| 1 | ###########################################################################
|
|---|
| 2 | #
|
|---|
| 3 | # NPPlug.pm -- Plugin for the niupepa collection
|
|---|
| 4 | # A component of the Greenstone digital library software
|
|---|
| 5 | # from the New Zealand Digital Library Project at the
|
|---|
| 6 | # University of Waikato, New Zealand.
|
|---|
| 7 | #
|
|---|
| 8 | # Copyright (C) 1999 New Zealand Digital Library Project
|
|---|
| 9 | #
|
|---|
| 10 | # This program is free software; you can redistribute it and/or modify
|
|---|
| 11 | # it under the terms of the GNU General Public License as published by
|
|---|
| 12 | # the Free Software Foundation; either version 2 of the License, or
|
|---|
| 13 | # (at your option) any later version.
|
|---|
| 14 | #
|
|---|
| 15 | # This program is distributed in the hope that it will be useful,
|
|---|
| 16 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|---|
| 17 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|---|
| 18 | # GNU General Public License for more details.
|
|---|
| 19 | #
|
|---|
| 20 | # You should have received a copy of the GNU General Public License
|
|---|
| 21 | # along with this program; if not, write to the Free Software
|
|---|
| 22 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
|---|
| 23 | #
|
|---|
| 24 | ###########################################################################
|
|---|
| 25 |
|
|---|
| 26 | # The niupepa collection has a file structure as follows:
|
|---|
| 27 | # Each niupepa series has its own directory containing some/all
|
|---|
| 28 | # of the following:
|
|---|
| 29 |
|
|---|
| 30 | # meta.txt - file contains metadata to be associated with all documents
|
|---|
| 31 | # in series.
|
|---|
| 32 | # *.issue - each issue should have a .issue file which may or may not
|
|---|
| 33 | # contain metadata to associate with the issue. also contains the list
|
|---|
| 34 | # of filenames that make up the issue (i.e. one for each page). meta.txt
|
|---|
| 35 | # is read before *.issue so metadata in .issue files will override that in
|
|---|
| 36 | # meta.txt
|
|---|
| 37 | # *.commentary - the commentary of the niupepa series (1 per series)
|
|---|
| 38 | # text/*.txt/htm - text/html files of issue pages (1 per page) -
|
|---|
| 39 | # text files are expected to be either .htm or .txt (lower case).
|
|---|
| 40 | # images/*.gif - image files of issue pages (1 per page)
|
|---|
| 41 | # abstracts/*.abstract - html files of issue abstracts (1 per issue)
|
|---|
| 42 |
|
|---|
| 43 |
|
|---|
| 44 | package NPPlug;
|
|---|
| 45 |
|
|---|
| 46 | use BasPlug;
|
|---|
| 47 | use util;
|
|---|
| 48 |
|
|---|
| 49 | sub BEGIN {
|
|---|
| 50 | @ISA = ('BasPlug');
|
|---|
| 51 | }
|
|---|
| 52 |
|
|---|
| 53 | use strict;
|
|---|
| 54 |
|
|---|
| 55 | sub print_usage {
|
|---|
| 56 | print STDERR "\nIncorrect options passed to NPPlug, check your collect.cfg configuration file\n";
