spark之spark本地运行

maven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>

    <groupId>com.zwy</groupId>
    <artifactId>recommend</artifactId>
    <version>1.0</version>
    <properties>
        <spark.version>2.3.2</spark.version>
        <scala.version>2.11.8</scala.version>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    </properties>
    <dependencies>
        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-client</artifactId>
            <version>1.3.1</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-server</artifactId>
            <version>1.3.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-common</artifactId>
            <version>1.3.1</version>
        </dependency>
        <dependency>
            <groupId>commons-logging</groupId>
            <artifactId>commons-logging</artifactId>
            <version>1.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.5.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.5.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.5.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hive</groupId>
            <artifactId>hive-exec</artifactId>
            <version>0.13.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hive</groupId>
            <artifactId>hive-jdbc</artifactId>
            <version>1.1.0</version>
        </dependency>

        <dependency>
            <groupId>mysql</groupId>
            <artifactId>mysql-connector-java</artifactId>
            <version>5.1.31</version>
        </dependency>
        <dependency>
            <groupId>commons-dbcp</groupId>
            <artifactId>commons-dbcp</artifactId>
            <version>1.4</version>
        </dependency>
        <dependency>
            <groupId>com.alibaba</groupId>
            <artifactId>fastjson</artifactId>
            <version>1.1.33</version>
        </dependency>
        <dependency>
            <groupId>redis.clients</groupId>
            <artifactId>jedis</artifactId>
            <version>2.7.0</version>
        </dependency>

        <!-- https://mvnrepository.com/artifact/org.projectlombok/lombok -->
        <dependency>
            <groupId>org.projectlombok</groupId>
            <artifactId>lombok</artifactId>
            <version>1.18.2</version>
            <scope>provided</scope>
        </dependency>

        <dependency>
            <groupId>org.apache.storm</groupId>
            <artifactId>storm-core</artifactId>
            <version>1.2.1</version>
            <!--<scope>provided</scope>-->
        </dependency>

        <!--spark 依赖-->
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-mllib_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming-kafka-0-8_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>

        <dependency>
            <groupId>io.netty</groupId>
            <artifactId>netty-all</artifactId>
            <version>4.1.17.Final</version>
        </dependency>
        <!--./spark依赖-->

        <!--scala环境-->
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
        </dependency>

        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-compiler</artifactId>
            <version>${scala.version}</version>
        </dependency>

        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-reflect</artifactId>
            <version>${scala.version}</version>
        </dependency>

        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-actors</artifactId>
            <version>${scala.version}</version>
        </dependency>

        <dependency>
            <groupId>org.scala-tools</groupId>
            <artifactId>maven-scala-plugin</artifactId>
            <version>2.15.2</version>
        </dependency>

        <!--./scala环境-->
        <dependency>
            <groupId>net.sf.jopt-simple</groupId>
            <artifactId>jopt-simple</artifactId>
            <version>4.3</version>
        </dependency>

        <dependency>
            <groupId>joda-time</groupId>
            <artifactId>joda-time</artifactId>
            <version>2.0</version>
        </dependency>

        <dependency>
            <groupId>org.apache.storm</groupId>
            <artifactId>storm-core</artifactId>
            <version>1.2.1</version>
            <!--<scope>provided</scope>-->
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.kafka/kafka -->
        <dependency>
            <groupId>org.apache.kafka</groupId>
            <artifactId>kafka_2.12</artifactId>
            <version>1.1.1</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.storm/storm-kafka -->
        <dependency>
            <groupId>org.apache.storm</groupId>
            <artifactId>storm-kafka</artifactId>
            <version>1.1.1</version>
            <!--<scope>provided</scope>-->
        </dependency>

    </dependencies>

    <repositories>
        <repository>
            <id>public</id>
            <name>aliyun nexus</name>
            <url>http://maven.aliyun.com/nexus/content/groups/public/</url>
            <releases>
                <enabled>true</enabled>
            </releases>
        </repository>
    </repositories>
    <build>
        <plugins>

            <plugin>
                <!-- 这是个编译scala代码的 -->
                <groupId>net.alchim31.maven</groupId>
                <artifactId>scala-maven-plugin</artifactId>
                <version>3.2.1</version>
                <executions>
                    <execution>
                        <id>scala-compile-first</id>
                        <phase>process-resources</phase>
                        <goals>
                            <goal>add-source</goal>
                            <goal>compile</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>

            <!-- 这是编译java全部包的 -->
            <plugin>
                <artifactId>maven-assembly-plugin</artifactId>
                <executions>
                    <execution>
                        <phase>package</phase>
                        <goals>
                            <goal>single</goal>
                        </goals>
                    </execution>
                </executions>
                <configuration>
                    <descriptorRefs>
                        <descriptorRef>jar-with-dependencies</descriptorRef>
                    </descriptorRefs>
                </configuration>
            </plugin>

            <!--编译java部分包-->
            <!--<plugin>-->
            <!--<groupId>org.apache.maven.plugins</groupId>-->
            <!--<artifactId>maven-compiler-plugin</artifactId>-->
            <!--<configuration>-->
            <!--<source>8</source>-->
            <!--<target>8</target>-->
            <!--</configuration>-->
            <!--</plugin>-->
        </plugins>
    </build>

</project>

配置运行环境变量：

1.下载https://github.com/sdravida/hadoop2.6_Win_x64/blob/master/bin/winutils.exe 文件

2.配置环境变量HADOOP_HOME

3.winutil.exe 放置在$HADOOP_HOME/bin下

Linux环境下，在winutil.exe没有的情况下，运行demo看缺少什么包（未测试）

最后：

win7系统重启电脑，win10重启IDE即可