Merge branch 'apache:master' into master

Author: jiayuasu

.asf.yaml

@@ -16,37 +16,40 @@
 # under the License.
 
 notifications:
-    commits:    [email protected]
-    issues_status:    [email protected]
-    issues_comment:    [email protected]
-    pullrequests_status:    [email protected]
-    pullrequests_comment:    [email protected]
-    jira_options: link label worklog
+  commits: [email protected]
+  issues_status: [email protected]
+  issues_comment: [email protected]
+  discussions: [email protected]
+  pullrequests_status: [email protected]
+  pullrequests_comment: [email protected]
+  jira_options: link label worklog
 github:
-    description: "A cluster computing framework for processing large-scale geospatial data"
-    homepage: https://sedona.apache.org/
-    collaborators:
-        - MrPowers
-        - umartin
-        - zhangfengcdt
-        - james-willis
-        - gregleleu
-    autolink_jira:
-        - SEDONA
-    labels:
-        - geospatial
-        - cluster-computing
-        - spatial-query
-        - spatial-analysis
-        - spatial-sql
-        - scala
-        - java
-        - python
-    features:
-        # Enable wiki for documentation
-        wiki: false
-        # Enable issue management
-        issues: true
-        # Enable projects for project management boards
-        projects: false
-    ghp_branch:
+  description: 'A cluster computing framework for processing large-scale geospatial data'
+  homepage: https://sedona.apache.org/
+  collaborators:
+    - MrPowers
+    - umartin
+    - zhangfengcdt
+    - james-willis
+    - gregleleu
+  autolink_jira:
+    - SEDONA
+  labels:
+    - geospatial
+    - cluster-computing
+    - spatial-query
+    - spatial-analysis
+    - spatial-sql
+    - scala
+    - java
+    - python
+  features:
+    # Enable wiki for documentation
+    wiki: false
+    # Enable issue management
+    issues: true
+    # Enable projects for project management boards
+    projects: false
+    # Enable GitHub discussion
+    discussions: true
+  ghp_branch:

.github/CODEOWNERS

@@ -1 +1,8 @@
-*   @jiayuasu
+*                           @jiayuasu
+.editorconfig               @jbampton @jiayuasu
+.pre-commit-config.yaml     @jbampton @jiayuasu
+.prettierignore             @jbampton @jiayuasu
+.prettierrc                 @jbampton @jiayuasu
+.shellcheckrc               @jbampton @jiayuasu
+Makefile                    @jbampton @jiayuasu
+/.github/linters/           @jbampton @jiayuasu

.github/linters/.yaml-lint.yml

@@ -21,6 +21,7 @@ extends: default
 
 rules:
   colons: disable
+  comments: disable
   document-start: disable
   line-length: disable
   truthy: false

.github/linters/codespell.txt

@@ -1,20 +1,12 @@
-LOD
 actualy
 afterall
 atmost
-bu
 celle
 checkin
 eiter
-errorprone
-fpt
-limite
-nd
-ois
 parm
 pavin
 pixelx
-refere
 ser
 shouldbe
 wel

.github/workflows/docker-build.yml

@@ -33,6 +33,10 @@ on:
 env:
   MAVEN_OPTS: -Dmaven.wagon.httpconnectionManager.ttlSeconds=60
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/master' }}
+
 permissions:
   contents: read
 
@@ -45,8 +49,8 @@ jobs:
         spark: ['3.5.1', '3.4.3', '3.3.4']
         include:
           - spark: 3.5.1
-            sedona: "latest"
-            geotools: "auto"
+            sedona: 'latest'
+            geotools: 'auto'
           - spark: 3.4.3
             sedona: 1.6.0
             geotools: 28.2

.github/workflows/docs.yml

@@ -29,6 +29,10 @@ on:
 env:
   MAVEN_OPTS: -Dmaven.wagon.httpconnectionManager.ttlSeconds=60
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/master' }}
+
 jobs:
   build:
     runs-on: ubuntu-22.04
@@ -40,31 +44,27 @@ jobs:
         uses: actions/setup-java@v4
         with:
           distribution: 'zulu'
-          java-version: '8'
+          java-version: '11'
       - name: Compile JavaDoc
         run: mvn -q clean install -DskipTests && mkdir -p docs/api/javadoc/spark && cp -r spark/common/target/apidocs/* docs/api/javadoc/spark/
       - name: Compile ScalaDoc
-        run: mvn scala:doc && mkdir -p docs/api/scaladoc/spark && cp -r spark/common/target/site/scaladocs/* docs/api/scaladoc/spark
+        run: mvn scala:doc -pl !common,!snowflake,!flink && mkdir -p docs/api/scaladoc/spark && cp -r spark/common/target/site/scaladocs/* docs/api/scaladoc/spark
       - uses: actions/setup-python@v5
         with:
           python-version: 3.x
-      - run: pip install mkdocs-jupyter
-      - run: pip install mkdocs-material
-      - run: pip install mkdocs-macros-plugin
-      - run: pip install mkdocs-git-revision-date-localized-plugin
-      - run: pip install mike
+      - run: pip install -r requirements-docs.txt
       - run: sudo apt update
-      - uses: r-lib/actions/[email protected].2
+      - uses: r-lib/actions/[email protected].3
         with:
           r-version: release
           use-public-rspm: true
       - name: Query R dependencies
-        uses: r-lib/actions/[email protected].2
+        uses: r-lib/actions/[email protected].3
         with:
           cache: true
           extra-packages: |
             any::pkgdown
-          working-directory : './R'
+          working-directory: './R'
       - run: Rscript -e 'pkgdown::build_site(pkg = "./R", preview = FALSE, override = list(destination = "../docs/api/rdocs"))'
       - run: git config --global user.name = "GitHub Action"
       - run: git config --global user.email = "[email protected]"

.github/workflows/example.yml

@@ -33,6 +33,10 @@ on:
 permissions:
   contents: read
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/master' }}
+
 jobs:
   build:
     runs-on: ubuntu-22.04
@@ -54,7 +58,7 @@ jobs:
       - uses: actions/setup-java@v4
         with:
           distribution: 'zulu'
-          java-version: '8'
+          java-version: '11'
       - run: sudo apt-get remove scala-library scala
       - run: sudo wget www.scala-lang.org/files/archive/scala-2.12.11.deb
       - run: sudo dpkg -i scala-2.12.11.deb
@@ -78,6 +82,7 @@ jobs:
           restore-keys: ${{ runner.os }}-m2
       - env:
           SPARK_VERSION: ${{ matrix.spark }}
+          SPARK_LOCAL_IP: 127.0.0.1
           SPARK_COMPAT_VERSION: ${{ matrix.spark-compat }}
           SEDONA_VERSION: ${{ matrix.sedona }}
         run: (cd examples/spark-sql;mvn clean install -Dspark.version=${SPARK_VERSION} -Dspark.compat.version=${SPARK_COMPAT_VERSION} -Dsedona.version=${SEDONA_VERSION};java -jar target/sedona-spark-example-1.6.0.jar)

.github/workflows/first-interaction.yml

@@ -23,6 +23,10 @@ on:
   pull_request:
     types: [opened]
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/master' }}
+
 jobs:
   first-interaction:
     runs-on: ubuntu-latest
@@ -31,5 +35,5 @@ jobs:
         uses: actions/first-interaction@v1
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
-          issue-message: "Thank you for your interest in Apache Sedona! We appreciate you opening your first issue. Contributions like yours help make Apache Sedona better."
-          pr-message: "Welcome and thank you for your first pull request! We appreciate your contribution to Apache Sedona. Your code changes will be reviewed shortly."
+          issue-message: 'Thank you for your interest in Apache Sedona! We appreciate you opening your first issue. Contributions like yours help make Apache Sedona better.'
+          pr-message: 'Welcome and thank you for your first pull request! We appreciate your contribution to Apache Sedona. Your code changes will be reviewed shortly.'

.github/workflows/java.yml

@@ -46,10 +46,15 @@ on:
 env:
   MAVEN_OPTS: -Dmaven.wagon.httpconnectionManager.ttlSeconds=60
   DO_NOT_TRACK: true
+  SPARK_LOCAL_IP: 127.0.0.1
 
