[1445] | 1 | #!/usr/bin/perl -w
|
---|
| 2 |
|
---|
| 3 | ###########################################################################
|
---|
| 4 | #
|
---|
| 5 | # gsConvert.pl -- convert documents to HTML ot TEXT format
|
---|
| 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 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 | # gsConvert.pl converts documents in a range of formats to HTML or TEXT
|
---|
| 30 | # by exploiting third-party programs. These are usually found in the
|
---|
| 31 | # $GSDLHOME/packages directory.
|
---|
| 32 | #
|
---|
| 33 | # Currently, we can convert Microsoft Word and Adobe PDF using specialised
|
---|
| 34 | # conversion utilities. We can convery any file to text with a perl
|
---|
| 35 | # implementation of the UNIX strings command.
|
---|
| 36 |
|
---|
| 37 |
|
---|
| 38 | BEGIN {
|
---|
| 39 | die "GSDLHOME not set\n" unless defined $ENV{'GSDLHOME'};
|
---|
| 40 | unshift (@INC, "$ENV{'GSDLHOME'}/perllib");
|
---|
| 41 | }
|
---|
| 42 |
|
---|
| 43 | use parsargv;
|
---|
| 44 | use util;
|
---|
| 45 | use Cwd;
|
---|
| 46 | use File::Basename;
|
---|
| 47 |
|
---|
| 48 |
|
---|
| 49 | sub print_usage
|
---|
| 50 | {
|
---|
| 51 | print STDERR "Usage: $0 [-type doc|pdf] [-output html|text] filename\n";
|
---|
| 52 | exit(1);
|
---|
| 53 | }
|
---|
| 54 |
|
---|
| 55 |
|
---|
| 56 | sub main
|
---|
| 57 | {
|
---|
| 58 | my (@ARGV) = @_;
|
---|
| 59 | my ($input_type,$output_type,$verbose);
|
---|
| 60 |
|
---|
| 61 | # read command-line arguments
|
---|
| 62 | if (!parsargv::parse(\@ARGV,
|
---|
| 63 | 'type/(doc|pdf)/', \$input_type,
|
---|
| 64 | 'output/(html|text)/', \$output_type,
|
---|
| 65 | 'verbose/\d+/0', \$verbose))
|
---|
| 66 | {
|
---|
| 67 | print_usage();
|
---|
| 68 | }
|
---|
| 69 |
|
---|
| 70 | # Make sure the input file exists and can be opened for reading
|
---|
| 71 | if (scalar(@ARGV!=1)) {
|
---|
| 72 | print_usage();
|
---|
| 73 | }
|
---|
| 74 | my $input_filename = $ARGV[0];
|
---|
| 75 | if (!-r $input_filename) {
|
---|
| 76 | print STDERR "Error: unable to open $input_filename for reading\n";
|
---|
| 77 | exit(1);
|
---|
| 78 | }
|
---|
| 79 |
|
---|
| 80 | # Deduce filenames
|
---|
| 81 | my ($tailname,$dirname,$suffix)
|
---|
| 82 | = File::Basename::fileparse($input_filename,'\..+');
|
---|
| 83 | my $output_filestem = &util::filename_cat($dirname,"$tailname");
|
---|
| 84 |
|
---|
| 85 | if ($input_type eq "")
|
---|
| 86 | {
|
---|
| 87 | $input_type = substr($suffix,1,length($suffix)-1);
|
---|
| 88 | }
|
---|
| 89 |
|
---|
| 90 | # Change to temporary working directory
|
---|
| 91 | my $stored_dir = cwd();
|
---|
| 92 | chdir ($dirname) || die "Unable to change to directory $dirname";
|
---|
| 93 |
|
---|
| 94 | # Select convert utility
|
---|
| 95 | if (!defined $input_type) {
|
---|
| 96 | print STDERR "Error: No filename extension or input type defined\n";
|
---|
| 97 | exit(1);
|
---|
| 98 | }
|
---|
| 99 | elsif ($input_type eq "doc") {
|
---|
| 100 | print &convertDOC($input_filename, $output_filestem, $output_type);
|
---|
| 101 | print "\n";
|
---|
| 102 | }
|
---|
| 103 | elsif ($input_type eq "pdf") {
|
---|
| 104 | print &convertPDF($dirname, $input_filename, $output_filestem, $output_type);
|
---|
| 105 | print "\n";
|
---|
| 106 | }
|
---|
| 107 | elsif ($input_type eq "ps") {
|
---|
| 108 | print &convertPS($input_filename, $output_filestem, $output_type);
|
---|
| 109 | print "\n";
|
---|
| 110 | }
|
---|
| 111 | else {
|
---|
| 112 | print STDERR "Error: Unable to convert type '$input_type'\n";
|
---|
| 113 | exit(1);
|
---|
| 114 | }
|
---|
| 115 |
|
---|
| 116 | # restore to original working directory
|
---|
| 117 | chdir ($stored_dir) || die "Unable to return to directory $stored_dir";
|
---|
| 118 |
|
---|
| 119 | }
|
---|
| 120 |
|
---|
| 121 | &main(@ARGV);
|
---|
| 122 |
|
---|
| 123 |
|
---|
| 124 |
|
---|
| 125 | # Document-type conversion fucntions
|
---|
| 126 | #
|
---|
| 127 | # The following functions attempt to convert documents from their
|
---|
| 128 | # input type to the specified output type. If no output type was
|
---|
| 129 | # given, then they first attempt HTML, and then TEXT.
