mirror of
https://github.com/Unidata/netcdf-c.git
synced 2024-12-09 08:11:38 +08:00
df3636b959
This PR started as an attempt to add unlimited dimensions to NCZarr. It did that, but this exposed significant problems with test interference. So this PR is mostly about fixing -- well mitigating anyway -- test interference. The problem of test interference is now documented in the document docs/internal.md. The solutions implemented here are also describe in that document. The solution is somewhat fragile but multiple cleanup mechanisms are provided. Note that this feature requires that the AWS command line utility must be installed. ## Unlimited Dimensions. The existing NCZarr extensions to Zarr are modified to support unlimited dimensions. NCzarr extends the Zarr meta-data for the ".zgroup" object to include netcdf-4 model extensions. This information is stored in ".zgroup" as dictionary named "_nczarr_group". Inside "_nczarr_group", there is a key named "dims" that stores information about netcdf-4 named dimensions. The value of "dims" is a dictionary whose keys are the named dimensions. The value associated with each dimension name has one of two forms Form 1 is a special case of form 2, and is kept for backward compatibility. Whenever a new file is written, it uses format 1 if possible, otherwise format 2. * Form 1: An integer representing the size of the dimension, which is used for simple named dimensions. * Form 2: A dictionary with the following keys and values" - "size" with an integer value representing the (current) size of the dimension. - "unlimited" with a value of either "1" or "0" to indicate if this dimension is an unlimited dimension. For Unlimited dimensions, the size is initially zero, and as variables extend the length of that dimension, the size value for the dimension increases. That dimension size is shared by all arrays referencing that dimension, so if one array extends an unlimited dimension, it is implicitly extended for all other arrays that reference that dimension. This is the standard semantics for unlimited dimensions. Adding unlimited dimensions required a number of other changes to the NCZarr code-base. These included the following. * Did a partial refactor of the slice handling code in zwalk.c to clean it up. * Added a number of tests for unlimited dimensions derived from the same test in nc_test4. * Added several NCZarr specific unlimited tests; more are needed. * Add test of endianness. ## Misc. Other Changes * Modify libdispatch/ncs3sdk_aws.cpp to optionally support use of the AWS Transfer Utility mechanism. This is controlled by the ```#define TRANSFER```` command in that file. It defaults to being disabled. * Parameterize both the standard Unidata S3 bucket (S3TESTBUCKET) and the netcdf-c test data prefix (S3TESTSUBTREE). * Fixed an obscure memory leak in ncdump. * Removed some obsolete unit testing code and test cases. * Uncovered a bug in the netcdf-c handling of big-endian floats and doubles. Have not fixed yet. See tst_h5_endians.c. * Renamed some nczarr_tests testcases to avoid name conflicts with nc_test4. * Modify the semantics of zmap\#ncsmap_write to only allow total rewrite of objects. * Modify the semantics of zodom to properly handle stride > 1. * Add a truncate operation to the libnczarr zmap code.
274 lines
6.6 KiB
Bash
Executable File
274 lines
6.6 KiB
Bash
Executable File
#!/bin/sh
|
|
|
|
if test "x$srcdir" = x ; then srcdir=`pwd`; fi
|
|
. ../test_common.sh
|
|
|
|
set -e
|
|
|
|
if test "x$TESTNCZARR" = x1 ; then
|
|
. "$srcdir/test_nczarr.sh"
|
|
s3isolate "testdir_nccopy5"
|
|
else
|
|
isolate testdir_ncccopy5
|
|
fi
|
|
THISDIR=`pwd`
|
|
cd $ISOPATH
|
|
|
|
# Program to run
|
|
if test "x$TESTNCZARR" = x1 ; then
|
|
CHUNKTEST="${execdir}/test_chunking"
|
|
else
|
|
CHUNKTEST="${execdir}/tst_chunking"
|
|
fi
|
|
|
|
# For a netCDF-4 build, test nccopy chunking rules
|
|
|
|
echo ""
|
|
|
|
# Trim off leading and trailing whitespace
|
|
# Also remove any <cr> and de-tabify
|
|
# usage: trim <line>
|
|
# Leaves result in variable TRIMMED
|
|
trim() {
|
|
# trim leading whitespace and remove <cr>
|
|
TMP=`echo "$1" |tr -d '\r' | tr '\t' ' ' |sed -e 's/^[ ]*//'`
|
|
# trim trailing whitespace
|
|
TRIMMED=`echo "$TMP" | sed -e 's/[ ]*$//'`
|
|
}
|
|
|
|
if test "x$TESTNCZARR" = x1 ; then
|
|
# NCZARR does not support contiguous storage
|
|
checkfvar() {
|
|
return
|
|
}
|
|
else
|
|
# usage: checkfvar <file>
|
|
checkfvar() {
|
|
# Make sure that fvar was not chunked
|
|
C5FVAR=`sed -e '/fvar:_ChunkSizes/p' -e d <$1`
|
|
if test "x$C5FVAR" != x ; then
|
|
echo "***Fail: fvar was chunked"
|
|
exit 1
|
|
fi
|
|
}
|
|
fi
|
|
|
|
# usage: checkivar <file>
|
|
checkivar() {
|
|
# Make sure that ivar was not chunked
|
|
C5IVAR=`sed -e '/ivar:_ChunkSizes/p' -e d <$1`
|
|
if test "x$C5IVAR" != x ; then
|
|
echo "***Fail: ivar was chunked"
|
|
exit 1
|
|
fi
|
|
}
|
|
|
|
# usage: verifychunkline line1 line2
|
|
verifychunkline() {
|
|
# trim leading whitespace
|
|
trim "$1"; L1="$TRIMMED"
|
|
trim "$2"; L2="$TRIMMED"
|
|
if test "x$L1" != "x$L2" ; then
|
|
echo "chunk line mismatch |$L1| |$L2|"
|
|
exit 1;
|
|
fi
|
|
}
|
|
|
|
# Remove any temporary files
|
|
cleanup() {
|
|
rm -f tmp_nc5.nc tmp_nc5a.nc
|
|
rm -f tmp_nc5.cdl tmp_nc5a.cdl tmp_nc5b.cdl
|
|
rm -f tmp_nc5_omit.nc tmp_nc5_omit.cdl
|
|
}
|
|
|
|
buildfile() {
|
|
zext=$1
|
|
index=$2
|
|
if test "x$TESTNCZARR" = x1 ; then
|
|
fileargs "tmp_nc5_${index}_${zext}"
|
|
deletemap $zext $file
|
|
file="$fileurl"
|
|
else
|
|
file="tmp_nc5_${index}_${zext}.nc"
|
|
rm -f $file
|
|
fi
|
|
}
|
|
|
|
testcase1() {
|
|
zext=$1
|
|
buildfile ${zext} 1
|
|
|
|
rm -fr tmp1${zext}.dir
|
|
mkdir tmp1${zext}.dir
|
|
cd tmp1${zext}.dir
|
|
|
|
# Create a simple classic input file
|
|
${CHUNKTEST} $file
|
|
|
|
# Save a .cdl version
|
|
${NCDUMP} -n tmp_nc5_base ${file} > tmp_nc5.cdl
|
|
|
|
echo "*** Test nccopy -c with per-variable chunking; classic->enhanced"
|
|
# This should produce same as -c dim0/,dim1/1,dim2/,dim3/1,dim4/,dim5/1,dim6/
|
|
# But note that the chunk product is less than default, so we need to reduce it (-M)
|
|
${NCCOPY} -M1000 -c ivar:7,1,2,1,5,1,9 ${file} tmp_nc34.nc
|
|
${NCDUMP} -n tmp_nc5_base tmp_nc34.nc > tmp_nc34.cdl
|
|
# Verify that the core cdl is the same
|
|
diff tmp_nc5.cdl tmp_nc34.cdl
|
|
|
|
# Look at the output chunking
|
|
${NCDUMP} -hs -n tmp_nc5_base tmp_nc34.nc > tmp_chunking.cdl
|
|
# extract the chunking line
|
|
TESTLINE=`sed -e '/ivar:_ChunkSizes/p' -e d <tmp_chunking.cdl`
|
|
# track line to match
|
|
BASELINE='ivar:_ChunkSizes = 7, 1, 2, 1, 5, 1, 9 ;'
|
|
verifychunkline "$TESTLINE" "$BASELINE"
|
|
# Make sure that fvar was not chunked
|
|
checkfvar tmp_chunking.cdl
|
|
} # T1
|
|
|
|
testcase2() {
|
|
zext=$1
|
|
buildfile ${zext} 2
|
|
|
|
rm -fr tmp2${zext}.dir
|
|
mkdir tmp2${zext}.dir
|
|
cd tmp2${zext}.dir
|
|
|
|
${CHUNKTEST} ${file} deflate
|
|
|
|
# Save a .cdl version
|
|
${NCDUMP} -n tmp_nc5_base ${file} > tmp_nc5.cdl
|
|
|
|
echo "*** Test nccopy -c with per-variable chunking; enhanced->enhanced"
|
|
# Use -M to ensure that chunking takes effect
|
|
${NCCOPY} -M500 -c ivar:4,1,2,1,5,2,3 $file tmp_nc44.nc
|
|
${NCDUMP} -n tmp_nc5_base tmp_nc44.nc > tmp_nc44.cdl
|
|
diff tmp_nc5.cdl tmp_nc44.cdl
|
|
|
|
# Look at the output chunking
|
|
${NCDUMP} -hs -n tmp_nc5_base tmp_nc44.nc > tmp_chunking.cdl
|
|
# extract the chunking line
|
|
TESTLINE=`sed -e '/ivar:_ChunkSizes/p' -e d <tmp_chunking.cdl`
|
|
# track line to match
|
|
BASELINE='ivar:_ChunkSizes = 4, 1, 2, 1, 5, 2, 3 ;'
|
|
verifychunkline "$TESTLINE" "$BASELINE"
|
|
# Make sure that fvar was not chunked
|
|
checkfvar tmp_chunking.cdl
|
|
|
|
} # T2
|
|
|
|
testcase3() {
|
|
zext=$1
|
|
buildfile ${zext} 3
|
|
|
|
rm -fr tmp3${zext}.dir
|
|
mkdir tmp3${zext}.dir
|
|
cd tmp3${zext}.dir
|
|
|
|
${CHUNKTEST} ${file} group
|
|
|
|
# Save a .cdl version
|
|
${NCDUMP} -n tmp_nc5_base ${file} > tmp_nc5.cdl
|
|
|
|
echo "*** Test nccopy -c with FQN var name; enhanced ->enhanced"
|
|
${NCCOPY} -M500 -c /g/ivar:4,1,2,1,5,2,3 ${file} tmp_nc44.nc
|
|
${NCDUMP} -n tmp_nc5_base tmp_nc44.nc > tmp_nc44.cdl
|
|
diff tmp_nc5.cdl tmp_nc44.cdl
|
|
|
|
# Verify chunking
|
|
${NCDUMP} -hs -n tmp_nc5_base tmp_nc44.nc > tmp_chunking.cdl
|
|
# extract the chunking line
|
|
TESTLINE=`sed -e '/ivar:_ChunkSizes/p' -e d <tmp_chunking.cdl`
|
|
# track line to match
|
|
BASELINE='ivar:_ChunkSizes = 4, 1, 2, 1, 5, 2, 3 ;'
|
|
verifychunkline "$TESTLINE" "$BASELINE"
|
|
# Make sure that fvar was not chunked
|
|
checkfvar tmp_chunking.cdl
|
|
|
|
} #T3
|
|
|
|
testcase4() {
|
|
zext=$1
|
|
buildfile ${zext} 4
|
|
|
|
rm -fr tmp4${zext}.dir
|
|
mkdir tmp4${zext}.dir
|
|
cd tmp4${zext}.dir
|
|
|
|
${CHUNKTEST} ${file} unlimited
|
|
|
|
# Save a .cdl version
|
|
${NCDUMP} -n tmp_nc5_base ${file} > tmp_nc5.cdl
|
|
|
|
echo "*** Test nccopy -c with unlimited dimension; classic ->enhanced"
|
|
# Warning: make sure that nccopy does not convert small chunking to contiguous => -M<small value>
|
|
${NCCOPY} -M50 -c ivar:5,3 $file tmp_nc34.nc
|
|
${NCDUMP} -n tmp_nc5_base tmp_nc34.nc > tmp_nc34.cdl
|
|
diff tmp_nc5.cdl tmp_nc34.cdl
|
|
|
|
# Verify chunking
|
|
${NCDUMP} -hs -n tmp_nc5_base tmp_nc34.nc > tmp_chunking.cdl
|
|
# extract the chunking line
|
|
TESTLINE=`sed -e '/ivar:_ChunkSizes/p' -e d <tmp_chunking.cdl`
|
|
# track line to match
|
|
BASELINE=' ivar:_ChunkSizes = 5, 3 ; '
|
|
verifychunkline "$TESTLINE" "$BASELINE"
|
|
|
|
# Make sure that fvar was not chunked
|
|
checkfvar tmp_chunking.cdl
|
|
|
|
} # T4
|
|
|
|
testcase5() {
|
|
zext=$1
|
|
buildfile ${zext} 5
|
|
|
|
rm -fr tmp5${zext}.dir
|
|
mkdir tmp5${zext}.dir
|
|
cd tmp5${zext}.dir
|
|
|
|
${CHUNKTEST} ${file}
|
|
|
|
# Save a .cdl version
|
|
${NCDUMP} -n tmp_nc5_base ${file} > tmp_nc5_omit.cdl
|
|
|
|
echo "*** Test nccopy -c fvar: to suppress chunking; classic ->enhanced"
|
|
${NCCOPY} -M500 -c ivar:7,1,2,1,5,1,9 -c fvar: $file tmp_nc34_omit.nc
|
|
${NCDUMP} -n tmp_nc5_base tmp_nc34_omit.nc > tmp_nc34_omit.cdl
|
|
diff tmp_nc5_omit.cdl tmp_nc34_omit.cdl
|
|
|
|
# Verify chunking of ivar
|
|
${NCDUMP} -hs -n tmp_nc5_omit tmp_nc34_omit.nc > tmp_chunking_omit.cdl
|
|
# extract the chunking line
|
|
TESTLINE=`sed -e '/ivar:_ChunkSizes/p' -e d <tmp_chunking_omit.cdl`
|
|
# track line to match
|
|
BASELINE=' ivar:_ChunkSizes = 7, 1, 2, 1, 5, 1, 9 ; '
|
|
verifychunkline "$TESTLINE" "$BASELINE"
|
|
|
|
# Make sure that fvar was not chunked
|
|
checkfvar tmp_chunking_omit.cdl
|
|
|
|
} # T5
|
|
|
|
testcases() {
|
|
testcase1 $1
|
|
testcase2 $1
|
|
testcase3 $1
|
|
testcase4 $1
|
|
testcase5 $1
|
|
}
|
|
|
|
if test "x$TESTNCZARR" != x ; then
|
|
testcases file
|
|
if test "x$FEATURE_NCZARR_ZIP" = xyes ; then testcases zip ; fi
|
|
if test "x$FEATURE_S3TESTS" = xyes ; then testcases s3 ; fi
|
|
if test "x$FEATURE_S3TESTS" = xyes ; then s3sdkdelete "/${S3ISOPATH}" ; fi # Cleanup
|
|
else
|
|
testcases nc
|
|
fi
|
|
|
|
echo "*** All nccopy tests passed!"
|
|
exit 0
|
|
|