--- test/html-webhacc/cc.cgi 2008/03/16 11:38:47 1.41 +++ test/html-webhacc/cc.cgi 2008/07/21 08:39:12 1.56 @@ -6,22 +6,13 @@ /home/wakaba/work/manakai2/lib]; use CGI::Carp qw[fatalsToBrowser]; use Scalar::Util qw[refaddr]; -use Time::HiRes qw/time/; -sub htescape ($) { - my $s = $_[0]; - $s =~ s/&/&/g; - $s =~ s//>/g; - $s =~ s/"/"/g; - $s =~ s{([\x00-\x09\x0B-\x1F\x7F-\xA0\x{FEFF}\x{FFFC}-\x{FFFF}])}{ - sprintf 'U+%04X', ord $1; - }ge; - return $s; -} # htescape + require WebHACC::Input; + require WebHACC::Result; + require WebHACC::Output; + +my $out; - my @nav; - my %time; require Message::DOM::DOMImplementation; my $dom = Message::DOM::DOMImplementation->new; { @@ -32,13 +23,14 @@ print STDOUT "Status: 404 Not Found\nContent-Type: text/plain; charset=us-ascii\n\n400"; exit; } - - binmode STDOUT, ':utf8'; - $| = 1; - + load_text_catalog ('en'); ## TODO: conneg - print STDOUT qq[Content-Type: text/html; charset=utf-8 + $out = WebHACC::Output->new; + $out->handle (*STDOUT); + $out->set_utf8; + $out->set_flush; + $out->html (qq[Content-Type: text/html; charset=utf-8 @@ -49,162 +41,87 @@

Web Document Conformance Checker (beta)