|
---|
| 130 | #
|
---|
| 131 | # Each returns the output type ("html" or "text") or "fail" if no
|
---|
| 132 | # conversion is possible.
|
---|
| 133 |
|
---|
| 134 | # Convert a Microsoft word document
|
---|
| 135 |
|
---|
| 136 | sub convertDOC {
|
---|
| 137 | ($input_filename, $output_filestem, $output_type) = @_;
|
---|
| 138 |
|
---|
[1654] | 139 | # Many .doc files are not in fact word documents!
|
---|
| 140 | my $realtype = &find_docfile_type($input_filename);
|
---|
| 141 |
|
---|
| 142 | if ($realtype eq "word678") {
|
---|
| 143 | return &convertWord678($input_filename, $output_filestem, $output_type);
|
---|
| 144 | } elsif ($realtype eq "rtf") {
|
---|
| 145 | return &convertRTF($input_filename, $output_filestem, $output_type);
|
---|
| 146 | } else {
|
---|
| 147 | return &convertAnything($input_filename, $output_filestem, $output_type);
|
---|
| 148 | }
|
---|
| 149 | }
|
---|
| 150 |
|
---|
| 151 | # Convert a Microsoft word 6/7/8 document
|
---|
| 152 |
|
---|
| 153 | sub convertWord678 {
|
---|
| 154 | ($input_filename, $output_filestem, $output_type) = @_;
|
---|
| 155 |
|
---|
[1445] | 156 | my $success = 0;
|
---|
| 157 |
|
---|
| 158 | # Attempt specialised conversion to HTML
|
---|
| 159 | if (!$output_type || ($output_type =~ /html/i)) {
|
---|
| 160 | $success = &doc_to_html($input_filename, $output_filestem);
|
---|
| 161 | if ($success) {
|
---|
| 162 | return "html";
|
---|
| 163 | }
|
---|
| 164 | }
|
---|
| 165 |
|
---|
[1654] | 166 | return &convertAnything($input_filename, $output_filestem, $output_type);
|
---|
| 167 | }
|
---|
| 168 |
|
---|
| 169 |
|
---|
| 170 | # Convert a Rich Text Format (RTF) file
|
---|
| 171 |
|
---|
| 172 | sub convertRTF {
|
---|
| 173 | ($input_filename, $output_filestem, $output_type) = @_;
|
---|
| 174 |
|
---|
| 175 | my $success = 0;
|
---|
| 176 |
|
---|
| 177 | # Attempt specialised conversion to HTML
|
---|
| 178 | if (!$output_type || ($output_type =~ /html/i)) {
|
---|
| 179 | $success = &rtf_to_html($input_filename, $output_filestem);
|
---|
| 180 | if ($success) {
|
---|
| 181 | return "html";
|
---|
| 182 | }
|
---|
| 183 | }
|
---|
| 184 |
|
---|
| 185 | return &convertAnything($input_filename, $output_filestem, $output_type);
|
---|
| 186 | }
|
---|
| 187 |
|
---|
| 188 |
|
---|
| 189 | # Convert an unidentified file
|
---|
| 190 |
|
---|
| 191 | sub convertAnything {
|
---|
| 192 | ($input_filename, $output_filestem, $output_type) = @_;
|
---|
| 193 |
|
---|
| 194 | my $success = 0;
|
---|
| 195 |
|
---|
[1445] | 196 | # Attempt simple conversion to HTML
|
---|
| 197 | if (!$output_type || ($output_type =~ /html/i)) {
|
---|
| 198 | $success = &any_to_html($input_filename, $output_filestem);
|
---|
| 199 | if ($success) {
|
---|
| 200 | return "html";
|
---|
| 201 | }
|
