1 | ###########################################################################
|
---|
2 | #
|
---|
3 | # PowerPointPlugin.pm -- plugin for importing Microsoft PowerPoint files.
|
---|
4 | # (basic version supports versions 95 and 97)
|
---|
5 | # (through OpenOffice extension, supports all contemporary formats)
|
---|
6 | #
|
---|
7 | # A component of the Greenstone digital library software
|
---|
8 | # from the New Zealand Digital Library Project at the
|
---|
9 | # University of Waikato, New Zealand.
|
---|
10 | #
|
---|
11 | # Copyright (C) 2002 New Zealand Digital Library Project
|
---|
12 | #
|
---|
13 | # This program is free software; you can redistribute it and/or modify
|
---|
14 | # it under the terms of the GNU General Public License as published by
|
---|
15 | # the Free Software Foundation; either version 2 of the License, or
|
---|
16 | # (at your option) any later version.
|
---|
17 | #
|
---|
18 | # This program is distributed in the hope that it will be useful,
|
---|
19 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
20 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
21 | # GNU General Public License for more details.
|
---|
22 | #
|
---|
23 | # You should have received a copy of the GNU General Public License
|
---|
24 | # along with this program; if not, write to the Free Software
|
---|
25 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
26 | #
|
---|
27 | ###########################################################################
|
---|
28 |
|
---|
29 | package PowerPointPlugin;
|
---|
30 |
|
---|
31 | use strict;
|
---|
32 | no strict 'refs'; # allow filehandles to be variables and viceversa
|
---|
33 | no strict 'subs';
|
---|
34 |
|
---|
35 | use gsprintf 'gsprintf';
|
---|
36 |
|
---|
37 | use AutoLoadConverters;
|
---|
38 | use ConvertBinaryFile;
|
---|
39 |
|
---|
40 | sub BEGIN {
|
---|
41 | @PowerPointPlugin::ISA = ('ConvertBinaryFile', 'AutoLoadConverters');
|
---|
42 | }
|
---|
43 |
|
---|
44 | my $openoffice_available = 0;
|
---|
45 |
|
---|
46 | my $windows_convert_to_list =
|
---|
47 | [ { 'name' => "auto",
|
---|
48 | 'desc' => "{ConvertBinaryFile.convert_to.auto}" },
|
---|
49 | { 'name' => "html",
|
---|
50 | 'desc' => "{ConvertBinaryFile.convert_to.html}" },
|
---|
51 | { 'name' => "text",
|
---|
52 | 'desc' => "{ConvertBinaryFile.convert_to.text}" },
|
---|
53 | { 'name' => "pagedimg_jpg",
|
---|
54 | 'desc' => "{PowerPointPlugin.convert_to.pagedimg_jpg}" },
|
---|
55 | { 'name' => "pagedimg_gif",
|
---|
56 | 'desc' => "{PowerPointPlugin.convert_to.pagedimg_gif}" },
|
---|
57 | { 'name' => "pagedimg_png",
|
---|
58 | 'desc' => "{PowerPointPlugin.convert_to.pagedimg_png}" }
|
---|
59 | ];
|
---|
60 |
|
---|
61 | my $openoffice_convert_to_list =
|
---|
62 | [ { 'name' => "auto",
|
---|
63 | 'desc' => "{ConvertBinaryFile.convert_to.auto}" },
|
---|
64 | { 'name' => "html_multi",
|
---|
65 | 'desc' => "{PowerPointPlugin.convert_to.html_multi}" },
|
---|
66 | { 'name' => "text",
|
---|
67 | 'desc' => "{ConvertBinaryFile.convert_to.text}" },
|
---|
68 | { 'name' => "pagedimg",
|
---|
69 | 'desc' => "{PowerPointPlugin.convert_to.pagedimg}" }
|
---|
70 | ];
|
---|
71 |
|
---|
72 | my $openoffice_extra_convert_to_list =
|
---|
73 | [ { 'name' => "html_multi",
|
---|
74 | 'desc' => "{PowerPointPlugin.convert_to.html_multi}" },
|
---|
75 | { 'name' => "pagedimg",
|
---|
76 | 'desc' => "{PowerPointPlugin.convert_to.pagedimg}" }
|
---|
77 | ];
|
---|
78 |
|
---|
79 | my $arguments =
|
---|
80 | [ { 'name' => "process_exp",
|
---|
81 | 'desc' => "{BaseImporter.process_exp}",
|
---|
82 | 'type' => "regexp",
|
---|
83 | 'reqd' => "no",
|
---|
84 | 'deft' => "&get_default_process_exp()", # delayed (see below)
|
---|
85 | }
|
---|
86 | ];
|
---|
87 |
|
---|
88 | my $opt_windows_args =
|
---|
89 | [ { 'name' => "convert_to",
|
---|
90 | 'desc' => "{ConvertBinaryFile.convert_to}",
|
---|
91 | 'type' => "enum",
|
---|
92 | 'reqd' => "yes",
|
---|
93 | 'list' => $windows_convert_to_list,
|
---|
94 | 'deft' => "html" },
|
---|
95 | { 'name' => "windows_scripting",
|
---|
96 | 'desc' => "{PowerPointPlugin.windows_scripting}",
|
---|
97 | 'type' => "flag",
|
---|
98 | 'reqd' => "no" }
|
---|
99 | ];
|
---|
100 |
|
---|
101 | my $opt_office_args =
|
---|
102 | [ { 'name' => "convert_to",
|
---|
103 | 'desc' => "{ConvertBinaryFile.convert_to}",
|
---|
104 | 'type' => "enum",
|
---|
105 | 'reqd' => "yes",
|
---|
106 | 'list' => $openoffice_convert_to_list,
|
---|
107 | 'deft' => "html" }
|
---|
108 | ];
|
---|
109 |
|
---|
110 | my $options = { 'name' => "PowerPointPlugin",
|
---|
111 | 'desc' => "{PowerPointPlugin.desc}",
|
---|
112 | 'abstract' => "no",
|
---|
113 | 'inherits' => "yes",
|
---|
114 | 'srcreplaceable' => "yes", # Source docs in PPT format can be replaced with GS-generated html
|
---|
115 | 'args' => $arguments };
|
---|
116 |
|
---|
117 | sub new {
|
---|
118 | my ($class) = shift (@_);
|
---|
119 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
---|
120 | push(@$pluginlist, $class);
|
---|
121 |
|
---|
122 | # this bit needs to happen later after the arguments array has been
|
---|
123 | # finished - used for parsing the input args.
|
---|
124 | # push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});
|
---|
125 | # this one needs to go in first, to get the print info in the right order
|
---|
126 | push(@{$hashArgOptLists->{"OptList"}},$options);
|
---|
127 |
|
---|
128 | my $auto_converter_self = new AutoLoadConverters($pluginlist,$inputargs,$hashArgOptLists,["OpenOfficeConverter"],1);
|
---|
129 |
|
---|
130 | if ($ENV{'GSDLOS'} =~ m/^windows$/i) {
|
---|
131 | if ($auto_converter_self->{'openoffice_available'}) {
|
---|
132 | # add openoffice convert_to options into list
|
---|
133 | push (@$windows_convert_to_list, @$openoffice_extra_convert_to_list);
|
---|
134 | $openoffice_available = 1;
|
---|
135 | }
|
---|
136 | push(@$arguments,@$opt_windows_args);
|
---|
137 | }
|
---|
138 | elsif ($auto_converter_self->{'openoffice_available'}) {
|
---|
139 | push (@$arguments,@$opt_office_args);
|
---|
140 | $openoffice_available = 1;
|
---|
141 | }
|
---|
142 | # TODO need to do the case where they are both enabled!!! what will the convert to list be???
|
---|
143 |
|
---|
144 | # evaluate the default for process_exp - it needs to be delayed till here so we know if openoffice is available or not. But needs to be done before parsing the args.
