[CI] Add pre-commit hook shellcheck-py to lint shell files

.pre-commit-config.yaml

@@ -70,6 +70,10 @@ repos:
         exclude: ^\.github/.*$
         types: [markdown]
         files: \.(md|mdown|markdown)$
+  - repo: https://github.com/shellcheck-py/shellcheck-py
+    rev: v0.10.0.1
+    hooks:
+      - id: shellcheck
   - repo: https://github.com/adrienverge/yamllint
     rev: v1.35.1
     hooks:

.shellcheckrc

@@ -0,0 +1 @@
+disable=SC2004,SC2041,SC2155,SC2181

docker/sedona-spark-jupyterlab/build.sh

@@ -23,7 +23,7 @@ BUILD_MODE=$3
 GEOTOOLS_VERSION=${4:-auto}
 
 SEDONA_SPARK_VERSION=${SPARK_VERSION:0:3}
-if [ ${SPARK_VERSION:0:1} -eq "3" ] && [ ${SPARK_VERSION:2:1} -le "3" ]; then
+if [ "${SPARK_VERSION:0:1}" -eq "3" ] && [ "${SPARK_VERSION:2:1}" -le "3" ]; then
     # 3.0, 3.1, 3.2, 3.3
     SEDONA_SPARK_VERSION=3.0
 fi
@@ -42,7 +42,7 @@ get_latest_version_with_suffix() {
 
   # Fetch the maven-metadata.xml file
   METADATA_URL="${BASE_URL}maven-metadata.xml"
-  METADATA_XML=$(curl -s $METADATA_URL)
+  METADATA_XML=$(curl -s "$METADATA_URL")
 
   # Extract versions from the XML
   VERSIONS=$(echo "$METADATA_XML" | grep -o '<version>[^<]*</version>' | awk -F'[<>]' '{print $3}')
@@ -52,7 +52,7 @@ get_latest_version_with_suffix() {
   # Filter versions that end with the specified suffix and find the largest one
   for VERSION in $VERSIONS; do
     if [[ $VERSION == *$SUFFIX ]]; then
-      if [[ -z $LATEST_VERSION ]] || version_gt $VERSION $LATEST_VERSION; then
+      if [[ -z $LATEST_VERSION ]] || version_gt "$VERSION" "$LATEST_VERSION"; then
         LATEST_VERSION=$VERSION
       fi
     fi
@@ -61,7 +61,7 @@ get_latest_version_with_suffix() {
   if [[ -z $LATEST_VERSION ]]; then
     exit 1
   else
-    echo $LATEST_VERSION
+    echo "$LATEST_VERSION"
   fi
 }
 
@@ -80,7 +80,7 @@ if [ "$SEDONA_VERSION" = "latest" ]; then
     echo "Using latest geotools-wrapper version: $GEOTOOLS_WRAPPER_VERSION"
 
     # The compilation must take place outside Docker to avoid unnecessary maven packages
-    mvn clean install -DskipTests -Dspark=${SEDONA_SPARK_VERSION} -Dscala=2.12
+    mvn clean install -DskipTests -Dspark="${SEDONA_SPARK_VERSION}" -Dscala=2.12
 fi
 
 # -- Building the image
@@ -92,7 +92,7 @@ if [ -z "$BUILD_MODE" ] || [ "$BUILD_MODE" = "local" ]; then
     --build-arg sedona_version="${SEDONA_VERSION}" \
     --build-arg geotools_wrapper_version="${GEOTOOLS_WRAPPER_VERSION}" \
     -f docker/sedona-spark-jupyterlab/sedona-jupyterlab.dockerfile \
-    -t apache/sedona:${SEDONA_VERSION} .
+    -t apache/sedona:"${SEDONA_VERSION}" .
 else
     # If release, build the image for cross-platform
     docker buildx build --platform linux/amd64,linux/arm64 \
@@ -103,5 +103,5 @@ else
     --build-arg sedona_version="${SEDONA_VERSION}" \
     --build-arg geotools_wrapper_version="${GEOTOOLS_WRAPPER_VERSION}" \
     -f docker/sedona-spark-jupyterlab/sedona-jupyterlab.dockerfile \
-    -t apache/sedona:${SEDONA_VERSION} .
+    -t apache/sedona:"${SEDONA_VERSION}" .
 fi

docker/sedona-spark-jupyterlab/start.sh

@@ -29,7 +29,7 @@ convert_to_mb() {
       echo $(($mem_value * 1024))
       ;;
     [mM])
-      echo $mem_value
+      echo "$mem_value"
       ;;
     *)
       echo "Invalid memory unit: $mem_str" >&2
@@ -39,13 +39,13 @@ convert_to_mb() {
 }
 
 # Convert DRIVER_MEM and EXECUTOR_MEM to megabytes
-DRIVER_MEM_MB=$(convert_to_mb $DRIVER_MEM)
+DRIVER_MEM_MB=$(convert_to_mb "$DRIVER_MEM")
 if [ $? -ne 0 ]; then
   echo "Error converting DRIVER_MEM to megabytes." >&2
   exit 1
 fi
 
