我有一个字符串列表，我想执行一个自然的字母排序。
例如，下面的列表是自然排序(我想要的):
['elm0', 'elm1', 'Elm2', 'elm9', 'elm10', 'Elm11', 'Elm12', 'elm13']
下面是上面列表的“排序”版本(我使用sorted()得到的):
['Elm11', 'Elm12', 'Elm2', 'elm0', 'elm1', 'elm10', 'elm13', 'elm9']
我在寻找一个排序函数它的行为和第一个一样。
当前回答
我使用的算法是padzero_with_lower，定义如下:
import re
def padzero_with_lower(s):
return re.sub(r'\d+', lambda m: m.group(0).rjust(10, '0'), s).lower()
该算法发现:
查找并填充任意长度的数字，直到足够大的长度，例如10 然后，它将字符串转换为小写
下面是一个用法示例:
print(padzero_with_lower('file1.txt')) # file0000000001.txt
print(padzero_with_lower('file12.txt')) # file0000000012.txt
print(padzero_with_lower('file23.txt')) # file0000000023.txt
print(padzero_with_lower('file123.txt')) # file0000000123.txt
print(padzero_with_lower('file301.txt')) # file0000000301.txt
print(padzero_with_lower('Dir2/file15.txt')) # dir0000000002/file0000000015.txt
print(padzero_with_lower('dir2/file123.txt')) # dir0000000002/file0000000123.txt
print(padzero_with_lower('dir15/file2.txt')) # dir0000000015/file0000000002.txt
print(padzero_with_lower('Dir15/file15.txt')) # dir0000000015/file0000000015.txt
print(padzero_with_lower('elm0')) # elm0000000000
print(padzero_with_lower('elm1')) # elm0000000001
print(padzero_with_lower('Elm2')) # elm0000000002
print(padzero_with_lower('elm9')) # elm0000000009
print(padzero_with_lower('elm10')) # elm0000000010
print(padzero_with_lower('Elm11')) # elm0000000011
print(padzero_with_lower('Elm12')) # elm0000000012
print(padzero_with_lower('elm13')) # elm0000000013
测试了这个函数后，我们现在可以使用它作为我们的键。
lis = ['elm0', 'elm1', 'Elm2', 'elm9', 'elm10', 'Elm11', 'Elm12', 'elm13']
lis.sort(key=padzero_with_lower)
print(lis)
# Output: ['elm0', 'elm1', 'Elm2', 'elm9', 'elm10', 'Elm11', 'Elm12', 'elm13']
其他回答
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
很可能functools.cmp_to_key()与python的sort的底层实现密切相关。此外，cmp参数是遗留的。现代的方法是将输入项转换为支持所需的丰富比较操作的对象。
在CPython 2下。X，即使没有实现各自的富比较操作符，也可以对不同类型的对象排序。在CPython 3下。X，不同类型的对象必须显式地支持比较。参见Python如何比较字符串和int?链接到官方文件。大多数答案都依赖于这种隐含的顺序。切换到Python 3。X将需要一个新的类型来实现和统一数字和字符串之间的比较。
Python 2.7.12 (default, Sep 29 2016, 13:30:34)
>>> (0,"foo") < ("foo",0)
True
Python 3.5.2 (default, Oct 14 2016, 12:54:53)
>>> (0,"foo") < ("foo",0)
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
TypeError: unorderable types: int() < str()
有三种不同的方法。第一种使用嵌套类来利用Python的Iterable比较算法。第二个函数将这个嵌套展开到单个类中。第三种方法放弃了str的子类化，专注于性能。所有都是有时间的;第二辆快了一倍，第三辆快了近六倍。对str进行子类化并不是必需的，而且首先可能是一个坏主意，但它确实带来了某些便利。
排序字符被复制以强制按大小写排序，并交换大小写以强制小写字母优先排序;这就是“自然排序”的典型定义。我无法决定分组的类型;有些人可能更喜欢以下选项，这也会带来显著的性能优势:
d = lambda s: s.lower()+s.swapcase()
在使用的地方，比较运算符被设置为object的运算符，这样它们就不会被functools. total_orders忽略。
import functools
import itertools
@functools.total_ordering
class NaturalStringA(str):
def __repr__(self):
return "{}({})".format\
( type(self).__name__
, super().__repr__()
)
d = lambda c, s: [ c.NaturalStringPart("".join(v))
for k,v in
itertools.groupby(s, c.isdigit)
]
d = classmethod(d)
@functools.total_ordering
class NaturalStringPart(str):
d = lambda s: "".join(c.lower()+c.swapcase() for c in s)
d = staticmethod(d)
def __lt__(self, other):
