1 | ###########################################################################
|
---|
2 | #
|
---|
3 | # PostScriptPlugin.pm -- plugin to process PostScript files
|
---|
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 PostScriptPlugin;
|
---|
27 |
|
---|
28 | use ConvertBinaryFile;
|
---|
29 | use ReadTextFile; # for read_file in convert_post_process. do we need it?
|
---|
30 | use sorttools;
|
---|
31 |
|
---|
32 | use strict;
|
---|
33 | no strict 'refs'; # allow filehandles to be variables and viceversa
|
---|
34 |
|
---|
35 | sub BEGIN {
|
---|
36 | @PostScriptPlugin::ISA = ('ConvertBinaryFile', 'ReadTextFile');
|
---|
37 | }
|
---|
38 |
|
---|
39 | my $convert_to_list =
|
---|
40 | [ { 'name' => "auto",
|
---|
41 | 'desc' => "{ConvertBinaryFile.convert_to.auto}" },
|
---|
42 | { 'name' => "text",
|
---|
43 | 'desc' => "{ConvertBinaryFile.convert_to.text}" },
|
---|
44 | { 'name' => "pagedimg_jpg",
|
---|
45 | 'desc' => "{ConvertBinaryFile.convert_to.pagedimg_jpg}" },
|
---|
46 | { 'name' => "pagedimg_gif",
|
---|
47 | 'desc' => "{ConvertBinaryFile.convert_to.pagedimg_gif}" },
|
---|
48 | { 'name' => "pagedimg_png",
|
---|
49 | 'desc' => "{ConvertBinaryFile.convert_to.pagedimg_png}" }
|
---|
50 | ];
|
---|
51 |
|
---|
52 | my $arguments =
|
---|
53 | [ { 'name' => "convert_to",
|
---|
54 | 'desc' => "{ConvertBinaryFile.convert_to}",
|
---|
55 | 'type' => "enum",
|
---|
56 | 'reqd' => "yes",
|
---|
57 | 'list' => $convert_to_list,
|
---|
58 | 'deft' => "text" },
|
---|
59 | { 'name' => "process_exp",
|
---|
60 | 'desc' => "{BasePlugin.process_exp}",
|
---|
61 | 'type' => "regexp",
|
---|
62 | 'deft' => &get_default_process_exp(),
|
---|
63 | 'reqd' => "no" },
|
---|
64 | { 'name' => "block_exp",
|
---|
65 | 'desc' => "{BasePlugin.block_exp}",
|
---|
66 | 'type' => 'regexp',
|
---|
67 | 'deft' => &get_default_block_exp() },
|
---|
68 | { 'name' => "extract_date",
|
---|
69 | 'desc' => "{PostScriptPlugin.extract_date}",
|
---|
70 | 'type' => "flag" },
|
---|
71 | { 'name' => "extract_pages",
|
---|
72 | 'desc' => "{PostScriptPlugin.extract_pages}",
|
---|
73 | 'type' => "flag" },
|
---|
74 | { 'name' => "extract_title",
|
---|
75 | 'desc' => "{PostScriptPlugin.extract_title}",
|
---|
76 | 'type' => "flag" } ];
|
---|
77 |
|
---|
78 | my $options = { 'name' => "PostScriptPlugin",
|
---|
79 | 'desc' => "{PostScriptPlugin.desc}",
|
---|
80 | 'abstract' => "no",
|
---|
81 | 'inherits' => "yes",
|
---|
82 | 'srcreplaceable' => "yes", # Source docs in postscript format can be replaced with GS-generated html
|
---|
83 | 'args' => $arguments };
|
---|
84 |
|
---|
85 | sub new {
|
---|
86 | my ($class) = shift (@_);
|
---|
87 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
---|
88 | push(@$pluginlist, $class);
|
---|
89 |
|
---|
90 | push(@$inputargs,"-title_sub");
|
---|
91 | push(@$inputargs,'^(Page\s+\d+)?(\s*1\s+)?');
|
---|
92 |
|
---|
93 | push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});
|
---|
94 | push(@{$hashArgOptLists->{"OptList"}},$options);
|
---|
95 |
|
---|
96 | my $self = new ConvertBinaryFile($pluginlist, $inputargs, $hashArgOptLists);
|
---|
97 |
|
---|
98 | if ($self->{'info_only'}) {
|
---|
99 | # don't worry about any options etc
|
---|
100 | return bless $self, $class;
|
---|
101 | }
|
---|
102 |
|
---|
103 | $self->{'filename_extension'} = "ps";
|
---|
104 | $self->{'file_type'} = "PS";
|
---|
105 |
|
---|
106 | if ($self->{'convert_to'} eq "auto") {
|
---|
107 | $self->{'convert_to'} = "text";
|
---|
108 | }
|
---|
109 |
|
---|
110 | # set convert_to_plugin and convert_to_ext
|
---|
111 | $self->ConvertBinaryFile::set_standard_convert_settings();
|
---|
112 | my $secondary_plugin_name = $self->{'convert_to_plugin'};
|
---|
113 | my $secondary_plugin_options = $self->{'secondary_plugin_options'};
|
---|
114 |
|
---|
115 | if (!defined $secondary_plugin_options->{$secondary_plugin_name}) {
|
---|
116 | $secondary_plugin_options->{$secondary_plugin_name} = [];
|
---|
117 | }
|
---|
118 | my $specific_options = $secondary_plugin_options->{$secondary_plugin_name};
|
---|
119 |
|
---|
120 | # following title_sub removes "Page 1" added by ps2ascii, and a leading
|
---|
121 | # "1", which is often the page number at the top of the page. Bad Luck
|
---|
122 | # if your document title actually starts with "1 " - is there a better way?
|
---|
123 | push(@$specific_options, "-title_sub", '^(Page\s+\d+)?(\s*1\s+)?');
|
---|
124 | push(@$specific_options, "-file_rename_method", "none");
|
---|
125 |
|
---|
126 | if ($secondary_plugin_name eq "TextPlugin") {
|
---|
127 | push(@$specific_options, "-input_encoding", "utf8");
|
---|
128 | push(@$specific_options,"-extract_language") if $self->{'extract_language'};
|
---|
129 | } elsif ($secondary_plugin_name eq "PagedImagePlugin") {
|
---|
130 | push(@$specific_options, "-processing_tmp_files");
|
---|
131 | }
|
---|
132 |
|
---|
133 | $self = bless $self, $class;
|
---|
134 | # used for convert_post_process
|
---|
135 | $self->{'input_encoding'} = "auto";
|
---|
136 | $self->{'default_encoding'} = "utf8";
|
---|
137 |
|
---|
138 | $self->load_secondary_plugins($class,$secondary_plugin_options, $hashArgOptLists);
|
---|
139 |
|
---|
140 | return $self;
|
---|
141 | }
|
---|
142 |
|
---|
143 |
|
---|
144 | sub get_default_block_exp {
|
---|
145 | my $self = shift (@_);
|
---|
146 |
|
---|
147 | return q^(?i)\.(eps)$^;
|
---|
148 | }
|
---|
149 |
|
---|
150 | sub get_default_process_exp {
|
---|
151 | my $self = shift (@_);
|
---|
152 |
|
---|
153 | return q^(?i)\.ps$^;
|
---|
154 | }
|
---|
155 |
|
---|
156 | # this has been commented out in other plugins. do we need it here?
|
---|
157 | # ps files are converted to images (item file should be in utf8) or text (uses pstoascii), so we shouldn't need to ensure utf8
|
---|
158 | sub convert_post_process
|
---|
159 | {
|
---|
160 | my $self = shift (@_);
|
---|
161 | my ($conv_filename) = @_;
|
---|
162 |
|
---|
163 | my $outhandle=$self->{'outhandle'};
|
---|
164 |
|
---|
165 | my ($language, $encoding) = $self->textcat_get_language_encoding ($conv_filename);
|
---|
166 |
|
---|
167 | # read in file ($text will be in utf8)
|
---|
168 | my $text = "";
|
---|
169 | $self->read_file ($conv_filename, $encoding, $language, \$text);
|
---|
170 |
|
---|
171 | # turn any high bytes that aren't valid utf-8 into utf-8.
|
---|
172 | unicode::ensure_utf8(\$text);
|
---|
173 |
|
---|
174 | # Write it out again!
