mirror of
https://github.com/Unidata/netcdf-c.git
synced 2024-11-27 07:30:33 +08:00
3ffe7be446
re: Discussion https://github.com/Unidata/netcdf-c/discussions/2214 The primary change is to support so-called "standard filters". A standard filter is one that is defined by the following netcdf-c API: ```` int nc_def_var_XXX(int ncid, int varid, size_t nparams, unsigned* params); int nc_inq_var_XXXX(int ncid, int varid, int* usefilterp, unsigned* params); ```` So for example, zstandard would be a standard filter by defining the functions *nc_def_var_zstandard* and *nc_inq_var_zstandard*. In order to define these functions, we need a new dispatch function: ```` int nc_inq_filter_avail(int ncid, unsigned filterid); ```` This function, combined with the existing filter API can be used to implement arbitrary standard filters using a simple code pattern. Note that I would have preferred that this function return a list of all available filters, but HDF5 does not support that functionality. So this PR implements the dispatch function and implements the following standard functions: + bzip2 + zstandard + blosc Specific test cases are also provided for HDF5 and NCZarr. Over time, other specific standard filters will be defined. ## Primary Changes * Add nc_inq_filter_avail() to netcdf-c API. * Add standard filter implementations to test use of *nc_inq_filter_avail*. * Bump the dispatch table version number and add to all the relevant dispatch tables (libsrc, libsrcp, etc). * Create a program to invoke nc_inq_filter_avail so that it is accessible to shell scripts. * Cleanup szip support to properly support szip when HDF5 is disabled. This involves detecting libsz separately from testing if HDF5 supports szip. * Integrate shuffle and fletcher32 into the existing filter API. This means that, for example, nc_def_var_fletcher32 is now a wrapper around nc_def_var_filter. * Extend the Codec defaulting to allow multiple default shared libraries. ## Misc. Changes * Modify configure.ac/CMakeLists.txt to look for the relevant libraries implementing standard filters. * Modify libnetcdf.settings to list available standard filters (including deflate and szip). * Add CMake test modules to locate libbz2 and libzstd. * Cleanup the HDF5 memory manager function use in the plugins. * remove unused file include//ncfilter.h * remove tests for the HDF5 memory operations e.g. H5allocate_memory. * Add flag to ncdump to force use of _Filter instead of _Deflate or _Shuffle or _Fletcher32. Used for testing.
360 lines
14 KiB
C
360 lines
14 KiB
C
/* * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * *
|
||
* Copyright by The HDF Group. *
|
||
* Copyright by the Board of Trustees of the University of Illinois. *
|
||
* All rights reserved. *
|
||
* *
|
||
* This file is part of HDF5. The full HDF5 copyright notice, including *
|
||
* terms governing use, modification, and redistribution, is contained in *
|
||
* the COPYING file, which can be found at the root of the source code *
|
||
* distribution tree, or in https://support.hdfgroup.org/ftp/HDF5/releases. *
|
||
* If you do not have access to either file, you may request a copy from *
|
||
* help@hdfgroup.org. *
|
||
* * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * */
|
||
|
||
#ifdef HAVE_CONFIG_H
|
||
#include "config.h"
|
||
#endif
|
||
|
||
#include <stdlib.h>
|
||
#include <string.h>
|
||
#include <math.h>
|
||
#include "netcdf_filter_build.h"
|
||
|
||
#ifdef HAVE_SZ
|
||
|
||
#include <szlib.h>
|
||
#include "H5Zszip.h"
|
||
|
||
/* Local function prototypes */
|
||
static htri_t H5Z___can_apply_szip(hid_t dcpl_id, hid_t type_id, hid_t space_id);
|
||
static herr_t H5Z___set_local_szip(hid_t dcpl_id, hid_t type_id, hid_t space_id);
|
||
static size_t H5Z___filter_szip(unsigned flags, size_t cd_nelmts,
|
||
const unsigned cd_values[], size_t nbytes, size_t *buf_size, void **buf);
|
||
|
||
/* This message derives from H5Z */
|
||
H5Z_class2_t H5Z_SZIP[1] = {{
|
||
H5Z_CLASS_T_VERS, /* H5Z_class_t version */
|
||
H5Z_FILTER_SZIP, /* Filter id number */
|
||
1, /* Assume encoder present: check before registering */
|
||
1, /* decoder_present flag (set to true) */
|
||
"szip", /* Filter name for debugging */
|
||
H5Z___can_apply_szip, /* The "can apply" callback */
|
||
H5Z___set_local_szip, /* The "set local" callback */
|
||
H5Z___filter_szip, /* The actual filter function */
|
||
}};
|
||
|
||
|
||
|
||
/*-------------------------------------------------------------------------
|
||
* Function: H5Z___can_apply_szip
|
||
*
|
||
* Purpose: Check the parameters for szip compression for validity and
|
||
* whether they fit a particular dataset.
