Merge pull request easybuilders#19243 from boegel/20231116121118_new_…

…pr_Spark350

{devel}[foss/2023a] Spark v3.5.0, Arrow v14.0.1, RapidJSON v1.1.0-20230928

easybuild/easyconfigs/a/Arrow/Arrow-14.0.1-gfbf-2023a.eb

@@ -0,0 +1,74 @@
+easyblock = 'CMakeMake'
+
+name = 'Arrow'
+version = '14.0.1'
+
+homepage = 'https://arrow.apache.org'
+description = """Apache Arrow (incl. PyArrow Python bindings), a cross-language development platform
+ for in-memory data."""
+
+toolchain = {'name': 'gfbf', 'version': '2023a'}
+
+source_urls = ['https://archive.apache.org/dist/%(namelower)s/%(namelower)s-%(version)s']
+sources = ['apache-arrow-%(version)s.tar.gz']
+checksums = ['5c70eafb1011f9d124bafb328afe54f62cc5b9280b7080e1e3d668f78c0e407e']
+
+builddependencies = [
+    ('CMake', '3.26.3'),
+    ('Autotools', '20220317'),
+    ('flex', '2.6.4'),
+    ('Bison', '3.8.2'),
+    ('pkgconf', '1.9.5'),
+]
+
+# Arrow strongly prefers included jemalloc, so not including it as a dependency
+dependencies = [
+    ('Python', '3.11.3'),
+    ('SciPy-bundle', '2023.07'),  # for numpy
+    ('Boost', '1.82.0'),
+    ('lz4', '1.9.4'),
+    ('zlib', '1.2.13'),
+    ('bzip2', '1.0.8'),
+    ('zstd', '1.5.5'),
+    ('snappy', '1.1.10'),
+    ('RapidJSON', '1.1.0-20230928'),
+    ('RE2', '2023-08-01'),
+    ('utf8proc', '2.8.0'),
+]
+
+start_dir = 'cpp'
+
+# see https://arrow.apache.org/docs/developers/python.html
+configopts = "-DARROW_DATASET=on -DARROW_PYTHON=on -DARROW_PARQUET=ON -DARROW_WITH_SNAPPY=ON "
+configopts += "-DCMAKE_INSTALL_LIBDIR=lib -DPython3_ROOT_DIR=$EBROOTPYTHON "
+configopts += "-DARROW_WITH_ZLIB=ON -DARROW_WITH_BZ2=ON -DARROW_WITH_ZSTD=ON -DARROW_WITH_LZ4=ON "
+configopts += "-DZSTD_ROOT=$EBROOTZSTD "
+
+# also install Python bindings
+local_install_pyarrow_cmds = "export PKG_CONFIG_PATH=%(installdir)s/lib/pkgconfig:$PKG_CONFIG_PATH && "
+local_install_pyarrow_cmds += "export Arrow_DIR=%(installdir)s && export ArrowDataset_DIR=%(installdir)s && "
+local_install_pyarrow_cmds += "export ArrowAcero_DIR=%(installdir)s && export Parquet_DIR=%(installdir)s && "
+local_install_pyarrow_cmds += "export PYTHONPATH=%(installdir)s/lib/python%(pyshortver)s/site-packages:$PYTHONPATH && "
+local_install_pyarrow_cmds += "cd %(builddir)s/*arrow-%(version)s/python && export XDG_CACHE_HOME=$TMPDIR && "
+local_install_pyarrow_cmds += "sed -i 's/numpy==[0-9.]*/numpy/g' pyproject.toml && "
+local_install_pyarrow_cmds += "Python3_ROOT_DIR=$EBROOTPYTHON "
+local_install_pyarrow_cmds += "PYARROW_CMAKE_OPTIONS='-DZSTD_LIB=$EBROOTZSTD/lib/libzstd.%s ' " % SHLIB_EXT
+local_install_pyarrow_cmds += "PYARROW_WITH_DATASET=1 PYARROW_WITH_PARQUET=1 "
+local_install_pyarrow_cmds += "python -m pip install --prefix %(installdir)s --no-build-isolation ."
+postinstallcmds = [local_install_pyarrow_cmds]
+
+modextrapaths = {'PYTHONPATH': 'lib/python%(pyshortver)s/site-packages'}
+
+sanity_check_paths = {
+    'files': ['lib/libarrow.a', 'lib/libarrow.%s' % SHLIB_EXT,
+              'lib/python%%(pyshortver)s/site-packages/pyarrow/libarrow_python.%s' % SHLIB_EXT],
+    'dirs': ['include/arrow', 'lib/cmake/Arrow', 'lib/pkgconfig', 'lib/python%(pyshortver)s/site-packages'],
+}
+
+sanity_check_commands = [
+    "python -c 'import pyarrow'",
+    "python -c 'import pyarrow.dataset'",
+    "python -c 'import pyarrow.parquet'",
+]
+
+moduleclass = 'data'

