| 1 | ###########################################################################
|
|---|
| 2 | #
|
|---|
| 3 | # PagedImgPlug.pm -- plugin for sets of images and OCR text that
|
|---|
| 4 | # make up a document
|
|---|
| 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 | # PagedImgPlug
|
|---|
| 28 | # processes sequences of images, with optional OCR text
|
|---|
| 29 | #
|
|---|
| 30 | # This plugin takes *.item files, which contain metadata and lists of image
|
|---|
| 31 | # files, and produces a document containing sections, one for each page.
|
|---|
| 32 | # The files should be named something.item, then you can have more than one
|
|---|
| 33 | # book in a directory. You will need to create these files, one for each
|
|---|
| 34 | # document/book.
|
|---|
| 35 | #
|
|---|
| 36 | #There are two formats for the item files: a plain text format, and an xml
|
|---|
| 37 | #format. You can use either format, and can have both formats in the same
|
|---|
| 38 | #collection if you like. If you use the plain format, you must not start the
|
|---|
| 39 | #file off with <PagedDocument>
|
|---|
| 40 |
|
|---|
| 41 | #### PLAIN FORMAT
|
|---|
| 42 | # The format of the xxx.item file is as follows:
|
|---|
| 43 | # The first lines contain any metadata for the whole document
|
|---|
| 44 | # <metadata-name>metadata-value
|
|---|
| 45 | # eg.
|
|---|
| 46 | # <Title>Snail farming
|
|---|
| 47 | # <Date>19230102
|
|---|
| 48 | # Then comes a list of pages, one page per line, each line has the format
|
|---|
| 49 | #
|
|---|
| 50 | # pagenum:imagefile:textfile:r
|
|---|
| 51 | #
|
|---|
| 52 | # page num and imagefile are required. pagenum is used for the Title
|
|---|
| 53 | # of the section, and in the display is shown as page <pagenum>.
|
|---|
| 54 | # imagefile is the image for the page. textfile is an optional text
|
|---|
| 55 | # file containing the OCR (or any) text for the page - this gets added
|
|---|
| 56 | # as the text for the section. r is optional, and signals that the image
|
|---|
| 57 | # should be rotated 180deg. Eg use this if the image has been made upside down.
|
|---|
| 58 | # So an example item file looks like:
|
|---|
| 59 | # <Title>Snail farming
|
|---|
| 60 | # <Date>19960403
|
|---|
| 61 | # 1:p1.gif:p1.txt:
|
|---|
| 62 | # 2:p2.gif::
|
|---|
| 63 | # 3:p3.gif:p3.txt:
|
|---|
| 64 | # 3b:p3b.gif:p3b.txt:r
|
|---|
| 65 | # The second page has no text, the fourth page is a back page, and
|
|---|
| 66 | # should be rotated.
|
|---|
| 67 | #
|
|---|
| 68 |
|
|---|
| 69 | #### XML FORMAT
|
|---|
| 70 | # The xml format looks like the following
|
|---|
| 71 | #<PagedDocument>
|
|---|
| 72 | #<Metadata name="Title">The Title of the entire document</Metadata>
|
|---|
| 73 | #<Page pagenum="1" imgfile="xxx.jpg" txtfile="yyy.txt">
|
|---|
| 74 | #<Metadata name="Title">The Title of this page</Metadata>
|
|---|
| 75 | #</Page>
|
|---|
| 76 | #... more pages
|
|---|
| 77 | #</PagedDocument>
|
|---|
| 78 | #PagedDocument contains a list of Pages, Metadata and PageGroups. Any metadata
|
|---|
| 79 | #that is not inside another tag will belong to the document.
|
|---|
| 80 | #Each Page has a pagenum (not used at the moment), an imgfile and/or a txtfile.
|
|---|
| 81 | #These are both optional - if neither is used, the section will have no content.
|
|---|
| 82 | #Pages can also have metadata associated with them.
|
|---|
| 83 | #PageGroups can be introduced at any point - they can contain Metadata and Pages and other PageGroups. They are used to introduce hierarchical structure into the document.
|
|---|
| 84 | #For example
|
|---|
| 85 | #<PagedDocument>
|
|---|
| 86 | #<PageGroup>
|
|---|
| 87 | #<Page>
|
|---|
| 88 | #<Page>
|
|---|
| 89 | #</PageGroup>
|
|---|
| 90 | #<Page>
|
|---|
| 91 | #</PagedDocument>
|
|---|
| 92 | #would generate a structure like
|
|---|
| 93 | #X
|
|---|
| 94 | #--X
|
|---|
| 95 | # --X
|
|---|
| 96 | # --X
|
|---|
| 97 | #--X
|
|---|
| 98 | #PageGroup tags can also have imgfile/textfile metadata if you like - this way they get some content themselves.
|
|---|
| 99 |
|
|---|
| 100 | #Currently the XML structure doesn't work very well with the paged document type, unless you use numerical Titles for each section.
|
|---|
| 101 | #There is still a bit of work to do on this format:
|
|---|
| 102 | #* enable other text file types, eg html, pdf etc
|
|---|
| 103 | #* make the document paging work properly
|
|---|
| 104 | #* add pagenum as Title unless a Title is present?
|
|---|
| 105 |
|
|---|
| 106 | # All the supplemetary image amd text files should be in the same folder as
|
|---|
| 107 | # the .item file.
|
|---|
| 108 | #
|
|---|
| 109 | # To display the images instead of the document text, you can use [srcicon]
|
|---|
| 110 | # in the DocumentText format statement.
|
|---|
| 111 | # For example,
|
|---|
| 112 | #
|
|---|
| 113 | # format DocumentText "<center><table width=_pagewidth_><tr><td>[srcicon]</td></tr></table></center>"
|
|---|
| 114 | #
|
|---|
| 115 | # To have it create thumbnail size images, use the '-thumbnail' option.
|
|---|
| 116 | # To have it create medium size images for display, use the '-screenview'
|
|---|
| 117 | # option. As usual, running
|
|---|
| 118 | # 'perl -S pluginfo.pl PagedImgPlug' will list all the options.
|
|---|
| 119 |
|
|---|
| 120 | # If you want the resulting documents to be presented with a table of
|
|---|
| 121 | # contents, use '-documenttype hierarchy', otherwise they will have
|
|---|
| 122 | # next and previous arrows, and a goto page X box.
|
|---|
| 123 |
|
|---|
| 124 | # If you have used -screenview, you can also use [screenicon] in the format
|
|---|
| 125 | # statement to display the smaller image. Here is an example that switches
|
|---|
| 126 | # between the two:
|
|---|
| 127 | #
|
|---|
| 128 | # format DocumentText "<center><table width=_pagewidth_><tr><td>{If}{_cgiargp_ eq full,<a href='_httpdocument_&d=_cgiargd_&p=small'>Switch to small version.</a>,<a href='_httpdocument_&d=_cgiargd_&p=full'>Switch to fullsize version</a>}</td></tr><tr><td>{If}{_cgiargp_ eq full,<a href='_httpdocument_&d=_cgiargd_&p=small' title='Switch to small version'>[srcicon]</a>,<a href='_httpdocument_&d=_cgiargd_&p=full' title='Switch to fullsize version'>[screenicon]</a>}</td></tr></table></center>"
|
|---|
| 129 | #
|
|---|
| 130 | # Additional metadata can be added into the .item files, alternatively you can
|
|---|
| 131 | # use normal metadata.xml files, with the name of the xxx.item file as the
|
|---|
| 132 | # FileName (only for document level metadata).