-]; +]); - $| = 0; my $input = get_input_document ($http, $dom); - my $char_length = 0; - print qq[ -
-
-
Request URI
-
<@{[htescape $input->{request_uri}]}>
-
Document URI
-
<@{[htescape $input->{uri}]}> -
-]; # no
yet - push @nav, ['#document-info' => 'Information']; - -if (defined $input->{s}) { - $char_length = length $input->{s}; - - print STDOUT qq[ -
Base URI
-
<@{[htescape $input->{base_uri}]}>
-
Internet Media Type
-
@{[htescape $input->{media_type}]} - @{[$input->{media_type_overridden} ? '(overridden)' : defined $input->{official_type} ? $input->{media_type} eq $input->{official_type} ? '' : '(sniffed; official type is: '.htescape ($input->{official_type}).')' : '(sniffed)']}
-
Character Encoding
-
@{[defined $input->{charset} ? ''.htescape ($input->{charset}).'' : '(none)']} - @{[$input->{charset_overridden} ? '(overridden)' : '']}
-
Length
-
$char_length byte@{[$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); -} else { - print STDOUT qq[]; - print_result_input_error_section ($input); -} + $out->input ($input); + $out->unset_flush; - print STDOUT qq[ - - - -]; - - for (qw/decode parse parse_html parse_xml parse_manifest - check check_manifest/) { - next unless defined $time{$_}; - open my $file, '>>', ".cc-$_.txt" or die ".cc-$_.txt: $!"; - print $file $char_length, "\t", $time{$_}, "\n"; - } + my $result = WebHACC::Result->new; + $result->output ($out); + $result->{conforming_min} = 1; + $result->{conforming_max} = 1; + + $out->html (''); + + check_and_print ($input => $result => $out); + + $result->generate_result_section; -exit; + $out->nav_list; + + exit; } -sub add_error ($$$) { - my ($layer, $err, $result) = @_; - if (defined $err->{level}) { - if ($err->{level} eq 's') { - $result->{$layer}->{should}++; - $result->{$layer}->{score_min} -= 2; - $result->{conforming_min} = 0; - } elsif ($err->{level} eq 'w' or $err->{level} eq 'g') { - $result->{$layer}->{warning}++; - } elsif ($err->{level} eq 'u' or $err->{level} eq 'unsupported') { - $result->{$layer}->{unsupported}++; - $result->{unsupported} = 1; - } elsif ($err->{level} eq 'i') { - # - } else { - $result->{$layer}->{must}++; - $result->{$layer}->{score_max} -= 2; - $result->{$layer}->{score_min} -= 2; - $result->{conforming_min} = 0; - $result->{conforming_max} = 0; - } - } else { - $result->{$layer}->{must}++; - $result->{$layer}->{score_max} -= 2; - $result->{$layer}->{score_min} -= 2; +sub check_and_print ($$$) { + 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}) { $result->{conforming_min} = 0; - $result->{conforming_max} = 0; + return; } -} # add_error -sub check_and_print ($$) { - my ($input, $result) = @_; + 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" - print_http_header_section ($input, $result); + $checker->generate_syntax_error_section; + $checker->generate_source_string_section; - my $doc; - my $el; - my $cssom; - my $manifest; my @subdoc; + $checker->onsubdoc (sub { + push @subdoc, shift; + }); - if ($input->{media_type} eq 'text/html') { - ($doc, $el) = print_syntax_error_html_section ($input, $result); - print_source_string_section - ($input, - \($input->{s}), - $input->{charset} || $doc->input_encoding); - } elsif ({ - 'text/xml' => 1, - 'application/atom+xml' => 1, - 'application/rss+xml' => 1, - 'application/svg+xml' => 1, - 'application/xhtml+xml' => 1, - 'application/xml' => 1, - }->{$input->{media_type}}) { - ($doc, $el) = print_syntax_error_xml_section ($input, $result); - print_source_string_section ($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, \($input->{s}), - 'utf-8'); - } else { - ## TODO: Change HTTP status code?? - print_result_unknown_type_section ($input, $result); - } + $checker->generate_structure_dump_section; + $checker->generate_structure_error_section; + $checker->generate_additional_sections; + +=pod if (defined $doc or defined $el) { - $doc->document_uri ($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}}; @@ -214,1015 +131,34 @@ print_listing_section ({ id => 'classes', label => 'Classes', heading => 'Classes', }, $input, $elements->{class}) if keys %{$elements->{class}}; - } elsif (defined $cssom) { - print_structure_dump_cssom_section ($input, $cssom); - ## TODO: CSSOM validation - add_error ('structure', {level => 'u'} => $result); - } elsif (defined $manifest) { - print_structure_dump_manifest_section ($input, $manifest); - print_structure_error_manifest_section ($input, $manifest, $result); + + print_rdf_section ($input, $elements->{rdf}) if @{$elements->{rdf}}; } +=cut + my $id_prefix = 0; - for my $subinput (@subdoc) { - $subinput->{id_prefix} = 'subdoc-' . ++$id_prefix; - $subinput->{nested} = 1; + 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}; - 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->{parent_input} = $input; - $subinput->{id_prefix} .= '-'; - check_and_print ($subinput => $result); - - print STDOUT qq[
]; + $subinput->start_section ($result); + check_and_print ($subinput => $result => $out); + $subinput->end_section ($result); } -} # check_and_print -sub print_http_header_section ($$) { - my ($input, $result) = @_; - return unless defined $input->{header_status_code} or - defined $input->{header_status_text} or - @{$input->{header_field} or []}; - - push @nav, ['#source-header' => 'HTTP Header'] unless $input->{nested}; - print STDOUT qq[
-

HTTP Header

- -

Note: Due to the limitation of the -network library in use, the content of this section might -not be the real header.

- - -]; - - if (defined $input->{header_status_code}) { - print STDOUT qq[]; - print STDOUT qq[]; - } - if (defined $input->{header_status_text}) { - print STDOUT qq[]; - print STDOUT qq[]; - } - - for (@{$input->{header_field}}) { - print STDOUT qq[]; - print STDOUT qq[]; - } - - print STDOUT qq[
Status code@{[htescape ($input->{header_status_code})]}
Status text@{[htescape ($input->{header_status_text})]}
@{[htescape ($_->[0])]}@{[htescape ($_->[1])]}
]; -} # print_http_header_section - -sub print_syntax_error_html_section ($$) { - my ($input, $result) = @_; - - require Encode; - require Whatpm::HTML; - - print STDOUT qq[ -
-

Parse Errors

- -
]; - push @nav, ['#parse-errors' => 'Parse Error'] unless $input->{nested}; - - my $onerror = sub { - my (%opt) = @_; - my ($type, $cls, $msg) = get_text ($opt{type}, $opt{level}); - print STDOUT qq[
], get_error_label ($input, \%opt), - qq[
]; - $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); - }; - - my $doc = $dom->create_document; - my $el; - 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}); - $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); - $time{parse} = time - $time1; - } else { - my $time1 = time; - Whatpm::HTML->parse_byte_string - ($input->{charset}, $input->{s} => $doc, $onerror); - $time{parse_html} = time - $time1; - } - $doc->manakai_charset ($input->{official_charset}) - if defined $input->{official_charset}; - - print STDOUT qq[
]; - - return ($doc, $el); -} # print_syntax_error_html_section - -sub print_syntax_error_xml_section ($$) { - my ($input, $result) = @_; - - require Message::DOM::XMLParserTemp; - - print STDOUT qq[ -
-

