Day 15 of the Perl6 2014 Advent Calendar

advent_15.pm6

grammar FASTA::Grammar {
    token TOP { <record>+ }

    token record { ">"<id><comment>?"\n"<sequence> }

    token id { <-[\ \n]>+ }

    token comment { " "<-[\n]>+ }

    proto rule sequence {*}
          rule sequence:sym<dna> { <[ACGTRYKMSWBDHVNX\-\n]>+ }
          rule sequence:sym<rna> { <[ACGURYKMSWBDHVNX\-\n]>+ }
          rule sequence:sym<aa> { <[A..Z\*\-\n]>+ }
}

class Seq {
    has Str $.id = "";
    has Str $.comment = "";
    has Str $.sequence = "";

    multi method Numeric (Seq:D: --> Numeric) {
        $.sequence.codes;
    }

    multi method Bag (Seq:D: --> Bag) {
        bag $.sequence.comb;
    }

    multi method Str (Seq:D: --> Str) {
        $.sequence;
    }

    multi method gist (Seq:D: --> Str) {
        ">$.id $.comment\n$.sequence";
    }
}

class FASTA::Actions {
    method TOP($/) {
        make $<record>>>.ast;
    }
    method record($/) {
        make Seq.new(
            id => ~$<id>,
            comment => ($<comment>) ?? (~$<comment>).trim !! '',
            sequence => $<sequence>.subst("\n","", :g)
        );
    }
}

Grammar_trace.txt

TOP
>
|  record
>
|  |  id
>
|  |  * MATCH "hello"
>
|  |  comment
>
|  |  * FAIL
>
|  |  sequence
>
|  |  |  sequence:sym<dna>
>
|  |  |  * MATCH "GCTATATAAGC\n"
>
|  |  * MATCH "GCTATATAAGC\n"
>
|  * MATCH ">hello\nGCTATATAAGC\n"
>
|  record
>
|  |  id
>
|  |  * MATCH "world"
>
|  |  comment
>
|  |  * MATCH " prot"
>
|  |  sequence
>
|  |  |  sequence:sym<dna>
>
|  |  |  * FAIL
>
|  |  |  sequence:sym<rna>
>
|  |  |  * FAIL
>
|  |  |  sequence:sym<aa>
>
|  |  |  * MATCH "TATAKEKEKELKL\n"
>
|  |  * MATCH "TATAKEKEKELKL\n"
>
|  * MATCH ">world prot\nTATAKEKEKELKL\n"
>
|  record
>
|  * FAIL
>
* MATCH ">hello\nGCTATATAAGC\n>world prot\nTATAKEKEKELKL\n"

test.fa

>hello
GCTATATAAGC
>world prot
TATAKEKEKELKL