|
---|
145 | foreach my $a (@$arguments) {
|
---|
146 | if ($a->{'name'} eq "process_exp") {
|
---|
147 | my $eval_expr = $a->{'deft'};
|
---|
148 | if ($eval_expr =~ m/^&/) {
|
---|
149 | $a->{'deft'} = eval "$eval_expr";
|
---|
150 | }
|
---|
151 | last;
|
---|
152 | }
|
---|
153 | }
|
---|
154 |
|
---|
155 | push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});
|
---|
156 |
|
---|
157 | my $cbf_self = new ConvertBinaryFile($pluginlist, $inputargs, $hashArgOptLists);
|
---|
158 | my $self = BaseImporter::merge_inheritance($auto_converter_self, $cbf_self);
|
---|
159 |
|
---|
160 | if ($self->{'info_only'}) {
|
---|
161 | # don't worry about any options etc
|
---|
162 | return bless $self, $class;
|
---|
163 | }
|
---|
164 |
|
---|
165 | $self = bless $self, $class;
|
---|
166 | $self->{'file_type'} = "PPT";
|
---|
167 |
|
---|
168 | if ($self->{'convert_to'} eq "auto") {
|
---|
169 | if ($self->{'windows_scripting'}) {
|
---|
170 | $self->{'convert_to'} = "pagedimg_jpg";
|
---|
171 | }
|
---|
172 | else {
|
---|
173 | $self->{'convert_to'} = "html";
|
---|
174 | }
|
---|
175 | }
|
---|
176 |
|
---|
177 | my $outhandle = $self->{'outhandle'};
|
---|
178 |
|
---|
179 | # can't have windows_scripting and openoffice_conversion at the same time
|
---|
180 | if ($self->{'windows_scripting'} && $self->{'openoffice_conversion'}) {
|
---|
181 | print $outhandle "Warning: Cannot have -windows_scripting and -openoffice_conversion\n";
|
---|
182 | print $outhandle " on at the same time. Defaulting to -windows_scripting\n";
|
---|
183 | $self->{'openoffice_conversion'} = 0;
|
---|
184 | }
|
---|
185 |
|
---|
186 | #these are passed through to gsConvert.pl by ConvertBinaryFile.pm
|
---|
187 | $self->{'convert_options'} = "-windows_scripting" if $self->{'windows_scripting'};
|
---|
188 |
|
---|
189 | # set convert_to_plugin and convert_to_ext
|
---|
190 | $self->set_standard_convert_settings();
|
---|
191 |
|
---|
192 | my $secondary_plugin_name = $self->{'convert_to_plugin'};
|
---|
193 | my $secondary_plugin_options = $self->{'secondary_plugin_options'};
|
---|
194 |
|
---|
195 | if (!defined $secondary_plugin_options->{$secondary_plugin_name}) {
|
---|
196 | $secondary_plugin_options->{$secondary_plugin_name} = [];
|
---|
197 | }
|
---|
198 | my $specific_options = $secondary_plugin_options->{$secondary_plugin_name};
|
---|
199 |
|
---|
200 | push(@$specific_options, "-file_rename_method", "none");
|
---|
201 | push(@$specific_options, "-extract_language") if $self->{'extract_language'};
|
---|
202 |
|
---|
203 | if ($secondary_plugin_name eq "HTMLPlugin") {
|
---|
204 | push(@$specific_options, "-processing_tmp_files");
|
---|
205 | push(@$specific_options,"-metadata_fields","Title,GENERATOR,date,author<Creator>");
|
---|
206 | }
|
---|
207 | elsif ($secondary_plugin_name eq "PagedImagePlugin") {
|
---|
208 | push(@$specific_options, "-processing_tmp_files");
|
---|
209 | #is this true??
