--- test/html-webhacc/cc.cgi 2008/02/10 02:05:30 1.31 +++ test/html-webhacc/cc.cgi 2008/05/18 03:47:56 1.51 @@ -20,6 +20,11 @@ return $s; } # htescape + my @nav; + my %time; + require Message::DOM::DOMImplementation; + my $dom = Message::DOM::DOMImplementation->new; +{ use Message::CGI::HTTP; my $http = Message::CGI::HTTP->new; @@ -31,12 +36,8 @@ binmode STDOUT, ':utf8'; $| = 1; - require Message::DOM::DOMImplementation; - my $dom = Message::DOM::DOMImplementation->new; - load_text_catalog ('en'); ## TODO: conneg - my @nav; print STDOUT qq[Content-Type: text/html; charset=utf-8 @@ -53,7 +54,6 @@ $| = 0; my $input = get_input_document ($http, $dom); my $char_length = 0; - my %time; print qq[
@@ -86,8 +86,12 @@
$char_length byte@{[$char_length == 1 ? '' : 's']}
+ + ]; + $input->{id_prefix} = ''; + #$input->{nested} = 0; my $result = {conforming_min => 1, conforming_max => 1}; check_and_print ($input => $result); print_result_section ($result); @@ -116,6 +120,7 @@ } exit; +} sub add_error ($$$) { my ($layer, $err, $result) = @_; @@ -129,6 +134,8 @@ } elsif ($err->{level} eq 'u' or $err->{level} eq 'unsupported') { $result->{$layer}->{unsupported}++; $result->{unsupported} = 1; + } elsif ($err->{level} eq 'i') { + # } else { $result->{$layer}->{must}++; $result->{$layer}->{score_max} -= 2; @@ -152,41 +159,100 @@ my $doc; my $el; + my $cssom; my $manifest; + my @subdoc; if ($input->{media_type} eq 'text/html') { ($doc, $el) = print_syntax_error_html_section ($input, $result); print_source_string_section - (\($input->{s}), $input->{charset} || $doc->input_encoding); + ($input, + \($input->{s}), + $input->{charset} || $doc->input_encoding); } elsif ({ 'text/xml' => 1, 'application/atom+xml' => 1, 'application/rss+xml' => 1, - 'application/svg+xml' => 1, + 'image/svg+xml' => 1, 'application/xhtml+xml' => 1, 'application/xml' => 1, + ## TODO: Should we make all XML MIME Types fall + ## into this category? + + 'application/rdf+xml' => 1, ## NOTE: This type has different model. }->{$input->{media_type}}) { ($doc, $el) = print_syntax_error_xml_section ($input, $result); - print_source_string_section (\($input->{s}), $doc->input_encoding); + print_source_string_section ($input, + \($input->{s}), + $doc->input_encoding); + } elsif ($input->{media_type} eq 'text/css') { + $cssom = print_syntax_error_css_section ($input, $result); + print_source_string_section + ($input, \($input->{s}), + $cssom->manakai_input_encoding); } elsif ($input->{media_type} eq 'text/cache-manifest') { ## TODO: MUST be text/cache-manifest $manifest = print_syntax_error_manifest_section ($input, $result); - print_source_string_section (\($input->{s}), 'utf-8'); + print_source_string_section ($input, \($input->{s}), + 'utf-8'); } else { ## TODO: Change HTTP status code?? print_result_unknown_type_section ($input, $result); } if (defined $doc or defined $el) { - print_structure_dump_dom_section ($doc, $el); - my $elements = print_structure_error_dom_section ($doc, $el, $result); - print_table_section ($elements->{table}) if @{$elements->{table}}; - print_id_section ($elements->{id}) if keys %{$elements->{id}}; - print_term_section ($elements->{term}) if keys %{$elements->{term}}; - print_class_section ($elements->{class}) if keys %{$elements->{class}}; + $doc->document_uri ($input->{uri}); + $doc->manakai_entity_base_uri ($input->{base_uri}); + print_structure_dump_dom_section ($input, $doc, $el); + my $elements = print_structure_error_dom_section + ($input, $doc, $el, $result, sub { + push @subdoc, shift; + }); + print_table_section ($input, $elements->{table}) if @{$elements->{table}}; + print_listing_section ({ + id => 'identifiers', label => 'IDs', heading => 'Identifiers', + }, $input, $elements->{id}) if keys %{$elements->{id}}; + print_listing_section ({ + id => 'terms', label => 'Terms', heading => 'Terms', + }, $input, $elements->{term}) if keys %{$elements->{term}}; + 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 + add_error ('structure', {level => 'u'} => $result); } elsif (defined $manifest) { - print_structure_dump_manifest_section ($manifest); - print_structure_error_manifest_section ($manifest, $result); + print_structure_dump_manifest_section ($input, $manifest); + print_structure_error_manifest_section ($input, $manifest, $result); + } + + my $id_prefix = 0; + for my $subinput (@subdoc) { + $subinput->{id_prefix} = 'subdoc-' . ++$id_prefix; + $subinput->{nested} = 1; + $subinput->{base_uri} = $subinput->{container_node}->base_uri + unless defined $subinput->{base_uri}; + my $ebaseuri = htescape ($subinput->{base_uri}); + push @nav, ['#' . $subinput->{id_prefix} => 'Sub #' . $id_prefix]; + print STDOUT qq[
+

