OS/2 Shareware BBS: 5 Edit/05-Edit.zip/txpdf56.zip/contributed/pdfindex/pdfindex

Text File | 2001-11-01 | 6KB | 191 lines

#!/usr/bin/perl
# Require Perl5
#
# pdfindex -- PDFs to index.txt
#
# by SANFACE Software <[e-mail]> 25 February 2001
#
#
# This is version 3.0
#
use strict;
use Getopt::Long;
use File::Basename;
use File::Find;
use File::DosGlob 'glob';
# You can find PDF.pm module at CPAN or at http://www.sanface.com/PDF-lib/
use PDF;

my $version="3.0";
my $producer="pdfindex";
my $configure="pdfindex.cfg";
my $help=0; my $verbose=0;
my $match=""; my $recursive="";
my $companyname="SANFACE Software";
my $pdfindexHome="http://www.sanface.com/pdfindex.html";
my $PDFinfo=""; my $PDFrules=""; my $output=""; my $i;
my $SANFACEmail="mailto:sanface\@sanface.com";
&GetOptions("configure=s"  => \$configure,
            "help"         => \$help,
            "output=s"     => \$output,
            "recursive=s"  => \$recursive,
            "match=s"      => \$match,
            "verbose"      => \$verbose) || usage() ;
my @elem=("tmpdir", "output");
my %option=(tmpdir       => './',
            output       => 'index.txt');
my $elem=""; my $input="";

$help and usage();

open (CNF, "$configure") || die "pdfindex: couldn't open configuration file $configure\n";
while (<CNF>) {
  if(/#\+Begin Variables\+/../#\+End Variables\+/)
    {
    s/\t/ /g;        #replace tabs by space
    next if /^ *\#/; #ignore comment lines
    next if /^ *$/;  #ignore empty lines
    foreach $elem (@elem) {if (/ *$elem *: *(.*)/i) {$option{$elem}=$1;}}
    }
  if(/#\+Begin PDF rules\+/../#\+End PDF rules\+/)
    {
    next if /^ *\#/; #ignore comment lines
    $PDFrules.=$_;
    }
  if(/#\+Begin PDF information\+/../#\+End PDF information\+/)
    {
    next if /^ *\#/; #ignore comment lines
    $PDFinfo.=$_;
    }
  }
close(CNF);

$output and $option{'output'}=$output;

sub wanted {
  if ($File::Find::name=~/$match/) {
    push @ARGV,$File::Find::name;
    }
  }

if ($match && !$recursive) {
   print "You can use -match option only with -recursive option\n";
   exit;
   }

if ($recursive) {
  $match=~s/\./\\./g;
  $match=~s/\*/.*/g;
  $match=~s/\?/./g;
  $match=~s/$/\$/;
  find (\&wanted,"$recursive");
  }

my $tmpfile = $option{'tmpdir'} . "pdfindex$$";

if (@ARGV) {
  my @files;
  if ($^O =~ /^MSWin32$/i && !$recursive) {
    foreach $i (@ARGV) {
      if($i=~/\*|\?/) {push @files,glob($i)}
      else {push @files,$i}
      }
    }
  else {@files = @ARGV}
  open (OUT, ">$option{'output'}") || die "pdfinfo: couldn't open output file $option{'output'}\n";
  foreach $input (@files) {
    my $pdf_file= PDF->new($input);
    if($pdf_file->IsaPDF) {
      my ($dev,$ino,$mode,$nlink,$uid,$gid,$rdev,$size,$atime,$mtime,$ctime,$blksize,$blocks) = stat($input);
      my $title=$pdf_file->GetInfo("Title");
      my $author=$pdf_file->GetInfo("Author");
      my $creationdate=$pdf_file->GetInfo("CreationDate");
      my $moddate=$pdf_file->GetInfo("ModDate");
      my $subject=$pdf_file->GetInfo("Subject");
      my $creator=$pdf_file->GetInfo("Creator");
      my $producer=$pdf_file->GetInfo("Producer");
      my $keywords=$pdf_file->GetInfo("Keywords");
      my $filename=basename($input,"");
      my $PDFinfocopy = $PDFinfo;
      if ($PDFrules =~ /\+title=(.*)\+/) {
        if ($title !~ /$1/) {next}
        }
      if ($PDFrules =~ /\+author=(.*)\+/) {
        if ($author !~ /$1/) {next}
        }
      if ($PDFrules =~ /\+filename=(.*)\+/) {
        if ($filename !~ /$1/) {next}
        }
      $PDFinfocopy =~ s/\+title\+/$title/g;
      $PDFinfocopy =~ s/\+author\+/$author/g;
      $PDFinfocopy =~ s/\+creationdate\+/$creationdate/g;
      $PDFinfocopy =~ s/\+moddate\+/$moddate/g;
      $PDFinfocopy =~ s/\+subject\+/$subject/g;
      $PDFinfocopy =~ s/\+creator\+/$creator/g;
      $PDFinfocopy =~ s/\+producer\+/$producer/g;
      $PDFinfocopy =~ s/\+keywords\+/$keywords/g;
      $PDFinfocopy =~ s/\+filename\+/$filename/g;
      $PDFinfocopy =~ s/\+filepath\+/$input/g;
      $PDFinfocopy =~ s/\+dev\+/$dev/g;
      $PDFinfocopy =~ s/\+ino\+/$ino/g;
      $PDFinfocopy =~ s/\+mode\+/$mode/g;
      $PDFinfocopy =~ s/\+nlink\+/$nlink/g;
      $PDFinfocopy =~ s/\+uid\+/$uid/g;
      $PDFinfocopy =~ s/\+gid\+/$gid/g;
      $PDFinfocopy =~ s/\+rdev\+/$rdev/g;
      $PDFinfocopy =~ s/\+size\+/$size/g;
      $PDFinfocopy =~ s/\+atime\+/$atime/g;
      $PDFinfocopy =~ s/\+mtime\+/$mtime/g;
      $PDFinfocopy =~ s/\+ctime\+/$ctime/g;
      $PDFinfocopy =~ s/\+blksize\+/$blksize/g;
      $PDFinfocopy =~ s/\+blocks\+/$blocks/g;
      print OUT $PDFinfocopy;
      }
    else {print "$input is not a PDF\n"}
    }
  close (OUT)
  &txt2pdf($option{'output'});
  unlink($option{'output'});
  } else {usage();}

sub usage {
    print <<USAGEDESC;

usage:
        pdfindex [-options ...] list

where options include:
    -help                        print out this message
    -configure file              default pdfindex.cfg
    -output    file              default index.txt
    -recursive directory         scan recursively the directory
    -match     files             match different files ex. *.pdf, a?.*
                                 (require -recursive option)
    -verbose                     verbose

list:
    with list you can use metacharacters and relative and absolute path name

example:
    pdfindex *.pdf
    pdfindex -m a*.pdf -r my_directory


If you want to know more about this tool, you might want
to read the docs. They came together with PDFindex!

Home: $pdfindexHome

USAGEDESC
    exit(1);
}



sub txt2pdf {
my @ARGV=shift(@_);

## Put here the txt2pdf perl code

}