/*===========================================================================
 *
 *                            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 Generic Fastq Sequence Read Archive schema
 */
version 1;

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

/* tokenize_spot_name - currently ascii only capability */

extern function NCBI:SRA:spot_name_token
    NCBI:SRA:GenericFastq:tokenize_spot_name #1 ( ascii name );

/*--------------------------------------------------------------------------
 * NCBI:SRA:GenericFastq:sequence
 *  Generic Fastq SRA Platform
 *
 * history:
 *  1.0.1 - base explicitly upon sra #2.1.4
 *  2.0.0 - NCBI:tbl:base_space uses metadata RNA_Flag to support RNA reads
 */
table NCBI:SRA:GenericFastq:sequence #2
    = NCBI:SRA:tbl:sra #2.1.4
    , NCBI:tbl:base_space #3
    , NCBI:tbl:phred_quality #2.0.6
    , NCBI:SRA:tbl:clip #1.0.2
{
    ascii platform_name
        = < ascii > echo < "UNDEFINED" > ();

    INSDC:SRA:platform_id out_platform
        = < INSDC:SRA:platform_id > echo < SRA_PLATFORM_UNDEFINED > ();

	/* ascii only spot name tokenizer */

    NCBI:SRA:spot_name_token out_spot_name_tok
        = NCBI:SRA:GenericFastq:tokenize_spot_name ( _out_name );

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

    /* 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;
}

database NCBI:SRA:GenericFastq:db #2
{
    table NCBI:SRA:GenericFastq:sequence #2.0 SEQUENCE;
};

/*--------------------------------------------------------------------------
 * Illumina db defined based on sra/illumina.vschema
 */
database NCBI:SRA:Illumina:db #2
{
    table NCBI:SRA:Illumina:tbl:phred:v2 #2 SEQUENCE;
};

/*--------------------------------------------------------------------------
 * NCBI:SRA:GenericFastq:sequence_no_name
 *  Generic Fastq SRA Platform (without name)
 *
 * history:
 *  1.0.1 - base explicitly upon sra #2.1.4
 *  2.0.0 - NCBI:tbl:base_space uses metadata RNA_Flag to support RNA reads
 */
table NCBI:SRA:GenericFastq:sequence_no_name #2
    = NCBI:SRA:tbl:sra #2.1.4
    , NCBI:tbl:base_space #3
    , NCBI:tbl:phred_quality #2.0.6
    , NCBI:SRA:tbl:clip #1.0.2
{
    ascii platform_name
        = < ascii > echo < "UNDEFINED" > ();

    INSDC:SRA:platform_id out_platform
        = < INSDC:SRA:platform_id > echo < SRA_PLATFORM_UNDEFINED > ();

    /* 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;
}

database NCBI:SRA:GenericFastqNoNames:db #2
{
    table NCBI:SRA:GenericFastq:sequence_no_name #2.0 SEQUENCE;
};

/*--------------------------------------------------------------------------
 * NCBI:SRA:GenericFastq:sequence_log_odds
 *  Generic Fastq SRA Platform (for log_odds)
 *
 * history:
 *  1.0.1 - base explicitly upon sra #2.1.4
 *  2.0.0 - NCBI:tbl:base_space uses metadata RNA_Flag to support RNA reads
 */
table NCBI:SRA:GenericFastq:sequence_log_odds #2
    = NCBI:SRA:tbl:sra #2.1.4
    , NCBI:tbl:base_space #3
    , NCBI:tbl:log_odds_quality #2.1.0
    , NCBI:SRA:tbl:clip #1.0.2
{
    ascii platform_name
        = < ascii > echo < "UNDEFINED" > ();

    INSDC:SRA:platform_id out_platform
        = < INSDC:SRA:platform_id > echo < SRA_PLATFORM_UNDEFINED > ();

	/* ascii only spot name tokenizer */

    NCBI:SRA:spot_name_token out_spot_name_tok
        = NCBI:SRA:GenericFastq:tokenize_spot_name ( _out_name );

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

    /* 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;
}

database NCBI:SRA:GenericFastqLogOdds:db #2
{
    table NCBI:SRA:GenericFastq:sequence_log_odds #2 SEQUENCE;
};

