在Hadoop的mapper类中,有4个主要的函数,分别是:setup,clearup,map,run。
protected void setup(Context context) throws IOException, InterruptedException {
// NOTHING
}
protected void map(KEYIN key, VALUEIN value,
Context context) throws IOException, InterruptedException {
context.write((KEYOUT) key, (VALUEOUT) value);
}
protected void cleanup(Context context) throws IOException, InterruptedException {
// NOTHING
}
public void run(Context context) throws IOException, InterruptedException {
setup(context);
while (context.nextKeyValue()) {
map(context.getCurrentKey(), context.getCurrentValue(), context);
}
cleanup(context);
}
}
在Hadoop的reducer类中,有3个主要的函数,分别是:setup,clearup,reduce。
/**
* Called once at the start of the task.
*/
protected void setup(Context context
) throws IOException, InterruptedException {
// NOTHING
}
/**
* This method is called once for each key. Most applications will define
* their reduce class by overriding this method. The default implementation
* is an identity function.
*/
@SuppressWarnings("unchecked")
protected void reduce(KEYIN key, Iterable<VALUEIN> values, Context context
) throws IOException, InterruptedException {
for(VALUEIN value: values) {
context.write((KEYOUT) key, (VALUEOUT) value);
}
}
/**
* Called once at the end of the task.
*/
protected void cleanup(Context context
) throws IOException, InterruptedException {
// NOTHING
}
/*
* control how the reduce task works.
*/
@SuppressWarnings("unchecked")
public void run(Context context) throws IOException, InterruptedException {
setup(context);
while (context.nextKey()) {
reduce(context.getCurrentKey(), context.getValues(), context);
// If a back up store is used, reset it
((ReduceContext.ValueIterator)
(context.getValues().iterator())).resetBackupStore();
}
cleanup(context);
}
}