| 1 | ###########################################################################
|
|---|
| 2 | #
|
|---|
| 3 | # UnknownConverterPlugin.pm -- plugin that runs the provided cmdline cmd
|
|---|
| 4 | # to launch an custom unknown external conversion application that will
|
|---|
| 5 | # convert from some custom unknown format to one of txt, html or xml.
|
|---|
| 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) 1999-2005 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 UnknownConverterPlugin;
|
|---|
| 30 |
|
|---|
| 31 | use strict;
|
|---|
| 32 | no strict 'subs';
|
|---|
| 33 | no strict 'refs'; # allow filehandles to be variables and viceversa
|
|---|
| 34 |
|
|---|
| 35 |
|
|---|
| 36 | # TO DO:
|
|---|
| 37 | # - error messages and other display strings need to go into strings.properties
|
|---|
| 38 | # - Have a TEMPDIR placeholder in the command, which, if present, gets replaced with the usual tempdir location
|
|---|
| 39 | # of a collection, and in which case we have to clean up intermediate files generated in there at the end?
|
|---|
| 40 |
|
|---|
| 41 | sub BEGIN {
|
|---|
| 42 | @UnknownConverterPlugin::ISA = ('UnknownPlugin', 'ConvertBinaryFile');
|
|---|
| 43 | }
|
|---|
| 44 |
|
|---|
| 45 | my $convert_to_list =
|
|---|
| 46 | [ { 'name' => "text",
|
|---|
| 47 | 'desc' => "{ConvertBinaryFile.convert_to.text}" },
|
|---|
| 48 | { 'name' => "html",
|
|---|
| 49 | 'desc' => "{ConvertBinaryFile.convert_to.html}" },
|
|---|
| 50 | { 'name' => "pagedimg_jpg",
|
|---|
| 51 | 'desc' => "{{ConvertBinaryFile.convert_to.pagedimg_jpg}" },
|
|---|
| 52 | { 'name' => "pagedimg_gif",
|
|---|
| 53 | 'desc' => "{{ConvertBinaryFile.convert_to.pagedimg_gif}" },
|
|---|
| 54 | { 'name' => "pagedimg_png",
|
|---|
| 55 | 'desc' => "{{ConvertBinaryFile.convert_to.pagedimg_png}" }
|
|---|
| 56 | ];
|
|---|
| 57 |
|
|---|
| 58 | my $arguments =
|
|---|
| 59 | [ { 'name' => "exec_cmd",
|
|---|
| 60 | 'desc' => "{UnknownConverterPlugin.exec_cmd}",
|
|---|
| 61 | 'type' => "string",
|
|---|
| 62 | 'deft' => "",
|
|---|
| 63 | 'reqd' => "yes" },
|
|---|
| 64 | { 'name' => "convert_to",
|
|---|
| 65 | 'desc' => "{ConvertBinaryFile.convert_to}",
|
|---|
| 66 | 'type' => "enum",
|
|---|
| 67 | 'reqd' => "yes",
|
|---|
| 68 | 'list' => $convert_to_list,
|
|---|
| 69 | 'deft' => "text" },
|
|---|
| 70 | { 'name' => "output_file_or_dir_name",
|
|---|
| 71 | 'desc' => "{UnknownConverterPlugin.output_file_or_dir_name}",
|
|---|
| 72 | 'type' => "string",
|
|---|
| 73 | 'reqd' => "yes",
|
|---|
| 74 | 'deft' => "" } ];
|
|---|
| 75 |
|
|---|
| 76 | my $options = { 'name' => "UnknownConverterPlugin",
|
|---|
| 77 | 'desc' => "{UnknownConverterPlugin.desc}",
|
|---|
| 78 | 'abstract' => "no",
|
|---|
| 79 | 'inherits' => "yes",
|
|---|
| 80 | 'args' => $arguments };
|
|---|
| 81 |
|
|---|
| 82 |
|
|---|
| 83 | sub new {
|
|---|
| 84 | my ($class) = shift (@_);
|
|---|
| 85 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
|---|
| 86 | push(@$pluginlist, $class);
|
|---|
| 87 |
|
|---|
| 88 | push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});
|
|---|
| 89 | push(@{$hashArgOptLists->{"OptList"}},$options);
|
|---|
| 90 |
|
|---|
| 91 | my $cbf_self = new ConvertBinaryFile($pluginlist, $inputargs, $hashArgOptLists);
|
|---|
| 92 | my $unknown_converter_self = new UnknownPlugin($pluginlist, $inputargs, $hashArgOptLists);
|
|---|
| 93 | my $self = BaseImporter::merge_inheritance($cbf_self, $unknown_converter_self);
|
|---|
| 94 |
|
|---|
