/*===========================================================================
*
*                            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 Ion Torrent Sequence Read Archive schema
 */
version 1;

include 'ncbi/sra.vschema';
include 'ncbi/spotname.vschema';
include 'ncbi/clip.vschema';


/*--------------------------------------------------------------------------
 * functions
 */


/* tokenize_spot_name
 *  scans name on input
 *  tokenizes into parts
 */
extern function NCBI:SRA:spot_name_token
    NCBI:SRA:IonTorrent:tokenize_spot_name #1 ( ascii name );


/*--------------------------------------------------------------------------
 * table
 */

physical INSDC:position:one NCBI:SRA:IonTorrent:encoding:POSITION #1
{
    decode
    {
        I32 pos_1st_deriv = iunzip ( @ );
        return ( INSDC:position:one ) < I32 > integral ( pos_1st_deriv );
    }
    encode
    {
        I32 pos_1st_deriv = < I32 > deriv ( @ );
        return izip ( pos_1st_deriv );
    }
}

/* IonTorrent:tbl
 *
 * history:
 *  1.0.1 - updated ancestry
 *  1.0.2 - updated ancestry
 *  1.0.3 - updated ancestry
 *  1.0.4 - updated ancestry
 *  2.0.0 - updated ancestry
 */
table NCBI:SRA:IonTorrent:tbl:v2 #2
    = INSDC:SRA:tbl:sra #1.0.4
    , NCBI:SRA:tbl:sra_nopos #2.1.4
    , NCBI:tbl:base_space #3
    , NCBI:tbl:phred_quality #2.0
    , NCBI:SRA:tbl:clip #1.0.2
{
    /* PLATFORM is always ION_TORRENT */
    ascii platform_name
        = < ascii > echo < "ION_TORRENT" > ();

    /* NAME tokenizing and coordinates
     *  most work happens in skeyname table
     */
    NCBI:SRA:spot_name_token out_spot_name_tok
        = NCBI:SRA:IonTorrent:tokenize_spot_name ( _out_name );

    NCBI:SRA:spot_name_token in_spot_name_tok
        = NCBI:SRA:IonTorrent:tokenize_spot_name ( NAME );

    // special sequences
    column < INSDC:dna:text > zip_encoding FLOW_CHARS;
    column < INSDC:dna:text > zip_encoding KEY_SEQUENCE;

    // position stored as normal 1-based coordinate
    INSDC:position:one out_position = .POSITION;
    physical column NCBI:SRA:IonTorrent:encoding:POSITION
        .POSITION = POSITION;


    // clips
    physical column < INSDC:coord:one > izip_encoding
        .CLIP_ADAPTER_LEFT = CLIP_ADAPTER_LEFT;
    physical column < INSDC:coord:one > izip_encoding
        .CLIP_ADAPTER_RIGHT = CLIP_ADAPTER_RIGHT;
    physical column < INSDC:coord:one > izip_encoding
        .CLIP_QUALITY_LEFT = CLIP_QUALITY_LEFT;
    physical column < INSDC:coord:one > izip_encoding
        .CLIP_QUALITY_RIGHT = CLIP_QUALITY_RIGHT;

    // signal
    column < NCBI:isamp1 > izip_encoding SIGNAL;
};