--- test/html-webhacc/cc.cgi 2007/09/02 07:59:01 1.17
+++ test/html-webhacc/cc.cgi 2007/09/10 11:51:09 1.19
@@ -54,8 +54,6 @@
my $inner_html_element = $http->get_parameter ('e');
my $char_length = 0;
my %time;
- my $time1;
- my $time2;
print qq[
@@ -85,60 +83,14 @@
];
- print_http_header_section ($input);
+ my $result = {};
+ print_http_header_section ($input, $result);
my $doc;
my $el;
if ($input->{media_type} eq 'text/html') {
- require Encode;
- require Whatpm::HTML;
-
- $input->{charset} ||= 'ISO-8859-1'; ## TODO: for now.
-
- $time1 = time;
- my $t = Encode::decode ($input->{charset}, $input->{s});
- $time2 = time;
- $time{decode} = $time2 - $time1;
-
- print STDOUT qq[
-
-
Parse Errors
-
-
];
- push @nav, ['#parse-errors' => 'Parse Error'];
-
- 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];
- }
- $type =~ tr/ /-/;
- $type =~ s/\|/%7C/g;
- $msg .= qq[ [Description]];
- print STDOUT qq[- $msg
\n];
- };
-
- $doc = $dom->create_document;
- $time1 = time;
- if (defined $inner_html_element and length $inner_html_element) {
- $el = $doc->create_element_ns
- ('http://www.w3.org/1999/xhtml', [undef, $inner_html_element]);
- Whatpm::HTML->set_inner_html ($el, $t, $onerror);
- } else {
- Whatpm::HTML->parse_string ($t => $doc, $onerror);
- }
- $time2 = time;
- $time{parse} = $time2 - $time1;
-
- print STDOUT qq[
-
-];
-
+ ($doc, $el) = print_syntax_error_html_section ($input, $result);
print_source_string_section (\($input->{s}), $input->{charset});
} elsif ({
'text/xml' => 1,
@@ -148,211 +100,26 @@
'application/xhtml+xml' => 1,
'application/xml' => 1,
}->{$input->{media_type}}) {
- require Message::DOM::XMLParserTemp;
-
- print STDOUT qq[
-
-
Parse Errors
-
-
];
- push @nav, ['#parse-errors' => 'Parse Error'];
-
- 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";
- return 1;
- };
-
- $time1 = time;
- open my $fh, '<', \($input->{s});
- $doc = Message::DOM::XMLParserTemp->parse_byte_stream
- ($fh => $dom, $onerror, charset => $input->{charset});
- $time2 = time;
- $time{parse_xml} = $time2 - $time1;
-
- print STDOUT qq[
-
-
-];
+ ($doc, $el) = print_syntax_error_xml_section ($input, $result);
print_source_string_section (\($input->{s}), $doc->input_encoding);
} else {
## TODO: Change HTTP status code??
- print STDOUT qq[
-
-
Media type @{[htescape $input->{media_type}]}
is not supported!
-
-];
- push @nav, ['#result-summary' => 'Result'];
+ print_result_unknown_type_section ($input);
}
-
if (defined $doc or defined $el) {
- print STDOUT qq[
-
-
Document Tree
-];
- push @nav, ['#document-tree' => 'Tree'];
-
- print_document_tree ($el || $doc);
-
- print STDOUT qq[
-
-
-
-
Document Errors
-
-
];
- push @nav, ['#document-errors' => 'Document Error'];
-
- 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;
- $msg .= qq[ [Description]];
- print STDOUT qq[- ] . get_node_link ($opt{node}) .
- qq[
\n- ], $msg, "
\n";
- };
-
- $time1 = time;
- my $elements;
- if ($el) {
- $elements = Whatpm::ContentChecker->check_element ($el, $onerror);
- } else {
- $elements = Whatpm::ContentChecker->check_document ($doc, $onerror);
- }
- $time2 = time;
- $time{check} = $time2 - $time1;
-
- print STDOUT qq[
-
-];
-
- if (@{$elements->{table}}) {
- require JSON;
-
- push @nav, ['#tables' => 'Tables'];
- print STDOUT qq[
-
-
Tables
-
-
-
-
-];
-
- my $i = 0;
- for my $table_el (@{$elements->{table}}) {
- $i++;
- print STDOUT qq[
] .