|
|---|
| 133 |
|
|---|
| 134 | package PagedImgPlug;
|
|---|
| 135 |
|
|---|
| 136 | use XMLPlug;
|
|---|
| 137 | use strict;
|
|---|
| 138 | no strict 'refs'; # allow filehandles to be variables and viceversa
|
|---|
| 139 |
|
|---|
| 140 | sub BEGIN {
|
|---|
| 141 | @PagedImgPlug::ISA = ('XMLPlug');
|
|---|
| 142 | }
|
|---|
| 143 |
|
|---|
| 144 | my $type_list =
|
|---|
| 145 | [ { 'name' => "paged",
|
|---|
| 146 | 'desc' => "{PagedImgPlug.documenttype.paged}" },
|
|---|
| 147 | { 'name' => "hierarchy",
|
|---|
| 148 | 'desc' => "{PagedImgPlug.documenttype.hierarchy}" } ];
|
|---|
| 149 |
|
|---|
| 150 | my $arguments =
|
|---|
| 151 | [ { 'name' => "process_exp",
|
|---|
| 152 | 'desc' => "{BasPlug.process_exp}",
|
|---|
| 153 | 'type' => "string",
|
|---|
| 154 | 'deft' => &get_default_process_exp(),
|
|---|
| 155 | 'reqd' => "no" },
|
|---|
| 156 | { 'name' => "block_exp",
|
|---|
| 157 | 'desc' => "{BasPlug.block_exp}",
|
|---|
| 158 | 'type' => "string",
|
|---|
| 159 | 'deft' => &get_default_block_exp(),
|
|---|
| 160 | 'reqd' => "no" },
|
|---|
| 161 | { 'name' => "title_sub",
|
|---|
| 162 | 'desc' => "{HTMLPlug.title_sub}",
|
|---|
| 163 | 'type' => "string",
|
|---|
| 164 | 'deft' => "" },
|
|---|
| 165 | { 'name' => "noscaleup",
|
|---|
| 166 | 'desc' => "{ImagePlug.noscaleup}",
|
|---|
| 167 | 'type' => "flag",
|
|---|
| 168 | 'reqd' => "no" },
|
|---|
| 169 | { 'name' => "thumbnail",
|
|---|
| 170 | 'desc' => "{PagedImgPlug.thumbnail}",
|
|---|
| 171 | 'type' => "flag",
|
|---|
| 172 | 'reqd' => "no" },
|
|---|
| 173 | { 'name' => "thumbnailsize",
|
|---|
| 174 | 'desc' => "{ImagePlug.thumbnailsize}",
|
|---|
| 175 | 'type' => "int",
|
|---|
| 176 | 'deft' => "100",
|
|---|
| 177 | 'range' => "1,",
|
|---|
| 178 | 'reqd' => "no" },
|
|---|
| 179 | { 'name' => "thumbnailtype",
|
|---|
| 180 | 'desc' => "{ImagePlug.thumbnailtype}",
|
|---|
| 181 | 'type' => "string",
|
|---|
| 182 | 'deft' => "gif",
|
|---|
| 183 | 'reqd' => "no" },
|
|---|
| 184 | { 'name' => "screenview",
|
|---|
| 185 | 'desc' => "{PagedImgPlug.screenview}",
|
|---|
| 186 | 'type' => "flag",
|
|---|
| 187 | 'reqd' => "no" },
|
|---|
| 188 | { 'name' => "screenviewsize",
|
|---|
| 189 | 'desc' => "{PagedImgPlug.screenviewsize}",
|
|---|
| 190 | 'type' => "int",
|
|---|
| 191 | 'deft' => "500",
|
|---|
| 192 | 'range' => "1,",
|
|---|
| 193 | 'reqd' => "no" },
|
|---|
| 194 | { 'name' => "screenviewtype",
|
|---|
| 195 | 'desc' => "{PagedImgPlug.screenviewtype}",
|
|---|
| 196 | 'type' => "string",
|
|---|
| 197 | 'deft' => "jpg",
|
|---|
| 198 | 'reqd' => "no" },
|
|---|
| 199 | { 'name' => "converttotype",
|
|---|
| 200 | 'desc' => "{ImagePlug.converttotype}",
|
|---|
| 201 | 'type' => "string",
|
|---|
| 202 | 'deft' => "",
|
|---|
| 203 | 'reqd' => "no" },
|
|---|
| 204 | { 'name' => "minimumsize",
|
|---|
| 205 | 'desc' => "{ImagePlug.minimumsize}",
|
|---|
| 206 | 'type' => "int",
|
|---|
| 207 | 'deft' => "100",
|
|---|
| 208 | 'range' => "1,",
|
|---|
| 209 | 'reqd' => "no" },
|
|---|
| 210 | { 'name' => "headerpage",
|
|---|
| 211 | 'desc' => "{PagedImgPlug.headerpage}",
|
|---|
| 212 | 'type' => "flag",
|
|---|
| 213 | 'reqd' => "no" },
|
|---|
| 214 | { 'name' => "documenttype",
|
|---|
| 215 | 'desc' => "{PagedImgPlug.documenttype}",
|
|---|
| 216 | 'type' => "enum",
|
|---|
| 217 | 'list' => $type_list,
|
|---|
| 218 | 'deft' => "paged",
|
|---|
| 219 | 'reqd' => "no" } ];
|
|---|
| 220 |
|
|---|
| 221 |
|
|---|
| 222 | my $options = { 'name' => "PagedImgPlug",
|
|---|
| 223 | 'desc' => "{PagedImgPlug.desc}",
|
|---|
| 224 | 'abstract' => "no",
|
|---|
| 225 | 'inherits' => "yes",
|
|---|
| 226 | 'args' => $arguments };
|
|---|
| 227 |
|
|---|
| 228 | sub new {
|
|---|
| 229 | my ($class) = shift (@_);
|
|---|
| 230 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
|---|
| 231 | push(@$pluginlist, $class);
|
|---|
| 232 |
|
|---|
| 233 | if(defined $arguments){ push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});}
|
|---|
| 234 | if(defined $options) { push(@{$hashArgOptLists->{"OptList"}},$options)};
|
|---|
| 235 |
|
|---|
| 236 | my $self = new XMLPlug($pluginlist, $inputargs, $hashArgOptLists);
|
|---|
| 237 |
|
|---|
| 238 | return bless $self, $class;
|
|---|
| 239 | }
|
|---|
| 240 |
|
|---|
| 241 | sub get_default_process_exp {
|
|---|
| 242 | my $self = shift (@_);
|
|---|
| 243 |
|
|---|
| 244 | return q^\.item$^;
|
|---|
| 245 | }
|
|---|
| 246 |
|
|---|
| 247 | sub get_doctype {
|
|---|
| 248 | my $self = shift(@_);
|
|---|
| 249 |
|
|---|
| 250 | return "PagedDocument";
|
|---|
| 251 | }
|
|---|
| 252 |
|
|---|
| 253 |
|
|---|
| 254 | # want to block everything except the .item ones
|
|---|
| 255 | # but instead we will block images and txt files
|
|---|
| 256 | sub get_default_block_exp {
|
|---|
| 257 | my $self = shift (@_);
|
|---|
| 258 |
|
|---|
| 259 | return q^(?i)(\.jpe?g|\.gif|\.png|\.tif?f|\.te?xt|\.html?|~)$^
|
|---|
| 260 | }
|
|---|
| 261 |
|
|---|
| 262 | # Create the thumbnail and screenview images, and discover the Image's
|
|---|
| 263 | # size, width, and height using the convert utility.
