netcdf-c/nc_test/Makefile.am
Dennis Heimbigner 231ae96c4b Add support for Zarr string type to NCZarr
* re: https://github.com/Unidata/netcdf-c/pull/2278
* re: https://github.com/Unidata/netcdf-c/issues/2485
* re: https://github.com/Unidata/netcdf-c/issues/2474

This PR subsumes PR https://github.com/Unidata/netcdf-c/pull/2278.
Actually is a bit an omnibus covering several issues.

## PR https://github.com/Unidata/netcdf-c/pull/2278
Add support for the Zarr string type.
Zarr strings are restricted currently to be of fixed size.
The primary issue to be addressed is to provide a way for user to
specify the size of the fixed length strings. This is handled by providing
the following new attributes special:
1. **_nczarr_default_maxstrlen** —
This is an attribute of the root group. It specifies the default
maximum string length for string types. If not specified, then
it has the value of 64 characters.
2. **_nczarr_maxstrlen** —
This is a per-variable attribute. It specifies the maximum
string length for the string type associated with the variable.
If not specified, then it is assigned the value of
**_nczarr_default_maxstrlen**.

This PR also requires some hacking to handle the existing netcdf-c NC_CHAR
type, which does not exist in zarr. The goal was to choose numpy types for
both the netcdf-c NC_STRING type and the netcdf-c NC_CHAR type such that
if a pure zarr implementation read them, it would still work and an
NC_CHAR type would be handled by zarr as a string of length 1.

For writing variables and NCZarr attributes, the type mapping is as follows:
* "|S1" for NC_CHAR.
* ">S1" for NC_STRING && MAXSTRLEN==1
* ">Sn" for NC_STRING && MAXSTRLEN==n

Note that it is a bit of a hack to use endianness, but it should be ok since for
string/char, the endianness has no meaning.

For reading attributes with pure zarr (i.e. with no nczarr
atribute types defined), they will always be interpreted as of
type NC_CHAR.

## Issue: https://github.com/Unidata/netcdf-c/issues/2474
This PR partly fixes this issue because it provided more
comprehensive support for Zarr attributes that are JSON valued expressions.
This PR still does not address the problem in that issue where the
_ARRAY_DIMENSION attribute is incorrectly set. Than can only be
fixed by the creator of the datasets.

## Issue: https://github.com/Unidata/netcdf-c/issues/2485
This PR also fixes the scalar failure shown in this issue.
It generally cleans up scalar handling.
It also adds a note to the documentation describing that
NCZarr supports scalars while Zarr does not and also how
scalar interoperability is achieved.

## Misc. Other Changes
1. Convert the nczarr special attributes and keys to be all lower case. So "_NCZARR_ATTR" now used "_nczarr_attr. Support back compatibility for the upper case names.
2. Cleanup my too-clever-by-half handling of scalars in libnczarr.
2022-08-27 20:21:13 -06:00

