Guia de geradores e iteradores Python 2026: rendimento, envio e pipelines

# Any object with __iter__ and __next__ is an iterator
class CountDown:
    def __init__(self, start: int):
        self.current = start

    def __iter__(self):
        return self  # iterator returns itself

    def __next__(self):
        if self.current <= 0:
            raise StopIteration
        value = self.current
        self.current -= 1
        return value

# Usage
for n in CountDown(5):
    print(n)  # 5, 4, 3, 2, 1

# Python's for loop is syntactic sugar for:
# it = iter(countdown)
# while True:
#     try: n = next(it)
#     except StopIteration: break
#     print(n)

from typing import Generator, Iterator

# Generator function — uses yield instead of return
def count_down(start: int) -> Generator[int, None, None]:
    while start > 0:
        yield start
        start -= 1

for n in count_down(5):
    print(n)

# Generator expression (like list comprehension but lazy)
squares_gen = (x ** 2 for x in range(1_000_000))  # doesn't compute all at once
first_ten = list(squares_gen)[:10]

# vs list comprehension (computes everything immediately)
squares_list = [x ** 2 for x in range(1_000_000)]  # uses ~8MB memory!

# Memory comparison
import sys
gen = (x ** 2 for x in range(1_000_000))
lst = [x ** 2 for x in range(1_000_000)]
print(sys.getsizeof(gen))   # ~200 bytes
print(sys.getsizeof(lst))   # ~8MB

from itertools import islice

def fibonacci() -> Generator[int, None, None]:
    a, b = 0, 1
    while True:  # infinite!
        yield a
        a, b = b, a + b

def primes() -> Generator[int, None, None]:
    def is_prime(n: int) -> bool:
        if n < 2: return False
        return all(n % i != 0 for i in range(2, int(n**0.5) + 1))

    n = 2
    while True:
        if is_prime(n):
            yield n
        n += 1

# Take first N from infinite generator
first_10_fibs = list(islice(fibonacci(), 10))
first_20_primes = list(islice(primes(), 20))

print(first_10_fibs)
print(first_20_primes)

import csv
from pathlib import Path

def read_large_csv(filepath: str) -> Generator[dict, None, None]:
    with open(filepath, newline='') as f:
        reader = csv.DictReader(f)
        for row in reader:
            yield row

def filter_rows(rows, **criteria) -> Generator[dict, None, None]:
    for row in rows:
        if all(row.get(k) == v for k, v in criteria.items()):
            yield row

def transform(rows, **transforms) -> Generator[dict, None, None]:
    for row in rows:
        transformed = {**row}
        for key, func in transforms.items():
            transformed[key] = func(row[key])
        yield transformed

def batch(rows, size: int = 100) -> Generator[list, None, None]:
    batch_data = []
    for row in rows:
        batch_data.append(row)
        if len(batch_data) >= size:
            yield batch_data
            batch_data = []
    if batch_data:
        yield batch_data

# Pipeline processes 10GB file with constant memory
pipeline = (
    read_large_csv("10gb_sales.csv")
    |> filter_rows(status="completed", year="2026")
    |> transform(amount=float, quantity=int)
    |> batch(size=1000)
)

# Actually in Python:
rows = read_large_csv("10gb_sales.csv")
filtered = filter_rows(rows, status="completed")
transformed = transform(filtered, amount=float)
batches = batch(transformed, size=1000)

for batch_data in batches:
    db.bulk_insert("sales", batch_data)
    print(f"Inserted {len(batch_data)} rows")

def flatten(nested) -> Generator:
    for item in nested:
        if isinstance(item, (list, tuple)):
            yield from flatten(item)  # delegate to sub-generator
        else:
            yield item

nested = [1, [2, 3, [4, 5]], 6, [[7]]]
print(list(flatten(nested)))  # [1, 2, 3, 4, 5, 6, 7]

# Combine multiple generators
def chain(*iterables) -> Generator:
    for it in iterables:
        yield from it

combined = chain(range(3), range(5, 8), "abc")
print(list(combined))  # [0, 1, 2, 5, 6, 7, 'a', 'b', 'c']

def running_average() -> Generator[float, float, None]:
    total = 0.0
    count = 0
    average = 0.0
    while True:
        value = yield average  # yield current average, receive new value
        if value is None:
            break
        total += value
        count += 1
        average = total / count

gen = running_average()
next(gen)  # prime the generator (advance to first yield)

print(gen.send(10))   # 10.0
print(gen.send(20))   # 15.0
print(gen.send(30))   # 20.0
print(gen.send(40))   # 25.0

import asyncio
import httpx

async def fetch_pages(urls: list[str]) -> AsyncGenerator[dict, None]:
    async with httpx.AsyncClient() as client:
        for url in urls:
            r = await client.get(url)
            yield {"url": url, "status": r.status_code, "data": r.json()}

async def main():
    urls = ["https://api.example.com/page/1",
            "https://api.example.com/page/2",
            "https://api.example.com/page/3"]

    async for page in fetch_pages(urls):
        print(f"Fetched {page['url']}: {page['status']}")
        process(page['data'])

asyncio.run(main())

# Async generator expression
squares = (x ** 2 async for x in async_range(100))

from itertools import (
    count, cycle, repeat,      # infinite
    chain, islice, takewhile,  # finite
    groupby, product,          # combinatorics
    accumulate, starmap        # transforms
)

# Infinite counter
for i in islice(count(10, 2), 5):
    print(i)  # 10, 12, 14, 16, 18

# Group consecutive elements
data = [{"date": "2026-01", "v": 10}, {"date": "2026-01", "v": 20},
        {"date": "2026-02", "v": 30}]
for month, rows in groupby(data, key=lambda x: x["date"]):
    total = sum(r["v"] for r in rows)
    print(f"{month}: {total}")

# Running total
sales = [100, 200, 150, 300, 250]
running = list(accumulate(sales))  # [100, 300, 450, 750, 1000]

# Cartesian product
for size, color in product(["S","M","L"], ["red","blue"]):
    print(f"{size}-{color}")