|
|---|
| 264 | sub process_image {
|
|---|
| 265 | my $self = shift (@_);
|
|---|
| 266 | my $filename = shift (@_); # filename with full path
|
|---|
| 267 | my $srcfile = shift (@_); # filename without path
|
|---|
| 268 | my $doc_obj = shift (@_);
|
|---|
| 269 | my $section = shift (@_); #the current section
|
|---|
| 270 | my $rotate = shift (@_); # whether to rotate the image or not
|
|---|
| 271 | $rotate = 0 unless defined $rotate;
|
|---|
| 272 |
|
|---|
| 273 | # check that the image file exists!!
|
|---|
| 274 | if (!-f $filename) {
|
|---|
| 275 | print "PagedImgPlug: ERROR: File $filename does not exist, skipping\n";
|
|---|
| 276 | return 0;
|
|---|
| 277 | }
|
|---|
| 278 |
|
|---|
| 279 | my $top=0;
|
|---|
| 280 | if ($section eq $doc_obj->get_top_section()) {
|
|---|
| 281 | $top=1;
|
|---|
| 282 | }
|
|---|
| 283 | my $verbosity = $self->{'verbosity'};
|
|---|
| 284 | my $outhandle = $self->{'outhandle'};
|
|---|
| 285 |
|
|---|
| 286 | # check the filename is okay
|
|---|
| 287 | return 0 if ($srcfile eq "" || $filename eq "");
|
|---|
| 288 |
|
|---|
| 289 | my $minimumsize = $self->{'minimumsize'};
|
|---|
| 290 | if (defined $minimumsize && (-s $filename < $minimumsize)) {
|
|---|
| 291 | print $outhandle "PagedImgPlug: \"$filename\" too small, skipping\n"
|
|---|
| 292 | if ($verbosity > 1);
|
|---|
| 293 | }
|
|---|
| 294 |
|
|---|
| 295 | # Convert the image to a new type (if required), and rotate if required.
|
|---|
| 296 | my $converttotype = $self->{'converttotype'};
|
|---|
| 297 | my $originalfilename = ""; # only set if we do a conversion
|
|---|
| 298 | my $type = "unknown";
|
|---|
| 299 | my $converted = 0;
|
|---|
| 300 | my $rotated=0;
|
|---|
| 301 |
|
|---|
| 302 | if ($converttotype ne "" && $filename !~ /$converttotype$/) {
|
|---|
| 303 | $converted=1;
|
|---|
| 304 | $originalfilename = $filename;
|
|---|
| 305 | my $filehead = &util::get_tmp_filename();
|
|---|
| 306 | $filename = $filehead . ".$converttotype";
|
|---|
| 307 | my $n = 1;
|
|---|
| 308 | while (-e $filename) {
|
|---|
| 309 | $filename = "$filehead$n\.$converttotype";
|
|---|
| 310 | $n++;
|
|---|
| 311 | }
|
|---|
| 312 | $self->{'tmp_filename1'} = $filename;
|
|---|
| 313 |
|
|---|
| 314 | my $rotate_option = "";
|
|---|
| 315 | if ($rotate eq "r") {
|
|---|
| 316 | $rotate_option = "-rotate 180 ";
|
|---|
| 317 | }
|
|---|
| 318 |
|
|---|
| 319 | my $command = "convert -verbose \"$originalfilename\" $rotate_option \"$filename\"";
|
|---|
| 320 | print $outhandle "CONVERT: $command\n" if ($verbosity > 2);
|
|---|
| 321 | my $result = '';
|
|---|
| 322 | $result = `$command`;
|
|---|
| 323 | print $outhandle "CONVERT RESULT = $result\n" if ($verbosity > 2);
|
|---|
| 324 |
|
|---|
| 325 | $type = $converttotype;
|
|---|
| 326 | } elsif ($rotate eq "r") {
|
|---|
| 327 | $rotated=1;
|
|---|
| 328 | $originalfilename = $filename;
|
|---|
| 329 | $filename = &util::get_tmp_filename();
|
|---|
| 330 |
|
|---|
| 331 | my $command = "convert \"$originalfilename\" -rotate 180 \"$filename\"";
|
|---|
| 332 | print $outhandle "ROTATE: $command\n" if ($verbosity > 2);
|
|---|
| 333 | my $result = '';
|
|---|
| 334 | $result = `$command`;
|
|---|
| 335 | print $outhandle "ROTATE RESULT = $result\n" if ($verbosity > 2);
|
|---|
| 336 |
|
|---|
| 337 | }
|
|---|
| 338 |
|
|---|
| 339 |
|
|---|
| 340 | # Add the image metadata
|
|---|
| 341 | my $file; # the new file name
|
|---|
| 342 | my $id = $srcfile;
|
|---|
| 343 | $id =~ s/\.([^\.]*)$//; # the new file name without an extension
|
|---|
| 344 | if ($converted) {
|
|---|
| 345 | # we have converted the image
|
|---|
| 346 | # add on the new extension
|
|---|
| 347 | $file .= "$id.$converttotype";
|
|---|
| 348 | } else {
|
|---|
| 349 | $file = $srcfile;
|
|---|
| 350 | }
|
|---|
| 351 |
|
|---|
| 352 | my $url =$file; # the new file name prepared for a url
|
|---|
| 353 | my $srcurl = $srcfile;
|
|---|
| 354 | ##$url =~ s/ /%20/g;
|
|---|
| 355 | ##$srcurl =~ s/ /%20/g;
|
|---|
| 356 |
|
|---|
| 357 | $doc_obj->add_metadata ($section, "Image", $url);
|
|---|
| 358 |
|
|---|
| 359 | # Also want to set filename as 'Source' metadata to be
|
|---|
| 360 | # consistent with other plugins
|
|---|
| 361 | $doc_obj->add_metadata ($section, "Source", $srcurl);
|
|---|
| 362 |
|
|---|
| 363 | my ($image_type, $image_width, $image_height, $image_size)
|
|---|
| 364 | = &identify($filename, $outhandle, $verbosity);
|
|---|
| 365 |
|
|---|
| 366 | $doc_obj->add_metadata ($section, "ImageType", $image_type);
|
|---|
| 367 | $doc_obj->add_metadata ($section, "ImageWidth", $image_width);
|
|---|
| 368 | $doc_obj->add_metadata ($section, "ImageHeight", $image_height);
|
|---|
| 369 | $doc_obj->add_metadata ($section, "ImageSize", $image_size);
|
|---|
| 370 | $doc_obj->add_metadata ($section, "FileFormat", "PagedImg");
|
|---|
| 371 | # add NoText metadata which can be used to suppress the dummy text
|
|---|
| 372 | $doc_obj->add_metadata ($section, "NoText", "1");
|
|---|
| 373 |
|
|---|
| 374 | if ($type eq "unknown" && $image_type) {
|
|---|
| 375 | $type = $image_type;
|
|---|
| 376 | }
|
|---|
| 377 |
|
|---|
| 378 | if ($top) {
|
|---|
| 379 | $doc_obj->add_metadata ($section, "srclink",
|
|---|
| 380 | "<a href=\"_httpprefix_/collect/[collection]/index/assoc/[assocfilepath]/[Image]\">");
|
|---|
| 381 | $doc_obj->add_metadata ($section, "srcicon", "<img src=\"_httpprefix_/collect/[collection]/index/assoc/[assocfilepath]/[Image]\">");
|
|---|
| 382 |
|
|---|
| 383 | } else {
|
|---|
| 384 | $doc_obj->add_metadata ($section, "srclink",
|
|---|
| 385 | "<a href=\"_httpprefix_/collect/[collection]/index/assoc/[parent(Top):assocfilepath]/[Image]\">");
|
|---|
| 386 | $doc_obj->add_metadata ($section, "srcicon", "<img src=\"_httpprefix_/collect/[collection]/index/assoc/[parent(Top):assocfilepath]/[Image]\">");
|
|---|
| 387 |
|
|---|
| 388 | }
|
|---|
| 389 | $doc_obj->add_metadata ($section, "/srclink", "</a>");
|
|---|
| 390 |
|
|---|
| 391 |
|
|---|
| 392 | # Add the image as an associated file
|
|---|
| 393 | $doc_obj->associate_file($filename,$file,"image/$type",$section);
|
|---|
| 394 | print $outhandle "associating file $filename as name $file\n" if ($verbosity > 2);
|
|---|
| 395 |
|
|---|
| 396 | if ($self->{'thumbnail'}) {
|
|---|
| 397 | # Make the thumbnail image
|
|---|
| 398 | my $thumbnailsize = $self->{'thumbnailsize'} || 100;
|
|---|
| 399 | my $thumbnailtype = $self->{'thumbnailtype'} || 'gif';
|
|---|
| 400 |
|
|---|
| 401 | my $filehead = &util::get_tmp_filename();
|
|---|
| 402 | my $thumbnailfile = $filehead . ".$thumbnailtype";
|
|---|
| 403 | my $n=1;
|
|---|
| 404 | while (-e $thumbnailfile) {
|
|---|
| 405 | $thumbnailfile = $filehead . $n . ".$thumbnailtype";
|
|---|
| 406 | $n++;
|
|---|
| 407 | }
|
|---|
| 408 |
|
|---|
| 409 | $self->{'tmp_filename2'} = $thumbnailfile;
|
|---|
| 410 |
|
|---|
| 411 | # Generate the thumbnail with convert
|
|---|
| 412 | my $command = "convert -verbose -geometry $thumbnailsize"
|
|---|
| 413 | . "x$thumbnailsize \"$filename\" \"$thumbnailfile\"";
|
|---|
| 414 | print $outhandle "THUMBNAIL: $command\n" if ($verbosity > 2);
|
|---|
| 415 | my $result = '';
|
|---|
| 416 | $result = `$command 2>&1` ;
|
|---|
| 417 | print $outhandle "THUMB RESULT: $result\n" if ($verbosity > 2);
|
|---|
| 418 |
|
|---|
| 419 | # Add the thumbnail as an associated file ...
