summaryrefslogtreecommitdiffstats
path: root/tests/Test-iri-list.px
blob: 5e5607217acf59afa3d9b5766efbc9913865707c (plain)
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
#!/usr/bin/env perl

use strict;
use warnings;

use WgetFeature qw(iri);
use HTTPTest;

# cf. http://en.wikipedia.org/wiki/Latin1
#     http://en.wikipedia.org/wiki/ISO-8859-15
###############################################################################
#
# mime : charset found in Content-Type HTTP MIME header
# meta : charset found in Content-Type meta tag
#
# index.html                  mime + file = iso-8859-15
# p1_français.html            meta + file = iso-8859-1, mime = utf-8
# p2_één.html                 meta + file = utf-8, mime =iso-8859-1
#

my $ccedilla_l1 = "\xE7";
my $ccedilla_u8 = "\xC3\xA7";
my $eacute_l1 = "\xE9";
my $eacute_u8 = "\xC3\xA9";

my $urllist = <<EOF;
http://localhost:{{port}}/
http://localhost:{{port}}/p1_fran${ccedilla_l1}ais.html
http://localhost:{{port}}/p2_${eacute_l1}${eacute_l1}n.html
EOF

my $pageindex = <<EOF;
<html>
<head>
  <title>Main Page</title>
</head>
<body>
  <p>
	Main page.
  </p>
</body>
</html>
EOF

my $pagefrancais = <<EOF;
<html>
<head>
  <title>La seule page en français</title>
  <meta http-equiv="Content-Type" content="text/html; charset=ISO-8859-1"/>
</head>
<body>
  <p>
    French page.
  </p>
</body>
</html>
EOF

my $pageeen = <<EOF;
<html>
<head>
  <title>Die enkele nederlandstalige pagina</title>
  <meta http-equiv="Content-Type" content="text/html; charset=UTF-8"/>
</head>
<body>
  <p>
    Dutch page.
  </p>
</body>
</html>
EOF

my $page404 = <<EOF;
<html>
<head>
  <title>404</title>
</head>
<body>
  <p>
    Nop nop nop...
  </p>
</body>
</html>
EOF

# code, msg, headers, content
my %urls = (
    '/index.html' => {
        code => "200",
        msg => "Ok",
        headers => {
            "Content-type" => "text/html; charset=ISO-8859-15",
        },
        content => $pageindex,
    },
    '/robots.txt' => {
        code => "200",
        msg => "Ok",
        headers => {
            "Content-type" => "text/plain",
        },
        content => "",
    },
    '/p1_fran%C3%A7ais.html' => {	# UTF-8 encoded
        code => "404",
        msg => "File not found",
        headers => {
            "Content-type" => "text/html; charset=UTF-8",
        },
        content => $page404,
    },
    '/p1_fran%E7ais.html' => {
        code => "200",
        msg => "Ok",
        headers => {
            "Content-type" => "text/html; charset=UTF-8",
        },
        content => $pagefrancais,
    },
    '/p2_%C3%A9%C3%A9n.html' => {	# UTF-8 encoded
        code => "200",
        msg => "Ok",
        headers => {
            "Content-type" => "text/html; charset=ISO-8859-1",
        },
        content => $pageeen,
    },
    '/p2_%E9%E9n.html' => {
        code => "200",
        msg => "Ok",
        headers => {
            "Content-type" => "text/html; charset=ISO-8859-1",
        },
        content => $pageeen,
    },
    '/url_list.txt' => {
        code => "200",
        msg => "Ok",
        headers => {
            "Content-type" => "text/plain; charset=ISO-8859-1",
        },
        content => $urllist,
    },
);

my $cmdline = $WgetTest::WGETPATH . " --iri --trust-server-names -i http://localhost:{{port}}/url_list.txt";

my $expected_error_code = 0;

my %expected_downloaded_files = (
    'url_list.txt' => {
        content => $urllist,
    },
    'index.html' => {
        content => $pageindex,
    },
    "p1_fran${ccedilla_l1}ais.html" => {
        content => $pagefrancais,
    },
    "p2_${eacute_u8}${eacute_u8}n.html" => {
        content => $pageeen,
    },
);

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

my $the_test = HTTPTest->new (input => \%urls,
                              cmdline => $cmdline,
                              errcode => $expected_error_code,
                              output => \%expected_downloaded_files);
exit $the_test->run();

# vim: et ts=4 sw=4