| 95 | $self = bless $self, $class;
|
|---|
| 96 |
|
|---|
| 97 |
|
|---|
| 98 | # Convert_To set up, including secondary_plugins for processing the text or html generated
|
|---|
| 99 | # set convert_to_plugin and convert_to_ext
|
|---|
| 100 | $self->set_standard_convert_settings();
|
|---|
| 101 |
|
|---|
| 102 | my $secondary_plugin_name = $self->{'convert_to_plugin'};
|
|---|
| 103 | my $secondary_plugin_options = $self->{'secondary_plugin_options'};
|
|---|
| 104 |
|
|---|
| 105 | if (!defined $secondary_plugin_options->{$secondary_plugin_name}) {
|
|---|
| 106 | $secondary_plugin_options->{$secondary_plugin_name} = [];
|
|---|
| 107 | }
|
|---|
| 108 | my $specific_options = $secondary_plugin_options->{$secondary_plugin_name};
|
|---|
| 109 |
|
|---|
| 110 | # using defaults for secondary plugins, taken from RTFPlugin
|
|---|
| 111 | push(@$specific_options, "-file_rename_method", "none");
|
|---|
| 112 | push(@$specific_options, "-extract_language") if $self->{'extract_language'};
|
|---|
| 113 | if ($secondary_plugin_name eq "TextPlugin") {
|
|---|
| 114 | push(@$specific_options, "-input_encoding", "utf8");
|
|---|
| 115 | }
|
|---|
| 116 | elsif ($secondary_plugin_name eq "HTMLPlugin") {
|
|---|
| 117 | push(@$specific_options, "-description_tags") if $self->{'description_tags'};
|
|---|
| 118 | push(@$specific_options, "-processing_tmp_files");
|
|---|
| 119 | }
|
|---|
| 120 |
|
|---|
| 121 | # bless again, copied from PDFPlugin, PowerPointPlugin
|
|---|
| 122 | $self = bless $self, $class;
|
|---|
| 123 | $self->load_secondary_plugins($class,$secondary_plugin_options,$hashArgOptLists;)
|
|---|
| 124 | return $self;
|
|---|
| 125 | }
|
|---|
| 126 |
|
|---|
| 127 | # Are init, begin and deinit necessary (will they not get called automatically)?
|
|---|
| 128 | # Copied here from PDFPlugin, PowerPointPlugin
|
|---|
| 129 | # https://stackoverflow.com/questions/42885207/why-doesnt-class-supernew-call-the-constructors-of-all-parent-classes-when
|
|---|
| 130 | # "$class->SUPER::new always calls A::new because A comes before B in @ISA. See method resolution order in perlobj: ..."
|
|---|
| 131 | # https://stackoverflow.com/questions/15414696/when-using-multiple-inheritance-in-perl-is-there-a-way-to-indicate-which-super-f
|
|---|
| 132 | sub init {
|
|---|
| 133 | my $self = shift (@_);
|
|---|
| 134 |
|
|---|
| 135 | # ConvertBinaryFile init
|
|---|
| 136 | $self->ConvertBinaryFile::init(@_);
|
|---|
| 137 | }
|
|---|
| 138 |
|
|---|
| 139 | sub begin {
|
|---|
| 140 | my $self = shift (@_);
|
|---|
| 141 |
|
|---|
| 142 | $self->ConvertBinaryFile::begin(@_);
|
|---|
| 143 |
|
|---|
| 144 | }
|
|---|
| 145 |
|
|---|
| 146 | sub deinit {
|
|---|
| 147 | my $self = shift (@_);
|
|---|
| 148 |
|
|---|
| 149 | $self->ConvertBinaryFile::deinit(@_);
|
|---|
| 150 |
|
|---|
| 151 | }
|
|---|
| 152 |
|
|---|
| 153 | # overridden to run the custom conversion command here in place of gsConvert.pl called by ConvertBinaryFile.pm
|
|---|
| 154 | sub tmp_area_convert_file {
|
|---|
| 155 | # should we first hardlink the output files/folder to tmp area, so we won't be working across drives?
|
|---|
| 156 |
|
|---|
| 157 | my $self = shift (@_);
|
|---|
| 158 | my ($output_ext, $input_filename, $textref) = @_;
|
|---|
| 159 |
|
|---|
| 160 | my $plugin_name = $self->{'plugin_type'}; # inherited from BaseImporter
|
|---|
| 161 |
|
|---|
| 162 | # On Linux: if the program isn't installed, $? tends to come back with 127, in any case neither 0 nor 1.
