/usr/share/perl5/TAP/Parser/Grammar.pm is in libtest-harness-perl 3.23-1.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 | package TAP::Parser::Grammar;
use strict;
use vars qw($VERSION @ISA);
use TAP::Object ();
use TAP::Parser::ResultFactory ();
use TAP::Parser::YAMLish::Reader ();
@ISA = qw(TAP::Object);
=head1 NAME
TAP::Parser::Grammar - A grammar for the Test Anything Protocol.
=head1 VERSION
Version 3.23
=cut
$VERSION = '3.23';
=head1 SYNOPSIS
use TAP::Parser::Grammar;
my $grammar = $self->make_grammar({
iterator => $tap_parser_iterator,
parser => $tap_parser,
version => 12,
});
my $result = $grammar->tokenize;
=head1 DESCRIPTION
C<TAP::Parser::Grammar> tokenizes lines from a L<TAP::Parser::Iterator> and
constructs L<TAP::Parser::Result> subclasses to represent the tokens.
Do not attempt to use this class directly. It won't make sense. It's mainly
here to ensure that we will be able to have pluggable grammars when TAP is
expanded at some future date (plus, this stuff was really cluttering the
parser).
=head1 METHODS
=head2 Class Methods
=head3 C<new>
my $grammar = TAP::Parser::Grammar->new({
iterator => $iterator,
parser => $parser,
version => $version,
});
Returns L<TAP::Parser> grammar object that will parse the TAP stream from the
specified iterator. Both C<iterator> and C<parser> are required arguments.
If C<version> is not set it defaults to C<12> (see L</set_version> for more
details).
=cut
# new() implementation supplied by TAP::Object
sub _initialize {
my ( $self, $args ) = @_;
$self->{iterator} = $args->{iterator}; # TODO: accessor
$self->{iterator} ||= $args->{stream}; # deprecated
$self->{parser} = $args->{parser}; # TODO: accessor
$self->set_version( $args->{version} || 12 );
return $self;
}
my %language_for;
{
# XXX the 'not' and 'ok' might be on separate lines in VMS ...
my $ok = qr/(?:not )?ok\b/;
my $num = qr/\d+/;
my %v12 = (
version => {
syntax => qr/^TAP\s+version\s+(\d+)\s*\z/i,
handler => sub {
my ( $self, $line ) = @_;
my $version = $1;
return $self->_make_version_token( $line, $version, );
},
},
plan => {
syntax => qr/^1\.\.(\d+)\s*(.*)\z/,
handler => sub {
my ( $self, $line ) = @_;
my ( $tests_planned, $tail ) = ( $1, $2 );
my $explanation = undef;
my $skip = '';
if ( $tail =~ /^todo((?:\s+\d+)+)/ ) {
my @todo = split /\s+/, _trim($1);
return $self->_make_plan_token(
$line, $tests_planned, 'TODO',
'', \@todo
);
}
elsif ( 0 == $tests_planned ) {
$skip = 'SKIP';
# If we can't match # SKIP the directive should be undef.
($explanation) = $tail =~ /^#\s*SKIP\S*\s+(.*)/i;
}
elsif ( $tail !~ /^\s*$/ ) {
return $self->_make_unknown_token($line);
}
$explanation = '' unless defined $explanation;
return $self->_make_plan_token(
$line, $tests_planned, $skip,
$explanation, []
);
