迭代器和生成器

#1、什么是可迭代对象？
可迭代对象指的是内置有__iter__方法的对象，即obj.__iter__，如下
‘hello‘.__iter__
(1,2,3).__iter__
[1,2,3].__iter__
{‘a‘:1}.__iter__
{‘a‘,‘b‘}.__iter__
open(‘a.txt‘).__iter__

#2、为何要有迭代器？
对于序列类型：字符串、列表、元组，我们可以使用索引的方式迭代取出其包含的元素。但对于字典、集合、文件等类型是没有索引的，若还想取出其内部包含的元素，则必须找出一种不依赖于索引的迭代方式，这就是迭代器


#3、什么是迭代器对象？
可迭代对象执行obj.__iter__()得到的结果就是迭代器对象
而迭代器对象指的是即内置有__iter__又内置有__next__方法的对象

文件类型是迭代器对象
open(‘a.txt‘).__iter__()
open(‘a.txt‘).__next__()


#4、注意：
迭代器对象一定是可迭代对象，而可迭代对象不一定是迭代器对象

dic={‘a‘:1,‘b‘:2,‘c‘:3}
iter_dic=dic.__iter__() #得到迭代器对象，迭代器对象即有__iter__又有__next__，但是：迭代器.__iter__()得到的仍然是迭代器本身
iter_dic.__iter__() is iter_dic #True

print(iter_dic.__next__()) #等同于next(iter_dic)
print(iter_dic.__next__()) #等同于next(iter_dic)
print(iter_dic.__next__()) #等同于next(iter_dic)
# print(iter_dic.__next__()) #抛出异常StopIteration，或者说结束标志

#有了迭代器，我们就可以不依赖索引迭代取值了
iter_dic=dic.__iter__()
while 1:
    try:
        k=next(iter_dic)
        print(dic[k])
    except StopIteration:
        break
        
#这么写太丑陋了，需要我们自己捕捉异常，控制next，python这么牛逼，能不能帮我解决呢？能，请看for循环

#初识生成器

def produce():
    """生产衣服"""
    for i in range(2000000):
        yield "生产了第%s件衣服"%i

product_g = produce()
print(product_g.__next__()) #要一件衣服
print(product_g.__next__()) #再要一件衣服
print(product_g.__next__()) #再要一件衣服
num = 0
for i in product_g:         #要一批衣服，比如5件
    print(i)
    num +=1
    if num == 5:
        break

#到这里我们找工厂拿了8件衣服，我一共让我的生产函数(也就是produce生成器函数)生产2000000件衣服。
#剩下的还有很多衣服，我们可以一直拿，也可以放着等想拿的时候再拿

import time


def tail(filename):
    f = open(filename)
    f.seek(0, 2) #从文件末尾算起
    while True:
        line = f.readline()  # 读取文件中新的文本行
        if not line:
            time.sleep(0.1)
            continue
        yield line

tail_g = tail(‘tmp‘)
for line in tail_g:
    print(line)

def averager():
    total = 0.0
    count = 0
    average = None
    while True:
        term = yield average
        total += term
        count += 1
        average = total/count


g_avg = averager()
next(g_avg)
print(g_avg.send(10))
print(g_avg.send(30))
print(g_avg.send(5))

def init(func):  #在调用被装饰生成器函数的时候首先用next激活生成器
    def inner(*args,**kwargs):
        g = func(*args,**kwargs)
        next(g)
        return g
    return inner

