| 1 | ###########################################################################
|
|---|
| 2 | #
|
|---|
| 3 | # ConvertToPlug.pm -- plugin that inherits from BasPlug
|
|---|
| 4 | #
|
|---|
| 5 | # A component of the Greenstone digital library software
|
|---|
| 6 | # from the New Zealand Digital Library Project at the
|
|---|
| 7 | # University of Waikato, New Zealand.
|
|---|
| 8 | #
|
|---|
| 9 | # Copyright (C) 1999 New Zealand Digital Library Project
|
|---|
| 10 | #
|
|---|
| 11 | # This program is free software; you can redistribute it and/or modify
|
|---|
| 12 | # it under the terms of the GNU General Public License as published by
|
|---|
| 13 | # the Free Software Foundation; either version 2 of the License, or
|
|---|
| 14 | # (at your option) any later version.
|
|---|
| 15 | #
|
|---|
| 16 | # This program is distributed in the hope that it will be useful,
|
|---|
| 17 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|---|
| 18 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|---|
| 19 | # GNU General Public License for more details.
|
|---|
| 20 | #
|
|---|
| 21 | # You should have received a copy of the GNU General Public License
|
|---|
| 22 | # along with this program; if not, write to the Free Software
|
|---|
| 23 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
|---|
| 24 | #
|
|---|
| 25 | ###########################################################################
|
|---|
| 26 |
|
|---|
| 27 | # This plugin is inherited by such plugins as WordPlug, PPTPlug, PSPlug,
|
|---|
| 28 | # RTFPlug and PDFPlug. It facilitates the conversion of these document types
|
|---|
| 29 | # to either HTML, TEXT or a series of images. It works by dynamically loading
|
|---|
| 30 | # an appropriate secondary plugin (HTMLPlug, StructuredHTMLPlug,
|
|---|
| 31 | # PagedImgPlug or TEXTPlug) based on the plugin argument 'convert_to'.
|
|---|
| 32 |
|
|---|
| 33 | package ConvertToPlug;
|
|---|
| 34 |
|
|---|
| 35 | use BasPlug;
|
|---|
| 36 | use ghtml;
|
|---|
| 37 | use HTMLPlug;
|
|---|
| 38 | use TEXTPlug;
|
|---|
| 39 | use PagedImgPlug;
|
|---|
| 40 |
|
|---|
| 41 | use strict;
|
|---|
| 42 | no strict 'refs'; # allow filehandles to be variables and viceversa
|
|---|
| 43 | no strict 'subs';
|
|---|
| 44 | sub BEGIN {
|
|---|
| 45 | @ConvertToPlug::ISA = ('BasPlug');
|
|---|
| 46 | }
|
|---|
| 47 |
|
|---|
| 48 | my $convert_to_list =
|
|---|
| 49 | [ { 'name' => "auto",
|
|---|
| 50 | 'desc' => "{ConvertToPlug.convert_to.auto}" },
|
|---|
| 51 | { 'name' => "html",
|
|---|
| 52 | 'desc' => "{ConvertToPlug.convert_to.html}" },
|
|---|
| 53 | { 'name' => "text",
|
|---|
| 54 | 'desc' => "{ConvertToPlug.convert_to.text}" }
|
|---|
| 55 | ];
|
|---|
| 56 |
|
|---|
| 57 | my $arguments =
|
|---|
| 58 | [ { 'name' => "convert_to",
|
|---|
| 59 | 'desc' => "{ConvertToPlug.convert_to}",
|
|---|
| 60 | 'type' => "enum",
|
|---|
| 61 | 'reqd' => "yes",
