1#!/usr/bin/perl
2
3use strict;
4use warnings;
5
6use HTTPTest;
7
8# This program tests that --restrict-file-names=ascii can be used to
9# ensure that all high-valued bytes are escaped. The sample filename was
10# chosen because in former versions of Wget, one could either choose not
11# to escape any portion of the UTF-8 filename via
12# --restrict-file-names=nocontrol (which would only be helpful if one
13# was _on_ a UTF-8 system), or else Wget would escape _portions_ of
14# characters, leaving irrelevant "latin1"-looking characters combined
15# with percent-encoded "control" characters, instead of encoding all the
16# bytes of an entire non-ASCII UTF-8 character.
17
18###############################################################################
19
20# "gnosis" in UTF-8 greek.
21my $gnosis = '%CE%B3%CE%BD%CF%89%CF%83%CE%B9%CF%82';
22
23my $mainpage = <<EOF;
24<html>
25<head>
26  <title>Some Page Title</title>
27</head>
28<body>
29  <p>
30    Some text...
31  </p>
32</body>
33</html>
34EOF
35
36# code, msg, headers, content
37my %urls = (
38    "/$gnosis.html" => {
39        code => "200",
40        msg => "Dontcare",
41        headers => {
42            "Content-type" => "text/html",
43        },
44        content => $mainpage,
45    },
46);
47
48my $cmdline = $WgetTest::WGETPATH . " --restrict-file-names=ascii "
49    . "http://localhost:{{port}}/${gnosis}.html";
50
51my $expected_error_code = 0;
52
53my %expected_downloaded_files = (
54    "${gnosis}.html" => {
55        content => $mainpage,
56    },
57);
58
59###############################################################################
60
61my $the_test = HTTPTest->new (name => "Test-restrict-ascii",
62                              input => \%urls,
63                              cmdline => $cmdline,
64                              errcode => $expected_error_code,
65                              output => \%expected_downloaded_files);
66exit $the_test->run();
67
68# vim: et ts=4 sw=4
69
70