/usr/share/perl5/PPI/Token/Word.pm is in libppi-perl 1.220-1.
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 | package PPI::Token::Word;
=pod
=head1 NAME
PPI::Token::Word - The generic "word" Token
=head1 INHERITANCE
PPI::Token::Word
isa PPI::Token
isa PPI::Element
=head1 DESCRIPTION
A C<PPI::Token::Word> object is a PPI-specific representation of several
different types of word-like things, and is one of the most common Token
classes found in typical documents.
Specifically, it includes not only barewords, but also any other valid
Perl identifier including non-operator keywords and core functions, and
any include C<::> separators inside it, as long as it fits the
format of a class, function, etc.
=head1 METHODS
There are no methods available for C<PPI::Token::Word> beyond those
provided by its L<PPI::Token> and L<PPI::Element> parent
classes.
We expect to add additional methods to help further resolve a Word as
a function, method, etc over time. If you need such a thing right
now, look at L<Perl::Critic::Utils>.
=cut
use strict;
use PPI::Token ();
use vars qw{$VERSION @ISA %OPERATOR %QUOTELIKE %KEYWORDS};
BEGIN {
$VERSION = '1.220';
@ISA = 'PPI::Token';
# Copy in OPERATOR from PPI::Token::Operator
*OPERATOR = *PPI::Token::Operator::OPERATOR;
%QUOTELIKE = (
'q' => 'Quote::Literal',
'qq' => 'Quote::Interpolate',
'qx' => 'QuoteLike::Command',
'qw' => 'QuoteLike::Words',
'qr' => 'QuoteLike::Regexp',
'm' => 'Regexp::Match',
's' => 'Regexp::Substitute',
'tr' => 'Regexp::Transliterate',
'y' => 'Regexp::Transliterate',
);
# List of keywords is from regen/keywords.pl in the perl source.
%KEYWORDS = map { $_ => 1 } qw{
abs accept alarm and atan2 bind binmode bless break caller chdir chmod
chomp chop chown chr chroot close closedir cmp connect continue cos
crypt dbmclose dbmopen default defined delete die do dump each else
elsif endgrent endhostent endnetent endprotoent endpwent endservent
eof eq eval evalbytes exec exists exit exp fc fcntl fileno flock for
foreach fork format formline ge getc getgrent getgrgid getgrnam
gethostbyaddr gethostbyname gethostent getlogin getnetbyaddr
getnetbyname getnetent getpeername getpgrp getppid getpriority
getprotobyname getprotobynumber getprotoent getpwent getpwnam
getpwuid getservbyname getservbyport getservent getsockname
getsockopt given glob gmtime goto grep gt hex if index int ioctl join
keys kill last lc lcfirst le length link listen local localtime lock
log lstat lt m map mkdir msgctl msgget msgrcv msgsnd my ne next no
not oct open opendir or ord our pack package pipe pop pos print
printf prototype push q qq qr quotemeta qw qx rand read readdir
readline readlink readpipe recv redo ref rename require reset return
reverse rewinddir rindex rmdir s say scalar seek seekdir select semctl
semget semop send setgrent sethostent setnetent setpgrp
setpriority setprotoent setpwent setservent setsockopt shift shmctl
shmget shmread shmwrite shutdown sin sleep socket socketpair sort
splice split sprintf sqrt srand stat state study sub substr symlink
syscall sysopen sysread sysseek system syswrite tell telldir tie tied
time times tr truncate uc ucfirst umask undef unless unlink unpack
unshift untie until use utime values vec wait waitpid wantarray warn
when while write x xor y
};
}
=pod
=head2 literal
Returns the value of the Word as a string. This assumes (often
incorrectly) that the Word is a bareword and not a function, method,
keyword, etc. This differs from C<content> because C<Foo'Bar> expands
to C<Foo::Bar>.
=cut
sub literal {
my $self = shift;
my $word = $self->content;
# Expand Foo'Bar to Foo::Bar
$word =~ s/\'/::/g;
return $word;
}
=pod
=head2 method_call
Answers whether this is the name of a method in a method call. Returns true if
yes, false if no, and nothing if unknown.
