def convert_to_html_file(notebook_path):
with (open(notebook_path, "r")) as notebook_file:
notebook_data = _read_notebook(notebook_file)
html = _convert_notebook_to_html(notebook_data)
notebook_html_file = create_temp_file()
write_to_file(html, notebook_html_file)
return notebook_html_file
def test_write_to_file_when_file_does_not_exist(self):
path = "../out/data.txt"
try:
os.remove(path)
except FileNotFoundError:
pass
self.assertFalse(write_to_file(path))
def get_bouquets(input_file_name: str, output_file_name: str):
"""
Main function for this task. This function is being called in script.py file.
It handles all bouquets and does the following:
1. reads input info from 'input_file_name' file.
2. handles bouquets and flowers info.
3. writes output info into 'output_file_name' file.
"""
total_bouquets, total_flowers = read_from_file(file_name=input_file_name)
bouquets_for_writing_to_file = list()
for bouquet in total_bouquets:
handled_bouquet = handle_bouquet(bouquet=bouquet,
total_flowers=total_flowers)
if handled_bouquet:
bouquets_for_writing_to_file.append(handled_bouquet)
write_to_file(file_name=output_file_name,
data=bouquets_for_writing_to_file)
def lsc_driver(cur_loc, log_file):
'''
Driver function for the LSC algorithm.
:param loc: Directory location.
:return: <>
'''
file_list = files.get_files_in_dir(cur_loc)
if len(file_list) == 0:
print('LONGEST COMMON SUBSTRING: No text files found! Exiting.')
files.write_to_file(
log_file,
'\nLONGEST COMMON SUBSTRING: No text files found! Exiting.\n')
return []
line_list = []
for f in file_list:
line_list.append(files.read_lines_in_file(cur_loc + '\\' + f))
# print(line_list)
new_line_list = []
for line in line_list:
new_line = list(map(common.beautify, line))
# print(new_line)
new_line_list.append(new_line)
print('\n')
print(new_line_list)
lsc_matrix = []
results = []
for i in range(len(new_line_list)):
for j in range(len(new_line_list)):
if i == len(lsc_matrix):
lsc_matrix.append([])
try:
lsc_matrix[i].append(lsc_matrix[j][i])
except:
if i == j:
lsc_matrix[i].append(-1)
else:
lsc_matrix[i].append(
get_longest_common_substring(new_line_list[i][0],
new_line_list[j][0]))
if (lsc_matrix[i][j] >= (70)) and i != j:
results.append(
(file_list[i], file_list[j], lsc_matrix[i][j]))
print('\n\nLONGEST COMMON SUBSEQUENCE:\n')
files.write_to_file(log_file, '\n\nLONGEST COMMON SUBSEQUENCE:\n')
for res in results:
files.write_to_file(
log_file, '\'' + res[0] + '\' and \'' + res[1] +
'\' are similar enough (' + str(res[2]) +
'% similarity) to each other (to suspect plagiarism).\n')
print('\'' + res[0] + '\' and \'' + res[1] +
'\' are similar enough (' + str(res[2]) +
'% similarity) to each other (to suspect plagiarism).')
return lsc_matrix
def main():
# Get the present working directory
cur_dir = os.path.abspath(os.curdir)
# Greeting message
print('\n\n****************** PLAGIARISM DETECTOR ******************',
end='')
print('\n ******************* SRIKANTH KAVURI *******************\n')
# Commented out and included this functionality in proceed() in common.py
# stop = False
# while not stop:
# choice = input('Default directory is ' + cur_dir + '. Continue? ').strip()
# if choice.lower() == 'y' or choice.lower() == 'n':
# stop = True
# else:
# # Validation
# print('Invalid.\n')
question = 'Default directory is ' + cur_dir + '. Continue? '
if not common.proceed(question):
stop = False
while not stop:
new_dir = input('Enter new directory: ').strip()
# Check if the entered path is a valid path in the system.
if os.path.isdir(new_dir):
stop = True
cur_dir = new_dir
else:
print('Invalid.\n')
# Giving the user the option of enabling log files.
question = '\nEnable logging? '
if common.proceed(question):
log_file_name = files.create_log_file(cur_dir)
else:
log_file_name = ''
print('\n')
# Call driver functions for Bag of Words and LCS
# bag_matrix = Matrix(bag_of_words.bag_driver(cur_dir, log_file_name))
# lsc_matrix = Matrix(lsc.lsc_driver(cur_dir, log_file_name))
bag_matrix = (bag_of_words.bag_driver(cur_dir, log_file_name))
lsc_matrix = (lsc.lsc_driver(cur_dir, log_file_name))
# Print results
print('\nBag of words matrix:')
print(bag_matrix)
print('\nLCS matrix:')
print(lsc_matrix)
# Write results to log file, if it exists.
# If the log file doesn't exist, then the error is just ignored.
files.write_to_file(log_file_name, '\nBag of words matrix:\n')
files.write_to_file(log_file_name, str(bag_matrix))
files.write_to_file(log_file_name, '\nLCS matrix:\n')
files.write_to_file(log_file_name, str(lsc_matrix))
files.write_to_file(log_file_name, '\n')
def test_write_to_file_when_file_exists(self):
path = "../out/data.txt"
with open(path, 'w'):
pass
self.assertTrue(write_to_file(path))
def bag_driver(cur_dir, log_file):
'''
Driver program for bag of words.
:param cur_dir: Current working directory. This is where the files are.
:return: <>
'''
# Get all files in cur_dir as a list
file_list = files.get_files_in_dir(cur_dir)
if len(file_list) == 0:
print('BAG OF WORDS: No text files found! Exiting.')
files.write_to_file(log_file,
'\nBAG OF WORDS: No text files found! Exiting.\n')
return []
# vecs will be a list of tuples.
# This is done to make sure that we can keep track of which vector is for
# which file.
vecs = []
for file in file_list:
vector = create_vector_for_file(cur_dir + '\\' + file)
# print(sorted(vector.elements()))
vecs.append(vector)
angles = []
results = []
# Get the angle between every pair of vectors.
for i in range(len(file_list)):
for j in range(len(file_list)):
# print(angles)
# Create the list at position i.
if i == len(angles):
angles.append([])
try:
# Angle between A and B is the same as angle between B and A.
angles[i].append(angles[j][i])
except:
if i == j:
# Comparing a file with itself makes no sense.
angles[i].append(-1)
else:
# Calculate angle
angles[i].append(100 *
(round(get_angle(vecs[i], vecs[j]), 2)))
# Similar enough to suspect plagiarism?
if (angles[i][j] >= 70) and i != j:
# print(angles[i][j], vecs[i].length)
results.append((file_list[i], file_list[j], angles[i][j]))
# for item in angles:
# if len(item) == 0:
# angles.remove(item)
# print(angles)
# Printouts
print('\nFor your reference:')
for ind in range(len(file_list)):
print('File number ' + str(ind) + ' corresponds to file ' +
file_list[ind])
print('\n')
files.write_to_file(log_file, '\nFor your reference:\n')
for ind in range(len(file_list)):
files.write_to_file(
log_file, 'File number ' + str(ind) + ' corresponds to file ' +
file_list[ind] + '\n')
files.write_to_file(log_file, '\n')
files.write_to_file(log_file, '\n\nBAG OF WORDS:\n')
print('\n\nBAG OF WORDS:\n')
for res in results:
files.write_to_file(
log_file, '\'' + res[0] + '\' and \'' + res[1] +
'\' are similar enough (' + str(res[2]) +
'% similarity) to each other (to suspect plagiarism).\n')
print('\'' + res[0] + '\' and \'' + res[1] +
'\' are similar enough (' + str(res[2]) +
'% similarity) to each other (to suspect plagiarism).')
return angles
