initial commit

.dockerignore

+.gradle
+.idea
+
+build
+out
+
+*.iml

.gitignore

+.idea
+!.idea/copyright
+
+build
+
+.gradle
\ No newline at end of file

.gitlab-ci.yml

+stages:
+  - test
+  - publish
+
+test:
+  stage: test
+  image: openjdk:8
+  script:
+    - ./gradlew clean test
+
+
+.build-image:
+  stage: publish
+  image: docker:stable
+  services:
+    - docker:dind
+  script:
+    - docker login -u "$REGISTRY_USER" -p "$REGISTRY_PASSWORD" "$REGISTRY"
+    - docker build --pull -t "$IMAGE_TAG" -f "$DOCKERFILE" .
+    - docker push "$IMAGE_TAG"
+    - docker logout
+
+build-tagged-image:
+  extends: .build-image
+  variables:
+    IMAGE_TAG: "$CI_REGISTRY_IMAGE:$CI_COMMIT_TAG"
+    REGISTRY_PASSWORD: "$CI_REGISTRY_PASSWORD"
+    REGISTRY_USER: "$CI_REGISTRY_USER"
+    REGISTRY: "$CI_REGISTRY"
+    DOCKERFILE: "Dockerfile"
+  only:
+    - tags
+
+build-latest-image:
+  extends: .build-image
+  variables:
+    IMAGE_TAG: "$CI_REGISTRY_IMAGE:latest"
+    REGISTRY_PASSWORD: "$CI_REGISTRY_PASSWORD"
+    REGISTRY_USER: "$CI_REGISTRY_USER"
+    REGISTRY: "$CI_REGISTRY"
+    DOCKERFILE: "Dockerfile"
+  only:
+    - master
+
+build-feature-branch-image:
+  extends: .build-image
+  variables:
+    IMAGE_TAG: "$CI_REGISTRY_IMAGE:$CI_COMMIT_REF_NAME"
+    REGISTRY_PASSWORD: "$CI_REGISTRY_PASSWORD"
+    REGISTRY_USER: "$CI_REGISTRY_USER"
+    REGISTRY: "$CI_REGISTRY"
+    DOCKERFILE: "Dockerfile"
+  except:
+    - master
+    - tags

Dockerfile

+FROM openjdk:8
+ADD . /
+WORKDIR /
+RUN ./gradlew -q --no-scan --no-daemon --no-build-cache distTar
+RUN cd /build/distributions && tar xf app.tar
+
+FROM openjdk:8-jre-alpine
+COPY --from=0 /build/distributions/app /app
+CMD /app/bin/record-parser

README.md

+## Record Parser
+
+
+[Confluence Doku](https://memobase.atlassian.net/wiki/spaces/TBAS/pages/29196525/Service%2BsFTP%2BReader%2BValidator)

build.gradle

+plugins {
+    id 'application'
+    id 'distribution'
+    id 'org.jetbrains.kotlin.jvm' version '1.3.71'
+    id 'com.palantir.git-version' version '0.11.0'
+    id 'org.jlleitschuh.gradle.ktlint' version '9.2.1'
+}
+
+group 'org.memobase'
+version = gitVersion()
+mainClassName = 'org.memobase.App'
+
+jar {
+    manifest {
+        attributes 'Main-Class': 'org.memobase.App'
+    }
+}
+
+sourceCompatibility = 1.8
+targetCompatibility = 1.8
+
+repositories {
+    jcenter()
+    maven { url 'https://gitlab.com/api/v4/projects/11507450/packages/maven' }
+    maven { url 'https://jitpack.io' }
+}
+
+ext {
+    kafkaV = '2.3.1'
+    log4jV = '2.11.2'
+}
+
+dependencies {
+    // https://mvnrepository.com/artifact/org.elasticsearch.client/elasticsearch-rest-high-level-client
+    //compile group: 'org.elasticsearch.client', name: 'elasticsearch-rest-high-level-client', version: '7.1.0'
+
+    // Logging Framework
+    implementation "org.apache.logging.log4j:log4j-api:${log4jV}"
+    implementation "org.apache.logging.log4j:log4j-core:${log4jV}"
+    implementation "org.apache.logging.log4j:log4j-slf4j-impl:${log4jV}"
+
+    // Kafka Imports
+    implementation group: 'org.apache.kafka', name: 'kafka-clients', version: kafkaV
+    implementation "org.apache.kafka:kafka-streams:${kafkaV}"
+
+    // https://mvnrepository.com/artifact/org.apache.kafka/kafka-streams-test-utils
+    //testCompile group: 'org.apache.kafka', name: 'kafka-streams-test-utils', version: kafkaV
+
+    // SFTP Client
+    implementation 'com.hierynomus:sshj:0.27.0'
+    // YAML Parser
+    implementation 'org.snakeyaml:snakeyaml-engine:2.1'
+    // CSV Reader
+    implementation("com.github.doyaaaaaken:kotlin-csv-jvm:0.7.3")
+    // JSON Parser
+    implementation 'com.beust:klaxon:5.2'
+    // Compression
+    //implementation "org.apache.commons:commons-compress:1.19"
+
+    compile 'org.jetbrains.kotlin:kotlin-stdlib-jdk8'
+    compile "org.jetbrains.kotlin:kotlin-script-runtime:1.3.71"
+    compile "org.jetbrains.kotlin:kotlin-reflect:1.3.71"
+
+    testCompile("org.junit.jupiter:junit-jupiter:5.4.2")
+
+    // https://mvnrepository.com/artifact/org.apache.kafka/kafka-streams-test-utils
+    testCompile group: 'org.apache.kafka', name: 'kafka-streams-test-utils', version: kafkaV
+    testImplementation "org.apache.kafka:kafka-clients:$kafkaV:test"
+    testImplementation "org.apache.kafka:kafka_2.11:$kafkaV"
+    testImplementation "org.apache.kafka:kafka_2.11:$kafkaV:test"
+}
+
+compileKotlin {
+    kotlinOptions.jvmTarget = "1.8"
+}
+compileTestKotlin {
+    kotlinOptions.jvmTarget = "1.8"
+}
+
+
+test {
+    useJUnitPlatform()
+    testLogging {
+        events "passed", "skipped", "failed"
+    }
+}
+
+sourceSets {
+    main.kotlin.srcDirs += 'src/main/kotlin'
+    main.resources.srcDirs = [ "src/main/resources" ]
+    main.resources.includes = [ "**/*.yml", "**/*.xml"]
+    test.kotlin.srcDirs += 'src/test'
+}
+
+plugins.withType(DistributionPlugin) {
+    distTar {
+        archiveFileName = 'app.tar'
+    }
+}
\ No newline at end of file