Subdocument #$id_prefix

+ +
+
Internet Media Type
+
@{[htescape $subinput->{media_type}]} +
Container Node
+
@{[get_node_link ($input, $subinput->{container_node})]}
+
Base URI
+
<$ebaseuri>
+
]; + + $subinput->{id_prefix} .= '-'; + check_and_print ($subinput => $result); + + print STDOUT qq[
]; } } # check_and_print @@ -194,10 +260,10 @@ my ($input, $result) = @_; return unless defined $input->{header_status_code} or defined $input->{header_status_text} or - @{$input->{header_field}}; + @{$input->{header_field} or []}; - push @nav, ['#source-header' => 'HTTP Header']; - print STDOUT qq[
+ push @nav, ['#source-header' => 'HTTP Header'] unless $input->{nested}; + print STDOUT qq[

HTTP Header

Note: Due to the limitation of the @@ -231,21 +297,17 @@ require Whatpm::HTML; print STDOUT qq[ -

+

Parse Errors

-
]; - push @nav, ['#parse-errors' => 'Parse Error']; +
]; + push @nav, ['#parse-errors' => 'Parse Error'] unless $input->{nested}; my $onerror = sub { my (%opt) = @_; my ($type, $cls, $msg) = get_text ($opt{type}, $opt{level}); - if ($opt{column} > 0) { - print STDOUT qq[
Line $opt{line} column $opt{column}
\n]; - } else { - $opt{line} = $opt{line} - 1 || 1; - print STDOUT qq[
Line $opt{line}
\n]; - } + print STDOUT qq[
], get_error_label ($input, \%opt), + qq[
]; $type =~ tr/ /-/; $type =~ s/\|/%7C/g; $msg .= qq[ [Description]]; @@ -257,22 +319,29 @@ my $doc = $dom->create_document; my $el; - my $inner_html_element = $http->get_parameter ('e'); + my $inner_html_element = $input->{inner_html_element}; 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}) @@ -289,16 +358,16 @@ require Message::DOM::XMLParserTemp; print STDOUT qq[ -
+