|
|---|
| 163 | # On Windows: echo %ERRORLEVEL% ends up as 9009 if the program is not installed.
|
|---|
| 164 | # If running the command returns 0, let's assume success and so the act of running the command
|
|---|
| 165 | # should produce either a text file or output to stdout.
|
|---|
| 166 |
|
|---|
| 167 | my $outhandle=$self->{'outhandle'};
|
|---|
| 168 |
|
|---|
| 169 | my $cmd = $self->{'exec_cmd'};
|
|---|
| 170 | if(!$cmd) { # empty string for instance
|
|---|
| 171 | print $outhandle "$plugin_name Conversion error: invalid cmd $cmd\n";
|
|---|
| 172 | return "";
|
|---|
| 173 | }
|
|---|
| 174 |
|
|---|
| 175 | # replace occurrences of '*' placeholder in cmd string with input filename
|
|---|
| 176 | my ($tailname, $dir, $suffix) = &File::Basename::fileparse($input_filename, "\\.[^\\.]+\$");
|
|---|
| 177 | $cmd ~= s/\*/$tailname/g;
|
|---|
| 178 | print STDERR "@@@@ $plugin_name: executing conversion cmd $cmd\n";
|
|---|
| 179 | my $status = system($cmd);
|
|---|
| 180 |
|
|---|
| 181 | if($status == 127 || $status == 9009) { # means the cmd isn't recognised on Unix and Windows, respectively
|
|---|
| 182 | print $outhandle "$plugin_name Conversion error: cmd unrecognised, may not be installed (got $status when running $cmd)\n";
|
|---|
| 183 | return "";
|
|---|
| 184 | }
|
|---|
| 185 |
|
|---|
| 186 | if($status != 0) {
|
|---|
| 187 | print $outhandle "$plugin_name Conversion error: conversion failed with exit value $status\n";
|
|---|
| 188 | return "";
|
|---|
| 189 | }
|
|---|
| 190 |
|
|---|
| 191 | my $output_file_or_dir = $self->{'output_file_or_dir_name'};
|
|---|
| 192 | if (!-e $output_file_or_dir) {
|
|---|
| 193 | print $outhandle "$plugin_name Conversion error: Output file/dir $output_file_or_dir doesn't exist\n";
|
|---|
| 194 | return "";
|
|---|
| 195 | }
|
|---|
| 196 |
|
|---|
| 197 | # else, conversion success
|
|---|
| 198 |
|
|---|
| 199 | # if multiple images were generated by running the conversion
|
|---|
| 200 | if ($self->{'convert_to'} eq "pagedimg") {
|
|---|
| 201 | my $item_filename = $self->generate_item_file($output_file_or_dir);
|
|---|
| 202 | return $item_filename;
|
|---|
| 203 | }
|
|---|
| 204 |
|
|---|
| 205 | return $output_file_or_dir;
|
|---|
| 206 | }
|
|---|
| 207 |
|
|---|
| 208 | # Copied from PowerPointPlugin, with some modifications
|
|---|
| 209 | # 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.
|
|---|
| 210 | sub read {
|
|---|
| 211 | my $self = shift (@_);
|
|---|
| 212 | my ($pluginfo, $base_dir, $file, $block_hash, $metadata, $processor, $maxdocs, $total_count, $gli) = @_;
|
|---|
| 213 |
|
|---|
| 214 | # can we process this file??