-EXECUTOR_MEM_MB=$(convert_to_mb $EXECUTOR_MEM)
+EXECUTOR_MEM_MB=$(convert_to_mb "$EXECUTOR_MEM")
 if [ $? -ne 0 ]; then
   echo "Error converting EXECUTOR_MEM to megabytes." >&2
   exit 1
@@ -58,7 +58,7 @@ TOTAL_PHYSICAL_MEM_MB=$(free -m | awk '/^Mem:/{print $2}')
 TOTAL_REQUIRED_MEM_MB=$(($DRIVER_MEM_MB + $EXECUTOR_MEM_MB))
 
 # Compare total required memory with total physical memory
-if [ $TOTAL_REQUIRED_MEM_MB -gt $TOTAL_PHYSICAL_MEM_MB ]; then
+if [ $TOTAL_REQUIRED_MEM_MB -gt "$TOTAL_PHYSICAL_MEM_MB" ]; then
     echo "Error: Insufficient memory" >&2
     echo "  total:    $TOTAL_PHYSICAL_MEM_MB MB" >&2
     echo "  required: $TOTAL_REQUIRED_MEM_MB MB (driver: $DRIVER_MEM_MB MB, executor: $EXECUTOR_MEM_MB MB)" >&2
@@ -68,14 +68,14 @@ if [ $TOTAL_REQUIRED_MEM_MB -gt $TOTAL_PHYSICAL_MEM_MB ]; then
 fi
 
 # Configure spark
-cp ${SPARK_HOME}/conf/spark-env.sh.template ${SPARK_HOME}/conf/spark-env.sh
-echo "SPARK_WORKER_MEMORY=${EXECUTOR_MEM}" >> ${SPARK_HOME}/conf/spark-env.sh
-echo "spark.driver.memory $DRIVER_MEM" >> ${SPARK_HOME}/conf/spark-defaults.conf
-echo "spark.executor.memory $EXECUTOR_MEM" >> ${SPARK_HOME}/conf/spark-defaults.conf
+cp "${SPARK_HOME}"/conf/spark-env.sh.template "${SPARK_HOME}"/conf/spark-env.sh
+echo "SPARK_WORKER_MEMORY=${EXECUTOR_MEM}" >> "${SPARK_HOME}"/conf/spark-env.sh
+echo "spark.driver.memory $DRIVER_MEM" >> "${SPARK_HOME}"/conf/spark-defaults.conf
+echo "spark.executor.memory $EXECUTOR_MEM" >> "${SPARK_HOME}"/conf/spark-defaults.conf
 
 # Start spark standalone cluster
 service ssh start
-${SPARK_HOME}/sbin/start-all.sh
+"${SPARK_HOME}"/sbin/start-all.sh
 
 # Start jupyter lab
 exec jupyter lab --ip=0.0.0.0 --port=8888 --no-browser --allow-root --NotebookApp.token=

docker/sedona.sh

@@ -25,29 +25,29 @@ spark_extension_version=$4
 
 spark_compat_version=${spark_version:0:3}
 sedona_spark_version=${spark_compat_version}
-if [ ${spark_version:0:1} -eq "3" ] && [ ${spark_version:2:1} -le "3" ]; then
+if [ "${spark_version:0:1}" -eq "3" ] && [ "${spark_version:2:1}" -le "3" ]; then
     # 3.0, 3.1, 3.2, 3.3
     sedona_spark_version=3.0
 fi
 
-if [ $sedona_version = "latest" ]; then
+if [ "$sedona_version" = "latest" ]; then
     # Code to execute when SEDONA_VERSION is "latest"
-    cp ${SEDONA_HOME}/spark-shaded/target/sedona-spark-shaded-*.jar ${SPARK_HOME}/jars/
-	cd ${SEDONA_HOME}/python;pip3 install .
+    cp "${SEDONA_HOME}"/spark-shaded/target/sedona-spark-shaded-*.jar "${SPARK_HOME}"/jars/
+	cd "${SEDONA_HOME}"/python;pip3 install .
 else
     # Code to execute when SEDONA_VERSION is not "latest"
     # Download Sedona
-	curl https://repo1.maven.org/maven2/org/apache/sedona/sedona-spark-shaded-${sedona_spark_version}_2.12/${sedona_version}/sedona-spark-shaded-${sedona_spark_version}_2.12-${sedona_version}.jar -o $SPARK_HOME/jars/sedona-spark-shaded-${sedona_spark_version}_2.12-${sedona_version}.jar
+	curl https://repo1.maven.org/maven2/org/apache/sedona/sedona-spark-shaded-"${sedona_spark_version}"_2.12/"${sedona_version}"/sedona-spark-shaded-"${sedona_spark_version}"_2.12-"${sedona_version}".jar -o "$SPARK_HOME"/jars/sedona-spark-shaded-"${sedona_spark_version}"_2.12-"${sedona_version}".jar
 
 	# Install Sedona Python
-	pip3 install apache-sedona==${sedona_version}
+	pip3 install apache-sedona=="${sedona_version}"
 fi
 