---|
| 202 | }
|
---|
| 203 |
|
---|
| 204 | # Convert to text
|
---|
| 205 | if (!$output_type || ($output_type =~ /text/i)) {
|
---|
| 206 | $success = any_to_text($input_filename, $output_filestem);
|
---|
| 207 | if ($success) {
|
---|
| 208 | return "text";
|
---|
| 209 | }
|
---|
| 210 | }
|
---|
| 211 | return "fail";
|
---|
| 212 | }
|
---|
| 213 |
|
---|
| 214 |
|
---|
[1654] | 215 |
|
---|
[1445] | 216 | # Convert an Adobe PDF document
|
---|
| 217 |
|
---|
| 218 | sub convertPDF {
|
---|
| 219 | ($dirname, $input_filename, $output_filestem, $output_type) = @_;
|
---|
| 220 |
|
---|
| 221 | my $success = 0;
|
---|
| 222 |
|
---|
| 223 | # Attempt conversion to HTML
|
---|
| 224 | if (!$output_type || ($output_type =~ /html/i)) {
|
---|
| 225 | $success = &pdf_to_html($dirname, $input_filename, $output_filestem);
|
---|
| 226 | if ($success) {
|
---|
| 227 | return "html";
|
---|
| 228 | }
|
---|
| 229 | }
|
---|
| 230 |
|
---|
| 231 | # Attempt conversion to TEXT
|
---|
| 232 | if (!$output_type || ($output_type =~ /text/i)) {
|
---|
| 233 | $success = &pdf_to_text($input_filename, $output_filestem);
|
---|
| 234 | if ($success) {
|
---|
| 235 | return "text";
|
---|
| 236 | }
|
---|
| 237 | }
|
---|
| 238 |
|
---|
| 239 | return "fail";
|
---|
| 240 |
|
---|
| 241 | }
|
---|
| 242 |
|
---|
| 243 |
|
---|
| 244 | # Convert an Adobe PostScript document
|
---|
| 245 |
|
---|
| 246 | sub convertPS {
|
---|
| 247 | ($input_filename, $output_filestem, $output_type) = @_;
|
---|
| 248 |
|
---|
| 249 | my $success = 0;
|
---|
| 250 |
|
---|
| 251 | # Attempt conversion to TEXT
|
---|
| 252 | if (!$output_type || ($output_type =~ /text/i)) {
|
---|
| 253 | $success = &ps_to_text($input_filename, $output_filestem);
|
---|
| 254 | if ($success) {
|
---|
| 255 | return "text";
|
---|
| 256 | }
|
---|
| 257 | }
|
---|
| 258 |
|
---|
| 259 | return "fail";
|
---|
| 260 |
|
---|
| 261 | }
|
---|
| 262 |
|
---|
| 263 |
|
---|
[1654] | 264 | # Find the real type of a .doc file
|
---|
| 265 | #
|
---|
| 266 | # We seem to have alot of files with a .dco extension that are .rtf
|
---|
| 267 | # files or Word 5 files. This function attempts to tell the difference.
|
---|
[1445] | 268 |
|
---|
[1654] | 269 | sub find_docfile_type {
|
---|
| 270 | ($input_filename) = @_;
|
---|
| 271 |
|
---|
| 272 | open(CHK, "<$input_filename");
|
---|
| 273 | my $line = "";
|
---|
| 274 | my $first = 1;
|
---|
| 275 |
|
---|
| 276 | while (<CHK>) {
|
---|
| 277 |
|
---|
| 278 | $line = $_;
|
---|
| 279 |
|
---|
| 280 | if ($first) {
|
---|
| 281 | # check to see if this is an rtf file
|
---|
| 282 | if ($line =~ /^\{\\rtf/) {
|
---|
| 283 | close(CHK);
|
---|
| 284 | return "rtf";
|
---|
| 285 | }
|
---|
| 286 | }
|
---|
| 287 |
|
---|
| 288 | # is theis a word 6/7/8 document?
