Update ZipFile to context manager (#9843)

* Update zipFile to context manager

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Cleanup

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Cleanup

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

utils/dataloaders.py

@@ -17,7 +17,6 @@ from multiprocessing.pool import Pool, ThreadPool
 from pathlib import Path
 from threading import Thread
 from urllib.parse import urlparse
-from zipfile import ZipFile
 
 import numpy as np
 import torch
@@ -31,7 +30,8 @@ from tqdm import tqdm
 from utils.augmentations import (Albumentations, augment_hsv, classify_albumentations, classify_transforms, copy_paste,
                                  cutout, letterbox, mixup, random_perspective)
 from utils.general import (DATASETS_DIR, LOGGER, NUM_THREADS, check_dataset, check_requirements, check_yaml, clean_str,
-                           cv2, is_colab, is_kaggle, segments2boxes, xyn2xy, xywh2xyxy, xywhn2xyxy, xyxy2xywhn)
+                           cv2, is_colab, is_kaggle, segments2boxes, unzip_file, xyn2xy, xywh2xyxy, xywhn2xyxy,
+                           xyxy2xywhn)
 from utils.torch_utils import torch_distributed_zero_first
 
 # Parameters
@@ -1053,7 +1053,7 @@ class HUBDatasetStats():
         if not str(path).endswith('.zip'):  # path is data.yaml
             return False, None, path
         assert Path(path).is_file(), f'Error unzipping {path}, file not found'
-        ZipFile(path).extractall(path=path.parent)  # unzip
+        unzip_file(path, path=path.parent)
         dir = path.with_suffix('')  # dataset directory == zip name
         assert dir.is_dir(), f'Error unzipping {path}, {dir} not found. path/to/abc.zip MUST unzip to path/to/abc/'
         return True, str(dir), self._find_yaml(dir)  # zipped, data_dir, yaml_path

utils/downloads.py

@@ -5,12 +5,9 @@ Download utils
 
 import logging
 import os
-import platform
 import subprocess
-import time
 import urllib
 from pathlib import Path
-from zipfile import ZipFile
 
 import requests
 import torch
@@ -109,81 +106,3 @@ def attempt_download(file, repo='ultralytics/yolov5', release='v6.2'):
                 error_msg=f'{file} missing, try downloading from https://github.com/{repo}/releases/{tag} or {url3}')
 
     return str(file)
-
-
-def gdrive_download(id='16TiPfZj7htmTyhntwcZyEEAejOUxuT6m', file='tmp.zip'):
-    # Downloads a file from Google Drive. from yolov5.utils.downloads import *; gdrive_download()
-    t = time.time()
-    file = Path(file)
-    cookie = Path('cookie')  # gdrive cookie
-    print(f'Downloading https://drive.google.com/uc?export=download&id={id} as {file}... ', end='')
-    if file.exists():
-        file.unlink()  # remove existing file
-    if cookie.exists():
-        cookie.unlink()  # remove existing cookie
-
-    # Attempt file download
-    out = "NUL" if platform.system() == "Windows" else "/dev/null"
-    os.system(f'curl -c ./cookie -s -L "drive.google.com/uc?export=download&id={id}" > {out}')
-    if os.path.exists('cookie'):  # large file
-        s = f'curl -Lb ./cookie "drive.google.com/uc?export=download&confirm={get_token()}&id={id}" -o {file}'
-    else:  # small file
-        s = f'curl -s -L -o {file} "drive.google.com/uc?export=download&id={id}"'
-    r = os.system(s)  # execute, capture return
-    if cookie.exists():
-        cookie.unlink()  # remove existing cookie
-
-    # Error check
-    if r != 0:
-        if file.exists():
-            file.unlink()  # remove partial
-        print('Download error ')  # raise Exception('Download error')
-        return r
-
-    # Unzip if archive
-    if file.suffix == '.zip':
-        print('unzipping... ', end='')
-        ZipFile(file).extractall(path=file.parent)  # unzip
-        file.unlink()  # remove zip
-
-    print(f'Done ({time.time() - t:.1f}s)')
-    return r
-
-
-def get_token(cookie="./cookie"):
-    with open(cookie) as f:
-        for line in f:
-            if "download" in line:
-                return line.split()[-1]
-    return ""
-
-
-# Google utils: https://cloud.google.com/storage/docs/reference/libraries ----------------------------------------------
-#
-#
-# def upload_blob(bucket_name, source_file_name, destination_blob_name):
-#     # Uploads a file to a bucket
-#     # https://cloud.google.com/storage/docs/uploading-objects#storage-upload-object-python
-#
-#     storage_client = storage.Client()
-#     bucket = storage_client.get_bucket(bucket_name)
-#     blob = bucket.blob(destination_blob_name)
-#
-#     blob.upload_from_filename(source_file_name)
-#
-#     print('File {} uploaded to {}.'.format(
-#         source_file_name,
-#         destination_blob_name))
-#
-#
-# def download_blob(bucket_name, source_blob_name, destination_file_name):
-#     # Uploads a blob from a bucket
-#     storage_client = storage.Client()
-#     bucket = storage_client.get_bucket(bucket_name)
-#     blob = bucket.blob(source_blob_name)
-#
-#     blob.download_to_filename(destination_file_name)
-#
-#     print('Blob {} downloaded to {}.'.format(
-#         source_blob_name,
-#         destination_file_name))

utils/general.py

@@ -511,7 +511,7 @@ def check_dataset(data, autodownload=True):
                 LOGGER.info(f'Downloading {s} to {f}...')
                 torch.hub.download_url_to_file(s, f)
                 Path(DATASETS_DIR).mkdir(parents=True, exist_ok=True)  # create root
-                ZipFile(f).extractall(path=DATASETS_DIR)  # unzip
+                unzip_file(f, path=DATASETS_DIR)  # unzip
                 Path(f).unlink()  # remove zip
                 r = None  # success
             elif s.startswith('bash '):  # bash script
@@ -566,6 +566,16 @@ def yaml_save(file='data.yaml', data={}):
         yaml.safe_dump({k: str(v) if isinstance(v, Path) else v for k, v in data.items()}, f, sort_keys=False)
 
 
+def unzip_file(file, path=None, exclude=('.DS_Store', '__MACOSX')):
+    # Unzip a *.zip file to path/, excluding files containing strings in exclude list
+    if path is None:
+        path = Path(file).parent  # default path
+    with ZipFile(file) as zipObj:
+        for f in zipObj.namelist():  # list all archived filenames in the zip
+            if all(x not in f for x in exclude):
+                zipObj.extract(f, path=path)
+
+
 def url2file(url):
     # Convert URL to filename, i.e. https://url.com/file.txt?auth -> file.txt
     url = str(Path(url)).replace(':/', '://')  # Pathlib turns :// -> :/
@@ -601,7 +611,7 @@ def download(url, dir='.', unzip=True, delete=True, curl=False, threads=1, retry
         if unzip and success and f.suffix in ('.zip', '.tar', '.gz'):
             LOGGER.info(f'Unzipping {f}...')
             if f.suffix == '.zip':
-                ZipFile(f).extractall(path=dir)  # unzip
+                unzip_file(f, dir)  # unzip
             elif f.suffix == '.tar':
                 os.system(f'tar xf {f} --directory {f.parent}')  # unzip
             elif f.suffix == '.gz':