gradle.properties

+kotlin.code.style=official
\ No newline at end of file

gradle/wrapper/gradle-wrapper.properties

+#Tue Apr 07 16:43:20 CEST 2020
+distributionUrl=https\://services.gradle.org/distributions/gradle-6.3-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 "$0"`
+
+# Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
+DEFAULT_JVM_OPTS='"-Xmx64m"'
+
+# Use the maximum available, or set MAX_FD != -1 to use that value.
+MAX_FD="maximum"
+
+warn () {
+    echo "$*"
+}
+
+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="-Xmx64m"
+
+@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 = 'record-parser'
+

src/main/kotlin/App.kt

+/*
+ * sftp-reader
+ * Copyright (C) 2020 Memoriav
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program.  If not, see <https://www.gnu.org/licenses/>.
+ */
+
+package org.memobase
+
+import org.apache.kafka.streams.KafkaStreams
+import java.io.File
+import kotlin.system.exitProcess
+import org.apache.logging.log4j.LogManager
+
+class App {
+    companion object {
+        private val log = LogManager.getLogger("RecordParser")
+        @JvmStatic fun main(args: Array<String>) {
+            try {
+                val settings = SettingsLoader()
+                val topology = KafkaTopology(settings).build()
+                val stream = KafkaStreams(topology, settings.kafkaStreamsSettings)
+
+                stream.use {
+                    it.start()
+                    while (stream.state().isRunning) {
+                        Thread.sleep(10_000L)
+                    }
+                }
+            } catch (ex: Exception) {
+                ex.printStackTrace()
+                log.error("Stopping application due to error: " + ex.message)
+                exitProcess(1)
+            }
+        }
+    }
+}

src/main/kotlin/CustomEnvConfig.kt

+/*
+ * sftp-reader
+ * Copyright (C) 2020 Memoriav
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program.  If not, see <https://www.gnu.org/licenses/>.
+ */
+
+package org.memobase
+
+import org.snakeyaml.engine.v2.env.EnvConfig
+
+class CustomEnvConfig : EnvConfig

src/main/kotlin/KafkaSettings.kt

+/*
+ * record-parser
+ * Copyright (C) 2020 Memoriav
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program.  If not, see <https://www.gnu.org/licenses/>.
+ */
+
+package org.memobase
+
+import org.apache.logging.log4j.Logger
+import java.util.*
+
+class KafkaSettings(private val map: Map<String, String>, private val log: Logger) {
+
+    val settings = Properties()
+
+    fun setKafkaProperty(propertyName: String, defaultValue: Any? = null, abortIfMissing: Boolean = false) {
+        val envProperty = propertyName.replace("\\.".toRegex(), "_").toUpperCase()
+        when {
+            System.getenv(envProperty) != null -> {
+                log.debug("Found value for property $propertyName in environment variable $envProperty.")
+                settings.setProperty(propertyName, System.getenv(envProperty))
+            }
+            map.containsKey(propertyName) -> {
+                log.debug("Found value for property $propertyName in app.yml file.")
+                settings.setProperty(propertyName, map[propertyName])
+            }
+            defaultValue != null -> {
+                log.debug("Using default value $defaultValue for $propertyName.")
+                settings[propertyName] = defaultValue
+            }
+            abortIfMissing -> {
+                log.error("Required producer property $propertyName was not set! Aborting...")
+                throw MissingSettingException("missing", "kafka.producer.$propertyName")
+            }
+            else -> log.trace("No value for property $propertyName found")
+        }
+    }
+
+}
\ No newline at end of file

src/main/kotlin/KafkaTopology.kt

+/*
+ * record-parser
+ * Copyright (C) 2020 Memoriav
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program.  If not, see <https://www.gnu.org/licenses/>.
+ */
+
+package org.memobase
+
+import com.beust.klaxon.Klaxon
+import com.github.doyaaaaaken.kotlincsv.dsl.csvReader
+import com.github.doyaaaaaken.kotlincsv.dsl.csvWriter
+import org.apache.kafka.streams.KeyValue
+import org.apache.kafka.streams.StreamsBuilder
+import org.apache.kafka.streams.Topology
+import org.apache.logging.log4j.LogManager
+import java.io.ByteArrayOutputStream
+import java.io.File
+import java.io.StringReader
+import java.nio.charset.Charset
+
+class KafkaTopology(private val settings: SettingsLoader
+) {
+    private val log = LogManager.getLogger("KafkaTopology")
+