netcdf-c/plugins/H5Zfletcher32.c
Dennis Heimbigner 11fe00ea05 Add filter support to NCZarr
Filter support has three goals:

1. Use the existing HDF5 filter implementations,
2. Allow filter metadata to be stored in the NumCodecs metadata format used by Zarr,
3. Allow filters to be used even when HDF5 is disabled

Detailed usage directions are define in docs/filters.md.

For now, the existing filter API is left in place. So filters
are defined using ''nc_def_var_filter'' using the HDF5 style
where the id and parameters are unsigned integers.

This is a big change since filters affect many parts of the code.

In the following, the terms "compressor" and "filter" and "codec" are generally
used synonomously.

### Filter-Related Changes:
* In order to support dynamic loading of shared filter libraries, a new library was added in the libncpoco directory; it helps to isolate dynamic loading across multiple platforms.
* Provide a json parsing library for use by plugins; this is created by merging libdispatch/ncjson.c with include/ncjson.h.
* Add a new _Codecs attribute to allow clients to see what codecs are being used; let ncdump -s print it out.
* Provide special headers to help support compilation of HDF5 filters when HDF5 is not enabled: netcdf_filter_hdf5_build.h and netcdf_filter_build.h.
* Add a number of new test to test the new nczarr filters.
* Let ncgen parse _Codecs attribute, although it is ignored.

### Plugin directory changes:
* Add support for the Blosc compressor; this is essential because it is the most common compressor used in Zarr datasets. This also necessitated adding a CMake FindBlosc.cmake file
* Add NCZarr support for the big-four filters provided by HDF5: shuffle, fletcher32, deflate (zlib), and szip
* Add a Codec defaulter (see docs/filters.md) for the big four filters.
* Make plugins work with windows by properly adding __declspec declaration.

### Misc. Non-Filter Changes
* Replace most uses of USE_NETCDF4 (deprecated) with USE_HDF5.
* Improve support for caching
* More fixes for path conversion code
* Fix misc. memory leaks
* Add new utility -- ncdump/ncpathcvt -- that does more or less the same thing as cygpath.
* Add a number of new test to test the non-filter fixes.
* Update the parsers
* Convert most instances of '#ifdef _MSC_VER' to '#ifdef _WIN32'
2021-09-02 17:04:26 -06:00

176 lines
6.0 KiB
C
Raw Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

/* * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * *
* 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. *
* * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * */
/*
* Programmer: Raymond Lu
* Jan 3, 2003
*/
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <errno.h>
#include "netcdf_filter_hdf5_build.h"
#ifndef H5Z_FILTER_FLETCHER32
#define H5Z_FILTER_FLETCHER32 3
#endif
extern unsigned int H5_checksum_fletcher32(const void *data, size_t len);
/* Local function prototypes */
static size_t H5Z_filter_fletcher32(unsigned flags, size_t cd_nelmts,
const unsigned cd_values[], size_t nbytes, size_t *buf_size, void **buf);
/* This message derives from H5Z */
const H5Z_class2_t H5Z_FLETCHER32[1] = {{
H5Z_CLASS_T_VERS, /* H5Z_class_t version */
H5Z_FILTER_FLETCHER32, /* Filter id number */
1, /* encoder_present flag (set to true) */
1, /* decoder_present flag (set to true) */
"fletcher32", /* Filter name for debugging */
NULL, /* The "can apply" callback */
NULL, /* The "set local" callback */
H5Z_filter_fletcher32, /* The actual filter function */
}};
/* External Discovery Functions */
H5PL_type_t
H5PLget_plugin_type(void)
{
return H5PL_TYPE_FILTER;
}
const void*
H5PLget_plugin_info(void)
{
return H5Z_FLETCHER32;
}
#define FLETCHER_LEN 4
/*-------------------------------------------------------------------------
* Function: H5Z__filter_fletcher32
*
* Purpose: Implement an I/O filter of Fletcher32 Checksum
*
* Return: Success: Size of buffer filtered
* Failure: 0
*
* Programmer: Raymond Lu
* Jan 3, 2003
*
*-------------------------------------------------------------------------
*/
static size_t
H5Z_filter_fletcher32(unsigned flags, size_t H5_ATTR_UNUSED cd_nelmts, const unsigned H5_ATTR_UNUSED cd_values[],
size_t nbytes, size_t *buf_size, void **buf)
{
void *outbuf = NULL; /* Pointer to new buffer */
unsigned char *src = (unsigned char*)(*buf);
uint32_t fletcher; /* Checksum value */
uint32_t reversed_fletcher; /* Possible wrong checksum value */
uint8_t c[4];
uint8_t tmp;
size_t ret_value = 0; /* Return value */
FUNC_ENTER_STATIC
HDassert(sizeof(uint32_t)>=4);
if (flags & H5Z_FLAG_REVERSE) { /* Read */
/* Do checksum if it's enabled for read; otherwise skip it
* to save performance. */
if (!(flags & H5Z_FLAG_SKIP_EDC)) {
unsigned char *tmp_src; /* Pointer to checksum in buffer */
size_t src_nbytes = nbytes; /* Original number of bytes */
uint32_t stored_fletcher; /* Stored checksum value */
/* Get the stored checksum */
src_nbytes -= FLETCHER_LEN;
tmp_src=src+src_nbytes;
UINT32DECODE(tmp_src, stored_fletcher);
/* Compute checksum (can't fail) */
fletcher = H5_checksum_fletcher32(src, src_nbytes);
/* The reversed checksum. There was a bug in the calculating code of
* the Fletcher32 checksum in the library before v1.6.3. The checksum
* value wasn't consistent between big-endian and little-endian systems.
* This bug was fixed in Release 1.6.3. However, after fixing the bug,
* the checksum value is no longer the same as before on little-endian
* system. We'll check both the correct checksum and the wrong
* checksum to be consistent with Release 1.6.2 and before.
*/
H5MM_memcpy(c, &fletcher, (size_t)4);
tmp = c[1];
c[1] = c[0];
c[0] = tmp;
tmp = c[3];
c[3] = c[2];
c[2] = tmp;
H5MM_memcpy(&reversed_fletcher, c, (size_t)4);
/* Verify computed checksum matches stored checksum */
if(stored_fletcher != fletcher && stored_fletcher != reversed_fletcher)
HGOTO_ERROR(H5E_STORAGE, H5E_READERROR, 0, "data error detected by Fletcher32 checksum")
}
/* Set return values */
/* (Re-use the input buffer, just note that the size is smaller by the size of the checksum) */
ret_value = nbytes-FLETCHER_LEN;
} else { /* Write */
unsigned char *dst; /* Temporary pointer to destination buffer */
/* Compute checksum (can't fail) */
fletcher = H5_checksum_fletcher32(src, nbytes);
if (NULL == (outbuf = H5MM_malloc(nbytes + FLETCHER_LEN)))
HGOTO_ERROR(H5E_RESOURCE, H5E_NOSPACE, 0, "unable to allocate Fletcher32 checksum destination buffer")
dst = (unsigned char *) outbuf;
/* Copy raw data */
H5MM_memcpy((void*)dst, (void*)(*buf), nbytes);
/* Append checksum to raw data for storage */
dst += nbytes;
UINT32ENCODE(dst, fletcher);
/* Free input buffer */
H5MM_xfree(*buf);
/* Set return values */
*buf_size = nbytes + FLETCHER_LEN;
*buf = outbuf;
outbuf = NULL;
ret_value = *buf_size;
}
done:
if(outbuf)
H5MM_xfree(outbuf);
FUNC_LEAVE_NOAPI(ret_value)
}