This file is indexed.

/usr/bin/extractallimages is in libcam-pdf-perl 1.60-3.

This file is owned by root:root, with mode 0o755.

The actual contents of the file can be viewed below.

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
#!/usr/bin/perl -w

package main;

use warnings;
use strict;
use CAM::PDF;
use Getopt::Long;
use Pod::Usage;

our $VERSION = '1.60';

my %opts = (
            template   => '/usr/share/libcam-pdf-perl/crunchjpg_tmpl.pdf',

            verbose    => 0,
            help       => 0,
            version    => 0,
            skip       => {},
            only       => {},

            # Temporary values:
            onlyval    => [],
            skipval    => [],
            );

Getopt::Long::Configure('bundling');
GetOptions('S|skip=s'     => \@{$opts{skipval}},
           'O|only=s'     => \@{$opts{onlyval}},
           'v|verbose'  => \$opts{verbose},
           'h|help'     => \$opts{help},
           'V|version'  => \$opts{version},
           ) or pod2usage(1);
if ($opts{help})
{
   pod2usage(-exitstatus => 0, -verbose => 2);
}
if ($opts{version})
{
   print "CAM::PDF v$CAM::PDF::VERSION\n";
   exit 0;
}

foreach my $flag (qw( skip only ))
{
   foreach my $val (@{$opts{$flag.'val'}})
   {
      foreach my $key (split /\D+/xms, $val)
      {
         $opts{$flag}->{$key} = 1;
      }
   }
}
if (!-f $opts{template})
{
   die "Cannot find the template pdf called $opts{template}\n";
}

if (@ARGV < 2)
{
   pod2usage(1);
}

my $infile = shift;
my $outdir = shift;

my $doc = CAM::PDF->new($infile) || die "$CAM::PDF::errstr\n";

my $nimages = 0;
my $rimages = 0;
my %doneobjs;

foreach my $objnum (keys %{$doc->{xref}})
{
   my $xobj = $doc->dereference($objnum);
   if ($xobj->{value}->{type} eq 'dictionary')
   {
      my $im = $xobj->{value}->{value};
      if (exists $im->{Type} && $doc->getValue($im->{Type}) eq 'XObject' &&
          exists $im->{Subtype} && $doc->getValue($im->{Subtype}) eq 'Image')
      {
         my $ref = '(no name)';
         if ($im->{Name})
         {
            $ref = $doc->getValue($im->{Name});
         }
         my $w = $im->{Width} || $im->{W} || 0;
         if ($w)
         {
            $w = $doc->getValue($w);
         }
         my $h = $im->{Height} || $im->{H} || 0;
         if ($h)
         {
            $h = $doc->getValue($h);
         }

         next if (exists $doneobjs{$objnum});

         $nimages++;
         _inform("Image $nimages, $ref = object $objnum, (w,h)=($w,$h)", $opts{verbose});

         if (exists $opts{skip}->{$objnum} ||
             (0 < scalar keys %{$opts{only}} && !exists $opts{only}->{$objnum}))
         {
            _inform("Skipping object $objnum", $opts{verbose});
            next;
         }

         my $isjpg = _isjpg($im);

         my $oldsize = $doc->getValue($im->{Length});
         if (!$oldsize)
         {
            die "PDF error: Failed to get size of image\n";
         }

         my $tmpl = CAM::PDF->new($opts{template}) || die "$CAM::PDF::errstr\n";

         # Get a handle on the needed data bits from the template
         my $media_array = $tmpl->getValue($tmpl->getPage(1)->{MediaBox});
         my $rawpage = $tmpl->getPageContent(1);

         $media_array->[2]->{value} = $w;
         $media_array->[3]->{value} = $h;
         my $page = $rawpage;
         $page =~ s/xxx/$w/igxms;
         $page =~ s/yyy/$h/igxms;
         $tmpl->setPageContent(1, $page);
         $tmpl->replaceObject(9, $doc, $objnum, 1);

         my $ofile = "/tmp/crunchjpg.$$";
         $tmpl->cleanoutput($ofile);

         if (!-d $outdir)
         {
            require File::Path;
            File::Path::mkpath($outdir);
         }
         if ($isjpg)
         {
            my $result = `convert -quality 50 -density 72x72 -page ${w}x$h pdf:$ofile jpg:$outdir/$objnum.jpg`;  ## no critic (Backtick)
            _inform($result, $opts{verbose});
         }
         else
         {
            my $result = `convert -density 72x72 -page ${w}x$h pdf:$ofile gif:$outdir/$objnum.gif`;  ## no critic (Backtick)
            _inform($result, $opts{verbose});
         }

         $doneobjs{$objnum} = 1;
         $rimages++;
      }
   }
}

_inform("Extracted $rimages of $nimages images", $opts{verbose});


sub _isjpg
{
   my $im = shift;
   return if (!$im->{Filter});

   my $f = $im->{Filter};
   my @names = $f->{type} eq 'array' ? @{$f->{value}} : $f;
   for my $e (@names)
   {
      my $name = $doc->getValue($e);
      if (ref $name)
      {
         $name = $name->{value};
      }
      #warn "Checking $name\n";
      if ($name eq 'DCTDecode')
      {
         return 1;
      }
   }
   return;
}

sub _inform
{
   my $str     = shift;
   my $verbose = shift;

   if ($verbose)
   {
      print STDERR $str, "\n";
   }
   return;
}

__END__


=for stopwords extractallimages.pl ImageMagick

=head1 NAME

extractallimages.pl - Save copies of all PDF images to a directory

=head1 SYNOPSIS

 extractallimages.pl [options] infile.pdf outdirectory

 Options:
   -O --only=imnum     only output the specified images (can be used multiple times)
   -S --skip=imnum     don't output the specified images (can be used multiple times)
   -v --verbose        print diagnostic messages
   -h --help           verbose help message
   -V --version        print CAM::PDF version

C<imnum> is a comma-separated list of integers indicating the images
in order that they appear in the PDF.  Use F<listimages.pl> to retrieve
the image numbers.

=head1 DESCRIPTION

Requires the ImageMagick B<convert> program to be available

Searches the PDF for images and saves them as individual files in the
specified directory.  The files are named C<E<lt>imnumE<gt>.jpg> or C<E<lt>imnumE<gt>.gif>.

=head1 SEE ALSO

CAM::PDF

F<crunchjpgs.pl>

F<listimages.pl>

F<extractjpgs.pl>

F<uninlinepdfimages.pl>

=head1 AUTHOR

See L<CAM::PDF>

=cut