Comparing texts as sequences

simple_plagiarism_check.py

import difflib

text_one = open("1.txt", "r").read()
text_two = open("2.txt", "r").read()

sm = difflib.SequenceMatcher(isjunk=None, a=text_one, b=text_two)
mbs = sm.get_matching_blocks()

for mb in mbs:
    if mb.size > 10:
        print("{", text_one[mb.a:mb.a + mb.size].replace("\n", " "))
        print("}", text_two[mb.b:mb.b + mb.size].replace("\n", " "))
        print()

print("difflib: a total of ", len(mbs), "blocks matching exactly")
print("difflib: ratio ", sm.ratio())

## -----------------

from fuzzywuzzy import fuzz

simple_ratio = fuzz.ratio(text_one, text_two)
print("fuzzywuzzy: simple ratio =", simple_ratio)

## takes a while to compute

# partial_ratio = fuzz.partial_ratio(text_one, text_two)
# print(partial_ratio)
#
#
# token_sort_ratio = fuzz.token_sort_ratio(text_one, text_two)
# print(token_sort_ratio)
#
#
# token_set_ratio = fuzz.token_set_ratio(text_one, text_two)
# print(token_set_ratio)