so I have a problem that I think it works as expected, but when I run the check50 it gives me all :)'s and just 1 error:
:( handles duplicate substrings in common Expected 4 matches, not 5
I checked further to see what the problem was, and it said that it's for inputs'foobarbaz' and 'barbaz', but when I tried printing it with those inputs (and I put n = 3, since that's the only way to expect 4 matches) and it worked fine again, returning ['bar', 'arb', 'rba', 'baz'].
What am I doing wrong?
from nltk.tokenize import sent_tokenize
def lines(a, b):
"""Return lines in both a and b"""
result = []
for line in a.split("\n"): #a je lista koja sadrzi redove bez \n
if line in b.split("\n"):
if line != "":
result.append(line)
return result
def sentences(a, b):
"""Return sentences in both a and b"""
result = []
a = sent_tokenize(a, language='english')
b = sent_tokenize(b, language='english')
for line in a:
if line in b:
if line != "" and line.strip() not in result:
result.append(line.strip())
return result
def substrings(a, b, n):
"""Return substrings of length n in both a and b"""
#this works only if a and b are just 1 word
a = a.split(" ")
result = []
#splits 1 text into a list whose elements are single words
for word in a:
listofsubs = find_substrings(word.strip(":;,."), n)
for sub in listofsubs:
if b.find(sub) != -1:
result.append(sub)
return result
def find_substrings(a, n):
"""Return list of substrings of length n"""
result = []
i = 0
while (i + n) < len(a) + 1:
result.append(a[i:i+n])
i += 1
return result
