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)
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)
假设一个流行的请求/问题是“如何像Windows资源管理器那样排序?”(或者不管你的操作系统的文件系统浏览器是什么)，从natsort version 7.1.0开始，就有一个名为os_sorted的函数来做这件事。在Windows上，它将按照与Windows资源管理器相同的顺序进行排序，而在其他操作系统上，它应该像本地文件系统浏览器一样进行排序。
>>> from natsort import os_sorted
>>> os_sorted(list_of_paths)
# your paths sorted like your file system browser
def natural_sort_key(string_or_number):
"""
by Scott S. Lawton <scott@ProductArchitect.com> 2014-12-11; public domain and/or CC0 license
handles cases where simple 'int' approach fails, e.g.
['0.501', '0.55'] floating point with different number of significant digits
[0.01, 0.1, 1] already numeric so regex and other string functions won't work (and aren't required)
['elm1', 'Elm2'] ASCII vs. letters (not case sensitive)
"""
def try_float(astring):
try:
return float(astring)
except:
return astring
if isinstance(string_or_number, basestring):
string_or_number = string_or_number.lower()
if len(re.findall('[.]\d', string_or_number)) <= 1:
# assume a floating point value, e.g. to correctly sort ['0.501', '0.55']
# '.' for decimal is locale-specific, e.g. correct for the Anglosphere and Asia but not continental Europe
return [try_float(s) for s in re.split(r'([\d.]+)', string_or_number)]
else:
# assume distinct fields, e.g. IP address, phone number with '.', etc.
# caveat: might want to first split by whitespace
# TBD: for unicode, replace isdigit with isdecimal
return [int(s) if s.isdigit() else s for s in re.split(r'(\d+)', string_or_number)]
else:
# consider: add code to recurse for lists/tuples and perhaps other iterables
return string_or_number
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__
# Copyright (C) 2018, Benjamin Drung <bdrung@posteo.de>
#
# Permission to use, copy, modify, and/or distribute this software for any
# purpose with or without fee is hereby granted, provided that the above
# copyright notice and this permission notice appear in all copies.
#
# THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
# WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
# MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
# ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
# WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
# ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
# OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
import re
def natural_sorted(iterable, key=None, reverse=False):
"""Return a new naturally sorted list from the items in *iterable*.
The returned list is in natural sort order. The string is ordered
lexicographically (using the Unicode code point number to order individual
characters), except that multi-digit numbers are ordered as a single
character.
Has two optional arguments which must be specified as keyword arguments.
*key* specifies a function of one argument that is used to extract a
comparison key from each list element: ``key=str.lower``. The default value
is ``None`` (compare the elements directly).
*reverse* is a boolean value. If set to ``True``, then the list elements are
sorted as if each comparison were reversed.
The :func:`natural_sorted` function is guaranteed to be stable. A sort is
stable if it guarantees not to change the relative order of elements that
compare equal --- this is helpful for sorting in multiple passes (for
example, sort by department, then by salary grade).
"""
prog = re.compile(r"(\d+)")
def alphanum_key(element):
"""Split given key in list of strings and digits"""
return [int(c) if c.isdigit() else c for c in prog.split(key(element)
if key else element)]
return sorted(iterable, key=alphanum_key, reverse=reverse)
def find_first_digit(s, non=False):
for i, x in enumerate(s):
if x.isdigit() ^ non:
return i
return -1
def split_digits(s, case=False):
non = True
while s:
i = find_first_digit(s, non)
if i == 0:
non = not non
elif i == -1:
yield int(s) if s.isdigit() else s if case else s.lower()
s = ''
else:
x, s = s[:i], s[i:]
yield int(x) if x.isdigit() else x if case else x.lower()
def natural_key(s, *args, **kwargs):
return tuple(split_digits(s, *args, **kwargs))
我们可以看到它是一般的，因为我们可以有多个数字块:
# Note that the key has lower case letters
natural_key('asl;dkfDFKJ:sdlkfjdf809lkasdjfa_543_hh')
('asl;dkfdfkj:sdlkfjdf', 809, 'lkasdjfa_', 543, '_hh')
def int_maybe(x):
return int(x) if str(x).isdigit() else x
def split_digits_re(s, case=False):
parts = re.findall('\d+|\D+', s)
if not case:
return map(int_maybe, (x.lower() for x in parts))
else:
return map(int_maybe, parts)
def natural_key_re(s, *args, **kwargs):
return tuple(split_digits_re(s, *args, **kwargs))
a = ['H1', 'H100', 'H10', 'H3', 'H2', 'H6', 'H11', 'H50', 'H5', 'H99', 'H8']
b = ''
c = []
def bubble(bad_list):#bubble sort method
length = len(bad_list) - 1
sorted = False
while not sorted:
sorted = True
for i in range(length):
if bad_list[i] > bad_list[i+1]:
sorted = False
bad_list[i], bad_list[i+1] = bad_list[i+1], bad_list[i] #sort the integer list
a[i], a[i+1] = a[i+1], a[i] #sort the main list based on the integer list index value
for a_string in a: #extract the number in the string character by character
for letter in a_string:
if letter.isdigit():
#print letter
b += letter
c.append(b)
b = ''
print 'Before sorting....'
print a
c = map(int, c) #converting string list into number list
print c
bubble(c)
print 'After sorting....'
print c
print a
def natsorted(seq, key=None):
def convert(text):
return int(text) if text.isdigit() else text
def alphanum(obj):
if key is not None:
return [convert(c) for c in re.split(r'([0-9]+)', key(obj))]
return [convert(c) for c in re.split(r'([0-9]+)', obj)]
return sorted(seq, key=alphanum)
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)
import re
from itertools import cycle
_re_digits = re.compile(r"(\d+)")
def natural_comparison_key(key):
return tuple(
int(part) if is_digit else part
for part, is_digit in zip(_re_digits.split(key), cycle((False, True)))
)
def natural_sort(key=None, _nsre=re.compile('([0-9]+)')):
return lambda x: [int(text) if text.isdigit() else text.casefold()
for text in _nsre.split(key(x) if key else x)]
使用示例:
# Original solution
data.sort(key=natural_sort)
# Select an additional key
image_files.sort(key=natural_sort(lambda x: x.original_filename))
