mapreduce倒排索引创建-切片 (eleven day)

 需求：在大量的文本中分别取到某个词出现的次数，输出单词在每个文件中的总次数

梳理逻辑：

1、先写一个mr程序：统计出每个单词在每个文件中的总次数

分析：map：会传key，value，content（inputsplit输入切片用于描述maptask处理的数据范围的切片信息）

如果maptask读的是文件：划分范围应该用如下信息描述：文件路径，偏移量范围，

如果maptask读的是数据库的数据：划分任务范围：库名，表名，行范围

2、然后在写一个mr程序，读取上述结果数据：

map： 根据-切，以单词做key，后面一段作为value

reduce： 拼接values里面的每一段，以单词做key，拼接结果做value，输出即可

 

public class IndexStepOne {

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

		// 产生 <hello-文件名，1> 
		@Override
		protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
			// 从输入切片信息中获取当前正在处理的一行数据所属的文件
			FileSplit inputSplit = (FileSplit) context.getInputSplit();
			String fileName = inputSplit.getPath().getName();

			String[] words = value.toString().split(" ");
			for (String w : words) {
				// 将"单词-文件名"作为key，1作为value，输出
				context.write(new Text(w + "-" + fileName), new IntWritable(1));
			}

		}

	}

	public static class IndexStepOneReducer extends Reducer<Text, IntWritable, Text, IntWritable> {

		@Override
		protected void reduce(Text key, Iterable<IntWritable> values,
				Reducer<Text, IntWritable, Text, IntWritable>.Context context)
				throws IOException, InterruptedException {

			int count = 0;
			for (IntWritable value : values) {
				count += value.get();
			}

			context.write(key, new IntWritable(count));

		}

	}
	
	
	
	public static void main(String[] args) throws Exception{
		
		Configuration conf = new Configuration(); 
		
		Job job = Job.getInstance(conf);

		job.setJarByClass(IndexStepOne.class);

		job.setMapperClass(IndexStepOneMapper.class);
		job.setReducerClass(IndexStepOneReducer.class);

		job.setNumReduceTasks(3);

		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(IntWritable.class);
		
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(IntWritable.class);
		
		// job.setOutputFormatClass(TextOutputFormat.class);  // 这是默认的输出组件
		job.setOutputFormatClass(SequenceFileOutputFormat.class);
		

		FileInputFormat.setInputPaths(job, new Path("F:\\mrdata\\index\\input"));
		FileOutputFormat.setOutputPath(job, new Path("F:\\mrdata\\index\\out-seq-1"));

		job.waitForCompletion(true);
		
	}
	

}

public class IndexStepTwo {

	public static class IndexStepTwoMapper extends Mapper<Text, IntWritable, Text, Text> {

		@Override
		protected void map(Text key, IntWritable value, Context context) throws IOException, InterruptedException {
			String[] split = key.toString().split("-");
			context.write(new Text(split[0]), new Text(split[1]+"-->"+value));
		}

	}

	public static class IndexStepTwoReducer extends Reducer<Text, Text, Text, Text> {

		// 一组数据：  <hello,a.txt-->4> <hello,b.txt-->4> <hello,c.txt-->4>
		@Override
		protected void reduce(Text key, Iterable<Text> values,Context context)
				throws IOException, InterruptedException {
			// stringbuffer是线程安全的，stringbuilder是非线程安全的，在不涉及线程安全的场景下，stringbuilder更快
			StringBuilder sb = new StringBuilder();
			
			for (Text value : values) {
				sb.append(value.toString()).append("\t");
			}
			
			context.write(key, new Text(sb.toString()));
			

		}

	}
	
	
	
	public static void main(String[] args) throws Exception{
		
		Configuration conf = new Configuration(); // 默认只加载core-default.xml core-site.xml
		
		Job job = Job.getInstance(conf);

		job.setJarByClass(IndexStepTwo.class);

		job.setMapperClass(IndexStepTwoMapper.class);
		job.setReducerClass(IndexStepTwoReducer.class);

		job.setNumReduceTasks(1);

		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(Text.class);
		
		// job.setInputFormatClass(TextInputFormat.class); 默认的输入组件
		job.setInputFormatClass(SequenceFileInputFormat.class);
		
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(Text.class);

		FileInputFormat.setInputPaths(job, new Path("F:\\mrdata\\index\\out1"));
		FileOutputFormat.setOutputPath(job, new Path("F:\\mrdata\\index\\out2"));

		job.waitForCompletion(true);
		
	}
	

}

mapreduce