Update spark and gradle versions, fix deprecated features

build.gradle

@@ -22,8 +22,9 @@ configurations {
     testImplementation.extendsFrom compileOnly
 }
 
-task scalaTest(dependsOn: ['testClasses'], type: JavaExec) {
+tasks.register('scalaTest', JavaExec) {
-    main = 'org.scalatest.tools.Runner'
+    dependsOn['testClasses']
+    mainClass = 'org.scalatest.tools.Runner'
     args = ['-R', 'build/classes/scala/test', '-o']
     classpath = sourceSets.test.runtimeClasspath
 }
@@ -35,7 +36,7 @@ jar {
         attributes "Main-Class": "${mainClass}"
     }
     from {
-        configurations.compile.collect { it.isDirectory() ? it : zipTree(it) }
+        configurations.runtimeClasspath.collect { it.isDirectory() ? it : zipTree(it) }
     }
     archiveFileName.set("${getArchiveBaseName().get()}-${projectVersion}.${getArchiveExtension().get()}")
 }

gradle.properties

@@ -1,9 +1,9 @@
-scalaMajorVersion=2.12
+scalaMajorVersion=2.13
 scalaMinorVersion=10
 
-apacheSparkVersion=3.0.1
+apacheSparkVersion=3.3.2
 
-scalaTestVersion=3.2.3
+scalaTestVersion=3.2.15
 
 mainClass=com.barrelsofdata.sparkexamples.Driver
 projectGroup=com.barrelsofdata.sparkexamples

gradle/wrapper/gradle-wrapper.properties

@@ -1,5 +1,6 @@
 distributionBase=GRADLE_USER_HOME
 distributionPath=wrapper/dists
-distributionUrl=https\://services.gradle.org/distributions/gradle-6.7.1-bin.zip
+distributionUrl=https\://services.gradle.org/distributions/gradle-8.0.2-bin.zip
+networkTimeout=10000
 zipStoreBase=GRADLE_USER_HOME
 zipStorePath=wrapper/dists

gradlew

@@ -1,7 +1,7 @@
-#!/usr/bin/env sh
+#!/bin/sh
 
 #
-# Copyright 2015 the original author or authors.
+# Copyright © 2015-2021 the original authors.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -17,67 +17,101 @@
 #
 
 ##############################################################################
-##
+#
-##  Gradle start up script for UN*X
+#   Gradle start up script for POSIX generated by Gradle.
-##
+#
+#   Important for running:
+#
+#   (1) You need a POSIX-compliant shell to run this script. If your /bin/sh is
+#       noncompliant, but you have some other compliant shell such as ksh or
+#       bash, then to run this script, type that shell name before the whole
+#       command line, like:
+#
+#           ksh Gradle
+#
+#       Busybox and similar reduced shells will NOT work, because this script
+#       requires all of these POSIX shell features:
+#         * functions;
+#         * expansions «$var», «${var}», «${var:-default}», «${var+SET}»,
+#           «${var#prefix}», «${var%suffix}», and «$( cmd )»;
+#         * compound commands having a testable exit status, especially «case»;
+#         * various built-in commands including «command», «set», and «ulimit».
+#
+#   Important for patching:
+#
+#   (2) This script targets any POSIX shell, so it avoids extensions provided
+#       by Bash, Ksh, etc; in particular arrays are avoided.
+#
+#       The "traditional" practice of packing multiple parameters into a
+#       space-separated string is a well documented source of bugs and security
+#       problems, so this is (mostly) avoided, by progressively accumulating
+#       options in "$@", and eventually passing that to Java.
+#
+#       Where the inherited environment variables (DEFAULT_JVM_OPTS, JAVA_OPTS,
+#       and GRADLE_OPTS) rely on word-splitting, this is performed explicitly;
+#       see the in-line comments for details.
+#
+#       There are tweaks for specific operating systems such as AIX, CygWin,
+#       Darwin, MinGW, and NonStop.
+#
+#   (3) This script is generated from the Groovy template
+#       https://github.com/gradle/gradle/blob/HEAD/subprojects/plugins/src/main/resources/org/gradle/api/internal/plugins/unixStartScript.txt
+#       within the Gradle project.
+#
+#       You can find Gradle at https://github.com/gradle/gradle/.
+#
 ##############################################################################
 
 # Attempt to set APP_HOME
-# Resolve links: $0 may be a link
-PRG="$0"
-# Need this for relative symlinks.
-while [ -h "$PRG" ] ; do
-    ls=`ls -ld "$PRG"`
-    link=`expr "$ls" : '.*-> \(.*\)$'`
-    if expr "$link" : '/.*' > /dev/null; then
-        PRG="$link"
-    else
-        PRG=`dirname "$PRG"`"/$link"
-    fi
-done
-SAVED="`pwd`"
-cd "`dirname \"$PRG\"`/" >/dev/null
-APP_HOME="`pwd -P`"
-cd "$SAVED" >/dev/null
 
