This file is indexed.

/usr/share/perl5/PPIx/Regexp/StringTokenizer.pm is in libppix-regexp-perl 0.047-1.

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
package PPIx::Regexp::StringTokenizer;

use 5.006;

use strict;
use warnings;

use base qw{ PPIx::Regexp::Tokenizer };

use Carp;
use PPIx::Regexp::Constant qw{
    TOKEN_UNKNOWN
};

our $VERSION = '0.047';

{
    # Names of classes containing tokenization machinery. There are few
    # known ordering requirements, since each class recognizes its own,
    # and I have tried to prevent overlap. Absent such constraints, the
    # order is in perceived frequency of acceptance, to keep the search
    # as short as possible. If I were conscientious I would gather
    # statistics on this.
    my @classes = (	# TODO make readonly when acceptable way appears
	'PPIx::Regexp::Token::Literal',
	'PPIx::Regexp::Token::Interpolation',
	'PPIx::Regexp::Token::Control',			# Note 1
#	'PPIx::Regexp::Token::CharClass::Simple',	# Note 2
#	'PPIx::Regexp::Token::Quantifier',
#	'PPIx::Regexp::Token::Greediness',
#	'PPIx::Regexp::Token::CharClass::POSIX',	# Note 3
#	'PPIx::Regexp::Token::Structure',
#	'PPIx::Regexp::Token::Assertion',
#	'PPIx::Regexp::Token::Backreference',
#	'PPIx::Regexp::Token::Operator',		# Note 4
    );

    # Note 1: If we are in quote mode ( \Q ... \E ), Control makes a
    #		literal out of anything it sees other than \E. So it
    #		needs to come before almost all other tokenizers. Not
    #		Literal, which already makes literals, and not
    #		Interpolation, which is legal in quote mode, but
    #		everything else.

    # Note 2: CharClass::Simple must come after Literal, because it
    #		relies on Literal to recognize a Unicode named character
    #		( \N{something} ), so any \N that comes through to it
    #		must be the \N simple character class (which represents
    #		anything but a newline, and was introduced in Perl
    #		5.11.0.

    # Note 3: CharClass::POSIX has to come before Structure, since both
    #		look for square brackets, and CharClass::POSIX is the
    #		more particular.

    # Note 4: Operator relies on Literal making the characters literal
    #		if they appear in a context where they can not be
    #		operators, and Control making them literals if quoting,
    #		so it must come after both.

    # Return the declared tokenizer classes.
    sub __tokenizer_classes {
	return @classes;
    }

}

my %bare_delim = map { $_ => 1 } qw{ ' " ` };

sub __PPIX_TOKENIZER__init {
    my ( $self ) = @_;

    my @tokens;

    if ( $self->find_regexp( qr{ \A \s* << }smx ) ) {

	my ( $leading_white, $next_white, $delim );
	if ( $self->find_regexp( qr{ \A ( \s* ) << ( \w+ \n ) }smx ) ) {
	    ( $leading_white, $delim ) = $self->capture();
	    $next_white = '';
	} elsif ( $self->find_regexp(
		qr{ \A ( \s* ) << ( \s+ ) ( ( ["'] ) .*? \4 \n ) }smx )
	    ) {
	    ( $leading_white, $next_white, $delim ) = $self->capture();
	} else {
	    return $self->__init_error();
	}

	$self->{type} = '<<';

	$self->{delimiter_start} = $delim;
	if ( $delim =~ s/ \A ( ["'] ) ( .* ) \1 \n \z /$2\n/smx ) {
	    my $quote = $1;
	    $delim =~ s/ \\ (?= \Q$quote\E ) //smxg;
	}

	'' ne $leading_white
	    and push @tokens, $self->make_token( length $leading_white,
	    'PPIx::Regexp::Token::Whitespace' );
	push @tokens, $self->make_token( length $self->{type},
	    'PPIx::Regexp::Token::Structure' );
	'' ne $next_white
	    and push @tokens, $self->make_token( length $next_white,
	    'PPIx::Regexp::Token::Whitespace' );
	push @tokens, $self->make_token( length $self->{delimiter_start},
	    'PPIx::Regexp::Token::Delimiter' );

	my ( $offset ) = $self->find_regexp( qr{ \Q$delim\E }smx )
	    or return $self->__init_error();
	my $cursor_limit = $self->{cursor_curr} + $offset;
	$self->{trace}
	    and warn "Tokenizer found here doc end delimiter at $cursor_limit\n";
	$self->{cursor_limit} = $cursor_limit;
	$self->{cursor_modifiers} = $cursor_limit + length $delim;
	$self->{delimiter_finish} = $delim;