|
---|
175 | $self->utf8_write_file (\$text, $conv_filename);
|
---|
176 | }
|
---|
177 |
|
---|
178 | sub extract_metadata_from_postscript {
|
---|
179 | my $self = shift (@_);
|
---|
180 |
|
---|
181 | my ($filename,$doc) = @_;
|
---|
182 |
|
---|
183 | my $section = $doc->get_top_section();
|
---|
184 |
|
---|
185 | my $title_found = 0;
|
---|
186 | my $pages_found = 0;
|
---|
187 | my $date_found = 0;
|
---|
188 |
|
---|
189 | print STDERR "PostScriptPlugin: extracting PostScript metadata from \"$filename\"\n"
|
---|
190 | if $self->{'verbosity'} > 1;
|
---|
191 |
|
---|
192 | open(INPUT, "<$filename");
|
---|
193 | my $date;
|
---|
194 |
|
---|
195 | while(my $line =<INPUT>) {
|
---|
196 | if ($self->{'extract_title'} && !$title_found) {
|
---|
197 | foreach my $word ($line =~ m|Title: ([-A-Za-z0-9@/\/\(\):,. ]*)|g) {
|
---|
198 | my $new_word = $word;
|
---|
199 | $new_word =~ s/\(Untitled\)//i;
|
---|
200 | $new_word =~ s/\(Microsoft Word\)//i;
|
---|
201 | $new_word =~ s/Microsoft Word//i;
|
---|
202 | $new_word =~ s/^\(//i;
|
---|
203 | $new_word =~ s/\)$//i;
|
---|
204 | $new_word =~ s/^ - //i;
|
---|
205 | if ($new_word ne "") {
|
---|
206 | $doc->add_utf8_metadata($section, "Title", $new_word );
|
---|
207 | $title_found = 1;
|
---|
208 | }
|
---|
209 | }
|
---|
210 | }
|
---|
211 | if ($self->{'extract_date'} && !$date_found) {
|
---|
212 | foreach my $word ($line =~ m/(Creation[-A-Za-z0-9@\/\(\):,. ]*)/g) {
|
---|
213 | if ($word =~ m/ ([A-Za-z][A-Za-z][A-Za-z]) ([0-9 ][0-9]) ?[0-9: ]+ ([0-9]{4})/) {
|
---|
214 | $date = &sorttools::format_date($2,$1,$3);
|
---|
215 | if (defined $date) {
|
---|
216 | $doc->add_utf8_metadata($section, "Date", $date );
|
---|
217 | }
|
---|
218 | }
|
---|
219 | if ($word =~ m/D:([0-9]{4})([0-9]{2})([0-9]{2})[0-9]{6}\)/) {
|
---|
220 | $date = &sorttools::format_date($3,$2,$1);
|
---|
221 | if (defined $date) {
|
---|
222 | $doc->add_utf8_metadata($section, "Date", $date );
|
---|
223 | }
|
---|
224 | }
|
---|
225 | if ($word =~ m/CreationDate: ([0-9]{4}) ([A-Za-z][A-Za-z][A-Za-z]) ([0-9 ][0-9]) [0-9:]*/) {
|
---|
226 | $date = &sorttools::format_date($3,$2,$1);
|
---|
227 | if (defined $date) {
|
---|
228 | $doc->add_utf8_metadata($section, "Date", $date );
|
---|
229 | }
|
---|
230 | }
|
---|
231 | $date_found = 1;
|
---|
232 | }
|
---|
233 | }
|
---|
234 | if ($self->{'extract_pages'} && !$pages_found) {
|
---|
235 | foreach my $word ($line =~ m/(Pages: [0-9]*)/g) {
|
---|
236 | my $digits = $word;
|
---|
237 | $digits =~ s/[^0-9]//g;
|
---|
238 | if ($digits ne "" && $digits ne "0") {
|
---|
239 | $doc->add_utf8_metadata($section, "Pages", $digits );
|
---|
240 | $pages_found = 1;
|
---|
241 | }
|
---|
242 | }
|
---|
243 | }
|
---|
244 | }
|
---|
245 | }
|
---|
246 |
|
---|
247 | # do plugin specific processing of doc_obj
|
---|
248 | sub process {
|
---|
249 | my $self = shift (@_);
|
---|
250 | my ($pluginfo, $base_dir, $file, $metadata, $doc_obj, $gli) = @_;
|
---|
251 |
|
---|
252 | my $filename = &util::filename_cat($base_dir,$file);
|
---|
253 | $self->extract_metadata_from_postscript($filename, $doc_obj);
|
---|
254 |
|
---|
255 | return $self->SUPER::process(@_);
|
---|
256 |
|
---|
257 | }
|
---|
258 |
|
---|
259 |
|
---|
260 | 1;
|
---|
261 |
|
---|