#!/usr/bin/env -S perl -I . use strict; use warnings; use HTTPTest; # This program tests that --restrict-file-names=ascii can be used to # ensure that all high-valued bytes are escaped. The sample filename was # chosen because in former versions of Wget, one could either choose not # to escape any portion of the UTF-8 filename via # --restrict-file-names=nocontrol (which would only be helpful if one # was _on_ a UTF-8 system), or else Wget would escape _portions_ of # characters, leaving irrelevant "latin1"-looking characters combined # with percent-encoded "control" characters, instead of encoding all the # bytes of an entire non-ASCII UTF-8 character. ############################################################################### # "gnosis" in UTF-8 greek. my $gnosis = '%CE%B3%CE%BD%CF%89%CF%83%CE%B9%CF%82'; my $mainpage = <<EOF; <html> <head> <title>Some Page Title</title> </head> <body> <p> Some text... </p> </body> </html> EOF # code, msg, headers, content my %urls = ( "/$gnosis.html" => { code => "200", msg => "Dontcare", headers => { "Content-type" => "text/html", }, content => $mainpage, }, ); my $cmdline = $WgetTest::WGETPATH . " --restrict-file-names=ascii " . "http://localhost:{{port}}/${gnosis}.html"; my $expected_error_code = 0; my %expected_downloaded_files = ( "${gnosis}.html" => { content => $mainpage, }, ); ############################################################################### 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