|
|---|
| 62 | 'list' => $convert_to_list,
|
|---|
| 63 | 'deft' => "auto" },
|
|---|
| 64 | { 'name' => "keep_original_filename",
|
|---|
| 65 | 'desc' => "{ConvertToPlug.keep_original_filename}",
|
|---|
| 66 | 'type' => "flag" },
|
|---|
| 67 | { 'name' => "title_sub",
|
|---|
| 68 | 'desc' => "{HTMLPlug.title_sub}",
|
|---|
| 69 | 'type' => "string",
|
|---|
| 70 | #'type' => "regexp",
|
|---|
| 71 | 'deft' => "" },
|
|---|
| 72 | { 'name' => "apply_fribidi",
|
|---|
| 73 | 'desc' => "{ConvertToPlug.apply_fribidi}",
|
|---|
| 74 | 'type' => "flag",
|
|---|
| 75 | 'reqd' => "no" },
|
|---|
| 76 | { 'name' => "use_strings",
|
|---|
| 77 | 'desc' => "{ConvertToPlug.use_strings}",
|
|---|
| 78 | 'type' => "flag",
|
|---|
| 79 | 'reqd' => "no" },
|
|---|
| 80 | { 'name' => "extract_keyphrases",
|
|---|
| 81 | 'desc' => "{BasPlug.extract_keyphrases}",
|
|---|
| 82 | 'type' => "flag",
|
|---|
| 83 | 'reqd' => "no",
|
|---|
| 84 | 'hiddengli' => "yes" },
|
|---|
| 85 | { 'name' => "extract_keyphrase_options",
|
|---|
| 86 | 'desc' => "{BasPlug.extract_keyphrase_options}",
|
|---|
| 87 | 'type' => "string",
|
|---|
| 88 | 'reqd' => "no",
|
|---|
| 89 | 'hiddengli' => "yes" } ];
|
|---|
| 90 |
|
|---|
| 91 | my $options = { 'name' => "ConvertToPlug",
|
|---|
| 92 | 'desc' => "{ConvertToPlug.desc}",
|
|---|
| 93 | 'abstract' => "yes",
|
|---|
| 94 | 'inherits' => "yes",
|
|---|
| 95 | 'args' => $arguments };
|
|---|
| 96 |
|
|---|
| 97 |
|
|---|
| 98 | sub load_secondary_plugins
|
|---|
| 99 | {
|
|---|
| 100 | my $self = shift (@_);
|
|---|
| 101 | my ($class,$input_args,$hashArgOptLists) = @_;
|
|---|
| 102 |
|
|---|
| 103 | my @convert_to_list = split(",",$self->{'convert_to'});
|
|---|
| 104 | my $secondary_plugins = {};
|
|---|
| 105 | # find the plugin
|
|---|
| 106 |
|
|---|
| 107 | foreach my $convert_to (@convert_to_list) {
|
|---|
| 108 | # load in "convert_to" plugin package
|
|---|
| 109 | my $plugin_class = $convert_to."Plug";
|
|---|
| 110 | my $plugin_package = $plugin_class.".pm";
|
|---|
| 111 |
|
|---|
| 112 | my $colplugname = undef;
|
|---|
| 113 | if (defined $ENV{'GSDLCOLLECTDIR'}) {
|
|---|
| 114 | $colplugname = &util::filename_cat($ENV{'GSDLCOLLECTDIR'},
|
|---|
| 115 | "perllib","plugins",
|
|---|
| 116 | $plugin_package);
|
|---|
| 117 | }
|
|---|
| 118 |
|
|---|
| 119 | my $mainplugname = &util::filename_cat($ENV{'GSDLHOME'},
|
|---|
| 120 | "perllib","plugins",
|
|---|
| 121 | $plugin_package);
|
|---|
| 122 |
|
|---|
| 123 | if ((defined $colplugname) && (-e $colplugname)) { require $colplugname;}
|
|---|
| 124 | elsif (-e $mainplugname) { require $mainplugname; }
|
|---|
| 125 | else {
|
|---|
| 126 | &gsprintf(STDERR, "{plugin.could_not_find_plugin}\n",
|
|---|
| 127 | $plugin_class);
|
|---|
| 128 | die "\n";
|
|---|
| 129 | }
|
|---|
| 130 |
|
|---|
| 131 | # call its constructor with extra options that we've worked out!