},
},
# An optimization to handle the most common test lines without
# directives.
simple_test => {
syntax => qr/^($ok) \ ($num) (?:\ ([^#]+))? \z/x,
handler => sub {
my ( $self, $line ) = @_;
my ( $ok, $num, $desc ) = ( $1, $2, $3 );
return $self->_make_test_token(
$line, $ok, $num,
$desc
);
},
},
test => {
syntax => qr/^($ok) \s* ($num)? \s* (.*) \z/x,
handler => sub {
my ( $self, $line ) = @_;
my ( $ok, $num, $desc ) = ( $1, $2, $3 );
my ( $dir, $explanation ) = ( '', '' );
if ($desc =~ m/^ ( [^\\\#]* (?: \\. [^\\\#]* )* )
\# \s* (SKIP|TODO) \b \s* (.*) $/ix
)
{
( $desc, $dir, $explanation ) = ( $1, $2, $3 );
}
return $self->_make_test_token(
$line, $ok, $num, $desc,
$dir, $explanation
);
},
},
comment => {
syntax => qr/^#(.*)/,
handler => sub {
my ( $self, $line ) = @_;
my $comment = $1;
return $self->_make_comment_token( $line, $comment );
},
},
bailout => {
syntax => qr/^\s*Bail out!\s*(.*)/,
handler => sub {
my ( $self, $line ) = @_;
my $explanation = $1;
return $self->_make_bailout_token(
$line,
$explanation
);
},
},
);
my %v13 = (
%v12,
plan => {
syntax => qr/^1\.\.(\d+)(?:\s*#\s*SKIP\b(.*))?\z/i,
handler => sub {
my ( $self, $line ) = @_;
my ( $tests_planned, $explanation ) = ( $1, $2 );
my $skip
= ( 0 == $tests_planned || defined $explanation )
? 'SKIP'
: '';
$explanation = '' unless defined $explanation;
return $self->_make_plan_token(
$line, $tests_planned, $skip,
$explanation, []
);
},
},
yaml => {
syntax => qr/^ (\s+) (---.*) $/x,
handler => sub {
my ( $self, $line ) = @_;
my ( $pad, $marker ) = ( $1, $2 );
return $self->_make_yaml_token( $pad, $marker );
},
},
pragma => {
syntax =>
qr/^ pragma \s+ ( [-+] \w+ \s* (?: , \s* [-+] \w+ \s* )* ) $/x,
handler => sub {
my ( $self, $line ) = @_;
my $pragmas = $1;
return $self->_make_pragma_token( $line, $pragmas );
},
},
);
%language_for = (
'12' => {
tokens => \%v12,
},
'13' => {
tokens => \%v13,
setup => sub {
shift->{iterator}->handle_unicode;
},
},
);
}
##############################################################################
=head2 Instance Methods
=head3 C<set_version>
$grammar->set_version(13);
Tell the grammar which TAP syntax version to support. The lowest
supported version is 12. Although 'TAP version' isn't valid version 12
syntax it is accepted so that higher version numbers may be parsed.
=cut
sub set_version {
my $self = shift;
my $version = shift;
if ( my $language = $language_for{$version} ) {
$self->{version} = $version;
$self->{tokens} = $language->{tokens};
if ( my $setup = $language->{setup} ) {
$self->$setup();
}
$self->_order_tokens;
}
else {
require Carp;
Carp::croak("Unsupported syntax version: $version");
}
}
# Optimization to put the most frequent tokens first.
sub _order_tokens {
my $self = shift;
my %copy = %{ $self->{tokens} };
my @ordered_tokens = grep {defined}
map { delete $copy{$_} } qw( simple_test test comment plan );
push @ordered_tokens, values %copy;
$self->{ordered_tokens} = \@ordered_tokens;
}
##############################################################################
=head3 C<tokenize>
my $token = $grammar->tokenize;
This method will return a L<TAP::Parser::Result> object representing the
current line of TAP.
=cut
sub tokenize {
my $self = shift;
my $line = $self->{iterator}->next;
unless ( defined $line ) {
delete $self->{parser}; # break circular ref
return;
}
my $token;
for my $token_data ( @{ $self->{ordered_tokens} } ) {
if ( $line =~ $token_data->{syntax} ) {
my $handler = $token_data->{handler};
$token = $self->$handler($line);
last;
}
}
$token = $self->_make_unknown_token($line) unless $token;
return $self->{parser}->make_result($token);
}
##############################################################################
=head3 C<token_types>
my @types = $grammar->token_types;
Returns the different types of tokens which this grammar can parse.
=cut
sub token_types {
my $self = shift;
return keys %{ $self->{tokens} };
}
##############################################################################
=head3 C<syntax_for>
my $syntax = $grammar->syntax_for($token_type);
Returns a pre-compiled regular expression which will match a chunk of TAP
corresponding to the token type. For example (not that you should really pay
attention to this, C<< $grammar->syntax_for('comment') >> will return
C<< qr/^#(.*)/ >>.