|
||
*
|
||
* Note: This function currently range-checks for datatypes with
|
||
* 8-bit boundaries (8, 16, 24, etc.). It appears that the szip
|
||
* library can actually handle 1-24, 32 & 64 bit samples. If
|
||
* this becomes important, we should make the checks below more
|
||
* sophisticated and have them check for n-bit datatypes of the
|
||
* correct size, etc. - QAK
|
||
*
|
||
* Return: Success: Non-negative
|
||
* Failure: Negative
|
||
*
|
||
* Programmer: Quincey Koziol
|
||
* Monday, April 7, 2003
|
||
*
|
||
*-------------------------------------------------------------------------
|
||
*/
|
||
static htri_t
|
||
H5Z___can_apply_szip(hid_t H5_ATTR_UNUSED dcpl_id, hid_t type_id, hid_t H5_ATTR_UNUSED space_id)
|
||
{
|
||
htri_t ret_value = TRUE; /* Return value */
|
||
#ifdef USE_HDF5
|
||
unsigned dtype_size; /* Datatype's size (in bits) */
|
||
H5T_order_t dtype_order; /* Datatype's endianness order */
|
||
|
||
FUNC_ENTER_STATIC
|
||
|
||
/* Get datatype's size, for checking the "bits-per-pixel" */
|
||
if((dtype_size = (8 * H5Tget_size(type_id))) == 0)
|
||
HGOTO_ERROR(H5E_PLINE, H5E_BADTYPE, FAIL, "bad datatype size")
|
||
|
||
/* Range check datatype's size */
|
||
if(dtype_size > 32 && dtype_size != 64)
|
||
HGOTO_ERROR(H5E_ARGS, H5E_BADVALUE, FALSE, "invalid datatype size")
|
||
|
||
/* Get datatype's endianness order */
|
||
if((dtype_order = H5Tget_order(type_id)) == H5T_ORDER_ERROR)
|
||
HGOTO_ERROR(H5E_PLINE, H5E_BADTYPE, FAIL, "can't retrieve datatype endianness order")
|
||
|
||
/* Range check datatype's endianness order */
|
||
/* (Note: this may not handle non-atomic datatypes well) */
|
||
if(dtype_order != H5T_ORDER_LE && dtype_order != H5T_ORDER_BE)
|
||
HGOTO_ERROR(H5E_ARGS, H5E_BADVALUE, FALSE, "invalid datatype endianness order")
|
||
|
||
done:
|
||
FUNC_LEAVE_NOAPI(ret_value)
|
||
#else /*!USE_HDF5*/
|
||
return ret_value;
|
||
#endif /*USE_HDF5*/
|
||
} /* end H5Z___can_apply_szip() */
|
||
|
||
|
||
/*-------------------------------------------------------------------------
|
||
* Function: H5Z___set_local_szip
|
||
*
|
||
* Purpose: Set the "local" dataset parameters for szip compression.
