京公网安备 11010802034615号
经营许可证编号:京B2-20210330
rm -rf /opt/linuxsir/hadoop/logs/*.*
ssh root@192.168.31.132 rm -rf /opt/linuxsir/hadoop/logs/*.*
ssh root@192.168.31.133 rm -rf /opt/linuxsir/hadoop/logs/*.*
clear
cd /opt/linuxsir/hadoop/sbin
./start-dfs.sh
./start-yarn.sh
clear
jps
ssh root@192.168.31.132 jps
ssh root@192.168.31.133 jps
在eclipse里面操作如下:
New-Java Project,名称自定义即可,如 java-prjNew-Package,名称自定义为com.pai.hdfs_demoNew-Class,名称自定义为ReadWriteHDFSExamplepackage com.pai.hdfs_demo;
import org.apache.commons.io.IOUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import java.io.*;
import java.nio.charset.StandardCharsets;
public class ReadWriteHDFSExample {
// main 新建一个类ReadWriteHDFSExample,编写main函数如下。main函数调用其它函数,创建目录,写入数据,添加数据,然后再读取数据
public static void main(String[] args) throws IOException {
// ReadWriteHDFSExample.checkExists();
ReadWriteHDFSExample.createDirectory();
ReadWriteHDFSExample.writeFileToHDFS();
ReadWriteHDFSExample.appendToHDFSFile();
ReadWriteHDFSExample.readFileFromHDFS();
}
// readFileFromHDFS 该函数读取文件内容,以字符串形式显示出来
public static void readFileFromHDFS() throws IOException {
Configuration configuration = new Configuration();
configuration.set("fs.defaultFS", "hdfs://192.168.31.131:9000");
FileSystem fileSystem = FileSystem.get(configuration);
// Create a path
String fileName = "read_write_hdfs_example.txt";
Path hdfsReadPath = new Path("/javareadwriteexample/" + fileName);
// initialize input stream
FSDataInputStream inputStream = fileSystem.open(hdfsReadPath);
// Classical input stream usage
String out = IOUtils.toString(inputStream, "UTF-8");
System.out.println(out);
// BufferedReader bufferedReader = new BufferedReader(
// new InputStreamReader(inputStream, StandardCharsets.UTF_8));
// String line = null;
// while ((line=bufferedReader.readLine())!=null){
// System.out.println(line);
// }
inputStream.close();
fileSystem.close();
}
// writeFileToHDFS writeFileToHDFS函数打开文件,写入一行文本
public static void writeFileToHDFS() throws IOException {
Configuration configuration = new Configuration();
configuration.set("fs.defaultFS", "hdfs://192.168.31.131:9000");
FileSystem fileSystem = FileSystem.get(configuration);
// Create a path
String fileName = "read_write_hdfs_example.txt";
Path hdfsWritePath = new Path("/javareadwriteexample/" + fileName);
FSDataOutputStream fsDataOutputStream = fileSystem.create(hdfsWritePath, true);
BufferedWriter bufferedWriter = new BufferedWriter(
new OutputStreamWriter(fsDataOutputStream, StandardCharsets.UTF_8));
bufferedWriter.write("Java API to write data in HDFS");
bufferedWriter.newLine();
bufferedWriter.close();
fileSystem.close();
}
// appendToHDFSFile 函数打开文件,添加一行文本。需要注意的是,需要对Configuration类的对象configuration进行适当设置,否则出错
public static void appendToHDFSFile() throws IOException {
Configuration configuration = new Configuration();
configuration.set("fs.defaultFS", "hdfs://192.168.31.131:9000");
//configuration.setBoolean("dfs.client.block.write.replace-datanode-on-failure.enabled", true);
configuration.set("dfs.client.block.write.replace-datanode-on-failure.policy","NEVER");
configuration.set("dfs.client.block.write.replace-datanode-on-failure.enable","true");
FileSystem fileSystem = FileSystem.get(configuration);
// Create a path
String fileName = "read_write_hdfs_example.txt";
Path hdfsWritePath = new Path("/javareadwriteexample/" + fileName);
FSDataOutputStream fsDataOutputStream = fileSystem.append(hdfsWritePath);
BufferedWriter bufferedWriter = new BufferedWriter(
new OutputStreamWriter(fsDataOutputStream, StandardCharsets.UTF_8));
bufferedWriter.write("Java API to append data in HDFS file");
bufferedWriter.newLine();
bufferedWriter.close();
fileSystem.close();
}
// createDirectory 函数创建一个目录
public static void createDirectory() throws IOException {
Configuration configuration = new Configuration();
