From f006e316257d790b8d1cf1bc347eff587303311b Mon Sep 17 00:00:00 2001 From: CoprDistGit Date: Mon, 10 Apr 2023 12:07:53 +0000 Subject: automatic import of python-databricks-connect --- python-databricks-connect.spec | 141 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 141 insertions(+) create mode 100644 python-databricks-connect.spec (limited to 'python-databricks-connect.spec') diff --git a/python-databricks-connect.spec b/python-databricks-connect.spec new file mode 100644 index 0000000..402dfe5 --- /dev/null +++ b/python-databricks-connect.spec @@ -0,0 +1,141 @@ +%global _empty_manifest_terminate_build 0 +Name: python-databricks-connect +Version: 11.3.7 +Release: 1 +Summary: Databricks Connect Client +License: Databricks Proprietary License +URL: https://pypi.org/project/databricks-connect/ +Source0: https://mirrors.nju.edu.cn/pypi/web/packages/c1/14/e9fdd8338b501d266eecc42ce4949eb3d0e6dc492e86707e4b4553b53693/databricks-connect-11.3.7.tar.gz +BuildArch: noarch + + +%description +Databricks Connect allows you to write +jobs using Spark native APIs and have them execute remotely on a Databricks +cluster instead of in the local Spark session. +For example, when you run the DataFrame command ``spark.read.parquet(...). +groupBy(...).agg(...).show()`` using Databricks Connect, the parsing and +planning of the job runs on your local machine. Then, the logical +representation of the job is sent to the Spark server running in Databricks +for execution in the cluster. +With Databricks Connect, you can: +- Run large-scale Spark jobs from any Python, Java, Scala, or R application. +Anywhere you can ``import pyspark``, ``import org.apache.spark``, or +``require(SparkR)``, you can now run Spark jobs directly from your +application, without needing to install any IDE plugins or use Spark +submission scripts. +- Step through and debug code in your IDE even when working with a remote +cluster. +- Iterate quickly when developing libraries. You do not need to restart the +cluster after changing Python or Java library dependencies in Databricks +Connect, because each client session is isolated from each other in the +cluster. +- Shut down idle clusters without losing work. Because the client session is +decoupled from the cluster, it is unaffected by cluster restarts or upgrades, +which would normally cause you to lose all the variables, RDDs, and DataFrame +objects defined in a notebook. + +%package -n python3-databricks-connect +Summary: Databricks Connect Client +Provides: python-databricks-connect +BuildRequires: python3-devel +BuildRequires: python3-setuptools +BuildRequires: python3-pip +%description -n python3-databricks-connect +Databricks Connect allows you to write +jobs using Spark native APIs and have them execute remotely on a Databricks +cluster instead of in the local Spark session. +For example, when you run the DataFrame command ``spark.read.parquet(...). +groupBy(...).agg(...).show()`` using Databricks Connect, the parsing and +planning of the job runs on your local machine. Then, the logical +representation of the job is sent to the Spark server running in Databricks +for execution in the cluster. +With Databricks Connect, you can: +- Run large-scale Spark jobs from any Python, Java, Scala, or R application. +Anywhere you can ``import pyspark``, ``import org.apache.spark``, or +``require(SparkR)``, you can now run Spark jobs directly from your +application, without needing to install any IDE plugins or use Spark +submission scripts. +- Step through and debug code in your IDE even when working with a remote +cluster. +- Iterate quickly when developing libraries. You do not need to restart the +cluster after changing Python or Java library dependencies in Databricks +Connect, because each client session is isolated from each other in the +cluster. +- Shut down idle clusters without losing work. Because the client session is +decoupled from the cluster, it is unaffected by cluster restarts or upgrades, +which would normally cause you to lose all the variables, RDDs, and DataFrame +objects defined in a notebook. + +%package help +Summary: Development documents and examples for databricks-connect +Provides: python3-databricks-connect-doc +%description help +Databricks Connect allows you to write +jobs using Spark native APIs and have them execute remotely on a Databricks +cluster instead of in the local Spark session. +For example, when you run the DataFrame command ``spark.read.parquet(...). +groupBy(...).agg(...).show()`` using Databricks Connect, the parsing and +planning of the job runs on your local machine. Then, the logical +representation of the job is sent to the Spark server running in Databricks +for execution in the cluster. +With Databricks Connect, you can: +- Run large-scale Spark jobs from any Python, Java, Scala, or R application. +Anywhere you can ``import pyspark``, ``import org.apache.spark``, or +``require(SparkR)``, you can now run Spark jobs directly from your +application, without needing to install any IDE plugins or use Spark +submission scripts. +- Step through and debug code in your IDE even when working with a remote +cluster. +- Iterate quickly when developing libraries. You do not need to restart the +cluster after changing Python or Java library dependencies in Databricks +Connect, because each client session is isolated from each other in the +cluster. +- Shut down idle clusters without losing work. Because the client session is +decoupled from the cluster, it is unaffected by cluster restarts or upgrades, +which would normally cause you to lose all the variables, RDDs, and DataFrame +objects defined in a notebook. + +%prep +%autosetup -n databricks-connect-11.3.7 + +%build +%py3_build + +%install +%py3_install +install -d -m755 %{buildroot}/%{_pkgdocdir} +if [ -d doc ]; then cp -arf doc %{buildroot}/%{_pkgdocdir}; fi +if [ -d docs ]; then cp -arf docs %{buildroot}/%{_pkgdocdir}; fi +if [ -d example ]; then cp -arf example %{buildroot}/%{_pkgdocdir}; fi +if [ -d examples ]; then cp -arf examples %{buildroot}/%{_pkgdocdir}; fi +pushd %{buildroot} +if [ -d usr/lib ]; then + find usr/lib -type f -printf "/%h/%f\n" >> filelist.lst +fi +if [ -d usr/lib64 ]; then + find usr/lib64 -type f -printf "/%h/%f\n" >> filelist.lst +fi +if [ -d usr/bin ]; then + find usr/bin -type f -printf "/%h/%f\n" >> filelist.lst +fi +if [ -d usr/sbin ]; then + find usr/sbin -type f -printf "/%h/%f\n" >> filelist.lst +fi +touch doclist.lst +if [ -d usr/share/man ]; then + find usr/share/man -type f -printf "/%h/%f.gz\n" >> doclist.lst +fi +popd +mv %{buildroot}/filelist.lst . +mv %{buildroot}/doclist.lst . + +%files -n python3-databricks-connect -f filelist.lst +%dir %{python3_sitelib}/* + +%files help -f doclist.lst +%{_docdir}/* + +%changelog +* Mon Apr 10 2023 Python_Bot - 11.3.7-1 +- Package Spec generated -- cgit v1.2.3