--- test/html-webhacc/cc.cgi 2008/03/11 14:10:11 1.38 +++ test/html-webhacc/cc.cgi 2008/05/18 03:47:56 1.51 @@ -86,6 +86,8 @@
$char_length byte@{[$char_length == 1 ? '' : 's']}
+ + ]; $input->{id_prefix} = ''; @@ -171,9 +173,13 @@ 'text/xml' => 1, 'application/atom+xml' => 1, 'application/rss+xml' => 1, - 'application/svg+xml' => 1, + 'image/svg+xml' => 1, 'application/xhtml+xml' => 1, 'application/xml' => 1, + ## TODO: Should we make all XML MIME Types fall + ## into this category? + + 'application/rdf+xml' => 1, ## NOTE: This type has different model. }->{$input->{media_type}}) { ($doc, $el) = print_syntax_error_xml_section ($input, $result); print_source_string_section ($input, @@ -212,6 +218,8 @@ print_listing_section ({ id => 'classes', label => 'Classes', heading => 'Classes', }, $input, $elements->{class}) if keys %{$elements->{class}}; + print_uri_section ($input, $elements->{uri}) if keys %{$elements->{uri}}; + print_rdf_section ($input, $elements->{rdf}) if @{$elements->{rdf}}; } elsif (defined $cssom) { print_structure_dump_cssom_section ($input, $cssom); ## TODO: CSSOM validation @@ -292,7 +300,7 @@

Parse Errors

-
]; +
]; push @nav, ['#parse-errors' => 'Parse Error'] unless $input->{nested}; my $onerror = sub { @@ -315,18 +323,25 @@ if (defined $inner_html_element and length $inner_html_element) { $input->{charset} ||= 'windows-1252'; ## TODO: for now. my $time1 = time; - my $t = Encode::decode ($input->{charset}, $input->{s}); + my $t = \($input->{s}); + unless ($input->{is_char_string}) { + $t = \(Encode::decode ($input->{charset}, $$t)); + } $time{decode} = time - $time1; $el = $doc->create_element_ns ('http://www.w3.org/1999/xhtml', [undef, $inner_html_element]); $time1 = time; - Whatpm::HTML->set_inner_html ($el, $t, $onerror); + Whatpm::HTML->set_inner_html ($el, $$t, $onerror); $time{parse} = time - $time1; } else { my $time1 = time; - Whatpm::HTML->parse_byte_string - ($input->{charset}, $input->{s} => $doc, $onerror); + if ($input->{is_char_string}) { + Whatpm::HTML->parse_char_string ($input->{s} => $doc, $onerror); + } else { + Whatpm::HTML->parse_byte_string + ($input->{charset}, $input->{s} => $doc, $onerror); + } $time{parse_html} = time - $time1; } $doc->manakai_charset ($input->{official_charset}) @@ -346,7 +361,7 @@

Parse Errors

-
]; +
]; push @nav, ['#parse-errors' => 'Parse Error'] unless $input->{prefix}; my $onerror = sub { @@ -366,8 +381,15 @@ return 1; }; + my $t = \($input->{s}); + if ($input->{is_char_string}) { + require Encode; + $t = \(Encode::encode ('utf8', $$t)); + $input->{charset} = 'utf-8'; + } + my $time1 = time; - open my $fh, '<', \($input->{s}); + open my $fh, '<', $t; my $doc = Message::DOM::XMLParserTemp->parse_byte_stream ($fh => $dom, $onerror, charset => $input->{charset}); $time{parse_xml} = time - $time1; @@ -557,7 +579,7 @@

Parse Errors

-
]; +
]; push @nav, ['#parse-errors' => 'Parse Error'] unless $input->{nested}; my $p = get_css_parser (); @@ -623,7 +645,7 @@

Parse Errors

-
]; +
]; push @nav, ['#parse-errors' => 'Parse Error'] unless $input->{nested}; my $onerror = sub { @@ -640,8 +662,9 @@ add_error ('syntax', \%opt => $result); }; + my $m = $input->{is_char_string} ? 'parse_char_string' : 'parse_byte_string'; my $time1 = time; - my $manifest = Whatpm::CacheManifest->parse_byte_string + my $manifest = Whatpm::CacheManifest->$m ($input->{s}, $input->{uri}, $input->{base_uri}, $onerror); $time{parse_manifest} = time - $time1; @@ -654,11 +677,28 @@ my $input = shift; my $s; unless ($input->{is_char_string}) { - require Encode; - my $enc = Encode::find_encoding ($_[1]); ## TODO: charset name -> Perl name - return unless $enc; + open my $byte_stream, '<', $_[0]; + require Message::Charset::Info; + my $charset = Message::Charset::Info->get_by_iana_name ($_[1]); + my ($char_stream, $e_status) = $charset->get_decode_handle + ($byte_stream, allow_error_reporting => 1, allow_fallback => 1); + return unless $char_stream; + + $char_stream->onerror (sub { + my (undef, $type, %opt) = @_; + if ($opt{octets}) { + ${$opt{octets}} = "\x{FFFD}"; + } + }); - $s = \($enc->decode (${$_[0]})); + my $t = ''; + while (1) { + my $c = $char_stream->getc; + last unless defined $c; + $t .= $c; + } + $s = \$t; + ## TODO: Output for each line, don't concat all of lines. } else { $s = $_[0]; } @@ -669,19 +709,22 @@

