File: 20-open.t

package info (click to toggle)
libio-html-perl 1.004-3
  • links: PTS, VCS
  • area: main
  • in suites: bookworm, forky, sid, trixie
  • size: 176 kB
  • sloc: perl: 463; makefile: 2; sh: 1
file content (169 lines) | stat: -rw-r--r-- 4,123 bytes parent folder | download | duplicates (2)
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
#! /usr/bin/perl
#---------------------------------------------------------------------
# 20-open.t
# Copyright 2012 Christopher J. Madsen
#
# Actually open files and check the encoding
#---------------------------------------------------------------------

use strict;
use warnings;

use Test::More 0.88;

plan tests => 107;

use IO::HTML;
use File::Temp;
use Scalar::Util 'blessed';

#---------------------------------------------------------------------
sub test
{
  my ($expected, $out, $data, $name, $nextArg) = @_;

  local $Test::Builder::Level = $Test::Builder::Level + 1;

  my $options;
  if (ref $name) {
    $options = $name;
    $name    = $nextArg;
  }

  unless ($name) {
    $name = 'test ' . ($expected || 'cp1252');
  }

  my $tmp = File::Temp->new(UNLINK => 1);
  open(my $mem, '>', \(my $buf)) or die;

  if ($out) {
    $out = ":encoding($out)" unless $out =~ /^:/;
    binmode $tmp, $out;
    binmode $mem, $out;
  }

  print $mem $data;
  print $tmp $data;
  close $mem;
  $tmp->close;

  my ($fh, $encoding, $bom) = IO::HTML::file_and_encoding("$tmp", $options);

  if ($options and $options->{encoding}) {
    ok(blessed($encoding), 'returned an object');

    $encoding = eval { $encoding->name };
  }

  is($encoding, $expected || 'cp1252', $name);

  my $firstLine = <$fh>;
  like($firstLine, qr/^<html/i);

  close $fh;

  $fh = html_file("$tmp", $options);

  is(<$fh>, $firstLine);

  close $fh;

  # Test sniff_encoding:
  undef $mem;
  open($mem, '<', \$buf) or die "Can't open in-memory file: $!";

  delete $options->{encoding} if $options;

  ($encoding, $bom) = IO::HTML::sniff_encoding($mem, undef, $options);

  is($encoding, $expected);

  seek $mem, 0, 0;

  $options->{encoding} = 1;

  ($encoding, $bom) = IO::HTML::sniff_encoding($mem, undef, $options);

  if (defined $expected) {
    ok(blessed($encoding), 'encoding is an object');

    is(eval { $encoding->name }, $expected);
  } else {
    is($encoding, undef);
  }
} # end test

#---------------------------------------------------------------------
test 'utf-8-strict' => '' => <<'';
<html><meta charset="UTF-8">

test 'utf-8-strict' => ':utf8' => <<"";
<html><head><title>Foo\xA0Bar</title>

test undef, latin1 => <<"";
<html><head><title>Foo\xA0Bar</title>

test 'UTF-16BE' => 'UTF-16BE' => <<"";
\x{FeFF}<html><head><title>Foo\xA0Bar</title>

test 'utf-8-strict' => ':utf8' => <<"";
\x{FeFF}<html><meta charset="UTF-16">

test 'utf-8-strict' => ':utf8' => <<"";
<html><meta charset="UTF-16BE">

test 'UTF-16LE' => 'UTF-16LE' => <<"";
\x{FeFF}<html><meta charset="UTF-16">

test 'UTF-16LE' => 'UTF-16LE' => <<"", { encoding => 1 };
\x{FeFF}<html><meta charset="UTF-16">

test 'utf-8-strict' => ':utf8' => <<"", { encoding => 1, need_pragma => 0 };
<html><meta charset="UTF-16BE">

test 'utf-8-strict' => ':utf8' =>
  "<html><title>Foo\xA0Bar" . ("\x{2014}" x 512) . "</title>\n",
  'UTF-8 character crosses boundary';

test 'utf-8-strict' => ':utf8' =>
  "<html><title>Foo Bar" . ("\x{2014}" x 512) . "</title>\n",
  'UTF-8 character crosses boundary 2';

test undef, '', <<'', 'wrong pragma';
<html>
<head>
<meta http-equiv="X-Content-Type" content="text/html; charset=UTF-8" />
<title>Title</title>

test 'utf-8-strict', '', <<'', {need_pragma => 0}, 'need_pragma 0';
<html>
<head>
<meta http-equiv="X-Content-Type" content="text/html; charset=UTF-8" />
<title>Title</title>

test 'iso-8859-15', '', <<"", { encoding => 1, need_pragma => 0 };
<html>
<meta content="text/html; charset=ISO-8859-15">
<meta charset="UTF-16BE">

test 'iso-8859-15', latin1 =>
    '<html>' . (' ' x 985) . qq'<head><meta charset="ISO-8859-15">\n',
    'found with 985 spaces';

test undef, latin1 =>
    '<html>' . (' ' x 986) . qq'<head><meta charset="ISO-8859-15">\n',
    'not found with 986 spaces';

{
  local $IO::HTML::bytes_to_check = 1040;
  test 'iso-8859-15', latin1 =>
      '<html>' . (' ' x 1001) . qq'<head><meta charset="ISO-8859-15">\n',
      'found with 1001 spaces';

  test undef, latin1 =>
      '<html>' . (' ' x 1002) . qq'<head><meta charset="ISO-8859-15">\n',
      'not found with 1002 spaces';
}

done_testing;