|
|---|
| 132 | my $arglist = $input_args->{$plugin_class};
|
|---|
| 133 |
|
|---|
| 134 | my ($secondary_plugin);
|
|---|
| 135 | eval("\$secondary_plugin = new $plugin_class([],\$arglist)");
|
|---|
| 136 | die "$@" if $@;
|
|---|
| 137 | $secondary_plugins->{$plugin_class} = $secondary_plugin;
|
|---|
| 138 | }
|
|---|
| 139 | $self->{'secondary_plugins'} = $secondary_plugins;
|
|---|
| 140 | }
|
|---|
| 141 |
|
|---|
| 142 | sub new {
|
|---|
| 143 | my ($class) = shift (@_);
|
|---|
| 144 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
|---|
| 145 | push(@$pluginlist, $class);
|
|---|
| 146 | my $classPluginName = (defined $pluginlist->[0]) ? $pluginlist->[0] : $class;
|
|---|
| 147 | if(defined $arguments){ push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});}
|
|---|
| 148 | if(defined $options) { push(@{$hashArgOptLists->{"OptList"}},$options)};
|
|---|
| 149 |
|
|---|
| 150 | my $self = new BasPlug($pluginlist, $inputargs, $hashArgOptLists);
|
|---|
| 151 |
|
|---|
| 152 | if ($self->{'info_only'}) {
|
|---|
| 153 | # don't worry about any options etc
|
|---|
| 154 | return bless $self, $class;
|
|---|
| 155 | }
|
|---|
| 156 |
|
|---|
| 157 | my $convert_to_type = $self->{'convert_to'};
|
|---|
| 158 | if (!defined $convert_to_type || $convert_to_type eq "") {
|
|---|
| 159 | $convert_to_type = "auto";
|
|---|
| 160 | }
|
|---|
| 161 | my $windows_scripting = $self->{'windows_scripting'};
|
|---|
| 162 | $windows_scripting = 0 unless defined $windows_scripting;
|
|---|
| 163 | if ($classPluginName eq "PDFPlug") {
|
|---|
| 164 | if ($convert_to_type eq "text" &&
|
|---|
| 165 | $ENV{'GSDLOS'} =~ /^windows$/i) {
|
|---|
| 166 | print STDERR "Windows does not support pdf to text. PDFs will be converted to HTML instead\n";
|
|---|
| 167 | $convert_to_type = "html";
|
|---|
| 168 | }
|
|---|
| 169 | } elsif ($classPluginName eq "WordPlug") {
|
|---|
| 170 | if ($windows_scripting && $ENV{'GSDLOS'} =~ /^windows$/i && $convert_to_type =~ /^(html|auto)$/) {
|
|---|
| 171 | # we use structured HTML, not normal html
|
|---|
| 172 | $convert_to_type = "structuredhtml";
|
|---|
| 173 | }
|
|---|
| 174 | } elsif ($classPluginName eq "PPTPlug") {
|
|---|
| 175 | if ($windows_scripting && $ENV{'GSDLOS'} =~ /^windows$/i && $convert_to_type eq "auto") {
|
|---|
| 176 | # we use paged img
|
|---|
| 177 | $convert_to_type = "pagedimg_jpg";
|
|---|
| 178 | }
|
|---|
| 179 | } elsif ($classPluginName eq "PSPlug") {
|
|---|
| 180 | if ($convert_to_type eq "auto") {
|
|---|
| 181 | # we use text
|
|---|
| 182 | $convert_to_type = "text";
|
|---|
| 183 | }
|
|---|
| 184 | }
|
|---|
| 185 |
|
|---|
| 186 | if ($convert_to_type eq "auto") {
|
|---|
| 187 | # choose html for now - should choose a format based on doc type
|
|---|
| 188 | $convert_to_type = "html";
|
|---|
| 189 | }
|
|---|
| 190 |
|
|---|
| 191 | if ($convert_to_type eq "html") {
|
|---|
| 192 | $self->{'convert_to'} = "HTML";
|
|---|
| 193 | $self->{'convert_to_ext'} = "html";
|
|---|
| 194 | } elsif ($convert_to_type eq "text") {
|
|---|
| 195 | $self->{'convert_to'} = "TEXT";
|
|---|
| 196 | $self->{'convert_to_ext'} = "txt";
|
|---|
| 197 | } elsif ($convert_to_type eq "structuredhtml") {
|
|---|
| 198 | $self->{'convert_to'} = "StructuredHTML";
|
|---|
| 199 | $self->{'convert_to_ext'} = "html";
|
|---|
| 200 | } elsif ($convert_to_type =~ /^pagedimg/) {
|