|
---|
| 289 | if ($line =~ /Word\.Document\.[678]/) {
|
---|
| 290 | close(CHK);
|
---|
| 291 | return "word678";
|
---|
| 292 | }
|
---|
| 293 |
|
---|
| 294 | $first = 0;
|
---|
| 295 |
|
---|
| 296 | }
|
---|
| 297 |
|
---|
| 298 | return "unknown";
|
---|
| 299 | }
|
---|
| 300 |
|
---|
| 301 |
|
---|
| 302 |
|
---|
[1445] | 303 | # Specific type-to-type cponversions
|
---|
| 304 | #
|
---|
| 305 | # Each of the following functions attempts to convert a document from
|
---|
| 306 | # a specific format to another. If they succeed yhey return 1 and leave
|
---|
| 307 | # the output document(s) in the appropriate place; if they fail they
|
---|
| 308 | # return 0 and delete any working files.
|
---|
| 309 |
|
---|
| 310 |
|
---|
| 311 | # Attempt to convert a word document to html with the wv program
|
---|
| 312 |
|
---|
| 313 | sub doc_to_html {
|
---|
| 314 | ($input_filename, $output_filestem) = @_;
|
---|
| 315 |
|
---|
| 316 | # formulate the command
|
---|
[1578] | 317 | my $wv_home = &util::filename_cat($ENV{'GSDLHOME'}, "packages", "unix", "wv");
|
---|
| 318 | my $wv_conf = &util::filename_cat($wv_home, "lib", "wv", "wvHtml.xml");
|
---|
| 319 | my $wvWare = &util::filename_cat($wv_home, "bin", "wvWare");
|
---|
| 320 | return 0 unless (-e "$wvWare");
|
---|
[1654] | 321 | $cmd = "ulimit -t 20;";
|
---|
| 322 | $cmd .= "$wvWare --charset utf-8 --config $wv_conf";
|
---|
[1578] | 323 | $cmd .= " \"$input_filename\" > \"$output_filestem.html\" 2>\"$output_filestem.err\"";
|
---|
[1654] | 324 |
|
---|
[1445] | 325 | # execute the command
|
---|
| 326 | if (system($cmd)>0)
|
---|
| 327 | {
|
---|
[1578] | 328 | print STDERR "Error executing wv converter: $!. Continuing...\n";
|
---|
[1445] | 329 | }
|
---|
[1578] | 330 |
|
---|
[1445] | 331 | # Was the conversion successful?
|
---|
| 332 | if (-e "$output_filestem.html") {
|
---|
| 333 | open(TMP, "$output_filestem.html");
|
---|
| 334 | $line = <TMP>;
|
---|
| 335 | close(TMP);
|
---|
[1578] | 336 | if ($line && $line =~ /DOCTYPE HTML/) {
|
---|
[1445] | 337 | &util::rm("$output_filestem.err");
|
---|
| 338 | return 1;
|
---|
| 339 | } else {
|
---|
| 340 | # An error of some sort occurred
|
---|
| 341 | &util::rm("$output_filestem.html");
|
---|
| 342 | &util::rm("$output_filestem.err");
|
---|
| 343 | }
|
---|
| 344 | }
|
---|
| 345 | return 0;
|
---|
| 346 | }
|
---|
| 347 |
|
---|
| 348 |
|
---|
[1654] | 349 | # Attempt to convert an RTF document to html with rtftohtml
|
---|
| 350 | #
|
---|
| 351 | # rtf2html isn't distributed with Greenstone because it is not
|
---|
| 352 | # distributed under teh GPL. If you know of a better solution,
|
---|
| 353 | # please let me know.