|
|---|
| 420 | if (-e "$thumbnailfile") {
|
|---|
| 421 | $doc_obj->associate_file("$thumbnailfile", $id."thumb.$thumbnailtype", "image/$thumbnailtype",$section);
|
|---|
| 422 | $doc_obj->add_metadata ($section, "ThumbType", $thumbnailtype);
|
|---|
| 423 | $doc_obj->add_metadata ($section, "Thumb", $id."thumb.$thumbnailtype");
|
|---|
| 424 | if ($top) {
|
|---|
| 425 | $doc_obj->add_metadata ($section, "thumbicon", "<img src=\"_httpprefix_/collect/[collection]/index/assoc/[assocfilepath]/[Thumb]\" width=[ThumbWidth] height=[ThumbHeight]>");
|
|---|
| 426 | } else {
|
|---|
| 427 | $doc_obj->add_metadata ($section, "thumbicon", "<img src=\"_httpprefix_/collect/[collection]/index/assoc/[parent(Top):assocfilepath]/[Thumb]\" width=[ThumbWidth] height=[ThumbHeight]>");
|
|---|
| 428 | }
|
|---|
| 429 | }
|
|---|
| 430 |
|
|---|
| 431 | # Extract Thumnail metadata from convert output
|
|---|
| 432 | if ($result =~ m/[0-9]+x[0-9]+=>([0-9]+)x([0-9]+)/) {
|
|---|
| 433 | $doc_obj->add_metadata ($section, "ThumbWidth", $1);
|
|---|
| 434 | $doc_obj->add_metadata ($section, "ThumbHeight", $2);
|
|---|
| 435 | }
|
|---|
| 436 | }
|
|---|
| 437 | # Make a screen-sized version of the picture if requested
|
|---|
| 438 | if ($self->{'screenview'}) {
|
|---|
| 439 |
|
|---|
| 440 | # To do: if the actual image is smaller than the screenview size,
|
|---|
| 441 | # we should use the original !
|
|---|
| 442 |
|
|---|
| 443 | my $screenviewsize = $self->{'screenviewsize'} || 500;
|
|---|
| 444 | my $screenviewtype = $self->{'screenviewtype'} || 'jpeg';
|
|---|
| 445 | my $filehead = &util::get_tmp_filename();
|
|---|
| 446 | my $screenviewfilename = $filehead . ".$screenviewtype";
|
|---|
| 447 | my $n=1;
|
|---|
| 448 | while (-e $screenviewfilename) {
|
|---|
| 449 | $screenviewfilename = "$filehead$n\.$screenviewtype";
|
|---|
| 450 | $n++;
|
|---|
| 451 | }
|
|---|
| 452 | $self->{'tmp_filename3'} = $screenviewfilename;
|
|---|
| 453 |
|
|---|
| 454 | # make the screenview image
|
|---|
| 455 | my $command = "convert -verbose -geometry $screenviewsize"
|
|---|
| 456 | . "x$screenviewsize \"$filename\" \"$screenviewfilename\"";
|
|---|
| 457 | print $outhandle "SCREENVIEW: $command\n" if ($verbosity > 2);
|
|---|
| 458 | my $result = "";
|
|---|
| 459 | $result = `$command 2>&1` ;
|
|---|
| 460 | print $outhandle "SCREENVIEW RESULT: $result\n" if ($verbosity > 3);
|
|---|
| 461 |
|
|---|
| 462 | # get screenview dimensions, size and type
|
|---|
| 463 | if ($result =~ m/[0-9]+x[0-9]+=>([0-9]+)x([0-9]+)/) {
|
|---|
| 464 | $doc_obj->add_metadata ($section, "ScreenWidth", $1);
|
|---|
| 465 | $doc_obj->add_metadata ($section, "ScreenHeight", $2);
|
|---|
| 466 | }elsif ($result =~ m/([0-9]+)x([0-9]+)/) {
|
|---|
| 467 | #if the image hasn't changed size, the previous regex doesn't match
|
|---|
| 468 | $doc_obj->add_metadata ($section, "ScreenWidth", $1);
|
|---|
| 469 | $doc_obj->add_metadata ($section, "ScreenHeight", $2);
|
|---|
| 470 | }
|
|---|
| 471 |
|
|---|
| 472 | #add the screenview as an associated file ...
|
|---|
| 473 | if (-e "$screenviewfilename") {
|
|---|
| 474 | $doc_obj->associate_file("$screenviewfilename", $id."sv.$screenviewtype",
|
|---|
| 475 | "image/$screenviewtype",$section);
|
|---|
| 476 | print $outhandle "associating screen file $screenviewfilename as name $id sv.$screenviewtype\n" if ($verbosity > 2);
|
|---|
| 477 |
|
|---|
| 478 | $doc_obj->add_metadata ($section, "ScreenType", $screenviewtype);
|
|---|
| 479 | $doc_obj->add_metadata ($section, "Screen", $id."sv.$screenviewtype");
|
|---|
| 480 |
|
|---|
| 481 | if ($top) {
|
|---|
| 482 | $doc_obj->add_metadata ($section, "screenicon", "<img src=\"_httpprefix_/collect/[collection]/index/assoc/[assocfilepath]/[Screen]\" width=[ScreenWidth] height=[ScreenHeight]>");
|
|---|
| 483 | } else {
|
|---|
| 484 | $doc_obj->add_metadata ($section, "screenicon", "<img src=\"_httpprefix_/collect/[collection]/index/assoc/[parent(Top):assocfilepath]/[Screen]\" width=[ScreenWidth] height=[ScreenHeight]>");
|
|---|
| 485 |
|
|---|
| 486 | }
|
|---|
| 487 | } else {
|
|---|
| 488 | print $outhandle "PagedImgPlug: couldn't find \"$screenviewfilename\"\n";
|
|---|
| 489 | }
|
|---|
| 490 | }
|
|---|
| 491 |
|
|---|
| 492 | return $type;
|
|---|
| 493 |
|
|---|
| 494 |
|
|---|
| 495 | }
|
|---|
| 496 |
|
|---|
| 497 |
|
|---|
| 498 |
|
|---|
| 499 | # Discover the characteristics of an image file with the ImageMagick
|
|---|
| 500 | # "identify" command.