Parse Errors

- -
]; - 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 $err->location->column_number, "
"; - print STDOUT htescape $err->text, "
\n"; - - add_error ('syntax', {type => $err->text, - level => [ - $err->SEVERITY_FATAL_ERROR => 'm', - $err->SEVERITY_ERROR => 'm', - $err->SEVERITY_WARNING => 's', - ]->[$err->severity]} => $result); - - return 1; - }; - - my $time1 = time; - open my $fh, '<', \($input->{s}); - my $doc = Message::DOM::XMLParserTemp->parse_byte_stream - ($fh => $dom, $onerror, charset => $input->{charset}); - $time{parse_xml} = time - $time1; - $doc->manakai_charset ($input->{official_charset}) - if defined $input->{official_charset}; - - print STDOUT qq[
]; - - return ($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'] unless $input->{nested}; - - my $onerror = sub { - my (%opt) = @_; - my ($type, $cls, $msg) = get_text ($opt{type}, $opt{level}); - print STDOUT qq[
], get_error_label ($input, \%opt), - qq[
]; - $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); - }; - - my $time1 = time; - my $manifest = Whatpm::CacheManifest->parse_byte_string - ($input->{s}, $input->{uri}, $input->{base_uri}, $onerror); - $time{parse_manifest} = time - $time1; - - print STDOUT qq[
]; - - return $manifest; -} # print_syntax_error_manifest_section - -sub print_source_string_section ($$$) { - 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; - - $s = \($enc->decode (${$_[0]})); - } else { - $s = $_[0]; - } - - my $i = 1; - push @nav, ['#source-string' => 'Source'] unless $input->{nested}; - print STDOUT qq[
-

Document Source

-
    \n]; - if (length $$s) { - while ($$s =~ /\G([^\x0D\x0A]*?)(?>\x0D\x0A?|\x0A)/gc) { - print STDOUT qq[
  1. ], htescape $1, - "
  2. \n"; - $i++; - } - if ($$s =~ /\G([^\x0D\x0A]+)/gc) { - print STDOUT qq[
  3. ], htescape $1, - "
  4. \n"; - } - } else { - print STDOUT q[
  5. ]; - } - print STDOUT "
-"; -} # print_input_string_section - -sub print_document_tree ($$) { - my ($input, $node) = @_; - - my $r = '
    '; - - my @node = ($node); - while (@node) { - my $child = shift @node; - unless (ref $child) { - $r .= $child; - next; - } - - 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; - $r .= qq[
  1. ] . htescape ($child->tag_name) . - ''; ## ISSUE: case - - if ($child->has_attributes) { - $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? - $r .= '' . htescape ($attr->[1]) . '
    • '; ## TODO: children - } - $r .= '
    '; - } - - if ($child->has_child_nodes) { - $r .= '
      '; - unshift @node, @{$child->child_nodes}, '
  2. '; - } else { - $r .= ''; - } - } elsif ($nt == $child->TEXT_NODE) { - $r .= qq'
  3. ' . htescape ($child->data) . '
  4. '; - } elsif ($nt == $child->CDATA_SECTION_NODE) { - $r .= qq'
  5. <[CDATA[' . htescape ($child->data) . ']]>
  6. '; - } elsif ($nt == $child->COMMENT_NODE) { - $r .= qq'
  7. <!--' . htescape ($child->data) . '-->
  8. '; - } elsif ($nt == $child->DOCUMENT_NODE) { - $r .= qq'
  9. Document'; - $r .= qq[
      ]; - my $cp = $child->manakai_charset; - if (defined $cp) { - $r .= qq[
    • charset parameter = ]; - $r .= htescape ($cp) . qq[
    • ]; - } - $r .= qq[
    • inputEncoding = ]; - my $ie = $child->input_encoding; - if (defined $ie) { - $r .= qq[@{[htescape ($ie)]}]; - if ($child->manakai_has_bom) { - $r .= qq[ (with BOM)]; - } - } else { - $r .= qq[(null)]; - } - $r .= qq[
    • @{[scalar get_text ('manakaiIsHTML:'.($child->manakai_is_html?1:0))]}
    • ]; - $r .= qq[
    • @{[scalar get_text ('manakaiCompatMode:'.$child->manakai_compat_mode)]}
    • ]; - unless ($child->manakai_is_html) { - $r .= qq[
    • XML version = @{[htescape ($child->xml_version)]}
    • ]; - if (defined $child->xml_encoding) { - $r .= qq[
    • XML encoding = @{[htescape ($child->xml_encoding)]}
    • ]; - } else { - $r .= qq[
    • XML encoding = (null)
    • ]; - } - $r .= qq[
    • XML standalone = @{[$child->xml_standalone ? 'true' : 'false']}
    • ]; - } - $r .= qq[
    ]; - if ($child->has_child_nodes) { - $r .= '
      '; - unshift @node, @{$child->child_nodes}, '
  10. '; - } - } elsif ($nt == $child->DOCUMENT_TYPE_NODE) { - $r .= qq'
  11. <!DOCTYPE>
      '; - $r .= qq[
    • Name = @{[htescape ($child->name)]}
    • ]; - $r .= qq[
    • Public identifier = @{[htescape ($child->public_id)]}
    • ]; - $r .= qq[
    • System identifier = @{[htescape ($child->system_id)]}
    • ]; - $r .= '
  12. '; - } elsif ($nt == $child->PROCESSING_INSTRUCTION_NODE) { - $r .= qq'
  13. <?@{[htescape ($child->target)]} @{[htescape ($child->data)]}?>
  14. '; - } else { - $r .= qq'
  15. @{[$child->node_type]} @{[htescape ($child->node_name)]}
  16. '; # error - } - } - - $r .= '
'; - print STDOUT $r; -} # print_document_tree - -sub print_structure_dump_dom_section ($$$) { - my ($input, $doc, $el) = @_; - - print STDOUT qq[ -
-

