Lesson 1

lesson_1/homework/HW_2.py

@@ -0,0 +1,87 @@
+from collections import OrderedDict
+import csv
+import doctest
+import hashlib
+import os.path
+import unittest
+
+import pytest  # Run from console 'python -m pytest HW_2.py'
+
+
+__author__ = "Vasilii Moskvin"
+
+
+class TestHashSumm(unittest.TestCase):
+    def test_hash_summ(self):
+        self.assertEqual(get_hash_summ('I love Python', 'sha1'), '9233eac58259dd3a13d6c9c59f8001823b6b1fee')
+
+    def test_hash_summ_exc(self):
+        with self.assertRaises(KeyError):
+            get_hash_summ('X', 'X')
+
+
+def tst_hash_summ(in_string, in_code, ans):
+    assert get_hash_summ(in_string, in_code) == ans, 'Неверная сумма'
+
+
+def get_hash_summ(in_string, in_code):
+    """
+    Returns a hexdigest of a in_string.
+    :param in_string: input string
+    :param in_code: hash algorithm
+    :return: a hexdigest of a in_string
+
+    >>> get_hash_summ('I love Python', 'sha1')  # doctest: +NORMALIZE_WHITESPACE
+    '9233eac58259dd3a13d6c9c59f8001823b6b1fee'
+
+    """
+    dct_hash = dict(sha1=hashlib.sha1,
+                    sha224=hashlib.sha224,
+                    sha256=hashlib.sha256,
+                    sha384=hashlib.sha384,
+                    sha512=hashlib.sha512,
+                    md5=hashlib.md5)
+
+    h = dct_hash[in_code]()
+    h.update(in_string.encode('utf-8'))
+
+    return h.hexdigest()
+
+
+def main():
+    """
+    Main function. Reades need_hashes.csv. Gets hexdigest for all strings in the file.
+    And appends the received codes in need_hashes.csv.
+    :return: chenged need_hashes.csv
+
+    """
+    file_path = os.path.abspath(input('Enter path to need_hashes.csv:\n'))
+    my_struct = ('string', 'code', 'hex_digest')
+
+    with open(file_path, 'r') as csv_file:
+        csv_file = csv.reader(csv_file, delimiter=';')
+        data = [OrderedDict(zip(my_struct, row)) for row in csv_file]
+
+    for src in data:                                                    # Вопрос: Как можно такую конструкцию в одну
+        src['hex_digest'] = get_hash_summ(src['string'], src['code'])   # строку записать?
+
+    with open(file_path, 'w', newline='') as csv_file:
+        csv_file = csv.DictWriter(csv_file, delimiter=';', fieldnames=my_struct)
+        csv_file.writerows(data)
+
+
+def run_test():
+    """
+    Conducts tests get_hash_summ(in_string, in_code).
+    assert, doctest, unittest
+    :return: Results of tests get_hash_summ(in_string, in_code)
+
+    """
+    tst_hash_summ('I love Python', 'sha1', '9233eac58259dd3a13d6c9c59f8001823b6b1fee')
+    doctest.testmod()
+    unittest.main()
+
+
+if __name__ == '__main__':
+    #run_test()
+    main()

