#!/usr/bin/perl use strict; use warnings; 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 = < Main Page

Main page.

EOF my $pagefrancais = < La seule page en français

French page.

EOF my $pageeen = < Die enkele nederlandstalige pagina

Dutch page.

EOF my $page404 = < 404

Nop nop nop...

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 -d -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 (name => "Test-iri-list", input => \%urls, cmdline => $cmdline, errcode => $expected_error_code, output => \%expected_downloaded_files); exit $the_test->run(); # vim: et ts=4 sw=4