1. 程式人生 > >倒排索引建立案例

倒排索引建立案例

重點注意:

  • 1.FileSplit split = (FileSplit) context.getInputSplit();

    String fileName = split.getPath().getName();

    //獲取檔案的名字

  • 2.context.write(new Text(split1[0]),new Text(split1[1].replaceAll("\t","–>")));

    replaceAll替換所有

  • 3.StringBuffer stringBuffer = new StringBuffer();

    stringBuffer.append(value.toString());

    //字串追加

第一次編寫類:

public class InvertedOne {
    public static class OneMapper extends Mapper<LongWritable,Text,Text,IntWritable>{

        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            FileSplit split = (FileSplit) context.getInputSplit();
            String fileName = split.getPath().getName();

            String string = value.toString();
            String[] split1 = string.split(" ");
            for (String s : split1) {
                context.write(new Text(s + "-"+fileName),new IntWritable(1));
            }
        }
    }
    public static class OneReducer extends Reducer<Text,IntWritable,Text,IntWritable>{

        @Override
        protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            int count = 0;
            for (IntWritable value : values) {
                count += value.get();
            }
            context.write(new Text(key),new IntWritable(count));
        }
    }
}

第一次測試類:

public class OneTest {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        job.setJarByClass(OneTest.class);

        job.setMapperClass(InvertedOne.OneMapper.class);
        job.setReducerClass(InvertedOne.OneReducer.class);

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        File file = new File("某盤output1");
        if (file.exists()){
            FileUtils.deleteDirectory(file);
        }
        FileInputFormat.setInputPaths(job,new Path("某盤input"));
        FileOutputFormat.setOutputPath(job,new Path("某盤output1"));

        job.setNumReduceTasks(1);

        boolean b = job.waitForCompletion(true);

        System.exit(b ? 0 : 1);
    }
}

第二次編寫類:

public class InvertedTwo {
    public static class TwoMapper extends Mapper<LongWritable,Text,Text,Text>{
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            FileSplit split = (FileSplit) context.getInputSplit();
            String fileName = split.getPath().getName();

            String[] split1 = value.toString().split("-");
            context.write(new Text(split1[0]),new Text(split1[1].replaceAll("\t","-->")));
        }
    }
    public static class TwoReducer extends Reducer<Text,Text,Text,Text>{
        @Override
        protected void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
            StringBuffer stringBuffer = new StringBuffer();

            for (Text value : values) {
            stringBuffer.append(value.toString());
            }context.write(new Text(key),new Text(stringBuffer.toString()));
        }
    }
}

第二次測試類:

public class Twotest {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        job.setJarByClass(Twotest.class);

        job.setMapperClass(InvertedTwo.TwoMapper.class);
        job.setReducerClass(InvertedTwo.TwoReducer.class);

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Text.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);

        File file = new File("某盤output2");
        if (file.exists()){
            FileUtils.deleteDirectory(file);
        }
        FileInputFormat.setInputPaths(job,new Path("某盤output1"));
        FileOutputFormat.setOutputPath(job,new Path("某盤output2"));

        job.setNumReduceTasks(1);

        boolean b = job.waitForCompletion(true);

        System.exit(b ? 0 : 1);
    }
}