Parse Errors

-
]; - push @nav, ['#parse-errors' => 'Parse Error']; +
]; + push @nav, ['#parse-errors' => 'Parse Error'] unless $input->{prefix}; my $onerror = sub { my $err = shift; my $line = $err->location->line_number; - print STDOUT qq[
Line $line column ]; + print STDOUT qq[
Line $line column ]; print STDOUT $err->location->column_number, "
"; print STDOUT htescape $err->text, "
\n"; @@ -312,8 +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 - $time1; @@ -325,22 +401,258 @@ return ($doc, undef); } # print_syntax_error_xml_section +sub get_css_parser () { + our $CSSParser; + return $CSSParser if $CSSParser; + + require Whatpm::CSS::Parser; + my $p = Whatpm::CSS::Parser->new; + + $p->{prop}->{$_} = 1 for qw/ + alignment-baseline + background background-attachment background-color background-image + background-position background-position-x background-position-y + background-repeat border border-bottom border-bottom-color + border-bottom-style border-bottom-width border-collapse border-color + border-left border-left-color + border-left-style border-left-width border-right border-right-color + border-right-style border-right-width + border-spacing -manakai-border-spacing-x -manakai-border-spacing-y + border-style border-top border-top-color border-top-style border-top-width + border-width bottom + caption-side clear clip color content counter-increment counter-reset + cursor direction display dominant-baseline empty-cells float font + font-family font-size font-size-adjust font-stretch + font-style font-variant font-weight height left + letter-spacing line-height + list-style list-style-image list-style-position list-style-type + margin margin-bottom margin-left margin-right margin-top marker-offset + marks max-height max-width min-height min-width opacity -moz-opacity + orphans outline outline-color outline-style outline-width overflow + overflow-x overflow-y + padding padding-bottom padding-left padding-right padding-top + page page-break-after page-break-before page-break-inside + position quotes right size table-layout + text-align text-anchor text-decoration text-indent text-transform + top unicode-bidi vertical-align visibility white-space width widows + word-spacing writing-mode z-index + /; + $p->{prop_value}->{display}->{$_} = 1 for qw/ + block clip inline inline-block inline-table list-item none + table table-caption table-cell table-column table-column-group + table-header-group table-footer-group table-row table-row-group + compact marker + /; + $p->{prop_value}->{position}->{$_} = 1 for qw/ + absolute fixed relative static + /; + $p->{prop_value}->{float}->{$_} = 1 for qw/ + left right none + /; + $p->{prop_value}->{clear}->{$_} = 1 for qw/ + left right none both + /; + $p->{prop_value}->{direction}->{ltr} = 1; + $p->{prop_value}->{direction}->{rtl} = 1; + $p->{prop_value}->{marks}->{crop} = 1; + $p->{prop_value}->{marks}->{cross} = 1; + $p->{prop_value}->{'unicode-bidi'}->{$_} = 1 for qw/ + normal bidi-override embed + /; + for my $prop_name (qw/overflow overflow-x overflow-y/) { + $p->{prop_value}->{$prop_name}->{$_} = 1 for qw/ + visible hidden scroll auto -webkit-marquee -moz-hidden-unscrollable + /; + } + $p->{prop_value}->{visibility}->{$_} = 1 for qw/ + visible hidden collapse + /; + $p->{prop_value}->{'list-style-type'}->{$_} = 1 for qw/ + disc circle square decimal decimal-leading-zero + lower-roman upper-roman lower-greek lower-latin + upper-latin armenian georgian lower-alpha upper-alpha none + hebrew cjk-ideographic hiragana katakana hiragana-iroha + katakana-iroha + /; + $p->{prop_value}->{'list-style-position'}->{outside} = 1; + $p->{prop_value}->{'list-style-position'}->{inside} = 1; + $p->{prop_value}->{'page-break-before'}->{$_} = 1 for qw/ + auto always avoid left right + /; + $p->{prop_value}->{'page-break-after'}->{$_} = 1 for qw/ + auto always avoid left right + /; + $p->{prop_value}->{'page-break-inside'}->{auto} = 1; + $p->{prop_value}->{'page-break-inside'}->{avoid} = 1; + $p->{prop_value}->{'background-repeat'}->{$_} = 1 for qw/ + repeat repeat-x repeat-y no-repeat + /; + $p->{prop_value}->{'background-attachment'}->{scroll} = 1; + $p->{prop_value}->{'background-attachment'}->{fixed} = 1; + $p->{prop_value}->{'font-size'}->{$_} = 1 for qw/ + xx-small x-small small medium large x-large xx-large + -manakai-xxx-large -webkit-xxx-large + larger smaller + /; + $p->{prop_value}->{'font-style'}->{normal} = 1; + $p->{prop_value}->{'font-style'}->{italic} = 1; + $p->{prop_value}->{'font-style'}->{oblique} = 1; + $p->{prop_value}->{'font-variant'}->{normal} = 1; + $p->{prop_value}->{'font-variant'}->{'small-caps'} = 1; + $p->{prop_value}->{'font-stretch'}->{$_} = 1 for + qw/normal wider narrower ultra-condensed extra-condensed + condensed semi-condensed semi-expanded expanded + extra-expanded ultra-expanded/; + $p->{prop_value}->{'text-align'}->{$_} = 1 for qw/ + left right center justify begin end + /; + $p->{prop_value}->{'text-transform'}->{$_} = 1 for qw/ + capitalize uppercase lowercase none + /; + $p->{prop_value}->{'white-space'}->{$_} = 1 for qw/ + normal pre nowrap pre-line pre-wrap -moz-pre-wrap + /; + $p->{prop_value}->{'writing-mode'}->{$_} = 1 for qw/ + lr rl tb lr-tb rl-tb tb-rl + /; + $p->{prop_value}->{'text-anchor'}->{$_} = 1 for qw/ + start middle end + /; + $p->{prop_value}->{'dominant-baseline'}->{$_} = 1 for qw/ + auto use-script no-change reset-size ideographic alphabetic + hanging mathematical central middle text-after-edge text-before-edge + /; + $p->{prop_value}->{'alignment-baseline'}->{$_} = 1 for qw/ + auto baseline before-edge text-before-edge middle central + after-edge text-after-edge ideographic alphabetic hanging + mathematical + /; + $p->{prop_value}->{'text-decoration'}->{$_} = 1 for qw/ + none blink underline overline line-through + /; + $p->{prop_value}->{'caption-side'}->{$_} = 1 for qw/ + top bottom left right + /; + $p->{prop_value}->{'table-layout'}->{auto} = 1; + $p->{prop_value}->{'table-layout'}->{fixed} = 1; + $p->{prop_value}->{'border-collapse'}->{collapse} = 1; + $p->{prop_value}->{'border-collapse'}->{separate} = 1; + $p->{prop_value}->{'empty-cells'}->{show} = 1; + $p->{prop_value}->{'empty-cells'}->{hide} = 1; + $p->{prop_value}->{cursor}->{$_} = 1 for qw/ + auto crosshair default pointer move e-resize ne-resize nw-resize n-resize + se-resize sw-resize s-resize w-resize text wait help progress + /; + for my $prop (qw/border-top-style border-left-style + border-bottom-style border-right-style outline-style/) { + $p->{prop_value}->{$prop}->{$_} = 1 for qw/ + none hidden dotted dashed solid double groove ridge inset outset + /; + } + for my $prop (qw/color background-color + border-bottom-color border-left-color border-right-color + border-top-color border-color/) { + $p->{prop_value}->{$prop}->{transparent} = 1; + $p->{prop_value}->{$prop}->{flavor} = 1; + $p->{prop_value}->{$prop}->{'-manakai-default'} = 1; + } + $p->{prop_value}->{'outline-color'}->{invert} = 1; + $p->{prop_value}->{'outline-color'}->{'-manakai-invert-or-currentcolor'} = 1; + $p->{pseudo_class}->{$_} = 1 for qw/ + active checked disabled empty enabled first-child first-of-type + focus hover indeterminate last-child last-of-type link only-child + only-of-type root target visited + lang nth-child nth-last-child nth-of-type nth-last-of-type not + -manakai-contains -manakai-current + /; + $p->{pseudo_element}->{$_} = 1 for qw/ + after before first-letter first-line + /; + + return $CSSParser = $p; +} # get_css_parser + +sub print_syntax_error_css_section ($$) { + my ($input, $result) = @_; + + print STDOUT qq[ +
+

