Use gradle version catalogs
All checks were successful
Tests / reset-status (push) Successful in 2s
Tests / tests (push) Successful in 4m6s
Tests / build (push) Successful in 4m20s

This commit is contained in:
karthik 2023-10-07 14:01:18 +02:00
parent c701d472df
commit a0cef20f21
15 changed files with 365 additions and 211 deletions

View File

@ -0,0 +1,72 @@
name: Tests
on: [push]
jobs:
reset-status:
runs-on: ubuntu-latest
steps:
- name: Reset test status
run: |
curl -v -X POST https://barrelsofdata.com/api/v1/git/action/status/publish \
-H 'X-API-KEY: ${{ secrets.STATUS_PUBLISH_API_KEY }}' \
-H 'Content-Type: application/json' \
-d '{"action":"${{ gitea.repository }}/action/tests","status":"starting"}'
- name: Reset build status
run: |
curl -v -X POST https://barrelsofdata.com/api/v1/git/action/status/publish \
-H 'X-API-KEY: ${{ secrets.STATUS_PUBLISH_API_KEY }}' \
-H 'Content-Type: application/json' \
-d '{"action":"${{ gitea.repository }}/action/build","status":"waiting for test"}'
tests:
needs: reset-status
runs-on: ubuntu-latest
steps:
- name: Set test running
run: |
curl -v -X POST https://barrelsofdata.com/api/v1/git/action/status/publish \
-H 'X-API-KEY: ${{ secrets.STATUS_PUBLISH_API_KEY }}' \
-H 'Content-Type: application/json' \
-d '{"action":"${{ gitea.repository }}/action/tests","status":"running"}'
- name: Checkout
uses: actions/checkout@v4
- name: Set up java
uses: actions/setup-java@v3
with:
java-version: '17'
distribution: 'temurin'
- name: Run tests
id: tests
run: ./gradlew test
- name: Publish test status
if: always()
run: |
curl -v -X POST https://barrelsofdata.com/api/v1/git/action/status/publish \
-H 'X-API-KEY: ${{ secrets.STATUS_PUBLISH_API_KEY }}' \
-H 'Content-Type: application/json' \
-d '{"action":"${{ gitea.repository }}/action/tests","status":"${{ steps.tests.conclusion }}"}'
build:
needs: tests
runs-on: ubuntu-latest
steps:
- name: Set build running
run: |
curl -v -X POST https://barrelsofdata.com/api/v1/git/action/status/publish \
-H 'X-API-KEY: ${{ secrets.STATUS_PUBLISH_API_KEY }}' \
-H 'Content-Type: application/json' \
-d '{"action":"${{ gitea.repository }}/action/build","status":"running"}'
- name: Checkout
uses: actions/checkout@v4
- name: Set up java
uses: actions/setup-java@v3
with:
java-version: '17'
distribution: 'temurin'
- name: Build
id: build
run: ./gradlew build -x test
- name: Publish build status
if: always()
run: |
curl -v -X POST https://barrelsofdata.com/api/v1/git/action/status/publish \
-H 'X-API-KEY: ${{ secrets.STATUS_PUBLISH_API_KEY }}' \
-H 'Content-Type: application/json' \
-d '{"action":"${{ gitea.repository }}/action/build","status":"${{ steps.build.conclusion }}"}'

2
.gitignore vendored
View File

@ -1,7 +1,7 @@
# Compiled classes # Compiled classes
*.class *.class
# Gradle files # Gradle files
.gralde .gradle
# IntelliJ IDEA files # IntelliJ IDEA files
.idea .idea
# Build files # Build files

View File

@ -1,5 +1,8 @@
[![Tests](https://barrelsofdata.com/api/v1/git/action/status/fetch/barrelsofdata/spark-state-store-data-deduplication/tests)](https://git.barrelsofdata.com/barrelsofdata/spark-state-store-data-deduplication/actions?workflow=workflow.yaml)
[![Build](https://barrelsofdata.com/api/v1/git/action/status/fetch/barrelsofdata/spark-state-store-data-deduplication/build)](https://git.barrelsofdata.com/barrelsofdata/spark-state-store-data-deduplication/actions?workflow=workflow.yaml)
# Spark Structured Streaming Data Deduplication using State Store # Spark Structured Streaming Data Deduplication using State Store
This is a project showing how the spark in-built HDFS backed state store can be used to deduplicate data in a stream. The related blog post can be found at [https://www.barrelsofdata.com/data-deduplication-spark-state-store](https://www.barrelsofdata.com/data-deduplication-spark-state-store) This is a project showing how the spark in-built HDFS backed state store can be used to deduplicate data in a stream. The related blog post can be found at [https://barrelsofdata.com/data-deduplication-spark-state-store](https://barrelsofdata.com/data-deduplication-spark-state-store)
## Build instructions ## Build instructions
From the root of the project execute the below commands From the root of the project execute the below commands
@ -13,23 +16,19 @@ From the root of the project execute the below commands
``` ```
- To build jar - To build jar
```shell script ```shell script
./gradlew shadowJar ./gradlew build
```
- All combined
```shell script
./gradlew clean test shadowJar
``` ```
## Run ## Run
Ensure your local hadoop cluster is running ([hadoop cluster tutorial](https://www.barrelsofdata.com/apache-hadoop-pseudo-distributed-mode)) and start two kafka brokers ([kafka tutorial](https://www.barrelsofdata.com/apache-kafka-setup)). Ensure your local hadoop cluster is running ([hadoop cluster tutorial](https://barrelsofdata.com/apache-hadoop-pseudo-distributed-mode)) and start two kafka brokers ([kafka tutorial](https://barrelsofdata.com/apache-kafka-setup)).
- Create kafka topic - Create kafka topic
```shell script ```shell script
kafka-topics.sh --create --bootstrap-server localhost:9092 --replication-factor 2 --partitions 2 --topic streaming-data kafka-topics.sh --create --bootstrap-server localhost:9092 --replication-factor 2 --partitions 2 --topic streaming-data
``` ```
- Start streaming job - Start streaming job
```shell script ```shell script
spark-submit --master yarn --deploy-mode cluster build/libs/spark-state-store-data-deduplication-1.0.jar <KAFKA_BROKER> <KAFKA_TOPIC> <FULL_OUTPUT_PATH> <DEDUPLICATED_OUTPUT_PATH> <WINDOW_SIZE_SECONDS> spark-submit --master yarn --deploy-mode cluster build/libs/spark-state-store-data-deduplication-1.0.0.jar <KAFKA_BROKER> <KAFKA_TOPIC> <FULL_OUTPUT_PATH> <DEDUPLICATED_OUTPUT_PATH> <WINDOW_SIZE_SECONDS>
Example: spark-submit --master yarn --deploy-mode client build/libs/spark-state-store-data-deduplication-1.0.jar localhost:9092 streaming-data fullOutput deduplicatedOutput 5 Example: spark-submit --master yarn --deploy-mode client build/libs/spark-state-store-data-deduplication-1.0.0.jar localhost:9092 streaming-data fullOutput deduplicatedOutput 5
``` ```
- You can feed simulated data to the kafka topic - You can feed simulated data to the kafka topic
- Open new terminal and run the shell script located at src/test/resources/dataProducer.sh - Open new terminal and run the shell script located at src/test/resources/dataProducer.sh

View File

@ -1,46 +0,0 @@
plugins {
id "scala"
id "com.github.johnrengelman.shadow" version "${shadowJarPluginVersion}"
}
group "${projectGroup}"
version "${projectVersion}"
repositories {
mavenCentral()
}
dependencies {
compileOnly group: "org.scala-lang", name:"scala-library", version: "${scalaMajorVersion}.${scalaMinorVersion}"
compileOnly group: "org.apache.spark", name: "spark-core_${scalaMajorVersion}", version: "${apacheSparkVersion}"
compileOnly group: "org.apache.spark", name: "spark-sql_${scalaMajorVersion}", version: "${apacheSparkVersion}"
implementation group: "org.apache.spark", name: "spark-sql-kafka-0-10_${scalaMajorVersion}", version: "${apacheSparkVersion}"
testImplementation group: "org.scalatest", name: "scalatest_${scalaMajorVersion}", version: "${scalaTestVersion}"
}
configurations {
testImplementation.extendsFrom compileOnly
}
task scalaTest(dependsOn: ['testClasses'], type: JavaExec) {
main = 'org.scalatest.tools.Runner'
args = ['-R', 'build/classes/scala/test', '-o']
classpath = sourceSets.test.runtimeClasspath
}
test.dependsOn scalaTest
shadowJar {
mergeServiceFiles()
zip64 true
manifest {
attributes "Main-Class": "${mainClass}"
}
archiveFileName.set("${getArchiveBaseName().get()}-${projectVersion}.${getArchiveExtension().get()}")
}
clean.doFirst {
delete "logs/"
}

55
build.gradle.kts Normal file
View File

@ -0,0 +1,55 @@
plugins {
scala
}
project.group = "com.barrelsofdata"
project.version = "1.0.0"
dependencies {
compileOnly(libs.scala.library)
compileOnly(libs.bundles.spark)
implementation(libs.spark.sql.kafka)
testImplementation(libs.scala.test)
}
tasks.withType<Test>().configureEach {
maxParallelForks = (Runtime.getRuntime().availableProcessors() / 2).coerceAtLeast(1)
}
configurations {
implementation {
resolutionStrategy.failOnVersionConflict()
}
testImplementation {
extendsFrom(configurations.compileOnly.get())
}
}
tasks.register<JavaExec>("scalaTest") {
dependsOn("testClasses")
mainClass = "org.scalatest.tools.Runner"
args = listOf("-R", "build/classes/scala/test", "-o")
jvmArgs = listOf("-Xms128m", "-Xmx512m", "-XX:MetaspaceSize=300m", "-ea", "--add-exports=java.base/sun.nio.ch=ALL-UNNAMED") // https://lists.apache.org/thread/p1yrwo126vjx5tht82cktgjbmm2xtpw9
classpath = sourceSets.test.get().runtimeClasspath
}
tasks.withType<Test> {
dependsOn(":scalaTest")
}
tasks.withType<Jar> {
manifest {
attributes["Main-Class"] = "com.barrelsofdata.sparkexamples.Driver"
}
duplicatesStrategy = DuplicatesStrategy.EXCLUDE
from (configurations.runtimeClasspath.get().map { if (it.isDirectory()) it else zipTree(it) })
archiveFileName.set("${archiveBaseName.get()}-${project.version}.${archiveExtension.get()}")
}
tasks.clean {
doFirst {
delete("logs/")
}
}

View File

@ -1,14 +1,7 @@
scalaMajorVersion=2.12 org.gradle.caching=true
scalaMinorVersion=10 org.gradle.configureondemand=true
apacheSparkVersion=3.0.0
scalaTestVersion=3.1.2
shadowJarPluginVersion=6.0.0
mainClass=com.barrelsofdata.sparkexamples.Driver
projectGroup=com.barrelsofdata.sparkexamples
projectVersion=1.0
org.gradle.daemon=false org.gradle.daemon=false
org.gradle.jvmargs=-Xms256m -Xmx2048m -XX:MaxMetaspaceSize=512m -XX:+UseParallelGC -XX:+HeapDumpOnOutOfMemoryError -Dfile.encoding=UTF-8
org.gradle.parallel=true
org.gradle.warning.mode=all
org.gradle.welcome=never

14
gradle/libs.versions.toml Normal file
View File

@ -0,0 +1,14 @@
[versions]
apache-spark = "3.5.0"
scala = "2.13.8"
scala-test = "3.2.17"
[libraries]
scala-library = { module = "org.scala-lang:scala-library", version.ref = "scala" }
scala-test = { module = "org.scalatest:scalatest_2.13", version.ref = "scala-test" }
spark-core = { module = "org.apache.spark:spark-core_2.13", version.ref = "apache-spark" }
spark-sql = { module = "org.apache.spark:spark-sql_2.13", version.ref = "apache-spark" }
spark-sql-kafka = { module = "org.apache.spark:spark-sql-kafka-0-10_2.13", version.ref = "apache-spark" }
[bundles]
spark = ["spark-core", "spark-sql"]

Binary file not shown.

View File

@ -1,5 +1,7 @@
distributionBase=GRADLE_USER_HOME distributionBase=GRADLE_USER_HOME
distributionPath=wrapper/dists distributionPath=wrapper/dists
distributionUrl=https\://services.gradle.org/distributions/gradle-6.5.1-bin.zip distributionUrl=https\://services.gradle.org/distributions/gradle-8.4-bin.zip
networkTimeout=10000
validateDistributionUrl=true
zipStoreBase=GRADLE_USER_HOME zipStoreBase=GRADLE_USER_HOME
zipStorePath=wrapper/dists zipStorePath=wrapper/dists

294
gradlew vendored
View File

@ -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"); # Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License. # you may not use this file except in compliance with the License.
@ -17,67 +17,99 @@
# #
############################################################################## ##############################################################################
## #
## 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 # Attempt to set APP_HOME
# Resolve links: $0 may be a link # Resolve links: $0 may be a link
PRG="$0" app_path=$0
# Need this for relative symlinks.
while [ -h "$PRG" ] ; do # Need this for daisy-chained symlinks.
ls=`ls -ld "$PRG"` while
link=`expr "$ls" : '.*-> \(.*\)$'` APP_HOME=${app_path%"${app_path##*/}"} # leaves a trailing /; empty if no leading path
if expr "$link" : '/.*' > /dev/null; then [ -h "$app_path" ]
PRG="$link" do
else ls=$( ls -ld "$app_path" )
PRG=`dirname "$PRG"`"/$link" link=${ls#*' -> '}
fi case $link in #(
/*) app_path=$link ;; #(
*) app_path=$APP_HOME$link ;;
esac
done done
SAVED="`pwd`"
cd "`dirname \"$PRG\"`/" >/dev/null
APP_HOME="`pwd -P`"
cd "$SAVED" >/dev/null
APP_NAME="Gradle" # This is normally unused
APP_BASE_NAME=`basename "$0"` # shellcheck disable=SC2034
APP_BASE_NAME=${0##*/}
# Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script. # Discard cd standard output in case $CDPATH is set (https://github.com/gradle/gradle/issues/25036)
DEFAULT_JVM_OPTS='"-Xmx64m" "-Xms64m"' APP_HOME=$( cd "${APP_HOME:-./}" > /dev/null && pwd -P ) || exit
# Use the maximum available, or set MAX_FD != -1 to use that value. # Use the maximum available, or set MAX_FD != -1 to use that value.
MAX_FD="maximum" MAX_FD=maximum
warn () { warn () {
echo "$*" echo "$*"
} } >&2
die () { die () {
echo echo
echo "$*" echo "$*"
echo echo
exit 1 exit 1
} } >&2
# OS specific support (must be 'true' or 'false'). # OS specific support (must be 'true' or 'false').
cygwin=false cygwin=false
msys=false msys=false
darwin=false darwin=false
nonstop=false nonstop=false
case "`uname`" in case "$( 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 esac
CLASSPATH=$APP_HOME/gradle/wrapper/gradle-wrapper.jar CLASSPATH=$APP_HOME/gradle/wrapper/gradle-wrapper.jar
@ -87,9 +119,9 @@ CLASSPATH=$APP_HOME/gradle/wrapper/gradle-wrapper.jar
if [ -n "$JAVA_HOME" ] ; then if [ -n "$JAVA_HOME" ] ; then
if [ -x "$JAVA_HOME/jre/sh/java" ] ; then if [ -x "$JAVA_HOME/jre/sh/java" ] ; then
# IBM's JDK on AIX uses strange locations for the executables # IBM's JDK on AIX uses strange locations for the executables
JAVACMD="$JAVA_HOME/jre/sh/java" JAVACMD=$JAVA_HOME/jre/sh/java
else else
JAVACMD="$JAVA_HOME/bin/java" JAVACMD=$JAVA_HOME/bin/java
fi fi
if [ ! -x "$JAVACMD" ] ; then if [ ! -x "$JAVACMD" ] ; then
die "ERROR: JAVA_HOME is set to an invalid directory: $JAVA_HOME die "ERROR: JAVA_HOME is set to an invalid directory: $JAVA_HOME
@ -98,88 +130,120 @@ Please set the JAVA_HOME variable in your environment to match the
location of your Java installation." location of your Java installation."
fi fi
else else
JAVACMD="java" JAVACMD=java
which java >/dev/null 2>&1 || die "ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH. if ! command -v java >/dev/null 2>&1
then
die "ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
Please set the JAVA_HOME variable in your environment to match the Please set the JAVA_HOME variable in your environment to match the
location of your Java installation." location of your Java installation."
fi
fi fi
# Increase the maximum file descriptors if we can. # Increase the maximum file descriptors if we can.
if [ "$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=SC2039,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: $MAX_FD_LIMIT" # In POSIX sh, ulimit -n is undefined. That's why the result is checked to see if it worked.
fi # shellcheck disable=SC2039,SC3045
fi ulimit -n "$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 esac
fi 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
# 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"'
# Collect all arguments for the java command:
# * DEFAULT_JVM_OPTS, JAVA_OPTS, JAVA_OPTS, and optsEnvironmentVar are not allowed to contain shell fragments,
# and any embedded shellness will be escaped.
# * For example: A user cannot expect ${Hostname} to be expanded, as it is an environment variable and will be
# treated as '${Hostname}' itself on the command line.
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 "$JAVACMD" "$@" exec "$JAVACMD" "$@"

34
gradlew.bat vendored
View File

@ -14,7 +14,7 @@
@rem limitations under the License. @rem limitations under the License.