|
---|
210 | push(@$specific_options,"-input_encoding", "utf8");
|
---|
211 | if ($self->{'openoffice_conversion'}) {
|
---|
212 | push(@$specific_options, "-create_thumbnail", "false", "-create_screenview", "false");
|
---|
213 | }
|
---|
214 | }
|
---|
215 |
|
---|
216 | $self = bless $self, $class;
|
---|
217 |
|
---|
218 | $self->load_secondary_plugins($class,$secondary_plugin_options,$hashArgOptLists);
|
---|
219 | return $self;
|
---|
220 | }
|
---|
221 |
|
---|
222 | sub get_default_process_exp {
|
---|
223 | my $self = shift (@_);
|
---|
224 |
|
---|
225 | if ($openoffice_available) {
|
---|
226 | return q^(?i)\.(ppt|pptx|odp)$^;
|
---|
227 | }
|
---|
228 |
|
---|
229 | return q^(?i)\.ppt$^;
|
---|
230 | }
|
---|
231 |
|
---|
232 | sub init {
|
---|
233 | my $self = shift (@_);
|
---|
234 |
|
---|
235 | # ConvertBinaryFile init
|
---|
236 | $self->SUPER::init(@_);
|
---|
237 | $self->AutoLoadConverters::init(@_);
|
---|
238 |
|
---|
239 | }
|
---|
240 |
|
---|
241 | sub begin {
|
---|
242 | my $self = shift (@_);
|
---|
243 |
|
---|
244 | $self->AutoLoadConverters::begin(@_);
|
---|
245 | $self->SUPER::begin(@_);
|
---|
246 |
|
---|
247 | }
|
---|
248 |
|
---|
249 | sub deinit {
|
---|
250 | my $self = shift (@_);
|
---|
251 |
|
---|
252 | $self->AutoLoadConverters::deinit(@_);
|
---|
253 | $self->SUPER::deinit(@_);
|
---|
254 |
|
---|
255 | }
|
---|
256 |
|
---|
257 | # override AutoLoadConverters version, as we need to do more stuff once its converted if we are converting to item file
|
---|
258 | sub tmp_area_convert_file {
|
---|
259 | my $self = shift (@_);
|
---|
260 | my ($output_ext, $input_filename, $textref) = @_;
|
---|
261 |
|
---|
262 | if ($self->{'openoffice_conversion'}) {
|
---|
263 | if ($self->{'convert_to'} eq "pagedimg") {
|
---|
264 | $output_ext = "html"; # first convert to html
|
---|
265 | }
|
---|
266 | my ($result, $result_str, $new_filename) = $self->OpenOfficeConverter::convert($input_filename, $output_ext);
|
---|
267 | if ($result == 0) {
|
---|
268 | my $outhandle=$self->{'outhandle'};
|
---|
269 | print $outhandle "OpenOfficeConverter Conversion error\n";
|
---|
270 | print $outhandle $result_str;
|
---|
271 | return "";
|
---|
272 |
|
---|
273 | }
|
---|
274 | #print STDERR "result = $result\n";
|
---|
275 | if ($self->{'convert_to'} eq "pagedimg") {
|
---|
276 | my $item_filename = $self->generate_item_file($new_filename);
|
---|
277 | return $item_filename;
|
---|
278 | }
|
---|
279 | return $new_filename;
|
---|
280 |
|
---|
281 | }
|
---|
282 | else {
|
---|
283 | return $self->ConvertBinaryFile::tmp_area_convert_file(@_);
|
---|
284 | }
|
---|
285 | # get tmp filename
|
---|
286 | }
|
---|
287 |
|
---|
288 | # override default read in some situations, as the conversion of ppt to html results in many files, and we want them all to be processed.
|
---|
289 | sub read {
|
---|
290 | my $self = shift (@_);
|
---|
291 | my ($pluginfo, $base_dir, $file, $block_hash, $metadata, $processor, $maxdocs, $total_count, $gli) = @_;
|
---|
292 |
|
---|
293 | # can we process this file??