=cut
sub syntax_for {
my ( $self, $type ) = @_;
return $self->{tokens}->{$type}->{syntax};
}
##############################################################################
=head3 C<handler_for>
my $handler = $grammar->handler_for($token_type);
Returns a code reference which, when passed an appropriate line of TAP,
returns the lexed token corresponding to that line. As a result, the basic
TAP parsing loop looks similar to the following:
my @tokens;
my $grammar = TAP::Grammar->new;
LINE: while ( defined( my $line = $parser->_next_chunk_of_tap ) ) {
for my $type ( $grammar->token_types ) {
my $syntax = $grammar->syntax_for($type);
if ( $line =~ $syntax ) {
my $handler = $grammar->handler_for($type);
push @tokens => $grammar->$handler($line);
next LINE;
}
}
push @tokens => $grammar->_make_unknown_token($line);
}
=cut
sub handler_for {
my ( $self, $type ) = @_;
return $self->{tokens}->{$type}->{handler};
}
sub _make_version_token {
my ( $self, $line, $version ) = @_;
return {
type => 'version',
raw => $line,
version => $version,
};
}
sub _make_plan_token {
my ( $self, $line, $tests_planned, $directive, $explanation, $todo ) = @_;
if ( $directive eq 'SKIP'
&& 0 != $tests_planned
&& $self->{version} < 13 )
{
warn
"Specified SKIP directive in plan but more than 0 tests ($line)\n";
}
return {
type => 'plan',
raw => $line,
tests_planned => $tests_planned,
directive => $directive,
explanation => _trim($explanation),
todo_list => $todo,
};
}
sub _make_test_token {
my ( $self, $line, $ok, $num, $desc, $dir, $explanation ) = @_;
return {
ok => $ok,
test_num => $num,
description => _trim($desc),
directive => ( defined $dir ? uc $dir : '' ),
explanation => _trim($explanation),
raw => $line,
type => 'test',
};
}
sub _make_unknown_token {
my ( $self, $line ) = @_;
return {
raw => $line,
type => 'unknown',
};
}
sub _make_comment_token {
my ( $self, $line, $comment ) = @_;
return {
type => 'comment',
raw => $line,
comment => _trim($comment)
};
}
sub _make_bailout_token {
my ( $self, $line, $explanation ) = @_;
return {
type => 'bailout',
raw => $line,
bailout => _trim($explanation)
};
}
sub _make_yaml_token {
my ( $self, $pad, $marker ) = @_;
my $yaml = TAP::Parser::YAMLish::Reader->new;
my $iterator = $self->{iterator};
# Construct a reader that reads from our input stripping leading
# spaces from each line.
my $leader = length($pad);
my $strip = qr{ ^ (\s{$leader}) (.*) $ }x;
my @extra = ($marker);
my $reader = sub {
return shift @extra if @extra;
my $line = $iterator->next;
return $2 if $line =~ $strip;
return;
};
my $data = $yaml->read($reader);
# Reconstitute input. This is convoluted. Maybe we should just
# record it on the way in...
chomp( my $raw = $yaml->get_raw );
$raw =~ s/^/$pad/mg;
return {
type => 'yaml',
raw => $raw,
data => $data
};
}
sub _make_pragma_token {
my ( $self, $line, $pragmas ) = @_;
return {
type => 'pragma',
raw => $line,
pragmas => [ split /\s*,\s*/, _trim($pragmas) ],
};
}
sub _trim {
my $data = shift;
return '' unless defined $data;
$data =~ s/^\s+//;
$data =~ s/\s+$//;
return $data;
}
1;
=head1 TAP GRAMMAR
B<NOTE:> This grammar is slightly out of date. There's still some discussion
about it and a new one will be provided when we have things better defined.
The L<TAP::Parser> does not use a formal grammar because TAP is essentially a
stream-based protocol. In fact, it's quite legal to have an infinite stream.
For the same reason that we don't apply regexes to streams, we're not using a
formal grammar here. Instead, we parse the TAP in lines.
For purposes for forward compatibility, any result which does not match the
following grammar is currently referred to as
L<TAP::Parser::Result::Unknown>. It is I<not> a parse error.
A formal grammar would look similar to the following:
(*
For the time being, I'm cheating on the EBNF by allowing
certain terms to be defined by POSIX character classes by
using the following syntax:
digit ::= [:digit:]
As far as I am aware, that's not valid EBNF. Sue me. I
didn't know how to write "char" otherwise (Unicode issues).
Suggestions welcome.
*)
tap ::= version? { comment | unknown } leading_plan lines
|
lines trailing_plan {comment}
version ::= 'TAP version ' positiveInteger {positiveInteger} "\n"
leading_plan ::= plan skip_directive? "\n"
trailing_plan ::= plan "\n"
plan ::= '1..' nonNegativeInteger
lines ::= line {line}
line ::= (comment | test | unknown | bailout ) "\n"
test ::= status positiveInteger? description? directive?
status ::= 'not '? 'ok '
description ::= (character - (digit | '#')) {character - '#'}
directive ::= todo_directive | skip_directive
todo_directive ::= hash_mark 'TODO' ' ' {character}
skip_directive ::= hash_mark 'SKIP' ' ' {character}
comment ::= hash_mark {character}
hash_mark ::= '#' {' '}
bailout ::= 'Bail out!' {character}
unknown ::= { (character - "\n") }
(* POSIX character classes and other terminals *)
digit ::= [:digit:]
character ::= ([:print:] - "\n")
positiveInteger ::= ( digit - '0' ) {digit}
nonNegativeInteger ::= digit {digit}
=head1 SUBCLASSING
Please see L<TAP::Parser/SUBCLASSING> for a subclassing overview.
If you I<really> want to subclass L<TAP::Parser>'s grammar the best thing to
do is read through the code. There's no easy way of summarizing it here.
=head1 SEE ALSO
L<TAP::Object>,
L<TAP::Parser>,
L<TAP::Parser::Iterator>,
L<TAP::Parser::Result>,
=cut
|