|---|
| 201 | $self->{'convert_to'} = "PagedImg";
|
|---|
| 202 | my ($convert_to_ext) = $convert_to_type =~ /pagedimg\_(jpg|gif|png)/i;
|
|---|
| 203 | $convert_to_ext = 'jpg' unless defined $convert_to_ext;
|
|---|
| 204 | $self->{'convert_to_ext'} = $convert_to_ext;
|
|---|
| 205 | }
|
|---|
| 206 |
|
|---|
| 207 | return bless $self, $class;
|
|---|
| 208 | }
|
|---|
| 209 |
|
|---|
| 210 |
|
|---|
| 211 | sub init {
|
|---|
| 212 | my $self = shift (@_);
|
|---|
| 213 | my ($verbosity, $outhandle, $failhandle) = @_;
|
|---|
| 214 |
|
|---|
| 215 | $self->SUPER::init($verbosity,$outhandle,$failhandle);
|
|---|
| 216 |
|
|---|
| 217 | my $secondary_plugins = $self->{'secondary_plugins'};
|
|---|
| 218 |
|
|---|
| 219 | foreach my $plug_name (keys %$secondary_plugins) {
|
|---|
| 220 | my $plugin = $secondary_plugins->{$plug_name};
|
|---|
| 221 | $plugin->init($verbosity,$outhandle,$failhandle);
|
|---|
| 222 | }
|
|---|
| 223 | }
|
|---|
| 224 |
|
|---|
| 225 | sub deinit {
|
|---|
| 226 | # called only once, after all plugin passes have been done
|
|---|
| 227 |
|
|---|
| 228 | my ($self) = @_;
|
|---|
| 229 |
|
|---|
| 230 | my $secondary_plugins = $self->{'secondary_plugins'};
|
|---|
| 231 |
|
|---|
| 232 | foreach my $plug_name (keys %$secondary_plugins) {
|
|---|
| 233 | my $plugin = $secondary_plugins->{$plug_name};
|
|---|
| 234 | $plugin->deinit();
|
|---|
| 235 | }
|
|---|
| 236 | }
|
|---|
| 237 |
|
|---|
| 238 | sub convert_post_process
|
|---|
| 239 | {
|
|---|
| 240 | # by default do no post processing
|
|---|
| 241 | return;
|
|---|
| 242 | }
|
|---|
| 243 |
|
|---|
| 244 |
|
|---|
| 245 | # Run conversion utility on the input file.
|
|---|
| 246 | #
|
|---|
| 247 | # The conversion takes place in a collection specific 'tmp' directory so
|
|---|
| 248 | # that we don't accidentally damage the input.
|
|---|
| 249 | #
|
|---|
| 250 | # The desired output type is indicated by $output_ext. This is usually
|
|---|
| 251 | # something like "html" or "word", but can be "best" (or the empty string)
|
|---|
| 252 | # to indicate that the conversion utility should do the best it can.
|
|---|
| 253 | sub tmp_area_convert_file {
|
|---|
| 254 | my $self = shift (@_);
|
|---|
| 255 | my ($output_ext, $input_filename, $textref) = @_;
|
|---|
| 256 |
|
|---|
| 257 | my $outhandle = $self->{'outhandle'};
|
|---|
| 258 | my $convert_to = $self->{'convert_to'};
|
|---|
| 259 | my $failhandle = $self->{'failhandle'};
|
|---|
| 260 | my $convert_to_ext = $self->{'convert_to_ext'};
|
|---|
| 261 |
|
|---|
| 262 | # derive tmp filename from input filename
|
|---|
| 263 | my ($tailname, $dirname, $suffix)
|
|---|
| 264 | = &File::Basename::fileparse($input_filename, "\\.[^\\.]+\$");
|
|---|
| 265 |
|
|---|
| 266 | # softlink to collection tmp dir
|
|---|
| 267 | my $tmp_dirname = $dirname;
|
|---|
| 268 | if(defined $ENV{'GSDLCOLLECTDIR'}) {
|
|---|
| 269 | $tmp_dirname = $ENV{'GSDLCOLLECTDIR'};
|
|---|
| 270 | } elsif(defined $ENV{'GSDLHOME'}) {
|
|---|
| 271 | $tmp_dirname = $ENV{'GSDLHOME'};
|
|---|
| 272 | }
|
|---|
| 273 | $tmp_dirname = &util::filename_cat($tmp_dirname, "tmp");
|
|---|
| 274 | &util::mk_dir($tmp_dirname) if (!-e $tmp_dirname);
|
|---|
| 275 |
|
|---|
| 276 | # Remove any white space from filename -- no risk of name collision, and
|
|---|
| 277 | # makes later conversion by utils simpler. Leave spaces in path...