|
||
*
|
||
* Return: Success: Non-negative
|
||
* Failure: Negative
|
||
*
|
||
* Programmer: Quincey Koziol
|
||
* Monday, April 7, 2003
|
||
*
|
||
*-------------------------------------------------------------------------
|
||
*/
|
||
|
||
static herr_t
|
||
H5Z___set_local_szip(hid_t dcpl_id, hid_t type_id, hid_t space_id)
|
||
{
|
||
herr_t ret_value = SUCCEED; /* Return value */
|
||
|
||
#ifdef USE_HDF5
|
||
unsigned flags; /* Filter flags */
|
||
size_t cd_nelmts = H5Z_SZIP_USER_NPARMS; /* Number of filter parameters */
|
||
unsigned cd_values[H5Z_SZIP_TOTAL_NPARMS]; /* Filter parameters */
|
||
hsize_t dims[H5S_MAX_RANK+1]; /* Dataspace (i.e. chunk) dimensions */
|
||
int ndims; /* Number of (chunk) dimensions */
|
||
H5T_order_t dtype_order; /* Datatype's endianness order */
|
||
size_t dtype_size; /* Datatype's size (in bits) */
|
||
size_t dtype_precision; /* Datatype's precision (in bits) */
|
||
size_t dtype_offset; /* Datatype's offset (in bits) */
|
||
hsize_t scanline; /* Size of dataspace's fastest changing dimension */
|
||
|
||
FUNC_ENTER_STATIC
|
||
|
||
/* Get the filter's current parameters */
|
||
if(H5Pget_filter_by_id1(dcpl_id, H5Z_FILTER_SZIP, &flags, &cd_nelmts, cd_values, 0, NULL) < 0)
|
||
HGOTO_ERROR(H5E_PLINE, H5E_CANTGET, FAIL, "can't get szip parameters")
|
||
|
||
/* Get datatype's size, for checking the "bits-per-pixel" */
|
||
if((dtype_size = (8 * H5Tget_size(type_id))) == 0)
|
||
HGOTO_ERROR(H5E_PLINE, H5E_BADTYPE, FAIL, "bad datatype size");
|
||
|
||
/* Get datatype's precision, in case is less than full bits */
|
||
if((dtype_precision = H5Tget_precision(type_id)) == 0)
|
||
HGOTO_ERROR(H5E_PLINE, H5E_BADTYPE, FAIL, "bad datatype precision");
|
||
|
||
if(dtype_precision < dtype_size) {
|
||
dtype_offset = H5Tget_offset(type_id);
|
||
if(dtype_offset != 0)
|
||
dtype_precision = dtype_size;
|
||
} /* end if */
|
||
if(dtype_precision > 24) {
|
||
if(dtype_precision <= 32)
|
||
dtype_precision = 32;
|
||
else if(dtype_precision <= 64)
|
||
dtype_precision = 64;
|
||
} /* end if */
|
||
|
||
/* Set "local" parameter for this dataset's "bits-per-pixel" */
|
||
cd_values[H5Z_SZIP_PARM_BPP] = dtype_precision;
|
||
|
||
/* Get dimensions for dataspace */
|
||
if((ndims = H5Sget_simple_extent_dims(space_id, dims, NULL)) < 0)
|
||
HGOTO_ERROR(H5E_PLINE, H5E_CANTGET, FAIL, "unable to get dataspace dimensions")
|
||
|
||
/* Set "local" parameter for this dataset's "pixels-per-scanline" */
|
||
/* (Use the chunk's fastest changing dimension size) */
|
||
HDassert(ndims > 0);
|
||
scanline = dims[ndims - 1];
|
||
|
||
/* Adjust scanline if it is smaller than number of pixels per block or
|
||
if it is bigger than maximum pixels per scanline, or there are more than
|
||
SZ_MAX_BLOCKS_PER_SCANLINE blocks per scanline */
|
||
|
||
/* Check the pixels per block against the 'scanline' size */
|
||
if(scanline < cd_values[H5Z_SZIP_PARM_PPB]) {
|
||
hssize_t npoints; /* Number of points in the dataspace */
|
||
|
||
/* Get number of elements for the dataspace; use
|
||
total number of elements in the chunk to define the new 'scanline' size */
|
||
if((npoints = H5Sget_simple_extent_npoints(space_id)) < 0)
|
||
HGOTO_ERROR(H5E_PLINE, H5E_CANTGET, FAIL, "unable to get number of points in the dataspace")
