** python 使用@classmethod形式的多态去通用地构建对象

统计输入中的换行符

import os
from threading import Thread


class InputData:
    def read(self):
        raise NotImplementedError


class PathInputData(InputData):
    def __init__(self, path):
        super().__init__()
        self.path = path

    def read(self):
        return open(self.path).read()


class Worker:
    def __init__(self, input_data):
        self.input_data = input_data
        self.result = None

    def map(self):
        raise NotImplementedError

    def reduce(self, other):
        raise NotImplementedError


class LineCountWorker(Worker):
    def map(self):
        data = self.input_data.read()
        self.result = data.count('\n')
        print('done')

    def reduce(self, other):
        self.result += other.result


def generate_inputs(data_dir):
    for name in os.listdir(data_dir):
        yield PathInputData(os.path.join(data_dir, name))


def create_workers(input_list):
    workers = []
    for input_data in input_list:
        workers.append(LineCountWorker(input_data))
    return workers


def execute(workers):
    threads = [Thread(target=w.map) for w in workers]
    for t in threads: t.start()
    for t in threads: t.join()

    first, rest = workers[0], workers[1:]
    for worker in rest:
        first.reduce(worker)
    return first.result


def mapreduce(data_dir):
    inputs = generate_inputs(data_dir)
    workers = create_workers(inputs)
    return execute(workers)


d = r'D:\codepath'
print(mapreduce(d))

---

优化版本

import os
from threading import Thread


class GenericInputData:
    def read(self):
        raise NotImplementedError

    @classmethod
    def generate_inputs(cls, config):
        raise NotImplementedError


class PathInputData(GenericInputData):
    def __init__(self, path):
        super().__init__()
        self.path = path

    def read(self):
        return open(self.path).read()

    @classmethod
    def generate_inputs(cls, config):
        data_dir = config['data_dir']
        for name in os.listdir(data_dir):
            yield cls(os.path.join(data_dir, name))


class GenericWorker:
    def __init__(self, input_data):
        self.input_data = input_data
        self.result = None

    def map(self):
        raise NotImplementedError

    def reduce(self, other):
        raise NotImplementedError

    @classmethod
    def create_workers(cls, input_class, config):
        workers = []
        for input_data in input_class.generate_inputs(config):
            workers.append(cls(input_data))
        return workers


class LineCountWorker(GenericWorker):
    def map(self):
        data = self.input_data.read()
        self.result = data.count('\n')

    def reduce(self, other):
        self.result += other.result


def execute(workers):
    threads = [Thread(target=w.map) for w in workers]
    for t in threads: t.start()
    for t in threads: t.join()

    first, rest = workers[0], workers[1:]
    for worker in rest:
        first.reduce(worker)
    return first.result


def mapreduce(worker_class, input_class, config):
    workers = worker_class.create_workers(input_class, config)
    return execute(workers)


d = r'D:\codepath'
config = {'data_dir': d}
result = mapreduce(LineCountWorker, PathInputData, config)
print(result)

优点：可以编写其它的 GenericWorker 和 GenericInputData 的子类，而且不用再修改刚才写好的那些拼接代码了。