快速体验 Spark Connect

docker run -it -p 15002:15002 -p 4040:4040  --name spark --rm  registry.cn-hangzhou.aliyuncs.com/udh/jdk:1.8.141 bash

wget https://dlcdn.apache.org/spark/spark-3.5.0/spark-3.5.0-bin-hadoop3.tgz

./sbin/start-connect-server.sh --jars /root/.ivy2/jars/org.apache.spark_spark-connect_2.12-3.5.0.jar,/root/.ivy2/jars/org.spark-project.spark_unused-1.0.0.jar

Usage: ./sbin/start-connect-server.sh [options]
Options:  --master MASTER_URL         spark://host:port, mesos://host:port, yarn,                              k8s://https://host:port, or local (Default: local[*]).  --deploy-mode DEPLOY_MODE   Whether to launch the driver program locally ("client") or                              on one of the worker machines inside the cluster ("cluster")                              (Default: client).  --class CLASS_NAME          Your application's main class (for Java / Scala apps).  --name NAME                 A name of your application.  --jars JARS                 Comma-separated list of jars to include on the driver                              and executor classpaths.  --packages                  Comma-separated list of maven coordinates of jars to include                              on the driver and executor classpaths. Will search the local                              maven repo, then maven central and any additional remote                              repositories given by --repositories. The format for the                              coordinates should be groupId:artifactId:version.  --exclude-packages          Comma-separated list of groupId:artifactId, to exclude while                              resolving the dependencies provided in --packages to avoid                              dependency conflicts.  --repositories              Comma-separated list of additional remote repositories to                              search for the maven coordinates given with --packages.  --py-files PY_FILES         Comma-separated list of .zip, .egg, or .py files to place                              on the PYTHONPATH for Python apps.  --files FILES               Comma-separated list of files to be placed in the working                              directory of each executor. File paths of these files                              in executors can be accessed via SparkFiles.get(fileName).  --archives ARCHIVES         Comma-separated list of archives to be extracted into the                              working directory of each executor.
  --conf, -c PROP=VALUE       Arbitrary Spark configuration property.  --properties-file FILE      Path to a file from which to load extra properties. If not                              specified, this will look for conf/spark-defaults.conf.
  --driver-memory MEM         Memory for driver (e.g. 1000M, 2G) (Default: 1024M).  --driver-java-options       Extra Java options to pass to the driver.  --driver-library-path       Extra library path entries to pass to the driver.  --driver-class-path         Extra class path entries to pass to the driver. Note that                              jars added with --jars are automatically included in the                              classpath.
  --executor-memory MEM       Memory per executor (e.g. 1000M, 2G) (Default: 1G).
  --proxy-user NAME           User to impersonate when submitting the application.                              This argument does not work with --principal / --keytab.
  --help, -h                  Show this help message and exit.  --verbose, -v               Print additional debug output.  --version,                  Print the version of current Spark.
 Spark Connect only:   --remote CONNECT_URL       URL to connect to the server for Spark Connect, e.g.,                              sc://host:port. --master and --deploy-mode cannot be set                              together with this option. This option is experimental, and                              might change between minor releases.
 Cluster deploy mode only:  --driver-cores NUM          Number of cores used by the driver, only in cluster mode                              (Default: 1).
 Spark standalone or Mesos with cluster deploy mode only:  --supervise                 If given, restarts the driver on failure.
 Spark standalone, Mesos or K8s with cluster deploy mode only:  --kill SUBMISSION_ID        If given, kills the driver specified.  --status SUBMISSION_ID      If given, requests the status of the driver specified.
 Spark standalone, Mesos and Kubernetes only:  --total-executor-cores NUM  Total cores for all executors.
 Spark standalone, YARN and Kubernetes only:  --executor-cores NUM        Number of cores used by each executor. (Default: 1 in                              YARN and K8S modes, or all available cores on the worker                              in standalone mode).
 Spark on YARN and Kubernetes only:  --num-executors NUM         Number of executors to launch (Default: 2).                              If dynamic allocation is enabled, the initial number of                              executors will be at least NUM.  --principal PRINCIPAL       Principal to be used to login to KDC.  --keytab KEYTAB             The full path to the file that contains the keytab for the                              principal specified above.
 Spark on YARN only:  --queue QUEUE_NAME          The YARN queue to submit to (Default: "default").