|
|---|
| 278 | # tidy up the filename with space, dot, hyphen between
|
|---|
| 279 | $tailname =~ s/\s+//g;
|
|---|
| 280 | $tailname =~ s/\.+//g;
|
|---|
| 281 | $tailname =~ s/\-+//g;
|
|---|
| 282 |
|
|---|
| 283 | # convert to utf-8 otherwise we have problems with the doc.xml file
|
|---|
| 284 | # later on
|
|---|
| 285 | &unicode::ensure_utf8(\$tailname);
|
|---|
| 286 |
|
|---|
| 287 | $suffix = lc($suffix);
|
|---|
| 288 | my $tmp_filename = &util::filename_cat($tmp_dirname, "$tailname$suffix");
|
|---|
| 289 | &util::soft_link($input_filename, $tmp_filename);
|
|---|
| 290 | my $verbosity = $self->{'verbosity'};
|
|---|
| 291 | if ($verbosity > 0) {
|
|---|
| 292 | print $outhandle "Converting $tailname$suffix to $convert_to format\n";
|
|---|
| 293 | }
|
|---|
| 294 |
|
|---|
| 295 | my $errlog = &util::filename_cat($tmp_dirname, "err.log");
|
|---|
| 296 |
|
|---|
| 297 | # Execute the conversion command and get the type of the result,
|
|---|
| 298 | # making sure the converter gives us the appropriate output type
|
|---|
| 299 | my $output_type="";
|
|---|
| 300 | if ($convert_to =~ m/PagedImg/i) {
|
|---|
| 301 | $output_type = lc($convert_to)."_".lc($convert_to_ext);
|
|---|
| 302 | } else {
|
|---|
| 303 | $output_type = lc($convert_to);
|
|---|
| 304 | }
|
|---|
| 305 |
|
|---|
| 306 | my $cmd = "perl -S gsConvert.pl -verbose $verbosity ";
|
|---|
| 307 | if (defined $self->{'convert_options'}) {
|
|---|
| 308 | $cmd .= $self->{'convert_options'} . " ";
|
|---|
| 309 | }
|
|---|
| 310 | if ($self->{'use_strings'}) {
|
|---|
| 311 | $cmd .= "-use_strings ";
|
|---|
| 312 | }
|
|---|
| 313 | $cmd .= "-errlog \"$errlog\" -output $output_type \"$tmp_filename\"";
|
|---|
| 314 | $output_type = `$cmd`;
|
|---|
| 315 |
|
|---|
| 316 | # remove symbolic link to original file
|
|---|
| 317 | &util::rm($tmp_filename);
|
|---|
| 318 |
|
|---|
| 319 | # Check STDERR here
|
|---|
| 320 | chomp $output_type;
|
|---|
| 321 | if ($output_type eq "fail") {
|
|---|
| 322 | print $outhandle "Could not convert $tailname$suffix to $convert_to format\n";
|
|---|
| 323 | print $failhandle "$tailname$suffix: " . ref($self) . " failed to convert to $convert_to\n";
|
|---|
| 324 | # The following meant that if a conversion failed, the document would be counted twice - do we need it for anything?