 # Download gresearch spark extension
-curl https://repo1.maven.org/maven2/uk/co/gresearch/spark/spark-extension_2.12/${spark_extension_version}-${spark_compat_version}/spark-extension_2.12-${spark_extension_version}-${spark_compat_version}.jar -o $SPARK_HOME/jars/spark-extension_2.12-${spark_extension_version}-${spark_compat_version}.jar
+curl https://repo1.maven.org/maven2/uk/co/gresearch/spark/spark-extension_2.12/"${spark_extension_version}"-"${spark_compat_version}"/spark-extension_2.12-"${spark_extension_version}"-"${spark_compat_version}".jar -o "$SPARK_HOME"/jars/spark-extension_2.12-"${spark_extension_version}"-"${spark_compat_version}".jar
 
 # Install Spark extension Python
-pip3 install pyspark-extension==${spark_extension_version}.${spark_compat_version}
+pip3 install pyspark-extension=="${spark_extension_version}"."${spark_compat_version}"
 
 # Download GeoTools jar
-curl https://repo1.maven.org/maven2/org/datasyslab/geotools-wrapper/${geotools_wrapper_version}/geotools-wrapper-${geotools_wrapper_version}.jar -o $SPARK_HOME/jars/geotools-wrapper-${geotools_wrapper_version}.jar
+curl https://repo1.maven.org/maven2/org/datasyslab/geotools-wrapper/"${geotools_wrapper_version}"/geotools-wrapper-"${geotools_wrapper_version}".jar -o "$SPARK_HOME"/jars/geotools-wrapper-"${geotools_wrapper_version}".jar

docker/spark.sh

@@ -30,20 +30,20 @@ apt-get install -y openjdk-19-jdk-headless curl python3-pip maven
 pip3 install --upgrade pip && pip3 install pipenv
 
 # Download Spark jar and set up PySpark
-curl https://archive.apache.org/dist/spark/spark-${spark_version}/spark-${spark_version}-bin-hadoop${hadoop_version}.tgz -o spark.tgz
-tar -xf spark.tgz && mv spark-${spark_version}-bin-hadoop${hadoop_version}/* ${SPARK_HOME}/
-rm spark.tgz && rm -rf spark-${spark_version}-bin-hadoop${hadoop_version}
-pip3 install pyspark==${spark_version}
+curl https://archive.apache.org/dist/spark/spark-"${spark_version}"/spark-"${spark_version}"-bin-hadoop"${hadoop_version}".tgz -o spark.tgz
+tar -xf spark.tgz && mv spark-"${spark_version}"-bin-hadoop"${hadoop_version}"/* "${SPARK_HOME}"/
+rm spark.tgz && rm -rf spark-"${spark_version}"-bin-hadoop"${hadoop_version}"
+pip3 install pyspark=="${spark_version}"
 
 # Add S3 jars
-curl https://repo1.maven.org/maven2/org/apache/hadoop/hadoop-aws/${hadoop_s3_version}/hadoop-aws-${hadoop_s3_version}.jar -o ${SPARK_HOME}/jars/hadoop-aws-${hadoop_s3_version}.jar
-curl https://repo1.maven.org/maven2/com/amazonaws/aws-java-sdk-bundle/${aws_sdk_version}/aws-java-sdk-bundle-${aws_sdk_version}.jar -o ${SPARK_HOME}/jars/aws-java-sdk-bundle-${aws_sdk_version}.jar
+curl https://repo1.maven.org/maven2/org/apache/hadoop/hadoop-aws/"${hadoop_s3_version}"/hadoop-aws-"${hadoop_s3_version}".jar -o "${SPARK_HOME}"/jars/hadoop-aws-"${hadoop_s3_version}".jar
+curl https://repo1.maven.org/maven2/com/amazonaws/aws-java-sdk-bundle/"${aws_sdk_version}"/aws-java-sdk-bundle-"${aws_sdk_version}".jar -o "${SPARK_HOME}"/jars/aws-java-sdk-bundle-"${aws_sdk_version}".jar
 
 # Add spark-xml jar
-curl https://repo1.maven.org/maven2/com/databricks/spark-xml_2.12/${spark_xml_version}/spark-xml_2.12-${spark_xml_version}.jar -o ${SPARK_HOME}/jars/spark-xml_2.12-${spark_xml_version}.jar
+curl https://repo1.maven.org/maven2/com/databricks/spark-xml_2.12/"${spark_xml_version}"/spark-xml_2.12-"${spark_xml_version}".jar -o "${SPARK_HOME}"/jars/spark-xml_2.12-"${spark_xml_version}".jar
 
 # Set up master IP address and executor memory
-cp ${SPARK_HOME}/conf/spark-defaults.conf.template ${SPARK_HOME}/conf/spark-defaults.conf
+cp "${SPARK_HOME}"/conf/spark-defaults.conf.template "${SPARK_HOME}"/conf/spark-defaults.conf
 
 # Install required libraries for GeoPandas on Apple chip mac
 apt-get install -y gdal-bin libgdal-dev