|
|---|
| 57 |
|
|---|
| 58 | print STDERR "\n usage: plugin NPPlug [options]\n\n";
|
|---|
| 59 | print STDERR " options:\n";
|
|---|
| 60 | print STDERR " -create_log Creates a log file containing info about which portions\n";
|
|---|
| 61 | print STDERR " of papers are missing\n";
|
|---|
| 62 | print STDERR " -logfile Path of logfile (defaults to ./log.txt)\n\n";
|
|---|
| 63 | }
|
|---|
| 64 |
|
|---|
| 65 | sub new {
|
|---|
| 66 | my ($class) = @_;
|
|---|
| 67 | my $self = new BasPlug ();
|
|---|
| 68 |
|
|---|
| 69 | if (!parsargv::parse(\@_,
|
|---|
| 70 | q^create_log^, \$self->{'create_log'},
|
|---|
| 71 | q^logfile/.*/./log.txt^, \$self->{'logfile'})) {
|
|---|
| 72 | &print_usage();
|
|---|
| 73 | die "\n";
|
|---|
| 74 | }
|
|---|
| 75 |
|
|---|
| 76 | $self->{'commentaries'} = {};
|
|---|
| 77 | $self->{'num_issues'} = 0;
|
|---|
| 78 | $self->{'num_text_pages'} = 0;
|
|---|
| 79 | $self->{'num_image_pages'} = 0;
|
|---|
| 80 | $self->{'num_abstracts'} = 0;
|
|---|
| 81 | return bless $self, $class;
|
|---|
| 82 | }
|
|---|
| 83 |
|
|---|
| 84 | sub is_recursive {
|
|---|
| 85 | my $self = shift (@_);
|
|---|
| 86 |
|
|---|
| 87 | return 0; # this is not a recursive plugin
|
|---|
| 88 | }
|
|---|
| 89 |
|
|---|
| 90 | sub begin {
|
|---|
| 91 | my $self = shift (@_);
|
|---|
| 92 | my ($pluginfo, $base_dir, $processor, $maxdocs) = @_;
|
|---|
| 93 |
|
|---|
| 94 | # open up logfile
|
|---|
| 95 | # note that we append to logfile as building will otherwise
|
|---|
| 96 | # overwrite a file generated at import time
|
|---|
| 97 | if ($self->{'create_log'}) {
|
|---|
| 98 | open (LOGFILE, ">>$self->{'logfile'}") || die
|
|---|
| 99 | "NPPlug.pm: Couldn't open log file $self->{'logfile'}\n";
|
|---|
| 100 |
|
|---|
| 101 | my @time = localtime (time);
|
|---|
| 102 |
|
|---|
| 103 | print LOGFILE "------------------------------------------------------------\n";
|
|---|
| 104 | print LOGFILE "Log start $time[3]/$time[4]/" . (1900 + $time[5]) . "\n";
|
|---|
| 105 | print LOGFILE "------------------------------------------------------------\n";
|
|---|
| 106 | }
|
|---|
| 107 | }
|
|---|
| 108 |
|
|---|
| 109 | sub end {
|
|---|
| 110 | my $self = shift (@_);
|
|---|
| 111 |
|
|---|
| 112 | if ($self->{'create_log'}) {
|
|---|
| 113 | my $numseries = 0;
|
|---|
| 114 | my $numcommentaries = 0;
|
|---|
| 115 |
|
|---|
| 116 | # record missing commentaries in logfile
|
|---|
| 117 | foreach my $key (keys %{$self->{'commentaries'}}) {
|
|---|
| 118 | $numseries ++;
|
|---|
| 119 | if (!$self->{'commentaries'}->{$key}) {
|
|---|
| 120 | print LOGFILE "Commentary missing for series $key\n";
|
|---|
| 121 | } else {
|
|---|
| 122 | $numcommentaries ++;
|
|---|
| 123 | }
|
|---|
| 124 | }
|
|---|
| 125 |
|
|---|
| 126 | print LOGFILE "\n\nStatistics:\n";
|
|---|
| 127 | print LOGFILE "series: $numseries\n";
|
|---|
| 128 | print LOGFILE "commentaries: $numcommentaries\n";