lesson_1/homework/HW_3.py

@@ -0,0 +1,205 @@
+from collections import OrderedDict
+import os
+import re
+import hashlib
+
+
+__author__ = "Vasilii Moskvin"
+
+
+def get_hash_summ(in_byte, in_code):
+    """
+    Returns a hexdigest of a in_byte.
+    :param in_byte: input byte string
+    :param in_code: hash algorithm
+    :return: a hexdigest of a in_string
+
+    >>> get_hash_summ('I love Python', 'sha1')  # doctest: +NORMALIZE_WHITESPACE
+    '9233eac58259dd3a13d6c9c59f8001823b6b1fee'
+
+    """
+    dct_hash = dict(sha1=hashlib.sha1,
+                    sha224=hashlib.sha224,
+                    sha256=hashlib.sha256,
+                    sha384=hashlib.sha384,
+                    sha512=hashlib.sha512,
+                    md5=hashlib.md5)
+
+    h = dct_hash[in_code]()
+    h.update(in_byte)
+
+    return h.hexdigest()
+
+
+# ------------------------------------------------------3.1------------------------------------------------------------
+
+'''
+    Реализовать функцию разбиения файла на кусочки указанной длины.
+
+        На входе: имя исходного файла и размер в байтах для разрезания файла<br>
+        На выходе: количество полученных файлов-фрагментов
+
+'''
+
+
+def cut_file(file_path, size):
+    """
+    Cuts the file 'file_path' into several parts of the size 'size'
+    :param file_path: path to file
+    :param size: size of parts
+    :return: several parts of the file 'file_path'
+
+    """
+    dir_path = os.sep.join(file_path.split(os.sep)[:-1])
+    with open(file_path, 'rb') as f:
+        raw_data = f.read()
+
+    reg = '.{{1,{}}}'.format(size)
+    data = re.findall(bytes(reg, encoding='utf-8'), raw_data, re.DOTALL)
+
+    for index, src in enumerate(data):
+        with open(os.path.join(dir_path, 'cut_{}'.format(str(index))), 'wb') as f:
+            f.write(src)
+
+    return str(index)
+
+
+def tst_cut_file(file_path, dir_path):
+    """
+    Tests function cut_file(file_path, size)
+    :param file_path: path to cut file
+    :param dir_path: path to directory with cut file
+    :return: error, if the file was not properly cut
+
+    """
+    lst_dir = [os.path.join(dir_path, filename) for filename in os.listdir(dir_path) if filename.startswith('cut_')]
+
+    log_path = os.path.join(dir_path, 'log.jpg')
+    with open(log_path, 'wb') as f:
+        for src in sorted(lst_dir, key=lambda x: float(re.findall(r'.*_(\d+)$', x)[0])):
+            with open(src, 'rb') as temp_f:
+                temp_data = temp_f.read()
+            f.write(temp_data)
+
+    with open(log_path, 'rb') as f:
+        log_data = f.read()
+    log_hash = get_hash_summ(log_data, 'md5')
+
+    with open(file_path, 'rb') as f:
+        file_data = f.read()
+    file_hash = get_hash_summ(file_data, 'md5')
+
+    os.remove(log_path)
+
+    assert log_hash == file_hash, 'Cut file error'
+
+
+# ------------------------------------------------------3.2------------------------------------------------------------
+
+'''
+    Реализовать функцию составления текстового файла с md5-хэшами файлов в указанной директории
+
+        На входе: имя директории с файлами, имя файла для записи результатов<br>
+        На выходе: количество просмотренных файлов
+
+'''
+
+
+def get_hash_in_dir(dir_path, res_path):
+    """
+    Returns file with the list of hash summs from files in the dir_path.
+    :param dir_path: path to directory with files
+    :param res_path: path to result files
+    :return: file with the list of hash summs from files in the dir_path
+
+    """
+    lst_files = [os.path.join(dir_path, file_name) for file_name in os.listdir(dir_path)
+                 if not file_name.endswith('.md5')]
+
+    lst_hash = []
+    for file_path in lst_files:
+        with open(file_path, 'rb') as f:
+            data = f.read()
+        lst_hash.append(get_hash_summ(data, 'md5'))
+
+    with open(res_path, 'w') as f:
+        for hash_line in lst_hash:
+            f.write('{}\n'.format(hash_line))
+
+    return len(lst_files)
+
+
+# ------------------------------------------------------3.3------------------------------------------------------------
+
+'''
+    Реализовать функцию "склеивания" файла на основе упорядоченных хэш-сумм
+
+        На входе: имя директории с файлами-кусочками, имя файла с хэш-суммами, имя выходного файла<br>
+        На выходе: размер полученного файла
+
+'''
+
+
+def get_full_file(dir_path, md5_file_path, res_path):
+    """
+    Creates full file from many parts.
+    :param dir_path: path to directory with parts of full file
+    :param md5_file_path: path to list of hash summs
+    :param res_path: path to result file
+    :return: Creates full file from many parts
+
+    """
+    lst_files = [os.path.join(dir_path, file_name) for file_name in os.listdir(dir_path)
+                 if not file_name.endswith('.md5')]
+
+    with open(md5_file_path, 'r') as f:
+        hash_summ = OrderedDict(map(lambda line: (line.strip(), ''), f))
+
+    for file_path in lst_files:
+        with open(file_path, 'rb') as f:
+            data = f.read()
+        h = hashlib.md5()
+        h.update(data)
+        hash_summ[h.hexdigest()] = file_path
+
+    with open(res_path, 'wb') as f_res:
+        for hash, file_path in hash_summ.items():
+            with open(file_path, 'rb') as f:
+                data = f.read()
+            f_res.write(data)
+
+    return os.path.getsize(res_path)
+
+
+def main():
+    # --------------------------------------3.1-----------------------------------------------------------------------
+
+    print('№ 3.1 "Cut file"')
+    dir_path = os.path.abspath(input('Enter path to directory with cut file:\n'))
+    file_path = os.path.join(dir_path, input('Enter the name of cut file:\n'))
+    size = int(input('Enter the size of cut parts (bytes):\n'))
+
+    print('Count of new files: {}'.format(cut_file(file_path, size)))
+
+    tst_cut_file(file_path, dir_path)
+
+    # --------------------------------------3.2-----------------------------------------------------------------------
+
+    print('№ 3.2 "List of hash in a directory"')
+    dir_path = os.path.abspath(input('Enter path to directory with files:\n'))
+    res_path = os.path.abspath(input('Enter path to result file:\n'))
+
+    print('Viewed {} files'.format(get_hash_in_dir(dir_path, res_path)))
+
+    # --------------------------------------3.3-----------------------------------------------------------------------
+
+    print('№ 3.3 "Creates full file from many parts."')
+    dir_path = os.path.abspath(input('Enter path to directory with files:\n'))
+    md5_file_path = os.path.abspath(input('Enter path to file with list of hashes:\n'))
+    res_path = os.path.abspath(input('Enter path to result file:\n'))
+
+    print('Size of reuslt file: {} bytes'.format(get_full_file(dir_path, md5_file_path, res_path)))
+
+
+if __name__ == '__main__':
+    main()