    } elsif ( $self->find_regexp(
	    qr{ \A ( \s* ) ( qq | q | qx )? ( \s* ) ( [^\w\s] ) }smx ) )
    {

	my ( $leading_white, $type, $next_white, $delim ) = $self->capture();

	unless ( defined $type ) {
	    $bare_delim{$delim}
		or return $self->__init_error();
	    $type = '';
	}

	$self->{type} = $type;

	'' ne $leading_white
	    and push @tokens, $self->make_token( length $leading_white,
	    'PPIx::Regexp::Token::Whitespace' );
	push @tokens, $self->make_token( length $type,
	    'PPIx::Regexp::Token::Structure' );
	'' ne $next_white
	    and push @tokens, $self->make_token( length $next_white,
	    'PPIx::Regexp::Token::Whitespace' );

	$self->{delimiter_start} = substr
	    $self->{content},
	    $self->{cursor_curr},
	    1;

	$self->{trace}
	    and warn "Tokenizer found string start delimiter '$self->{delimiter_start}' at $self->{cursor_curr}\n";

	my $offset = $self->find_matching_delimiter()
	    or return $self->__init_error(
	    'Tokenizer found mismatched string delimiters' );

	my $cursor_limit = $self->{cursor_curr} + $offset;
	$self->{trace}
	    and warn "Tokenizer found string end delimiter at $cursor_limit\n";
	$self->{cursor_limit} = $cursor_limit;
	$self->{cursor_modifiers} = $cursor_limit + 1;
	$self->{delimiter_finish} = substr
	    $self->{content},
	    $self->{cursor_limit},
	    1;

	push @tokens, $self->make_token( 1,
	    'PPIx::Regexp::Token::Delimiter' );


    } else {
	return $self->__init_error();
    }

    {
	pos $self->{content} = $self->{cursor_modifiers};
	local $self->{cursor_curr} = $self->{cursor_modifiers};
	local $self->{cursor_limit} = length $self->{content};
	my @trailing;
	if ( my $len = $self->find_regexp( qr{ \A \s+ }smx ) ) {
	    push @trailing, $self->make_token( $len,
		'PPIx::Regexp::Token::Whitespace' );
	}
	if ( my $len = $self->find_regexp( qr{ \A .+ }smx ) ) {
	    push @trailing, $self->make_token( $len, TOKEN_UNKNOWN, {
		    error	=> 'Trailing characters after expression',
		} );
	}
	$self->{trailing_tokens} = \@trailing;
	$self->{effective_modifiers} = undef;
	$self->{modifiers} = [ {} ];
    }

    $self->{find} = undef;

    $self->_set_mode( 'repl' );

    return @tokens;
}

# Return the number of extra delimited parts. This will be 0 for all
# strings.
sub __number_of_extra_parts {
    return 0;
}

# Return the classes for the parts of the expression.
sub __part_classes {
    return ( 'PPIx::Regexp::Structure::Replacement' );
}

{
    my %from_delim = map { $_ => 1 } '', 'qx', '<<';
    my %from_type = map { $_ => 1 } qw{ qq qx };

    sub interpolates {
	my ( $self ) = @_;
	$from_delim{$self->{type}}
	    and return $self->{delimiter_start} !~ m/ \A ' /smx;
	return $from_type{$self->{type}};
    }
}

1;

__END__

=head1 NAME

PPIx::Regexp::StringTokenizer - Tokenize a string literal

=head1 SYNOPSIS

 use PPIx::Regexp::Dumper;
 PPIx::Regexp::Dumper->new( 'qq{foo$bar}', parse => 'string' )
     ->print();

C<PPIx::Regexp::StringTokenizer> is a
L<PPIx::Regexp::Tokenizer|PPIx::Regexp::Tokenizer>.

C<PPIx::Regexp::StringTokenizer> has no descendants.

=head1 DESCRIPTION

This class provides tokenization of string literals.

=head1 METHODS

This class supports no public methods over and above those of the
superclass.

=head1 SEE ALSO

L<PPIx::Regexp::Tokenizer|PPIx::Regexp::Tokenizer>.

=head1 SUPPORT

Support is by the author. Please file bug reports at
L<http://rt.cpan.org>, or in electronic mail to the author.

=head1 AUTHOR

Tom Wyant F<wyant at cpan dot org>

=head1 COPYRIGHT AND LICENSE

Copyright (C) 2015-2016 by Thomas R. Wyant, III

This program is free software; you can redistribute it and/or modify it
under the same terms as Perl 5.10.0. For more details, see the full text
of the licenses in the directory LICENSES.

This program is distributed in the hope that it will be useful, but
without any warranty; without even the implied warranty of
merchantability or fitness for a particular purpose.

=cut

# ex: set textwidth=72 :