Document Source

    \n]; if (length $$s) { - while ($$s =~ /\G([^\x0A]*?)\x0D?\x0A/gc) { + while ($$s =~ /\G([^\x0D\x0A]*?)(?>\x0D\x0A?|\x0A)/gc) { print STDOUT qq[
  1. ], htescape $1, "
    2. \n"; $i++; } - if ($$s =~ /\G([^\x0A]+)/gc) { + if ($$s =~ /\G([^\x0D\x0A]+)/gc) { print STDOUT qq[
  2. ], htescape $1, "
    3. \n"; } } else { print STDOUT q[
  3. ]; } - print STDOUT "
"; + print STDOUT "
+"; } # print_input_string_section sub print_document_tree ($$) { @@ -850,7 +893,7 @@ print STDOUT qq[

Document Errors

-
]; +
]; push @nav, [qq[#$input->{id_prefix}document-errors] => 'Document Error'] unless $input->{nested}; @@ -878,7 +921,10 @@ } $time{check} = time - $time1; - print STDOUT qq[
]; + print STDOUT qq[
+
]; return $elements; } # print_structure_error_dom_section @@ -927,16 +973,15 @@ require JSON; my $i = 0; - for my $table_el (@$tables) { + for my $table (@$tables) { $i++; print STDOUT qq[

] . - get_node_link ($input, $table_el) . q[

]; + get_node_link ($input, $table->{element}) . q[]; - ## TODO: Make |ContentChecker| return |form_table| result - ## so that this script don't have to run the algorithm twice. - my $table = Whatpm::HTMLTable->form_table ($table_el); - - for (@{$table->{column_group}}, @{$table->{column}}, $table->{caption}) { + delete $table->{element}; + + for (@{$table->{column_group}}, @{$table->{column}}, $table->{caption}, + @{$table->{row}}) { next unless $_; delete $_->{element}; } @@ -989,6 +1034,106 @@ print STDOUT qq[
]; } # print_listing_section +sub print_uri_section ($$$) { + my ($input, $uris) = @_; + + ## NOTE: URIs contained in the DOM (i.e. in HTML or XML documents), + ## except for those in RDF triples. + ## TODO: URIs in CSS + + push @nav, ['#' . $input->{id_prefix} . 'uris' => 'URIs'] + unless $input->{nested}; + print STDOUT qq[ +
+

URIs

+ +
]; + for my $uri (sort {$a cmp $b} keys %$uris) { + my $euri = htescape ($uri); + print STDOUT qq[
<$euri>]; + my $eccuri = htescape (get_cc_uri ($uri)); + print STDOUT qq[
Check conformance of this document]; + print STDOUT qq[
Found at:
    ]; + for my $entry (@{$uris->{$uri}}) { + print STDOUT qq[
  • ], get_node_link ($input, $entry->{node}); + if (keys %{$entry->{type} or {}}) { + print STDOUT ' ('; + print STDOUT join ', ', map { + { + hyperlink => 'Hyperlink', + resource => 'Link to an external resource', + namespace => 'Namespace URI', + cite => 'Citation or link to a long description', + embedded => 'Link to an embedded content', + base => 'Base URI', + action => 'Submission URI', + }->{$_} + or + htescape ($_) + } keys %{$entry->{type}}; + print STDOUT ')'; + } + } + print STDOUT qq[
]; + } + print STDOUT qq[
]; +} # print_uri_section + +sub print_rdf_section ($$$) { + my ($input, $rdfs) = @_; + + push @nav, ['#' . $input->{id_prefix} . 'rdf' => 'RDF'] + unless $input->{nested}; + print STDOUT qq[ +
+

