Created
July 30, 2019 03:32
-
-
Save wecacuee/1e4c9ea5f9baad9154d13aad06f19ce2 to your computer and use it in GitHub Desktop.
Remove common parts and keep only the differences
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def common_substr(strs, return_diffs=False): | |
""" | |
>>> common_substr("abcd", "xbcd") | |
'bcd' | |
""" | |
strs = list(strs) | |
min_len = min(map(len, strs)) | |
max_len = max(map(len, strs)) | |
first = strs[0] | |
comm = type(first)() | |
diffs = [type(first)() for s in strs] | |
for i in range(max_len): | |
if i < min_len and all((first[i] == s[i]) for s in strs): | |
comm.append(first[i]) | |
else: | |
for d, s in zip(diffs, strs): | |
if i < len(s): | |
d.append(s[i]) | |
return (comm, diffs) if return_diffs else comm | |
def diff_substr(strs, splitre="[-_/]", joinstr="-"): | |
comm, diffs = common_substr((re.split(splitre, s) for s in strs), | |
return_diffs=True) | |
return map(joinstr.join, diffs) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment