2
0
mirror of https://github.com/Unidata/netcdf-c.git synced 2024-12-27 08:49:16 +08:00
netcdf-c/plugins/NCZmisc.c

184 lines
5.2 KiB
C
Raw Normal View History

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'
2021-09-03 07:04:26 +08:00
/* * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * *
* 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: Robb Matzke
* Friday, August 27, 1999
*/
/* Converted to NCZarr support by Dennis Heimbigner 5/1/2021 */
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <math.h>
#include <assert.h>
#include "netcdf_json.h"
#include "netcdf.h"
#include "netcdf_filter.h"
#include "netcdf_filter_build.h"
#include "h5misc.h"
/**************************************************/
/* NCZarr Filter Objects */
/* Codec Format
{
"id": "test",
"testcase": "n",
"byte": "<unsigned int>",
"ubyte": "<unsigned int>",
"short": "<unsigned int>",
"ushort": "<unsigned int>",
"int": "<unsigned int>",
"uint": "<unsigned int>",
"float": "<unsigned int>",
"double0": "<unsigned int>",
"double1": "<unsigned int>",
"int640": "<unsigned int>",
"int641": "<unsigned int>",
"uint640": "<unsigned int>",
"uint641": "<unsigned int>",
}
*/
/* Give unique dict key names for parameters */
static const char* fields[14] = {
"testcase",
"byte",
"ubyte",
"short",
"ushort",
"int",
"uint",
"float",
"double_0",
"double_1",
"int64_0",
"int64_1",
"uint64_0",
"uint64_1"
};
/* Forward */
static int NCZ_misc_codec_to_hdf5(const char* codec, size_t* nparamsp, unsigned** paramsp);
static int NCZ_misc_hdf5_to_codec(size_t nparams, const unsigned* params, char** codecp);
/* Structure for NCZ_PLUGIN_CODEC */
static NCZ_codec_t NCZ_misc_codec = {/* NCZ_codec_t codec fields */
NCZ_CODEC_CLASS_VER, /* Struct version number */
NCZ_CODEC_HDF5, /* Struct sort */
"test", /* Standard name/id of the codec */
H5Z_FILTER_TEST, /* HDF5 alias for misc */
NULL, /*NCZ_misc_codec_initialize*/
NULL, /*NCZ_misc_codec_finalize*/
NCZ_misc_codec_to_hdf5,
NCZ_misc_hdf5_to_codec,
NULL, /*NCZ_misc_modify_parameters*/
};
/* External Export API */
DLLEXPORT
const void*
NCZ_get_codec_info(void)
{
return (void*)&NCZ_misc_codec;
}
/* NCZarr Interface Functions */
static int
NCZ_misc_codec_to_hdf5(const char* codec_json, size_t* nparamsp, unsigned** paramsp)
{
int stat = NC_NOERR;
NCjson* jcodec = NULL;
NCjson* jtmp = NULL;
size_t i,nparams = 0;
unsigned* params = NULL;
/* parse the JSON */
if(NCJparse(codec_json,0,&jcodec))
{stat = NC_EFILTER; goto done;}
if(NCJsort(jcodec) != NCJ_DICT) {stat = NC_EPLUGIN; goto done;}
/* Verify the codec ID */
if(NCJdictget(jcodec,"id",&jtmp))
{stat = NC_EFILTER; goto done;}
if(jtmp == NULL || !NCJisatomic(jtmp)) {stat = NC_EINVAL; goto done;}
if(strcmp(NCJstring(jtmp),NCZ_misc_codec.codecid)!=0) {stat = NC_EINVAL; goto done;}
/* The codec will have (2*14 + 1) +1 = 29 dict entries + id*/
nparams = (2*14 + 1) + 1;
if(NCJlength(jcodec) != nparams) {
fprintf(stderr,"Incorrect no. of codec parameters: need=29 sent=%ld\n",(unsigned long)(nparams-1));
stat = NC_EINVAL;
goto done;
}
/* Actual # of parameters is 14 (ignoring the testcase number) */
nparams = 14;
if((params = (unsigned*)calloc(nparams,sizeof(unsigned)))== NULL)
{stat = NC_ENOMEM; goto done;}
for(i=0;i<nparams;i++) {
struct NCJconst jc;
if(NCJdictget(jcodec,fields[i],&jtmp))
{stat = NC_EFILTER; goto done;}
if(NCJcvt(jtmp,NCJ_INT,&jc))
{stat = NC_EFILTER; goto done;}
if(jc.ival < 0 || jc.ival > NC_MAX_UINT) {stat = NC_EINVAL; goto done;}
params[i] = (unsigned)jc.ival;
}
if(nparamsp) *nparamsp = nparams;
if(paramsp) {*paramsp = params; params = NULL;}
done:
if(params) free(params);
NCJreclaim(jcodec);
return stat;
}
static int
NCZ_misc_hdf5_to_codec(size_t nparams, const unsigned* params, char** codecp)
{
int i,stat = NC_NOERR;
char json[4096];
char value[1024];