configuration.set("fs.defaultFS", "hdfs://192.168.31.131:9000");
FileSystem fileSystem = FileSystem.get(configuration);
String directoryName = "/javareadwriteexample";
Path path = new Path(directoryName);
fileSystem.mkdirs(path);
}
// checkExists checkExists检查目录或者文件是否存在。注意如下代码的最后一个括号是ReadWriteHDFSExample类的结束括号
public static void checkExists() throws IOException {
Configuration configuration = new Configuration();
configuration.set("fs.defaultFS", "hdfs://192.168.31.131:9000");
FileSystem fileSystem = FileSystem.get(configuration);
String directoryName = "/javareadwriteexample";
Path path = new Path(directoryName);
if (fileSystem.exists(path)) {
System.out.println("File/Folder Exists : " + path.getName());
} else {
System.out.println("File/Folder does not Exists : " + path.getName());
}
}
}
为了编译通过上述Java代码,需要把如下目录下的jar包导入Eclipse项目的Build Path
操作序列为 右键点击Eclipse里的Java项目→Properties→Java Build Path →Libraries→Add External Jars
# 添加如下路径的包
D:hadoop-2.7.3sharehadoopcommonlib
D:hadoop-2.7.3sharehadoopcommon
D:hadoop-2.7.3sharehadoophdfs
D:hadoop-2.7.3sharehadoophdfslib
D:hadoop-2.7.3sharehadoopmapreducelib
D:hadoop-2.7.3sharehadoopmapreduce
D:hadoop-2.7.3sharehadoopyarnlib
D:hadoop-2.7.3sharehadoopyarn
就可以愉快地执行了,执行完毕上述代码后,在hd-master主机上可以通过如下命令,检查已经写入的文件
[root@hd-master bin]# cd /opt/linuxsir/hadoop/bin
[root@hd-master bin]# ./hdfs dfs -ls /javareadwriteexample/read_write_hdfs_example.txt
-rw-r--r-- 3 root supergroup 70 2024-10-10 04:47 /javareadwriteexample/read_write_hdfs_example.txt
[root@hd-master bin]# ./hdfs dfs -cat /javareadwriteexample/read_write_hdfs_example.txt
Java API to write data in HDFS
Java API to append data in HDFS file
为了多次进行实验(或者为了调试代码),可以把HDFS文件删除,然后再执行或者调试Java代码,否则一经存在该目录,执行创建目录的代码就会出错
cd /opt/linuxsir/hadoop/bin
./hdfs dfs -rm /javareadwriteexample/*
./hdfs dfs -rmdir /javareadwriteexample
cd /opt/linuxsir/hadoop/sbin
./stop-yarn.sh
./stop-dfs.sh
jps
ssh root@192.168.31.132 jps
ssh root@192.168.31.133 jps
package mywordcount;
import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
public class WordCount {
//定义WordCount类的内部类TokenizerMapper 该类实现了map函数,把从文件读取的每个word变成一个形式为<word,1>的Key Value对,输出到map函数的参数context对象,由执行引擎完成Shuffle
public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
StringTokenizer itr = new StringTokenizer(value.toString());
while (itr.hasMoreTokens()) {
word.set(itr.nextToken());
context.write(word, one);
}
}
}
//定义WordCount类的内部类IntSumReducer 该类实现了reduce函数,它收拢所有相同key的、形式为<word,1>的Key-Value对,对Value部分进行累加,输出一个计数
public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
private IntWritable result = new IntWritable();
public void reduce(Text key, Iterable<IntWritable> values, Context context)
throws IOException, InterruptedException {
int sum = 0;
for (IntWritable val : values) {
sum += val.get();
}
result.set(sum);
context.write(key, result);
String thekey = key.toString();
int thevalue = sum;
}
}
// WordCount类的main函数,负责配置Job的若干关键的参数,并且启动这个Job。在main函数中,conf对象包含了一个属性即“fs.defaultFS”,它的值为“hdfs://192.168.31.131:9000”,使得WordCount程序知道如何存取HDFS
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
if (otherArgs.length != 2) {
System.err.println("Usage: wordcount <in> <out>");
System.exit(2);
}
conf.set("fs.defaultFS", "hdfs://192.168.31.131:9000");
Job job = new Job(conf, "word count");
job.setJarByClass(WordCount.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
[root@hd-master bin]# ./hdfs dfs -ls /output1
Found 2 items
-rw-r--r-- 3 root supergroup 0 2024-10-10 05:17 /output1/_SUCCESS
-rw-r--r-- 3 root supergroup 89 2024-10-10 05:17 /output1/part-r-00000
[root@hd-master bin]# ./hdfs dfs -cat /output1/part-r-00000
I 1
apache 1
cloudera 1
google 1
hadoop 8
hortonworks 1
ibm 1
intel 1
like 1
microsoft 1
数据分析咨询请扫描二维码
若不方便扫码,搜微信号:CDAshujufenxi
在数据统计分析、数据清洗、异常值识别与数据分布研究中,箱型图是最直观、高效、专业的可视化分析工具。相较于柱状图、折线图仅 ...