|
---|
| 354 |
|
---|
| 355 | sub rtf_to_html {
|
---|
| 356 | ($input_filename, $output_filestem) = @_;
|
---|
| 357 |
|
---|
| 358 | # formulate the command
|
---|
| 359 | my $r_cmd = &util::filename_cat($ENV{'GSDLHOME'}, "packages", "unix",
|
---|
| 360 | "rtf2html", "rtf2html", "rtf2html");
|
---|
| 361 | $r_cmd = "rtf2html" unless (-e "$r_cmd");
|
---|
| 362 | return 0 unless (-e "$r_cmd");
|
---|
| 363 | $cmd = "ulimit -t 20;";
|
---|
| 364 | $cmd .= "$r_cmd";
|
---|
| 365 | $cmd .= " \"$input_filename\" > \"$output_filestem.html\" 2>\"$output_filestem.err\"";
|
---|
| 366 |
|
---|
| 367 | # execute the command
|
---|
| 368 | if (system($cmd)>0)
|
---|
| 369 | {
|
---|
| 370 | print STDERR "Error executing rtf converter: $!. Continuing...\n";
|
---|
| 371 | }
|
---|
| 372 |
|
---|
| 373 | # Was the conversion successful?
|
---|
| 374 | if (-e "$output_filestem.html") {
|
---|
| 375 | open(TMP, "$output_filestem.html");
|
---|
| 376 | $line = <TMP>;
|
---|
| 377 | close(TMP);
|
---|
| 378 | if ($line && $line =~ /DOCTYPE HTML/) {
|
---|
| 379 | &util::rm("$output_filestem.err");
|
---|
| 380 | return 1;
|
---|
| 381 | } else {
|
---|
| 382 | # An error of some sort occurred
|
---|
| 383 | &util::rm("$output_filestem.html");
|
---|
| 384 | &util::rm("$output_filestem.err");
|
---|
| 385 | }
|
---|
| 386 | }
|
---|
| 387 | return 0;
|
---|
| 388 | }
|
---|
| 389 |
|
---|
| 390 |
|
---|
[1445] | 391 | # Convert a pdf file to html with the pdftohtml command
|
---|
| 392 |
|
---|
| 393 | sub pdf_to_html {
|
---|
| 394 | ($dirname, $input_filename, $output_filestem) = @_;
|
---|
| 395 |
|
---|
| 396 | $cmd = "pdftohtml -F -d $dirname -o \"$output_filestem.html\" \"$input_filename\"";
|
---|
| 397 | $cmd .= " > $output_filestem.out";
|
---|
| 398 |
|
---|
| 399 | if (system($cmd)>0)
|
---|
| 400 | {
|
---|
| 401 | print STDERR "Error executing $cmd: $!\n";
|
---|
| 402 | &util::rm("$output_filestem.html") if (-e "$output_filestem.html");
|
---|
| 403 | &util::rm("$output_filestem.out") if (-e "$output_filestem.out");
|
---|
| 404 | return 0;
|
---|
| 405 | }
|
---|
| 406 |
|
---|
| 407 | &util::rm("$output_filestem.out") if (-e "$output_filestem.out");
|
---|
| 408 | return 1;
|
---|
| 409 | }
|
---|
| 410 |
|
---|
| 411 |
|
---|
| 412 | # Convert a PDF file to text with the pdftotext command
|
---|
| 413 |
|
---|
| 414 | sub pdf_to_text {
|
---|
| 415 | ($dirname, $input_filename, $output_filestem) = @_;
|
---|
| 416 |
|
---|
| 417 | $cmd = "pdftotext \"$input_filename\" > \"$output_filestem.text\"";
|
---|
| 418 | $cmd .= " 2> $output_filestem.err";
|
---|
| 419 |
|
---|
| 420 | if (system($cmd)>0)
|
---|
| 421 | {
|
---|
| 422 | print STDERR "Error executing $cmd: $!\n";
|
---|
| 423 | &util::rm("$output_filestem.text") if (-e "$output_filestem.text");
|
---|
| 424 | &util::rm("$output_filestem.err") if (-e "$output_filestem.err");
|
---|
| 425 | return 0;
|
---|
| 426 | }
|
---|
| 427 |
|
---|
| 428 | &util::rm("$output_filestem.err") if (-e "$output_filestem.err");
|
---|
| 429 | return 1;
|
---|
| 430 | }
|
---|
| 431 |
|
---|
| 432 |
|
---|
| 433 | # Convert a PostScript document to text with ps2ascii
|
---|
| 434 |
|
---|
| 435 | sub ps_to_text {
|
---|
| 436 | ($input_filename, $output_filestem) = @_;
|
---|
| 437 |
|
---|
| 438 | my $cmd = "ps2ascii \"$input_filename\" > \"$output_filestem.text\"";
|
---|
| 439 | $cmd .= " 2> $output_filestem.err";
|
---|
| 440 |
|
---|
| 441 | if (system($cmd)>0)
|
---|
| 442 | {
|
---|
| 443 | print STDERR "Error executing $cmd: $!\n";
|
---|
| 444 | &util::rm("$output_filestem.text") if (-e "$output_filestem.text");
|
---|
| 445 | &util::rm("$output_filestem.err") if (-e "$output_filestem.err");
|
---|
| 446 | return 0;
|
---|
| 447 | }
|
---|
| 448 |
|
---|
| 449 | &util::rm("$output_filestem.err") if (-e "$output_filestem.err");
|
---|
| 450 | return 1;
|
---|
| 451 | }
|
---|
| 452 |
|
---|
| 453 |
|
---|
| 454 | # Convert any file to HTML with a crude perl implementation of the
|
---|
| 455 | # UNIX strings command.
