我正在为Web应用程序编写一个日志文件查看器,为此我想通过日志文件的行分页.文件中的项目是基于行的,底部是最新项目.
所以我需要一种tail()方法,可以n从底部读取行并支持偏移量.我想出的是这样的:
def tail(f, n, offset=0):
"""Reads a n lines from f with an offset of offset lines."""
avg_line_length = 74
to_read = n + offset
while 1:
try:
f.seek(-(avg_line_length * to_read), 2)
except IOError:
# woops. apparently file is smaller than what we want
# to step back, go to the beginning instead
f.seek(0)
pos = f.tell()
lines = f.read().splitlines()
if len(lines) >= to_read or pos == 0:
return lines[-to_read:offset and -offset or None]
avg_line_length *= 1.3
这是一种合理的方法吗？使用偏移量尾部日志文件的推荐方法是什么？
这可能比你的更快.不对线长做出假设.一次一个块地返回文件,直到找到正确数量的'\n'字符.
def tail( f, lines=20 ):
total_lines_wanted = lines
BLOCK_SIZE = 1024
f.seek(0, 2)
block_end_byte = f.tell()
lines_to_go = total_lines_wanted
block_number = -1
blocks = [] # blocks of size BLOCK_SIZE, in reverse order starting
# from the end of the file
while lines_to_go > 0 and block_end_byte > 0:
if (block_end_byte - BLOCK_SIZE > 0):
# read the last block we haven't yet read
f.seek(block_number*BLOCK_SIZE, 2)
blocks.append(f.read(BLOCK_SIZE))
else:
# file too small, start from begining
f.seek(0,0)
# only read what was not read
blocks.append(f.read(block_end_byte))
lines_found = blocks[-1].count('\n')
lines_to_go -= lines_found
block_end_byte -= BLOCK_SIZE
block_number -= 1
all_read_text = ''.join(reversed(blocks))
return '\n'.join(all_read_text.splitlines()[-total_lines_wanted:])
我不喜欢关于线长的棘手假设 - 作为一个实际问题 - 你永远不会知道这样的事情.
通常,这将在第一次或第二次通过循环时找到最后20行.如果你的74个角色实际上是准确的,你可以使块大小为2048,你几乎可以立即尾随20行.
此外,我没有燃烧大量的脑热量,试图巧妙地与物理OS块对齐.使用这些高级I/O包,我怀疑你会看到尝试在OS块边界上对齐的任何性能后果.如果您使用较低级别的I/O,那么您可能会看到加速.
假设你可以在Python 2上使用类似unix的系统:
import os
def tail(f, n, offset=0):
stdin,stdout = os.popen2("tail -n "+n+offset+" "+f)
stdin.close()
lines = stdout.readlines(); stdout.close()
return lines[:,-offset]
对于python 3,您可以这样做:
import subprocess
def tail(f, n, offset=0):
proc = subprocess.Popen(['tail', '-n', n + offset, f], stdout=subprocess.PIPE)
lines = proc.stdout.readlines()
return lines[:, -offset]
如果读取整个文件是可以接受的,那么使用双端队列.
from collections import deque deque(f, maxlen=n)
在2.6之前,deques没有maxlen选项,但它很容易实现.
import itertools
def maxque(items, size):
items = iter(items)
q = deque(itertools.islice(items, size))
for item in items:
del q[0]
q.append(item)
return q
如果要求从最后读取文件,则使用驰骋(又称指数)搜索.
def tail(f, n):
assert n >= 0
pos, lines = n+1, []
while len(lines) <= n:
try:
f.seek(-pos, 2)
except IOError:
f.seek(0)
break
finally:
lines = list(f)
pos *= 2
return lines[-n:]
这是我的答案.纯蟒蛇.使用timeit似乎很快.拖尾100行有100,000行的日志文件:
>>> timeit.timeit('tail.tail(f, 100, 4098)', 'import tail; f = open("log.txt", "r");', number=10)
0.0014600753784179688
>>> timeit.timeit('tail.tail(f, 100, 4098)', 'import tail; f = open("log.txt", "r");', number=100)
0.00899195671081543
>>> timeit.timeit('tail.tail(f, 100, 4098)', 'import tail; f = open("log.txt", "r");', number=1000)
0.05842900276184082
>>> timeit.timeit('tail.tail(f, 100, 4098)', 'import tail; f = open("log.txt", "r");', number=10000)
0.5394978523254395
>>> timeit.timeit('tail.tail(f, 100, 4098)', 'import tail; f = open("log.txt", "r");', number=100000)
5.377126932144165
这是代码:
import os
def tail(f, lines=1, _buffer=4098):
"""Tail a file and get X lines from the end"""
# place holder for the lines found
lines_found = []
# block counter will be multiplied by buffer
# to get the block size from the end
block_counter = -1
# loop until we find X lines
while len(lines_found) < lines:
try:
f.seek(block_counter * _buffer, os.SEEK_END)
except IOError: # either file is too small, or too many lines requested
f.seek(0)
lines_found = f.readlines()
break
lines_found = f.readlines()
# we found enough lines, get out
# Removed this line because it was redundant the while will catch
# it, I left it for history
# if len(lines_found) > lines:
# break
# decrement the block counter to get the
# next X bytes
block_counter -= 1
return lines_found[-lines:]
S.Lott上面的答案几乎对我有用,但最终给了我部分线条.事实证明它破坏了块边界上的数据,因为数据以相反的顺序保持读取块.当调用'.join(数据)时,块的顺序错误.这解决了这个问题.
def tail(f, window=20):
"""
Returns the last `window` lines of file `f` as a list.
f - a byte file-like object
"""
if window == 0:
return []
BUFSIZ = 1024
f.seek(0, 2)
bytes = f.tell()
size = window + 1
block = -1
data = []
while size > 0 and bytes > 0:
if bytes - BUFSIZ > 0:
# Seek back one whole BUFSIZ
f.seek(block * BUFSIZ, 2)
# read BUFFER
data.insert(0, f.read(BUFSIZ))
else:
# file too small, start from begining
f.seek(0,0)
# only read what was not read
data.insert(0, f.read(bytes))
linesFound = data[0].count('\n')
size -= linesFound
bytes -= BUFSIZ
block -= 1
return ''.join(data).splitlines()[-window:]
我最终使用的代码.我认为这是迄今为止最好的:
def tail(f, n, offset=None):
"""Reads a n lines from f with an offset of offset lines. The return
value is a tuple in the form ``(lines, has_more)`` where `has_more` is
an indicator that is `True` if there are more lines in the file.
"""
avg_line_length = 74
to_read = n + (offset or 0)
while 1:
try:
f.seek(-(avg_line_length * to_read), 2)
except IOError:
# woops. apparently file is smaller than what we want
# to step back, go to the beginning instead
f.seek(0)
pos = f.tell()
lines = f.read().splitlines()
if len(lines) >= to_read or pos == 0:
return lines[-to_read:offset and -offset or None], \
len(lines) > to_read or pos > 0
avg_line_length *= 1.3
使用mmap简单快速的解决方案:
import mmap
import os
def tail(filename, n):
"""Returns last n lines from the filename. No exception handling"""
size = os.path.getsize(filename)
with open(filename, "rb") as f:
# for Windows the mmap parameters are different
fm = mmap.mmap(f.fileno(), 0, mmap.MAP_SHARED, mmap.PROT_READ)
try:
for i in xrange(size - 1, -1, -1):
if fm[i] == '\n':
n -= 1
if n == -1:
break
return fm[i + 1 if i else 0:].splitlines()
finally:
fm.close()
京公网安备 11010802040832号 | 京ICP备19059560号-6 