/*===========================================================================
 *
 *                            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.
 *
 * ===========================================================================
 *
 */

version 1;

include 'vdb/vdb.vschema';

table NCBI:tbl:IR:raw #1
{
    extern column <ascii>  zip_encoding READ_GROUP;
    extern column <ascii>  zip_encoding NAME;
    extern column   <I32> izip_encoding READNO;
    extern column <ascii>  zip_encoding PLATFORM;
    extern column <ascii>  zip_encoding SEQUENCE;
    
    /* the following would all be empty for unaligned */
    extern column <ascii>  zip_encoding REFERENCE;
    extern column <ascii>  zip_encoding STRAND;
    extern column   <I32> izip_encoding POSITION;
    extern column <ascii>  zip_encoding CIGAR;

    extern column <ascii>  zip_encoding QUALITY;

    extern column <ascii> zip_encoding REJECT_REASON;
};

table NCBI:tbl:aligned:SPOT_STATISTICS #1
{
    extern column ascii READ_GROUP;
    extern column U8  LAYOUT;
    extern column F64 FREQ_FORWARD;
    extern column F64 FREQ_REVERSE;
    extern column F64 FRAGMENT_LENGTH_AVERAGE;
    extern column F64 FRAGMENT_LENGTH_STD_DEV;
    extern column U32 FRAGMENT_LENGTH_MODE;
    extern column U32 FRAGMENT_LENGTH_MEDIAN;
    extern column U32 FRAGMENT_LENGTH_EQUIPART;
};

table NCBI:tbl:IR:CONTIGS #1
{
    extern column <ascii>  zip_encoding REFERENCE_1;
    extern column   <I32> izip_encoding START_1;
    extern column   <I32> izip_encoding END_1;

    extern column <ascii>  zip_encoding REFERENCE_2;
    extern column   <I32> izip_encoding START_2;
    extern column   <I32> izip_encoding END_2;

    extern column   <U32> izip_encoding COUNT;
    extern column <ascii>  zip_encoding READ_GROUP;
};

table NCBI:tbl:aligned:CONTIGS #1
{
    extern column <ascii>  zip_encoding READ_GROUP;
    extern column <ascii>  zip_encoding REFERENCE;
    extern column   <I32> izip_encoding START;
    extern column   <I32> izip_encoding END;

/* these statistics were gathered from the fragments that the contig was built from */
    extern column   <F32>  zip_encoding SEQ_LENGTH_AVERAGE;
    extern column   <F32>  zip_encoding SEQ_LENGTH_STD_DEV;
    extern column   <F32>  zip_encoding REF_LENGTH_AVERAGE;
    extern column   <F32>  zip_encoding REF_LENGTH_STD_DEV;

    extern column   <U32> izip_encoding FRAGMENT_COUNT;
    extern column   <F32>  zip_encoding FRAGMENT_LENGTH_AVERAGE;
    extern column   <F32>  zip_encoding FRAGMENT_LENGTH_STD_DEV;
};

table NCBI:tbl:aligned:REFERENCE #1
{
    extern column <ascii>  zip_encoding NAME;

/* these columns are empty for a "real" reference */
    extern column <ascii>  zip_encoding REFERENCE_1; ///< the name of a "real" reference (another record in this table)
    extern column   <I32> izip_encoding START_1;
    extern column   <I32> izip_encoding END_1;

    extern column   <I32> izip_encoding GAP; ///< if >1, this value is a suggested adjustment to the fragment length of all fragments that aligned here;

    extern column <ascii>  zip_encoding REFERENCE_2; ///< the name of a "real" reference (another record in this table)
    extern column   <I32> izip_encoding START_2;
    extern column   <I32> izip_encoding END_2;
};

table NCBI:tbl:aligned:FRAGMENT #1
{
    extern column <ascii>  zip_encoding READ_GROUP;
    extern column <ascii>  zip_encoding PLATFORM;

    extern column <ascii>  zip_encoding REFERENCE; ///< the NAME in the REFERENCE table; not a canonical link
    extern column   <I64> izip_encoding CONTIG; ///< the ROW ID in the REFERENCE table; this is the canonical link between a fragments and its coresponding record in the REFERENCE table
    extern column <ascii>  zip_encoding LAYOUT; ///< encoded as readno strand readno strand, e.g. 1+2- or 2+1-
    extern column   <I32> izip_encoding POSITION; ///< this is the position of 5'-most base of the 5'-most mate; unlike SAM, it is not the position of the first aligned base
    extern column   <I32> izip_encoding LENGTH; ///< the fragment length as implied by the alignment; i.e. the distance from the 5'-most base to the 3'-most base, but see GAP in the REFERENCE table
    extern column <ascii>  zip_encoding CIGAR; ///< the CIGAR, as given, of the 5'-most mate + "0P" + the CIGAR of the other mate

    extern column <ascii>  zip_encoding NAME; ///< the name of the fragment, as given, i.e. QNAME or SRA spot id
    extern column <ascii>  zip_encoding SEQUENCE;
    extern column <ascii>  zip_encoding QUALITY;
};

database NCBI:db:IR:raw #1
{
    table NCBI:tbl:IR:raw #1.0 RAW;
    table NCBI:tbl:IR:raw #1.0 DISCARDED;
    table NCBI:tbl:IR:CONTIGS #1.0 CONTIGS;
};

database NCBI:db:IR:aligned #1
{
    table NCBI:tbl:aligned:FRAGMENT #1.0 FRAGMENTS;
    table NCBI:tbl:aligned:REFERENCE #1.0 REFERENCES;
    table NCBI:tbl:IR:raw #1.0 REJECTS;
    table NCBI:tbl:aligned:CONTIGS #1.0 CONTIGS;
};