/*===========================================================================
*
*                            PUBLIC DOMAIN NOTICE
*               National Center for Biotechnology Information
*
*  This software/database is a "United States Government Work" under the
*  terms of the United States Copyright Act.  It was written as part of
*  the author's official duties as a United States Government employee and
*  thus cannot be copyrighted.  This software/database is freely available
*  to the public for use. The National Library of Medicine and the U.S.
*  Government have not placed any restriction on its use or reproduction.
*
*  Although all reasonable efforts have been taken to ensure the accuracy
*  and reliability of the software and data, the NLM and the U.S.
*  Government do not and cannot warrant the performance or results that
*  may be obtained by using this software or data. The NLM and the U.S.
*  Government disclaim all warranties, express or implied, including
*  warranties of performance, merchantability or fitness for any particular
*  purpose.
*
*  Please cite the author in any work or product based on this material.
*
* ===========================================================================
*
*/

/*==========================================================================
 * NCBI Likelihood & Event schema
 */
version 1;
include 'vdb/vdb.vschema';

typedef U8 INSDC:phred;
typedef ascii INSDC:event:text;
const INSDC:event:text INSDC:event:CHARSET = "ACGT0123B+-";
const INSDC:event:text INSDC:event:ACCEPTSET = "ACGTacgt0123B+-";

extern function < U32 dim >
U32 NCBI:SRA:sort_order #1.0 ( F32[dim] likelihoods );

extern function < U32 dim >
F32 NCBI:SRA:reorder #1.0 ( U32 sort_order, F32[dim] likelihoods );

extern function < U32 dim >
F32 NCBI:SRA:restore_order #1.0 ( U32 sort_order, F32[dim] likelihoods );

extern function < U32 sdim, U32 rdim >
INSDC:phred[rdim] NCBI:SRA:likelihood_to_phred #1.0 ( F32 like_scale, F32[sdim] likelihoods );

extern function < U32 sdim, U32 rdim >
F32[rdim] NCBI:SRA:phred_to_likelihood #1.0 ( F32 like_scale, F32[sdim] phred );

table NCBI:SRA:tbl:pevents #1.0
{
    // event labels - single character events
    extern column
        INSDC:event:text PEVENTS = .PEVENTS;

    physical column < INSDC:event:text >
        zip_encoding #1.0 .PEVENTS = PEVENTS;

    // likelihoods
    extern default column
        F32[4] LIKELIHOODS = likelihoods;
    extern readonly column
        INSDC:phred[4] LIKELIHOODS = phred;

    U32 sort_encode = NCBI:SRA:sort_order < 4 > ( LIKELIHOODS );

    physical column < U32 >
        zip_encoding #1.0 < Z_RLE > .SORT_ORDER = sort_encode;

    F32 reorder = NCBI:SRA:reorder < 4 > ( sort_encode, LIKELIHOODS );
    F32 like_scale = vdb:fixed_vec_sum < F32, 4 > ( reorder );

    physical column < F32 >
        fzip_encoding #1.0 < 4 > .SCALE = like_scale;

    INSDC:phred cut_phred = NCBI:SRA:likelihood_to_phred #1.0 < 4, 3 > ( like_scale, reorder );

    physical column < INSDC:phred >
        zip_encoding #1.0 < 5 > .PHRED = cut_phred;

    // normalization scaling factors
    extern readonly column
        F32 LIKELIHOOD_NORM = .SCALE;

    // phred scores
    extern readonly column
        INSDC:phred[4] PHRED = phred;
};