This file is indexed.

/usr/share/perl5/PPI/Token/Whitespace.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
433
434
435
436
437
438
439
440
441
442
443
444
445
446
package PPI::Token::Whitespace;

=pod

=head1 NAME

PPI::Token::Whitespace - Tokens representing ordinary white space

=head1 INHERITANCE

  PPI::Token::Whitespace
  isa PPI::Token
      isa PPI::Element

=head1 DESCRIPTION

As a full "round-trip" parser, PPI records every last byte in a
file and ensure that it is included in the L<PPI::Document> object.

This even includes whitespace. In fact, Perl documents are seen
as "floating in a sea of whitespace", and thus any document will
contain vast quantities of C<PPI::Token::Whitespace> objects.

For the most part, you shouldn't notice them. Or at least, you
shouldn't B<have> to notice them.

This means doing things like consistently using the "S for significant"
series of L<PPI::Node> and L<PPI::Element> methods to do things.

If you want the nth child element, you should be using C<schild> rather
than C<child>, and likewise C<snext_sibling>, C<sprevious_sibling>, and
so on and so forth.

=head1 METHODS

Again, for the most part you should really B<not> need to do anything
very significant with whitespace.

But there are a couple of convenience methods provided, beyond those
provided by the parent L<PPI::Token> and L<PPI::Element> classes.

=cut

use strict;
use Clone      ();
use PPI::Token ();

use vars qw{$VERSION @ISA};
BEGIN {
	$VERSION = '1.220';
	@ISA     = 'PPI::Token';
}

=pod

=head2 null

Because L<PPI> sees documents as sitting on a sort of substrate made of
whitespace, there are a couple of corner cases that get particularly
nasty if they don't find whitespace in certain places.

Imagine walking down the beach to go into the ocean, and then quite
unexpectedly falling off the side of the planet. Well it's somewhat
equivalent to that, including the whole screaming death bit.

The C<null> method is a convenience provided to get some internals
out of some of these corner cases.

Specifically it create a whitespace token that represents nothing,
or at least the null string C<''>. It's a handy way to have some
"whitespace" right where you need it, without having to have any
actual characters.

=cut

my $null;

sub null {
	$null ||= $_[0]->new('');
	Clone::clone($null);
}

### XS -> PPI/XS.xs:_PPI_Token_Whitespace__significant 0.900+
sub significant() { '' }

=pod

=head2 tidy

C<tidy> is a convenience method for removing unneeded whitespace.

Specifically, it removes any whitespace from the end of a line.

Note that this B<doesn't> include POD, where you may well need
to keep certain types of whitespace. The entire POD chunk lives
in its own L<PPI::Token::Pod> object.

=cut

sub tidy {
	$_[0]->{content} =~ s/^\s+?(?>\n)//;
	1;
}





#####################################################################
# Parsing Methods

# Build the class and commit maps
use vars qw{ @CLASSMAP @COMMITMAP %MATCHWORD };
BEGIN {
	@CLASSMAP  = ();
	@COMMITMAP = ();
	foreach (
		'a' .. 'u', 'w', 'y', 'z', 'A' .. 'Z', '_'
	) {
		$COMMITMAP[ord $_] = 'PPI::Token::Word';
	}
	foreach ( qw!; [ ] { } )! )       { $COMMITMAP[ord $_] = 'PPI::Token::Structure' }
	foreach ( 0 .. 9 )                { $CLASSMAP[ord $_]  = 'Number'   }
	foreach ( qw{= ? | + > . ! ~ ^} ) { $CLASSMAP[ord $_]  = 'Operator' }
	foreach ( qw{* $ @ & : %} )       { $CLASSMAP[ord $_]  = 'Unknown'  }

	# Miscellaneous remainder
	$COMMITMAP[ord '#'] = 'PPI::Token::Comment';
	$COMMITMAP[ord 'v'] = 'PPI::Token::Number::Version';
	$CLASSMAP[ord ',']  = 'PPI::Token::Operator';
	$CLASSMAP[ord "'"]  = 'Quote::Single';
	$CLASSMAP[ord '"']  = 'Quote::Double';
	$CLASSMAP[ord '`']  = 'QuoteLike::Backtick';
	$CLASSMAP[ord '\\'] = 'Cast';
	$CLASSMAP[ord '_']  = 'Word';
	$CLASSMAP[9]        = 'Whitespace'; # A horizontal tab
	$CLASSMAP[10]       = 'Whitespace'; # A newline
	$CLASSMAP[12]       = 'Whitespace'; # A form feed
	$CLASSMAP[13]       = 'Whitespace'; # A carriage return
	$CLASSMAP[32]       = 'Whitespace'; # A normal space