Document Tree

-]; - push @nav, [qq[#$input->{id_prefix}document-tree] => 'Tree'] - unless $input->{nested}; - - print_document_tree ($input, $el || $doc); - - print STDOUT qq[
]; -} # print_structure_dump_dom_section - -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, [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[
Fallback entries
- - ]; - for my $uri (sort {$a cmp $b} keys %{$manifest->[1]}) { - my $euri = htescape ($uri); - my $euri2 = htescape ($manifest->[1]->{$uri}); - print STDOUT qq[ - ]; - } - - print STDOUT qq[
Oppotunistic Caching NamespaceFallback Entry
<$euri><$euri2>
Online whitelist
]; - for my $uri (@{$manifest->[2]}) { - my $euri = htescape ($uri); - print STDOUT qq[
<$euri>
]; - } - - print STDOUT qq[
]; -} # print_structure_dump_manifest_section - -sub print_structure_error_dom_section ($$$$$) { - my ($input, $doc, $el, $result, $onsubdoc) = @_; - - print STDOUT qq[
-

Document Errors

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

Document Errors

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

Tables

- - - - -]; - - require JSON; - - my $i = 0; - for my $table_el (@$tables) { - $i++; - print STDOUT qq[

] . - get_node_link ($input, $table_el) . 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}) { - next unless $_; - delete $_->{element}; - } - - for (@{$table->{row_group}}) { - next unless $_; - next unless $_->{element}; - $_->{type} = $_->{element}->manakai_local_name; - delete $_->{element}; - } - - for (@{$table->{cell}}) { - next unless $_; - for (@{$_}) { - next unless $_; - for (@$_) { - $_->{id} = refaddr $_->{element} if defined $_->{element}; - delete $_->{element}; - $_->{is_header} = $_->{is_header} ? 1 : 0; - } - } - } - - print STDOUT '
]; - } - - print STDOUT qq[
]; -} # print_table_section - -sub print_listing_section ($$$) { - my ($opt, $input, $ids) = @_; - - push @nav, ['#' . $input->{id_prefix} . $opt->{id} => $opt->{label}] - unless $input->{nested}; - print STDOUT qq[ -
-

$opt->{heading}

- -
-]; - for my $id (sort {$a cmp $b} keys %$ids) { - print STDOUT qq[
@{[htescape $id]}
]; - for (@{$ids->{$id}}) { - print STDOUT qq[
].get_node_link ($input, $_).qq[
]; - } - } - print STDOUT qq[
]; -} # print_listing_section - -sub print_result_section ($) { - my $result = shift; - - print STDOUT qq[ -
-

Result

]; - - if ($result->{unsupported} and $result->{conforming_max}) { - print STDOUT qq[

The conformance - checker cannot decide whether the document is conforming or - not, since the document contains one or more unsupported - features. The document might or might not be conforming.