|
|---|
| 501 |
|
|---|
| 502 | sub identify {
|
|---|
| 503 | my ($image, $outhandle, $verbosity) = @_;
|
|---|
| 504 |
|
|---|
| 505 | # Use the ImageMagick "identify" command to get the file specs
|
|---|
| 506 | my $command = "identify \"$image\" 2>&1";
|
|---|
| 507 | print $outhandle "$command\n" if ($verbosity > 2);
|
|---|
| 508 | my $result = '';
|
|---|
| 509 | $result = `$command`;
|
|---|
| 510 | print $outhandle "$result\n" if ($verbosity > 3);
|
|---|
| 511 |
|
|---|
| 512 | # Read the type, width, and height
|
|---|
| 513 | my $type = 'unknown';
|
|---|
| 514 | my $width = 'unknown';
|
|---|
| 515 | my $height = 'unknown';
|
|---|
| 516 |
|
|---|
| 517 | my $image_safe = quotemeta $image;
|
|---|
| 518 | if ($result =~ /^$image_safe (\w+) (\d+)x(\d+)/) {
|
|---|
| 519 | $type = $1;
|
|---|
| 520 | $width = $2;
|
|---|
| 521 | $height = $3;
|
|---|
| 522 | }
|
|---|
| 523 |
|
|---|
| 524 | # Read the size
|
|---|
| 525 | my $size = "unknown";
|
|---|
| 526 | if ($result =~ m/^.* ([0-9]+)b/) {
|
|---|
| 527 | $size = $1;
|
|---|
| 528 | } elsif ($result =~ m/^.* ([0-9]+)kb/) {
|
|---|
| 529 | $size = 1024 * $1;
|
|---|
| 530 | }
|
|---|
| 531 |
|
|---|
| 532 | print $outhandle "file: $image:\t $type, $width, $height, $size\n"
|
|---|
| 533 | if ($verbosity > 3);
|
|---|
| 534 |
|
|---|
| 535 | # Return the specs
|
|---|
| 536 | return ($type, $width, $height, $size);
|
|---|
| 537 | }
|
|---|
| 538 |
|
|---|
| 539 |
|
|---|
| 540 | # The PagedImgPlug read() function. This function does all the right things
|
|---|
| 541 | # to make general options work for a given plugin. It calls the process()
|
|---|
| 542 | # function which does all the work specific to a plugin (like the old
|
|---|
| 543 | # read functions used to do). Most plugins should define their own
|
|---|
| 544 | # process() function and let this read() function keep control.
|
|---|
| 545 | #
|
|---|
| 546 | # PagedImgPlug overrides read() because there is no need to read the actual
|
|---|
| 547 | # text of the file in, because the contents of the file is not text...
|
|---|
| 548 | #
|
|---|
| 549 | # Return number of files processed, undef if can't process
|
|---|
| 550 | # Note that $base_dir might be "" and that $file might
|
|---|
| 551 | # include directories
|
|---|
| 552 |
|
|---|
| 553 | sub read_into_doc_obj {
|
|---|
| 554 | my $self = shift (@_);
|
|---|
| 555 | my ($pluginfo, $base_dir, $file, $metadata, $processor, $maxdocs, $total_count, $gli) = @_;
|
|---|
| 556 | my $outhandle = $self->{'outhandle'};
|
|---|
| 557 |
|
|---|
| 558 | #check process and block exps, smart block, etc
|
|---|
| 559 | my ($block_status,$filename) = $self->read_block(@_);
|
|---|
| 560 | return $block_status if ((!defined $block_status) || ($block_status==0));
|
|---|
| 561 |
|
|---|
| 562 | print $outhandle "PagedImgPlug processing \"$filename\"\n"
|
|---|
| 563 | if $self->{'verbosity'} > 1;
|
|---|
| 564 | print STDERR "<Processing n='$file' p='PagedImgPlug'>\n" if ($gli);
|
|---|
| 565 |
|
|---|
| 566 | # here we need to decide if we have an old text .item file, or a new xml
|
|---|
| 567 | # .item file - for now the test is if the first non-empty line is
|
|---|
| 568 | # <PagedDocument> then its xml
|
|---|
| 569 | my $xml_version = 0;
|
|---|
| 570 | open (ITEMFILE, $filename) || die "couldn't open $filename\n";
|
|---|
| 571 |
|
|---|
| 572 | my $backup_filename = "backup.item";
|
|---|
| 573 | open (BACKUP,">$backup_filename")|| die "couldn't write to $backup_filename\n";
|
|---|
| 574 | my $line = "";
|
|---|
| 575 | my $num = 0;
|
|---|
| 576 | $line = <ITEMFILE>;
|
|---|
| 577 | while ($line !~ /\w/) {
|
|---|
| 578 | $line = <ITEMFILE>;
|
|---|
| 579 | }
|
|---|
| 580 | chomp $line;
|
|---|
| 581 | if ($line =~ /<PagedDocument/) {
|
|---|
| 582 | $xml_version = 1;
|
|---|
| 583 | }
|
|---|
| 584 | close ITEMFILE;
|
|---|
| 585 | open (ITEMFILE, $filename) || die "couldn't open $filename\n";
|
|---|
| 586 | $line = <ITEMFILE>;
|
|---|
| 587 | $line =~ s/^\xEF\xBB\xBF//; # strip BOM
|
|---|
| 588 | $line =~ s/\x0B+//ig;
|
|---|
| 589 | $line =~ s/&/&/g;
|
|---|
| 590 | print BACKUP ($line);
|
|---|
| 591 | #Tidy up the item file some metadata title contains \vt-vertical tab
|
|---|
| 592 | while ($line = <ITEMFILE>) {
|
|---|
| 593 | $line =~ s/\x0B+//ig;
|
|---|
| 594 | $line =~ s/&/&/g;
|
|---|
| 595 | print BACKUP ($line);
|
|---|
| 596 | }
|
|---|
| 597 | close ITEMFILE;
|
|---|
| 598 | close BACKUP;
|
|---|
| 599 | &File::Copy::copy ($backup_filename, $filename);
|
|---|
| 600 | &util::rm($backup_filename);
|
|---|
| 601 |
|
|---|
| 602 | my $doc_obj;
|
|---|
| 603 | if ($xml_version) {
|
|---|
| 604 | $file =~ s/^[\/\\]+//; # $file often begins with / so we'll tidy it up
|
|---|
| 605 | $self->{'file'} = $file;
|
|---|
| 606 | $self->{'filename'} = $filename;
|
|---|
| 607 | $self->{'processor'} = $processor;
|
|---|
| 608 | $self->{'metadata'} = $metadata;
|
|---|
| 609 |
|
|---|
| 610 | eval {
|
|---|
| 611 | $@ = "";
|
|---|
| 612 | my $xslt = $self->{'xslt'};
|
|---|
| 613 | if (defined $xslt && ($xslt ne "")) {
|
|---|
| 614 | # perform xslt
|
|---|
| 615 | my $transformed_xml = $self->apply_xslt($xslt,$filename);
|
|---|
| 616 |
|
|---|
