我写了一个基于http://www.codinghorror.com/blog/2007/12/sorting-for-humans-natural-sort-order.html的函数，它增加了传递自己的“键”参数的能力。我需要这样才能执行包含更复杂对象(不仅仅是字符串)的列表的自然排序。

import re

def natural_sort(list, key=lambda s:s):
    """
    Sort the list into natural alphanumeric order.
    """
    def get_alphanum_key_func(key):
        convert = lambda text: int(text) if text.isdigit() else text 
        return lambda s: [convert(c) for c in re.split('([0-9]+)', key(s))]
    sort_key = get_alphanum_key_func(key)
    list.sort(key=sort_key)

例如:

my_list = [{'name':'b'}, {'name':'10'}, {'name':'a'}, {'name':'1'}, {'name':'9'}]
natural_sort(my_list, key=lambda x: x['name'])
print my_list
[{'name': '1'}, {'name': '9'}, {'name': '10'}, {'name': 'a'}, {'name': 'b'}]

下面是马克·拜尔回答的一个更加python化的版本:

import re

def natural_sort_key(s, _nsre=re.compile('([0-9]+)')):
    return [int(text) if text.isdigit() else text.lower()
            for text in _nsre.split(s)]

现在这个函数可以在任何使用它的函数中用作键，比如list。Sort, sorted, max，等等。

作为lambda:

lambda s: [int(t) if t.isdigit() else t.lower() for t in re.split('(\d+)', s)]

完全可重复的演示代码:

import re
natsort = lambda s: [int(t) if t.isdigit() else t.lower() for t in re.split('(\d+)', s)]
L = ["a1", "a10", "a11", "a2", "a22", "a3"]   
print(sorted(L, key=natsort))  
# ['a1', 'a2', 'a3', 'a10', 'a11', 'a22'] 

现在是一些更优雅的东西(pythonic)

-只要碰一下

有很多实现，虽然有些已经接近，但没有一个能完全捕获现代python所提供的优雅。

使用python测试(3.5.1) 包含了一个额外的列表，以演示当 数字在字符串中间 没有测试，但是，我假设如果您的列表是相当大的，那么事先编译正则表达式会更有效 如果这是一个错误的假设，我相信有人会纠正我

罢工

from re import compile, split    
dre = compile(r'(\d+)')
mylist.sort(key=lambda l: [int(s) if s.isdigit() else s.lower() for s in split(dre, l)])

完整代码

#!/usr/bin/python3
# coding=utf-8
"""
Natural-Sort Test
"""

from re import compile, split

dre = compile(r'(\d+)')
mylist = ['elm0', 'elm1', 'Elm2', 'elm9', 'elm10', 'Elm11', 'Elm12', 'elm13', 'elm']
mylist2 = ['e0lm', 'e1lm', 'E2lm', 'e9lm', 'e10lm', 'E12lm', 'e13lm', 'elm', 'e01lm']

mylist.sort(key=lambda l: [int(s) if s.isdigit() else s.lower() for s in split(dre, l)])
mylist2.sort(key=lambda l: [int(s) if s.isdigit() else s.lower() for s in split(dre, l)])

print(mylist)  
  # ['elm', 'elm0', 'elm1', 'Elm2', 'elm9', 'elm10', 'Elm11', 'Elm12', 'elm13']
print(mylist2)  
  # ['e0lm', 'e1lm', 'e01lm', 'E2lm', 'e9lm', 'e10lm', 'E12lm', 'e13lm', 'elm']

使用时注意

从操作系统。路径导入分割 您需要区分导入

灵感来自

Python文档-如何排序 人类排序:自然排序顺序 人的分类 这篇文章的贡献者/评论员和引用帖子

克劳狄对马克·拜尔斯的回答的改进;-)

import re

def natural_sort_key(s, _re=re.compile(r'(\d+)')):
    return [int(t) if i & 1 else t.lower() for i, t in enumerate(_re.split(s))]

...
my_naturally_sorted_list = sorted(my_list, key=natural_sort_key)

顺便说一句，也许不是每个人都记得函数参数默认值是在def时求值的

一个紧凑的解决方案，基于将字符串转换为List[Tuple(str, int)]。

Code

def string_to_pairs(s, pairs=re.compile(r"(\D*)(\d*)").findall):
    return [(text.lower(), int(digits or 0)) for (text, digits) in pairs(s)[:-1]]

示范

sorted(['Elm11', 'Elm12', 'Elm2', 'elm0', 'elm1', 'elm10', 'elm13', 'elm9'], key=string_to_pairs)

输出:

['elm0', 'elm1', 'Elm2', 'elm9', 'elm10', 'Elm11', 'Elm12', 'elm13']

测试

转换

assert string_to_pairs("") == []
assert string_to_pairs("123") == [("", 123)]
assert string_to_pairs("abc") == [("abc", 0)]
assert string_to_pairs("123abc") == [("", 123), ("abc", 0)]
assert string_to_pairs("abc123") == [("abc", 123)]
assert string_to_pairs("123abc456") == [("", 123), ("abc", 456)]
assert string_to_pairs("abc123efg") == [("abc", 123), ("efg", 0)]