- get_node_link ($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} = $_->{is_header} ? 1 : 0;
- }
- }
- }
-
- print STDOUT '];
- }
-
- print STDOUT qq[
];
- }
-
- if (keys %{$elements->{id}}) {
- push @nav, ['#identifiers' => 'IDs'];
- print STDOUT qq[
-
-
Identifiers
-
-
-];
- for my $id (sort {$a cmp $b} keys %{$elements->{id}}) {
- print STDOUT qq[@{[htescape $id]}
];
- for (@{$elements->{id}->{$id}}) {
- print STDOUT qq[- ].get_node_link ($_).qq[
];
- }
- }
- print STDOUT qq[
];
- }
-
- if (keys %{$elements->{term}}) {
- push @nav, ['#terms' => 'Terms'];
- print STDOUT qq[
-
-
Terms
-
-
-];
- for my $term (sort {$a cmp $b} keys %{$elements->{term}}) {
- print STDOUT qq[- @{[htescape $term]}
];
- for (@{$elements->{term}->{$term}}) {
- print STDOUT qq[- ].get_node_link ($_).qq[
];
- }
- }
- print STDOUT qq[
];
- }
-
- if (keys %{$elements->{class}}) {
- push @nav, ['#classes' => 'Classes'];
- print STDOUT qq[
-
-
Classes
-
-
-];
- for my $class (sort {$a cmp $b} keys %{$elements->{class}}) {
- print STDOUT qq[@{[htescape $class]}
];
- for (@{$elements->{class}->{$class}}) {
- print STDOUT qq[- ].get_node_link ($_).qq[
];
- }
- }
- print STDOUT qq[
];
- }
+ print_structure_dump_section ($doc, $el);
+ my $elements = print_structure_error_section ($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 %{$elements->{class}};
}
- ## TODO: Show result
+ print_result_section ($result);
} else {
- print STDOUT qq[
-
-
-
-
-
Input Error: @{[htescape ($input->{error_status_text})]}
-
-];
- push @nav, ['#result-summary' => 'Result'];
-
+ print STDOUT qq[];
+ print_result_input_error_section ($input);
}
print STDOUT qq[
@@ -375,8 +142,36 @@
exit;
-sub print_http_header_section ($) {
- my $input = shift;
+sub add_error ($$$) {
+ my ($layer, $err, $result) = @_;
+ if (defined $err->{level}) {
+ if ($err->{level} eq 's') {
+ $result->{$layer}->{should}++;
+ $result->{$layer}->{score_min} -= 2;
+ $result->{conforming_min} = 0;
+ } elsif ($err->{level} eq 'w' or $err->{level} eq 'g') {
+ $result->{$layer}->{warning}++;
+ } elsif ($err->{level} eq 'unsupported') {
+ $result->{$layer}->{unsupported}++;
+ $result->{unsupported} = 1;
+ } else {
+ $result->{$layer}->{must}++;
+ $result->{$layer}->{score_max} -= 2;
+ $result->{$layer}->{score_min} -= 2;
+ $result->{conforming_min} = 0;
+ $result->{conforming_max} = 0;
+ }
+ } else {
+ $result->{$layer}->{must}++;
+ $result->{$layer}->{score_max} -= 2;
+ $result->{$layer}->{score_min} -= 2;
+ $result->{conforming_min} = 0;
+ $result->{conforming_max} = 0;
+ }
+} # add_error
+
+sub print_http_header_section ($$) {
+ my ($input, $result) = @_;
return unless defined $input->{header_status_code} or
defined $input->{header_status_text} or
@{$input->{header_field}};
@@ -409,6 +204,99 @@
print STDOUT qq[];
} # print_http_header_section
+sub print_syntax_error_html_section ($$) {
+ my ($input, $result) = @_;
+
+ require Encode;
+ require Whatpm::HTML;
+
+ $input->{charset} ||= 'ISO-8859-1'; ## TODO: for now.
+
+ my $time1 = time;
+ my $t = Encode::decode ($input->{charset}, $input->{s});
+ $time{decode} = time - $time1;
+
+ print STDOUT qq[
+
+
Parse Errors
+
+
];
+ push @nav, ['#parse-errors' => 'Parse Error'];
+
+ my $onerror = sub {
+ my (%opt) = @_;
+ my ($type, $cls, $msg) = get_text ($opt{type}, $opt{level});
+ if ($opt{column} > 0) {
+ print STDOUT qq[- Line $opt{line} column $opt{column}
\n];
+ } else {
+ $opt{line} = $opt{line} - 1 || 1;
+ print STDOUT qq[- Line $opt{line}
\n];
+ }
+ $type =~ tr/ /-/;
+ $type =~ s/\|/%7C/g;
+ $msg .= qq[ [Description]];
+ print STDOUT qq[- $msg
\n];
+
+ add_error ('syntax', \%opt => $result);
+ };
+
+ my $doc = $dom->create_document;
+ my $el;
+ $time1 = time;
+ if (defined $inner_html_element and length $inner_html_element) {
+ $el = $doc->create_element_ns
+ ('http://www.w3.org/1999/xhtml', [undef, $inner_html_element]);
+ Whatpm::HTML->set_inner_html ($el, $t, $onerror);
+ } else {
+ Whatpm::HTML->parse_string ($t => $doc, $onerror);
+ }
+ $time{parse} = time - $time1;
+
+ print STDOUT qq[
];
+
+ return ($doc, $el);
+} # print_syntax_error_html_section
+
+sub print_syntax_error_xml_section ($$) {
+ my ($input, $result) = @_;
+
+ require Message::DOM::XMLParserTemp;
+
+ print STDOUT qq[
+
+
Parse Errors
+
+
];
+ push @nav, ['#parse-errors' => 'Parse Error'];
+
+ 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 - $time1;
+
+ print STDOUT qq[
];
+
+ return ($doc, undef);
+} # print_syntax_error_xml_section
+
sub print_source_string_section ($$) {
require Encode;
my $enc = Encode::find_encoding ($_[1]); ## TODO: charset name -> Perl name
@@ -511,6 +399,273 @@
print STDOUT $r;
} # print_document_tree
+sub print_structure_dump_section ($$) {
+ my ($doc, $el) = @_;
+
+ print STDOUT qq[
+
+
Document Tree
+];
+ push @nav, ['#document-tree' => 'Tree'];
+
+ print_document_tree ($el || $doc);
+
+ print STDOUT qq[];
+} # print_structure_dump_section
+
+sub print_structure_error_section ($$$) {
+ my ($doc, $el, $result) = @_;
+
+ print STDOUT qq[
+
Document Errors
+
+
];
+ push @nav, ['#document-errors' => 'Document Error'];
+
+ 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;
+ $msg .= qq[ [Description]];
+ print STDOUT qq[- ] . get_node_link ($opt{node}) .
