[SPARK-48204][INFRA][FOLLOW] fix release scripts for the "finalize" step

### What changes were proposed in this pull request?

Necessary fixes to finalize the spark 4.0 preview release. The major one is that pypi now requires API token instead of username/password for authentication.

### Why are the changes needed?

release

### Does this PR introduce _any_ user-facing change?

no

### How was this patch tested?

manual

### Was this patch authored or co-authored using generative AI tooling?

no

Closes #46840 from cloud-fan/script.

Authored-by: Wenchen Fan <wenchen@databricks.com>
Signed-off-by: Hyukjin Kwon <gurwls223@apache.org>

dev/create-release/do-release-docker.sh

@@ -84,8 +84,8 @@ if [ ! -z "$RELEASE_STEP" ] && [ "$RELEASE_STEP" = "finalize" ]; then
     error "Exiting."
   fi
 
-  if [ -z "$PYPI_PASSWORD" ]; then
-    stty -echo && printf "PyPi password: " && read PYPI_PASSWORD && printf '\n' && stty echo
+  if [ -z "$PYPI_API_TOKEN" ]; then
+    stty -echo && printf "PyPi API token: " && read PYPI_API_TOKEN && printf '\n' && stty echo
   fi
 fi
 
@@ -142,7 +142,7 @@ GIT_NAME=$GIT_NAME
 GIT_EMAIL=$GIT_EMAIL
 GPG_KEY=$GPG_KEY
 ASF_PASSWORD=$ASF_PASSWORD
-PYPI_PASSWORD=$PYPI_PASSWORD
+PYPI_API_TOKEN=$PYPI_API_TOKEN
 GPG_PASSPHRASE=$GPG_PASSPHRASE
 RELEASE_STEP=$RELEASE_STEP
 USER=$USER

dev/create-release/release-build.sh

@@ -98,40 +98,45 @@ init_java
 init_maven_sbt
 
 if [[ "$1" == "finalize" ]]; then
-  if [[ -z "$PYPI_PASSWORD" ]]; then
-    error 'The environment variable PYPI_PASSWORD is not set. Exiting.'
+  if [[ -z "$PYPI_API_TOKEN" ]]; then
+    error 'The environment variable PYPI_API_TOKEN is not set. Exiting.'
   fi
 
   git config --global user.name "$GIT_NAME"
   git config --global user.email "$GIT_EMAIL"
 
   # Create the git tag for the new release
   echo "Creating the git tag for the new release"
-  rm -rf spark
-  git clone "https://$ASF_USERNAME:$ASF_PASSWORD@$ASF_SPARK_REPO" -b master
-  cd spark
-  git tag "v$RELEASE_VERSION" "$RELEASE_TAG"
-  git push origin "v$RELEASE_VERSION"
-  cd ..
-  rm -rf spark
-  echo "git tag v$RELEASE_VERSION created"
+  if check_for_tag "v$RELEASE_VERSION"; then
+    echo "v$RELEASE_VERSION already exists. Skip creating it."
+  else
+    rm -rf spark
+    git clone "https://$ASF_USERNAME:$ASF_PASSWORD@$ASF_SPARK_REPO" -b master
+    cd spark
+    git tag "v$RELEASE_VERSION" "$RELEASE_TAG"
+    git push origin "v$RELEASE_VERSION"
+    cd ..
+    rm -rf spark
+    echo "git tag v$RELEASE_VERSION created"
+  fi
 
   # download PySpark binary from the dev directory and upload to PyPi.
   echo "Uploading PySpark to PyPi"
   svn co --depth=empty "$RELEASE_STAGING_LOCATION/$RELEASE_TAG-bin" svn-spark
   cd svn-spark
-  svn update "pyspark-$RELEASE_VERSION.tar.gz"
-  svn update "pyspark-$RELEASE_VERSION.tar.gz.asc"
-  TWINE_USERNAME=spark-upload TWINE_PASSWORD="$PYPI_PASSWORD" twine upload \
+  PYSPARK_VERSION=`echo "$RELEASE_VERSION" |  sed -e "s/-/./" -e "s/preview/dev/"`
+  svn update "pyspark-$PYSPARK_VERSION.tar.gz"
+  svn update "pyspark-$PYSPARK_VERSION.tar.gz.asc"
+  twine upload -u __token__  -p $PYPI_API_TOKEN \
     --repository-url https://upload.pypi.org/legacy/ \
-    "pyspark-$RELEASE_VERSION.tar.gz" \
-    "pyspark-$RELEASE_VERSION.tar.gz.asc"
-  svn update "pyspark_connect-$RELEASE_VERSION.tar.gz"
-  svn update "pyspark_connect-$RELEASE_VERSION.tar.gz.asc"
-  TWINE_USERNAME=spark-upload TWINE_PASSWORD="$PYPI_PASSWORD" twine upload \
+    "pyspark-$PYSPARK_VERSION.tar.gz" \
+    "pyspark-$PYSPARK_VERSION.tar.gz.asc"
+  svn update "pyspark_connect-$PYSPARK_VERSION.tar.gz"
+  svn update "pyspark_connect-$PYSPARK_VERSION.tar.gz.asc"
+  twine upload -u __token__  -p $PYPI_API_TOKEN \
     --repository-url https://upload.pypi.org/legacy/ \
-    "pyspark_connect-$RELEASE_VERSION.tar.gz" \
-    "pyspark_connect-$RELEASE_VERSION.tar.gz.asc"
+    "pyspark_connect-$PYSPARK_VERSION.tar.gz" \
+    "pyspark_connect-$PYSPARK_VERSION.tar.gz.asc"
   cd ..
   rm -rf svn-spark
   echo "PySpark uploaded"

dev/create-release/spark-rm/Dockerfile

@@ -95,7 +95,7 @@ RUN curl -sS https://bootstrap.pypa.io/get-pip.py | pypy3
 RUN pypy3 -m pip install numpy 'six==1.16.0' 'pandas==2.2.2' scipy coverage matplotlib lxml
 
 
-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"
+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==1.56.4"