|
---|
| 456 |
|
---|
| 457 | sub any_to_html {
|
---|
| 458 | ($input_filename, $output_filestem) = @_;
|
---|
| 459 |
|
---|
| 460 | # First generate a text file
|
---|
| 461 | return 0 unless (&any_to_text($input_filename, $output_filestem));
|
---|
| 462 |
|
---|
| 463 | # create an HTML file from the text file
|
---|
| 464 | open(TEXT, "<$output_filestem.text");
|
---|
| 465 | open(HTML, ">$output_filestem.html");
|
---|
| 466 |
|
---|
| 467 | print HTML '<html><head>
|
---|
| 468 | <META HTTP-EQUIV="Content-Type" CONTENT="text/html">
|
---|
[1578] | 469 | <META NAME="GENERATOR" CONTENT="Greenstone any_to_html">
|
---|
[1445] | 470 | </head><body>\n\n';
|
---|
| 471 | while (<TEXT>) {
|
---|
| 472 | print HTML "<p> ", $_;
|
---|
| 473 |
|
---|
| 474 | }
|
---|
| 475 | print HTML "\n</body></html>]\n";
|
---|
| 476 |
|
---|
| 477 | &util::rm("$output_filestem.text") if (-e "$output_filestem.text");
|
---|
| 478 | return 1;
|
---|
| 479 | }
|
---|
| 480 |
|
---|
| 481 | # Convert any file to TEXT with a crude perl implementation of the
|
---|
| 482 | # UNIX strings command.
|
---|
| 483 |
|
---|
| 484 | sub any_to_text {
|
---|
| 485 | ($input_filename, $output_filestem) = @_;
|
---|
| 486 |
|
---|
| 487 | open(IN, "<$input_filename");
|
---|
| 488 | open(OUT, ">$output_filestem.text");
|
---|
| 489 |
|
---|
| 490 | my ($line);
|
---|
| 491 | while (<IN>) {
|
---|
| 492 | $line = $_;
|
---|
[1578] | 493 |
|
---|
[1445] | 494 | # delete anything that isn't a printable character
|
---|
| 495 | $line =~ s/[^\040-\176]+/\n/sg;
|
---|
| 496 |
|
---|
| 497 | # delete any string less than 10 characters long
|
---|
[1578] | 498 | $line =~ s/^[^\n]{0,9}$/\n/mg;
|
---|
[1445] | 499 | while ($line =~ /^[^\n]{1,9}$/m) {
|
---|
| 500 | $line =~ s/^[^\n]{0,9}$/\n/mg;
|
---|
| 501 | $line =~ s/\n+/\n/sg;
|
---|
| 502 | }
|
---|
| 503 |
|
---|
| 504 | # remove extraneous whitespace
|
---|
| 505 | $line =~ s/\n+/\n/gs;
|
---|
| 506 | $line =~ s/^\n//gs;
|
---|
[1578] | 507 |
|
---|
[1445] | 508 | # output whatever is left
|
---|
[1578] | 509 | if ($line =~ /[^\n ]/) {
|
---|
[1445] | 510 | print OUT $line;
|
---|
| 511 | }
|
---|
| 512 | }
|
---|
| 513 | return 1;
|
---|
| 514 | }
|
---|
| 515 |
|
---|
| 516 |
|
---|
| 517 |
|
---|