-APP_NAME="Gradle"
+# Resolve links: $0 may be a link
-APP_BASE_NAME=`basename "$0"`
+app_path=$0
+
+# Need this for daisy-chained symlinks.
+while
+    APP_HOME=${app_path%"${app_path##*/}"}  # leaves a trailing /; empty if no leading path
+    [ -h "$app_path" ]
+do
+    ls=$( ls -ld "$app_path" )
+    link=${ls#*' -> '}
+    case $link in             #(
+      /*)   app_path=$link ;; #(
+      *)    app_path=$APP_HOME$link ;;
+    esac
+done
+
+# This is normally unused
+# shellcheck disable=SC2034
+APP_BASE_NAME=${0##*/}
+APP_HOME=$( cd "${APP_HOME:-./}" && pwd -P ) || exit
 
 # Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
 DEFAULT_JVM_OPTS='"-Xmx64m" "-Xms64m"'
 
 # Use the maximum available, or set MAX_FD != -1 to use that value.
-MAX_FD="maximum"
+MAX_FD=maximum
 
 warn () {
     echo "$*"
-}
+} >&2
 
 die () {
     echo
     echo "$*"
     echo
     exit 1
-}
+} >&2
 
 # OS specific support (must be 'true' or 'false').
 cygwin=false
 msys=false
 darwin=false
 nonstop=false
-case "`uname`" in
+case "$( uname )" in                #(
-  CYGWIN* )
+  CYGWIN* )         cygwin=true  ;; #(
-    cygwin=true
+  Darwin* )         darwin=true  ;; #(
-    ;;
+  MSYS* | MINGW* )  msys=true    ;; #(
-  Darwin* )
+  NONSTOP* )        nonstop=true ;;
-    darwin=true
-    ;;
-  MINGW* )
-    msys=true
-    ;;
-  NONSTOP* )
-    nonstop=true
-    ;;
 esac
 
 CLASSPATH=$APP_HOME/gradle/wrapper/gradle-wrapper.jar
@@ -87,9 +121,9 @@ CLASSPATH=$APP_HOME/gradle/wrapper/gradle-wrapper.jar
 if [ -n "$JAVA_HOME" ] ; then
     if [ -x "$JAVA_HOME/jre/sh/java" ] ; then
         # IBM's JDK on AIX uses strange locations for the executables
-        JAVACMD="$JAVA_HOME/jre/sh/java"
+        JAVACMD=$JAVA_HOME/jre/sh/java
     else
-        JAVACMD="$JAVA_HOME/bin/java"
+        JAVACMD=$JAVA_HOME/bin/java
     fi
     if [ ! -x "$JAVACMD" ] ; then
         die "ERROR: JAVA_HOME is set to an invalid directory: $JAVA_HOME
@@ -98,7 +132,7 @@ Please set the JAVA_HOME variable in your environment to match the
 location of your Java installation."
     fi
 else
-    JAVACMD="java"
+    JAVACMD=java
     which java >/dev/null 2>&1 || die "ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
 
 Please set the JAVA_HOME variable in your environment to match the
@@ -106,80 +140,105 @@ location of your Java installation."
 fi
 