Improve S3 Documentation and Support ## Improvements to S3 Documentation * Create a new document *quickstart_paths.md* that give a summary of the legal path formats used by netcdf-c. This includes both file paths and URL paths. * Modify *nczarr.md* to remove most of the S3 related text. * Move the S3 text from *nczarr.md* to a new document *cloud.md*. * Add some S3-related text to the *byterange.md* document. Hopefully, this will make it easier for users to find the information they want. ## Rebuild NCZarr Testing In order to avoid problems with running make check in parallel, two changes were made: 1. The *nczarr_test* test system was rebuilt. Now, for each test. any generated files are kept in a test-specific directory, isolated from all other test executions. 2. Similarly, since the S3 test bucket is shared, any generated S3 objects are isolated using a test-specific key path. ## Other S3 Related Changes * Add code to ensure that files created on S3 are reclaimed at end of testing. * Used the bash "trap" command to ensure S3 cleanup even if the test fails. * Cleanup the S3 related configure.ac flag set since S3 is used in several places. So now one should use the option *--enable-s3* instead of *--enable-nczarr-s3*, although the latter is still kept as a deprecated alias for the former. * Get some of the github actions yml to work with S3; required fixing various test scripts adding a secret to access the Unidata S3 bucket. * Cleanup S3 portion of libnetcdf.settings.in and netcdf_meta.h.in and test_common.in. * Merge partial S3 support into dhttp.c. * Create an experimental s3 access library especially for use with Windows. It is enabled by using the options *--enable-s3-internal* (automake) or *-DENABLE_S3_INTERNAL=ON* (CMake). Also add a unit-test for it. * Move some definitions from ncrc.h to ncs3sdk.h ## Other Changes * Provide a default implementation of strlcpy and move this and similar defaults into *dmissing.c*.
2023-04-26 07:15:06 +08:00
size_t count, jlen;
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'
2021-09-03 07:04:26 +08:00
if(nparams == 0 || params == NULL)
{stat = NC_EINVAL; goto done;}
if(nparams != 14) {
fprintf(stderr,"Incorrect no. of parameters: need=14 sent=%ld\n",(unsigned long)nparams);
stat = NC_EINVAL;
goto done;
}
Improve S3 Documentation and Support ## Improvements to S3 Documentation * Create a new document *quickstart_paths.md* that give a summary of the legal path formats used by netcdf-c. This includes both file paths and URL paths. * Modify *nczarr.md* to remove most of the S3 related text. * Move the S3 text from *nczarr.md* to a new document *cloud.md*. * Add some S3-related text to the *byterange.md* document. Hopefully, this will make it easier for users to find the information they want. ## Rebuild NCZarr Testing In order to avoid problems with running make check in parallel, two changes were made: 1. The *nczarr_test* test system was rebuilt. Now, for each test. any generated files are kept in a test-specific directory, isolated from all other test executions. 2. Similarly, since the S3 test bucket is shared, any generated S3 objects are isolated using a test-specific key path. ## Other S3 Related Changes * Add code to ensure that files created on S3 are reclaimed at end of testing. * Used the bash "trap" command to ensure S3 cleanup even if the test fails. * Cleanup the S3 related configure.ac flag set since S3 is used in several places. So now one should use the option *--enable-s3* instead of *--enable-nczarr-s3*, although the latter is still kept as a deprecated alias for the former. * Get some of the github actions yml to work with S3; required fixing various test scripts adding a secret to access the Unidata S3 bucket. * Cleanup S3 portion of libnetcdf.settings.in and netcdf_meta.h.in and test_common.in. * Merge partial S3 support into dhttp.c. * Create an experimental s3 access library especially for use with Windows. It is enabled by using the options *--enable-s3-internal* (automake) or *-DENABLE_S3_INTERNAL=ON* (CMake). Also add a unit-test for it. * Move some definitions from ncrc.h to ncs3sdk.h ## Other Changes * Provide a default implementation of strlcpy and move this and similar defaults into *dmissing.c*.