|
---|
294 | my ($filename_full_path, $filename_no_path) = &util::get_full_filenames($base_dir, $file);
|
---|
295 |
|
---|
296 | return undef unless $self->can_process_this_file($filename_full_path);
|
---|
297 |
|
---|
298 | # we are only doing something special for html_multi
|
---|
299 | if (!($self->{'openoffice_conversion'} && $self->{'convert_to'} eq "html_multi")) {
|
---|
300 | return $self->BaseImporter::read(@_);
|
---|
301 | }
|
---|
302 | my $outhandle = $self->{'outhandle'};
|
---|
303 | print STDERR "<Processing n='$file' p='$self->{'plugin_type'}'>\n" if ($gli);
|
---|
304 | print $outhandle "$self->{'plugin_type'} processing $file\n"
|
---|
305 | if $self->{'verbosity'} > 1;
|
---|
306 |
|
---|
307 | my $conv_filename = $self->tmp_area_convert_file("html", $filename_full_path);
|
---|
308 | if ("$conv_filename" eq "") {return -1;} # had an error, will be passed down pipeline
|
---|
309 | if (! -e "$conv_filename") {return -1;}
|
---|
310 |
|
---|
311 | my ($tailname, $html_dirname, $suffix)
|
---|
312 | = &File::Basename::fileparse($conv_filename, "\\.[^\\.]+\$");
|
---|
313 |
|
---|
314 | my $collect_file = &util::filename_within_collection($filename_full_path);
|
---|
315 | my $dirname_within_collection = &util::filename_within_collection($html_dirname);
|
---|
316 | my $secondary_plugin = $self->{'secondary_plugins'}->{"HTMLPlugin"};
|
---|
317 |
|
---|
318 | my @dir;
|
---|
319 | if (!opendir (DIR, $html_dirname)) {
|
---|
320 | print $outhandle "PowerPointPlugin: Couldn't read directory $html_dirname\n";
|
---|
321 | # just process the original file
|
---|
322 | @dir = ("$tailname.$suffix");
|
---|
323 |
|
---|
324 | } else {
|
---|
325 | @dir = readdir (DIR);
|
---|
326 | closedir (DIR);
|
---|
327 | }
|
---|
328 |
|
---|
329 | foreach my $file (@dir) {
|
---|
330 | next unless $file =~ /\.html$/;
|
---|
331 |
|
---|
332 | my ($rv, $doc_obj) =
|
---|
333 | $secondary_plugin->read_into_doc_obj ($pluginfo,"", &util::filename_cat($html_dirname,$file), $block_hash, {}, $processor, $maxdocs, $total_count, $gli);
|
---|
334 | if ((!defined $rv) || ($rv<1)) {
|
---|
335 | # wasn't processed
|
---|
336 | return $rv;
|
---|
337 | }
|
---|
338 |
|
---|
339 | # next block copied from ConvertBinaryFile
|
---|
340 | # from here ...
|
---|
341 | # Override previous gsdlsourcefilename set by secondary plugin
|
---|
342 |
|
---|
343 | $doc_obj->set_source_filename ($collect_file, $self->{'file_rename_method'});
|
---|
344 | ## set_source_filename does not set the doc_obj source_path which is used in archives dbs for incremental
|
---|
345 | # build. so set it manually.
|
---|
346 | $doc_obj->set_source_path($filename_full_path);
|
---|
347 | $doc_obj->set_converted_filename(&util::filename_cat($dirname_within_collection, $file));
|
---|
348 |
|
---|
349 | my $plugin_filename_encoding = $self->{'filename_encoding'};
|
---|
350 | my $filename_encoding = $self->deduce_filename_encoding($file,$metadata,$plugin_filename_encoding);
|
---|
351 | $self->set_Source_metadata($doc_obj, $filename_full_path,$filename_encoding);
|
---|
352 |
|
---|
353 | $doc_obj->set_utf8_metadata_element($doc_obj->get_top_section(), "Plugin", "$self->{'plugin_type'}");
|
---|
354 | $doc_obj->set_utf8_metadata_element($doc_obj->get_top_section(), "FileSize", (-s $filename_full_path));
|
---|
355 |
|
---|
356 |
|
---|
357 | my ($tailname, $dirname, $suffix)
|
---|
358 | = &File::Basename::fileparse($filename_full_path, "\\.[^\\.]+\$");
|
---|
359 | $doc_obj->set_utf8_metadata_element($doc_obj->get_top_section(), "FilenameRoot", $tailname);
|
---|
360 |
|
---|
361 |
|
---|
362 | my $topsection = $doc_obj->get_top_section();
|
---|
363 | $self->add_associated_files($doc_obj, $filename_full_path);
|
---|
364 |
|
---|
365 | # extra_metadata is already called by sec plugin in process??
