Replace os.system('unzip file.zip') -> ZipFile.extractall() (ultr…

…alytics#4919)

* Replace `os.system('unzip file.zip')` -> `ZipFile.extractall()`

* Cleanup

utils/datasets.py

@@ -15,6 +15,7 @@
 from multiprocessing.pool import ThreadPool, Pool
 from pathlib import Path
 from threading import Thread
+from zipfile import ZipFile
 
 import cv2
 import numpy as np
@@ -928,8 +929,8 @@ def unzip(path):
         # Unzip data.zip TODO: CONSTRAINT: path/to/abc.zip MUST unzip to 'path/to/abc/'
         if str(path).endswith('.zip'):  # path is data.zip
             assert Path(path).is_file(), f'Error unzipping {path}, file not found'
-            assert os.system(f'unzip -q {path} -d {path.parent}') == 0, f'Error unzipping {path}'
-            dir = path.with_suffix('')  # dataset directory
+            ZipFile(path).extractall(path=path.parent)  # unzip
+            dir = path.with_suffix('')  # dataset directory == zip name
             return True, str(dir), next(dir.rglob('*.yaml'))  # zipped, data_dir, yaml_path
         else:  # path is data.yaml
             return False, None, path

utils/downloads.py

@@ -9,6 +9,7 @@
 import time
 import urllib
 from pathlib import Path
+from zipfile import ZipFile
 
 import requests
 import torch
@@ -104,8 +105,8 @@ def gdrive_download(id='16TiPfZj7htmTyhntwcZyEEAejOUxuT6m', file='tmp.zip'):
     # Unzip if archive
     if file.suffix == '.zip':
         print('unzipping... ', end='')
-        os.system(f'unzip -q {file}')  # unzip
-        file.unlink()  # remove zip to free space
+        ZipFile(file).extractall(path=file.parent)  # unzip
+        file.unlink()  # remove zip
 
     print(f'Done ({time.time() - t:.1f}s)')
     return r

utils/general.py

@@ -18,6 +18,7 @@
 from multiprocessing.pool import ThreadPool
 from pathlib import Path
 from subprocess import check_output
+from zipfile import ZipFile
 
 import cv2
 import numpy as np
@@ -353,17 +354,19 @@ def check_dataset(data, autodownload=True):
             if s and autodownload:  # download script
                 if s.startswith('http') and s.endswith('.zip'):  # URL
                     f = Path(s).name  # filename
-                    print(f'Downloading {s} ...')
+                    print(f'Downloading {s} to {f}...')
                     torch.hub.download_url_to_file(s, f)
                     root = path.parent if 'path' in data else '..'  # unzip directory i.e. '../'
                     Path(root).mkdir(parents=True, exist_ok=True)  # create root
-                    r = os.system(f'unzip -q {f} -d {root} && rm {f}')  # unzip
+                    ZipFile(f).extractall(path=root)  # unzip
+                    Path(f).unlink()  # remove zip
+                    r = None  # success
                 elif s.startswith('bash '):  # bash script
                     print(f'Running {s} ...')
                     r = os.system(s)
                 else:  # python script
                     r = exec(s, {'yaml': data})  # return None
-                print('Dataset autodownload %s\n' % ('success' if r in (0, None) else 'failure'))  # print result
+                print(f"Dataset autodownload {f'success, saved to {root}' if r in (0, None) else 'failure'}")
             else:
                 raise Exception('Dataset not found.')
 
@@ -393,12 +396,11 @@ def download_one(url, dir):
         if unzip and f.suffix in ('.zip', '.gz'):
             print(f'Unzipping {f}...')
             if f.suffix == '.zip':
-                s = f'unzip -qo {f} -d {dir}'  # unzip -quiet -overwrite
+                ZipFile(f).extractall(path=dir)  # unzip
             elif f.suffix == '.gz':
-                s = f'tar xfz {f} --directory {f.parent}'  # unzip
-            if delete:  # delete zip file after unzip
-                s += f' && rm {f}'
-            os.system(s)
+                os.system(f'tar xfz {f} --directory {f.parent}')  # unzip
+            if delete:
+                f.unlink()  # remove zip
 
     dir = Path(dir)
     dir.mkdir(parents=True, exist_ok=True)  # make directory