pyspark-connect 4.0.0__tar.gz

pyspark_connect-4.0.0/MANIFEST.in

@@ -0,0 +1,31 @@
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# Reference: https://setuptools.pypa.io/en/latest/userguide/miscellaneous.html
+
+recursive-include pyspark *.pyi py.typed *.json
+recursive-include deps/jars *.jar
+graft deps/bin
+recursive-include deps/sbin spark-config.sh spark-daemon.sh start-history-server.sh stop-history-server.sh
+recursive-include deps/data *.data *.txt
+recursive-include deps/licenses *.txt
+recursive-include deps/examples *.py
+recursive-include lib *.zip
+include README.md
+
+# Note that these commands are processed in the order they appear, so keep
+# this exclude at the end.
+global-exclude *.py[cod] __pycache__ .DS_Store

pyspark_connect-4.0.0/PKG-INFO

@@ -0,0 +1,71 @@
+Metadata-Version: 2.2
+Name: pyspark-connect
+Version: 4.0.0
+Summary: Apache Spark Python API with Spark Connect by default
+Home-page: https://github.com/apache/spark/tree/master/python
+Author: Spark Developers
+Author-email: dev@spark.apache.org
+License: http://www.apache.org/licenses/LICENSE-2.0
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Classifier: Programming Language :: Python :: Implementation :: PyPy
+Classifier: Typing :: Typed
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: pyspark==4.0.0
+Requires-Dist: pandas>=2.0.0
+Requires-Dist: pyarrow>=11.0.0
+Requires-Dist: grpcio>=1.67.0
+Requires-Dist: grpcio-status>=1.67.0
+Requires-Dist: googleapis-common-protos>=1.65.0
+Requires-Dist: numpy>=1.21
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# Apache Spark
+
+Spark is a unified analytics engine for large-scale data processing. It provides
+high-level APIs in Scala, Java, Python, and R, and an optimized engine that
+supports general computation graphs for data analysis. It also supports a
+rich set of higher-level tools including Spark SQL for SQL and DataFrames,
+pandas API on Spark for pandas workloads, MLlib for machine learning, GraphX for graph processing,
+and Structured Streaming for stream processing.
+
+<https://spark.apache.org/>
+
+## Online Documentation
+
+You can find the latest Spark documentation, including a programming
+guide, on the [project web page](https://spark.apache.org/documentation.html)
+
+
+## Python Packaging
+
+This README file only contains basic information related to pip installed PySpark.
+This packaging is currently experimental and may change in future versions (although we will do our best to keep compatibility).
+Using PySpark requires the Spark JARs, and if you are building this from source please see the builder instructions at
+["Building Spark"](https://spark.apache.org/docs/latest/building-spark.html).
+
+The Python packaging for Spark is not intended to replace all of the other use cases. This Python packaged version of Spark is suitable for interacting with an existing cluster (be it Spark standalone, YARN) - but does not contain the tools required to set up your own standalone Spark cluster. You can download the full version of Spark from the [Apache Spark downloads page](https://spark.apache.org/downloads.html).
+
+
+**NOTE:** If you are using this with a Spark standalone cluster you must ensure that the version (including minor version) matches or you may experience odd errors.
+
+## Python Requirements
+
+At its core PySpark depends on Py4J, but some additional sub-packages have their own extra requirements for some features (including numpy, pandas, and pyarrow).
+See also [Dependencies](https://spark.apache.org/docs/latest/api/python/getting_started/install.html#dependencies) for production, and [dev/requirements.txt](https://github.com/apache/spark/blob/master/dev/requirements.txt) for development.

pyspark_connect-4.0.0/README.md

@@ -0,0 +1,33 @@
+# Apache Spark
+
+Spark is a unified analytics engine for large-scale data processing. It provides
+high-level APIs in Scala, Java, Python, and R, and an optimized engine that
+supports general computation graphs for data analysis. It also supports a
+rich set of higher-level tools including Spark SQL for SQL and DataFrames,
+pandas API on Spark for pandas workloads, MLlib for machine learning, GraphX for graph processing,
+and Structured Streaming for stream processing.
+
+<https://spark.apache.org/>
+
+## Online Documentation
+
+You can find the latest Spark documentation, including a programming
+guide, on the [project web page](https://spark.apache.org/documentation.html)
+
+
+## Python Packaging
+
+This README file only contains basic information related to pip installed PySpark.
+This packaging is currently experimental and may change in future versions (although we will do our best to keep compatibility).
+Using PySpark requires the Spark JARs, and if you are building this from source please see the builder instructions at
+["Building Spark"](https://spark.apache.org/docs/latest/building-spark.html).
+
+The Python packaging for Spark is not intended to replace all of the other use cases. This Python packaged version of Spark is suitable for interacting with an existing cluster (be it Spark standalone, YARN) - but does not contain the tools required to set up your own standalone Spark cluster. You can download the full version of Spark from the [Apache Spark downloads page](https://spark.apache.org/downloads.html).
+
+
+**NOTE:** If you are using this with a Spark standalone cluster you must ensure that the version (including minor version) matches or you may experience odd errors.
+
+## Python Requirements
+
+At its core PySpark depends on Py4J, but some additional sub-packages have their own extra requirements for some features (including numpy, pandas, and pyarrow).
+See also [Dependencies](https://spark.apache.org/docs/latest/api/python/getting_started/install.html#dependencies) for production, and [dev/requirements.txt](https://github.com/apache/spark/blob/master/dev/requirements.txt) for development.

pyspark_connect-4.0.0/pyspark_connect/__init__.py

@@ -0,0 +1,26 @@
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+"""
+A marker package to make Spark Connect default.
+"""
+
+from pyspark_connect.version import __version__
+
+__all__ = [
+    "__version__",
+]

pyspark_connect-4.0.0/pyspark_connect/version.py

@@ -0,0 +1 @@
+__version__: str = '4.0.0'

pyspark_connect-4.0.0/pyspark_connect.egg-info/PKG-INFO

@@ -0,0 +1,71 @@
+Metadata-Version: 2.2
+Name: pyspark-connect
+Version: 4.0.0
+Summary: Apache Spark Python API with Spark Connect by default
+Home-page: https://github.com/apache/spark/tree/master/python
+Author: Spark Developers
+Author-email: dev@spark.apache.org
+License: http://www.apache.org/licenses/LICENSE-2.0
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Classifier: Programming Language :: Python :: Implementation :: PyPy
+Classifier: Typing :: Typed
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: pyspark==4.0.0
+Requires-Dist: pandas>=2.0.0
+Requires-Dist: pyarrow>=11.0.0
+Requires-Dist: grpcio>=1.67.0
+Requires-Dist: grpcio-status>=1.67.0
+Requires-Dist: googleapis-common-protos>=1.65.0
+Requires-Dist: numpy>=1.21
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# Apache Spark
+
+Spark is a unified analytics engine for large-scale data processing. It provides
+high-level APIs in Scala, Java, Python, and R, and an optimized engine that
+supports general computation graphs for data analysis. It also supports a
+rich set of higher-level tools including Spark SQL for SQL and DataFrames,
+pandas API on Spark for pandas workloads, MLlib for machine learning, GraphX for graph processing,
+and Structured Streaming for stream processing.
+
+<https://spark.apache.org/>
+
+## Online Documentation
+
+You can find the latest Spark documentation, including a programming
+guide, on the [project web page](https://spark.apache.org/documentation.html)
+
+
+## Python Packaging
+
+This README file only contains basic information related to pip installed PySpark.
+This packaging is currently experimental and may change in future versions (although we will do our best to keep compatibility).
+Using PySpark requires the Spark JARs, and if you are building this from source please see the builder instructions at
+["Building Spark"](https://spark.apache.org/docs/latest/building-spark.html).
+
+The Python packaging for Spark is not intended to replace all of the other use cases. This Python packaged version of Spark is suitable for interacting with an existing cluster (be it Spark standalone, YARN) - but does not contain the tools required to set up your own standalone Spark cluster. You can download the full version of Spark from the [Apache Spark downloads page](https://spark.apache.org/downloads.html).
+
+
+**NOTE:** If you are using this with a Spark standalone cluster you must ensure that the version (including minor version) matches or you may experience odd errors.
+
+## Python Requirements
+
+At its core PySpark depends on Py4J, but some additional sub-packages have their own extra requirements for some features (including numpy, pandas, and pyarrow).
+See also [Dependencies](https://spark.apache.org/docs/latest/api/python/getting_started/install.html#dependencies) for production, and [dev/requirements.txt](https://github.com/apache/spark/blob/master/dev/requirements.txt) for development.

pyspark_connect-4.0.0/pyspark_connect.egg-info/SOURCES.txt

@@ -0,0 +1,11 @@
+MANIFEST.in
+README.md
+setup.cfg
+setup.py
+pyspark_connect/__init__.py
+pyspark_connect/version.py
+pyspark_connect.egg-info/PKG-INFO
+pyspark_connect.egg-info/SOURCES.txt
+pyspark_connect.egg-info/dependency_links.txt
+pyspark_connect.egg-info/requires.txt
+pyspark_connect.egg-info/top_level.txt

pyspark_connect-4.0.0/pyspark_connect.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

pyspark_connect-4.0.0/pyspark_connect.egg-info/requires.txt

@@ -0,0 +1,7 @@
+pyspark==4.0.0
+pandas>=2.0.0
+pyarrow>=11.0.0
+grpcio>=1.67.0
+grpcio-status>=1.67.0
+googleapis-common-protos>=1.65.0
+numpy>=1.21

pyspark_connect-4.0.0/pyspark_connect.egg-info/top_level.txt

@@ -0,0 +1 @@
+pyspark_connect

pyspark_connect-4.0.0/setup.cfg

@@ -0,0 +1,10 @@
+[bdist_wheel]
+universal = 1
+
+[metadata]
+description_file = README.md
+
+[egg_info]
+tag_build = 
+tag_date = 0
+