 permissions:
   contents: read
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/master' }}
+
 jobs:
   build:
     runs-on: ubuntu-22.04
@@ -59,35 +64,27 @@ jobs:
         include:
           - spark: 3.5.0
             scala: 2.13.8
-            jdk: '8'
-            skipTests: ''
-          - spark: 3.5.0
-            scala: 2.12.15
-            jdk: '8'
+            jdk: '11'
             skipTests: ''
           - spark: 3.5.0
             scala: 2.12.15
             jdk: '11'
             skipTests: ''
           - spark: 3.4.0
             scala: 2.13.8
-            jdk: '8'
-            skipTests: ''
-          - spark: 3.4.0
-            scala: 2.12.15
-            jdk: '8'
+            jdk: '11'
             skipTests: ''
           - spark: 3.4.0
             scala: 2.12.15
             jdk: '11'
             skipTests: ''
           - spark: 3.3.0
             scala: 2.13.8
-            jdk: '8'
+            jdk: '11'
             skipTests: ''
           - spark: 3.3.0
             scala: 2.12.15
-            jdk: '8'
+            jdk: '11'
             skipTests: ''
     steps:
       - uses: actions/checkout@v4
@@ -97,7 +94,7 @@ jobs:
           java-version: ${{ matrix.jdk }}
       - uses: actions/setup-python@v5
         with:
-          python-version: '3.7'
+          python-version: '3.10'
       - name: Cache Maven packages
         uses: actions/cache@v4
         with:
@@ -110,6 +107,12 @@ jobs:
           SKIP_TESTS: ${{ matrix.skipTests }}
         run: |
           SPARK_COMPAT_VERSION=${SPARK_VERSION:0:3}
+
+          if [ "${SPARK_VERSION}" == "3.5.0" ]; then
+              pip install pyspark==3.5.0 pandas shapely apache-sedona pyarrow
+              export SPARK_HOME=$(python -c "import pyspark; print(pyspark.__path__[0])")
+          fi
+
           mvn -q clean install -Dspark=${SPARK_COMPAT_VERSION} -Dscala=${SCALA_VERSION:0:4} -Dspark.version=${SPARK_VERSION} ${SKIP_TESTS}
       - run: mkdir staging
       - run: cp spark-shaded/target/sedona-*.jar staging

.github/workflows/labeler.yml

@@ -28,5 +28,5 @@ jobs:
     steps:
       - uses: actions/labeler@v5
         with:
-          repo-token: "${{ secrets.GITHUB_TOKEN }}"
+          repo-token: '${{ secrets.GITHUB_TOKEN }}'
           sync-labels: true

.github/workflows/lint.yml

@@ -22,18 +22,22 @@ on: [pull_request]
 permissions:
   contents: read
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/master' }}
+
 jobs:
   pre-commit:
-    name: Run pre-commit  # https://pre-commit.com/
+    name: Run pre-commit # https://pre-commit.com/
     runs-on: ubuntu-latest
     steps:
-      - name: "Checkout ${{ github.ref }} ( ${{ github.sha }} )"
+      - name: 'Checkout ${{ github.ref }} ( ${{ github.sha }} )'
         uses: actions/checkout@v4
-      - uses: actions/setup-python@v5  # https://www.python.org/
+      - uses: actions/setup-python@v5 # https://www.python.org/
         with:
-          python-version: '3.x'  # Version range or exact version of a Python version to use, using SemVer's version range syntax
-          architecture: 'x64'  # optional x64 or x86. Defaults to x64 if not specified
-      - name: Install dependencies  # https://pip.pypa.io/en/stable/
+          python-version: '3.x' # Version range or exact version of a Python version to use, using SemVer's version range syntax
+          architecture: 'x64' # optional x64 or x86. Defaults to x64 if not specified
+      - name: Install dependencies # https://pip.pypa.io/en/stable/
         run: |
           python -m pip install --upgrade pip
           pip install pre-commit

.github/workflows/python-extension.yml

@@ -42,6 +42,10 @@ on:
 permissions:
   contents: read
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/master' }}
+
 jobs:
   build:
     strategy:
@@ -62,8 +66,13 @@ jobs:
       - name: Install dependencies
         run: |
           cd python
-          pipenv --python ${{ matrix.python }}
-          pipenv install --dev
+          if [[ "$RUNNER_OS" == "Windows" ]]; then
+              PYTHON_EXE_PATH="$pythonLocation/python.exe"
+          else
+              PYTHON_EXE_PATH="$pythonLocation/python"
+          fi
+          echo "Using Python executable at: $PYTHON_EXE_PATH"
+          pipenv install --dev --python "$PYTHON_EXE_PATH"
       - name: Build extension
         run: |
           cd python

.github/workflows/python-wheel.yml

@@ -39,6 +39,10 @@ on:
       - 'python/**'
       - '.github/workflows/python-wheel.yml'
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/master' }}
+
 jobs:
   build:
     strategy:
@@ -59,7 +63,7 @@ jobs:
           image: tonistiigi/binfmt:qemu-v8.1.5
           platforms: all
       - name: Build wheels
-        uses: pypa/cibuildwheel@v2.22.0
+        uses: pypa/cibuildwheel@v2.23.3
         env:
           CIBW_SKIP: 'pp* *musl*'
           CIBW_ARCHS_LINUX: 'x86_64 aarch64'