 # Increase the maximum file descriptors if we can.
-if [ "$cygwin" = "false" -a "$darwin" = "false" -a "$nonstop" = "false" ] ; then
+if ! "$cygwin" && ! "$darwin" && ! "$nonstop" ; then
-    MAX_FD_LIMIT=`ulimit -H -n`
+    case $MAX_FD in #(
-    if [ $? -eq 0 ] ; then
+      max*)
-        if [ "$MAX_FD" = "maximum" -o "$MAX_FD" = "max" ] ; then
+        # In POSIX sh, ulimit -H is undefined. That's why the result is checked to see if it worked.
-            MAX_FD="$MAX_FD_LIMIT"
+        # shellcheck disable=SC3045
-        fi
+        MAX_FD=$( ulimit -H -n ) ||
-        ulimit -n $MAX_FD
+            warn "Could not query maximum file descriptor limit"
-        if [ $? -ne 0 ] ; then
+    esac
-            warn "Could not set maximum file descriptor limit: $MAX_FD"
+    case $MAX_FD in  #(
-        fi
+      '' | soft) :;; #(
-    else
+      *)
-        warn "Could not query maximum file descriptor limit: $MAX_FD_LIMIT"
+        # In POSIX sh, ulimit -n is undefined. That's why the result is checked to see if it worked.
-    fi
+        # shellcheck disable=SC3045
-fi
+        ulimit -n "$MAX_FD" ||
-
+            warn "Could not set maximum file descriptor limit to $MAX_FD"
-# For Darwin, add options to specify how the application appears in the dock
-if $darwin; then
-    GRADLE_OPTS="$GRADLE_OPTS \"-Xdock:name=$APP_NAME\" \"-Xdock:icon=$APP_HOME/media/gradle.icns\""
-fi
-
-# For Cygwin or MSYS, switch paths to Windows format before running java
-if [ "$cygwin" = "true" -o "$msys" = "true" ] ; then
-    APP_HOME=`cygpath --path --mixed "$APP_HOME"`
-    CLASSPATH=`cygpath --path --mixed "$CLASSPATH"`
-
-    JAVACMD=`cygpath --unix "$JAVACMD"`
-
-    # We build the pattern for arguments to be converted via cygpath
-    ROOTDIRSRAW=`find -L / -maxdepth 1 -mindepth 1 -type d 2>/dev/null`
-    SEP=""
-    for dir in $ROOTDIRSRAW ; do
-        ROOTDIRS="$ROOTDIRS$SEP$dir"
-        SEP="|"
-    done
-    OURCYGPATTERN="(^($ROOTDIRS))"
-    # Add a user-defined pattern to the cygpath arguments
-    if [ "$GRADLE_CYGPATTERN" != "" ] ; then
-        OURCYGPATTERN="$OURCYGPATTERN|($GRADLE_CYGPATTERN)"
-    fi
-    # Now convert the arguments - kludge to limit ourselves to /bin/sh
-    i=0
-    for arg in "$@" ; do
-        CHECK=`echo "$arg"|egrep -c "$OURCYGPATTERN" -`
-        CHECK2=`echo "$arg"|egrep -c "^-"`                                 ### Determine if an option
-
-        if [ $CHECK -ne 0 ] && [ $CHECK2 -eq 0 ] ; then                    ### Added a condition
-            eval `echo args$i`=`cygpath --path --ignore --mixed "$arg"`
-        else
-            eval `echo args$i`="\"$arg\""
-        fi
-        i=`expr $i + 1`
-    done
-    case $i in
-        0) set -- ;;
-        1) set -- "$args0" ;;
-        2) set -- "$args0" "$args1" ;;
-        3) set -- "$args0" "$args1" "$args2" ;;
-        4) set -- "$args0" "$args1" "$args2" "$args3" ;;
-        5) set -- "$args0" "$args1" "$args2" "$args3" "$args4" ;;
-        6) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" ;;
-        7) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" ;;
-        8) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" ;;
-        9) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" "$args8" ;;
     esac
 fi
 
-# Escape application args
+# Collect all arguments for the java command, stacking in reverse order:
-save () {
+#   * args from the command line
-    for i do printf %s\\n "$i" | sed "s/'/'\\\\''/g;1s/^/'/;\$s/\$/' \\\\/" ; done
+#   * the main class name
-    echo " "
+#   * -classpath
-}
+#   * -D...appname settings
-APP_ARGS=`save "$@"`
+#   * --module-path (only if needed)
+#   * DEFAULT_JVM_OPTS, JAVA_OPTS, and GRADLE_OPTS environment variables.
 