+ qq[
\n- ], $msg, "
\n";
+ add_error ('structure', \%opt => $result);
+ };
+
+ my $elements;
+ my $time1 = time;
+ if ($el) {
+ $elements = Whatpm::ContentChecker->check_element ($el, $onerror);
+ } else {
+ $elements = Whatpm::ContentChecker->check_document ($doc, $onerror);
+ }
+ $time{check} = time - $time1;
+
+ print STDOUT qq[
];
+
+ return $elements;
+} # print_structure_error_section
+
+sub print_table_section ($) {
+ my $tables = shift;
+
+ push @nav, ['#tables' => 'Tables'];
+ print STDOUT qq[
+
+
Tables
+
+
+
+
+];
+
+ require JSON;
+
+ my $i = 0;
+ for my $table_el (@$tables) {
+ $i++;
+ print STDOUT qq[
] .
+ get_node_link ($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} = $_->{is_header} ? 1 : 0;
+ }
+ }
+ }
+
+ print STDOUT '];
+ }
+
+ print STDOUT qq[
];
+} # print_table_section
+
+sub print_id_section ($) {
+ my $ids = shift;
+
+ push @nav, ['#identifiers' => 'IDs'];
+ print STDOUT qq[
+
+
Identifiers
+
+
+];
+ 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[
];
+} # print_id_section
+
+sub print_term_section ($) {
+ my $terms = shift;
+
+ push @nav, ['#terms' => 'Terms'];
+ print STDOUT qq[
+
+
Terms
+
+
+];
+ for my $term (sort {$a cmp $b} keys %$terms) {
+ print STDOUT qq[- @{[htescape $term]}
];
+ for (@{$terms->{$term}}) {
+ print STDOUT qq[- ].get_node_link ($_).qq[
];
+ }
+ }
+ print STDOUT qq[
];
+} # print_term_section
+
+sub print_class_section ($) {
+ my $classes = shift;
+
+ push @nav, ['#classes' => 'Classes'];
+ print STDOUT qq[
+
+
Classes
+
+
+];
+ for my $class (sort {$a cmp $b} keys %$classes) {
+ print STDOUT qq[@{[htescape $class]}
];
+ for (@{$classes->{$class}}) {
+ print STDOUT qq[- ].get_node_link ($_).qq[
];
+ }
+ }
+ print STDOUT qq[
];
+} # print_class_section
+
+sub print_result_section ($) {
+ my $result = shift;
+
+ print STDOUT qq[
+
+
Result
];
+
+ if ($result->{unsupported}) {
+ print STDOUT qq[
The conformance
+ checker cannot decide whether the document is conforming or
+ not, since the document contains one or more unsupported
+ features.
];
+ } 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[
+
+
+ | MUST-level
+Errors | SHOULD-level
+Errors | Warnings | Score |
+];
+
+ my $must_error = 0;
+ my $should_error = 0;
+ my $warning = 0;
+ my $score_min = 0;
+ my $score_max = 0;
+ my $score_base = 20;
+ 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_base);
+ $score_max += ($result->{$_->[1]}->{score_max} += $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[$label | $result->{$_->[1]}->{must}$uncertain | $result->{$_->[1]}->{should}$uncertain | $result->{$_->[1]}->{warning}$uncertain | ];
+ if ($uncertain) {
+ 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} + $score_base |
];
+ } else {
+ print qq[$result->{$_->[1]}->{score_min} | ];
+ }
+ }
+
+ $score_max += $score_base;
+
+ print STDOUT qq[
+Semantics | 0? | 0? | 0? | −∞..$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 = shift;
+
+ print STDOUT qq[
+
+
Media type @{[htescape $input->{media_type}]}
is not supported!
+
+];
+ push @nav, ['#result-summary' => 'Result'];
+} # print_result_unknown_type_section
+
+sub print_result_input_error_section ($) {
+ 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_node_path ($) {
my $node = shift;
my @r;
@@ -759,4 +914,4 @@
=cut
-## $Date: 2007/09/02 07:59:01 $
+## $Date: 2007/09/10 11:51:09 $