|
|---|
| 129 | print LOGFILE "issues: $self->{'num_issues'}\n";
|
|---|
| 130 | print LOGFILE "abstracts: $self->{'num_abstracts'}\n";
|
|---|
| 131 | print LOGFILE "text pages: $self->{'num_text_pages'}\n";
|
|---|
| 132 | print LOGFILE "image pages: $self->{'num_image_pages'}\n";
|
|---|
| 133 |
|
|---|
| 134 | # close logfile
|
|---|
| 135 | close LOGFILE;
|
|---|
| 136 | }
|
|---|
| 137 | }
|
|---|
| 138 |
|
|---|
| 139 | # return number of files processed, undef if can't process
|
|---|
| 140 | # Note that $base_dir might be "" and that $file might
|
|---|
| 141 | # include directories
|
|---|
| 142 | sub read {
|
|---|
| 143 | my $self = shift (@_);
|
|---|
| 144 | my ($pluginfo, $base_dir, $file, $metadata, $processor) = @_;
|
|---|
| 145 |
|
|---|
| 146 | my $filename = &util::filename_cat($base_dir, $file);
|
|---|
| 147 |
|
|---|
| 148 | # we don't want RecPlug to go recursing into the text, images or
|
|---|
| 149 | # abstracts directories
|
|---|
| 150 | return 0 if (-d $filename && $filename =~ /(abstracts|images|text)/);
|
|---|
| 151 |
|
|---|
| 152 | return 0 if $filename =~ /meta\.txt$/i;
|
|---|
| 153 |
|
|---|
| 154 | return undef unless ($filename =~ /\.(issue|commentary)$/i && (-e $filename));
|
|---|
| 155 |
|
|---|
| 156 | $self->{'verbosity'} = $processor->{'verbosity'};
|
|---|
| 157 | print STDERR "NPPlug: processing $filename\n" if $self->{'verbosity'};
|
|---|
| 158 |
|
|---|
| 159 | my ($dir);
|
|---|
| 160 | ($dir, $file) = $filename =~ /^(.*?)([^\/\\]*)$/;
|
|---|
| 161 | my ($issuekey) = $file =~ /^([^\.\_]*)/;
|
|---|
| 162 |
|
|---|
| 163 | if ($filename =~ /\.commentary$/i) {
|
|---|
| 164 | # commentary
|
|---|
| 165 | return $self->process_commentary ($filename, $issuekey, $dir, $file, $processor);
|
|---|
| 166 | }
|
|---|
| 167 |
|
|---|
| 168 | my $numprocessed = 0;
|
|---|
| 169 | $self->{'commentaries'}->{$issuekey} = 0 unless defined $self->{'commentaries'}->{$issuekey};
|
|---|
| 170 |
|
|---|
| 171 | my ($abstractfile) = $file =~ /^([^\.]*)\.issue/i;
|
|---|
| 172 | my $abstractOID = $abstractfile . "abstract";
|
|---|
| 173 | $abstractfile .= ".abstract";
|
|---|
| 174 | my $afile = &util::filename_cat($dir, "abstracts", $abstractfile);
|
|---|
| 175 | my $hasabstract = 0;
|
|---|
| 176 | if (-e $afile) {$hasabstract = 1;}
|
|---|
| 177 | else {$abstractOID = undef;}
|
|---|
| 178 |
|
|---|
| 179 | # process the .issue file
|
|---|
| 180 | my %meta = ();
|
|---|
| 181 | $numprocessed += $self->process_issue ($filename, $issuekey, $dir, $file,
|
|---|
| 182 | $abstractOID, $processor, \%meta);
|
|---|
| 183 |
|
|---|
| 184 | # process abstract of this issue
|
|---|
| 185 | if ($hasabstract) {
|
|---|
| 186 | $numprocessed += $self->process_abstract ($afile, $issuekey, $dir,
|
|---|
| 187 | $abstractfile, $processor, \%meta);
|
|---|
| 188 | }
|
|---|
| 189 |
|
|---|
| 190 | return $numprocessed;
|
|---|
| 191 | }
|
|---|
| 192 |
|
