--- test/html-webhacc/cc.cgi 2007/06/27 12:35:24 1.2 +++ test/html-webhacc/cc.cgi 2008/08/14 15:50:42 1.62 @@ -2,309 +2,137 @@ use strict; use lib qw[/home/httpd/html/www/markup/html/whatpm - /home/wakaba/work/manakai/lib - /home/wakaba/public_html/-temp/wiki/lib]; + /home/wakaba/work/manakai2/lib]; use CGI::Carp qw[fatalsToBrowser]; -use Scalar::Util qw[refaddr]; -use SuikaWiki::Input::HTTP; ## TODO: Use some better CGI module + require WebHACC::Input; -sub htescape ($) { - my $s = $_[0]; - $s =~ s/&/&/g; - $s =~ s//>/g; - $s =~ s/"/"/g; - $s =~ s!([\x00-\x09\x0B-\x1F\x7F-\x80])!sprintf 'U+%04X', ord $1!ge; - return $s; -} # htescape - -my $http = SuikaWiki::Input::HTTP->new; - -## TODO: _charset_ - - my $input_format = $http->parameter ('i') || 'text/html'; - my $inner_html_element = $http->parameter ('e'); - my $input_uri = 'thismessage:/'; - - my $s = $http->parameter ('s'); - if (length $s > 1000_000) { - print STDOUT "Status: 400 Document Too Long\nContent-Type: text/plain; charset=us-ascii\n\nToo long"; - exit; - } - - print STDOUT qq[Content-Type: text/html; charset=utf-8 - - - - -Web Document Conformance Checker (BETA) - - - - -

Web Document Conformance Checker (beta)

- -
-
Document URI
-
<@{[htescape $input_uri]}>
-
Internet Media Type
-
@{[htescape $input_format]}
-]; # no
yet - - require Message::DOM::DOMImplementation; - my $dom = Message::DOM::DOMImplementation->____new; - my $doc; - my $el; - - if ($input_format eq 'text/html') { - require Encode; - require Whatpm::HTML; - - $s = Encode::decode ('utf-8', $s); - - print STDOUT qq[ -
Character Encoding
-
(none)
- - -
-]; - print_source_string (\$s); - print STDOUT qq[ -
- -
-

Parse Errors

- - -
-]; - } elsif ($input_format eq 'application/xhtml+xml') { - require Message::DOM::XMLParserTemp; - require Encode; - - my $t = Encode::decode ('utf-8', $s); - - print STDOUT qq[ -
Character Encoding
-
(none)
- - -
-]; - print_source_string (\$t); - print STDOUT qq[ -
- -
-

Parse Errors

- - -
-]; - } else { - print STDOUT qq[ - +{ + require Message::CGI::HTTP; + my $http = Message::CGI::HTTP->new; + + require WebHACC::Output; + my $out = WebHACC::Output->new; + $out->handle (*STDOUT); + $out->set_utf8; -

Media type @{[htescape $input_format]} is not supported!

-]; + if ($http->get_meta_variable ('PATH_INFO') ne '/') { + $out->http_error (404); + exit; } - - if (defined $doc or defined $el) { - print STDOUT qq[ -
-

