【Spark-HDFS小文件合并】使用 Spark 实现 HDFS 小文件合并

需求描述：

1、使用 Spark 做小文件合并压缩处理。

2、实际生产中相关配置、日志、明细可以记录在 Mysql 中。

3、core-site.xml、hdfs-site.xml、hive-site.xml、yarn-site.xmlx 等文件放在项目的 resources 目录下进行认证。

4、下面的案例抽取出了主体部分的代码，具体实现时需要结合 HDFS 工具类，利用好 Mysql 做好配置、日志、以及相关明细，结合各自业务进行文件合并。

1）导入依赖

<?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>test.cn.suitcase</groupId>
    <artifactId>mergefiles</artifactId>
    <version>4.0.0</version>

    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding>
        <java.version>1.8</java.version>
        <maven.compiler.source>1.8</maven.compiler.source>
        <maven.compiler.target>1.8</maven.compiler.target>
        <encoding>UTF-8</encoding>
<!--        <spark.version>3.0.2</spark.version>-->
        <spark.version>2.4.8</spark.version>
        <scala.version>2.11.12</scala.version>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.apache.logging.log4j</groupId>
            <artifactId>log4j-core</artifactId>
            <version>2.20.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>3.3.2</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-client -->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>3.3.2</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-hdfs -->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>3.3.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.logging.log4j</groupId>
            <artifactId>log4j-api</artifactId>
            <version>2.20.0</version>
        </dependency>
        <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><