Last active
August 29, 2015 14:06
-
-
Save rns/8241288fe9351f29a28a to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
input : <[/] Trading 10mm ABC 2.5 19 05/06 mkt can use 50mm> | |
extracted: <ABC 2.5 19> | |
input : <XYZ 6.5 15 10-2B 106-107 B3 AAA- 1.646MM 2x2> | |
extracted: <XYZ 6.5 15> |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
use 5.010; | |
use strict; | |
use warnings; | |
use YAML; | |
use Marpa::R2 2.090; # for parse() | |
my $g = Marpa::R2::Scanless::G->new( { | |
source => \(<<'END_OF_SOURCE'), | |
:default ::= action => [ name, value] | |
lexeme default = action => [ name, value] latm => 1 | |
info ::= item+ | |
item ::= (chars_if_any) ticket (whitespace) float (whitespace) int (whitespace) (chars_if_any) | |
ticket ::= capital capital capital | |
float ::= digits '.' digits | |
int ::= digits | |
capital ::= [A-Z] | |
digits ::= [0-9]+ | |
chars_if_any ::= [\d\D]* | |
whitespace ::= [\s]+ | |
END_OF_SOURCE | |
} ); | |
my @tests = ( | |
[ | |
'[/] Trading 10mm ABC 2.5 19 05/06 mkt can use 50mm', | |
'ABC 2.5 19' | |
], | |
[ | |
'XYZ 6.5 15 10-2B 106-107 B3 AAA- 1.646MM 2x2', | |
'XYZ 6.5 15' | |
] | |
); | |
for my $test (@tests){ | |
my ($input, $expected) = @$test; | |
my $r = Marpa::R2::Scanless::R->new( { | |
grammar => $g, | |
too_many_earley_items => 500, | |
# trace_terminals => 1 | |
} ); | |
eval {$r->read(\$input)} || warn "Parse failure, progress report is:\n" . $r->show_progress; | |
my $ast = $r->value; | |
unless (defined $ast){ | |
die "No parse"; | |
} | |
say "input : <$input>\n", "extracted: <", ast_process( ${$ast} ), ">"; | |
} | |
sub ast_process{ | |
my $ast = shift; | |
if (ref $ast){ | |
my ($id, @children) = @$ast; | |
if ($id eq 'info'){ | |
return join "\n", map { ast_process( $_ ) } @children; | |
} | |
if ($id eq 'item'){ | |
return join " ", map { ast_process( $_ ) } @children; | |
} | |
elsif ($id =~ /^ticket|float|int$/){ | |
return join "", map { ast_process( $_ ) } @children; | |
} | |
elsif ($id eq 'capital'){ | |
return $children[0]; | |
} | |
elsif ($id eq 'digits'){ | |
return join '', @children; | |
} | |
} | |
else{ | |
return $ast; | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment