feat(hbase-lesson): 添加新模块 hbase-20250509

- 新增 hbase-20250509 模块用于 HBase 课程项目
- 实现了流量统计和词频统计两个 MapReduce 任务
- 添加了相应的 Mapper、Reducer 和 Driver 类- 创建了输入样例文件- 配置了 Maven 依赖

hbase-lesson/hbase-20250509/src/main/java/FlowCount2/FlowBean.java

@@ -0,0 +1,77 @@
+package FlowCount2;
+
+import org.apache.hadoop.io.Writable;
+
+import java.io.DataInput;
+import java.io.DataOutput;
+import java.io.IOException;
+
+//implements关键字用于接口的实现,接口定义一个类应该如何操作的蓝图
+public class FlowBean implements Writable {
+    private long upFlow;
+    private long downFlow;
+    private long sumFlow;
+
+    public FlowBean(){
+
+    }
+
+    public FlowBean(long upFlow, long downFlow){
+        this.upFlow = upFlow;
+        this.downFlow =downFlow;
+        this.sumFlow = upFlow+downFlow;
+
+    }
+
+    public long getUpFlow() {
+        return upFlow;
+    }
+
+    public void setUpFlow(long upFlow) {
+        this.upFlow = upFlow;
+    }
+
+    public long getDownFlow() {
+        return downFlow;
+    }
+
+    public void setDownFlow(long downFlow) {
+        this.downFlow = downFlow;
+    }
+
+    public long getSumFlow() {
+        return sumFlow;
+    }
+
+    public void setSumFlow(long sumFlow) {
+        this.sumFlow = sumFlow;
+    }
+
+    //写的方法 序列化方式 Java原始数据类型写入到字节流
+    public void write(DataOutput out) throws IOException {
+        out.writeLong(this.upFlow);
+        out.writeLong(this.downFlow);
+        out.writeLong(this.sumFlow);
+
+    }
+
+    //读的方法 反序列化 从字节流中读取Java原始数据类型的值
+    public void readFields(DataInput in) throws IOException {
+        this.upFlow = in.readLong();
+        this.downFlow = in.readLong();
+        this.sumFlow =in.readLong();
+
+    }
+
+    // Object 类的 toString() 方法返回的格式是 ClassName@hashcode
+    // 重写 toString() 方法
+    // 当MapReduce框架需要将 FlowBean 对象转换为字符串形式会调用自定义的 toString() 方法
+    @Override
+    public String toString() {
+        return "FlowBean{" +
+                "upFlow=" + upFlow +
+                ", downFlow=" + downFlow +
+                ", sumFlow=" + sumFlow +
+                '}';
+    }
+}

hbase-lesson/hbase-20250509/src/main/java/FlowCount2/FlowCountDriver.java

@@ -0,0 +1,35 @@
+package FlowCount2;
+
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.mapreduce.Job;
+import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
+import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
+
+import java.io.IOException;
+
+public class FlowCountDriver {
+    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
+        Configuration conf = new Configuration();
+
+        Job job = Job.getInstance(conf, "FlowBean");
+
+        job.setMapperClass(FlowCountMapper.class);
+        job.setReducerClass(FlowCountReducer.class);
+
+        job.setMapOutputKeyClass(Text.class);
+        job.setMapOutputValueClass(FlowBean.class);
+        job.setOutputKeyClass(Text.class);
+        job.setOutputValueClass(FlowBean.class);
+
+        job.setNumReduceTasks(1);
+
+        FileInputFormat.setInputPaths(job, new Path("hbase-lesson/hbase-20250509/src/main/java/FlowCount2/input/"));
+        FileOutputFormat.setOutputPath(job, new Path("hbase-lesson/hbase-20250509/src/main/java/FlowCount2/output/"));
+
+        job.waitForCompletion(true);
+
+
+    }
+}

hbase-lesson/hbase-20250509/src/main/java/FlowCount2/FlowCountMapper.java

@@ -0,0 +1,26 @@
+package FlowCount2;
+
+import org.apache.hadoop.io.LongWritable;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.mapreduce.Mapper;
+
+import java.io.IOException;
+
+public class FlowCountMapper extends Mapper<LongWritable, Text, Text, FlowBean> {
+
+    @Override
+    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
+        String[] oneLine = value.toString().split("\\s+");
+        try {
+            long upFlow = Long.parseLong(oneLine[1]);
+            long downFlow = Long.parseLong(oneLine[2]);
+            long sumFlow = upFlow + downFlow;
+
+            context.write(new Text(oneLine[0]), new FlowBean(upFlow, downFlow));
+        } catch (Exception e) {
+            e.printStackTrace();
+        }
+
+    }
+}
+

hbase-lesson/hbase-20250509/src/main/java/FlowCount2/FlowCountReducer.java

@@ -0,0 +1,21 @@
+package FlowCount2;
+
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.mapreduce.Reducer;
+
+import java.io.IOException;
+
+public class FlowCountReducer extends Reducer<Text, FlowBean, Text, FlowBean> {
+
+    @Override
+    protected void reduce(Text key, Iterable<FlowBean> values, Context context) throws IOException, InterruptedException {
+        long sumUpFLow =0;
+        long sumDownFLow =0;
+        for(FlowBean value_i: values) {
+            sumUpFLow+=value_i.getUpFlow();
+            sumDownFLow+=value_i.getDownFlow();
+        }
+
+        context.write(key, new FlowBean(sumUpFLow, sumDownFLow));
+    }
+}

hbase-lesson/hbase-20250509/src/main/java/FlowCount2/input/FlowCountSample.txt

@@ -0,0 +1,7 @@
+手机号 上行流量 下行流量
+13726230501 200 1100
+13396230502 300 1200
+13897230503 400 1300
+13897230503 100 300
+13597230534 500 1400
+13597230534 300 1200