|
|
@@ -8,7 +8,8 @@ from tqdm import tqdm
|
|
|
# директория файла
|
|
|
BASE_DIR = os.path.abspath(os.path.dirname(__file__))
|
|
|
|
|
|
-files_path = []
|
|
|
+print()
|
|
|
+files_paths = []
|
|
|
dirs = os.listdir(BASE_DIR)
|
|
|
for dir in dirs:
|
|
|
dir_path = os.path.join(BASE_DIR, dir)
|
|
|
@@ -19,16 +20,37 @@ for dir in dirs:
|
|
|
filename, fileext = os.path.splitext(file)
|
|
|
|
|
|
if os.path.isfile(file_path) and (fileext=='.md'):
|
|
|
- files_path.append(file_path)
|
|
|
+ files_paths.append(file_path)
|
|
|
|
|
|
-
|
|
|
-for file_1 in tqdm(files_path):
|
|
|
- for file_2 in files_path:
|
|
|
+print(f"Всего файлов: {len(files_paths)}")
|
|
|
+for file_1 in tqdm(files_paths):
|
|
|
+ for file_2 in files_paths:
|
|
|
if (file_1 != file_2):
|
|
|
- with open(file_1, encoding="utf-8") as f_1:
|
|
|
- str1 = f_1.read()
|
|
|
- with open(file_2, encoding="utf-8") as f_2:
|
|
|
- str2 = f_2.read()
|
|
|
+ try:
|
|
|
+ with open(file_1, encoding="utf-8") as f_1:
|
|
|
+ str1 = f_1.read()
|
|
|
+ except:
|
|
|
+ with open(file_1, encoding="cp1251") as f_1:
|
|
|
+ str1 = f_1.read()
|
|
|
+ f_1.close()
|
|
|
+ with open(file_1, 'w', encoding="utf-8") as f_1:
|
|
|
+ f_1.write(str1)
|
|
|
+ f_1.close()
|
|
|
+
|
|
|
+ try:
|
|
|
+ with open(file_2, encoding="utf-8") as f_2:
|
|
|
+ str2 = f_2.read()
|
|
|
+ except:
|
|
|
+ print()
|
|
|
+ print(file_2)
|
|
|
+ print("Неверная кодировка")
|
|
|
+ with open(file_2, encoding="cp1251") as f_2:
|
|
|
+ str2 = f_2.read()
|
|
|
+ f_2.close()
|
|
|
+ with open(file_2, 'w', encoding="utf-8") as f_2:
|
|
|
+ f_2.write(str2)
|
|
|
+ f_2.close()
|
|
|
+
|
|
|
|
|
|
ratio = int(SequenceMatcher(None, str1.lower(), str2.lower()).ratio() * 100)
|
|
|
if (ratio > 70):
|
