def test_cursor_assignment_does_not_exceed_bounds(self):
""" testing that cursors don't overlap or exceed bounds """
f = File()
f.file_lines = ['line: ' + str(i) for i in range(0, 10)]
f.cursor_end = 20
f.cursor_start = 15
self.assertEqual(
f.file_length - 1,
f.cursor_end,
msg='End cursor should match file length when bounds exceed')
self.assertEqual(
f.cursor_end,
f.cursor_start,
msg='start cursor should match end cursor when start overlaps')
f.cursor_start = -10
f.cursor_end = -5
self.assertEqual(
f.cursor_start,
0,
msg='End cursor should match file length when bounds exceed')
self.assertEqual(
f.cursor_end,
f.cursor_start,
msg='end cursor should match start cursor when end overlaps')
f.cursor_end = 4
f.cursor_start = 2
f.cursor_end = 1
self.assertEqual(
f.cursor_end,
f.cursor_start,
msg='end cursor should match start cursor when end overlaps')
def test_strip_all_files_does_strips_all_files(self):
""" """
f = File()
f.file_lines = [
str(i) + ' squared is: ' + str(i * i) + '\n'
for i in range(0, 100, 3)
]
other_lines = [
str(i) + ' squared is: ' + str(i * i) for i in range(0, 100, 3)
]
f.rstrip_all_lines('\n')
self.assertEqual(f.file_lines,
other_lines,
msg='all newlines should have been stripped.')
def test_file_lines_assignment_updates_file_length(self):
""" test that file line assignment functions correctly."""
f = File()
self.assertEqual(f.file_length,
0,
msg='Zero Lines, length should be 0')
f.file_lines = ['line: ' + str(i) for i in range(0, 10)]
self.assertEqual(len(f.file_lines),
10,
msg='Ten Lines, length should be 0')
self.assertEqual(f.file_length,
10,
msg='Ten Lines, length should be 0')
def create_file(file_path):
""" creates plain file object. """
f = open(file_path)
file_lines = f.readlines()
line_count = len(file_lines)
return File.PopulatedFile('dir_file', file_lines, 0, line_count - 1)
def add_word_file(self, file_path):
try:
text = docx2txt.process(file_path)
file = File(file_path, text)
self.files.append(file)
except Exception as error:
print("Couldn't Load {0}: {1}".format(file_path, error))
return
def __get_folder_content(self) -> List[File]:
content_list = []
if self.path_exist():
content_list = [
File(item) for item in glob.glob('{}*.{}'.format(
self.__work_path, self.__work_extension))
]
return content_list
def add_text_file(self, file_path):
try:
with open(file_path, "r", encoding="utf8",
errors="ignore") as file:
text_file = File(file_path, file.read())
self.files.append(text_file)
except Exception as error:
print("Couldn't Load {0}: {1}".format(file_path, error))
return
def test_returns_file_content(self):
file_mock = Mock(readlines=Mock(), close=Mock())
open_mock = Mock(return_value=file_mock)
File().read('some file name', open_function=open_mock)
open_mock.assert_called_once_with('some file name', 'r')
file_mock.readlines.assert_called_once_with()
file_mock.close.assert_called_once_with()
def add_pdf_file(self, file_path):
try:
with open(file_path, "rb") as raw_file:
reader = PyPDF2.PdfFileReader(raw_file)
pages = reader.numPages
text = ""
for i in range(pages):
page = reader.getPage(i)
text += page.extractText()
file = File(file_path, text)
self.files.append(file)
except Exception as error:
print("Couldn't Load {0}: {1}".format(file_path, error))
def __init__(self,
input_file,
wordlist_file,
file=File(),
similarity_checker=SimilarityChecker,
print_function=print):
sentance = file.read(input_file)[0]
wordlist = file.read(wordlist_file)
closest_sentance = similarity_checker.process_sentance(
wordlist, sentance)
print_function('Closest sentance: ' + closest_sentance['sentance'])
print_function('Total number of changes that had to be made: ' +
str(closest_sentance['distance']))
def sort_file(self, file: File):
if self.logging:
echo("Sorting file: {}".format(path.basename(file.path)))
if file.sorted:
return
# Check to see if a file can be sorted into a pre-existing category
for category in self.categories:
similarity = 0
# Collects the average similarity to each document already in the category
for category_file in category.files:
file_doc_no_stop = self.nlp(' '.join([
str(t) for t in self.nlp(file.contents) if not t.is_stop
]))
other_doc_no_stop = self.nlp(' '.join([
str(t) for t in self.nlp(category_file.contents)
if not t.is_stop
]))
similarity += (file_doc_no_stop.similarity(other_doc_no_stop)
) / len(category.files)
if similarity >= DocumentSorter.threshold:
category.files.append(file)
file.sorted = True
return
# Checks to see if a file can be sorted into a new category with another file
similar_files = self.document_sorter.check_for_similar(
file.path, file.contents)
top_similar = (None, float("-inf"))
for other_file, similarity in similar_files:
if other_file.sorted is False and similarity >= top_similar[1]:
top_similar = (other_file, similarity)
if top_similar[0] is not None:
category = Category("untitled")
file.sorted = True
top_similar[0].sorted = True
category.files.append(file)
category.files.append(top_similar[0])
self.categories.append(category)
return
def get_published_elements(self):
"""
:return: published elements
"""
json_dict = self._get_dictionary_of_published_files()
elements = []
for item in json_dict["items"]:
if item["type"] == "dir":
elements.append(Directory(**item))
elif item["type"] == "file":
elements.append(File(**item))
return elements
def __init__(self, **kwargs):
self.children = []
for key in kwargs:
if key is not "_embedded":
setattr(self, key, kwargs[key])
if "_embedded" in kwargs:
for item in kwargs["_embedded"]['items']:
if item["type"] == "dir":
d = Directory(**item)
self.children.append(d)
if item["type"] == "file":
f = File(**item)
self.children.append(f)
def get_list_of_all_files(self):
"""
:return: List of all files
"""
url = self._base_url + "/resources/files"
r = requests.get(url, headers=self.base_headers)
self._check_code(r)
json_dict = r.json()
files = []
for item in json_dict["items"]:
f = File(**item)
files.append(f)
return files
def test_cursor_assignment_via_setter_property_works(self):
""" test the cursor assignment functions correctly """
f = File()
f.cursor_start = 1
f.cursor_end = 1
f.file_length = 20
self.assertEqual(f.cursor_start,
0,
msg='Zero Lines, cursor should reset to 0')
self.assertEqual(f.cursor_end,
0,
msg='Zero Lines, cursor should reset to 0')
f.file_lines = ['line: ' + str(i) for i in range(0, 10)]
self.assertEqual(f.file_length,
10,
msg='Ten Lines, length should be 0')
def __init__(self):
File.__init__(self)
def test_processes_input(self):
list = ['ABC', 'ABC\n', 'A B C\n\r']
self.assertEqual(File().process_input(list), ['abc', 'abc', 'a b c'])
def __init__(self):
""" Model Class Constructor """
self.replacement_file = File()
self.dirs = {}
self.dir_count = 0