easybuild/easyconfigs/r/RapidJSON/RapidJSON-1.1.0-20230928-GCCcore-12.3.0.eb

@@ -0,0 +1,31 @@
+easyblock = 'CMakeMake'
+
+name = 'RapidJSON'
+# no new release since Aug'16 so using latest commit;
+# see also https://github.com/Tencent/rapidjson/issues/2202
+version = '1.1.0-20230928'
+local_commit = 'f9d5341'
+
+homepage = 'https://rapidjson.org'
+description = "A fast JSON parser/generator for C++ with both SAX/DOM style API"
+
+toolchain = {'name': 'GCCcore', 'version': '12.3.0'}
+
+source_urls = ['https://github.com/Tencent/%(namelower)s/archive/']
+sources = [{'download_filename': '%s.tar.gz' % local_commit, 'filename': 'v%(version)s.tar.gz'}]
+checksums = ['2b521dba5c22eaae6e6e7d4d304cb317e2cf8c687c70046b02792c02f78c127e']
+
+builddependencies = [
+    ('binutils', '2.40'),
+    ('CMake', '3.26.3'),
+]
+
+# strip out hardcoded use of -march=native, EasyBuild should be in control of this
+preconfigopts = "sed -i 's/-march=native//g' ../rapidjson-*/CMakeLists.txt && "
+
+sanity_check_paths = {
+    'files': ['lib/pkgconfig/%(name)s.pc'],
+    'dirs': ['include/%(namelower)s', 'lib/cmake', 'share'],
+}
+
+moduleclass = 'lib'

easybuild/easyconfigs/s/Spark/Spark-3.5.0-foss-2023a.eb

@@ -0,0 +1,52 @@
+# Author: Denis Krišťák (INUITS)
+
+easyblock = 'Tarball'
+
+name = 'Spark'
+version = '3.5.0'
+homepage = 'https://spark.apache.org'
+description = """Spark is Hadoop MapReduce done in memory"""
+
+toolchain = {'name': 'foss', 'version': '2023a'}
+
+source_urls = [
+    'https://archive.apache.org/dist//%(namelower)s/%(namelower)s-%(version)s/',
+    'https://downloads.apache.org/%(namelower)s/%(namelower)s-%(version)s/'
+]
+sources = ['%(namelower)s-%(version)s-bin-hadoop3.tgz']
+checksums = ['ac064ec620129b4b9630e180e25ac2b71a8ccd4c6912bf5b5631943b742f0379']
+
+dependencies = [
+    ('Python', '3.11.3'),
+    ('Java', '11', '', SYSTEM),
+    ('Arrow', '14.0.1'),
+]
+
+exts_defaultclass = 'PythonPackage'
+exts_default_options = {
+    'source_urls': [PYPI_SOURCE],
+    'download_dep_fail': True,
+    'use_pip': True,
+}
+
+exts_list = [
+    ('py4j', '0.10.9.7', {
+        'checksums': ['0b6e5315bb3ada5cf62ac651d107bb2ebc02def3dee9d9548e3baac644ea8dbb'],
+    }),
+]
+
+sanity_check_paths = {
+    'files': ['bin/pyspark', 'bin/spark-shell'],
+    'dirs': ['python']
+}
+
+sanity_check_commands = [
+    "pyspark -h",
+    "python -c 'import pyspark'",
+]
+
+modextrapaths = {'PYTHONPATH': ['python', 'lib/python%(pyshortver)s/site-packages']}
+
+modextravars = {'SPARK_HOME': '%(installdir)s'}
+
+moduleclass = 'devel'