File: 275_split.t

package info (click to toggle)
gscan2pdf 2.13.5-3
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 5,700 kB
  • sloc: perl: 22,713; xml: 81; makefile: 6
file content (127 lines) | stat: -rw-r--r-- 4,659 bytes parent folder | download
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
use warnings;
use strict;
use File::Basename;    # Split filename into dir, file, ext
use IPC::System::Simple qw(system capture);
use Test::More tests => 8;

BEGIN {
    use Gscan2pdf::Document;
    use Gtk3 -init;    # Could just call init separately
}

#########################

Gscan2pdf::Translation::set_domain('gscan2pdf');
use Log::Log4perl qw(:easy);
Log::Log4perl->easy_init($WARN);
my $logger = Log::Log4perl::get_logger;
Gscan2pdf::Document->setup($logger);

# Create test image
system( Gscan2pdf::Helpers::get_imagemagick_command(), qw(rose: test.gif) );

my $slist = Gscan2pdf::Document->new;

# dir for temporary files
my $dir = File::Temp->newdir;
$slist->set_dir($dir);

$slist->import_files(
    paths             => ['test.gif'],
    finished_callback => sub {
        $slist->{data}[0][2]->import_hocr(<<'EOS');
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
 <head>
  <meta http-equiv="Content-Type" content="text/html;charset=utf-8" />
  <meta name='ocr-system' content='gscan2pdf 2.7.0' />
  <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocr_word'/>
 </head>
 <body>
  <div class='ocr_page' title='bbox 0 0 70 46'>
   <span class='ocr_word' title='bbox 0 0 9 46'>left</span>
   <span class='ocr_word' title='bbox 10 0 45 46'>middle</span>
   <span class='ocr_word' title='bbox 46 0 70 46'>right</span>
  </div>
 </body>
</html>
EOS
        $slist->split_page(
            page              => $slist->{data}[0][2]->{uuid},
            direction         => 'v',
            position          => 35,
            finished_callback => sub {
                is_deeply [ $slist->{data}[0][2]{width},
                    $slist->{data}[0][2]{height} ],
                  [ 35, 46 ],
                  'dimensions 1st page after split';
                my $got = capture( qw(identify -format %g),
                    $slist->{data}[0][2]{filename} );
                chomp($got);
                is $got, "35x46+0+0", 'GIF split correctly';
                is dirname("$slist->{data}[0][2]{filename}"),
                  "$dir", 'using session directory';
                my $expected_hocr = <<"EOS";
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
 <head>
  <meta http-equiv="Content-Type" content="text/html;charset=utf-8" />
  <meta name='ocr-system' content='gscan2pdf $Gscan2pdf::Document::VERSION' />
  <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocr_word'/>
 </head>
 <body>
  <div class='ocr_page' title='bbox 0 0 35 46'>
   <span class='ocr_word' title='bbox 0 0 9 46'>left</span>
   <span class='ocr_word' title='bbox 10 0 35 46'>middle</span>
  </div>
 </body>
</html>
EOS
                is $slist->{data}[0][2]->export_hocr, $expected_hocr,
                  'split hocr';
                is_deeply [ $slist->{data}[1][2]{width},
                    $slist->{data}[1][2]{height} ],
                  [ 35, 46 ],
                  'dimensions 2nd page after split';
                $got = capture( qw(identify -format %g),
                    $slist->{data}[1][2]{filename} );
                chomp($got);
                is $got, "35x46+0+0", 'GIF split correctly 2';
                is dirname("$slist->{data}[1][2]{filename}"),
                  "$dir", 'using session directory 2';
                $expected_hocr = <<"EOS";
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
 <head>
  <meta http-equiv="Content-Type" content="text/html;charset=utf-8" />
  <meta name='ocr-system' content='gscan2pdf $Gscan2pdf::Document::VERSION' />
  <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocr_word'/>
 </head>
 <body>
  <div class='ocr_page' title='bbox 0 0 35 46'>
   <span class='ocr_word' title='bbox 0 0 10 46'>middle</span>
   <span class='ocr_word' title='bbox 11 0 35 46'>right</span>
  </div>
 </body>
</html>
EOS
                is $slist->{data}[1][2]->export_hocr, $expected_hocr,
                  'split hocr 2';
                Gtk3->main_quit;
            }
        );
    }
);
Gtk3->main;

#########################

unlink 'test.gif', <$dir/*>;
rmdir $dir;
Gscan2pdf::Document->quit();