python对象互相引用计算文件行数

2022-08-13 00:00:09 阅读：138 来源： 互联网

标签：python self 互相引用 input data workers def result

from threading import Thread
import os


class InputData(object):
    def read(self):
        raise NotImplementedError


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

    def read(self):
        return open(self.path, encoding='utf8').read()


class Worker(object):
    def __init__(self, input_data):
        self.input_data = input_data
        self.result = 0

    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')

    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 = []
    print('input_list', input_list)
    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 thread in threads: thread.start()
    for thread in threads: thread.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)


path = "D:\\python3.64\\CorePython\\chapter-6"
result = mapreduce(path)
print('There are', result, 'lines')

输出:

input_list <generator object generate_inputs at 0x00000278722C7BF8>
There are 83 lines

升级版:

from threading import Thread
import os


class GenericInputData(object):
    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, encoding='utf-8').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(object):
    def __init__(self, input_data):
        self.input_data = input_data
        self.result = 0

    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 thread in threads: thread.start()
    for thread in threads: thread.join()

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


# 最后,重写mapreduce函数,令其变得完全通用.
def mapreduce(worker_class, input_class, config):
    workers = worker_class.create_workers(input_class, config)
    return execute(workers)
    # 在测试文件上面执行修改后的MapReduce程序,所得结果与原来那套实现方式是相同的
    # .区别在于,现在的mapreduce函数需要更多的参数,以便用更加通用的方式来梁作相关对象.


path = "D:\\python3.64\\CorePython\\chapter-6"
config = {'data_dir': path}
result = mapreduce(LineCountWorker, PathInputData, config)
print('There are', result, 'lines')

输出:
There are 83 lines

标签：python,self,互相,引用,input,data,workers,def,result
来源： https://www.cnblogs.com/heris/p/16581766.html

本站声明： 1. iCode9 技术分享网（下文简称本站）提供的所有内容，仅供技术学习、探讨和分享；
2. 关于本站的所有留言、评论、转载及引用，纯属内容发起人的个人观点，与本站观点和立场无关；
3. 关于本站的所有言论和文字，纯属内容发起人的个人观点，与本站观点和立场无关；
4. 本站文章均是网友提供，不完全保证技术分享内容的完整性、准确性、时效性、风险性和版权归属；如您发现该文章侵犯了您的权益，可联系我们第一时间进行删除；
5. 本站为非盈利性的个人网站，所有内容不会用来进行牟利，也不会利用任何形式的广告来间接获益，纯粹是为了广大技术爱好者提供技术内容和技术思想的分享性交流网站。

ICode9

python对象互相引用计算文件行数

升级版: