Hadoop:倒排索引源代码

814247614

mapper端实现
public static class Mapclass extends MapReduceBase implements
Mapper<LongWritable,Text,Text,Text>{
public Text name = new Text();
public Text location = new Text();
public void map(LongWritable key,Text value,
OutputCollector<Text,Text> output,Reporter reporter)throws IOException{
FileSplit fs = (FileSplit) reporter.getInputSplit();
String filename = fs.getPath().getName();
this.location.set(filename);
StringTokenizer itr = new StringTokenizer(value.toString());
while(itr.hasMoreTokens()){
this.name.set(itr.nextToken());
output.collect(this.name, this.location);
}
}
}

Reducer端实现：
public static class Reducerclass extends MapReduceBase implements
Reducer<Text,Text,Text,Text>{
public void reduce(Text key,Iterator<Text> values,
OutputCollector<Text,Text> output,Reporter reporter) throws IOException{
String first = ((Text) values.next()).toString();
String curr = first;
int sum = 1;
StringBuffer sb = new StringBuffer();
while (values.hasNext()) {
String next = ((Text) values.next()).toString();
if (curr.equals(next)) {
sum++;
} else {
sb.append(curr).append("\t").append(sum).append("\t");
sum = 1;
curr = next;
}
};
sb.append(curr).append("\t").append(sum).append("\t");
output.collect(key, new Text(sb.toString()));
}//end reducer
}


其他 job 输入输出路径就自己写吧