if not isinstance(self, type(other)):
return NotImplemented
try:
return int(self) < int(other)
except ValueError:
if self.isdigit():
return True
elif other.isdigit():
return False
else:
return self.d(self) < self.d(other)
def __eq__(self, other):
if not isinstance(self, type(other)):
return NotImplemented
try:
return int(self) == int(other)
except ValueError:
if self.isdigit() or other.isdigit():
return False
else:
return self.d(self) == self.d(other)
__le__ = object.__le__
__ne__ = object.__ne__
__gt__ = object.__gt__
__ge__ = object.__ge__
def __lt__(self, other):
return self.d(self) < self.d(other)
def __eq__(self, other):
return self.d(self) == self.d(other)
__le__ = object.__le__
__ne__ = object.__ne__
__gt__ = object.__gt__
__ge__ = object.__ge__
import functools
import itertools
@functools.total_ordering
class NaturalStringB(str):
def __repr__(self):
return "{}({})".format\
( type(self).__name__
, super().__repr__()
)
d = lambda s: "".join(c.lower()+c.swapcase() for c in s)
d = staticmethod(d)
def __lt__(self, other):
if not isinstance(self, type(other)):
return NotImplemented
groups = map(lambda i: itertools.groupby(i, type(self).isdigit), (self, other))
zipped = itertools.zip_longest(*groups)
for s,o in zipped:
if s is None:
return True
if o is None:
return False
s_k, s_v = s[0], "".join(s[1])
o_k, o_v = o[0], "".join(o[1])
if s_k and o_k:
s_v, o_v = int(s_v), int(o_v)
if s_v == o_v:
continue
return s_v < o_v
elif s_k:
return True
elif o_k:
return False
else:
s_v, o_v = self.d(s_v), self.d(o_v)
if s_v == o_v:
continue
return s_v < o_v
return False
def __eq__(self, other):
if not isinstance(self, type(other)):
return NotImplemented
groups = map(lambda i: itertools.groupby(i, type(self).isdigit), (self, other))
zipped = itertools.zip_longest(*groups)
for s,o in zipped:
if s is None or o is None:
return False
s_k, s_v = s[0], "".join(s[1])
o_k, o_v = o[0], "".join(o[1])
if s_k and o_k:
s_v, o_v = int(s_v), int(o_v)
if s_v == o_v:
continue
return False
elif s_k or o_k:
return False
else:
s_v, o_v = self.d(s_v), self.d(o_v)
if s_v == o_v:
continue
return False
return True
__le__ = object.__le__
__ne__ = object.__ne__
__gt__ = object.__gt__
__ge__ = object.__ge__
import functools
import itertools
import enum
class OrderingType(enum.Enum):
PerWordSwapCase = lambda s: s.lower()+s.swapcase()
PerCharacterSwapCase = lambda s: "".join(c.lower()+c.swapcase() for c in s)
class NaturalOrdering:
@classmethod
def by(cls, ordering):
def wrapper(string):
return cls(string, ordering)
return wrapper
def __init__(self, string, ordering=OrderingType.PerCharacterSwapCase):
self.string = string
self.groups = [ (k,int("".join(v)))
if k else
(k,ordering("".join(v)))
for k,v in
itertools.groupby(string, str.isdigit)
]
def __repr__(self):
return "{}({})".format\
( type(self).__name__
, self.string
)
def __lesser(self, other, default):
if not isinstance(self, type(other)):
return NotImplemented
for s,o in itertools.zip_longest(self.groups, other.groups):
if s is None:
return True
if o is None:
return False
s_k, s_v = s
