSPlug: passing $_[3] on to $self->{'converted_to'}Plug\n"
|
---|
169 | if $self->{'verbosity'} > 1;
|
---|
170 | print STDERR "<Processing n='$_[3]' p='PSPlug'>\n" if ($gli);
|
---|
171 |
|
---|
172 | &extract_metadata_from_postscript($self,"$path/$file", $doc);
|
---|
173 |
|
---|
174 | return ConvertToPlug::process_type($self,"ps",@_);
|
---|
175 | }
|
---|
176 |
|
---|
177 |
|
---|
178 | 1;
|
---|
179 |
|
---|