[SPARK-50106][PYTHON] Upgrade protobuf Python package to 5.28.3 and…

… `protobuf-java` to 4.28.3

.github/workflows/build_and_test.yml

@@ -276,7 +276,7 @@ jobs:
     - name: Install Python packages (Python 3.11)
       if: (contains(matrix.modules, 'sql') && !contains(matrix.modules, 'sql-')) || contains(matrix.modules, 'connect')
       run: |
-        python3.11 -m pip install 'numpy>=1.20.0' pyarrow pandas scipy unittest-xml-reporting 'lxml==4.9.4' 'grpcio==1.62.0' 'grpcio-status==1.62.0' 'protobuf==4.25.1'
+        python3.11 -m pip install 'numpy>=1.20.0' pyarrow pandas scipy unittest-xml-reporting 'lxml==4.9.4' 'grpcio==1.62.0' 'grpcio-status==1.62.0' 'protobuf==5.28.3'
         python3.11 -m pip list
     # Run the tests.
     - name: Run tests
@@ -614,7 +614,7 @@ jobs:
         python-version: '3.11'
     - name: Install dependencies for Python CodeGen check
       run: |
-        python3.11 -m pip install 'black==23.9.1' 'protobuf==4.25.1' 'mypy==1.8.0' 'mypy-protobuf==3.3.0'
+        python3.11 -m pip install 'black==23.9.1' 'protobuf==5.28.3' 'mypy==1.8.0' 'mypy-protobuf==3.3.0'
         python3.11 -m pip list
     - name: Python CodeGen check
       run: ./dev/connect-check-protos.py

.github/workflows/maven_test.yml

@@ -178,7 +178,7 @@ jobs:
       - name: Install Python packages (Python 3.11)
         if: (contains(matrix.modules, 'sql#core')) || contains(matrix.modules, 'connect')
         run: |
-          python3.11 -m pip install 'numpy>=1.20.0' pyarrow pandas scipy unittest-xml-reporting 'grpcio==1.62.0' 'grpcio-status==1.62.0' 'protobuf==4.25.1'
+          python3.11 -m pip install 'numpy>=1.20.0' pyarrow pandas scipy unittest-xml-reporting 'grpcio==1.62.0' 'grpcio-status==1.62.0' 'protobuf==5.28.3'
           python3.11 -m pip list
       # Run the tests.
       - name: Run tests

dev/create-release/spark-rm/Dockerfile

@@ -102,7 +102,7 @@ RUN pypy3 -m pip install numpy 'six==1.16.0' 'pandas==2.2.2' scipy coverage matp
 
 ARG BASIC_PIP_PKGS="numpy pyarrow>=15.0.0 six==1.16.0 pandas==2.2.2 scipy plotly>=4.8 mlflow>=2.8.1 coverage matplotlib openpyxl memory-profiler>=0.61.0 scikit-learn>=1.3.2 twine==3.4.1"
 # Python deps for Spark Connect
-ARG CONNECT_PIP_PKGS="grpcio==1.62.0 grpcio-status==1.62.0 protobuf==4.25.1 googleapis-common-protos==1.65.0"
+ARG CONNECT_PIP_PKGS="grpcio==1.62.0 grpcio-status==1.62.0 protobuf==5.28.3 googleapis-common-protos==1.65.0"
 
 # Install Python 3.10 packages
 RUN curl -sS https://bootstrap.pypa.io/get-pip.py | python3.10

dev/infra/Dockerfile

@@ -96,7 +96,7 @@ RUN pypy3 -m pip install numpy 'six==1.16.0' 'pandas==2.2.3' scipy coverage matp
 
 ARG BASIC_PIP_PKGS="numpy pyarrow>=15.0.0 six==1.16.0 pandas==2.2.3 scipy plotly>=4.8 mlflow>=2.8.1 coverage matplotlib openpyxl memory-profiler>=0.61.0 scikit-learn>=1.3.2"
 # Python deps for Spark Connect
-ARG CONNECT_PIP_PKGS="grpcio==1.62.0 grpcio-status==1.62.0 protobuf==4.25.1 googleapis-common-protos==1.65.0 graphviz==0.20.3"
+ARG CONNECT_PIP_PKGS="grpcio==1.62.0 grpcio-status==1.62.0 protobuf==5.28.3 googleapis-common-protos==1.65.0 graphviz==0.20.3"
 
 # Install Python 3.10 packages
 RUN curl -sS https://bootstrap.pypa.io/get-pip.py | python3.10

pom.xml

@@ -125,7 +125,7 @@
     <!-- make sure to update IsolatedClientLoader whenever this version is changed -->
     <hadoop.version>3.4.1</hadoop.version>
     <!-- SPARK-41247: When updating `protobuf.version`, also need to update `protoVersion` in `SparkBuild.scala` -->
-    <protobuf.version>3.25.5</protobuf.version>
+    <protobuf.version>4.28.3</protobuf.version>
     <protoc-jar-maven-plugin.version>3.11.4</protoc-jar-maven-plugin.version>
     <yarn.version>${hadoop.version}</yarn.version>
     <zookeeper.version>3.9.2</zookeeper.version>

project/SparkBuild.scala

@@ -89,7 +89,7 @@ object BuildCommons {
 
   // Google Protobuf version used for generating the protobuf.
   // SPARK-41247: needs to be consistent with `protobuf.version` in `pom.xml`.
-  val protoVersion = "3.25.5"
+  val protoVersion = "4.28.3"
   // GRPC version used for Spark Connect.
   val grpcVersion = "1.62.2"
 }