Parse Errors

+ +
]; + push @nav, ['#parse-errors' => 'Parse Error'] unless $input->{nested}; + + my $p = get_css_parser (); + $p->init; + $p->{onerror} = sub { + my (%opt) = @_; + my ($type, $cls, $msg) = get_text ($opt{type}, $opt{level}); + if ($opt{token}) { + print STDOUT qq[
Line $opt{token}->{line} column $opt{token}->{column}]; + } else { + print STDOUT qq[
Unknown location]; + } + if (defined $opt{value}) { + print STDOUT qq[ (@{[htescape ($opt{value})]})]; + } elsif (defined $opt{token}) { + print STDOUT qq[ (@{[htescape (Whatpm::CSS::Tokenizer->serialize_token ($opt{token}))]})]; + } + $type =~ tr/ /-/; + $type =~ s/\|/%7C/g; + $msg .= qq[ [Description]]; + print STDOUT qq[
], get_error_level_label (\%opt); + print STDOUT qq[$msg
\n]; + + add_error ('syntax', \%opt => $result); + }; + $p->{href} = $input->{uri}; + $p->{base_uri} = $input->{base_uri}; + +# if ($parse_mode eq 'q') { +# $p->{unitless_px} = 1; +# $p->{hashless_color} = 1; +# } + +## TODO: Make $input->{s} a ref. + + my $s = \$input->{s}; + my $charset; + unless ($input->{is_char_string}) { + require Encode; + if (defined $input->{charset}) {## TODO: IANA->Perl + $charset = $input->{charset}; + $s = \(Encode::decode ($input->{charset}, $$s)); + } else { + ## TODO: charset detection + $s = \(Encode::decode ($charset = 'utf-8', $$s)); + } + } + + my $cssom = $p->parse_char_string ($$s); + $cssom->manakai_input_encoding ($charset) if defined $charset; + + print STDOUT qq[
]; + + return $cssom; +} # print_syntax_error_css_section + sub print_syntax_error_manifest_section ($$) { my ($input, $result) = @_; require Whatpm::CacheManifest; print STDOUT qq[ -
+

Parse Errors

-
]; - push @nav, ['#parse-errors' => 'Parse Error']; +
]; + push @nav, ['#parse-errors' => 'Parse Error'] unless $input->{nested}; my $onerror = sub { my (%opt) = @_; my ($type, $cls, $msg) = get_text ($opt{type}, $opt{level}); - print STDOUT qq[
], get_error_label (\%opt), qq[
]; + print STDOUT qq[
], get_error_label ($input, \%opt), + qq[
]; $type =~ tr/ /-/; $type =~ s/\|/%7C/g; $msg .= qq[ [Description]]; @@ -350,8 +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; @@ -360,33 +673,63 @@ return $manifest; } # print_syntax_error_manifest_section -sub print_source_string_section ($$) { - require Encode; - my $enc = Encode::find_encoding ($_[1]); ## TODO: charset name -> Perl name - return unless $enc; +sub print_source_string_section ($$$) { + my $input = shift; + my $s; + unless ($input->{is_char_string}) { + 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}"; + } + }); + + 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]; + } - my $s = \($enc->decode (${$_[0]})); my $i = 1; - push @nav, ['#source-string' => 'Source']; - print STDOUT qq[
+ push @nav, ['#source-string' => 'Source'] unless $input->{nested}; + print STDOUT qq[

