def test2_single_full_match(self):
pattern = b"hello"
text = b"how delightful, hello there"
matches = gst.match(pattern, '', text, '', len(pattern))
self.assertIsInstance(matches, list)
self.assertEqual(len(matches), 1)
self.assertCorrectMatchSubstringMapping(pattern, text, matches[0])
pattern_str, text_str = pattern.decode("ascii"), text.decode("ascii")
matches = gst.match(pattern_str, '', text_str, '', len(pattern_str))
self.assertCorrectMatchSubstringMapping(pattern, text, matches[0])
def test4_no_match(self):
pattern = b"hello"
text = b"go away, you nuisance"
matches = gst.match(pattern, '', text, '', len(pattern))
self.assertIsInstance(matches, list)
self.assertEqual(len(matches), 0)
pattern_str, text_str = pattern.decode("ascii"), text.decode("ascii")
matches = gst.match(pattern_str, '', text_str, '', len(pattern_str))
self.assertIsInstance(matches, list)
self.assertEqual(len(matches), 0)
def test3_single_partial_match(self):
pattern = b"hello"
text = b"we are in helsinki now"
match_len = 3
matches = gst.match(pattern, '', text, '', match_len)
self.assertIsInstance(matches, list)
self.assertEqual(len(matches), 1)
self.assertCorrectMatchSubstringMapping(pattern, text, matches[0])
pattern_str, text_str = pattern.decode("ascii"), text.decode("ascii")
matches = gst.match(pattern_str, '', text_str, '', match_len)
self.assertIsInstance(matches, list)
self.assertEqual(len(matches), 1)
self.assertCorrectMatchSubstringMapping(pattern, text, matches[0])
def test2_full_match_bytes(self, text_and_pattern):
text, pattern = text_and_pattern
pattern_bytes, text_bytes = pattern.encode("ascii"), text.encode(
"ascii")
matches = gst.match(pattern_bytes, '', text_bytes, '',
len(pattern_bytes))
for match in matches:
self.assertCorrectMatchSubstringMapping(pattern, text, match)
def compare_files(filename_one, filename_two):
"""
Receives filenames as parameters, compares the list of lines received
Returns the tuple containing the plagiarism percentage
"""
if utils.check_file(
utils.get_file_path(filename_one)) and utils.check_file(
utils.get_file_path(filename_two)):
file_one_tokens, file_two_tokens = [], []
file_one_clean, file_two_clean = utils.extract_files(
filename_one, filename_two, True)
print(file_one_clean)
print(file_two_clean)
if filename_one.split(".")[1] == "py":
write_to_file(file_one_clean, "1")
write_to_file(file_two_clean, "2")
token_generator('./dataset/type_two_dump_1.py', file_one_tokens)
token_generator('./dataset/type_two_dump_2.py', file_two_tokens)
# print("yyyyyyyyyyy")
else:
file_one_tokens = c_token_generator(filename_one)
file_two_tokens = c_token_generator(filename_two)
# print(file_one_tokens)
# print(file_two_tokens)
ignore_a = ''
string_a = ",".join(str(e) for e in file_one_tokens)
string_b = ",".join(str(e) for e in file_two_tokens)
number_of_lines_plagiarised = list(
match(string_a, ignore_a, string_b, ignore_a, 6)[0])[2]
# print(string_a)
# print(string_b)
# print(match(string_a, ignore_a, string_b, ignore_a, 3)[0])
file_two_plagiarism_score = utils.get_plagiarism_percentage(
number_of_lines_plagiarised * 2,
len(string_a) + len(string_b))
return file_two_plagiarism_score, file_two_plagiarism_score
# return type_one.compare_files('type_two_dump_1.py', 'type_two_dump_2.py')
else:
print("Error file format not supported")
def test_edge_cases(self):
for a, b in EDGE_CASES:
matches = gst.match(a, '', b, '', 1)
self.assertGreater(len(matches), 0)
def test1_full_match(self, text_and_pattern):
text, pattern = text_and_pattern
matches = gst.match(pattern, '', text, '', len(pattern))
for match in matches:
self.assertCorrectMatchSubstringMapping(pattern, text, match)
# }
Char = collections.namedtuple("Char", ("char", "match_edge", "match_number"))
output_html_path = "index.html"
min_match_length = 50
num_match_colors = 4
# Load data
with open("text1.txt") as f:
text1 = f.read()
text2 = ''
for line in text1.splitlines():
text2 += ' '.join(l for l in line.split(' ') if random.random() > 0.05)
# Get matches and sort in ascending order by starting indexes of matches in text1
match_list = gst.match(text1, '', text2, '', min_match_length)
match_list.sort()
# Annotate every character that is the first or last character of a match
# This makes it trivial to generate HTML around these positions
text1 = [Char(char=c, match_edge=0, match_number=0) for c in text1]
text2 = [Char(char=c, match_edge=0, match_number=0) for c in text2]
for match_num, (i1, i2, length) in enumerate(match_list, start=1):
text1[i1] = Char(char=text1[i1].char, match_edge=-1, match_number=match_num)
text2[i2] = Char(char=text2[i2].char, match_edge=-1, match_number=match_num)
text1[i1+length-1] = Char(char=text1[i1+length-1].char, match_edge=1, match_number=match_num)
text2[i2+length-1] = Char(char=text2[i2+length-1].char, match_edge=1, match_number=match_num)
template = jinja2.Environment(loader=jinja2.FileSystemLoader(".")).get_template("template.html")
html = template.render(
text1=text1,