|
|---|
| 325 | #$self->{'num_not_processed'} ++;
|
|---|
| 326 | if (-s "$errlog") {
|
|---|
| 327 | open(ERRLOG, "$errlog");
|
|---|
| 328 | while (<ERRLOG>) {
|
|---|
| 329 | print $outhandle "$_";
|
|---|
| 330 | }
|
|---|
| 331 | print $outhandle "\n";
|
|---|
| 332 | close ERRLOG;
|
|---|
| 333 | }
|
|---|
| 334 | &util::rm("$errlog") if (-e "$errlog");
|
|---|
| 335 | return "";
|
|---|
| 336 | }
|
|---|
| 337 |
|
|---|
| 338 | # store the *actual* output type and return the output filename
|
|---|
| 339 | # it's possible we requested conversion to html, but only to text succeeded
|
|---|
| 340 | #$self->{'convert_to_ext'} = $output_type;
|
|---|
| 341 | if ($output_type =~ /html/i) {
|
|---|
| 342 | $self->{'converted_to'} = "HTML";
|
|---|
| 343 | } elsif ($output_type =~ /te?xt/i) {
|
|---|
| 344 | $self->{'converted_to'} = "TEXT";
|
|---|
| 345 | } elsif ($output_type =~ /item/i){
|
|---|
| 346 | $self->{'converted_to'} = "PagedImg";
|
|---|
| 347 | }
|
|---|
| 348 |
|
|---|
| 349 | my $output_filename = $tmp_filename;
|
|---|
| 350 | if ($output_type =~ /item/i) {
|
|---|
| 351 | # running under windows
|
|---|
| 352 | if ($ENV{'GSDLOS'} =~ /^windows$/i) {
|
|---|
| 353 | $output_filename = $tmp_dirname . "\\$tailname\\" . $tailname . ".$output_type";
|
|---|
| 354 | } else {
|
|---|
| 355 | $output_filename = $tmp_dirname . "\/$tailname\/" . $tailname . ".$output_type";
|
|---|
| 356 | }
|
|---|
| 357 | } else {
|
|---|
| 358 | $output_filename =~ s/$suffix$/.$output_type/;
|
|---|
| 359 | }
|
|---|
| 360 |
|
|---|
| 361 | return $output_filename;
|
|---|
| 362 | }
|
|---|
| 363 |
|
|---|
| 364 |
|
|---|
| 365 | # Override BasPlug read
|
|---|
| 366 | # We don't want to get language encoding stuff until after we've converted
|
|---|
| 367 | # our file to either TEXT or HTML or PagedImage.
|
|---|
| 368 | sub read {
|
|---|
| 369 | my $self = shift (@_);
|
|---|
| 370 | my ($pluginfo, $base_dir, $file, $metadata, $processor, $maxdocs, $total_count, $gli) = @_;
|
|---|
| 371 |
|
|---|
| 372 | my $outhandle = $self->{'outhandle'};
|
|---|
| 373 |
|
|---|
| 374 | my ($block_status,$filename) = $self->read_block(@_);
|
|---|
| 375 | return $block_status if ((!defined $block_status) || ($block_status==0));
|
|---|
| 376 | $file = $self->read_tidy_file($file);
|
|---|
| 377 |
|
|---|
| 378 | my $output_ext = $self->{'convert_to_ext'};
|
|---|
| 379 | my $conv_filename = "";
|
|---|
| 380 | $conv_filename = $self->tmp_area_convert_file($output_ext, $filename);
|
|---|
| 381 |
|
|---|
| 382 | if ("$conv_filename" eq "") {return -1;} # had an error, will be passed down pipeline
|
|---|
| 383 | if (! -e "$conv_filename") {return -1;}
|
|---|
| 384 | $self->{'conv_filename'} = $conv_filename;
|
|---|
| 385 | $self->convert_post_process($conv_filename);
|
|---|
| 386 |
|
|---|
| 387 | # Run the "fribidi" (http://fribidi.org) Unicode Bidirectional Algorithm program over the converted file
|
|---|
| 388 | # Added for fixing up Persian PDFs after being processed by pdftohtml, but may be useful in other cases too
|
|---|
| 389 | if ($self->{'apply_fribidi'} && $self->{'converted_to'} =~ /(HTML|TEXT)/) {
|
|---|
| 390 | my $fribidi_command = "fribidi \"$conv_filename\" >\"${conv_filename}.tmp\"";
|
|---|
| 391 | if (system($fribidi_command) != 0) {
|
|---|