|
||
if(npoints < cd_values[H5Z_SZIP_PARM_PPB])
|
||
HGOTO_ERROR(H5E_ARGS, H5E_BADVALUE, FAIL, "pixels per block greater than total number of elements in the chunk")
|
||
scanline = MIN((cd_values[H5Z_SZIP_PARM_PPB] * SZ_MAX_BLOCKS_PER_SCANLINE), npoints);
|
||
}
|
||
else {
|
||
if(scanline <= SZ_MAX_PIXELS_PER_SCANLINE)
|
||
scanline = MIN((cd_values[H5Z_SZIP_PARM_PPB] * SZ_MAX_BLOCKS_PER_SCANLINE), scanline);
|
||
else
|
||
scanline = cd_values[H5Z_SZIP_PARM_PPB] * SZ_MAX_BLOCKS_PER_SCANLINE;
|
||
} /* end else */
|
||
|
||
/* Assign the final value to the scanline */
|
||
H5_CHECKED_ASSIGN(cd_values[H5Z_SZIP_PARM_PPS], unsigned, scanline, hsize_t);
|
||
|
||
/* Get datatype's endianness order */
|
||
if((dtype_order = H5Tget_order(type_id)) == H5T_ORDER_ERROR)
|
||
HGOTO_ERROR(H5E_PLINE, H5E_BADTYPE, FAIL, "bad datatype endianness order")
|
||
|
||
/* Set the correct endianness flag for szip */
|
||
/* (Note: this may not handle non-atomic datatypes well) */
|
||
cd_values[H5Z_SZIP_PARM_MASK] &= ~(H5_SZIP_LSB_OPTION_MASK|H5_SZIP_MSB_OPTION_MASK);
|
||
switch(dtype_order) {
|
||
case H5T_ORDER_LE: /* Little-endian byte order */
|
||
cd_values[H5Z_SZIP_PARM_MASK] |= H5_SZIP_LSB_OPTION_MASK;
|
||
break;
|
||
|
||
case H5T_ORDER_BE: /* Big-endian byte order */
|
||
cd_values[H5Z_SZIP_PARM_MASK] |= H5_SZIP_MSB_OPTION_MASK;
|
||
break;
|
||
|
||
case H5T_ORDER_ERROR:
|
||
case H5T_ORDER_VAX:
|
||
case H5T_ORDER_MIXED:
|
||
case H5T_ORDER_NONE:
|
||
default:
|
||
HGOTO_ERROR(H5E_PLINE, H5E_BADTYPE, FAIL, "bad datatype endianness order")
|
||
} /* end switch */
|
||
|
||
/* Modify the filter's parameters for this dataset */
|
||
if(H5Pmodify_filter(dcpl_id, H5Z_FILTER_SZIP, flags, H5Z_SZIP_TOTAL_NPARMS, cd_values) < 0)
|
||
HGOTO_ERROR(H5E_PLINE, H5E_CANTSET, FAIL, "can't set local szip parameters")
|
||
|
||
done:
|
||
FUNC_LEAVE_NOAPI(ret_value)
|
||
#else /*!USE_HDF5*/
|
||
return ret_value;
|
||
#endif /*USE_HDF5*/
|
||
} /* end H5Z___set_local_szip() */
|
||
|
||
|
||
/*-------------------------------------------------------------------------
|
||
* Function: H5Z___filter_szip
|
||
*
|
||
* Purpose: Implement an I/O filter around the 'rice' algorithm in
|
||
* libsz
|
||
*
|
||
* Return: Success: Size of buffer filtered
|
||
* Failure: 0
|
||
*
|
||
* Programmer: Kent Yang
|
||
* Tuesday, April 1, 2003
|
||
*
|
||
*-------------------------------------------------------------------------
|
||
*/
|
||
static size_t
|
||
H5Z___filter_szip(unsigned flags, size_t cd_nelmts, const unsigned cd_values[],
|
||
size_t nbytes, size_t *buf_size, void **buf)
|
||
{
|
||
size_t ret_value = 0; /* Return value */
|
||
size_t size_out = 0; /* Size of output buffer */
|
||
unsigned char *outbuf = NULL; /* Pointer to new output buffer */
|
||
unsigned char *newbuf = NULL; /* Pointer to input buffer */
|
||
SZ_com_t sz_param; /* szip parameter block */
|
||
|
||
FUNC_ENTER_STATIC
|
||
|
||
/* Sanity check to make certain that we haven't drifted out of date with
|
||
* the mask options from the szlib.h header */
|
||
HDassert(H5_SZIP_ALLOW_K13_OPTION_MASK==SZ_ALLOW_K13_OPTION_MASK);
|
||
HDassert(H5_SZIP_CHIP_OPTION_MASK==SZ_CHIP_OPTION_MASK);
|
||
HDassert(H5_SZIP_EC_OPTION_MASK==SZ_EC_OPTION_MASK);
|
||
