wget/tests/Test-iri.px
Tim Rühsen b3f86f90cc Revert "Add . to perl path for all perl tests"
This reverts commit 79be99aff4.

/usr/bin/env 8.28 and below doesn't know -S.
2019-05-30 12:06:01 +02:00

209 lines
5.1 KiB
Perl
Executable File

#!/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
# p3_€€€.html meta + file = utf-8, mime = iso-8859-1
# p4_méér.html mime + file = utf-8
#
my $ccedilla_l15 = "\xE7";
my $ccedilla_u8 = "\xC3\xA7";
my $eacute_l1 = "\xE9";
my $eacute_u8 = "\xC3\xA9";
my $eurosign_l15 = "\xA4";
my $eurosign_u8 = "\xE2\x82\xAC";
my $pageindex = <<EOF;
<html>
<head>
<title>Main Page</title>
</head>
<body>
<p>
Link to page 1 <a href="http://localhost:{{port}}/p1_fran${ccedilla_l15}ais.html">La seule page en fran&ccedil;ais</a>.
Link to page 3 <a href="http://localhost:{{port}}/p3_${eurosign_l15}${eurosign_l15}${eurosign_l15}.html">My tailor is rich</a>.
</p>
</body>
</html>
EOF
# specifying a wrong charset in http-equiv - it will be overridden by Content-Type HTTP header
my $pagefrancais = <<EOF;
<html>
<head>
<title>La seule page en français</title>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8"/>
</head>
<body>
<p>
Link to page 2 <a href="http://localhost:{{port}}/p2_${eacute_l1}${eacute_l1}n.html">Die enkele nerderlangstalige pagina</a>.
</p>
</body>
</html>
EOF
my $pageeen = <<EOF;
<html>
<head>
<title>Die enkele nederlandstalige pagina</title>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8"/>
</head>
<body>
<p>
&Eacute;&eacute;n is niet veel maar toch meer dan nul.<br/>
Nerdelands is een mooie taal... dit zin stuckje spreekt vanzelf, of niet :)<br/>
<a href="http://localhost:{{port}}/p4_m${eacute_u8}${eacute_u8}r.html">M&eacute&eacute;r</a>
</p>
</body>
</html>
EOF
my $pageeuro = <<EOF;
<html>
<head>
<title>Euro page</title>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8"/>
</head>
<body>
<p>
My tailor isn't rich anymore.
</p>
</body>
</html>
EOF
my $pagemeer = <<EOF;
<html>
<head>
<title>Bekende supermarkt</title>
</head>
<body>
<p>
Ik ben toch niet gek !
</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 => "200",
msg => "Ok",
headers => {
# Content-Type header overrides http-equiv Content-Type
"Content-type" => "text/html; charset=ISO-8859-15",
},
content => $pagefrancais,
},
'/p2_%C3%A9%C3%A9n.html' => { # UTF-8 encoded
code => "200",
msg => "Ok",
request_headers => {
"Referer" => qr|http://localhost:[0-9]+/p1_fran%C3%A7ais.html|,
},
headers => {
"Content-type" => "text/html; charset=UTF-8",
},
content => $pageeen,
},
'/p3_%E2%82%AC%E2%82%AC%E2%82%AC.html' => { # UTF-8 encoded
code => "200",
msg => "Ok",
headers => {
"Content-type" => "text/plain; charset=ISO-8859-1",
},
content => $pageeuro,
},
'/p4_m%C3%A9%C3%A9r.html' => {
code => "200",
msg => "Ok",
request_headers => {
"Referer" => qr|http://localhost:[0-9]+/p2_%C3%A9%C3%A9n.html|,
},
headers => {
"Content-type" => "text/plain; charset=UTF-8",
},
content => $pagemeer,
},
);
my $cmdline = $WgetTest::WGETPATH . " --iri --trust-server-names --restrict-file-names=nocontrol -nH -r http://localhost:{{port}}/";
my $expected_error_code = 0;
my %expected_downloaded_files = (
'index.html' => {
content => $pageindex,
},
'robots.txt' => {
content => "",
},
"p1_fran${ccedilla_u8}ais.html" => {
content => $pagefrancais,
},
"p2_${eacute_u8}${eacute_u8}n.html" => {
content => $pageeen,
},
"p3_${eurosign_u8}${eurosign_u8}${eurosign_u8}.html" => {
content => $pageeuro,
},
"p4_m${eacute_u8}${eacute_u8}r.html" => {
content => $pagemeer,
},
);
###############################################################################
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