|---|
| 193 | sub process_issue {
|
|---|
| 194 | my $self = shift (@_);
|
|---|
| 195 | my ($filename, $issuekey, $dir, $file, $abstract, $processor, $meta) = @_;
|
|---|
| 196 |
|
|---|
| 197 | $self->{'num_issues'} ++;
|
|---|
| 198 | my $doc_obj = new doc ($file, "indexed_doc");
|
|---|
| 199 | my $topsection = $doc_obj->get_top_section();
|
|---|
| 200 | $self->associate_cover_images ($doc_obj, $dir, $issuekey);
|
|---|
| 201 | $doc_obj->set_utf8_metadata_element ($topsection, 'Title', $self->get_title_string($file));
|
|---|
| 202 | $doc_obj->set_utf8_metadata_element ($topsection, 'abstract', $abstract) if defined $abstract;
|
|---|
| 203 | $self->set_main_metadata ($doc_obj, $dir);
|
|---|
| 204 |
|
|---|
| 205 | # process issue's pdf if one exists
|
|---|
| 206 | my ($pdffile) = $file =~ /^([^\.]*)\.issue/i;
|
|---|
| 207 | $pdffile .= ".pdf";
|
|---|
| 208 | $pdffile = &util::filename_cat($dir, "pdf", $pdffile);
|
|---|
| 209 | if (-e $pdffile) {
|
|---|
| 210 | $doc_obj->set_utf8_metadata_element ($topsection, "haspdf", "1");
|
|---|
| 211 | $doc_obj->associate_file($pdffile, "paper.pdf");
|
|---|
| 212 | } else {
|
|---|
| 213 | $doc_obj->set_utf8_metadata_element ($topsection, "haspdf", "0");
|
|---|
| 214 | }
|
|---|
| 215 |
|
|---|
| 216 | open (ISSUEFILE, $filename) || die "couldn't open $filename\n";
|
|---|
| 217 | my $line = "";
|
|---|
| 218 | while (defined ($line = <ISSUEFILE>)) {
|
|---|
| 219 | next unless $line =~ /\w/;
|
|---|
| 220 | chomp $line;
|
|---|
| 221 | if ($line =~ /^<([^>]*)>(.*?)\s*$/) {
|
|---|
| 222 | $doc_obj->set_utf8_metadata_element ($topsection, $1, $2);
|
|---|
| 223 | $meta->{$1} = $2;
|
|---|
| 224 | } else {
|
|---|
| 225 | # should be a section name
|
|---|
| 226 | $line =~ s/^\s+//;
|
|---|
| 227 | $line =~ s/\s+$//;
|
|---|
| 228 | my ($pagenum) = $line =~ /([^_]*)$/;
|
|---|
| 229 | # $doc_obj->create_named_section($pagenum); <-- can't do this anymore as pagenum may
|
|---|
| 230 | # be something like "cover"
|
|---|
| 231 | my $cursection = $doc_obj->insert_section($doc_obj->get_end_child($topsection));
|
|---|
| 232 |
|
|---|
| 233 | # $doc_obj->set_utf8_metadata_element($pagenum, 'Title', $pagenum);
|
|---|
| 234 | $doc_obj->set_utf8_metadata_element($cursection, 'Title', $pagenum);
|
|---|
| 235 | # $self->process_text ($dir, $line, $doc_obj, $pagenum);
|
|---|
| 236 | $self->process_text ($dir, $line, $doc_obj, $cursection);
|
|---|
| 237 | # $self->process_images ($dir, $line, $doc_obj, $pagenum);
|
|---|
| 238 | $self->process_images ($dir, $line, $doc_obj, $cursection);
|
|---|
| 239 | }
|
|---|
| 240 | }
|
|---|
| 241 | $file =~ s/\.issue//i;
|
|---|
| 242 | $doc_obj->set_OID ($file);
|
|---|
| 243 | $processor->process ($doc_obj);
|
|---|
| 244 | return 1;
|
|---|
| 245 | }
|
|---|
| 246 |
|
|---|
| 247 | sub process_images {
|
|---|
| 248 | my $self = shift (@_);
|
|---|
| 249 | my ($dir, $page, $doc_obj, $cursection) = @_;
