/usr/share/perl5/HTML/Lint.pm is in libhtml-lint-perl 2.06+dfsg-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 | package HTML::Lint;
use warnings;
use strict;
use HTML::Lint::Error;
=head1 NAME
HTML::Lint - check for HTML errors in a string or file
=head1 VERSION
Version 2.06
=cut
our $VERSION = '2.06';
=head1 SYNOPSIS
my $lint = HTML::Lint->new;
$lint->only_types( HTML::Lint::STRUCTURE );
$lint->parse( $data );
$lint->parse_file( $filename );
my $error_count = $lint->errors;
foreach my $error ( $lint->errors ) {
print $error->as_string, "\n";
}
HTML::Lint also comes with a wrapper program called F<weblint> that handles
linting from the command line:
$ weblint http://www.cnn.com/
http://www.cnn.com/ (395:83) <IMG SRC="spacer.gif"> tag has no HEIGHT and WIDTH attributes.
http://www.cnn.com/ (395:83) <IMG SRC="goofus.gif"> does not have ALT text defined
http://www.cnn.com/ (396:217) Unknown element <nobr>
http://www.cnn.com/ (396:241) </nobr> with no opening <nobr>
http://www.cnn.com/ (842:7) target attribute in <a> is repeated
And finally, you can also get L<Apache::HTML::Lint> that passes any
mod_perl-generated code through HTML::Lint and get it dumped into your
Apache F<error_log>.
[Mon Jun 3 14:03:31 2002] [warn] /foo.pl (1:45) </p> with no opening <p>
[Mon Jun 3 14:03:31 2002] [warn] /foo.pl (1:49) Unknown element <gronk>
[Mon Jun 3 14:03:31 2002] [warn] /foo.pl (1:56) Unknown attribute "x" for tag <table>
=cut
=head1 METHODS
NOTE: Some of these methods mirror L<HTML::Parser>'s methods, but HTML::Lint
is not a subclass of HTML::Parser.
=head2 new()
Create an HTML::Lint object, which inherits from HTML::Parser.
You may pass the types of errors you want to check for in the
C<only_types> parm.
my $lint = HTML::Lint->new( only_types => HTML::Lint::Error::STRUCTURE );
If you want more than one, you must pass an arrayref:
my $lint = HTML::Lint->new(
only_types => [HTML::Lint::Error::STRUCTURE, HTML::Lint::Error::FLUFF] );
=cut
sub new {
my $class = shift;
my %args = @_;
my $self = {
_errors => [],
_types => [],
};
$self->{_parser} = HTML::Lint::Parser->new( sub { $self->gripe( @_ ) } );
bless $self, $class;
if ( my $only = $args{only_types} ) {
$self->only_types( ref $only eq 'ARRAY' ? @{$only} : $only );
delete $args{only_types};
}
warn "Unknown argument $_\n" for keys %args;
return $self;
}
=head2 $lint->parse( $chunk )
=head2 $lint->parse( $code_ref )
Passes in a chunk of HTML to be linted, either as a piece of text,
or a code reference.
See L<HTML::Parser>'s C<parse_file> method for details.
=cut
sub parse {
my $self = shift;
return $self->_parser->parse( @_ );
}
=head2 $lint->parse_file( $file )
Analyzes HTML directly from a file. The C<$file> argument can be a filename,
an open file handle, or a reference to an open file handle.
See L<HTML::Parser>'s C<parse_file> method for details.
=cut
sub parse_file {
my $self = shift;
return $self->_parser->parse_file( @_ );
}
=head2 $lint->eof
Signals the end of a block of text getting passed in. This must be
called to make sure that all parsing is complete before looking at errors.
Any parameters (and there shouldn't be any) are passed through to
HTML::Parser's eof() method.
=cut
sub eof {
my $self = shift;
my $rc;
my $parser = $self->_parser;
if ( $parser ) {
$rc = $self->_parser->eof(@_);
delete $self->{_parser};
}
return $rc;
}
=head2 $lint->errors()
In list context, C<errors> returns all of the errors found in the
parsed text. Each error is an object of the type L<HTML::Lint::Error>.
In scalar context, it returns the number of errors found.
=cut
sub errors {
my $self = shift;
if ( wantarray ) {
return @{$self->{_errors}};
}
else {
return scalar @{$self->{_errors}};
}
}
=head2 $lint->clear_errors()
Clears the list of errors, in case you want to print and clear, print and clear.
=cut
sub clear_errors {
my $self = shift;
$self->{_errors} = [];
return;
}
=head2 $lint->only_types( $type1[, $type2...] )
Specifies to only want errors of a certain type.
$lint->only_types( HTML::Lint::Error::STRUCTURE );
Calling this without parameters makes the object return all possible
errors.
The error types are C<STRUCTURE>, C<HELPER> and C<FLUFF>.
See L<HTML::Lint::Error> for details on these types.
=cut
sub only_types {
my $self = shift;
$self->{_types} = [@_];
}
=head2 $lint->gripe( $errcode, [$key1=>$val1, ...] )
Adds an error message, in the form of an L<HTML::Lint::Error> object,
to the list of error messages for the current object. The file,
line and column are automatically passed to the L<HTML::Lint::Error>
constructor, as well as whatever other key value pairs are passed.
For example:
$lint->gripe( 'attr-repeated', tag => $tag, attr => $attr );
Usually, the user of the object won't call this directly, but just
in case, here you go.
=cut
sub gripe {
my $self = shift;
my $parser = $self->_parser;
my $error = new HTML::Lint::Error(
$self->{_file}, $parser->{_line}, $parser->{_column}, @_ );
my @keeps = @{$self->{_types}};
if ( !@keeps || $error->is_type(@keeps) ) {
push( @{$self->{_errors}}, $error );
}
}
=head2 $lint->newfile( $filename )
Call C<newfile()> whenever you switch to another file in a batch
of linting. Otherwise, the object thinks everything is from the
same file. Note that the list of errors is NOT cleared.
Note that I<$filename> does NOT need to match what's put into parse()
or parse_file(). It can be a description, a URL, or whatever.
=cut
sub newfile {
my $self = shift;
my $file = shift;
delete $self->{_parser};
$self->{_parser} = HTML::Lint::Parser->new( sub { $self->gripe( @_ ) } );
$self->{_file} = $file;
$self->{_line} = 0;
$self->{_column} = 0;
$self->{_first_seen} = {};
return $self->{_file};
} # newfile
sub _parser {
my $self = shift;
return $self->{_parser};
}
=pod
HTML::Lint::Parser is a class only for this module.
=cut
package HTML::Lint::Parser;
use HTML::Parser 3.20;
use HTML::Tagset 3.03;
use HTML::Lint::HTML4 qw( %isKnownAttribute %isRequired %isNonrepeatable %isObsolete );
use HTML::Entities qw( %char2entity );
use base 'HTML::Parser';
sub new {
my $class = shift;
my $gripe = shift;
my $self =
HTML::Parser->new(
api_version => 3,
start_document_h => [ \&_start_document, 'self' ],
end_document_h => [ \&_end_document, 'self,line,column' ],
start_h => [ \&_start, 'self,tagname,line,column,@attr' ],
end_h => [ \&_end, 'self,tagname,line,column,@attr' ],
text_h => [ \&_text, 'self,text' ],
strict_names => 1,
);
bless $self, $class;
$self->{_gripe} = $gripe;
$self->{_stack} = [];
return $self;
}
sub gripe {
my $self = shift;
return $self->{_gripe}->( @_ );
}
sub _start_document {
}
sub _end_document {
my ($self,$line,$column) = @_;
for my $tag ( keys %isRequired ) {
if ( !$self->{_first_seen}->{$tag} ) {
$self->gripe( 'doc-tag-required', tag => $tag );
}
}
return;
}
sub _start {
my ($self,$tag,$line,$column,@attr) = @_;
$self->{_line} = $line;
$self->{_column} = $column;
my $validattr = $isKnownAttribute{ $tag };
if ( $validattr ) {
my %seen;
my $i = 0;
while ( $i < @attr ) {
my ($attr,$val) = @attr[$i++,$i++];
if ( $seen{$attr}++ ) {
$self->gripe( 'attr-repeated', tag => $tag, attr => $attr );
}
