1 | #!/usr/bin/perl -w
|
---|
2 |
|
---|
3 |
|
---|
4 | ###########################################################################
|
---|
5 | #
|
---|
6 | # pdfpstoimg.pl -- convert PDF or PS documents to various types of Image format
|
---|
7 | #
|
---|
8 | # A component of the Greenstone digital library software
|
---|
9 | # from the New Zealand Digital Library Project at the
|
---|
10 | # University of Waikato, New Zealand.
|
---|
11 | #
|
---|
12 | # Copyright (C) 2001 New Zealand Digital Library Project
|
---|
13 | #
|
---|
14 | # This program is free software; you can redistribute it and/or modify
|
---|
15 | # it under the terms of the GNU General Public License as published by
|
---|
16 | # the Free Software Foundation; either version 2 of the License, or
|
---|
17 | # (at your option) any later version.
|
---|
18 | #
|
---|
19 | # This program is distributed in the hope that it will be useful,
|
---|
20 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
21 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
22 | # GNU General Public License for more details.
|
---|
23 | #
|
---|
24 | # You should have received a copy of the GNU General Public License
|
---|
25 | # along with this program; if not, write to the Free Software
|
---|
26 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
27 | #
|
---|
28 | ###########################################################################
|
---|
29 | # pdfpstoimg.pl is a wrapper for running the ImageMagick 'convert' utility
|
---|
30 | # which converts PDF and PS documents to various types of image (e.g. PNG,
|
---|
31 | # GIF, JPEG format). We then create an item file to join the images together
|
---|
32 | # into a document. The item file will be processed by PagedImagePlugin
|
---|
33 |
|
---|
34 | BEGIN {
|
---|
35 | die "GSDLHOME not set\n" unless defined $ENV{'GSDLHOME'};
|
---|
36 | unshift (@INC, "$ENV{'GSDLHOME'}/perllib");
|
---|
37 | }
|
---|
38 |
|
---|
39 | use parsargv;
|
---|
40 | use util;
|
---|
41 | use Cwd;
|
---|
42 | use File::Basename;
|
---|
43 |
|
---|
44 | sub print_usage {
|
---|
45 | print STDERR
|
---|
46 | ("pdfpstoimg.pl wrapper for converting PDF or PS files to a series of images.\n",
|
---|
47 | "Usage: pdfpstoimg.pl [options] <PDF/PS-file> <output-filestem>>\n",
|
---|
48 | "Options:\n",
|
---|
49 | "\t-convert_to\toutput image type (gif, jpg, png) \n"
|
---|
50 | );
|
---|
51 | exit (1);
|
---|
52 | }
|
---|
53 |
|
---|
54 | sub main {
|
---|
55 | my (@ARGV) = @_;
|
---|
56 | my ($convert_to);
|
---|
57 |
|
---|
58 | # read command-line arguments so that
|
---|
59 | # you can change the command in this script
|
---|
60 | if (!parsargv::parse(\@ARGV,
|
---|
61 | 'convert_to/.*/^', \$convert_to,
|
---|
62 | )) {
|
---|
63 | print_usage();
|
---|
64 | }
|
---|
65 |
|
---|
66 | # Make sure the user has specified both input and output files
|
---|
67 | if (scalar(@ARGV) != 2) {
|
---|
68 | print_usage();
|
---|
69 | }
|
---|
70 |
|
---|
71 | my $input_filename = $ARGV[0];
|
---|
72 | my $output_filestem = $ARGV[1];
|
---|
73 |
|
---|
74 | # test that the directories exist to create the output file, or
|
---|
75 | # we should exit immediately.