]; - } elsif ($result->{conforming_min}) { - print STDOUT qq[

No conformance-error is - found in this document.

]; - } elsif ($result->{conforming_max}) { - print STDOUT qq[

This document - is likely non-conforming, but in rare case - it might be conforming.

]; - } else { - print STDOUT qq[

This document is - non-conforming.

]; - } - - print STDOUT qq[ -- - - - - -]; - - my $must_error = 0; - my $should_error = 0; - my $warning = 0; - my $score_min = 0; - my $score_max = 0; - my $score_base = 20; - my $score_unit = $score_base / 100; - for ( - [Transfer => 'transfer', ''], - [Character => 'char', ''], - [Syntax => 'syntax', '#parse-errors'], - [Structure => 'structure', '#document-errors'], - ) { - $must_error += ($result->{$_->[1]}->{must} += 0); - $should_error += ($result->{$_->[1]}->{should} += 0); - $warning += ($result->{$_->[1]}->{warning} += 0); - $score_min += (($result->{$_->[1]}->{score_min} *= $score_unit) += $score_base); - $score_max += (($result->{$_->[1]}->{score_max} *= $score_unit) += $score_base); - - my $uncertain = $result->{$_->[1]}->{unsupported} ? '?' : ''; - my $label = $_->[0]; - if ($result->{$_->[1]}->{must} or - $result->{$_->[1]}->{should} or - $result->{$_->[1]}->{warning} or - $result->{$_->[1]}->{unsupported}) { - $label = qq[$label]; - } - - print STDOUT qq[]; - if ($uncertain) { - print qq[]; - } elsif ($result->{$_->[1]}->{score_min} != $result->{$_->[1]}->{score_max}) { - print qq[]; - } else { - print qq[]; - } - } - - $score_max += $score_base; - - print STDOUT qq[ - - - - - - - -
MUST‐level -ErrorsSHOULD‐level -ErrorsWarningsScore
$label$result->{$_->[1]}->{must}$uncertain$result->{$_->[1]}->{should}$uncertain$result->{$_->[1]}->{warning}$uncertain−∞..$result->{$_->[1]}->{score_max}$result->{$_->[1]}->{score_min}..$result->{$_->[1]}->{score_max}
$result->{$_->[1]}->{score_min}
Semantics0?0?0?−∞..$score_base
Total$must_error?$should_error?$warning?−∞..$score_max
- -

Important: This conformance checking service -is under development. The result above might be wrong.

-
]; - push @nav, ['#result-summary' => 'Result']; -} # print_result_section - -sub print_result_unknown_type_section ($$) { - my ($input, $result) = @_; - - my $euri = htescape ($input->{uri}); - print STDOUT qq[ -
-

Errors

- -
-
<$euri>
-
Not - supported: - Media type - @{[htescape $input->{media_type}]} - is not supported.
-
-
-]; - push @nav, [qq[#$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'} => $result); -} # print_result_unknown_type_section - -sub print_result_input_error_section ($) { - my $input = shift; - print STDOUT qq[
-