	# Words (functions and keywords) after which a following / is
	# almost certainly going to be a regex
	%MATCHWORD = map { $_ => 1 } qw{
		return
		split
		if
		unless
		grep
		map
	};
}


sub __TOKENIZER__on_line_start {
	my $t    = $_[1];
	my $line = $t->{line};

	# Can we classify the entire line in one go
	if ( $line =~ /^\s*$/ ) {
		# A whitespace line
		$t->_new_token( 'Whitespace', $line );
		return 0;

	} elsif ( $line =~ /^\s*#/ ) {
		# A comment line
		$t->_new_token( 'Comment', $line );
		$t->_finalize_token;
		return 0;

	} elsif ( $line =~ /^=(\w+)/ ) {
		# A Pod tag... change to pod mode
		$t->_new_token( 'Pod', $line );
		if ( $1 eq 'cut' ) {
			# This is an error, but one we'll ignore
			# Don't go into Pod mode, since =cut normally
			# signals the end of Pod mode
		} else {
			$t->{class} = 'PPI::Token::Pod';
		}
		return 0;

	} elsif ( $line =~ /^use v6\-alpha\;/ ) {
		# Indicates a Perl 6 block. Make the initial
		# implementation just suck in the entire rest of the
		# file.
		my @perl6;
		while ( 1 ) {
			my $line6 = $t->_get_line;
			last unless defined $line6;
			push @perl6, $line6;
		}
		push @{ $t->{perl6} }, join '', @perl6;

		# We only sucked in the block, we don't actually do
		# anything to the "use v6..." line. So return as if
		# we didn't find anything at all.
		return 1;
	}

	1;
}

sub __TOKENIZER__on_char {
	my $t    = $_[1];
	my $char = ord substr $t->{line}, $t->{line_cursor}, 1;

	# Do we definitely know what something is?
	return $COMMITMAP[$char]->__TOKENIZER__commit($t) if $COMMITMAP[$char];

	# Handle the simple option first
	return $CLASSMAP[$char] if $CLASSMAP[$char];

	if ( $char == 40 ) {  # $char eq '('
		# Finalise any whitespace token...
		$t->_finalize_token if $t->{token};

		# Is this the beginning of a sub prototype?
		# We are a sub prototype IF
		# 1. The previous significant token is a bareword.
		# 2. The one before that is the word 'sub'.
		# 3. The one before that is a 'structure'

		# Get the three previous significant tokens
		my $tokens = $t->_previous_significant_tokens(3);
		if ( $tokens ) {
			# A normal subroutine declaration
			my $p1 = $tokens->[1];
			my $p2 = $tokens->[2];
			if (
				$tokens->[0]->isa('PPI::Token::Word')
				and
				$p1->isa('PPI::Token::Word')
				and
				$p1->content eq 'sub'
				and (
					$p2->isa('PPI::Token::Structure')
					or (
						$p2->isa('PPI::Token::Whitespace')
						and
						$p2->content eq ''
					)
				)
			) {
				# This is a sub prototype
				return 'Prototype';
			}

			# An prototyped anonymous subroutine
			my $p0 = $tokens->[0];
			if ( $p0->isa('PPI::Token::Word') and $p0->content eq 'sub'
				# Maybe it's invoking a method named 'sub'
				and not ( $p1 and $p1->isa('PPI::Token::Operator') and $p1->content eq '->')
			) {
				return 'Prototype';
			}
		}

		# This is a normal open bracket
		return 'Structure';

	} elsif ( $char == 60 ) { # $char eq '<'
		# Finalise any whitespace token...
		$t->_finalize_token if $t->{token};

		# This is either "less than" or "readline quote-like"
		# Do some context stuff to guess which.
		my $prev = $t->_last_significant_token;

		# The most common group of less-thans are used like
		# $foo < $bar
		# 1 < $bar
		# $#foo < $bar
		return 'Operator' if $prev->isa('PPI::Token::Symbol');
		return 'Operator' if $prev->isa('PPI::Token::Magic');
		return 'Operator' if $prev->isa('PPI::Token::Number');
		return 'Operator' if $prev->isa('PPI::Token::ArrayIndex');

		# If it is <<... it's a here-doc instead
		my $next_char = substr( $t->{line}, $t->{line_cursor} + 1, 1 );
		if ( $next_char eq '<' ) {
			return 'Operator';
		}