2026-05-29Tkinter是Python内置的标准GUI图形界面库,具备无需额外安装、调用简单、兼容性强、轻量化高效等优势,是Python快速开发桌面小程 ...
2026-05-29 很多分析师在设计标签时思路清晰,但真到落地环节却面临“数据在手,不知如何转化为可用标签”的困境:或因加工方式选择不当 ...
2026-05-29【核心关键词】大数据、经理、专业、金融、客户、传统、建模、数据产品、互联网金融、产品经理、数据分析、金融行业、数据模型 ...
2026-05-28 很多分析师每天和数据打交道,但当被问到“标签是什么”“标签和指标有什么区别”“标签体系如何设计”时,却常常答不上来。 ...
2026-05-28随着大数据技术的快速普及,各行各业积累了海量的用户数据、交易数据、生产数据与行为数据。单纯的数据统计与报表分析只能呈现表 ...
2026-05-28在Python网络请求、接口测试、数据爬取、业务对接开发中,Requests库是最简洁、最高效的HTTP请求工具,凭借简洁的语法、完善的适 ...
2026-05-272025 年,零售与服务行业的竞争已从 “经验驱动” 全面转向 “数据驱动”。中小企业门店普遍面临数据零散、分析浅层、决策凭感觉 ...
2026-05-27 很多数据分析师每天都在写SQL,但当被问到“数据查询语言(DQL)的本质是什么”“SELECT语句中各子句的书写顺序与实际执行顺 ...
2026-05-27在统计学分析、实验研究、业务数据复盘过程中,单因素方差分析是检验自变量对因变量是否存在显著影响的核心方法。其中,两个水平 ...
2026-05-26【核心关键词】算法、客户、大数据、互联网、调优、建模、模型优化、机器学习、评分卡模型、模型开发、智能风控、业务场景、数 ...
2026-05-26 很多数据分析师写过无数个 SELECT,但当被问到“新建一张表,该如何定义字段类型来保证数据质量”“创建视图和存储物理表有 ...
2026-05-26在数据清洗、统计分析与数据质量检测工作中,箱型图(又称箱线图、Box Plot)是最直观、最高效的可视化分析工具之一。相较于柱状 ...
2026-05-25在大数据分析、数据清洗、质量管控、风险监测等领域,异常数据识别是保障数据质量、确保分析结论精准、规避业务决策失误的核心基 ...
2026-05-25 很多数据分析师精通Excel函数和透视表,但当被问到“数据从哪里来”“表和视图有什么区别”“数据库管理系统和SQL是什么关系 ...
2026-05-25数字化经营时代,企业的市场竞争早已从经验决策转向数据决策。门店营收、用户转化、产品销量、成本损耗、存量资产等所有经营行为 ...
2026-05-22在MySQL数据库日常运维、业务数据校验、数据迁移与数据清洗场景中,自增主键ID的连续性校验是一项基础且关键的工作。MySQL的Auto ...
2026-05-22 很多企业团队并非缺乏指标,而是陷入“指标失控”:仪表盘上堆满实时跳动的数据,却无法回答“当前瓶颈在哪、下一步该做什么 ...
2026-05-22【核心关键词】大数据、可视化、存储、架构、客户、离线、产品、同步、实时、数据仓库、数据分析、数据可视化、存储数据、离线 ...
2026-05-21在电商流量红利消退、公域获客成本持续走高的当下,存量用户深度挖掘已成为店铺增收增效的核心抓手。相较于付费投放获取的陌生新 ...
2026-05-21