2023-04-26 07:15:06 +08:00
jlen = sizeof(json);
count = snprintf(json,sizeof(json),"{\"id\": \"%s\"",NCZ_misc_codec.codecid);
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'
2021-09-03 07:04:26 +08:00
for(i=0;i<14;i++) {
Improve S3 Documentation and Support ## Improvements to S3 Documentation * Create a new document *quickstart_paths.md* that give a summary of the legal path formats used by netcdf-c. This includes both file paths and URL paths. * Modify *nczarr.md* to remove most of the S3 related text. * Move the S3 text from *nczarr.md* to a new document *cloud.md*. * Add some S3-related text to the *byterange.md* document. Hopefully, this will make it easier for users to find the information they want. ## Rebuild NCZarr Testing In order to avoid problems with running make check in parallel, two changes were made: 1. The *nczarr_test* test system was rebuilt. Now, for each test. any generated files are kept in a test-specific directory, isolated from all other test executions. 2. Similarly, since the S3 test bucket is shared, any generated S3 objects are isolated using a test-specific key path. ## Other S3 Related Changes * Add code to ensure that files created on S3 are reclaimed at end of testing. * Used the bash "trap" command to ensure S3 cleanup even if the test fails. * Cleanup the S3 related configure.ac flag set since S3 is used in several places. So now one should use the option *--enable-s3* instead of *--enable-nczarr-s3*, although the latter is still kept as a deprecated alias for the former. * Get some of the github actions yml to work with S3; required fixing various test scripts adding a secret to access the Unidata S3 bucket. * Cleanup S3 portion of libnetcdf.settings.in and netcdf_meta.h.in and test_common.in. * Merge partial S3 support into dhttp.c. * Create an experimental s3 access library especially for use with Windows. It is enabled by using the options *--enable-s3-internal* (automake) or *-DENABLE_S3_INTERNAL=ON* (CMake). Also add a unit-test for it. * Move some definitions from ncrc.h to ncs3sdk.h ## Other Changes * Provide a default implementation of strlcpy and move this and similar defaults into *dmissing.c*.
2023-04-26 07:15:06 +08:00
size_t len = snprintf(value,sizeof(value),", \"%s\": \"%u\"",fields[i],params[i]);
count += len; assert(jlen > count);
strcat(json,value);
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'
2021-09-03 07:04:26 +08:00
}
Improve S3 Documentation and Support ## Improvements to S3 Documentation * Create a new document *quickstart_paths.md* that give a summary of the legal path formats used by netcdf-c. This includes both file paths and URL paths. * Modify *nczarr.md* to remove most of the S3 related text. * Move the S3 text from *nczarr.md* to a new document *cloud.md*. * Add some S3-related text to the *byterange.md* document. Hopefully, this will make it easier for users to find the information they want. ## Rebuild NCZarr Testing In order to avoid problems with running make check in parallel, two changes were made: 1. The *nczarr_test* test system was rebuilt. Now, for each test. any generated files are kept in a test-specific directory, isolated from all other test executions. 2. Similarly, since the S3 test bucket is shared, any generated S3 objects are isolated using a test-specific key path. ## Other S3 Related Changes * Add code to ensure that files created on S3 are reclaimed at end of testing. * Used the bash "trap" command to ensure S3 cleanup even if the test fails. * Cleanup the S3 related configure.ac flag set since S3 is used in several places. So now one should use the option *--enable-s3* instead of *--enable-nczarr-s3*, although the latter is still kept as a deprecated alias for the former. * Get some of the github actions yml to work with S3; required fixing various test scripts adding a secret to access the Unidata S3 bucket. * Cleanup S3 portion of libnetcdf.settings.in and netcdf_meta.h.in and test_common.in. * Merge partial S3 support into dhttp.c. * Create an experimental s3 access library especially for use with Windows. It is enabled by using the options *--enable-s3-internal* (automake) or *-DENABLE_S3_INTERNAL=ON* (CMake). Also add a unit-test for it. * Move some definitions from ncrc.h to ncs3sdk.h ## Other Changes * Provide a default implementation of strlcpy and move this and similar defaults into *dmissing.c*.
2023-04-26 07:15:06 +08:00
count += 1; assert(jlen > count);
strcat(json,"}");
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'
2021-09-03 07:04:26 +08:00
if(codecp) {
if((*codecp = strdup(json))==NULL) {stat = NC_ENOMEM; goto done;}
}
done:
return stat;
}