pyspark_connect-4.0.0/setup.py

@@ -0,0 +1,145 @@
+#!/usr/bin/env python3
+
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# cd python
+# python packaging/connect/setup.py sdist
+
+# cd python/packaging/connect
+# python setup.py sdist
+
+import sys
+from setuptools import setup
+import os
+from shutil import copyfile, copytree, move, rmtree
+import glob
+from pathlib import Path
+
+if (
+    # When we package, the parent directory 'connect' dir
+    # (as we pip install -e python/packaging/connect)
+    os.getcwd() == str(Path(__file__).parent.absolute())
+    and str(Path(__file__).parent.name) == "connect"
+):
+    # For:
+    # - pip install -e python/packaging/connect
+    #     It moves the current working directory to 'connect'
+    # - cd python/packaging/connect; python setup.py sdist
+    #
+    # For:
+    # - python packaging/connect/setup.py sdist, it does not
+    #     execute this branch.
+    #
+    # Move to spark/python
+    os.chdir(Path(__file__).parent.parent.parent.absolute())
+
+# Check and see if we are under the spark path in which case we need to build the symlink farm.
+# This is important because we only want to build the symlink farm while under Spark otherwise we
+# want to use the symlink farm. And if the symlink farm exists under while under Spark (e.g. a
+# partially built sdist) we should error and have the user sort it out.
+in_spark = os.path.isfile("../core/src/main/scala/org/apache/spark/SparkContext.scala") or (
+    os.path.isfile("../RELEASE") and len(glob.glob("../jars/spark*core*.jar")) == 1
+)
+
+try:
+    if in_spark:
+        # !!HACK ALTERT!!
+        # 1. `setup.py` has to be located with the same directory with the package.
+        #    Therefore, we copy the current file, and place it at `spark/python` directory.
+        #    After that, we remove it in the end.
+        # 2. Here it renames `pyspark` and `lib` to `pyspark.back` and `lib.back` so MANIFEST.in
+        #    does not pick `pyspark` and `py4j` up. We rename it back in the end.
+        move("pyspark", "pyspark.back")
+        move("lib", "lib.back")
+        copyfile("packaging/connect/setup.py", "setup.py")
+        copyfile("packaging/connect/setup.cfg", "setup.cfg")
+        copytree("packaging/connect/pyspark_connect", "pyspark_connect")
+        copyfile("pyspark.back/version.py", "pyspark_connect/version.py")
+
+    try:
+        exec(open("pyspark_connect/version.py").read())
+    except IOError:
+        print(
+            "Failed to load PySpark Connect version file for packaging. "
+            "You must be in Spark's python dir.",
+            file=sys.stderr,
+        )
+        sys.exit(-1)
+    VERSION = __version__  # noqa
+
+    # If you are changing the versions here, please also change ./python/pyspark/sql/pandas/utils.py
+    # For Arrow, you should also check ./pom.xml and ensure there are no breaking changes in the
+    # binary format protocol with the Java version, see ARROW_HOME/format/* for specifications.
+    # Also don't forget to update python/docs/source/getting_started/install.rst,
+    # python/packaging/classic/setup.py, and python/packaging/client/setup.py
+    _minimum_pandas_version = "2.0.0"
+    _minimum_numpy_version = "1.21"
+    _minimum_pyarrow_version = "11.0.0"
+    _minimum_grpc_version = "1.67.0"
+    _minimum_googleapis_common_protos_version = "1.65.0"
+
+    with open("README.md") as f:
+        long_description = f.read()
+
+    connect_packages = [
+        "pyspark_connect",
+    ]
+
+    setup(
+        name="pyspark-connect",
+        version=VERSION,
+        description="Apache Spark Python API with Spark Connect by default",
+        long_description=long_description,
+        long_description_content_type="text/markdown",
+        author="Spark Developers",
+        author_email="dev@spark.apache.org",
+        url="https://github.com/apache/spark/tree/master/python",
+        packages=connect_packages,
+        include_package_data=True,
+        license="http://www.apache.org/licenses/LICENSE-2.0",
+        # Don't forget to update python/docs/source/getting_started/install.rst
+        # if you're updating the versions or dependencies.
+        install_requires=[
+            "pyspark==%s" % VERSION,
+            "pandas>=%s" % _minimum_pandas_version,
+            "pyarrow>=%s" % _minimum_pyarrow_version,
+            "grpcio>=%s" % _minimum_grpc_version,
+            "grpcio-status>=%s" % _minimum_grpc_version,
+            "googleapis-common-protos>=%s" % _minimum_googleapis_common_protos_version,
+            "numpy>=%s" % _minimum_numpy_version,
+        ],
+        python_requires=">=3.9",
+        classifiers=[
+            "Development Status :: 5 - Production/Stable",
+            "License :: OSI Approved :: Apache Software License",
+            "Programming Language :: Python :: 3.9",
+            "Programming Language :: Python :: 3.10",
+            "Programming Language :: Python :: 3.11",
+            "Programming Language :: Python :: 3.12",
+            "Programming Language :: Python :: 3.13",
+            "Programming Language :: Python :: Implementation :: CPython",
+            "Programming Language :: Python :: Implementation :: PyPy",
+            "Typing :: Typed",
+        ],
+    )
+finally:
+    if in_spark:
+        move("pyspark.back", "pyspark")
+        move("lib.back", "lib")
+        os.remove("setup.py")
+        os.remove("setup.cfg")
+        rmtree("pyspark_connect")