o_k, o_v = o
if s_k and o_k:
if s_v == o_v:
continue
return s_v < o_v
elif s_k:
return True
elif o_k:
return False
else:
if s_v == o_v:
continue
return s_v < o_v
return default
def __lt__(self, other):
return self.__lesser(other, default=False)
def __le__(self, other):
return self.__lesser(other, default=True)
def __eq__(self, other):
if not isinstance(self, type(other)):
return NotImplemented
for s,o in itertools.zip_longest(self.groups, other.groups):
if s is None or o is None:
return False
s_k, s_v = s
o_k, o_v = o
if s_k and o_k:
if s_v == o_v:
continue
return False
elif s_k or o_k:
return False
else:
if s_v == o_v:
continue
return False
return True
# functools.total_ordering doesn't create single-call wrappers if both
# __le__ and __lt__ exist, so do it manually.
def __gt__(self, other):
op_result = self.__le__(other)
if op_result is NotImplemented:
return op_result
return not op_result
def __ge__(self, other):
op_result = self.__lt__(other)
if op_result is NotImplemented:
return op_result
return not op_result
# __ne__ is the only implied ordering relationship, it automatically
# delegates to __eq__
>>> import natsort
>>> import timeit
>>> l1 = ['Apple', 'corn', 'apPlE', 'arbour', 'Corn', 'Banana', 'apple', 'banana']
>>> l2 = list(map(str, range(30)))
>>> l3 = ["{} {}".format(x,y) for x in l1 for y in l2]
>>> print(timeit.timeit('sorted(l3+["0"], key=NaturalStringA)', number=10000, globals=globals()))
362.4729259099986
>>> print(timeit.timeit('sorted(l3+["0"], key=NaturalStringB)', number=10000, globals=globals()))
189.7340817489967
>>> print(timeit.timeit('sorted(l3+["0"], key=NaturalOrdering.by(OrderingType.PerCharacterSwapCase))', number=10000, globals=globals()))
69.34636392899847
>>> print(timeit.timeit('natsort.natsorted(l3+["0"], alg=natsort.ns.GROUPLETTERS | natsort.ns.LOWERCASEFIRST)', number=10000, globals=globals()))
98.2531585780016
自然排序既相当复杂，又定义模糊。不要忘记事先运行unicodedata.normalize(…)，并考虑使用str.casefold()而不是str.lower()。可能有一些微妙的编码问题我还没有考虑到。因此，我尝试性地推荐natsort库。我快速浏览了一下github存储库;代码维护非常出色。
All the algorithms I've seen depend on tricks such as duplicating and lowering characters, and swapping case. While this doubles the running time, an alternative would require a total natural ordering on the input character set. I don't think this is part of the unicode specification, and since there are many more unicode digits than [0-9], creating such a sorting would be equally daunting. If you want locale-aware comparisons, prepare your strings with locale.strxfrm per Python's Sorting HOW TO.
试试这个:
import re
def natural_sort(l):
convert = lambda text: int(text) if text.isdigit() else text.lower()
alphanum_key = lambda key: [convert(c) for c in re.split('([0-9]+)', key)]
return sorted(l, key=alphanum_key)
输出:
['elm0', 'elm1', 'Elm2', 'elm9', 'elm10', 'Elm11', 'Elm12', 'elm13']
代码改编自这里:排序人类:自然排序顺序。
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。
>>> import re
>>> sorted(lst, key=lambda x: int(re.findall(r'\d+$', x)[0]))
['elm0', 'elm1', 'Elm2', 'elm9', 'elm10', 'Elm11', 'Elm12', 'elm13']