/*--------------------------------------------------------------------------
 * NCBI:SRA:GenericFastq:sequence_nanopore
 *  Oxford Nanopore SRA Platform
 *
 * history:
 *  1.0.1 - base explicitly upon sra #2.1.4
 *  2.0.0 - NCBI:tbl:base_space uses metadata RNA_Flag to support RNA reads
 */
table NCBI:SRA:GenericFastq:sequence_nanopore #2
    = NCBI:SRA:tbl:sra #2.1.4
    , NCBI:tbl:base_space #3
    , NCBI:tbl:phred_quality #2.0.6
{
    ascii platform_name
        = < ascii > echo < "OXFORD_NANOPORE" > ();

    INSDC:SRA:platform_id out_platform
        = < INSDC:SRA:platform_id > echo < SRA_PLATFORM_OXFORD_NANOPORE > ();

	/* ascii only spot name tokenizer */

    NCBI:SRA:spot_name_token out_spot_name_tok
        = NCBI:SRA:GenericFastq:tokenize_spot_name ( _out_name );

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

	/* channel and read number columns */

    extern column < U32 > izip_encoding #1 CHANNEL;
    extern column < U32 > izip_encoding #1 READ_NUMBER;
}

/*--------------------------------------------------------------------------
 * NCBI:SRA:GenericFastq:consensus_nanopore
 *  Oxford Nanopore SRA Platform
 *
 * history:
 *  1.0.1 - base explicitly upon sra #2.1.4
 *  2.0.0 - NCBI:tbl:base_space uses metadata RNA_Flag to support RNA reads
 */
table NCBI:SRA:GenericFastq:consensus_nanopore #2
    = NCBI:SRA:tbl:sra #2.1.4
    , NCBI:tbl:base_space #3
    , NCBI:tbl:phred_quality #2.0.6
{
    ascii platform_name
        = < ascii > echo < "OXFORD_NANOPORE" > ();

    INSDC:SRA:platform_id out_platform
        = < INSDC:SRA:platform_id > echo < SRA_PLATFORM_OXFORD_NANOPORE > ();

	/* ascii only spot name tokenizer */

    NCBI:SRA:spot_name_token out_spot_name_tok
        = NCBI:SRA:GenericFastq:tokenize_spot_name ( _out_name );

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

	/* channel and read number columns */

    extern column < U32 > izip_encoding #1 CHANNEL;
    extern column < U32 > izip_encoding #1 READ_NUMBER;
}

database NCBI:SRA:GenericFastqNanopore:db #2
{
    table NCBI:SRA:GenericFastq:sequence_nanopore #2.0 SEQUENCE;
    table NCBI:SRA:GenericFastq:consensus_nanopore #2.0 CONSENSUS;
};

database NCBI:SRA:GenericFastqNanoporeConsensusOnly:db #2
{
    table NCBI:SRA:GenericFastq:consensus_nanopore #2.0 CONSENSUS;
};

/*--------------------------------------------------------------------------
 * NCBI:SRA:GenericFastq:absolid
 *  Generic fastq for AB Solid platform
 *
 * history:
 *  1.0.1 - base explicitly upon sra #2.1.4
 */
table NCBI:SRA:GenericFastq:absolid #1.0.1
    = NCBI:SRA:tbl:sra #2.1.4
    , NCBI:tbl:color_space #2.1.0
    , NCBI:tbl:phred_quality #2.0.6
    , NCBI:SRA:tbl:clip #1.0.2
{
    ascii platform_name
        = < ascii > echo < "UNDEFINED" > ();

    INSDC:SRA:platform_id out_platform
        = < INSDC:SRA:platform_id > echo < SRA_PLATFORM_UNDEFINED > ();

	/* ascii only spot name tokenizer */

    NCBI:SRA:spot_name_token out_spot_name_tok
        = NCBI:SRA:GenericFastq:tokenize_spot_name ( _out_name );

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

    /* 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;
}

database NCBI:SRA:GenericFastqAbsolid:db #1.0.1
{
    table NCBI:SRA:GenericFastq:absolid #1.0.1 SEQUENCE;
};