From 5b262b1f0e006b31118706ac45d5089db08a80ba Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Tim=20R=C3=BChsen?= Date: Thu, 16 Feb 2017 12:05:06 +0100 Subject: [PATCH] Add tests/Test-iri-P.log --- tests/Makefile.am | 1 + tests/Test-iri-P.px | 209 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 210 insertions(+) create mode 100755 tests/Test-iri-P.px diff --git a/tests/Makefile.am b/tests/Makefile.am index c27c4ce2..3e613fe4 100644 --- a/tests/Makefile.am +++ b/tests/Makefile.am @@ -85,6 +85,7 @@ PX_TESTS = \ Test-idn-robots.px \ Test-idn-robots-utf8.px \ Test-iri.px \ + Test-iri-P.px \ Test-iri-percent.px \ Test-iri-disabled.px \ Test-iri-forced-remote.px \ diff --git a/tests/Test-iri-P.px b/tests/Test-iri-P.px new file mode 100755 index 00000000..42f4e691 --- /dev/null +++ b/tests/Test-iri-P.px @@ -0,0 +1,209 @@ +#!/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 = < + + Main Page + + +

+ Link to page 1 La seule page en français. + Link to page 3 My tailor is rich. +

+ + +EOF + +# specifying a wrong charset in http-equiv - it will be overridden by Content-Type HTTP header +my $pagefrancais = < + + La seule page en français + + + +

+ Link to page 2 Die enkele nerderlangstalige pagina. +

+ + +EOF + +my $pageeen = < + + Die enkele nederlandstalige pagina + + + +

+ Één is niet veel maar toch meer dan nul.
+ Nerdelands is een mooie taal... dit zin stuckje spreekt vanzelf, of niet :)
+ Méér +

+ + +EOF + +my $pageeuro = < + + Euro page + + + +

+ My tailor isn't rich anymore. +

+ + +EOF + +my $pagemeer = < + + Bekende supermarkt + + +

+ Ik ben toch niet gek ! +

+ + +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 => "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 $iso885915_path = "\xfc"; +my $cmdline = $WgetTest::WGETPATH . " -d -P ${iso885915_path} --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 -- 2.11.0