| 617 | # feed transformed file (now in memory as string) into XML parser
|
|---|
| 618 | #$self->{'parser'}->parse($transformed_xml);
|
|---|
| 619 | $self->parse_string($transformed_xml);
|
|---|
| 620 | }
|
|---|
| 621 | else {
|
|---|
| 622 | #$self->{'parser'}->parsefile($filename);
|
|---|
| 623 | $self->parse_file($filename);
|
|---|
| 624 | }
|
|---|
| 625 | };
|
|---|
| 626 |
|
|---|
| 627 |
|
|---|
| 628 |
|
|---|
| 629 | if ($@) {
|
|---|
| 630 |
|
|---|
| 631 | # parsefile may either croak somewhere in XML::Parser (e.g. because
|
|---|
| 632 | # the document is not well formed) or die somewhere in XMLPlug or a
|
|---|
| 633 | # derived plugin (e.g. because we're attempting to process a
|
|---|
| 634 | # document whose DOCTYPE is not meant for this plugin). For the
|
|---|
| 635 | # first case we'll print a warning and continue, for the second
|
|---|
| 636 | # we'll just continue quietly
|
|---|
| 637 |
|
|---|
| 638 | print STDERR "**** XML Parse Error is: $@\n";
|
|---|
| 639 |
|
|---|
| 640 | my ($msg) = $@ =~ /Carp::croak\(\'(.*?)\'\)/;
|
|---|
| 641 | if (defined $msg) {
|
|---|
| 642 | my $outhandle = $self->{'outhandle'};
|
|---|
| 643 | my $plugin_name = ref ($self);
|
|---|
| 644 | print $outhandle "$plugin_name failed to process $file ($msg)\n";
|
|---|
| 645 | }
|
|---|
| 646 |
|
|---|
| 647 | # reset ourself for the next document
|
|---|
| 648 | $self->{'section_level'}=0;
|
|---|
| 649 | print STDERR "<ProcessingError n='$file'>\n" if ($gli);
|
|---|
| 650 | return -1; # error during processing
|
|---|
| 651 | }
|
|---|
| 652 | $doc_obj = $self->{'doc_obj'};
|
|---|
| 653 | } else {
|
|---|
| 654 | my ($dir);
|
|---|
| 655 | ($dir, $file) = $filename =~ /^(.*?)([^\/\\]*)$/;
|
|---|
| 656 |
|
|---|
| 657 | #process the .item file
|
|---|
| 658 | $doc_obj = $self->process_item($filename, $dir, $file, $processor);
|
|---|
| 659 |
|
|---|
| 660 | }
|
|---|
| 661 |
|
|---|
| 662 | if ($self->{'cover_image'}) {
|
|---|
| 663 | $self->associate_cover_image($doc_obj, $filename);
|
|---|
| 664 | }
|
|---|
| 665 |
|
|---|
| 666 | # include any metadata passed in from previous plugins
|
|---|
| 667 | # note that this metadata is associated with the top level section
|
|---|
| 668 | my $section = $doc_obj->get_top_section();
|
|---|
| 669 | $self->extra_metadata ($doc_obj, $section, $metadata);
|
|---|
| 670 | #my $text="";
|
|---|
| 671 | # do plugin specific processing of doc_obj
|
|---|
| 672 | #unless (defined ($self->process(\$text, $pluginfo, $base_dir, $file, $metadata, $doc_obj))) {
|
|---|
| 673 | #print STDERR "<ProcessingError n='$file'>\n" if ($gli);
|
|---|
| 674 | #return -1;
|
|---|
| 675 | #}
|
|---|
| 676 | # do any automatic metadata extraction
|
|---|
| 677 | $self->auto_extract_metadata ($doc_obj);
|
|---|
| 678 |
|
|---|
| 679 | $self->{'num_processed'}++;
|
|---|
| 680 | return (1,$doc_obj);
|
|---|
| 681 | }
|
|---|
| 682 |
|
|---|
| 683 | sub read
|
|---|
| 684 | {
|
|---|
| 685 | my $self = shift (@_);
|
|---|
| 686 | my ($pluginfo, $base_dir, $file, $metadata, $processor, $maxdocs, $total_count, $gli) = @_; my ($process_status,$doc_obj) = $self->read_into_doc_obj(@_);
|
|---|
| 687 |
|
|---|
| 688 | if ((defined $process_status) && ($process_status == 1)) {
|
|---|
| 689 | # process the document
|
|---|
| 690 | $processor->process($doc_obj);
|
|---|
| 691 |
|
|---|
| 692 | #if(defined($self->{'places_filename'})){
|
|---|
| 693 | # &util::rm($self->{'places_filename'});
|
|---|
| 694 | # $self->{'places_filename'} = undef;
|
|---|
| 695 | #}
|
|---|
| 696 | #$self->{'num_processed'} ++;
|
|---|
| 697 | undef $doc_obj;
|
|---|
| 698 | }
|
|---|
| 699 |
|
|---|
| 700 | # clean up temporary files - we do this here instead of in
|
|---|
| 701 | # process_image becuase associated files aren't actually copied
|
|---|
| 702 | # until after process has been run.
|
|---|
| 703 | if (defined $self->{'tmp_filename1'} &&
|
|---|
| 704 | -e $self->{'tmp_filename1'}) {
|
|---|
| 705 | &util::rm($self->{'tmp_filename1'})
|
|---|
| 706 | }
|
|---|
| 707 | if (defined $self->{'tmp_filename2'} &&
|
|---|
| 708 | -e $self->{'tmp_filename2'}) {
|
|---|
| 709 | &util::rm($self->{'tmp_filename2'})
|
|---|
| 710 | }
|
|---|
| 711 | if (defined $self->{'tmp_filename3'} &&
|
|---|
| 712 | -e $self->{'tmp_filename3'}) {
|
|---|
| 713 | &util::rm($self->{'tmp_filename3'})
|
|---|
| 714 | }
|
|---|
| 715 | # if process_status == 1, then the file has been processed.
|
|---|
| 716 | return $process_status;
|
|---|
| 717 | }
|
|---|
| 718 |
|
|---|
| 719 | sub xml_start_tag {
|
|---|
| 720 | my $self = shift(@_);
|
|---|
| 721 | my ($expat, $element) = @_;
|
|---|
| 722 | $self->{'element'} = $element;
|
|---|
| 723 |
|
|---|
| 724 | my $doc_obj = $self->{'doc_obj'};
|
|---|
| 725 | if ($element eq "PagedDocument") {
|
|---|
| 726 | $self->{'current_section'} = $doc_obj->get_top_section();
|
|---|
| 727 | } elsif ($element eq "PageGroup" || $element eq "Page") {
|
|---|
| 728 | # create a new section as a child
|
|---|
| 729 | $self->{'current_section'} = $doc_obj->insert_section($doc_obj->get_end_child($self->{'current_section'}));
|
|---|
| 730 | $self->{'num_pages'}++;
|
|---|
| 731 | # assign pagenum as what??
|
|---|
| 732 | my $pagenum = $_{'pagenum'}; #TODO!!