排序

# Some extracts from the test suite of the natsort library. Permalink:
# https://github.com/SethMMorton/natsort/blob/e3c32f5638bf3a0e9a23633495269bea0e75d379/tests/test_natsorted.py

sort_data = [
    (  # same as test_natsorted_can_sort_as_unsigned_ints_which_is_default()
        ["a50", "a51.", "a50.31", "a-50", "a50.4", "a5.034e1", "a50.300"],
        ["a5.034e1", "a50", "a50.4", "a50.31", "a50.300", "a51.", "a-50"],
    ),
    (  # same as test_natsorted_numbers_in_ascending_order()
        ["a2", "a5", "a9", "a1", "a4", "a10", "a6"],
        ["a1", "a2", "a4", "a5", "a6", "a9", "a10"],
    ),
    (  # same as test_natsorted_can_sort_as_version_numbers()
        ["1.9.9a", "1.11", "1.9.9b", "1.11.4", "1.10.1"],
        ["1.9.9a", "1.9.9b", "1.10.1", "1.11", "1.11.4"],
    ),
    (  # different from test_natsorted_handles_filesystem_paths()
        [
            "/p/Folder (10)/file.tar.gz",
            "/p/Folder (1)/file (1).tar.gz",
            "/p/Folder/file.x1.9.tar.gz",
            "/p/Folder (1)/file.tar.gz",
            "/p/Folder/file.x1.10.tar.gz",
        ],
        [
            "/p/Folder (1)/file (1).tar.gz",
            "/p/Folder (1)/file.tar.gz",
            "/p/Folder (10)/file.tar.gz",
            "/p/Folder/file.x1.9.tar.gz",
            "/p/Folder/file.x1.10.tar.gz",
        ],
    ),
    (  # same as test_natsorted_path_extensions_heuristic()
        [
            "Try.Me.Bug - 09 - One.Two.Three.[text].mkv",
            "Try.Me.Bug - 07 - One.Two.5.[text].mkv",
            "Try.Me.Bug - 08 - One.Two.Three[text].mkv",
        ],
        [
            "Try.Me.Bug - 07 - One.Two.5.[text].mkv",
            "Try.Me.Bug - 08 - One.Two.Three[text].mkv",
            "Try.Me.Bug - 09 - One.Two.Three.[text].mkv",
        ],
    ),
    (  # same as ns.IGNORECASE for test_natsorted_supports_case_handling()
        ["Apple", "corn", "Corn", "Banana", "apple", "banana"],
        ["Apple", "apple", "Banana", "banana", "corn", "Corn"],
    ),

]

for (given, expected) in sort_data:
    assert sorted(given, key=string_to_pairs) == expected

奖金

如果字符串混合了非ascii文本和数字，您可能会对将string_to_pairs()与我在其他地方给出的函数remove_diacritics()组合感兴趣。

一种选择是将字符串转换为元组，并使用展开形式http://wiki.answers.com/Q/What_does_expanded_form_mean替换数字

这样a90就会变成("a"，90,0)而a1就会变成("a"，1)

下面是一些示例代码(这不是很有效，因为它从数字中删除前导0的方式)

alist=["something1",
    "something12",
    "something17",
    "something2",
    "something25and_then_33",
    "something25and_then_34",
    "something29",
    "beta1.1",
    "beta2.3.0",
    "beta2.33.1",
    "a001",
    "a2",
    "z002",
    "z1"]

def key(k):
    nums=set(list("0123456789"))
        chars=set(list(k))
    chars=chars-nums
    for i in range(len(k)):
        for c in chars:
            k=k.replace(c+"0",c)
    l=list(k)
    base=10
    j=0
    for i in range(len(l)-1,-1,-1):
        try:
            l[i]=int(l[i])*base**j
            j+=1
        except:
            j=0
    l=tuple(l)
    print l
    return l

print sorted(alist,key=key)

输出:

('s', 'o', 'm', 'e', 't', 'h', 'i', 'n', 'g', 1)
('s', 'o', 'm', 'e', 't', 'h', 'i', 'n', 'g', 10, 2)
('s', 'o', 'm', 'e', 't', 'h', 'i', 'n', 'g', 10, 7)
('s', 'o', 'm', 'e', 't', 'h', 'i', 'n', 'g', 2)
('s', 'o', 'm', 'e', 't', 'h', 'i', 'n', 'g', 20, 5, 'a', 'n', 'd', '_', 't', 'h', 'e', 'n', '_', 30, 3)
('s', 'o', 'm', 'e', 't', 'h', 'i', 'n', 'g', 20, 5, 'a', 'n', 'd', '_', 't', 'h', 'e', 'n', '_', 30, 4)
('s', 'o', 'm', 'e', 't', 'h', 'i', 'n', 'g', 20, 9)
('b', 'e', 't', 'a', 1, '.', 1)
('b', 'e', 't', 'a', 2, '.', 3, '.')
('b', 'e', 't', 'a', 2, '.', 30, 3, '.', 1)
('a', 1)
('a', 2)
('z', 2)
('z', 1)
['a001', 'a2', 'beta1.1', 'beta2.3.0', 'beta2.33.1', 'something1', 'something2', 'something12', 'something17', 'something25and_then_33', 'something25and_then_34', 'something29', 'z1', 'z002']