HDassert(H5_SZIP_LSB_OPTION_MASK==SZ_LSB_OPTION_MASK);
|
||
HDassert(H5_SZIP_MSB_OPTION_MASK==SZ_MSB_OPTION_MASK);
|
||
HDassert(H5_SZIP_NN_OPTION_MASK==SZ_NN_OPTION_MASK);
|
||
HDassert(H5_SZIP_RAW_OPTION_MASK==SZ_RAW_OPTION_MASK);
|
||
|
||
/* Check arguments */
|
||
if (cd_nelmts!=4)
|
||
HGOTO_ERROR(H5E_ARGS, H5E_BADVALUE, 0, "invalid number of filter parameters")
|
||
|
||
/* Copy the filter parameters into the szip parameter block */
|
||
H5_CHECKED_ASSIGN(sz_param.options_mask, int, cd_values[H5Z_SZIP_PARM_MASK], unsigned);
|
||
H5_CHECKED_ASSIGN(sz_param.bits_per_pixel, int, cd_values[H5Z_SZIP_PARM_BPP], unsigned);
|
||
H5_CHECKED_ASSIGN(sz_param.pixels_per_block, int, cd_values[H5Z_SZIP_PARM_PPB], unsigned);
|
||
H5_CHECKED_ASSIGN(sz_param.pixels_per_scanline, int, cd_values[H5Z_SZIP_PARM_PPS], unsigned);
|
||
|
||
/* Input; uncompress */
|
||
if (flags & H5Z_FLAG_REVERSE) {
|
||
uint32_t stored_nalloc; /* Number of bytes the compressed block will expand into */
|
||
size_t nalloc; /* Number of bytes the compressed block will expand into */
|
||
|
||
/* Get the size of the uncompressed buffer */
|
||
newbuf = (unsigned char *)(*buf);
|
||
UINT32DECODE(newbuf,stored_nalloc);
|
||
H5_CHECKED_ASSIGN(nalloc, size_t, stored_nalloc, uint32_t);
|
||
|
||
/* Allocate space for the uncompressed buffer */
|
||
if(NULL == (outbuf = (unsigned char *)H5MM_malloc(nalloc)))
|
||
HGOTO_ERROR(H5E_RESOURCE, H5E_NOSPACE, 0, "memory allocation failed for szip decompression")
|
||
|
||
/* Decompress the buffer */
|
||
size_out=nalloc;
|
||
if(SZ_BufftoBuffDecompress(outbuf, &size_out, newbuf, nbytes-4, &sz_param) != SZ_OK)
|
||
HGOTO_ERROR(H5E_RESOURCE, H5E_NOSPACE, 0, "szip_filter: decompression failed")
|
||
HDassert(size_out==nalloc);
|
||
|
||
/* Free the input buffer */
|
||
H5MM_xfree(*buf);
|
||
|
||
/* Set return values */
|
||
*buf = outbuf;
|
||
outbuf = NULL;
|
||
*buf_size = nalloc;
|
||
ret_value = size_out;
|
||
}
|
||
/* Output; compress */
|
||
else {
|
||
unsigned char *dst = NULL; /* Temporary pointer to new output buffer */
|
||
|
||
/* Allocate space for the compressed buffer & header (assume data won't get bigger) */
|
||
if(NULL == (dst=outbuf = (unsigned char *)H5MM_malloc(nbytes+4)))
|
||
HGOTO_ERROR(H5E_RESOURCE, H5E_NOSPACE, 0, "unable to allocate szip destination buffer")
|
||
|
||
/* Encode the uncompressed length */
|
||
H5_CHECK_OVERFLOW(nbytes,size_t,uint32_t);
|
||
UINT32ENCODE(dst,nbytes);
|
||
|
||
/* Compress the buffer */
|
||
size_out = nbytes;
|
||
if(SZ_OK!= SZ_BufftoBuffCompress(dst, &size_out, *buf, nbytes, &sz_param))
|
||
HGOTO_ERROR(H5E_PLINE, H5E_CANTINIT, 0, "overflow")
|
||
HDassert(size_out<=nbytes);
|
||
|
||
/* Free the input buffer */
|
||
H5MM_xfree(*buf);
|
||
|
||
/* Set return values */
|
||
*buf = outbuf;
|
||
outbuf = NULL;
|
||
*buf_size = nbytes+4;
|
||
ret_value = size_out+4;
|
||
}
|
||
|
||
done:
|
||
if(outbuf)
|
||
H5MM_xfree(outbuf);
|
||
FUNC_LEAVE_NOAPI(ret_value)
|
||
}
|
||
|
||
/* External Discovery Functions */
|
||
DLLEXPORT
|
||
H5PL_type_t
|
||
H5PLget_plugin_type(void)
|
||
{
|
||
return H5PL_TYPE_FILTER;
|
||
}
|
||
|
||
DLLEXPORT
|
||
const void*
|
||
H5PLget_plugin_info(void)
|
||
{
|
||
return H5Z_SZIP;
|
||
}
|
||
|
||
#endif /* HAVE_SZ */
|