Document Source

    \n]; if (length $$s) { - while ($$s =~ /\G([^\x0A]*?)\x0D?\x0A/gc) { - print STDOUT qq[
  1. ], htescape $1, "
    2. \n"; + while ($$s =~ /\G([^\x0D\x0A]*?)(?>\x0D\x0A?|\x0A)/gc) { + print STDOUT qq[
  2. ], htescape $1, + "
    3. \n"; $i++; } - if ($$s =~ /\G([^\x0A]+)/gc) { - print STDOUT qq[
  3. ], htescape $1, "
    4. \n"; + if ($$s =~ /\G([^\x0D\x0A]+)/gc) { + print STDOUT qq[
  4. ], htescape $1, + "
    5. \n"; } } else { - print STDOUT q[
  5. ]; + print STDOUT q[
  6. ]; } - print STDOUT "
"; + print STDOUT "
+"; } # print_input_string_section -sub print_document_tree ($) { - my $node = shift; +sub print_document_tree ($$) { + my ($input, $node) = @_; + my $r = '
    '; my @node = ($node); @@ -397,7 +740,7 @@ next; } - my $node_id = 'node-'.refaddr $child; + my $node_id = $input->{id_prefix} . 'node-'.refaddr $child; my $nt = $child->node_type; if ($nt == $child->ELEMENT_NODE) { my $child_nsuri = $child->namespace_uri; @@ -408,7 +751,7 @@ $r .= '
      '; for my $attr (sort {$a->[0] cmp $b->[0]} map { [$_->name, $_->value, $_->namespace_uri, 'node-'.refaddr $_] } @{$child->attributes}) { - $r .= qq[
    • ] . htescape ($attr->[0]) . ' = '; ## ISSUE: case? + $r .= qq[
    • ] . htescape ($attr->[0]) . ' = '; ## ISSUE: case? $r .= '' . htescape ($attr->[1]) . '
      • '; ## TODO: children } $r .= '
    '; @@ -477,33 +820,52 @@ print STDOUT $r; } # print_document_tree -sub print_structure_dump_dom_section ($$) { - my ($doc, $el) = @_; +sub print_structure_dump_dom_section ($$$) { + my ($input, $doc, $el) = @_; print STDOUT qq[ -
    +

    Document Tree

    ]; - push @nav, ['#document-tree' => 'Tree']; + push @nav, [qq[#$input->{id_prefix}document-tree] => 'Tree'] + unless $input->{nested}; - print_document_tree ($el || $doc); + print_document_tree ($input, $el || $doc); print STDOUT qq[
    ]; } # print_structure_dump_dom_section -sub print_structure_dump_manifest_section ($) { - my $manifest = shift; +sub print_structure_dump_cssom_section ($$) { + my ($input, $cssom) = @_; print STDOUT qq[ -
    +
    +

    Document Tree

    +]; + push @nav, [qq[#$input->{id_prefix}document-tree] => 'Tree'] + unless $input->{nested}; + + ## TODO: + print STDOUT "
    ".htescape ($cssom->css_text)."
    "; + + print STDOUT qq[
    ]; +} # print_structure_dump_cssom_section + +sub print_structure_dump_manifest_section ($$) { + my ($input, $manifest) = @_; + + print STDOUT qq[ +

    Cache Manifest

    ]; - push @nav, ['#dump-manifest' => 'Caceh Manifest']; + push @nav, [qq[#$input->{id_prefix}dump-manifest] => 'Cache Manifest'] + unless $input->{nested}; print STDOUT qq[
    Explicit entries
    ]; + my $i = 0; for my $uri (@{$manifest->[0]}) { my $euri = htescape ($uri); - print STDOUT qq[
    <$euri>
    ]; + print STDOUT qq[
    <$euri>
    ]; } print STDOUT qq[
    Fallback entries
    @@ -512,27 +874,28 @@ for my $uri (sort {$a cmp $b} keys %{$manifest->[1]}) { my $euri = htescape ($uri); my $euri2 = htescape ($manifest->[1]->{$uri}); - print STDOUT qq[<$euri> - <$euri2>]; + print STDOUT qq[<$euri> + <$euri2>]; } print STDOUT qq[
    Online whitelist
    ]; for my $uri (@{$manifest->[2]}) { my $euri = htescape ($uri); - print STDOUT qq[
    <$euri>
    ]; + print STDOUT qq[
    <$euri>
    ]; } print STDOUT qq[
    ]; } # print_structure_dump_manifest_section -sub print_structure_error_dom_section ($$$) { - my ($doc, $el, $result) = @_; +sub print_structure_error_dom_section ($$$$$) { + my ($input, $doc, $el, $result, $onsubdoc) = @_; - print STDOUT qq[
    + print STDOUT qq[