if ( $validattr && ( !$validattr->{$attr} ) ) {
$self->gripe( 'attr-unknown', tag => $tag, attr => $attr );
}
} # while attribs
}
else {
$self->gripe( 'elem-unknown', tag => $tag );
}
$self->_element_push( $tag ) unless $HTML::Tagset::emptyElement{ $tag };
if ( my $where = $self->{_first_seen}{$tag} ) {
if ( $isNonrepeatable{$tag} ) {
$self->gripe( 'elem-nonrepeatable',
tag => $tag,
where => HTML::Lint::Error::where( @{$where} )
);
}
}
else {
$self->{_first_seen}{$tag} = [$line,$column];
}
# Call any other overloaded func
my $tagfunc = "_start_$tag";
if ( $self->can($tagfunc) ) {
$self->$tagfunc( $tag, @attr );
}
return;
}
sub _text {
my ($self,$text) = @_;
while ( $text =~ /([^\x09\x0A\x0D -~])/g ) {
my $bad = $1;
$self->gripe(
'text-use-entity',
char => sprintf( '\x%02lX', ord($bad) ),
entity => $char2entity{ $bad },
);
}
return;
}
sub _end {
my ($self,$tag,$line,$column,@attr) = @_;
$self->{_line} = $line;
$self->{_column} = $column;
if ( $HTML::Tagset::emptyElement{ $tag } ) {
$self->gripe( 'elem-empty-but-closed', tag => $tag );
}
else {
if ( $self->_in_context($tag) ) {
my @leftovers = $self->_element_pop_back_to($tag);
for ( @leftovers ) {
my ($tag,$line,$col) = @{$_};
$self->gripe( 'elem-unclosed', tag => $tag,
where => HTML::Lint::Error::where($line,$col) )
unless $HTML::Tagset::optionalEndTag{$tag};
} # for
}
else {
$self->gripe( 'elem-unopened', tag => $tag );
}
} # is empty element
# Call any other overloaded func
my $tagfunc = "_end_$tag";
if ( $self->can($tagfunc) ) {
$self->$tagfunc( $tag, $line );
}
return;
}
sub _element_push {
my $self = shift;
for ( @_ ) {
push( @{$self->{_stack}}, [$_,$self->{_line},$self->{_column}] );
} # while
return;
}
sub _find_tag_in_stack {
my $self = shift;
my $tag = shift;
my $stack = $self->{_stack};
my $offset = @{$stack} - 1;
while ( $offset >= 0 ) {
if ( $stack->[$offset][0] eq $tag ) {
return $offset;
}
--$offset;
} # while
return;
}
sub _element_pop_back_to {
my $self = shift;
my $tag = shift;
my $offset = $self->_find_tag_in_stack($tag) or return;
my @leftovers = splice( @{$self->{_stack}}, $offset + 1 );
pop @{$self->{_stack}};
return @leftovers;
}
sub _in_context {
my $self = shift;
my $tag = shift;
my $offset = $self->_find_tag_in_stack($tag);
return defined $offset;
}
# Overridden tag-specific stuff
sub _start_img {
my ($self,$tag,%attr) = @_;
my ($h,$w,$src) = @attr{qw( height width src )};
if ( defined $h && defined $w ) {
# Check sizes
}
else {
$self->gripe( 'elem-img-sizes-missing', src=>$src );
}
if ( not defined $attr{alt} ) {
$self->gripe( 'elem-img-alt-missing', src=>$src );
}
return;
}
=head1 BUGS, WISHES AND CORRESPONDENCE
All bugs and requests are now being handled through the Google
Code issue tracker at http://code.google.com/p/html-lint/issues/list.
DO NOT send bug reports to http://rt.cpan.org/
=head1 TODO
=over 4
=item * Check for attributes that require values
=item * <TABLE>s that have no rows.
=item * Form fields that aren't in a FORM
=item * Check for valid entities, and that they end with semicolons
=item * DIVs with nothing in them.
=item * HEIGHT= that have percents in them.
=item * Check for goofy stuff like:
<b><li></b><b>Hello Reader - Spanish Level 1 (K-3)</b>
=back
=head1 LICENSE
Copyright 2005-2008 Andy Lester, All Rights Reserved.
This program is free software; you can redistribute it and/or modify it
under the same terms as Perl itself.
Please note that these modules are not products of or supported by the
employers of the various contributors to the code.
=head1 AUTHOR
Andy Lester, andy at petdance.com
=cut
1;
|