718c41634f
1.项目后端整体迁移至PaddleOCR-NCNN算法，已通过基本的兼容性测试 2.工程改为使用CMake组织，后续为了更好地兼容第三方库，不再提供QMake工程 3.重整权利声明文件，重整代码工程，确保最小化侵权风险 Log: 切换后端至PaddleOCR-NCNN，切换工程为CMake Change-Id: I4d5d2c5d37505a4a24b389b1a4c5d12f17bfa38c
116 lines
3.9 KiB
Python
116 lines
3.9 KiB
Python
# Tencent is pleased to support the open source community by making ncnn available.
|
|
#
|
|
# Copyright (C) 2020 THL A29 Limited, a Tencent company. All rights reserved.
|
|
#
|
|
# Licensed under the BSD 3-Clause License (the "License"); you may not use this file except
|
|
# in compliance with the License. You may obtain a copy of the License at
|
|
#
|
|
# https://opensource.org/licenses/BSD-3-Clause
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software distributed
|
|
# under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
|
|
# CONDITIONS OF ANY KIND, either express or implied. See the License for the
|
|
# specific language governing permissions and limitations under the License.
|
|
|
|
"""Download files with progress bar."""
|
|
|
|
import os
|
|
import hashlib
|
|
import requests
|
|
from tqdm import tqdm
|
|
|
|
|
|
def check_sha1(filename, sha1_hash):
|
|
"""Check whether the sha1 hash of the file content matches the expected hash.
|
|
Parameters
|
|
----------
|
|
filename : str
|
|
Path to the file.
|
|
sha1_hash : str
|
|
Expected sha1 hash in hexadecimal digits.
|
|
Returns
|
|
-------
|
|
bool
|
|
Whether the file content matches the expected hash.
|
|
"""
|
|
sha1 = hashlib.sha1()
|
|
with open(filename, "rb") as f:
|
|
while True:
|
|
data = f.read(1048576)
|
|
if not data:
|
|
break
|
|
sha1.update(data)
|
|
|
|
sha1_file = sha1.hexdigest()
|
|
l = min(len(sha1_file), len(sha1_hash))
|
|
return sha1.hexdigest()[0:l] == sha1_hash[0:l]
|
|
|
|
|
|
def download(url, path=None, overwrite=False, sha1_hash=None):
|
|
"""Download an given URL
|
|
Parameters
|
|
----------
|
|
url : str
|
|
URL to download
|
|
path : str, optional
|
|
Destination path to store downloaded file. By default stores to the
|
|
current directory with same name as in url.
|
|
overwrite : bool, optional
|
|
Whether to overwrite destination file if already exists.
|
|
sha1_hash : str, optional
|
|
Expected sha1 hash in hexadecimal digits. Will ignore existing file when hash is specified
|
|
but doesn't match.
|
|
Returns
|
|
-------
|
|
str
|
|
The file path of the downloaded file.
|
|
"""
|
|
if path is None:
|
|
fname = url.split("/")[-1]
|
|
else:
|
|
path = os.path.expanduser(path)
|
|
if os.path.isdir(path):
|
|
fname = os.path.join(path, url.split("/")[-1])
|
|
else:
|
|
fname = path
|
|
|
|
if (
|
|
overwrite
|
|
or not os.path.exists(fname)
|
|
or (sha1_hash and not check_sha1(fname, sha1_hash))
|
|
):
|
|
dirname = os.path.dirname(os.path.abspath(os.path.expanduser(fname)))
|
|
if not os.path.exists(dirname):
|
|
os.makedirs(dirname)
|
|
|
|
print("Downloading %s from %s..." % (fname, url))
|
|
r = requests.get(url, stream=True)
|
|
if r.status_code != 200:
|
|
raise RuntimeError("Failed downloading url %s" % url)
|
|
total_length = r.headers.get("content-length")
|
|
with open(fname, "wb") as f:
|
|
if total_length is None: # no content length header
|
|
for chunk in r.iter_content(chunk_size=1024):
|
|
if chunk: # filter out keep-alive new chunks
|
|
f.write(chunk)
|
|
else:
|
|
total_length = int(total_length)
|
|
for chunk in tqdm(
|
|
r.iter_content(chunk_size=1024),
|
|
total=int(total_length / 1024.0 + 0.5),
|
|
unit="KB",
|
|
unit_scale=False,
|
|
dynamic_ncols=True,
|
|
):
|
|
f.write(chunk)
|
|
|
|
if sha1_hash and not check_sha1(fname, sha1_hash):
|
|
raise UserWarning(
|
|
"File {} is downloaded but the content hash does not match. "
|
|
"The repo may be outdated or download may be incomplete. "
|
|
'If the "repo_url" is overridden, consider switching to '
|
|
"the default repo.".format(fname)
|
|
)
|
|
|
|
return fname
|