    Document Errors

    -
    ]; - push @nav, ['#document-errors' => 'Document Error']; +
    ]; + push @nav, [qq[#$input->{id_prefix}document-errors] => 'Document Error'] + unless $input->{nested}; require Whatpm::ContentChecker; my $onerror = sub { @@ -541,7 +904,7 @@ $type =~ tr/ /-/; $type =~ s/\|/%7C/g; $msg .= qq[ [Description]]; - print STDOUT qq[
    ] . get_error_label (\%opt) . + print STDOUT qq[
    ] . get_error_label ($input, \%opt) . qq[
    \n
    ], get_error_level_label (\%opt); print STDOUT $msg, "
    \n"; add_error ('structure', \%opt => $result); @@ -550,25 +913,31 @@ my $elements; my $time1 = time; if ($el) { - $elements = Whatpm::ContentChecker->check_element ($el, $onerror); + $elements = Whatpm::ContentChecker->check_element + ($el, $onerror, $onsubdoc); } else { - $elements = Whatpm::ContentChecker->check_document ($doc, $onerror); + $elements = Whatpm::ContentChecker->check_document + ($doc, $onerror, $onsubdoc); } $time{check} = time - $time1; - print STDOUT qq[
    ]; + print STDOUT qq[
+
]; return $elements; } # print_structure_error_dom_section sub print_structure_error_manifest_section ($$$) { - my ($manifest, $result) = @_; + my ($input, $manifest, $result) = @_; - print STDOUT qq[
+ print STDOUT qq[

Document Errors

]; - push @nav, ['#document-errors' => 'Document Error']; + push @nav, [qq[#$input->{id_prefix}document-errors] => 'Document Error'] + unless $input->{nested}; require Whatpm::CacheManifest; Whatpm::CacheManifest->check_manifest ($manifest, sub { @@ -577,7 +946,7 @@ $type =~ tr/ /-/; $type =~ s/\|/%7C/g; $msg .= qq[ [Description]]; - print STDOUT qq[
] . get_error_label (\%opt) . + print STDOUT qq[
] . get_error_label ($input, \%opt) . qq[
\n
], $msg, "
\n"; add_error ('structure', \%opt => $result); }); @@ -585,12 +954,13 @@ print STDOUT qq[
]; } # print_structure_error_manifest_section -sub print_table_section ($) { - my $tables = shift; +sub print_table_section ($$) { + my ($input, $tables) = @_; - push @nav, ['#tables' => 'Tables']; + push @nav, [qq[#$input->{id_prefix}tables] => 'Tables'] + unless $input->{nested}; print STDOUT qq[ -
+

Tables

@@ -603,16 +973,15 @@ require JSON; my $i = 0; - for my $table_el (@$tables) { + for my $table (@$tables) { $i++; - print STDOUT qq[

] . - get_node_link ($table_el) . q[

]; + print STDOUT qq[

] . + 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 $_->{element}; } @@ -638,68 +1007,132 @@ print STDOUT '
]; + print STDOUT qq[, document.getElementById ('$input->{id_prefix}table-$i')]; + print STDOUT qq[, '$input->{id_prefix}');]; } print STDOUT qq[
]; } # print_table_section -sub print_id_section ($) { - my $ids = shift; +sub print_listing_section ($$$) { + my ($opt, $input, $ids) = @_; - push @nav, ['#identifiers' => 'IDs']; + push @nav, ['#' . $input->{id_prefix} . $opt->{id} => $opt->{label}] + unless $input->{nested}; print STDOUT qq[ -
-

