view release on metacpan or  search on metacpan

inc/Inline/C/Parser/RegExp.pm  view on Meta::CPAN

use strict; use warnings;
package Inline::C::Parser::RegExp;

use Carp;

sub register {
    {
        extends => [qw(C)],
        overrides => [qw(get_parser)],
    }
}

sub get_parser {
    Inline::C::_parser_test($_[0]->{CONFIG}{DIRECTORY}, "Inline::C::Parser::RegExp::get_parser called\n") if $_[0]->{CONFIG}{_TESTING};
    bless {}, 'Inline::C::Parser::RegExp'
}

sub code {
    my ($self,$code) = @_;

    # These regular expressions were derived from Regexp::Common v0.01.
    my $RE_comment_C = q{(?:(?:\/\*)(?:(?:(?!\*\/)[\s\S])*)(?:\*\/))};
    my $RE_comment_Cpp = q{(?:\/\*(?:(?!\*\/)[\s\S])*\*\/|\/\/[^\n]*\n)};
    my $RE_quoted = (
        q{(?:(?:\")(?:[^\\\"]*(?:\\.[^\\\"]*)*)(?:\")}
        . q{|(?:\')(?:[^\\\']*(?:\\.[^\\\']*)*)(?:\'))}
    );
    our $RE_balanced_brackets; $RE_balanced_brackets =
        qr'(?:[{]((?:(?>[^{}]+)|(??{$RE_balanced_brackets}))*)[}])';
    our $RE_balanced_parens; $RE_balanced_parens   =
        qr'(?:[(]((?:(?>[^()]+)|(??{$RE_balanced_parens}))*)[)])';

    # First, we crush out anything potentially confusing.
    # The order of these _does_ matter.
    $code =~ s/$RE_comment_C/ /go;
    $code =~ s/$RE_comment_Cpp/ /go;
    $code =~ s/^\#.*(\\\n.*)*//mgo;
    #$code =~ s/$RE_quoted/\"\"/go; # Buggy, if included.
    $code =~ s/$RE_balanced_brackets/{ }/go;

    $self->{_the_code_most_recently_parsed} = $code; # Simplifies debugging.

    my $normalize_type = sub {
        # Normalize a type for lookup in a typemap.
        my($type) = @_;

        # Remove "extern".
        # But keep "static", "inline", "typedef", etc,
        #  to cause desirable typemap misses.
        $type =~ s/\bextern\b//g;

        # Whitespace: only single spaces, none leading or trailing.
        $type =~ s/\s+/ /g;
        $type =~ s/^\s//; $type =~ s/\s$//;

        # Adjacent "derivative characters" are not separated by whitespace,
        # but _are_ separated from the adjoining text.
        # [ Is really only * (and not ()[]) needed??? ]
        $type =~ s/\*\s\*/\*\*/g;
        $type =~ s/(?<=[^ \*])\*/ \*/g;

        return $type;
    };

    # The decision of what is an acceptable declaration was originally
    # derived from Inline::C::grammar.pm version 0.30 (Inline 0.43).

    my $re_plausible_place_to_begin_a_declaration = qr {
        # The beginning of a line, possibly indented.
        # (Accepting indentation allows for C code to be aligned with
        #  its surrounding perl, and for backwards compatibility with
        #  Inline 0.43).
        (?m: ^ ) \s*
    }xo;