RDF Triples

+ +
]; + my $i = 0; + for my $rdf (@$rdfs) { + print STDOUT qq[
]; + print STDOUT get_node_link ($input, $rdf->[0]); + print STDOUT qq[
]; + for my $triple (@{$rdf->[1]}) { + print STDOUT '
' . get_node_link ($input, $triple->[0]) . '
'; + print STDOUT get_rdf_resource_html ($triple->[1]); + print STDOUT ' '; + print STDOUT get_rdf_resource_html ($triple->[2]); + print STDOUT ' '; + print STDOUT get_rdf_resource_html ($triple->[3]); + } + print STDOUT qq[
]; + } + print STDOUT qq[
]; +} # print_rdf_section + +sub get_rdf_resource_html ($) { + my $resource = shift; + if (defined $resource->{uri}) { + my $euri = htescape ($resource->{uri}); + return '<' . $euri . + '>'; + } elsif (defined $resource->{bnodeid}) { + return htescape ('_:' . $resource->{bnodeid}); + } elsif ($resource->{nodes}) { + return '(rdf:XMLLiteral)'; + } elsif (defined $resource->{value}) { + my $elang = htescape (defined $resource->{language} + ? $resource->{language} : ''); + my $r = qq[] . htescape ($resource->{value}) . ''; + if (defined $resource->{datatype}) { + my $euri = htescape ($resource->{datatype}); + $r .= '^^<' . $euri . + '>'; + } elsif (length $resource->{language}) { + $r .= '@' . htescape ($resource->{language}); + } + return $r; + } else { + return '??'; + } +} # get_rdf_resource_html + sub print_result_section ($) { my $result = shift; @@ -1054,24 +1199,25 @@ print STDOUT qq[$label$result->{$_->[1]}->{must}$uncertain$result->{$_->[1]}->{should}$uncertain$result->{$_->[1]}->{warning}$uncertain]; if ($uncertain) { - print qq[−∞..$result->{$_->[1]}->{score_max}]; + print qq[−∞..$result->{$_->[1]}->{score_max}]; } elsif ($result->{$_->[1]}->{score_min} != $result->{$_->[1]}->{score_max}) { - print qq[$result->{$_->[1]}->{score_min}..$result->{$_->[1]}->{score_max}]; + print qq[$result->{$_->[1]}->{score_min}..$result->{$_->[1]}->{score_max}]; } else { - print qq[$result->{$_->[1]}->{score_min}]; + print qq[$result->{$_->[1]}->{score_min}]; } + print qq[ / 20]; } $score_max += $score_base; print STDOUT qq[ -Semantics0?0?0?−∞..$score_base +Semantics0?0?0?−∞..$score_base / 20 Total $must_error? $should_error? $warning? -−∞..$score_max +−∞..$score_max / 100

Important: This conformance checking service @@ -1118,18 +1264,49 @@ my $r = ''; - if (defined $err->{line}) { - if ($err->{column} > 0) { - $r = qq[Line $err->{line} column $err->{column}]; + my $line; + my $column; + + if (defined $err->{node}) { + $line = $err->{node}->get_user_data ('manakai_source_line'); + if (defined $line) { + $column = $err->{node}->get_user_data ('manakai_source_column'); + } else { + if ($err->{node}->node_type == $err->{node}->ATTRIBUTE_NODE) { + my $owner = $err->{node}->owner_element; + $line = $owner->get_user_data ('manakai_source_line'); + $column = $owner->get_user_data ('manakai_source_column'); + } else { + my $parent = $err->{node}->parent_node; + if ($parent) { + $line = $parent->get_user_data ('manakai_source_line'); + $column = $parent->get_user_data ('manakai_source_column'); + } + } + } + } + unless (defined $line) { + if (defined $err->{token} and defined $err->{token}->{line}) { + $line = $err->{token}->{line}; + $column = $err->{token}->{column}; + } elsif (defined $err->{line}) { + $line = $err->{line}; + $column = $err->{column}; + } + } + + if (defined $line) { + if (defined $column and $column > 0) { + $r = qq[Line $line column $column]; } else { - $err->{line} = $err->{line} - 1 || 1; - $r = qq[Line $err->{line}]; + $line = $line - 1 || 1; + $r = qq[Line $line]; } } if (defined $err->{node}) { $r .= ' ' if length $r; - $r = get_node_link ($input, $err->{node}); + $r .= get_node_link ($input, $err->{node}); } if (defined $err->{index}) { @@ -1183,10 +1360,10 @@ while (defined $node) { my $rs; if ($node->node_type == 1) { - $rs = $node->manakai_local_name; + $rs = $node->node_name; $node = $node->parent_node; } elsif ($node->node_type == 2) { - $rs = '@' . $node->manakai_local_name; + $rs = '@' . $node->node_name; $node = $node->owner_element; } elsif ($node->node_type == 3) { $rs = '"' . $node->data . '"'; @@ -1264,6 +1441,17 @@ } +sub encode_uri_component ($) { + require Encode; + my $s = Encode::encode ('utf8', shift); + $s =~ s/([^0-9A-Za-z_.~-])/sprintf '%%%02X', ord $1/ge; + return $s; +} # encode_uri_component + +sub get_cc_uri ($) { + return './?uri=' . encode_uri_component ($_[0]); +} # get_cc_uri + sub get_input_document ($$) { my ($http, $dom) = @_; @@ -1453,4 +1641,4 @@ =cut -## $Date: 2008/03/11 14:10:11 $ +## $Date: 2008/05/18 03:47:56 $