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

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


/*--------------------------------------------------------------------------
 * NCBI:SRA:tbl:clip
 *  common clip column processing
 *  shared by 454 and ion-torrent
 *
 *  uses spotdesc because it has a dependency upon spot_len
 *
 * history:
 *  1.0.1 - base explicitly upon spotdesc #1.0.1
 *  1.0.2 - base explicitly upon spotdesc #1.0.2
 */
table NCBI:SRA:tbl:clip #1.0.2 = INSDC:SRA:tbl:spotdesc #1.0.2
{
    /* CLIP_ADAPTER_LEFT, CLIP_ADAPTER_RIGHT
     *  adapter clips in 1-based coordinates
     *  when value is 0, implies that they are NOT SET
     */
    column INSDC:coord:one CLIP_ADAPTER_LEFT = out_clip_adapt_left;
    column INSDC:coord:one CLIP_ADAPTER_RIGHT = out_clip_adapt_right;

    // casts are required to allow multple storage formats
    INSDC:coord:one out_clip_adapt_left = cast ( .CLIP_ADAPTER_LEFT );
    INSDC:coord:one out_clip_adapt_right = cast ( .CLIP_ADAPTER_RIGHT );


    /* CLIP_QUALITY_LEFT, CLIP_QUALITY_RIGHT
     *  quality clips in 1-based coordinates
     *  when value is 0, implies that they are NOT SET
     */
    column INSDC:coord:one CLIP_QUALITY_LEFT = out_clip_qual_left;
    column INSDC:coord:one CLIP_QUALITY_RIGHT = out_clip_qual_right;

    // casts are required to allow multple storage formats
    INSDC:coord:one out_clip_qual_left
        = cast ( .CLIP_QUALITY_LEFT )
        | < INSDC:coord:one > echo < 1 > ();
    INSDC:coord:one out_clip_qual_right
        = cast ( .CLIP_QUALITY_RIGHT )
        | cast ( spot_len );

    // support for reading 16-bit clips, as in v1 schema
    readonly column U16 CLIP_ADAPTER_LEFT
        = .CLIP_ADAPTER_LEFT
        | cast ( out_clip_adapt_left );
    readonly column U16 CLIP_ADAPTER_RIGHT
        = .CLIP_ADAPTER_RIGHT
        | cast ( out_clip_adapt_right );
    readonly column U16 CLIP_QUALITY_LEFT = cast ( out_clip_qual_left );
    readonly column U16 CLIP_QUALITY_RIGHT = cast ( out_clip_qual_right );


    /* CLIP-MANIA
     */

    // 1-based fully-closed right edge is row-length
    INSDC:coord:one spot_right = ( INSDC:coord:one ) spot_len;

    // processed 1-based coordinates >= 1
    INSDC:coord:one lim_clip_adapt_left
        = < INSDC:coord:one > clip < 1, 0x7FFFFFFF > ( out_clip_adapt_left );
    INSDC:coord:one max_clip_adapt_right
        = < INSDC:coord:one, INSDC:coord:one > map < 0, 0x7FFFFFFF > ( out_clip_adapt_right );
    INSDC:coord:one lim_clip_adapt_right
        = < INSDC:coord:one > min ( spot_right, max_clip_adapt_right );
    INSDC:coord:one lim_clip_qual_left
        = < INSDC:coord:one > clip < 1, 0x7FFFFFFF > ( out_clip_qual_left );
    INSDC:coord:one max_clip_qual_right
        = < INSDC:coord:one, INSDC:coord:one > map < 0, 0x7FFFFFFF > ( out_clip_qual_right );
    INSDC:coord:one lim_clip_qual_right
        = < INSDC:coord:one > min ( spot_right, max_clip_qual_right );

    // read-only columns with 0-based coordinates
    readonly column INSDC:coord:zero CLIP_ADAPTER_LEFT
        = ( INSDC:coord:zero ) < I32 > diff < 1 > ( lim_clip_adapt_left );
    readonly column INSDC:coord:zero CLIP_ADAPTER_RIGHT
        = ( INSDC:coord:zero ) < I32 > diff < 1 > ( lim_clip_adapt_right );
    readonly column INSDC:coord:zero CLIP_QUALITY_LEFT
        = ( INSDC:coord:zero ) < I32 > diff < 1 > ( lim_clip_qual_left );
    readonly column INSDC:coord:zero CLIP_QUALITY_RIGHT
        = ( INSDC:coord:zero ) < I32 > diff < 1 > ( lim_clip_qual_right );

    // combined clips
    INSDC:coord:one max_clip_left
        = < INSDC:coord:one > max ( lim_clip_adapt_left, lim_clip_qual_left )
        | lim_clip_adapt_left
        | lim_clip_qual_left;
    INSDC:coord:zero max_zclip_left
        = ( INSDC:coord:zero ) < I32 > diff < 1 > ( max_clip_left );
    INSDC:coord:one min_clip_right
        = < INSDC:coord:one > min ( lim_clip_adapt_right, lim_clip_qual_right )
        | lim_clip_adapt_right
        | lim_clip_qual_right;


    /* TRIMMED SEQUENCE
     *  need to find the 0-based trim_start and trim_len
     */
    INSDC:coord:zero bio_start
        = NCBI:SRA:bio_start ( out_read_start, out_read_type );
    INSDC:coord:zero trim_start
        = < INSDC:coord:zero > max ( bio_start, max_zclip_left )
        | bio_start;

    INSDC:coord:zero bio_end
        = NCBI:SRA:bio_end < false > ( out_read_start, out_read_type, out_read_len );

    I32 trim_stop
        = < I32 > max ( min_clip_right, trim_start )
        | spot_right;
    INSDC:coord:len trim_len
        = ( INSDC:coord:len ) < I32 > diff ( trim_stop, trim_start );
};