题目:假设在HDFS下有几个文件,分别是file1.txt、file2.txt、file3.txt、file4.abc、file5.abc,这里需要从目录中过滤出所有后缀不为.abc的文件,对过滤之后的文件进行读取,并将这些文件的内容合并到文件merge.txt中。
一、新建Java的maven工程
二、配置环境
1、 配置坐标(pom.xml)
<?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>org.hqp</groupId>
<artifactId>BigData</artifactId>
<version>1.0-SNAPSHOT</version>
<properties>
<maven.compiler.source>8</maven.compiler.source>
<maven.compiler.target>8</maven.compiler.target>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
</properties>
<dependencies>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>3.1.3</version>
</dependency>
<dependency>
<groupId>org.apache.velocity</groupId>
<artifactId>velocity-tools</artifactId>
<version>2.0</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-client</artifactId>
<version>2.4.14</version>
<exclusions>
<exclusion>
<groupId>org.glassfish</groupId>
<artifactId>javax.el</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.glassfish</groupId>
<artifactId>javax.el</artifactId>
<version>3.0.1-b12</version>
</dependency>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>4.12</version>
</dependency>
<dependency>
<groupId>com.google.guava</groupId>
<artifactId>guava</artifactId>
<version>24.0-jre</version>
</dependency>
<dependency>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-log4j12</artifactId>
<version>1.7.30</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-auth</artifactId>
<version>3.1.2</version>
</dependency>
</dependencies>
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.10.1</version>
<configuration>
<source>1.8</source>
<target>1.8</target>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-assembly-plugin</artifactId>
<version>3.1.1</version>
<configuration>
<descriptorRefs>
<descriptorRef>
jar-with-dependencies
</descriptorRef>
</descriptorRefs>
</configuration>
<executions>
<execution>
<id>make-assembly</id>
<phase>package</phase>
<goals>
<goal>single</goal>
</goals>
</execution>
</executions>
</plugin>
</plugins>
</build>
</project>
2. 配置日志(log4j.properties)
log4j.rootLogger=debug,stdout,R
log4j.appender.stdout=org.apache.log4j.ConsoleAppender
log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
# Pattern to output the caller's file name and line number.
log4j.appender.stdout.layout.ConversionPattern=%5p [%t] (%F:%L) - %m%n
log4j.appender.R=org.apache.log4j.RollingFileAppender
log4j.appender.R.File=example.log
log4j.appender.R.MaxFileSize=100KB
# Keep one backup file
log4j.appender.R.MaxBackupIndex=5
log4j.appender.R.layout=org.apache.log4j.PatternLayout
log4j.appender.R.layout.ConversionPattern=%p %t %c - %m%n
三、编写程序代码(merge.java)
package org.hqp.task.task1;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.*;
import org.apache.hadoop.io.IOUtils;
import java.io.IOException;
import java.net.URI;
public class merge {
static FileSystem fs = null;
// 创建连接,得到hdfs
public static void init() throws Exception {
//填入hadoop配置文件core-site.xml中的fs.defaultFS值即可
URI uri = URI.create("hdfs://node0:9000");
Configuration configuration = new Configuration();
//第三个参数输入用户名,与hdfs-site.xml的hadoop.http.staticuser.user的值即可
fs = FileSystem.get(uri, configuration, "hqp");
}
public static void destroy() throws IOException {
//关闭文件系统
fs.close();
}
//筛选文件并合并到一个新的的文件
public static void combine(Path path) throws IOException {
// 在输入的文件目录下新建一个merge.txt用以存放合并后的内容
String res = "/merge.txt";
String curPath = path.toString() + res;
fs.create(new Path(curPath));
// 得到merge.txt的输出流用以写入
FSDataOutputStream fso = fs.create(new Path(curPath));
// 遍历输入目录下所有的文件
for (FileStatus file : fs.listStatus(path)) {
// 得到文件名,getPath得到的是文件全路径,此时得到文件名即可
String fname = file.getPath().getName();
// 通过拆分文件名得到文件后缀
String suffix = fname.split("\\.")[1];
if (suffix.equals("txt") && !fname.equals(res.substring(1))) {
// 得到符合要求的文件(txt文件),获得其输入流用以复制
FSDataInputStream fsi = fs.open(file.getPath());
// 将输出流写入merge.txt的输出流
IOUtils.copyBytes(fsi, fso, 1024);
// 关闭文件的输入流
fsi.close();
}
}
// 关闭merge.txt的输出流
fso.close();
}
public static void main(String[] args) throws Exception {
init();
combine(new Path(args[0]));
destroy();
}
}
四、运行程序
由于该程序读入的是程序实参,在运行程序时指定一个实参(输入文件的路径)即可
然后运行此代码即可成功在hdfs上得到输出结果