MR框架-->Word2

省份浏览量统计功能实现：

1.统计各个省份的浏览量

1. 省份浏览器统计值ip库解析
2. 省份浏览器统计之日志解析
3. 省份浏览器统计之功能实现

前期准备：

1. 4个工具类：GetPageId   IPParser   IPSeeker   LogParser    qqwry.dat

Mapper类

//Mapper类
    static class LogMapper extends Mapper<LongWritable, Text, Text, IntWritable>{
          //定义ONE为全局变量
        private  IntWritable ONE = new IntWritable(1);

        @Override
        protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, IntWritable>.Context context)
                throws IOException, InterruptedException {
            //获取一行数据
            String log = value.toString();
            //创建LogParser对象
            LogParser logParser = new LogParser();
            //从LogParser对象中获取ip
            Map<String, String> map = logParser.parse(log);
            String ip = map.get("ip");
            //创建IPParser对象
            RegionInfo analyseIp = IPParser.getInstance().analyseIp(ip);
            //通过get方法获取省份
            String province = analyseIp.getProvince();
            //对省份进行判断
            if(StringUtils.isNotBlank(province)) {
                 context.write(new Text(province), ONE);
             }else {
                 context.write(new Text("-"), ONE);    
            }
        }
    }

Reducer类

static class LogReducer extends Reducer<Text, IntWritable, Text, IntWritable>{
        protected void reduce(Text key, Iterable<IntWritable> values, Reducer<Text, IntWritable, Text, IntWritable>.Context context)
                throws IOException, InterruptedException {
            //定义一个空变量
            int i = 0 ;
            //遍历
            for (IntWritable value : values) {
                //结果累加
                i += value.get();
            }
            //写入到上下文中
            context.write(key, new IntWritable(i));
        }
    }

Submit类

public static void main(String[] args) throws Exception {
        //加载配置文件
        Configuration conf = new Configuration();
        //创建Job对象
        Job job = Job.getInstance(conf);
        //设置提交主类
        job.setJarByClass(LogApp.class);
        //设置Mapper类相关的参数
        job.setMapperClass(LogMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        //设置Reducer类相关的参数
        job.setReducerClass(LogReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        //设置输入路径
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        //设置输出路径
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        //提交任务
        job.waitForCompletion(true);
    }

如果hdfs操作不太熟悉请参考前面的Hadoop