Document Tree

-]; - - print_document_tree ($el || $doc); - - print STDOUT qq[ -
- -
-

Document Errors

- - -
-]; + ## TODO: We need real conneg support... + my $primary_language = 'en'; + if ($ENV{HTTP_ACCEPT_LANGUAGE} =~ /ja/) { + $primary_language = 'ja'; + } + $out->load_text_catalog ($primary_language); + + $out->set_flush; + $out->http_header; + $out->html_header; + $out->unset_flush; + + $out->generate_input_section ($http); + + my $u = $http->get_parameter ('uri'); + my $s = $http->get_parameter ('s'); + if ((not defined $u or not length $u) and + (not defined $s or not length $s)) { + exit; } - ## TODO: Show result - print STDOUT qq[ - - -]; - -exit; - -sub print_source_string ($) { - my $s = $_[0]; - my $i = 1; - print STDOUT qq[
    \n]; - while ($$s =~ /\G([^\x0A]*?)\x0D?\x0A/gc) { - print STDOUT qq[
  1. ], htescape $1, "
  2. \n"; - $i++; + require WebHACC::Result; + my $result = WebHACC::Result->new; + $result->output ($out); + + require WebHACC::Input; + my $input = WebHACC::Input->get_document ($http => $result => $out); + + check_and_print ($input => $result => $out); + + $out->nav_list; + + exit; +} + +sub check_and_print ($$$) { + my ($input, $result, $out) = @_; + my $original_input = $out->input; + $out->input ($input); + + $input->generate_info_section ($result); + + $input->generate_transfer_sections ($result); + + unless (defined $input->{s}) { + ## NOTE: This is an error of the implementation. + $result->layer_uncertain ('transfer'); + $result->generate_result_section; + return; + } + + my $checker_class = { + 'text/cache-manifest' => 'WebHACC::Language::CacheManifest', + 'text/css' => 'WebHACC::Language::CSS', + 'text/html' => 'WebHACC::Language::HTML', + 'text/x-webidl' => 'WebHACC::Language::WebIDL', + + 'text/xml' => 'WebHACC::Language::XML', + 'application/atom+xml' => 'WebHACC::Language::XML', + 'application/rss+xml' => 'WebHACC::Language::XML', + 'image/svg+xml' => 'WebHACC::Language::XML', + 'application/xhtml+xml' => 'WebHACC::Language::XML', + 'application/xml' => 'WebHACC::Language::XML', + ## TODO: Should we make all XML MIME Types fall + ## into this category? + + ## NOTE: This type has different model from normal XML types. + 'application/rdf+xml' => 'WebHACC::Language::XML', + }->{$input->{media_type}} || 'WebHACC::Language::Default'; + + eval qq{ require $checker_class } or die "$0: Loading $checker_class: $@"; + my $checker = $checker_class->new; + $checker->input ($input); + $checker->output ($out); + $checker->result ($result); + + ## TODO: A cache manifest MUST be text/cache-manifest + ## TODO: WebIDL media type "text/x-webidl" + + $checker->generate_syntax_error_section; + $checker->generate_source_string_section; + + my @subdoc; + $checker->onsubdoc (sub { + push @subdoc, shift; + }); + + $checker->generate_structure_dump_section; + $checker->generate_structure_error_section; + $checker->generate_additional_sections; + + my $id_prefix = 0; + for my $_subinput (@subdoc) { + my $subinput = WebHACC::Input::Subdocument->new (++$id_prefix); + $subinput->{$_} = $_subinput->{$_} for keys %$_subinput; + $subinput->{base_uri} = $subinput->{container_node}->base_uri + unless defined $subinput->{base_uri}; + $subinput->{parent_input} = $input; + + my $subresult = WebHACC::Result->new; + $subresult->output ($out); + $subresult->parent_result ($result); + + $subinput->start_section ($subresult); + check_and_print ($subinput => $subresult => $out); + $subinput->end_section ($subresult); } - if ($$s =~ /\G([^\x0A]+)/gc) { - print STDOUT qq[
  3. ], htescape $1, "
  4. \n"; - } - print STDOUT "
"; -} # print_input_string -sub print_document_tree ($) { - my $node = shift; - my $r = '
    '; - - my @node = ($node); - while (@node) { - my $child = shift @node; - unless (ref $child) { - $r .= $child; - next; - } - - my $node_id = 'node-'.refaddr $child; - my $nt = $child->node_type; - if ($nt == $child->ELEMENT_NODE) { - $r .= qq'
  1. ' . htescape ($child->tag_name) . - ''; ## ISSUE: case - - if ($child->has_attributes) { - $r .= ''; - } - - if ($node->has_child_nodes) { - $r .= '
      '; - unshift @node, @{$child->child_nodes}, '
    '; - } - } elsif ($nt == $child->TEXT_NODE) { - $r .= qq'
  2. ' . htescape ($child->data) . '
  3. '; - } elsif ($nt == $child->CDATA_SECTION_NODE) { - $r .= qq'
  4. <[CDATA[' . htescape ($child->data) . ']]>
  5. '; - } elsif ($nt == $child->COMMENT_NODE) { - $r .= qq'
  6. <!--' . htescape ($child->data) . '-->
  7. '; - } elsif ($nt == $child->DOCUMENT_NODE) { - $r .= qq'
  8. Document
  9. '; - if ($child->has_child_nodes) { - $r .= '
      '; - unshift @node, @{$child->child_nodes}, '
    '; - } - } elsif ($nt == $child->DOCUMENT_TYPE_NODE) { - $r .= qq'
  10. <!DOCTYPE>
  11. '; - } elsif ($nt == $child->PROCESSING_INSTRUCTION_NODE) { - $r .= qq'
  12. <?@{[htescape ($child->target)]}?>'; - $r .= '
  13. '; - } else { - $r .= qq'
  14. @{[$child->node_type]} @{[htescape ($child->node_name)]}
  15. '; # error - } - } + $result->generate_result_section; - $r .= '
'; - print STDOUT $r; -} # print_document_tree - -sub get_node_path ($) { - my $node = shift; - my @r; - while (defined $node) { - my $rs; - if ($node->node_type == 1) { - $rs = $node->manakai_local_name; - $node = $node->parent_node; - } elsif ($node->node_type == 2) { - $rs = '@' . $node->manakai_local_name; - $node = $node->owner_element; - } elsif ($node->node_type == 3) { - $rs = '"' . $node->data . '"'; - $node = $node->parent_node; - } elsif ($node->node_type == 9) { - $rs = ''; - $node = $node->parent_node; - } else { - $rs = '#' . $node->node_type; - $node = $node->parent_node; - } - unshift @r, $rs; - } - return join '/', @r; -} # get_node_path + $out->input ($original_input); +} # check_and_print =head1 AUTHOR @@ -312,11 +140,11 @@ =head1 LICENSE -Copyright 2007 Wakaba +Copyright 2007-2008 Wakaba This library is free software; you can redistribute it and/or modify it under the same terms as Perl itself. =cut -## $Date: 2007/06/27 12:35:24 $ +## $Date: 2008/08/14 15:50:42 $