|
|---|
| 250 |
|
|---|
| 251 | my $filename = &util::filename_cat ($dir, "images", $page);
|
|---|
| 252 |
|
|---|
| 253 | if (-e "$filename.gif") {
|
|---|
| 254 | $self->{'num_image_pages'} ++;
|
|---|
| 255 | $doc_obj->set_utf8_metadata_element ($cursection, "hasimg", "1");
|
|---|
| 256 | $doc_obj->set_utf8_metadata_element ($cursection, "Source", $page);
|
|---|
| 257 | $doc_obj->associate_file("$filename.gif", "$page.gif", "image/gif");
|
|---|
| 258 | } elsif ($self->{'create_log'}) {
|
|---|
| 259 | $doc_obj->set_utf8_metadata_element ($cursection, "hasimg", "0");
|
|---|
| 260 | print LOGFILE "no fullsize image file for $page\n";
|
|---|
| 261 | }
|
|---|
| 262 |
|
|---|
| 263 | if (-e "${filename}_p.gif") {
|
|---|
| 264 | $doc_obj->set_utf8_metadata_element ($cursection, "hasprevimg", "1");
|
|---|
| 265 | $doc_obj->set_utf8_metadata_element ($cursection, "Source", $page);
|
|---|
| 266 | $doc_obj->associate_file("${filename}_p.gif", "${page}_p.gif", "image/gif");
|
|---|
| 267 | } elsif ($self->{'create_log'}) {
|
|---|
| 268 | $doc_obj->set_utf8_metadata_element ($cursection, "hasprevimg", "0");
|
|---|
| 269 | print LOGFILE "no preview image file for $page\n";
|
|---|
| 270 | }
|
|---|
| 271 | }
|
|---|
| 272 |
|
|---|
| 273 | sub process_text {
|
|---|
| 274 | my $self = shift (@_);
|
|---|
| 275 | my ($dir, $page, $doc_obj, $cursection) = @_;
|
|---|
| 276 | my ($text);
|
|---|
| 277 |
|
|---|
| 278 | my $filename = &util::filename_cat ($dir, "text", $page);
|
|---|
| 279 | if (-e "$filename.htm") {
|
|---|
| 280 | $text = $self->get_text ("$filename.htm");
|
|---|
| 281 | } elsif (-e "$filename.txt") {
|
|---|
| 282 | $text = $self->get_text ("$filename.txt");
|
|---|
| 283 | }
|
|---|
| 284 |
|
|---|
| 285 | if (defined $text) {
|
|---|
| 286 | $self->{'num_text_pages'} ++;
|
|---|
| 287 | $doc_obj->add_utf8_text ($cursection, $text);
|
|---|
| 288 | } elsif ($self->{'create_log'}) {
|
|---|
| 289 | print LOGFILE "no txt or htm file for $page\n";
|
|---|
| 290 | }
|
|---|
| 291 | }
|
|---|
| 292 |
|
|---|
| 293 | sub process_abstract {
|
|---|
| 294 | my $self = shift (@_);
|
|---|
| 295 | my ($filename, $issuekey, $dir, $file, $processor, $meta) = @_;
|
|---|
| 296 |
|
|---|
| 297 | my $text = $self->get_text ($filename);
|
|---|
| 298 | if (defined $text) {
|
|---|
| 299 | $self->{'num_abstracts'} ++;
|
|---|
| 300 | my $doc_obj = new doc ($file, "indexed_doc");
|
|---|
| 301 | my $cursection = $doc_obj->get_top_section();
|
|---|
| 302 | $self->associate_cover_images ($doc_obj, $dir, $issuekey);
|
|---|
| 303 | $doc_obj->set_utf8_metadata_element ($cursection, 'Title', $self->get_title_string($file));
|
|---|
| 304 | $self->set_main_metadata ($doc_obj, $dir);
|
|---|
| 305 | map { $doc_obj->set_utf8_metadata_element ($cursection, $_, $meta->{$_}); } keys %$meta;
|
|---|
| 306 | $doc_obj->set_utf8_metadata_element ($cursection, "doctype", "Description");
