JOOL API

build.gradle

+plugins {
+    id 'java'
+}
+
+group = 'org.example'
+version = '1.0'
+
+sourceCompatibility = 8
+targetCompatibility = 8
+
+repositories {
+    mavenCentral()
+    maven {
+        url = 'https://packages.confluent.io/maven'
+    }
+}
+
+dependencies {
+    compile group: 'org.apache.spark', name: 'spark-core_2.12', version:'3.0.0-preview2'
+    compile group: 'org.apache.spark', name: 'spark-sql_2.12', version:'3.0.0-preview2'
+
+    compile group: 'org.apache.spark', name: 'spark-avro_2.12', version:'3.0.0-preview2'
+    compile group: 'io.confluent', name: 'kafka-schema-registry-client', version:'5.5.0'
+
+    compile group: 'org.jooq', name: 'jool', version: '0.9.0'
+    compileOnly 'org.projectlombok:lombok:1.18.12'
+    annotationProcessor 'org.projectlombok:lombok:1.18.12'
+}
+
+test {
+    useJUnitPlatform()
+}
+

gradle/wrapper/gradle-wrapper.properties

+#Tue Jun 30 13:55:45 IST 2020
+distributionUrl=https\://services.gradle.org/distributions/gradle-6.4.1-all.zip
+distributionBase=GRADLE_USER_HOME
+distributionPath=wrapper/dists
+zipStorePath=wrapper/dists
+zipStoreBase=GRADLE_USER_HOME

gradlew

+#!/usr/bin/env sh
+
+##############################################################################
+##
+##  Gradle start up script for UN*X
+##
+##############################################################################
+
+# 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"
+APP_BASE_NAME=`basename "$0"`
+
+# Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
+DEFAULT_JVM_OPTS=""
+
+# Use the maximum available, or set MAX_FD != -1 to use that value.
+MAX_FD="maximum"
+
+warn () {
+    echo "$*"
+}
+
+die () {
+    echo
+    echo "$*"
+    echo
+    exit 1
+}
+
+# OS specific support (must be 'true' or 'false').
+cygwin=false
+msys=false
+darwin=false
+nonstop=false
+case "`uname`" in
+  CYGWIN* )
+    cygwin=true
+    ;;
+  Darwin* )
+    darwin=true
+    ;;
+  MINGW* )
+    msys=true
+    ;;
+  NONSTOP* )
+    nonstop=true
+    ;;
+esac
+
+CLASSPATH=$APP_HOME/gradle/wrapper/gradle-wrapper.jar
+
+# Determine the Java command to use to start the JVM.
+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="$JAVA_HOME/jre/sh/java"
+    else
+        JAVACMD="$JAVA_HOME/bin/java"
+    fi
+    if [ ! -x "$JAVACMD" ] ; then
+        die "ERROR: JAVA_HOME is set to an invalid directory: $JAVA_HOME
+
+Please set the JAVA_HOME variable in your environment to match the
+location of your Java installation."
+    fi
+else
+    JAVACMD="java"
+    which java >/dev/null 2>&1 || die "ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
+
+Please set the JAVA_HOME variable in your environment to match the
+location of your Java installation."
+fi
+
+# Increase the maximum file descriptors if we can.
+if [ "$cygwin" = "false" -a "$darwin" = "false" -a "$nonstop" = "false" ] ; then
+    MAX_FD_LIMIT=`ulimit -H -n`
+    if [ $? -eq 0 ] ; then
+        if [ "$MAX_FD" = "maximum" -o "$MAX_FD" = "max" ] ; then
+            MAX_FD="$MAX_FD_LIMIT"
+        fi
+        ulimit -n $MAX_FD
+        if [ $? -ne 0 ] ; then
+            warn "Could not set maximum file descriptor limit: $MAX_FD"
+        fi
+    else
+        warn "Could not query maximum file descriptor limit: $MAX_FD_LIMIT"
+    fi
+fi
+
+# 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, switch paths to Windows format before running java
+if $cygwin ; then
+    APP_HOME=`cygpath --path --mixed "$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`="\"$arg\""
+        fi
+        i=$((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
+save () {
+    for i do printf %s\\n "$i" | sed "s/'/'\\\\''/g;1s/^/'/;\$s/\$/' \\\\/" ; done
+    echo " "
+}
+APP_ARGS=$(save "$@")
+
+# Collect all arguments for the java command, following the shell quoting and substitution rules
+eval set -- $DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS "\"-Dorg.gradle.appname=$APP_BASE_NAME\"" -classpath "\"$CLASSPATH\"" org.gradle.wrapper.GradleWrapperMain "$APP_ARGS"
+
+# by default we should be in the correct project dir, but when run from Finder on Mac, the cwd is wrong
+if [ "$(uname)" = "Darwin" ] && [ "$HOME" = "$PWD" ]; then
+  cd "$(dirname "$0")"
+fi
+
+exec "$JAVACMD" "$@"

gradlew.bat

+@if "%DEBUG%" == "" @echo off
+@rem ##########################################################################
+@rem
+@rem  Gradle startup script for Windows
+@rem
+@rem ##########################################################################
+
+@rem Set local scope for the variables with windows NT shell
+if "%OS%"=="Windows_NT" setlocal
+
+set DIRNAME=%~dp0
+if "%DIRNAME%" == "" set DIRNAME=.
+set APP_BASE_NAME=%~n0
+set APP_HOME=%DIRNAME%
+
+@rem Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
+set DEFAULT_JVM_OPTS=
+
+@rem Find java.exe
+if defined JAVA_HOME goto findJavaFromJavaHome
+
+set JAVA_EXE=java.exe
+%JAVA_EXE% -version >NUL 2>&1
+if "%ERRORLEVEL%" == "0" goto init
+
+echo.
+echo ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
+echo.
+echo Please set the JAVA_HOME variable in your environment to match the
+echo location of your Java installation.
+
+goto fail
+
+:findJavaFromJavaHome
+set JAVA_HOME=%JAVA_HOME:"=%
+set JAVA_EXE=%JAVA_HOME%/bin/java.exe
+
+if exist "%JAVA_EXE%" goto init
+
+echo.
+echo ERROR: JAVA_HOME is set to an invalid directory: %JAVA_HOME%
+echo.
+echo Please set the JAVA_HOME variable in your environment to match the
+echo location of your Java installation.
+
+goto fail
+
+:init
+@rem Get command-line arguments, handling Windows variants
+
+if not "%OS%" == "Windows_NT" goto win9xME_args
+
+:win9xME_args
+@rem Slurp the command line arguments.
+set CMD_LINE_ARGS=
+set _SKIP=2
+
+:win9xME_args_slurp
+if "x%~1" == "x" goto execute
+
+set CMD_LINE_ARGS=%*
+
+:execute
+@rem Setup the command line
+
+set CLASSPATH=%APP_HOME%\gradle\wrapper\gradle-wrapper.jar
+
+@rem Execute Gradle
+"%JAVA_EXE%" %DEFAULT_JVM_OPTS% %JAVA_OPTS% %GRADLE_OPTS% "-Dorg.gradle.appname=%APP_BASE_NAME%" -classpath "%CLASSPATH%" org.gradle.wrapper.GradleWrapperMain %CMD_LINE_ARGS%
+
+:end
+@rem End local scope for the variables with windows NT shell
+if "%ERRORLEVEL%"=="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
+exit /b 1
+
+:mainEnd
+if "%OS%"=="Windows_NT" endlocal
+
+:omega

settings.gradle

+rootProject.name = 'sparkexceptionExample'