@init
def averager():
    total = 0.0
    count = 0
    average = None
    while True:
        term = yield average
        total += term
        count += 1
        average = total/count


g_avg = averager()
# next(g_avg)   在装饰器中执行了next方法
print(g_avg.send(10))
print(g_avg.send(30))
print(g_avg.send(5))

def gen1():
    for c in ‘AB‘:
        yield c
    for i in range(3):
        yield i

print(list(gen1()))

def gen2():
    yield from ‘AB‘
    yield from range(3)

print(list(gen2()))

def eater(name):
    print(‘%s ready to eat‘ %(name))
    foog_list=[]
    while True:
        food=yield foog_list
        print(‘%s start to eat %s‘ %(name,food))
        foog_list.append(food)

g=eater(‘alex‘)
next(g)
print(g.send(‘烧鸡‘))
print(g.send(‘烧鹅‘))
print(g.send(‘烤鸭‘))
print(g.send(‘烤熊掌‘))
print(g.send(‘烤乳猪‘))
print(g.send(‘凉菜‘))

#题目一：
def my_range(start,stop,step=1):
    while start < stop:
        yield start
        start+=step

#执行函数得到生成器，本质就是迭代器
obj=my_range(1,7,2) #1  3  5
print(next(obj))
print(next(obj))
print(next(obj))
print(next(obj)) #StopIteration

#应用于for循环
for i in my_range(1,7,2):
    print(i)

#题目二：
import time
def tail(filepath):
    with open(filepath,‘rb‘) as f:
        f.seek(0,2)
        while True:
            line=f.readline()
            if line:
                yield line
            else:
                time.sleep(0.2)

def grep(pattern,lines):
    for line in lines:
        line=line.decode(‘utf-8‘)
        if pattern in line:
            yield line

for line in grep(‘404‘,tail(‘access.log‘)):
    print(line,end=‘‘)

#题目三：
def  init(func):
    def inner(*args,**kwargs):
        res=func(*args,**kwargs)
        next(res)
        return res
    return inner

@init
def eater(name):
    print(‘%s ready to eat‘ %(name))
    foog_list=[]
    while True:
        food=yield foog_list
        print(‘%s start to eat %s‘ %(name,food))
        foog_list.append(food)

print(eater(‘alex‘).send(‘熊掌‘))
print(eater(‘alex‘).send(‘烧鸡‘))
print(eater(‘alex‘).send(‘烧鹅‘))
print(eater(‘alex‘).send(‘烤鸭‘))

#题目四：
import os
def init(func):
    def wrapper(*args,**kwargs):
        g=func(*args,**kwargs)
        next(g)
        return g
    return wrapper
#阶段一：递归地找文件的绝对路径，把路径发给阶段二
@init
def search(target):
    ‘search file abspath‘
    while True:
        start_path=yield
        g = os.walk(start_path)
        for par_dir, _, files in g:
            # print(par_dir,files)
            for file in files:
                file_path = r‘%s\%s‘ % (par_dir, file)
                target.send(file_path)
#阶段二：收到文件路径，打开文件获取获取对象，把文件对象发给阶段三
@init
def opener(target):
    ‘get file obj: f=open(filepath)‘
    while True:
        file_path=yield
        with open(file_path,encoding=‘utf-8‘) as f:
            target.send((file_path,f))

#阶段三：收到文件对象，for循环读取文件的每一行内容，把每一行内容发给阶段四
@init
def cat(target):
    ‘read file‘
    while True:
        filepath,f=yield
        for line in f:
            res=target.send((filepath,line))
            if res:
                break

#阶段四：收到一行内容，判断root是否在这一行中，如果在，则把文件名发给阶段五
@init
def grep(target,pattern):
    ‘grep function‘
    tag=False
    while True:
        filepath,line=yield tag #target.send((filepath,line))
        tag=False
        if pattern in line:
            target.send(filepath)
            tag=True
#阶段五：收到文件名，打印结果
@init
def printer():
    ‘print function‘
    while True:
        filename=yield
        print(filename)

start_path1=r‘C:\Users\Administrator\PycharmProjects\python5期\a‘
start_path2=r‘C:\Users\Administrator\PycharmProjects\python5期\a\b‘
g=search(opener(cat(grep(printer(),‘root‘))))

print(g)
# g.send(start_path1)
g.send(start_path2)