149 lines
4.6 KiB
Makefile

## This is a automake file, part of Unidata's netCDF package.
# Copyright 2018, see the COPYRIGHT file for more information.
# This file builds and runs the nc_test program, which tests the
# netCDF-3 API for all formats.
# Ed Hartnett, Dennis Heimbigner, Ward Fisher
# Un comment to use a more verbose test driver
#SH_LOG_DRIVER = $(SHELL) $(top_srcdir)/test-driver-verbose
#sh_LOG_DRIVER = $(SHELL) $(top_srcdir)/test-driver-verbose
#LOG_DRIVER = $(SHELL) $(top_srcdir)/test-driver-verbose
#TESTS_ENVIRONMENT = export SETX=1;
# Put together AM_CPPFLAGS and AM_LDFLAGS.
include $(top_srcdir)/lib_flags.am
AM_CPPFLAGS += -I$(top_srcdir)/libsrc
AM_CPPFLAGS += -DTOPSRCDIR=${abs_top_srcdir}
AM_CPPFLAGS += -DTOPBINDIR=${abs_top_builddir}
LDADD = ${top_builddir}/liblib/libnetcdf.la
AM_CPPFLAGS += -I$(top_builddir)/liblib -I$(top_builddir)/include -I$(top_srcdir)/libsrc
TEST_EXTENSIONS = .sh
# These are the tests which are always run.
TESTPROGRAMS = tst_names tst_nofill2 tst_nofill3 tst_meta \
tst_inq_type tst_utf8_validate tst_utf8_phrases tst_global_fillval \
tst_max_var_dims tst_formats tst_def_var_fill tst_err_enddef \
tst_default_format
# These are always built, but for parallel builds are run from a test
# script, because they are parallel-enabled tests.
check_PROGRAMS = t_nc tst_atts3 tst_nofill nc_test tst_small
# These tests are only run if pnetcdf is enabled.
if USE_PNETCDF
check_PROGRAMS += tst_parallel2 tst_pnetcdf tst_addvar \
tst_formatx_pnetcdf tst_default_format_pnetcdf
endif
if USE_PNETCDF
if ENABLE_CDF5
check_PROGRAMS += tst_cdf5format
endif
endif
# These are the source files for the main workhorse test program,
# nc_test. If you pass nc_test, you are doing well.
nc_test_SOURCES = nc_test.c error.c test_get.c test_put.c test_read.c \
test_write.c util.c error.h tests.h
# If the user asked for large file tests, then add them.
if LARGE_FILE_TESTS
TESTPROGRAMS += quick_large_files tst_big_var6 tst_big_var2 \
tst_big_rvar tst_big_var tst_large large_files
endif # LARGE_FILE_TESTS
if BUILD_BENCHMARKS
TESTPROGRAMS += testnc3perf
endif
if USE_HDF5
TESTPROGRAMS += tst_diskless6
endif
# Set up the tests.
check_PROGRAMS += $(TESTPROGRAMS)
# Build Diskless test helpers
check_PROGRAMS += tst_diskless tst_diskless3 tst_diskless4 \
tst_diskless5 tst_inmemory tst_open_mem
if USE_HDF5
check_PROGRAMS += tst_diskless2
endif
TESTS = $(TESTPROGRAMS)
if BUILD_UTILITIES
if ENABLE_BYTERANGE
if ENABLE_EXTERNAL_SERVER_TESTS
tst_byterange_SOURCES = tst_byterange.c
check_PROGRAMS += tst_byterange
TESTS += test_byterange.sh
endif
endif
TESTS += run_diskless.sh run_diskless5.sh run_inmemory.sh
if LARGE_FILE_TESTS
if ! ENABLE_PARALLEL
TESTS += run_diskless2.sh
endif
endif
if BUILD_MMAP
TESTS += run_mmap.sh
run_mmap.log: run_diskless.log
endif
# If pnetcdf is enabled, these tests are run by a test
# script. Otherwise, the are run by automake in the usual way.
if USE_PNETCDF
TESTS += run_pnetcdf_tests.sh
else
TESTS += t_nc tst_atts3 tst_nofill nc_test tst_small
endif
endif # BUILD_UTILITIES
# The .c files that are generated with m4 are already distributed, but
# we also include the original m4 files, plus test scripts data.
EXTRA_DIST = test_get.m4 test_put.m4 run_diskless.sh run_diskless2.sh \
run_diskless5.sh run_mmap.sh test_read.m4 \
test_write.m4 ref_tst_diskless2.cdl tst_diskless5.cdl \
ref_tst_diskless3_create.cdl ref_tst_diskless3_open.cdl \
run_inmemory.sh run_mmap.sh f03tst_open_mem.nc test_byterange.sh \
ref_tst_http_nc3.cdl ref_tst_http_nc4a.cdl ref_tst_http_nc4b.cdl \
ref_tst_http_nc4c.cdl CMakeLists.txt run_pnetcdf_tests.sh.in \
tst_misc.c tst_norm.c
# These files are created by the tests.
CLEANFILES = nc_test_*.nc tst_*.nc t_nc.nc large_files.nc \
quick_large_files.nc tst_diskless3_file.cdl \
tst_diskless4.cdl ref_tst_diskless4.cdl benchmark.nc \
tst_http_nc3.cdl tst_http_nc4?.cdl tmp*.cdl tmp*.nc
EXTRA_DIST += bad_cdf5_begin.nc run_cdf5.sh nc_enddef.cdl
if ENABLE_CDF5
# bad_cdf5_begin.nc is a corrupted CDF-5 file with bad variable starting
# file offsets. It is to be used by tst_open_cdf5.c to check if it can
# detect and report error code NC_ENOTNC.
TESTS += run_cdf5.sh
check_PROGRAMS += tst_open_cdf5
if LARGE_FILE_TESTS
TESTPROGRAMS += tst_large_cdf5 tst_cdf5_begin
endif
endif
# Only clean these on maintainer-clean, because they require m4 to
# regenerate.
MAINTAINERCLEANFILES = test_get.c test_put.c
# This rule tells make how to turn our .m4 files into .c files.
.m4.c:
m4 $(AM_M4FLAGS) $(M4FLAGS) $< >$@
# If valgrind is present, add valgrind targets.
@VALGRIND_CHECK_RULES@