src/main/java/com/example/SparkExceptionExample/SparkExample.java

+package com.example.SparkExceptionExample;
+
+import com.example.SparkExceptionExample.model.Promotion;
+import com.fasterxml.jackson.databind.ObjectMapper;
+import io.confluent.kafka.schemaregistry.client.rest.exceptions.RestClientException;
+import lombok.extern.slf4j.Slf4j;
+import org.apache.spark.api.java.JavaRDD;
+import org.apache.spark.sql.*;
+import org.apache.spark.sql.types.DataTypes;
+import org.apache.spark.sql.types.StructField;
+import org.apache.spark.sql.types.StructType;
+import org.jooq.lambda.Unchecked;
+
+import java.io.IOException;
+import java.nio.file.Files;
+import java.nio.file.Paths;
+import java.util.List;
+
+@Slf4j
+public class SparkExample {
+
+    static SparkSession sparkSession;
+    static StructType schema;
+    final static String jsonPath = "/Users/nisum/Desktop/EPE/sparkstructtype/src/main/resources/promotions.json";
+    static ObjectMapper mapper = new ObjectMapper();
+    public static void main(String[] args) throws AnalysisException, IOException, RestClientException {
+        sparkSession = SparkSession.builder().master("local").appName("Spark StructType").getOrCreate();
+        schema = new StructType(new StructField[]{
+                DataTypes.createStructField("promotionId", DataTypes.IntegerType, true),
+                DataTypes.createStructField("promotionType", DataTypes.StringType, true),
+                DataTypes.createStructField("discount", DataTypes.IntegerType, true),
+        });
+        String jsonString = new String(Files.readAllBytes(Paths.get("/Users/nisum/Desktop/EPE/sparkstructtype/src/main/resources/schemas/promotion.json")));
+        StructType structType = (StructType) StructType.fromJson(jsonString);
+        Dataset<Promotion> promotionDatasets = sparkSession.read().schema(structType).json(jsonPath).as(Encoders.bean(Promotion.class));
+        promotionDatasets.printSchema();
+        promotionDatasets.show();
+        Dataset<Row> dataSetRowValue = sparkSession.read().schema(schema).json(jsonPath);
+        dataSetRowValue.printSchema();
+        dataSetRowValue.show();
+        List<Row> rowList = dataSetRowValue.filter(dataSetRowValue.col("discount").$eq$eq$eq(10))
+                .collectAsList();
+        rowList.forEach(Unchecked.consumer(row -> log.info(row.json())));
+        String jsonDir = System.getProperty("/Users/nisum/Desktop/EPE/sparkstructtype/src/main/resources/promotions.json");
+        Dataset<Promotion> promotionDataset = sparkSession
+                .read()
+                .schema(schema)
+                .json(jsonDir)
+                .as(Encoders.bean(Promotion.class));
+        promotionDataset.show();
+        promotionDataset.createTempView("promotions");
+        Dataset<Row> dataset = sparkSession.sql("select * from promotions where discount>=10");
+        dataset.show();
+        dataReader(jsonPath, Promotion.class).collect()
+                .forEach(Unchecked.consumer(promotion -> log.info(promotion.toString())));
+
+    }
+    public static <T> JavaRDD<T> dataReader(String filePath, Class<T> clazz) {
+        return sparkSession.read().textFile(filePath).toJavaRDD().map(
+                value -> mapper.readValue(value, clazz));
+    }
+}

src/main/java/com/example/SparkExceptionExample/model/Promotion.java

+package com.example.SparkExceptionExample.model;
+
+import lombok.Data;
+
+import java.io.Serializable;
+
+@Data
+public class Promotion implements Serializable {
+    private int promotionId;
+    private String promotionType;
+    private Integer discount;
+}

src/main/resources/promotions.json

+{ "promotionId": 123456, "promotionType": "faishion", "discount": 10 }
+{ "promotionId": 123457, "promotionType": "big billion", "discount": 12 }
+{ "promotionId": 123458, "promotionType": "electronics", "discount": 13}
+{ "promotionId": 123459, "promotionType": "kitchen", "discount": 14 }
+{ "promotionId": 123451, "promotionType": "home", "discount": 15 }
+

src/main/resources/schemas/promotion.avsc

+{
+  "namespace" : "com.safeway.epe.model",
+  "type": "record",
+  "name": "PromotionData",
+  "fields": [
+    {"name": "promotionId","type": ["null","int"]},
+    {"name": "promotionType" , "type":  ["null","string"]},
+    {"name": "discount" , "type":["null","int"]}
+  ]
+}
\ No newline at end of file

src/main/resources/schemas/promotion.json

+{
+  "type": "struct",
+  "fields": [
+    {
+      "name": "promotionId",
+      "type": "integer",
+      "nullable": true,
+      "metadata": {}
+    },
+    {
+      "name": "promotionType",
+      "type": "string",
+      "nullable": true,
+      "metadata": {}
+    },
+    {
+      "name": "discount",
+      "type": "integer",
+      "nullable": true,
+      "metadata": {}
+    }
+  ]
+}
\ No newline at end of file