|
---|
76 | &util::mk_dir($output_filestem) if (!-e $output_filestem);
|
---|
77 |
|
---|
78 | my @dir = split (/(\/|\\)/, $input_filename);
|
---|
79 | my $input_basename = pop(@dir);
|
---|
80 | $input_basename =~ s/\.(pdf|ps)$//i;
|
---|
81 | my $dir = join ("", @dir);
|
---|
82 |
|
---|
83 | if (!-r $input_filename) {
|
---|
84 | print STDERR "Error: unable to open $input_filename for reading\n";
|
---|
85 | exit(1);
|
---|
86 | }
|
---|
87 | # don't include path on windows (to avoid having to play about
|
---|
88 | # with quoting when GSDLHOME might contain spaces) but assume
|
---|
89 | # that the PATH is set up correctly.
|
---|
90 | $cmd = "convert";
|
---|
91 |
|
---|
92 | my $output_filename = &util::filename_cat($output_filestem, $input_basename);
|
---|
93 | if ($convert_to eq "gif") {
|
---|
94 | $cmd .= " \"$input_filename\" \"$output_filename-%02d.$convert_to\"";
|
---|
95 | } else {
|
---|
96 | $cmd .= " \"$input_filename\" \"$output_filename.$convert_to\"";
|
---|
97 | }
|
---|
98 |
|
---|
99 | # system() returns -1 if it can't run, otherwise it's $cmds ret val.
|
---|
100 | # note we return 0 if the file is "encrypted"
|
---|
101 | $!=0;
|
---|
102 | if (system($cmd)!=0) {
|
---|
103 | print STDERR "Convert error for $input_filename $!\n";
|
---|
104 | # leave these for gsConvert.pl...
|
---|
105 | #&util::rm("$output_filestem.text") if (-e "$output_filestem.text");
|
---|
106 | #&util::rm("$output_filestem.err") if (-e "$output_filestem.err");
|
---|
107 | return 1;
|
---|
108 | } else {
|
---|
109 | # command execute successfully
|
---|
110 | create_itemfile($output_filestem, $input_basename, $convert_to);
|
---|
111 | }
|
---|
112 | return 0;
|
---|
113 | }
|
---|
114 |
|
---|
115 | sub create_itemfile
|
---|
116 | {
|
---|
117 | my ($output_dir, $convert_basename, $convert_to) = @_;
|
---|
118 | opendir(DIR, $output_dir) || die "can't opendir $output_dir: $!";
|
---|
119 | my $item_file = $output_dir."/".$convert_basename.".item";
|
---|
120 | open(FILE,">$item_file");
|
---|
121 |
|
---|
122 | print FILE "<PagedDocument>\n";
|
---|
123 |
|
---|
124 | my $page_num = "";
|
---|
125 | @dir_files = grep {-f "$output_dir/$_"} readdir(DIR);
|
---|
126 |
|
---|
127 | # Sort files in the directory by page_num
|
---|
128 | sub page_number {
|
---|
129 | my ($dir) = @_;
|
---|
130 | my ($pagenum) =($dir =~ m/^.*[-\.](\d+)(\.(jpg|gif|png))?$/i);
|
---|
131 |
|
---|
132 | $pagenum = 1 unless defined $pagenum;
|
---|
133 | return $pagenum;
|
---|
134 | }
|
---|
135 |
|
---|
136 | # sort the files in the directory in the order of page_num rather than lexically.
|
---|
137 | @dir_files = sort { page_number($a) <=> page_number($b) } @dir_files;
|
---|
138 |
|
---|
139 | foreach my $file (@dir_files){
|
---|
140 | $page_num = page_number($file)+1; # image numbers start at 0, so add 1
|
---|
141 | if ($file !~ /\.item/i){
|
---|
142 | print FILE " <Page pagenum=\"$page_num\" imgfile=\"$file\" txtfile=\"\"/>\n";
|
---|
143 | }
|
---|
144 | }
|
---|
145 |
|
---|
146 | print FILE "</PagedDocument>\n";
|
---|
147 | closedir DIR;
|
---|
148 | return "";
|
---|
149 | }
|
---|
150 |
|
---|
151 | # indicate our error status, 0 = success
|
---|
152 | exit (&main(@ARGV));
|
---|
153 |
|
---|
154 |
|
---|
155 |
|
---|