spark中各个技术点中的依赖(pom.xml)

mapreduce依赖

    <properties>
        <hadoop.version>2.8.5</hadoop.version>
    </properties>
 
    <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
 
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
 
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.12</version>
            <scope>test</scope>
        </dependency>
    </dependencies>

1. sparkcore

<dependency>
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-core_2.11</artifactId>
<version>2.3.1</version>

2. sparksql

• 需要引入jdbc连接和sparksql连接(sparksql中包含了sparkcore，所以不需要单独引入sparkcore)

<dependency>
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-sql_2.11</artifactId>
    <version>2.3.1</version>
</dependency>
<dependency>
    <groupId>mysql</groupId>
    <artifactId>mysql-connector-java</artifactId>
    <version>8.0.18</version>
</dependency>

3. hive

• 需要引入依赖spark连接操作hive以及MySQL驱动依赖

<dependency>
    <groupId>mysql</groupId>
    <artifactId>mysql-connector-java</artifactId>
    <version>8.0.18</version>
</dependency>
<dependency>
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-hive_2.11</artifactId>
    <version>2.3.1</version>
</dependency>

4. spark

<dependency>
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-streaming_2.11</artifactId>
    <version>2.3.1</version>
</dependency>

5. spark整合flume

<dependency>
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-streaming_2.11</artifactId>
    <version>2.3.1</version>
</dependency>
<dependency>
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-streaming-flume_2.11</artifactId>
    <version>2.3.1</version>
</dependency>

6. zookeeper

<dependencies>
    <dependency>
        <groupId>org.apache.zookeeper</groupId>
        <artifactId>zookeeper</artifactId>
        <version>3.4.6</version>
    </dependency>
</dependencies>

7. kafka

<!--引入Kafka的编程依赖 kafka    kafka-clients-->
<dependency>
    <groupId>org.apache.kafka</groupId>
    <artifactId>kafka-clients</artifactId>
    <version>0.11.0.0</version>
</dependency>
 
<dependency>
    <groupId>org.apache.kafka</groupId>
    <artifactId>kafka_2.12</artifactId>
    <version>0.11.0.0</version>
</dependency>

8. sparkstreaming整合kafka

 <dependency>
    <groupId>org.apache.kafka</groupId>
    <artifactId>kafka_2.12</artifactId>
    <version>0.11.0.0</version>
</dependency>
 
<dependency>
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-streaming_2.11</artifactId>
    <version>2.3.1</version>
</dependency>
 
<dependency>
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-streaming-kafka-0-10_2.11</artifactId>
    <version>2.3.1</version>
</dependency>