=cut
sub method_call {
my $self = shift;
my $previous = $self->sprevious_sibling;
if (
$previous
and
$previous->isa('PPI::Token::Operator')
and
$previous->content eq '->'
) {
return 1;
}
my $snext = $self->snext_sibling;
return 0 unless $snext;
if (
$snext->isa('PPI::Structure::List')
or
$snext->isa('PPI::Token::Structure')
or
$snext->isa('PPI::Token::Operator')
and (
$snext->content eq ','
or
$snext->content eq '=>'
)
) {
return 0;
}
if (
$snext->isa('PPI::Token::Word')
and
$snext->content =~ m< \w :: \z >xms
) {
return 1;
}
return;
}
sub __TOKENIZER__on_char {
my $class = shift;
my $t = shift;
# Suck in till the end of the bareword
pos $t->{line} = $t->{line_cursor};
if ( $t->{line} =~ m/\G(\w+(?:(?:\'|::)\w+)*(?:::)?)/gc ) {
my $word = $1;
# Special Case: If we accidentally treat eq'foo' like
# the word "eq'foo", then just make 'eq' (or whatever
# else is in the %KEYWORDS hash.
if ( $word =~ /^(\w+)'/ && $KEYWORDS{$1} ) {
$word = $1;
}
$t->{token}->{content} .= $word;
$t->{line_cursor} += length $word;
}
# We might be a subroutine attribute.
my $tokens = $t->_previous_significant_tokens(1);
if ( $tokens and $tokens->[0]->{_attribute} ) {
$t->{class} = $t->{token}->set_class( 'Attribute' );
return $t->{class}->__TOKENIZER__commit( $t );
}
# Check for a quote like operator
my $word = $t->{token}->{content};
if ( $QUOTELIKE{$word} and ! $class->__TOKENIZER__literal($t, $word, $tokens) ) {
$t->{class} = $t->{token}->set_class( $QUOTELIKE{$word} );
return $t->{class}->__TOKENIZER__on_char( $t );
}
# Or one of the word operators
if ( $OPERATOR{$word} and ! $class->__TOKENIZER__literal($t, $word, $tokens) ) {
$t->{class} = $t->{token}->set_class( 'Operator' );
return $t->_finalize_token->__TOKENIZER__on_char( $t );
}
# Unless this is a simple identifier, at this point
# it has to be a normal bareword
if ( $word =~ /\:/ ) {
return $t->_finalize_token->__TOKENIZER__on_char( $t );
}
# If the NEXT character in the line is a colon, this
# is a label.
my $char = substr( $t->{line}, $t->{line_cursor}, 1 );
if ( $char eq ':' ) {
$t->{token}->{content} .= ':';
$t->{line_cursor}++;
$t->{class} = $t->{token}->set_class( 'Label' );
# If not a label, '_' on its own is the magic filehandle
} elsif ( $word eq '_' ) {
$t->{class} = $t->{token}->set_class( 'Magic' );
}
# Finalise and process the character again
$t->_finalize_token->__TOKENIZER__on_char( $t );
}
# We are committed to being a bareword.
# Or so we would like to believe.
sub __TOKENIZER__commit {
my ($class, $t) = @_;
# Our current position is the first character of the bareword.
# Capture the bareword.
pos $t->{line} = $t->{line_cursor};
unless ( $t->{line} =~ m/\G((?!\d)\w+(?:(?:\'|::)\w+)*(?:::)?)/gc ) {
# Programmer error
die sprintf "Fatal error... regex failed to match in '%s' when expected", substr $t->{line}, $t->{line_cursor};
}
# Special Case: If we accidentally treat eq'foo' like the word "eq'foo",
# then unwind it and just make it 'eq' (or the other stringy comparitors)
my $word = $1;
if ( $word =~ /^(\w+)'/ && $KEYWORDS{$1} ) {
$word = $1;
}
# Advance the position one after the end of the bareword
$t->{line_cursor} += length $word;
# We might be a subroutine attribute.
my $tokens = $t->_previous_significant_tokens(1);
if ( $tokens and $tokens->[0]->{_attribute} ) {
$t->_new_token( 'Attribute', $word );
return ($t->{line_cursor} >= $t->{line_length}) ? 0
: $t->{class}->__TOKENIZER__on_char($t);
}
# Check for the end of the file
if ( $word eq '__END__' ) {
# Create the token for the __END__ itself
$t->_new_token( 'Separator', $1 );
$t->_finalize_token;
# Move into the End zone (heh)
$t->{zone} = 'PPI::Token::End';
