Python计算大文件行数方法及性能比较

1
2

def readline_count(file_name):
    return len(open(file_name).readlines())

1
2
3
4
5

def simple_count(file_name):
    lines = 0
    for _ in open(file_name):
        lines += 1
    return lines

1
2

def sum_count(file_name):
    return sum(1 for _ in open(file_name))

1
2
3
4
5

def enumerate_count(file_name):
    with open(file_name) as f:
        for count, _ in enumerate(f, 1):
            pass
    return count

1
2
3
4
5
6
7
8
9

def buff_count(file_name):
    with open(file_name, 'rb') as f:
        count = 0
        buf_size = 1024 * 1024
        buf = f.read(buf_size)
        while buf:
            count += buf.count(b'\n')
            buf = f.read(buf_size)
        return count

1
2
3
4

def wc_count(file_name):
    import subprocess
    out = subprocess.getoutput("wc -l %s" % file_name)
    return int(out.split()[0])

1
2
3
4
5

def partial_count(file_name):
    from functools import partial
    buffer = 1024 * 1024
    with open(file_name) as f:
        return sum(x.count('\n') for x in iter(partial(f.read, buffer), ''))

1
2
3
4
5
6

def iter_count(file_name):
    from itertools import (takewhile, repeat)
    buffer = 1024 * 1024
    with open(file_name) as f:
        buf_gen = takewhile(lambda x: x, (f.read(buffer) for _ in repeat(None)))
        return sum(buf.count('\n') for buf in buf_gen)