<dependencies>
    <dependency>      <groupId>org.apache.spark</groupId>      <artifactId>spark-sql-api_2.12</artifactId>      <version>3.5.0</version>    </dependency>

    <!-- https://mvnrepository.com/artifact/org.apache.spark/spark-connect-client-jvm -->    <dependency>      <groupId>org.apache.spark</groupId>      <artifactId>spark-connect-client-jvm_2.12</artifactId>      <version>3.5.0</version>    </dependency>
  </dependencies>

public class App {    public static void main( String[] args )    {        SparkSession spark = SparkSession.builder().remote("sc://localhost").build();
        spark.stop();    }}

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"  xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">  <modelVersion>4.0.0</modelVersion>
  <groupId>org.example</groupId>  <artifactId>shade-spark-connect</artifactId>  <version>1.0-SNAPSHOT</version>  <packaging>jar</packaging>
  <name>shade-spark-connect</name>  <url>http://maven.apache.org</url>
  <properties>    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>    <maven.compiler.source>1.8</maven.compiler.source>    <maven.compiler.target>1.8</maven.compiler.target>    <spark.shade.packageName>org.sparkproject.connect.client</spark.shade.packageName>    <io.grpc.version>1.59.0</io.grpc.version>    <netty.version>4.1.100.Final</netty.version>
  </properties>
  <dependencies>    <dependency>      <groupId>com.google.guava</groupId>      <artifactId>guava</artifactId>      <version>32.0.1-jre</version>    </dependency>
    <dependency>      <groupId>com.google.protobuf</groupId>      <artifactId>protobuf-java</artifactId>      <version>3.25.1</version>    </dependency>  </dependencies>

  <build>    <plugins>      <plugin>        <groupId>org.apache.maven.plugins</groupId>        <artifactId>maven-shade-plugin</artifactId>        <version>3.1.1</version>        <configuration>          <shadedArtifactAttached>false</shadedArtifactAttached>          <artifactSet>            <!-- 包含 guava jar，但排除 com.google.thirdparty目录 -->            <includes>              <include>com.google.guava:*</include>            </includes>          </artifactSet>          <transformers>            <transformer implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer"/>          </transformers>        </configuration>        <executions>          <execution>            <phase>package</phase>            <goals>              <goal>shade</goal>            </goals>            <configuration>              <filters>                <filter>                  <artifact>*:*</artifact>                  <excludes>                    <exclude>com/google/thirdparty/**</exclude>                  </excludes>                </filter>              </filters>            </configuration>          </execution>        </executions>      </plugin>      <plugin>        <groupId>org.apache.maven.plugins</groupId>        <artifactId>maven-shade-plugin</artifactId>        <version>3.1.1</version>        <configuration>          <shadedArtifactAttached>false</shadedArtifactAttached>          <artifactSet>
            <includes>              <include>com.google.protobuf:**</include>              <include>com.google.guava:**</include>

            </includes>          </artifactSet>
          <!--                  依赖的 jar 包中的一些类文件打包到项目构建生成的 jar 包中，在打包的时候把类重命名-->          <relocations>            <relocation>              <pattern>com.google.common</pattern>              <shadedPattern>org.sparkproject.connect.client.com.google.common</shadedPattern>              <includes>                <include>com.google.common.*</include>              </includes>
            </relocation>            <relocation>              <pattern>com.google.protobuf</pattern>              <shadedPattern>org.sparkproject.connect.client.com.google.protobuf</shadedPattern>              <includes>                <include>com.google.protobuf.**</include>              </includes>
            </relocation>          </relocations>          <transformers>            <transformer                    implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer"/>          </transformers>        </configuration>        <executions>          <execution>            <phase>package</phase>            <goals>              <goal>shade</goal>            </goals>          </execution>        </executions>      </plugin>
    </plugins>
  </build></project>