# Add the rest of the line as a comment, and a whitespace newline
# Anything after the __END__ on the line is "ignored". So we must
# also ignore it, by turning it into a comment.
my $end_rest = substr( $t->{line}, $t->{line_cursor} );
$t->{line_cursor} = length $t->{line};
if ( $end_rest =~ /\n$/ ) {
chomp $end_rest;
$t->_new_token( 'Comment', $end_rest ) if length $end_rest;
$t->_new_token( 'Whitespace', "\n" );
} else {
$t->_new_token( 'Comment', $end_rest ) if length $end_rest;
}
$t->_finalize_token;
return 0;
}
# Check for the data section
if ( $word eq '__DATA__' ) {
# Create the token for the __DATA__ itself
$t->_new_token( 'Separator', "$1" );
$t->_finalize_token;
# Move into the Data zone
$t->{zone} = 'PPI::Token::Data';
# Add the rest of the line as the Data token
my $data_rest = substr( $t->{line}, $t->{line_cursor} );
$t->{line_cursor} = length $t->{line};
if ( $data_rest =~ /\n$/ ) {
chomp $data_rest;
$t->_new_token( 'Comment', $data_rest ) if length $data_rest;
$t->_new_token( 'Whitespace', "\n" );
} else {
$t->_new_token( 'Comment', $data_rest ) if length $data_rest;
}
$t->_finalize_token;
return 0;
}
my $token_class;
if ( $word =~ /\:/ ) {
# Since its not a simple identifier...
$token_class = 'Word';
} elsif ( $class->__TOKENIZER__literal($t, $word, $tokens) ) {
$token_class = 'Word';
} elsif ( $QUOTELIKE{$word} ) {
# Special Case: A Quote-like operator
$t->_new_token( $QUOTELIKE{$word}, $word );
return ($t->{line_cursor} >= $t->{line_length}) ? 0
: $t->{class}->__TOKENIZER__on_char( $t );
} elsif ( $OPERATOR{$word} && ($word ne 'x' || $t->_current_x_is_operator) ) {
# Word operator
$token_class = 'Operator';
} else {
# If the next character is a ':' then its a label...
pos $t->{line} = $t->{line_cursor};
if ( $t->{line} =~ m/\G(\s*:)(?!:)/gc ) {
if ( $tokens and $tokens->[0]->{content} eq 'sub' ) {
# ... UNLESS its after 'sub' in which
# case it is a sub name and an attribute
# operator.
# We COULD have checked this at the top
# level of checks, but this would impose
# an additional performance per-word
# penalty, and every other case where the
# attribute operator doesn't directly
# touch the object name already works.
$token_class = 'Word';
} else {
$word .= $1;
$t->{line_cursor} += length($1);
$token_class = 'Label';
}
} elsif ( $word eq '_' ) {
$token_class = 'Magic';
} else {
$token_class = 'Word';
}
}
# Create the new token and finalise
$t->_new_token( $token_class, $word );
if ( $t->{line_cursor} >= $t->{line_length} ) {
# End of the line
$t->_finalize_token;
return 0;
}
$t->_finalize_token->__TOKENIZER__on_char($t);
}
# Is the word in a "forced" context, and thus cannot be either an
# operator or a quote-like thing. This version is only useful
# during tokenization.
sub __TOKENIZER__literal {
my ($class, $t, $word, $tokens) = @_;
# Is this a forced-word context?
# i.e. Would normally be seen as an operator.
unless ( $QUOTELIKE{$word} or $PPI::Token::Operator::OPERATOR{$word} ) {
return '';
}
# Check the cases when we have previous tokens
pos $t->{line} = $t->{line_cursor};
if ( $tokens ) {
my $token = $tokens->[0] or return '';
# We are forced if we are a method name
return 1 if $token->{content} eq '->';
# We are forced if we are a sub name
return 1 if $token->isa('PPI::Token::Word') && $token->{content} eq 'sub';
# If we are contained in a pair of curly braces,
# we are probably a bareword hash key
if ( $token->{content} eq '{' and $t->{line} =~ /\G\s*\}/gc ) {
return 1;
}
}
# In addition, if the word is followed by => it is probably
# also actually a word and not a regex.
if ( $t->{line} =~ /\G\s*=>/gc ) {
return 1;
}
# Otherwise we probably aren't forced
'';
}
1;
=pod
=head1 TO DO
- Add C<function>, C<method> etc detector methods
=head1 SUPPORT
See the L<support section|PPI/SUPPORT> in the main module.
=head1 AUTHOR
Adam Kennedy E<lt>adamk@cpan.orgE<gt>
=head1 COPYRIGHT
Copyright 2001 - 2011 Adam Kennedy.
This program is free software; you can redistribute
it and/or modify it under the same terms as Perl itself.
The full text of the license can be found in the
LICENSE file included with this module.
=cut
|