Identifiers

+
+

$opt->{heading}

]; for my $id (sort {$a cmp $b} keys %$ids) { print STDOUT qq[
@{[htescape $id]}
]; for (@{$ids->{$id}}) { - print STDOUT qq[
].get_node_link ($_).qq[
]; + print STDOUT qq[
].get_node_link ($input, $_).qq[
]; } } print STDOUT qq[
]; -} # print_id_section +} # print_listing_section + +sub print_uri_section ($$$) { + my ($input, $uris) = @_; -sub print_term_section ($) { - my $terms = shift; + ## 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, ['#terms' => 'Terms']; + push @nav, ['#' . $input->{id_prefix} . 'uris' => 'URIs'] + unless $input->{nested}; print STDOUT qq[ -
-

Terms

+
+

URIs

-
-]; - for my $term (sort {$a cmp $b} keys %$terms) { - print STDOUT qq[
@{[htescape $term]}
]; - for (@{$terms->{$term}}) { - print STDOUT qq[
].get_node_link ($_).qq[
]; +
]; + 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 %{$entry->{type}}; + print STDOUT ')'; + } } + print STDOUT qq[
]; } print STDOUT qq[
]; -} # print_term_section +} # print_uri_section -sub print_class_section ($) { - my $classes = shift; +sub print_rdf_section ($$$) { + my ($input, $rdfs) = @_; - push @nav, ['#classes' => 'Classes']; + push @nav, ['#' . $input->{id_prefix} . 'rdf' => 'RDF'] + unless $input->{nested}; print STDOUT qq[ -
-

Classes

+
+

RDF Triples

-
-]; - for my $class (sort {$a cmp $b} keys %$classes) { - print STDOUT qq[
@{[htescape $class]}
]; - for (@{$classes->{$class}}) { - print STDOUT qq[
].get_node_link ($_).qq[
]; +
]; + 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_class_section +} # 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 $result = shift; @@ -766,24 +1199,25 @@ print STDOUT qq[$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 @@ -797,7 +1231,7 @@ my $euri = htescape ($input->{uri}); print STDOUT qq[ -

+

Errors

@@ -810,7 +1244,8 @@
]; - push @nav, ['#parse-errors' => 'Errors']; + push @nav, [qq[#$input->{id_prefix}parse-errors] => 'Errors'] + unless $input->{nested}; add_error (char => {level => 'u'} => $result); add_error (syntax => {level => 'u'} => $result); add_error (structure => {level => 'u'} => $result); @@ -822,30 +1257,65 @@

Input Error: @{[htescape ($input->{error_status_text})]}

]; push @nav, ['#result-summary' => 'Result']; -} # print_Result_input_error_section +} # print_result_input_error_section -sub get_error_label ($) { - my $err = shift; +sub get_error_label ($$) { + my ($input, $err) = @_; 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 ($err->{node}); + $r .= get_node_link ($input, $err->{node}); } if (defined $err->{index}) { - $r .= ' ' if length $r; - $r .= 'Index ' . (0+$err->{index}); + if (length $r) { + $r .= ', Index ' . (0+$err->{index}); + } else { + $r .= "Index " + . (0+$err->{index}) . ''; + } } if (defined $err->{value}) { @@ -873,6 +1343,8 @@ } elsif ($err->{level} eq 'u' or $err->{level} eq 'unsupported') { $r = qq[Not supported: ]; + } elsif ($err->{level} eq 'i') { + $r = qq[Information: ]; } else { my $elevel = htescape ($err->{level}); $r = qq[$elevel: @@ -888,10 +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 . '"'; @@ -909,9 +1381,9 @@ return join '/', @r; } # get_node_path -sub get_node_link ($) { - return qq[] . - htescape (get_node_path ($_[0])) . qq[]; +sub get_node_link ($$) { + return qq[] . + htescape (get_node_path ($_[1])) . qq[]; } # get_node_link { @@ -969,6 +1441,17 @@ } +sub encode_uri_component ($) { + 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) = @_; @@ -1117,6 +1600,8 @@ return $r; } + $r->{inner_html_element} = $http->get_parameter ('e'); + return $r; } # get_input_document @@ -1149,11 +1634,11 @@ =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: 2008/02/10 02:05:30 $ +## $Date: 2008/05/18 03:47:56 $