Re: validating a quoted string

[choroba]

It seems there hasn't been enough Marpa examples today. If you want to validate and split on unquoted space, build a proper parser!

#!/usr/bin/perl
use warnings;
use strict;
use feature qw{ say };

use Marpa::R2;

my $dsl = << '__DSL__';

:default ::= action => ::first
lexeme default = latm => 1

List   ::= Token                       action => [value]
         | Token space List            action => list
Token  ::= Naked
         | Quoted
         | Quoted Token                action => concat
         | Naked Quoted                action => concat
         | Naked Quoted Token          action => concat
Quoted ::= ('"') InQ  ('"')
InQ    ::= CharQ InQ                   action => concat
         | CharQ
CharQ  ::= nonq
         | backslash quote             action => second
Naked  ::= CharO+                      action => concat
CharO  ::= nonqs
         | backslash quote             action => second
         | backslash single_space      action => second

backslash    ~ [\\]
quote        ~ '"'
single_space ~ [\s]
nonq         ~ [^"\\]+
nonqs        ~ [^"\s\\]+
space        ~ [\s]+

__DSL__

sub concat        { shift; join q(), @_ }
sub list          { [ $_[1], @{ $_[3] } ] }
sub second        { $_[2] }

my $grammar = 'Marpa::R2::Scanless::G'->new({ source => \$dsl });

for my $string (
                 '"ab" "cd"',
                 '"ef" "gh ij"',
                 'kl mn',
                 'op "qr st"',
                 '"uv \"wx" yz',
                 'AB\ CD',
                 'EF"GH"',
                 '"IJ""KL""MN"',
                 'OP"QR"\ "ST"UV"WX YZ"\"ABC"DEF"\"GHI\"',
                 '"abc\ def"',
                 '"ghi "jkl"',
                 'mno "pqr stu',
               ) {
    my $v;
    eval {
        $v = $grammar->parse(\$string, 'main');
    1 } or warn "invalid $string\n";
    say join '|', @$$v if $v;
}

Output:

ab|cd
ef|gh ij
kl|mn
op|qr st
uv "wx|yz
AB CD
EFGH
IJKLMN
OPQR STUVWX YZ"ABCDEF"GHI"
invalid "abc\ def"
invalid "ghi "jkl"
invalid mno "pqr stu