|
---|
366 | $self->extra_metadata($doc_obj, $topsection, $metadata); # do we need this here??
|
---|
367 | # do any automatic metadata extraction
|
---|
368 | $self->auto_extract_metadata ($doc_obj);
|
---|
369 |
|
---|
370 | # have we found a Title??
|
---|
371 | $self->title_fallback($doc_obj,$topsection,$filename_no_path);
|
---|
372 |
|
---|
373 | # use the one generated by HTMLPlugin, otherwise they all end up with same id.
|
---|
374 | #$self->add_OID($doc_obj);
|
---|
375 | # to here...
|
---|
376 |
|
---|
377 | # process it
|
---|
378 | $processor->process($doc_obj);
|
---|
379 | undef $doc_obj;
|
---|
380 | }
|
---|
381 | $self->{'num_processed'} ++;
|
---|
382 |
|
---|
383 | # my ($process_status,$doc_obj) = $self->read_into_doc_obj(@_);
|
---|
384 |
|
---|
385 | # if ((defined $process_status) && ($process_status == 1)) {
|
---|
386 |
|
---|
387 | # process the document
|
---|
388 | # $processor->process($doc_obj);
|
---|
389 |
|
---|
390 | # $self->{'num_processed'} ++;
|
---|
391 | # undef $doc_obj;
|
---|
392 | # }
|
---|
393 | # delete any temp files that we may have created
|
---|
394 | $self->clean_up_after_doc_obj_processing();
|
---|
395 |
|
---|
396 |
|
---|
397 | # if process_status == 1, then the file has been processed.
|
---|
398 | return 1;
|
---|
399 |
|
---|
400 | }
|
---|
401 |
|
---|
402 | # want to sort img1, img2, ...img10, img11 etc.
|
---|
403 | sub alphanum_sort {
|
---|
404 |
|
---|
405 | my ($a_txt, $a_num) = $a =~ /^([^\d]*)(\d*)/;
|
---|
406 | my ($b_txt, $b_num) = $b =~ /^([^\d]*)(\d*)/;
|
---|
407 |
|
---|
408 | if ($a_txt ne $b_txt) { return ($a cmp $b) };
|
---|
409 | return ($a_num <=> $b_num);
|
---|
410 | }
|
---|
411 |
|
---|
412 | # Want to remove the line that links to first page, last page, next page, text etc.
|
---|
413 | sub tidy_up_html {
|
---|
414 |
|
---|
415 | my $self = shift(@_);
|
---|
416 | my ($filename) = @_;
|
---|
417 | return unless (-f $filename);
|
---|
418 | my $backup_filename = "$filename.bak";
|
---|
419 |
|
---|
420 | &File::Copy::copy($filename, $backup_filename);
|
---|
421 |
|
---|
422 | open (ORIGINAL, $backup_filename) || return;
|
---|
423 | open(HTMLFILE, ">$filename") || return;
|
---|
424 |
|
---|
425 | my $line ="";
|
---|
426 | while ($line = <ORIGINAL>) {
|
---|
427 | if ($line =~ /\<body\>/) {
|
---|
428 | print HTMLFILE $line;
|
---|
429 | $line = <ORIGINAL>;
|
---|
430 | next if $line =~ /\<center\>/;
|
---|
431 | }
|
---|
432 | next if $line =~ /First page/;
|
---|
433 | print HTMLFILE ($line);
|
---|
434 | }
|
---|
435 |
|
---|
436 | close HTMLFILE;
|
---|
437 | close ORIGINAL;
|
---|
438 | }
|
---|
439 | 1;
|
---|
440 |
|
---|