p6.p6

#!/usr/bin/env perl6

grammar CDHit {
    token TOP    { <record>+ }
    token record { <id> <member>+ }
    token id     { ^^ <seq_id> \n }
    token num    { \d+ }
    token len    { <-[,]>+ }
    token seq_id { '>' (\S+) }
    token pct    { <[\d.]>+ '%' }
    token member {
        <num> \s+ <len> ',' \s+ <seq_id> \s+ 'at' \s+ <pct> \n
    }
}

class CDHit::Actions {
    method TOP ($/) { make $<record>».made }

    method record ($/) {
        make { id => $<id>.made, members => $<member>».made }
    }

    method id ($/) { make $<seq_id>.made }

    method seq_id ($/) { make ~$/[0] }

    method member ($/) {
        make {
            num => $<num>,
            len => $<len>,
            id  => $<seq_id>,
            pct => $<pct>,
        }
    }
}

subset File of Str where *.IO.f;

sub MAIN {
    my $result = CDHit.parse(q:to/IN/, :actions(CDHit::Actions)).made;
    >Cluster_5086
    0	358aa, >gi|317183610|gb|ADV... at 66.76%
    1	361aa, >gi|315661179|gb|ADU... at 70.36%
    >Cluster_10030
    0	85aa, >gi|315661182|gb|ADU... at 64.71%
    1	85aa, >gi|268687968|emb|CB... at 75.29%
    2	100aa, >gi|747172712|gb|AJE... at 74.00%
    IN
    dd $result;
}