|
|---|
| 215 | my ($filename_full_path, $filename_no_path) = &util::get_full_filenames($base_dir, $file);
|
|---|
| 216 |
|
|---|
| 217 | return undef unless $self->can_process_this_file($filename_full_path);
|
|---|
| 218 |
|
|---|
| 219 | my $output_file_or_dir = $self->{'output_file_or_dir_name'};
|
|---|
| 220 | my $is_output_dir = (-d $output_file_or_dir) ? 1 : 0;
|
|---|
| 221 |
|
|---|
| 222 | # we are only doing something special if we have a directory of html files
|
|---|
| 223 | if (!$is_output_dir || $self->{'convert_to'} ne "html") {
|
|---|
| 224 | return $self->BaseImporter::read(@_); # no read in ConvertBinaryFile.pm
|
|---|
| 225 | }
|
|---|
| 226 | my $outhandle = $self->{'outhandle'};
|
|---|
| 227 | print STDERR "<Processing n='$file' p='$self->{'plugin_type'}'>\n" if ($gli);
|
|---|
| 228 | print $outhandle "$self->{'plugin_type'} processing $file\n"
|
|---|
| 229 | if $self->{'verbosity'} > 1;
|
|---|
| 230 |
|
|---|
| 231 | my $conv_filename = $self->tmp_area_convert_file("html", $filename_full_path); # uses our overridden version
|
|---|
| 232 | if ("$conv_filename" eq "") {return -1;} # had an error, will be passed down pipeline
|
|---|
| 233 | if (! -e "$conv_filename") {return -1;}
|
|---|
| 234 |
|
|---|
| 235 | my ($tailname, $html_dirname, $suffix)
|
|---|
| 236 | = &File::Basename::fileparse($conv_filename, "\\.[^\\.]+\$");
|
|---|
| 237 |
|
|---|
| 238 | my $collect_file = &util::filename_within_collection($filename_full_path);
|
|---|
| 239 | my $dirname_within_collection = &util::filename_within_collection($html_dirname);
|
|---|
| 240 | my $secondary_plugin = $self->{'secondary_plugins'}->{"HTMLPlugin"};
|
|---|
| 241 |
|
|---|
| 242 | my @dir;
|
|---|
| 243 | if (!opendir (DIR, $html_dirname)) {
|
|---|
| 244 | print $outhandle "PowerPointPlugin: Couldn't read directory $html_dirname\n";
|
|---|
| 245 | # just process the original file
|
|---|
| 246 | @dir = ("$tailname.$suffix");
|
|---|
| 247 |
|
|---|
| 248 | } else {
|
|---|
| 249 | @dir = readdir (DIR);
|
|---|
| 250 | closedir (DIR);
|
|---|
| 251 | }
|
|---|
| 252 |
|
|---|
| 253 | foreach my $file (@dir) {
|
|---|
| 254 | next unless $file =~ /\.html$/;
|
|---|
| 255 |
|
|---|
| 256 | my ($rv, $doc_obj) =
|
|---|
| 257 | $secondary_plugin->read_into_doc_obj ($pluginfo,"", &util::filename_cat($html_dirname,$file), $block_hash, {}, $processor, $maxdocs, $total_count, $gli);
|
|---|
| 258 | if ((!defined $rv) || ($rv<1)) {
|
|---|
| 259 | # wasn't processed
|
|---|
| 260 | return $rv;
|
|---|
| 261 | }
|
|---|
| 262 |
|
|---|
| 263 | # next block copied from ConvertBinaryFile
|
|---|
| 264 | # from here ...
|
|---|
| 265 | # Override previous gsdlsourcefilename set by secondary plugin
|
|---|
| 266 |
|
|---|
| 267 | $doc_obj->set_source_filename ($collect_file, $self->{'file_rename_method'});
|
|---|
| 268 | ## set_source_filename does not set the doc_obj source_path which is used in archives dbs for incremental
|
|---|
| 269 | # build. so set it manually.
|
|---|
| 270 | $doc_obj->set_source_path($filename_full_path);
|
|---|
| 271 | $doc_obj->set_converted_filename(&util::filename_cat($dirname_within_collection, $file));
|
|---|
| 272 |
|
|---|
| 273 | my $plugin_filename_encoding = $self->{'filename_encoding'};
|
|---|
| 274 | my $filename_encoding = $self->deduce_filename_encoding($file,$metadata,$plugin_filename_encoding);
|
|---|
| 275 | $self->set_Source_metadata($doc_obj, $filename_full_path,$filename_encoding);
|
|---|
| 276 |
|
|---|
| 277 | $doc_obj->set_utf8_metadata_element($doc_obj->get_top_section(), "Plugin", "$self->{'plugin_type'}");
|
|---|
| 278 | $doc_obj->set_utf8_metadata_element($doc_obj->get_top_section(), "FileSize", (-s $filename_full_path));
|
|---|
| 279 |
|
|---|
| 280 |
|
|---|
| 281 | my ($tailname, $dirname, $suffix)
|
|---|
| 282 | = &File::Basename::fileparse($filename_full_path, "\\.[^\\.]+\$");
|
|---|
| 283 | $doc_obj->set_utf8_metadata_element($doc_obj->get_top_section(), "FilenameRoot", $tailname);
|
|---|
| 284 |
|
|---|
| 285 |
|
|---|
| 286 | my $topsection = $doc_obj->get_top_section();
|
|---|
| 287 | $self->add_associated_files($doc_obj, $filename_full_path);
|
|---|
| 288 |
|
|---|
| 289 | # extra_metadata is already called by sec plugin in process??
|
|---|
| 290 | $self->extra_metadata($doc_obj, $topsection, $metadata); # do we need this here??
|
|---|
| 291 | # do any automatic metadata extraction
|
|---|
| 292 | $self->auto_extract_metadata ($doc_obj);
|
|---|
| 293 |
|
|---|
| 294 | # have we found a Title??
|
|---|
| 295 | $self->title_fallback($doc_obj,$topsection,$filename_no_path);
|
|---|
| 296 |
|
|---|
| 297 | # use the one generated by HTMLPlugin, otherwise they all end up with same id.
|
|---|
| 298 | #$self->add_OID($doc_obj);
|
|---|
| 299 | # to here...
|
|---|
| 300 |
|
|---|
| 301 | # process it
|
|---|
| 302 | $processor->process($doc_obj);
|
|---|
| 303 | undef $doc_obj;
|
|---|
| 304 | }
|
|---|
| 305 | $self->{'num_processed'} ++;
|
|---|
| 306 |
|
|---|
| 307 | # deleted some commented out code here that exists in PowerPointPlugin
|
|---|
| 308 |
|
|---|
| 309 | # for UnknownConverterPlugin, don't delete any temp files that the conversion may have created
|
|---|
| 310 | # as we don't know where it was created
|
|---|
| 311 | #$self->clean_up_after_doc_obj_processing();
|
|---|
| 312 |
|
|---|
| 313 |
|
|---|
| 314 | # if process_status == 1, then the file has been processed.
|
|---|
| 315 | return 1;
|
|---|
| 316 |
|
|---|
| 317 | }
|
|---|
| 318 |
|
|---|
| 319 | # use the read_into_doc_obj inherited from ConvertBinaryFile "to call secondary plugin stuff"
|
|---|
| 320 | sub read_into_doc_obj {
|
|---|
| 321 | my $self = shift (@_);
|
|---|
| 322 | $self->ConvertBinaryFile::deinit(@_);
|
|---|
| 323 | }
|
|---|
| 324 |
|
|---|
| 325 | sub process {
|
|---|
| 326 | my $self = shift (@_);
|
|---|
| 327 | $self->UnknownPlugin::process(@_);
|
|---|
| 328 | }
|
|---|
| 329 |
|
|---|
| 330 | # do we also need a html_multi option to convert_to?
|
|---|
| 331 | # move the following, copied from PPT Plugin, into parent ConvertBinaryPlugin, as it's now shared
|
|---|
| 332 | sub generate_item_file {
|
|---|
| 333 | my $self = shift(@_);
|
|---|
| 334 | my ($input_filename) = @_;
|
|---|
| 335 | my $outhandle = $self->{'outhandle'};
|
|---|
| 336 | my ($tailname, $dirname, $suffix)
|
|---|
| 337 | = &File::Basename::fileparse($input_filename, "\\.[^\\.]+\$");
|
|---|
| 338 |
|
|---|
| 339 | my $plugin_name = $self->{'plugin_type'}; # inherited from BaseImporter
|
|---|
| 340 |
|
|---|
| 341 | # find all the files in the directory
|
|---|
| 342 | if (!opendir (DIR, $dirname)) {
|
|---|
| 343 | print $outhandle "$plugin_name: Couldn't read directory $dirname\n";
|
|---|
| 344 | return $input_filename;
|
|---|
| 345 | }
|
|---|
| 346 |
|
|---|
| 347 | my @dir = readdir (DIR);
|
|---|
| 348 | closedir (DIR);
|
|---|
| 349 |
|
|---|
| 350 | # start the item file
|
|---|
| 351 | my $itemfile_name = &util::filename_cat($dirname, "$tailname.item");
|
|---|
| 352 |
|
|---|
| 353 | # encoding specification????
|
|---|
| 354 | if (!open (ITEMFILE, ">$itemfile_name")) {
|
|---|
| 355 | print $outhandle "$plugin_name: Couldn't open $itemfile_name for writing\n";
|
|---|
| 356 | }
|
|---|
| 357 | print ITEMFILE "<GeneratedBy>$plugin_name\n";
|
|---|
| 358 | # print the first page
|
|---|
| 359 | my @sorted_dir = sort alphanum_sort @dir;
|
|---|
| 360 | for (my $i = 0; $i < scalar(@sorted_dir); $i++) {
|
|---|
| 361 | my $file = $sorted_dir[$i];
|
|---|
| 362 | if ($file =~ /^img(\d+)\.jpg$/) {
|
|---|
| 363 | my $num = $1;
|
|---|
| 364 | $self->tidy_up_html(&util::filename_cat($dirname, "text$num.html"));
|
|---|
| 365 | print ITEMFILE "$num:img$num.jpg:text$num.html:\n";
|
|---|
| 366 | }
|
|---|
| 367 | }
|
|---|
| 368 | close ITEMFILE;
|
|---|
| 369 | return $itemfile_name;
|
|---|
| 370 |
|
|---|
| 371 | }
|
|---|