|
|---|
| 733 | if (defined $pagenum) {
|
|---|
| 734 | $doc_obj->set_utf8_metadata_element($self->{'current_section'}, 'PageNum', $pagenum);
|
|---|
| 735 | }
|
|---|
| 736 | my ($imgfile) = $_{'imgfile'};
|
|---|
| 737 | if (defined $imgfile) {
|
|---|
| 738 | $self->process_image($self->{'base_dir'}.$imgfile, $imgfile, $doc_obj, $self->{'current_section'});
|
|---|
| 739 | }
|
|---|
| 740 | my ($txtfile) = $_{'txtfile'};
|
|---|
| 741 | if (defined($txtfile)&& $txtfile ne "") {
|
|---|
| 742 | $self->process_text ($self->{'base_dir'}.$txtfile, $txtfile, $doc_obj, $self->{'current_section'});
|
|---|
| 743 | $doc_obj->set_metadata_element($self->{'current_section'},"NoText","0");
|
|---|
| 744 | } else {
|
|---|
| 745 | # otherwise add in some dummy text
|
|---|
| 746 | #create an empty text string so we don't break downstream plugins
|
|---|
| 747 | my $text = &gsprintf::lookup_string("{BasPlug.dummy_text}",1);
|
|---|
| 748 | $doc_obj->add_utf8_text($self->{'current_section'}, $text);
|
|---|
| 749 | $doc_obj->add_metadata($self->{'current_section'},"NoText","1");
|
|---|
| 750 | }
|
|---|
| 751 | } elsif ($element eq "Metadata") {
|
|---|
| 752 | $self->{'metadata_name'} = $_{'name'};
|
|---|
| 753 | }
|
|---|
| 754 | }
|
|---|
| 755 |
|
|---|
| 756 | sub xml_end_tag {
|
|---|
| 757 | my $self = shift(@_);
|
|---|
| 758 | my ($expat, $element) = @_;
|
|---|
| 759 |
|
|---|
| 760 | my $doc_obj = $self->{'doc_obj'};
|
|---|
| 761 | if ($element eq "Page" || $element eq "PageGroup") {
|
|---|
| 762 | # if Title hasn't been assigned, set PageNum as Title
|
|---|
| 763 | if (!defined $doc_obj->get_metadata_element ($self->{'current_section'}, "Title") && defined $doc_obj->get_metadata_element ($self->{'current_section'}, "PageNum" )) {
|
|---|
| 764 | $doc_obj->add_utf8_metadata ($self->{'current_section'}, "Title", $doc_obj->get_metadata_element ($self->{'current_section'}, "PageNum" ));
|
|---|
| 765 | }
|
|---|
| 766 | # move the current section back to the parent
|
|---|
| 767 | $self->{'current_section'} = $doc_obj->get_parent_section($self->{'current_section'});
|
|---|
| 768 | } elsif ($element eq "Metadata") {
|
|---|
| 769 |
|
|---|
| 770 | $doc_obj->add_utf8_metadata ($self->{'current_section'}, $self->{'metadata_name'}, $self->{'metadata_value'});
|
|---|
| 771 | $self->{'metadata_name'} = "";
|
|---|
| 772 | $self->{'metadata_value'} = "";
|
|---|
| 773 |
|
|---|
| 774 | }
|
|---|
| 775 | # otherwise we ignore the end tag
|
|---|
| 776 | }
|
|---|
| 777 |
|
|---|
| 778 |
|
|---|
| 779 | sub xml_text {
|
|---|
| 780 | my $self = shift(@_);
|
|---|
| 781 | my ($expat) = @_;
|
|---|
| 782 |
|
|---|
| 783 | if ($self->{'element'} eq "Metadata" && $self->{'metadata_name'}) {
|
|---|
| 784 | $self->{'metadata_value'} .= $_;
|
|---|
| 785 | }
|
|---|
| 786 | }
|
|---|
| 787 |
|
|---|
| 788 | sub xml_doctype {
|
|---|
| 789 | }
|
|---|
| 790 |
|
|---|
| 791 | sub open_document {
|
|---|
| 792 | my $self = shift(@_);
|
|---|
| 793 |
|
|---|
| 794 | # create a new document
|
|---|
| 795 | $self->{'doc_obj'} = new doc ($self->{'filename'}, "indexed_doc");
|
|---|
| 796 | my $doc_obj = $self->{'doc_obj'};
|
|---|
| 797 | $doc_obj->set_OIDtype ($self->{'processor'}->{'OIDtype'});
|
|---|
| 798 | my ($dir, $file) = $self->{'filename'} =~ /^(.*?)([^\/\\]*)$/;
|
|---|
| 799 | $self->{'base_dir'} = $dir;
|
|---|
| 800 | $self->{'num_pages'} = 0;
|
|---|
| 801 | my $topsection = $doc_obj->get_top_section();
|
|---|
| 802 | if ($self->{'documenttype'} eq 'paged') {
|
|---|
| 803 | # set the gsdlthistype metadata to Paged - this ensures this document will
|
|---|
| 804 | # be treated as a Paged doc, even if Titles are not numeric
|
|---|
| 805 |
|
|---|
| 806 | $doc_obj->set_utf8_metadata_element ($topsection, "gsdlthistype", "Paged");
|
|---|
| 807 | } else {
|
|---|
| 808 | $doc_obj->set_utf8_metadata_element ($topsection, "gsdlthistype", "Hierarchy");
|
|---|
| 809 | }
|
|---|
| 810 |
|
|---|
| 811 | $doc_obj->add_metadata ($topsection, "Source", $file);
|
|---|
| 812 | if ($self->{'headerpage'}) {
|
|---|
| 813 | $doc_obj->add_text($topsection, &gsprintf::lookup_string("{BasPlug.dummy_text}"));
|
|---|
| 814 | }
|
|---|
| 815 |
|
|---|
| 816 | }
|
|---|
| 817 |
|
|---|
| 818 | sub close_document {
|
|---|
| 819 | my $self = shift(@_);
|
|---|
| 820 | my $doc_obj = $self->{'doc_obj'};
|
|---|
| 821 |
|
|---|
| 822 | $doc_obj->add_utf8_metadata($doc_obj->get_top_section(), "Plugin", "$self->{'plugin_type'}");
|
|---|
| 823 | $doc_obj->add_metadata($doc_obj->get_top_section(), "FileFormat", "PagedImg");
|
|---|
| 824 |
|
|---|
| 825 | # add numpages metadata
|
|---|
| 826 | $doc_obj->set_utf8_metadata_element ($doc_obj->get_top_section(), 'NumPages', $self->{'num_pages'});
|
|---|
| 827 |
|
|---|
| 828 | # add an OID
|
|---|
| 829 | $doc_obj->set_OID();
|
|---|
| 830 |
|
|---|
| 831 | }
|
|---|
| 832 |
|
|---|
| 833 | sub process_item {
|
|---|
| 834 | my $self = shift (@_);
|
|---|
| 835 | my ($filename, $dir, $file, $processor) = @_;
|
|---|
| 836 |
|
|---|
| 837 | my $doc_obj = new doc ($filename, "indexed_doc");
|
|---|
| 838 | $doc_obj->set_OIDtype ($processor->{'OIDtype'}, $processor->{'OIDmetadata'});
|
|---|
| 839 | my $topsection = $doc_obj->get_top_section();
|
|---|
| 840 | $doc_obj->add_utf8_metadata($topsection, "Plugin", "$self->{'plugin_type'}");
|
|---|
| 841 | $doc_obj->add_metadata($topsection, "FileFormat", "PagedImg");
|
|---|
| 842 |
|
|---|
| 843 | if ($self->{'documenttype'} eq 'paged') {
|
|---|
| 844 | # set the gsdlthistype metadata to Paged - this ensures this document will
|
|---|
| 845 | # be treated as a Paged doc, even if Titles are not numeric
|
|---|
| 846 | $doc_obj->set_utf8_metadata_element ($topsection, "gsdlthistype", "Paged");
