def check(origin, plagiarized):
with open(origin, "r") as file:
origin = file.read()
with open(plagiarized, "r") as file:
plagiarism = file.read()
text_length = min(len(origin.split()), len(plagiarism.split()))
if text_length < 60:
raise NotImplementedError("Compare texts with at least 60 words.")
window = max(text_length // 21, 3)
kgram = window - 1
base = 11 if text_length < 250 else 23 if text_length < 600 else 101
modulo = max(round(text_length * 5, -3), 1000)
fprint = Fingerprint(kgram_len=kgram, window_len=window, base=base, modulo=modulo)
first = fprint.generate(str=origin)
second = fprint.generate(str=plagiarism)
similar = [
x
for x in first
if x in second
]
similar_grams = Counter([
element[0]
for element in first
for sec in second
if sec[0] == element[0]
])
print("Identical substring hashes:")
pprint(similar)
print("\nIdentical grams:")
pprint(similar_grams)
def fingerprint_function(url):
f = Fingerprint(kgram_len=4, window_len=1, base=10, modulo=1000)
return f.generate(str=url)