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

-
]; - push @nav, ['#result-summary' => 'Result']; -} # print_result_input_error_section - -sub get_error_label ($$) { - my ($input, $err) = @_; - - my $r = ''; - - if (defined $err->{token} and defined $err->{token}->{line}) { - if ($err->{token}->{column} > 0) { - $r = qq[Line $err->{token}->{line} column $err->{token}->{column}]; - } else { - $err->{token}->{line} = $err->{token}->{line} - 1 || 1; - $r = qq[Line $err->{token}->{line}]; - } - } elsif (defined $err->{line}) { - if ($err->{column} > 0) { - $r = qq[Line $err->{line} column $err->{column}]; - } else { - $err->{line} = $err->{line} - 1 || 1; - $r = qq[Line $err->{line}]; - } - } - - if (defined $err->{node}) { - $r .= ' ' if length $r; - $r = get_node_link ($input, $err->{node}); - } - - if (defined $err->{index}) { - if (length $r) { - $r .= ', Index ' . (0+$err->{index}); - } else { - $r .= "Index " - . (0+$err->{index}) . ''; - } - } - - if (defined $err->{value}) { - $r .= ' ' if length $r; - $r .= '' . htescape ($err->{value}) . ''; - } - - return $r; -} # get_error_label - -sub get_error_level_label ($) { - my $err = shift; - - my $r = ''; - - if (not defined $err->{level} or $err->{level} eq 'm') { - $r = qq[MUST‐level - error: ]; - } elsif ($err->{level} eq 's') { - $r = qq[SHOULD‐level - error: ]; - } elsif ($err->{level} eq 'w') { - $r = qq[Warning: - ]; - } 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: - ]; - } - - return $r; -} # get_error_level_label - -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) { - @r = ('') unless @r; - $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 -sub get_node_link ($$) { - return qq[] . - htescape (get_node_path ($_[1])) . qq[]; -} # get_node_link { my $Msg = {}; sub load_text_catalog ($) { +# my $self = shift; my $lang = shift; # MUST be a canonical lang name open my $file, '<:utf8', "cc-msg.$lang.txt" or die "$0: cc-msg.$lang.txt: $!"; @@ -1235,7 +171,8 @@ } } # load_text_catalog -sub get_text ($) { +sub get_text ($;$$) { +# my $self = shift; my ($type, $level, $node) = @_; $type = $level . ':' . $type if defined $level; $level = 'm' unless defined $level; @@ -1244,24 +181,24 @@ if (defined $Msg->{$type}) { my $msg = $Msg->{$type}->[1]; $msg =~ s{\$([0-9]+)}{ - defined $arg[$1] ? htescape ($arg[$1]) : '(undef)'; - }ge; + defined $arg[$1] ? ($arg[$1]) : '(undef)'; + }ge; ##BUG: ^ must be escaped $msg =~ s{{\@([A-Za-z0-9:_.-]+)}}{ UNIVERSAL::can ($node, 'get_attribute_ns') - ? htescape ($node->get_attribute_ns (undef, $1)) : '' - }ge; - $msg =~ s{{\@}}{ - UNIVERSAL::can ($node, 'value') ? htescape ($node->value) : '' + ? ($node->get_attribute_ns (undef, $1)) : '' + }ge; ## BUG: ^ must be escaped + $msg =~ s{{\@}}{ ## BUG: v must be escaped + UNIVERSAL::can ($node, 'value') ? ($node->value) : '' }ge; $msg =~ s{{local-name}}{ UNIVERSAL::can ($node, 'manakai_local_name') - ? htescape ($node->manakai_local_name) : '' - }ge; + ? ($node->manakai_local_name) : '' + }ge; ## BUG: ^ must be escaped $msg =~ s{{element-local-name}}{ (UNIVERSAL::can ($node, 'owner_element') and $node->owner_element) - ? htescape ($node->owner_element->manakai_local_name) - : '' + ? ($node->owner_element->manakai_local_name) + : '' ## BUG: ^ must be escaped }ge; return ($type, 'level-' . $level . ' ' . $Msg->{$type}->[0], $msg); } elsif ($type =~ s/:([^:]*)$//) { @@ -1269,7 +206,8 @@ redo; } } - return ($type, 'level-'.$level, htescape ($_[0])); + return ($type, 'level-'.$level, ($_[0])); + ## BUG: ^ must be escaped } # get_text } @@ -1277,15 +215,18 @@ sub get_input_document ($$) { my ($http, $dom) = @_; - my $request_uri = $http->get_parameter ('uri'); - my $r = {}; + require Encode; + my $request_uri = Encode::decode ('utf-8', $http->get_parameter ('uri')); + my $r = WebHACC::Input->new; if (defined $request_uri and length $request_uri) { my $uri = $dom->create_uri_reference ($request_uri); unless ({ http => 1, }->{lc $uri->uri_scheme}) { - return {uri => $request_uri, request_uri => $request_uri, - error_status_text => 'URI scheme not allowed'}; + $r = WebHACC::Input::Error->new; + $r->{uri} = $request_uri; + $r->{request_uri} = $request_uri; + $r->{error_status_text} = 'URL scheme not allowed'; } require Message::Util::HostPermit; @@ -1312,8 +253,11 @@ Allow host=* EOH unless ($host_permit->check ($uri->uri_host, $uri->uri_port || 80)) { - return {uri => $request_uri, request_uri => $request_uri, - error_status_text => 'Connection to the host is forbidden'}; + my $r = WebHACC::Input::Error->new; + $r->{uri} = $request_uri; + $r->{request_uri} = $request_uri; + $r->{error_status_text} = 'Connection to the host is forbidden'; + return $r; } require LWP::UserAgent; @@ -1463,4 +407,4 @@ =cut -## $Date: 2008/03/16 11:38:47 $ +## $Date: 2008/07/21 08:39:12 $