| 392 | print STDERR "ERROR: Cannot run fribidi on \"$conv_filename\".\n";
|
|---|
| 393 | }
|
|---|
| 394 | else {
|
|---|
| 395 | &util::mv("${conv_filename}.tmp", $conv_filename);
|
|---|
| 396 | }
|
|---|
| 397 | }
|
|---|
| 398 |
|
|---|
| 399 | my $secondary_plugins = $self->{'secondary_plugins'};
|
|---|
| 400 | my $num_secondary_plugins = scalar(keys %$secondary_plugins);
|
|---|
| 401 |
|
|---|
| 402 | if ($num_secondary_plugins == 0) {
|
|---|
| 403 | print $outhandle "Warning: No secondary plugin to use in conversion. Skipping $file\n";
|
|---|
| 404 | return 0; # effectively block it
|
|---|
| 405 | }
|
|---|
| 406 |
|
|---|
| 407 | my @plugin_names = keys %$secondary_plugins;
|
|---|
| 408 | my $plugin_name = shift @plugin_names;
|
|---|
| 409 |
|
|---|
| 410 | if ($num_secondary_plugins > 1) {
|
|---|
| 411 | print $outhandle "Warning: Multiple secondary plugins not supported yet! Choosing $plugin_name\n.";
|
|---|
| 412 | }
|
|---|
| 413 |
|
|---|
| 414 | my $secondary_plugin = $secondary_plugins->{$plugin_name};
|
|---|
| 415 |
|
|---|
| 416 | # note: metadata is not carried on to the next level
|
|---|
| 417 | my ($rv,$doc_obj)
|
|---|
| 418 | = $secondary_plugin->read_into_doc_obj ($pluginfo,"", $conv_filename,
|
|---|
| 419 | $metadata, $processor, $maxdocs, $total_count,
|
|---|
| 420 | $gli);
|
|---|
| 421 |
|
|---|
| 422 | if ((!defined $rv) || ($rv<1)) {
|
|---|
| 423 | # wasn't processed
|
|---|
| 424 | return $rv;
|
|---|
| 425 | }
|
|---|
| 426 |
|
|---|
| 427 | # Override previous gsdlsourcefilename set by secondary plugin
|
|---|
| 428 | my $collect_file = &util::filename_within_collection($filename);
|
|---|
| 429 | my $collect_conv_file = &util::filename_within_collection($conv_filename);
|
|---|
| 430 | $doc_obj->set_source_filename ($collect_file);
|
|---|
| 431 | $doc_obj->set_converted_filename($collect_conv_file);
|
|---|
| 432 |
|
|---|
| 433 | my ($filemeta) = $file =~ /([^\\\/]+)$/;
|
|---|
| 434 | $doc_obj->set_utf8_metadata_element($doc_obj->get_top_section(), "Source", &ghtml::dmsafe($filemeta));
|
|---|
| 435 | $doc_obj->set_utf8_metadata_element($doc_obj->get_top_section(), "Plugin", "$self->{'plugin_type'}");
|
|---|
| 436 | $doc_obj->set_utf8_metadata_element($doc_obj->get_top_section(), "FileSize", (-s $filename));
|
|---|
| 437 |
|
|---|
| 438 | if ($self->{'cover_image'}) {
|
|---|
| 439 | $self->associate_cover_image($doc_obj, $filename);
|
|---|
| 440 | }
|
|---|
| 441 |
|
|---|
| 442 | # do plugin specific processing of doc_obj
|
|---|
| 443 | unless (defined ($self->process(undef, $pluginfo, $base_dir, $file, $metadata, $doc_obj, $gli))) {
|
|---|
| 444 | print STDERR "<ProcessingError n='$file'>\n" if ($gli);
|
|---|
| 445 | return -1;
|
|---|
| 446 | }
|
|---|
| 447 | # do any automatic metadata extraction
|
|---|
| 448 | $self->auto_extract_metadata ($doc_obj);
|
|---|
| 449 |
|
|---|
| 450 | # have we found a Title??
|
|---|
| 451 | $self->title_fallback($doc_obj,$doc_obj->get_top_section(),$filemeta);
|
|---|
| 452 |
|
|---|
| 453 | # # add an OID
|
|---|
| 454 | # $doc_obj->set_OID();
|
|---|
| 455 |
|
|---|
| 456 | # add an OID
|
|---|
| 457 | # see if there is a plugin-specific set_OID function...
|
|---|
| 458 | if (defined ($self->can('set_OID'))) {
|
|---|
| 459 | # it will need $doc_obj to set the Identifier metadata...
|
|---|
| 460 | $self->set_OID($doc_obj);
|
|---|
| 461 | } else {
|
|---|
| 462 | # use the default set_OID() in doc.pm
|
|---|
| 463 | $doc_obj->set_OID();
|
|---|
| 464 | }
|
|---|
| 465 |
|
|---|
| 466 |
|
|---|
| 467 | # process the document
|
|---|
| 468 | $processor->process($doc_obj);
|
|---|
| 469 |
|
|---|
| 470 | $self->{'num_processed'} ++;
|
|---|
| 471 |
|
|---|
| 472 | return 1;
|
|---|
| 473 | }
|
|---|
| 474 |
|
|---|
| 475 |
|
|---|
| 476 | # do plugin specific processing of doc_obj for doc_ext type
|
|---|
| 477 | sub process_type {
|
|---|
| 478 | my $self = shift (@_);
|
|---|
| 479 | my ($doc_ext, $base_dir, $file, $doc_obj) = @_;
|
|---|
| 480 |
|
|---|
| 481 | # associate original file with doc object
|
|---|
| 482 | my $cursection = $doc_obj->get_top_section();
|
|---|
| 483 | my $filename = &util::filename_cat($base_dir, $file);
|
|---|
| 484 | my $assocfilename = "doc.$doc_ext";
|
|---|
| 485 | if ($self->{'keep_original_filename'} == 1) {
|
|---|
| 486 | # this should be the same filename that was used for the Source metadata, as we will use [Source] in the srclink
|
|---|
| 487 | ($assocfilename) = $file =~ /([^\\\/]+)$/;
|
|---|
| 488 | }
|
|---|
| 489 | $doc_obj->associate_file($filename, $assocfilename, undef, $cursection);
|
|---|
| 490 |
|
|---|
| 491 | my $file_type;
|
|---|
| 492 |
|
|---|
| 493 | if ($doc_ext eq "doc") {
|
|---|
| 494 | $file_type = "Word";
|
|---|
| 495 | } elsif ($doc_ext eq "xls") {
|
|---|
| 496 | $file_type = "Excel";
|
|---|
| 497 | } elsif ($doc_ext eq "ppt") {
|
|---|
| 498 | $file_type = "PPT";
|
|---|
| 499 | } elsif ($doc_ext eq "pdf") {
|
|---|
| 500 | $file_type = "PDF";
|
|---|
| 501 | } elsif ($doc_ext eq "rtf") {
|
|---|
| 502 | $file_type = "RTF";
|
|---|
| 503 | } elsif ($doc_ext eq "ps") {
|
|---|
| 504 | $file_type = "PS";
|
|---|
| 505 | }
|
|---|
| 506 |
|
|---|
| 507 | my $file_format = $file_type || "unknown";
|
|---|
| 508 |
|
|---|
| 509 | # We use set instead of add here because we only want one value
|
|---|
| 510 | $doc_obj->set_utf8_metadata_element($cursection, "FileFormat", $file_format);
|
|---|
| 511 | my $doclink = "<a href=\"_httpprefix_/collect/[collection]/index/assoc/[archivedir]/doc.$doc_ext\">";
|
|---|
| 512 | if ($self->{'keep_original_filename'} == 1) {
|
|---|
| 513 | $doclink = "<a href=\"_httpprefix_/collect/[collection]/index/assoc/[archivedir]/[Source]\">";
|
|---|
| 514 | }
|
|---|
| 515 | $doc_obj->add_utf8_metadata ($cursection, "srclink", $doclink);
|
|---|
| 516 | $doc_obj->add_utf8_metadata ($cursection, "srcicon", "_icon".$doc_ext."_");
|
|---|
| 517 | $doc_obj->add_utf8_metadata ($cursection, "/srclink", "</a>");
|
|---|
| 518 |
|
|---|
| 519 | return 1;
|
|---|
| 520 | }
|
|---|
| 521 |
|
|---|
| 522 | 1;
|
|---|
| 523 |
|
|---|
| 524 |
|
|---|
| 525 |
|
|---|
| 526 |
|
|---|
| 527 |
|
|---|
| 528 |
|
|---|
| 529 |
|
|---|