-# Collect all arguments for the java command, following the shell quoting and substitution rules
+# For Cygwin or MSYS, switch paths to Windows format before running java
-eval set -- $DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS "\"-Dorg.gradle.appname=$APP_BASE_NAME\"" -classpath "\"$CLASSPATH\"" org.gradle.wrapper.GradleWrapperMain "$APP_ARGS"
+if "$cygwin" || "$msys" ; then
+    APP_HOME=$( cygpath --path --mixed "$APP_HOME" )
+    CLASSPATH=$( cygpath --path --mixed "$CLASSPATH" )
+
+    JAVACMD=$( cygpath --unix "$JAVACMD" )
+
+    # Now convert the arguments - kludge to limit ourselves to /bin/sh
+    for arg do
+        if
+            case $arg in                                #(
+              -*)   false ;;                            # don't mess with options #(
+              /?*)  t=${arg#/} t=/${t%%/*}              # looks like a POSIX filepath
+                    [ -e "$t" ] ;;                      #(
+              *)    false ;;
+            esac
+        then
+            arg=$( cygpath --path --ignore --mixed "$arg" )
+        fi
+        # Roll the args list around exactly as many times as the number of
+        # args, so each arg winds up back in the position where it started, but
+        # possibly modified.
+        #
+        # NB: a `for` loop captures its iteration list before it begins, so
+        # changing the positional parameters here affects neither the number of
+        # iterations, nor the values presented in `arg`.
+        shift                   # remove old arg
+        set -- "$@" "$arg"      # push replacement arg
+    done
+fi
+
+# Collect all arguments for the java command;
+#   * $DEFAULT_JVM_OPTS, $JAVA_OPTS, and $GRADLE_OPTS can contain fragments of
+#     shell script including quotes and variable substitutions, so put them in
+#     double quotes to make sure that they get re-expanded; and
+#   * put everything else in single quotes, so that it's not re-expanded.
+
+set -- \
+        "-Dorg.gradle.appname=$APP_BASE_NAME" \
+        -classpath "$CLASSPATH" \
+        org.gradle.wrapper.GradleWrapperMain \
+        "$@"
+
+# Stop when "xargs" is not available.
+if ! command -v xargs >/dev/null 2>&1
+then
+    die "xargs is not available"
+fi
+
+# Use "xargs" to parse quoted args.
+#
+# With -n1 it outputs one arg per line, with the quotes and backslashes removed.
+#
+# In Bash we could simply go:
+#
+#   readarray ARGS < <( xargs -n1 <<<"$var" ) &&
+#   set -- "${ARGS[@]}" "$@"
+#
+# but POSIX shell has neither arrays nor command substitution, so instead we
+# post-process each arg (as a line of input to sed) to backslash-escape any
+# character that might be a shell metacharacter, then use eval to reverse
+# that process (while maintaining the separation between arguments), and wrap
+# the whole thing up as a single "set" statement.
+#
+# This will of course break if any of these variables contains a newline or
+# an unmatched quote.
+#
+
+eval "set -- $(
+        printf '%s\n' "$DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS" |
+        xargs -n1 |
+        sed ' s~[^-[:alnum:]+,./:=@_]~\\&~g; ' |
+        tr '\n' ' '
+    )" '"$@"'
 
 exec "$JAVACMD" "$@"

gradlew.bat

@@ -14,7 +14,7 @@
 @rem limitations under the License.
 @rem
 
-@if "%DEBUG%" == "" @echo off
+@if "%DEBUG%"=="" @echo off
 @rem ##########################################################################
 @rem
 @rem  Gradle startup script for Windows
@@ -25,7 +25,8 @@
 if "%OS%"=="Windows_NT" setlocal
 
 set DIRNAME=%~dp0
-if "%DIRNAME%" == "" set DIRNAME=.
+if "%DIRNAME%"=="" set DIRNAME=.
+@rem This is normally unused
 set APP_BASE_NAME=%~n0
 set APP_HOME=%DIRNAME%
 
@@ -40,7 +41,7 @@ if defined JAVA_HOME goto findJavaFromJavaHome
 
 set JAVA_EXE=java.exe
 %JAVA_EXE% -version >NUL 2>&1
-if "%ERRORLEVEL%" == "0" goto execute
+if %ERRORLEVEL% equ 0 goto execute
 
 echo.
 echo ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
@@ -75,13 +76,15 @@ set CLASSPATH=%APP_HOME%\gradle\wrapper\gradle-wrapper.jar
 
 :end
 @rem End local scope for the variables with windows NT shell
-if "%ERRORLEVEL%"=="0" goto mainEnd
+if %ERRORLEVEL% equ 0 goto mainEnd
 
 :fail
 rem Set variable GRADLE_EXIT_CONSOLE if you need the _script_ return code instead of
 rem the _cmd.exe /c_ return code!
-if  not "" == "%GRADLE_EXIT_CONSOLE%" exit 1
+set EXIT_CODE=%ERRORLEVEL%
-exit /b 1
+if %EXIT_CODE% equ 0 set EXIT_CODE=1
+if not ""=="%GRADLE_EXIT_CONSOLE%" exit %EXIT_CODE%
+exit /b %EXIT_CODE%
 
 :mainEnd
 if "%OS%"=="Windows_NT" endlocal

src/test/scala/com/barrelsofdata/sparkexamples/DriverTest.scala

@@ -22,20 +22,19 @@ class DriverTest extends AnyFunSuite with BeforeAndAfterAll {
     PropertyConfigurator.configure(properties)
   }
 
-  override def beforeAll: Unit = {
+  override def beforeAll(): Unit = {
     setupLogger()
     LOG.info("Setting up spark session")
     spark = SparkSession.builder().appName(JOB_NAME).master("local[*]").getOrCreate()
   }
+  
+  override def afterAll(): Unit = {
+    LOG.info("Closing spark session")
+    spark.close()
+  }
 
   test("Check if spark session is working") {
     LOG.info("Testing spark job")
     assertResult("hello")(spark.sql("SELECT 'hello'").collect().head.get(0))
   }
-
-  override def afterAll: Unit = {
-    LOG.info("Closing spark session")
-    spark.close()
-  }
-
 }