@rem @rem
@if "%DEBUG%" == "" @echo off @if "%DEBUG%"=="" @echo off
@rem ########################################################################## @rem ##########################################################################
@rem @rem
@rem Gradle startup script for Windows @rem Gradle startup script for Windows
@ -25,7 +25,8 @@
if "%OS%"=="Windows_NT" setlocal if "%OS%"=="Windows_NT" setlocal
set DIRNAME=%~dp0 set DIRNAME=%~dp0
if "%DIRNAME%" == "" set DIRNAME=. if "%DIRNAME%"=="" set DIRNAME=.
@rem This is normally unused
set APP_BASE_NAME=%~n0 set APP_BASE_NAME=%~n0
set APP_HOME=%DIRNAME% set APP_HOME=%DIRNAME%
@ -40,7 +41,7 @@ if defined JAVA_HOME goto findJavaFromJavaHome
set JAVA_EXE=java.exe set JAVA_EXE=java.exe
%JAVA_EXE% -version >NUL 2>&1 %JAVA_EXE% -version >NUL 2>&1
if "%ERRORLEVEL%" == "0" goto init if %ERRORLEVEL% equ 0 goto execute
echo. echo.
echo ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH. echo ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
@ -54,7 +55,7 @@ goto fail
set JAVA_HOME=%JAVA_HOME:"=% set JAVA_HOME=%JAVA_HOME:"=%
set JAVA_EXE=%JAVA_HOME%/bin/java.exe set JAVA_EXE=%JAVA_HOME%/bin/java.exe
if exist "%JAVA_EXE%" goto init if exist "%JAVA_EXE%" goto execute
echo. echo.
echo ERROR: JAVA_HOME is set to an invalid directory: %JAVA_HOME% echo ERROR: JAVA_HOME is set to an invalid directory: %JAVA_HOME%
@ -64,21 +65,6 @@ echo location of your Java installation.
goto fail 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 :execute
@rem Setup the command line @rem Setup the command line
@ -86,17 +72,19 @@ set CLASSPATH=%APP_HOME%\gradle\wrapper\gradle-wrapper.jar
@rem Execute Gradle @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% "%JAVA_EXE%" %DEFAULT_JVM_OPTS% %JAVA_OPTS% %GRADLE_OPTS% "-Dorg.gradle.appname=%APP_BASE_NAME%" -classpath "%CLASSPATH%" org.gradle.wrapper.GradleWrapperMain %*
:end :end
@rem End local scope for the variables with windows NT shell @rem End local scope for the variables with windows NT shell
if "%ERRORLEVEL%"=="0" goto mainEnd if %ERRORLEVEL% equ 0 goto mainEnd
:fail :fail
rem Set variable GRADLE_EXIT_CONSOLE if you need the _script_ return code instead of rem Set variable GRADLE_EXIT_CONSOLE if you need the _script_ return code instead of
rem the _cmd.exe /c_ return code! 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 :mainEnd
if "%OS%"=="Windows_NT" endlocal if "%OS%"=="Windows_NT" endlocal

View File

@ -1 +0,0 @@
rootProject.name = 'spark-state-store-data-deduplication'

14
settings.gradle.kts Normal file
View File

@ -0,0 +1,14 @@
pluginManagement {
repositories {
mavenCentral()
gradlePluginPortal()
}
}
dependencyResolutionManagement {
repositories {
mavenCentral()
}
}
rootProject.name = "spark-state-store-data-deduplication"

View File

@ -58,7 +58,7 @@ object Driver {
def main(args: Array[String]): Unit = { def main(args: Array[String]): Unit = {
if(args.length != 5) { if(args.length != 5) {
println("Invalid usage") println("Invalid usage")
println("Usage: spark-submit --master <local|yarn> spark-structured-streaming-deduplication-1.0.jar <kafka_broker> <kafka_topic> <full_output_path> <deduplicated_output_path> <window_seconds>") println("Usage: spark-submit --master <local|yarn> spark-structured-streaming-deduplication-1.0.0.jar <kafka_broker> <kafka_topic> <full_output_path> <deduplicated_output_path> <window_seconds>")
LOG.error(s"Invalid number of arguments, arguments given: [${args.mkString(",")}]") LOG.error(s"Invalid number of arguments, arguments given: [${args.mkString(",")}]")
System.exit(1) System.exit(1)
} }

View File

@ -26,7 +26,7 @@ object StateOperations {
userData userData
} }
state.update(currentState.get) state.update(currentState.get)
results.toIterator results.iterator
} }
} }