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/FlowCount/FlowCountDriver.java

@@ -0,0 +1,37 @@
+package FlowCount;
+
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.io.LongWritable;
+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, "FlowCount");
+
+        job.setMapperClass(FlowCountMapper.class);
+        job.setReducerClass(FlowCountReducer.class);
+
+        job.setMapOutputKeyClass(Text.class);
+        job.setMapOutputValueClass(LongWritable.class);
+        job.setOutputKeyClass(Text.class);
+        job.setOutputValueClass(LongWritable.class);
+
+        job.setNumReduceTasks(1);
+
+        FileInputFormat.setInputPaths(job, new Path("hbase-lesson/hbase-20250509/src/main/java/FlowCount/input/"));
+        FileOutputFormat.setOutputPath(job, new Path("hbase-lesson/hbase-20250509/src/main/java/FlowCount/output/"));
+
+        job.waitForCompletion(true);
+
+
+    }
+}
+

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

@@ -0,0 +1,25 @@
+package FlowCount;
+
+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, LongWritable> {
+
+    @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 LongWritable(sumFlow));
+        } catch (Exception e) {
+            e.printStackTrace();
+        }
+
+    }
+}

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

@@ -0,0 +1,20 @@
+package FlowCount;
+
+import org.apache.hadoop.io.LongWritable;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.mapreduce.Reducer;
+
+import java.io.IOException;
+
+public class FlowCountReducer extends Reducer<Text, LongWritable, Text, LongWritable> {
+
+    @Override
+    protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {
+        long count =0;
+        for(LongWritable value_i: values) {
+            count+=value_i.get();
+        }
+
+        context.write(key, new LongWritable(count));
+    }
+}

hbase-lesson/hbase-20250509/src/main/java/FlowCount/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