view libs/sratoolkit.2.8.0-centos_linux64/schema/ncbi/ncbi.vschema @ 3:38ad1130d077 draft

planemo upload commit a4fb57231f274270afbfebd47f67df05babffa4a-dirty

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

/*==========================================================================
 * VDB Schema intrinsic types and functions
 */
version 1;

include 'vdb/vdb.vschema';
include 'insdc/insdc.vschema';


/*--------------------------------------------------------------------------
 * data types
 */

// N-encoded phred has values limited to 1..63 and 0 used for N
typedef INSDC:quality:phred NCBI:quality:n_encoded:phred;
// N-encoded log-odds has values limite to -5..40 and -6 for N
typedef INSDC:quality:log_odds NCBI:quality:n_encoded:log_odds;

// these types have been restated
alias INSDC:dna:text INSDC:fasta;
alias INSDC:4na:packed INSDC:dna:4na;
alias INSDC:2na:packed INSDC:dna:2na;
alias INSDC:2na:packed NCBI:2na;
alias INSDC:2cs:packed INSDC:color:2cs;
alias INSDC:2cs:packed NCBI:2cs;
alias INSDC:quality:phred NCBI:qual1;
alias NCBI:quality:n_encoded:phred NCBI:SRA:enc_qual1;

// 16-bit integer sample data
typedef I16 NCBI:isamp1;

// 32-bit floating point sample data
typedef F32 NCBI:fsamp1, NCBI:fsamp4 [ 4 ];

// ASN.1
typedef B8 NCBI:asn:binary; 
typedef ascii NCBI:asn:text;

// GenInfo id - 64 bit because we are almost out of 32 bit ids
typedef U64 NCBI:gi;

// Taxonomy id
typedef U32 NCBI:taxid;

// Genbank status
typedef U32 NCBI:gb_state;


/*--------------------------------------------------------------------------
 * formats
 *  many of these formats are older than the current corresponding vdb fmts
 */

fmtdef merged_t;
fmtdef fp_encoded_t;
fmtdef rl_encoded_t;
fmtdef NCBI:zlib_encoded_t;
fmtdef NCBI:fp_encoded_t;


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


/* merge
 * split
 *  the original versions of these functions
 *  used a slightly different format giving them
 *  a different signature from their vdb counterparts.
 *
 *  here to maintain backward compatibility for
 *  column schema functions
 */
extern function
merged_t NCBI:merge #1.0 ( any in, ... );

extern function
any NCBI:split #1.0 < U32 idx > ( merged_t in )
    = vdb:split;


/* cut
 * paste
 *  these have no compiler type-checking
 */
extern function
any NCBI:cut #1.0 < U32 idx, ... > ( any in )
    = vdb:cut;

extern function
any NCBI:paste #1.0 ( any in, ... )
    = vdb:paste;


/* pack
 * unpack
 *  wildcard typed
 */
extern function
any NCBI:pack #1.0 < U32 from, U32 to > ( any in );

extern function
any NCBI:unpack #1.0 < U32 from, U32 to > ( any in );


/* fp_decode
 *  OBSOLETE
 *  here to handle anything encoded with fp_encode
 */
extern function
any NCBI:fp_decode #1.0 ( fp_encoded_t in );


/* fp_extend
 *  OBSOLETE
 *  here to handle anything encoded with fp_truncate
 */
extern function
any NCBI:fp_extend #1.0 < U32 bits > ( NCBI:fp_encoded_t in );


/* run_length_encode
 * run_length_decode
 */
extern function
rl_encoded_t NCBI:run_length_encode #1.0 ( any in )
    = vdb:rlencode;

extern function
any NCBI:run_length_decode #1.0 ( rl_encoded_t in )
    = vdb:rldecode;


/* zlib
 * unzip
 *  variation on the formatting
 */
extern function
NCBI:zlib_encoded_t NCBI:zlib #1.0 < * I32 strategy, I32 level > ( any in )
    = vdb:zip;

extern function
any NCBI:unzip #1.0 ( NCBI:zlib_encoded_t in );


/* zlib_huffman_compress
 *  invokes zlib in huffman + rle mode
 */
schema function
NCBI:zlib_encoded_t NCBI:zlib_huffman_compress #1.0 ( any in )
{
    // named as Huffman, but apply RLE as well
    return NCBI:zlib < Z_RLE > ( in );
}

/* zlib_compress
 *  standard zlib
 */
schema function
NCBI:zlib_encoded_t NCBI:zlib_compress #1.0 ( any in )
{
    return NCBI:zlib < Z_DEFAULT_STRATEGY > ( in );
}

/* zlib_decompress
 *  alternate name for unzip
 */
alias NCBI:unzip NCBI:zlib_decompress;