|
|---|
| 847 | } else {
|
|---|
| 848 | $doc_obj->set_utf8_metadata_element ($topsection, "gsdlthistype", "Hierarchy");
|
|---|
| 849 | }
|
|---|
| 850 |
|
|---|
| 851 | $doc_obj->add_metadata ($topsection, "Source", $file);
|
|---|
| 852 |
|
|---|
| 853 | open (ITEMFILE, $filename) || die "couldn't open $filename\n";
|
|---|
| 854 | my $line = "";
|
|---|
| 855 | my $num = 0;
|
|---|
| 856 | while (defined ($line = <ITEMFILE>)) {
|
|---|
| 857 | next unless $line =~ /\w/;
|
|---|
| 858 | chomp $line;
|
|---|
| 859 | next if $line =~ /^#/; # ignore comment lines
|
|---|
| 860 | if ($line =~ /^<([^>]*)>\s*(.*?)\s*$/) {
|
|---|
| 861 | $doc_obj->set_utf8_metadata_element ($topsection, $1, $2);
|
|---|
| 862 | #$meta->{$1} = $2;
|
|---|
| 863 | } else {
|
|---|
| 864 | $num++;
|
|---|
| 865 | # line should be like page:imagefilename:textfilename:r - the r is optional -> means rotate the image 180 deg
|
|---|
| 866 | $line =~ s/^\s+//; #remove space at the front
|
|---|
| 867 | $line =~ s/\s+$//; #remove space at the end
|
|---|
| 868 | my ($pagenum, $imgname, $txtname, $rotate) = split /:/, $line;
|
|---|
| 869 |
|
|---|
| 870 | # create a new section for each image file
|
|---|
| 871 | my $cursection = $doc_obj->insert_section($doc_obj->get_end_child($topsection));
|
|---|
| 872 | # the page number becomes the Title
|
|---|
| 873 | $doc_obj->set_utf8_metadata_element($cursection, 'Title', $pagenum);
|
|---|
| 874 |
|
|---|
| 875 | # process the image for this page if there is one
|
|---|
| 876 | if (defined $imgname && $imgname ne "") {
|
|---|
| 877 | my $result1 = $self->process_image($dir.$imgname, $imgname, $doc_obj, $cursection, $rotate);
|
|---|
| 878 |
|
|---|
| 879 | if (!defined $result1)
|
|---|
| 880 | {
|
|---|
| 881 | print "PagedImgPlug: couldn't process image \"$dir.$imgname\" for item \"$filename\"\n";
|
|---|
| 882 | }
|
|---|
| 883 | }
|
|---|
| 884 | # process the text file if one is there
|
|---|
| 885 | if (defined $txtname && $txtname ne "") {
|
|---|
| 886 | my $result2 = $self->process_text ($dir.$txtname, $txtname, $doc_obj, $cursection);
|
|---|
| 887 |
|
|---|
| 888 | if (!defined $result2) {
|
|---|
| 889 | print "PagedImgPlug: couldn't process text file \"$dir.$txtname\" for item \"$filename\"\n";
|
|---|
| 890 | }
|
|---|
| 891 | else{
|
|---|
| 892 | $doc_obj->set_metadata_element($cursection, "NoText", "0");
|
|---|
| 893 | }
|
|---|
| 894 | } else {
|
|---|
| 895 | # otherwise add in some dummy text
|
|---|
| 896 | $doc_obj->add_text($cursection, &gsprintf::lookup_string("{BasPlug.dummy_text}"));
|
|---|
| 897 | # add NoText metadata which can be used to suppress the dummy text
|
|---|
| 898 | }
|
|---|
| 899 | }
|
|---|
| 900 | }
|
|---|
| 901 |
|
|---|
| 902 | close ITEMFILE;
|
|---|
| 903 |
|
|---|
| 904 | # if we want a header page, we need to add some text into the top section, otherwise this section will become invisible
|
|---|
| 905 | if ($self->{'headerpage'}) {
|
|---|
| 906 | $doc_obj->add_text($topsection, &gsprintf::lookup_string("{BasPlug.dummy_text}"));
|
|---|
| 907 | }
|
|---|
| 908 | $file =~ s/\.item//i;
|
|---|
| 909 | $doc_obj->set_OID ();
|
|---|
| 910 | # add numpages metadata
|
|---|
| 911 | $doc_obj->set_utf8_metadata_element ($topsection, 'NumPages', "$num");
|
|---|
| 912 | return $doc_obj;
|
|---|
| 913 | }
|
|---|
| 914 |
|
|---|
| 915 | sub process_text {
|
|---|
| 916 | my $self = shift (@_);
|
|---|
| 917 | my ($fullpath, $file, $doc_obj, $cursection) = @_;
|
|---|
| 918 |
|
|---|
| 919 | # check that the text file exists!!
|
|---|
| 920 | if (!-f $fullpath) {
|
|---|
| 921 | print "PagedImgPlug: ERROR: File $fullpath does not exist, skipping\n";
|
|---|
| 922 | return 0;
|
|---|
| 923 | }
|
|---|
| 924 |
|
|---|
| 925 | # Do encoding stuff
|
|---|
| 926 | my ($language, $encoding) = $self->textcat_get_language_encoding ($fullpath);
|
|---|
| 927 |
|
|---|
| 928 | my $text="";
|
|---|
| 929 | &BasPlug::read_file($self, $fullpath, $encoding, $language, \$text);
|
|---|
| 930 | if (!length ($text)) {
|
|---|
| 931 | # It's a bit unusual but not out of the question to have no text, so just give a warning
|
|---|
| 932 | print "PagedImgPlug: WARNING: $fullpath contains no text\n";
|
|---|
| 933 | }
|
|---|
| 934 |
|
|---|
| 935 | # we need to escape the escape character, or else mg will convert into
|
|---|
| 936 | # eg literal newlines, instead of leaving the text as '\n'
|
|---|
| 937 | $text =~ s/\\/\\\\/g; # macro language
|
|---|
| 938 | $text =~ s/_/\\_/g; # macro language
|
|---|
| 939 |
|
|---|
| 940 |
|
|---|
| 941 | if ($text =~ m/<html.*?>\s*<head.*?>.*<\/head>\s*<body.*?>(.*)<\/body>\s*<\/html>\s*$/s) {
|
|---|
| 942 | # looks like HTML input
|
|---|
| 943 | # no need to escape < and > or put in <pre> tags
|
|---|
| 944 |
|
|---|
| 945 | $text = $1;
|
|---|
| 946 |
|
|---|
| 947 | # insert preformat tags and add text to document object
|
|---|
| 948 | $doc_obj->add_utf8_text($cursection, "$text");
|
|---|
| 949 | }
|
|---|
| 950 | else {
|
|---|
| 951 | $text =~ s/</</g;
|
|---|
| 952 | $text =~ s/>/>/g;
|
|---|
| 953 |
|
|---|
| 954 | # insert preformat tags and add text to document object
|
|---|
| 955 | $doc_obj->add_utf8_text($cursection, "<pre>\n$text\n</pre>");
|
|---|
| 956 | }
|
|---|
| 957 |
|
|---|
| 958 |
|
|---|
| 959 | return 1;
|
|---|
| 960 | }
|
|---|
| 961 |
|
|---|
| 962 | # do plugin specific processing of doc_obj
|
|---|
| 963 | sub process {
|
|---|
| 964 | my $self = shift (@_);
|
|---|
| 965 | my ($textref, $pluginfo, $base_dir, $file, $metadata, $doc_obj) = @_;
|
|---|
| 966 | my $outhandle = $self->{'outhandle'};
|
|---|
| 967 |
|
|---|
| 968 | return 1;
|
|---|
| 969 | }
|
|---|
| 970 |
|
|---|
| 971 | 1;
|
|---|