lesson_1/homework/need_hashes.csv

@@ -1,5 +1,5 @@
 I love Python;sha1;9233eac58259dd3a13d6c9c59f8001823b6b1fee
-Я люблю Питон;md5;
-Guido like beer;sha512;
-Тили-мили-трямзия;md5;
-Spam and eggs and ham;sha1;
+Я люблю Питон;md5;8cda44d3a8ca06e9ebcd9e50fbb060a9
+Guido like beer;sha512;9490ca5a146f482ea40649b832017dbec7279462766ec6e02fac4c7910584c50572b3efd3d257c089431b8b88603226a9d3aa2fcd4185fcc8db9f71114e06d93
+Тили-мили-трямзия;md5;178d4b8a96e116c4462bfed4b6e83988
+Spam and eggs and ham;sha1;c13dd8ebf6f20c890594773c965932336d58277a

lesson_1/homework/pep8_me.py

@@ -2,28 +2,31 @@
 import string
 
 
-def create_file(namef,dir,size):
-        if(size.isdigit()!=True):
-                if size.endswith('KB')==True:
-                        s1 = size.split('KB')
-                        size1 = int(s1[0])*1024
-                        token = ''.join(random.choice(string.ascii_uppercase + string.ascii_lowercase + string.digits) for x in range(size1))
-                if size.endswith('MB')==True:
-                        s1 = size.split('MB')
-                        size1 = int(s1[0])*1048567
-                        token = ''.join(random.choice(string.ascii_uppercase + string.ascii_lowercase + string.digits) for x in range(size1))
-                if size.endswith('GB') == True:
-                        s1 = size.split('GB')
-                        size1 = int(s1[0]) * 1073741824
-                        token = ''.join(random.choice(string.ascii_uppercase + string.ascii_lowercase + string.digits) for x in range(size1))
-        else:
-                token = ''.join(random.choice(string.ascii_uppercase + string.ascii_lowercase + string.digits) for x in range(int(size)))
-
-        file = open(dir+namef,"w")
+def create_file(name_f, dir_path, size):
+    if not size.isdigit():
+        if size.endswith('KB'):
+            s1 = size.split('KB')
+            size1 = int(s1[0]) * 1024
+            token = ''.join(random.choice(string.ascii_uppercase + string.ascii_lowercase + string.digits) 
+                            for _ in range(size1))
+        elif size.endswith('MB'):
+            s1 = size.split('MB')
+            size1 = int(s1[0]) * 1048567
+            token = ''.join(random.choice(string.ascii_uppercase + string.ascii_lowercase + string.digits) 
+                            for _ in range(size1))
+        elif size.endswith('GB'):
+            s1 = size.split('GB')
+            size1 = int(s1[0]) * 1073741824
+            token = ''.join(random.choice(string.ascii_uppercase + string.ascii_lowercase + string.digits) 
+                            for _ in range(size1))
+    else:
+        token = ''.join(random.choice(string.ascii_uppercase + string.ascii_lowercase + string.digits) 
+                        for _ in range(int(size)))
+    with open(dir_path + name_f, "w") as file:  # По-хорошшему, здесь нужно использовать os.path.join(dir_path, name_f)
         file.write(token)
+
 
-
-create_file("/test1.txt","E:",'10KB')
-create_file("/test2.txt","E:",'1024')
-create_file("/test11.txt","E:",'2MB')
-create_file("/test21.txt","E:",'1B')
+create_file("/test1.txt", "E:", '10KB')
+create_file("/test2.txt", "E:", '1024')
+create_file("/test11.txt", "E:", '2MB')
+create_file("/test21.txt", "E:", '1B')