python模式字符串_Python字符串模式识别/压缩

I can do basic regex alright, but this is slightly different, namely I don't know what the pattern is going to be.

For example, I have a list of similar strings:

lst = ['asometxt0moretxt', 'bsometxt1moretxt', 'aasometxt10moretxt', 'zzsometxt999moretxt']

In this case the common pattern is two segments of common text: 'sometxt' and 'moretxt', starting and separated by something else that is variable in length.

The common string and variable string can of course occur at any order and at any number of occasions.

What would be a good way to condense/compress the list of strings into their common parts and individual variations?

An example output might be:

c = ['sometxt', 'moretxt']

v = [('a','0'), ('b','1'), ('aa','10'), ('zz','999')]

解决方案

This solution finds the two longest common substrings and uses them to delimit the input strings:

def an_answer_to_stackoverflow_question_1914394(lst):

"""

>>> lst = ['asometxt0moretxt', 'bsometxt1moretxt', 'aasometxt10moretxt', 'zzsometxt999moretxt']

>>> an_answer_to_stackoverflow_question_1914394(lst)

(['sometxt', 'moretxt'], [('a', '0'), ('b', '1'), ('aa', '10'), ('zz', '999')])

"""

delimiters = find_delimiters(lst)

return delimiters, list(split_strings(lst, delimiters))

find_delimiters and friends finds the delimiters:

import itertools

def find_delimiters(lst):

"""

>>> lst = ['asometxt0moretxt', 'bsometxt1moretxt', 'aasometxt10moretxt', 'zzsometxt999moretxt']

>>> find_delimiters(lst)

['sometxt', 'moretxt']

"""

candidates = list(itertools.islice(find_longest_common_substrings(lst), 3))

if len(candidates) == 3 and len(candidates[1]) == len(candidates[2]):

raise ValueError("Unable to find useful delimiters")

if candidates[1] in candidates[0]:

raise ValueError("Unable to find useful delimiters")

return candidates[0:2]

def find_longest_common_substrings(lst):

"""

>>> lst = ['asometxt0moretxt', 'bsometxt1moretxt', 'aasometxt10moretxt', 'zzsometxt999moretxt']

>>> list(itertools.islice(find_longest_common_substrings(lst), 3))

['sometxt', 'moretxt', 'sometx']

"""

for i in xrange(min_length(lst), 0, -1):

for substring in common_substrings(lst, i):

yield substring

def min_length(lst):

return min(len(item) for item in lst)

def common_substrings(lst, length):

"""

>>> list(common_substrings(["hello", "world"], 2))

[]

>>> list(common_substrings(["aabbcc", "dbbrra"], 2))

['bb']

"""

assert length <= min_length(lst)

returned = set()

for i, item in enumerate(lst):

for substring in all_substrings(item, length):

in_all_others = True

for j, other_item in enumerate(lst):

if j == i:

continue

if substring not in other_item:

in_all_others = False

if in_all_others:

if substring not in returned:

returned.add(substring)

yield substring

def all_substrings(item, length):

"""

>>> list(all_substrings("hello", 2))

['he', 'el', 'll', 'lo']

"""

for i in range(len(item) - length + 1):

yield item[i:i+length]

split_strings splits the strings using the delimiters:

import re

def split_strings(lst, delimiters):

"""

>>> lst = ['asometxt0moretxt', 'bsometxt1moretxt', 'aasometxt10moretxt', 'zzsometxt999moretxt']

>>> list(split_strings(lst, find_delimiters(lst)))

[('a', '0'), ('b', '1'), ('aa', '10'), ('zz', '999')]

"""

for item in lst:

parts = re.split("|".join(delimiters), item)

yield tuple(part for part in parts if part != '')