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"  xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">  <modelVersion>4.0.0</modelVersion>
  <groupId>org.example</groupId>  <artifactId>spark-connect-demo</artifactId>  <version>1.0-SNAPSHOT</version>  <packaging>jar</packaging>
  <name>spark-connect-demo</name>  <url>http://maven.apache.org</url>
  <properties>    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>    <maven.compiler.source>1.8</maven.compiler.source>    <maven.compiler.target>1.8</maven.compiler.target>    <io.grpc.version>1.59.0</io.grpc.version>    <netty.version>4.1.100.Final</netty.version>
  </properties>
  <dependencies>    <dependency>      <groupId>io.grpc</groupId>      <artifactId>grpc-netty</artifactId>      <version>${io.grpc.version}</version>    </dependency>    <dependency>      <groupId>io.grpc</groupId>      <artifactId>grpc-protobuf</artifactId>      <version>${io.grpc.version}</version>    </dependency>    <dependency>      <groupId>io.grpc</groupId>      <artifactId>grpc-services</artifactId>      <version>${io.grpc.version}</version>    </dependency>    <dependency>      <groupId>io.grpc</groupId>      <artifactId>grpc-stub</artifactId>      <version>${io.grpc.version}</version>    </dependency>    <dependency>      <groupId>io.grpc</groupId>      <artifactId>grpc-inprocess</artifactId>      <version>${io.grpc.version}</version>    </dependency>    <dependency>      <groupId>io.netty</groupId>      <artifactId>netty-codec-http2</artifactId>      <version>${netty.version}</version>    </dependency>    <dependency>      <groupId>io.netty</groupId>      <artifactId>netty-handler-proxy</artifactId>      <version>${netty.version}</version>    </dependency>    <dependency>      <groupId>io.netty</groupId>      <artifactId>netty-transport-native-unix-common</artifactId>      <version>${netty.version}</version>    </dependency>    <dependency>      <groupId>org.apache.spark</groupId>      <artifactId>spark-connect-client-jvm_2.12</artifactId>      <version>3.5.0</version>    </dependency>
    <dependency>      <groupId>junit</groupId>      <artifactId>junit</artifactId>      <version>3.8.1</version>      <scope>test</scope>    </dependency>
    <dependency>      <groupId>org.example</groupId>      <artifactId>demo</artifactId>      <version>1.0</version>      <scope>system</scope>      <systemPath>E:\opensource\shade-spark-connect\target\shade-spark-connect-1.0-SNAPSHOT.jar</systemPath>    </dependency>  </dependencies>

  <build>   <plugins>

     <plugin>       <groupId>org.scala-tools</groupId>       <artifactId>maven-scala-plugin</artifactId>       <version>2.12.2</version> <!-- 适用于你的 Scala 版本 -->       <executions>         <execution>           <goals>             <goal>compile</goal>             <goal>testCompile</goal>           </goals>         </execution>       </executions>     </plugin>   </plugins>

  </build></project>

import org.apache.spark.sql.SparkSessionimport org.apache.spark.sql.functions._import org.apache.spark.sql.types._import org.apache.spark.sql._import org.apache.spark.sql.expressions._object Myapp extends App {
  println(spark.version)  val spark: SparkSession = SparkSession.builder.remote("sc://localhost").getOrCreate()//using list to init  df  val df = spark.createDataFrame(List(("a a a", 1), ("b b b b", 2), ("c c d a", 3))).toDF("value", "col2")  df.show()

// word count  val words = df.select(explode(split(col("value"), " ")).as("word"))  val wordCounts = words.groupBy("word").count()  wordCounts.show()

  spark.stop()
}