springboot集成spark并使用spark-sql的示例详解

首先添加相关依赖：

<?xml version="1.0" encoding="UTF-8"?>
<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>
  <parent>
    <groupId>org.springframework.boot</groupId>
    <artifactId>spring-boot-starter-parent</artifactId>
    <version>1.5.6.RELEASE</version>
    <relativePath />
  </parent>
  <groupId>com.cord</groupId>
  <artifactId>spark-example</artifactId>
  <version>1.0-SNAPSHOT</version>
  <name>spark-example</name>
  <!-- FIXME change it to the project's website -->
  <url>http://www.example.com</url>
  <properties>
    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    <project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding>
    <java.version>1.8</java.version>
    <scala.version>2.10.3</scala.version>
    <maven.compiler.source>1.8</maven.compiler.source>
    <maven.compiler.target>1.8</maven.compiler.target>
  </properties>
  <dependencies>
    <dependency>
      <groupId>org.springframework.boot</groupId>
      <artifactId>spring-boot-starter</artifactId>
      <version>1.5.6.RELEASE</version>
        <exclusions>
            <exclusion>
                <groupId>org.springframework.boot</groupId>
                <artifactId>spring-boot-starter-logging</artifactId>
            </exclusion>
        </exclusions>
    </dependency>
    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-core_2.10</artifactId>
      <version>1.6.1</version>
      <scope>provided</scope>
        <exclusions>
            <exclusion>
                <groupId>org.slf4j</groupId>
                <artifactId>slf4j-log4j12</artifactId>
            </exclusion>
            <exclusion>
                <groupId>log4j</groupId>
                <artifactId>log4j</artifactId>
            </exclusion>
        </exclusions>
    </dependency>
    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-sql_2.10</artifactId>
      <version>1.6.1</version>
      <scope>provided</scope>
    </dependency>
    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-hive_2.10</artifactId>
      <version>1.6.1</version>
      <scope>provided</scope>
    </dependency>
    <dependency>
      <groupId>org.scala-lang</groupId>
      <artifactId>scala-library</artifactId>
      <version>${scala.version}</version>
      <scope>provided</scope>
    </dependency>
    <!-- yarn-cluster模式 -->
    <dependency>
      <groupId>mysql</groupId>
      <artifactId>mysql-connector-java</artifactId>
      <version>5.1.22</version>
    </dependency>
  </dependencies>
    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId>
                <dependencies>
                    <dependency>
                        <groupId>org.springframework.boot</groupId>
                        <artifactId>spring-boot-maven-plugin</artifactId>
                        <version>1.5.6.RELEASE</version>
                    </dependency>
                </dependencies>
                <configuration>
                    <keepDependenciesWithProvidedScope>false</keepDependenciesWithProvidedScope>
                    <createDependencyReducedPom>false</createDependencyReducedPom>
                    <filters>
                        <filter>
                            <artifact>*:*</artifact>
                            <excludes>
                                <exclude>META-INF/*.SF</exclude>
                                <exclude>META-INF/*.DSA</exclude>
                                <exclude>META-INF/*.RSA</exclude>
                            </excludes>
                        </filter>
                    </filters>
                    <transformers>
                        <transformer
                                implementation="org.apache.maven.plugins.shade.resource.AppendingTransformer">
                            <resource>META-INF/spring.handlers</resource>
                        </transformer>
                        <transformer
                                implementation="org.springframework.boot.maven.PropertiesMergingResourceTransformer">
                            <resource>META-INF/spring.factories</resource>
                        </transformer>
                        <transformer
                                implementation="org.apache.maven.plugins.shade.resource.AppendingTransformer">
                            <resource>META-INF/spring.schemas</resource>
                        </transformer>
                        <transformer
                                implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer" />
                        <transformer
                                implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
                            <mainClass>com.cord.StartApplication</mainClass>
                        </transformer>
                    </transformers>
                </configuration>
                <executions>
                    <execution>
                        <phase>package</phase>
                        <goals>
                            <goal>shade</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>
</project>

需要注意的是依赖中排除掉的日志模块，以及特殊的打包方式

定义配置类:

SparkContextBean.class

@Configuration
public class SparkContextBean {
    private String appName = "sparkExp";
    private String master = "local";
    @Bean
    @ConditionalOnMissingBean(SparkConf.class)
    public SparkConf sparkConf() throws Exception {
        SparkConf conf = new SparkConf().setAppName(appName).setMaster(master);
        return conf;
    }
    @Bean
    @ConditionalOnMissingBean
    public JavaSparkContext javaSparkContext() throws Exception {
        return new JavaSparkContext(sparkConf());
    }
    @Bean
    @ConditionalOnMissingBean
    public HiveContext hiveContext() throws Exception {
        return new HiveContext(javaSparkContext());
    }
    ......
}

启动类：

StartApplication.class

@SpringBootApplication
public class StartApplication implements CommandLineRunner {
    @Autowired
    private HiveContext hc;
    public static void main(String[] args) {
        SpringApplication.run(StartApplication.class, args);
    }
    @Override
    public void run(String... args) throws Exception {
        DataFrame df = hc.sql("select count(1) from LCS_DB.STAFF_INFO");
        List<Long> result = df.javaRDD().map((Function<Row, Long>) row -> {
            return row.getLong(0);
        }).collect();
        result.stream().forEach(System.out::println);
}

执行方式：

spark-submit \
    --class com.cord.StartApplication  \
    --executor-memory 4G \
    --num-executors 8 \
    --master yarn-client \
/data/cord/spark-example-1.0-SNAPSHOT.jar

参考链接：

https://stackoverflow.com/questions/45189701/submitting-spring-boot-application-jar-to-spark-submit

https://my.oschina.net/woter/blog/1843755

到此这篇关于spring-boot集成spark并使用spark-sql的文章就介绍到这了,更多相关spring-boot集成spark内容请搜索我们以前的文章或继续浏览下面的相关文章希望大家以后多多支持我们！