|
|---|
| 307 | $doc_obj->add_utf8_text ($cursection, $text);
|
|---|
| 308 | $file =~ s/\.abstract//i;
|
|---|
| 309 | $doc_obj->set_OID ($file . "abstract");
|
|---|
| 310 | $processor->process ($doc_obj);
|
|---|
| 311 | return 1;
|
|---|
| 312 | }
|
|---|
| 313 |
|
|---|
| 314 | if ($self->{'create_log'}) {
|
|---|
| 315 | print LOGFILE "abstract file $filename doesn't exist\n";
|
|---|
| 316 | }
|
|---|
| 317 | return 0;
|
|---|
| 318 | }
|
|---|
| 319 |
|
|---|
| 320 | sub process_commentary {
|
|---|
| 321 | my $self = shift (@_);
|
|---|
| 322 | my ($filename, $issuekey, $dir, $file, $processor) = @_;
|
|---|
| 323 |
|
|---|
| 324 | my $text = $self->get_text ($filename);
|
|---|
| 325 |
|
|---|
| 326 | return 0 unless defined $text;
|
|---|
| 327 |
|
|---|
| 328 | $self->{'commentaries'}->{$issuekey} = 1;
|
|---|
| 329 | my $doc_obj = new doc ($file, "indexed_doc");
|
|---|
| 330 | my $cursection = $doc_obj->get_top_section();
|
|---|
| 331 | $self->associate_cover_images ($doc_obj, $dir, $issuekey);
|
|---|
| 332 | $doc_obj->set_utf8_metadata_element ($cursection, 'Title', "_commentary_");
|
|---|
| 333 | $self->set_main_metadata ($doc_obj, $dir);
|
|---|
| 334 | $doc_obj->set_utf8_metadata_element ($cursection, "doctype", "Commentary");
|
|---|
| 335 | $doc_obj->add_utf8_text ($cursection, $text);
|
|---|
| 336 | $doc_obj->set_OID ($issuekey . "commentary");
|
|---|
| 337 | $processor->process ($doc_obj);
|
|---|
| 338 | return 1;
|
|---|
| 339 | }
|
|---|
| 340 |
|
|---|
| 341 | sub associate_cover_images {
|
|---|
| 342 | my $self = shift (@_);
|
|---|
| 343 | my ($doc_obj, $dir, $issuekey) = @_;
|
|---|
| 344 |
|
|---|
| 345 | my $cover = &util::filename_cat ($dir, $issuekey);
|
|---|
| 346 | $doc_obj->associate_file("${cover}on.gif", "${issuekey}/coveron.gif", "image/gif");
|
|---|
| 347 | $doc_obj->associate_file("${cover}of.gif", "${issuekey}/coverof.gif", "image/gif");
|
|---|
| 348 | }
|
|---|
| 349 |
|
|---|
| 350 | # reads in the meta.txt file and sets metadata
|
|---|
| 351 | sub set_main_metadata {
|
|---|
| 352 | my $self = shift (@_);
|
|---|
| 353 | my ($doc_obj, $dir) = @_;
|
|---|
| 354 |
|
|---|
| 355 | my $metafile = &util::filename_cat ($dir, "meta.txt");
|
|---|
| 356 | return unless (-e $metafile);
|
|---|
| 357 |
|
|---|
| 358 | if (!open (METAFILE, $metafile)) {
|
|---|
| 359 | print STDERR "NPPlug: Couldn't read $metafile\n" if $self->{'verbosity'};
|
|---|
| 360 | return;
|
|---|
| 361 | }
|
|---|
| 362 |
|
|---|
| 363 | my $cursection = $doc_obj->get_top_section();
|
|---|
| 364 | my $line = "";
|
|---|
| 365 | while (defined ($line = <METAFILE>)) {
|
|---|
| 366 | next unless $line =~ /\w/;
|
|---|
| 367 | chomp $line;
|
|---|
| 368 | if ($line =~ /<([^>]*)>(.*)$/) {
|
|---|
| 369 | # note we're using set_metadata_element (not add_metadata_element)
|
|---|
| 370 | # this will override any previously set metadata of the same name
|
|---|
