File: Code.pm

package info (click to toggle)
libppix-regexp-perl 0.091-1
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 1,524 kB
  • sloc: perl: 8,022; makefile: 8
file content (242 lines) | stat: -rw-r--r-- 6,306 bytes parent folder | download
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
=head1 NAME

PPIx::Regexp::Token::Code - Represent a chunk of Perl embedded in a regular expression.

=head1 SYNOPSIS

 use PPIx::Regexp::Dumper;
 PPIx::Regexp::Dumper->new(
     'qr{(?{print "hello sailor\n"})}smx')->print;

=head1 INHERITANCE

C<PPIx::Regexp::Token::Code> is a
L<PPIx::Regexp::Token|PPIx::Regexp::Token>.

C<PPIx::Regexp::Token::Code> is the parent of
L<PPIx::Regexp::Token::Interpolation|PPIx::Regexp::Token::Interpolation>.

=head1 DESCRIPTION

This class represents a chunk of Perl code embedded in a regular
expression. Specifically, it results from parsing things like

 (?{ code })
 (??{ code })

or from the replacement side of an s///e. Technically, interpolations
are also code, but they parse differently and therefore end up in a
different token.

This token may not appear inside a regex set (i.e. C<(?[ ... ])>. If
found, it will become a C<PPIx::Regexp::Token::Unknown>.

=head1 METHODS

This class provides the following public methods. Methods not documented
here are private, and unsupported in the sense that the author reserves
the right to change or remove them without notice.

=cut

package PPIx::Regexp::Token::Code;

use strict;
use warnings;

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

use PPI::Document;
use PPIx::Regexp::Constant qw{
    COOKIE_REGEX_SET
    LOCATION_COLUMN
    LOCATION_LOGICAL_LINE
    LOCATION_LOGICAL_FILE
    @CARP_NOT
};
use PPIx::Regexp::Util qw{ __instance };

our $VERSION = '0.091';

use constant TOKENIZER_ARGUMENT_REQUIRED => 1;
use constant VERSION_WHEN_IN_REGEX_SET => undef;

sub __new {
    my ( $class, $content, %arg ) = @_;

    defined $arg{perl_version_introduced}
	or $arg{perl_version_introduced} = '5.005';

    my $self = $class->SUPER::__new( $content, %arg );

    # TODO sort this out, since Token::Interpolation is a subclass, and
    # those are legal in regex sets
    if ( $arg{tokenizer}->cookie( COOKIE_REGEX_SET ) ) {
	my $ver = $self->VERSION_WHEN_IN_REGEX_SET()
	    or return $self->__error( 'Code token not valid in Regex set' );
	$self->{perl_version_introduced} < $ver
	    and $self->{perl_version_introduced} = $ver;
    }

    $arg{tokenizer}->__recognize_postderef( $self )
	and $self->{perl_version_introduced} < 5.019005
	and $self->{perl_version_introduced} = '5.019005';

    return $self;
}

sub content {
    my ( $self ) = @_;
    if ( exists $self->{content} ) {
	return $self->{content};
    } elsif ( exists $self->{ppi} ) {
	return ( $self->{content} = $self->{ppi}->content() );
    } else {
	return;
    }
}

sub explain {
    return 'Perl expression';
}

=head2 is_matcher

This method returns C<undef> because a static analysis can not in
general tell whether an interpolated value matches anything.

=cut

sub is_matcher { return undef; }	## no critic (ProhibitExplicitReturnUndef)

=head2 ppi

This convenience method returns the L<PPI::Document|PPI::Document>
representing the content. This document should be considered read only.

B<Note> that if the location of the invocant is available the PPI
document will have stuff prefixed to it to make the location of the
tokens in the new document consistent with the location. This "stuff"
will include at least a C<#line> directive, and maybe leading white
space.

=cut

sub ppi {
    my ( $self ) = @_;
    if ( exists $self->{ppi} ) {
	return $self->{ppi};
    } elsif ( exists $self->{content} ) {
	my $content;
	my $location = $self->{location};
	if ( $location ) {
	    my $fn;
	    if( defined( $fn = $location->[LOCATION_LOGICAL_FILE] ) ) {
		$fn =~ s/ (?= [\\"] ) /\\/smxg;
		$content = qq{#line $location->[LOCATION_LOGICAL_LINE] "$fn"\n};
	    } else {
		$content = qq{#line $location->[LOCATION_LOGICAL_LINE]\n};
	    }
	    $content .= ' ' x ( $location->[LOCATION_COLUMN] - 1 );
	}

	$content .= $self->__ppi_normalize_content();

	$self->{ppi} = PPI::Document->new( \$content );

	if ( $location ) {
	    # Generate locations now.
	    $self->{ppi}->location();
	    # Remove the stuff we originally injected. NOTE that we can
	    # only get away with doing this if the removal does not
	    # invalidate the locations of the other tokens that we just
	    # generated.
	    my $elem;
	    # Remove the '#line' directive if we find it
	    $elem = $self->{ppi}->child( 0 )
		and $elem->isa( 'PPI::Token::Comment' )
		and $elem->content() =~ m/ \A \#line\b /smx
		and $elem->remove();
	    # Remove the white space if we find it, and if it in fact
	    # represents only the white space we injected to get the
	    # column numbers right.
	    my $wid = $location->[LOCATION_COLUMN] - 1;
	    $wid
		and $elem = $self->{ppi}->child( 0 )
		and $elem->isa( 'PPI::Token::Whitespace' )
		and $wid == length $elem->content()
		and $elem->remove();
	}

	return $self->{ppi};

    } else {
	return;
    }
}

sub width {
    return ( undef, undef );
}

sub __ppi_normalize_content {
    my ( $self ) = @_;
    return $self->{content};
}

# Return true if the token can be quantified, and false otherwise
# sub can_be_quantified { return };

{
    no warnings qw{ qw };	## no critic (ProhibitNoWarnings)

    my %accept = map { $_ => 1 } qw{ $ $# @ % & * };

    # Say what casts are accepted, since not all are in an
    # interpolation.
    sub __postderef_accept_cast {
	return \%accept;
    }
}

sub __PPIX_TOKENIZER__regexp {
    my ( undef, $tokenizer, $character ) = @_;

    $character eq '{' or return;

    my $offset = $tokenizer->find_matching_delimiter()
	or return;

    return $offset + 1;	# to include the closing delimiter.
}

1;

__END__

=head1 SUPPORT

Support is by the author. Please file bug reports at
L<https://rt.cpan.org/Public/Dist/Display.html?Name=PPIx-Regexp>,
L<https://github.com/trwyant/perl-PPIx-Regexp/issues>, or in
electronic mail to the author.

=head1 AUTHOR

Thomas R. Wyant, III F<wyant at cpan dot org>

=head1 COPYRIGHT AND LICENSE

Copyright (C) 2009-2023, 2025 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 :