		# The most common group of readlines are used like
		# while ( <...> )
		# while <>;
		my $prec = $prev->content;
		if ( $prev->isa('PPI::Token::Structure') and $prec eq '(' ) {
			return 'QuoteLike::Readline';
		}
		if ( $prev->isa('PPI::Token::Word') and $prec eq 'while' ) {
			return 'QuoteLike::Readline';
		}
		if ( $prev->isa('PPI::Token::Operator') and $prec eq '=' ) {
			return 'QuoteLike::Readline';
		}
		if ( $prev->isa('PPI::Token::Operator') and $prec eq ',' ) {
			return 'QuoteLike::Readline';
		}

		if ( $prev->isa('PPI::Token::Structure') and $prec eq '}' ) {
			# Could go either way... do a regex check
			# $foo->{bar} < 2;
			# grep { .. } <foo>;
			pos $t->{line} = $t->{line_cursor};
			if ( $t->{line} =~ m/\G<(?!\d)\w+>/gc ) {
				# Almost definitely readline
				return 'QuoteLike::Readline';
			}
		}

		# Otherwise, we guess operator, which has been the default up
		# until this more comprehensive section was created.
		return 'Operator';

	} elsif ( $char == 47 ) { #  $char eq '/'
		# Finalise any whitespace token...
		$t->_finalize_token if $t->{token};

		# This is either a "divided by" or a "start regex"
		# Do some context stuff to guess ( ack ) which.
		# Hopefully the guess will be good enough.
		my $prev = $t->_last_significant_token;
		my $prec = $prev->content;

		# Most times following an operator, we are a regex.
		# This includes cases such as:
		# ,  - As an argument in a list 
		# .. - The second condition in a flip flop
		# =~ - A bound regex
		# !~ - Ditto
		return 'Regexp::Match' if $prev->isa('PPI::Token::Operator');

		# After a symbol
		return 'Operator' if $prev->isa('PPI::Token::Symbol');
		if ( $prec eq ']' and $prev->isa('PPI::Token::Structure') ) {
			return 'Operator';
		}

		# After another number
		return 'Operator' if $prev->isa('PPI::Token::Number');

		# After going into scope/brackets
		if (
			$prev->isa('PPI::Token::Structure')
			and (
				$prec eq '('
				or
				$prec eq '{'
				or
				$prec eq ';'
			)
		) {
			return 'Regexp::Match';
		}

		# Functions and keywords
		if (
			$MATCHWORD{$prec}
			and
			$prev->isa('PPI::Token::Word')
		) {
			return 'Regexp::Match';
		}

		# Or as the very first thing in a file
		return 'Regexp::Match' if $prec eq '';

		# What about the char after the slash? There's some things
		# that would be highly illogical to see if its an operator.
		my $next_char = substr $t->{line}, $t->{line_cursor} + 1, 1;
		if ( defined $next_char and length $next_char ) {
			if ( $next_char =~ /(?:\^|\[|\\)/ ) {
				return 'Regexp::Match';
			}
		}

		# Otherwise... erm... assume operator?
		# Add more tests here as potential cases come to light
		return 'Operator';

	} elsif ( $char == 120 ) { # $char eq 'x'
		# x followed immediately by a digit can be the x
		# operator or a word.  Disambiguate by checking
		# whether the previous token is an operator that cannot be
		# followed by the x operator, e.g.: +.
		#
		# x followed immediately by '=' is the 'x=' operator, not
		# 'x ='. An important exception is x followed immediately by
		# '=>', which makes the x into a bareword.
		pos $t->{line} = $t->{line_cursor} + 1;
		return 'Operator'
			if $t->_current_x_is_operator and $t->{line} =~ m/\G(?:\d|(?!(=>|[\w\s])))/gc;

		# Otherwise, commit like a normal bareword
		return PPI::Token::Word->__TOKENIZER__commit($t);

	} elsif ( $char == 45 ) { # $char eq '-'
		# Look for an obvious operator operand context
		my $context = $t->_opcontext;
		if ( $context eq 'operator' ) {
			return 'Operator';
		} else {
			# More logic needed
			return 'Unknown';
		}

	} elsif ( $char >= 128 ) { # Outside ASCII
		return 'PPI::Token::Word'->__TOKENIZER__commit($t) if $t =~ /\w/;
		return 'Whitespace' if $t =~ /\s/;
        }


	# All the whitespaces are covered, so what to do
	### For now, die
	PPI::Exception->throw("Encountered unexpected character '$char'");
}

sub __TOKENIZER__on_line_end {
	$_[1]->_finalize_token if $_[1]->{token};
}

1;

=pod

=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