| 371 | $doc_obj->set_utf8_metadata_element ($cursection, $1, $2);
|
|---|
| 372 | } elsif ($self->{'verbosity'}) {
|
|---|
| 373 | print STDERR "NPPlug: Badly formatted line in $metafile\n";
|
|---|
| 374 | print STDERR "meta.txt lines should be formatted '<metaname>metavalue'\n";
|
|---|
| 375 | }
|
|---|
| 376 | }
|
|---|
| 377 | }
|
|---|
| 378 |
|
|---|
| 379 | sub get_text {
|
|---|
| 380 | my $self = shift (@_);
|
|---|
| 381 | my ($filename) = @_;
|
|---|
| 382 |
|
|---|
| 383 | if (open (FILE, $filename)) {
|
|---|
| 384 | my $text = "";
|
|---|
| 385 | my $line = "";
|
|---|
| 386 | if ($filename =~ /\.(htm|commentary|abstract)$/i) {
|
|---|
| 387 | my $savedtext = "";
|
|---|
| 388 | my $foundbody = 0;
|
|---|
| 389 | while (defined ($line = <FILE>)) {
|
|---|
| 390 | if ($line =~ s/.*?<body[^>]*>//i) {
|
|---|
| 391 | $foundbody = 1;
|
|---|
| 392 | }
|
|---|
| 393 | $line =~ s/(<\/?html[^>]*>|<\/?head[^>]*>|<\/p>|<\/?font[^>]*>|<\/?body[^>]*>)//ig;
|
|---|
| 394 | if ($foundbody) {
|
|---|
| 395 | $text .= $line;
|
|---|
| 396 | } else {
|
|---|
| 397 | $savedtext .= $line;
|
|---|
| 398 | }
|
|---|
| 399 | }
|
|---|
| 400 | close FILE;
|
|---|
| 401 | if (!$foundbody) {$text = $savedtext;}
|
|---|
| 402 | if ($filename =~ /\.(commentary|abstract)$/i) {
|
|---|
| 403 | # commentaries and abstracts should already be utf8
|
|---|
| 404 | return $text;
|
|---|
| 405 | } else {
|
|---|
| 406 | # a few extended ascii characters have snuck through
|
|---|
| 407 | # in some text files so we need to convert them to utf8
|
|---|
| 408 | return &unicode::ascii2utf8(\$text);
|
|---|
| 409 | }
|
|---|
| 410 |
|
|---|
| 411 | } else {
|
|---|
| 412 | while (defined ($line = <FILE>)) {
|
|---|
| 413 | $line = "<p>\n" unless $line =~ /\w/;
|
|---|
| 414 | $text .= $line;
|
|---|
| 415 | }
|
|---|
| 416 | close FILE;
|
|---|
| 417 | # a few extended ascii characters have snuck through
|
|---|
| 418 | # in some text files so we need to convert them to utf8
|
|---|
| 419 | return &unicode::ascii2utf8(\$text);
|
|---|
| 420 | }
|
|---|
| 421 |
|
|---|
| 422 | } else {
|
|---|
| 423 | print STDERR "NPPlug: Warning: get_text() couldn't open $filename\n"
|
|---|
| 424 | if $self->{'verbosity'};
|
|---|
| 425 | return undef;
|
|---|
| 426 | }
|
|---|
| 427 | }
|
|---|
| 428 |
|
|---|
| 429 | sub get_title_string {
|
|---|
| 430 | my $self = shift (@_);
|
|---|
| 431 | my ($filename) = @_;
|
|---|
| 432 |
|
|---|
| 433 | $filename =~ s/\.(issue|abstract)$//i;
|
|---|
| 434 | my ($series, $vol, $num) = split /\_/, $filename;
|
|---|
| 435 | my $title = "";
|
|---|
| 436 | $title .= "_vol_ $vol" if defined $vol && $vol =~ /\w/;
|
|---|
| 437 | if (defined $num && $num =~ /\w/) {
|
|---|
| 438 | $title .= ", " if defined $vol && $vol =~ /\w/;
|
|---|
| 439 | $title .= "_num_ $num";
|
|---|
| 440 | }
|
|---|
| 441 | return $title;
|
|---|
| 442 | }
|
|---|
| 443 |
|
|---|
| 444 | 1;
|
|---|
