common.py 2.2 KB
Newer Older
D
dangqingqing 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14
# Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# 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.

15
import requests
Y
Yu Yang 已提交
16
import hashlib
Y
Yu Yang 已提交
17
import os
Y
Yu Yang 已提交
18
import shutil
H
Helin Wang 已提交
19
import sys
Y
Yu Yang 已提交
20

21
__all__ = ['DATA_HOME', 'download', 'md5file']
Y
Yu Yang 已提交
22

23
DATA_HOME = os.path.expanduser('~/.cache/paddle/dataset')
Y
Yu Yang 已提交
24 25 26

if not os.path.exists(DATA_HOME):
    os.makedirs(DATA_HOME)
Y
Yu Yang 已提交
27 28


29 30 31 32 33 34 35
def md5file(fname):
    hash_md5 = hashlib.md5()
    f = open(fname, "rb")
    for chunk in iter(lambda: f.read(4096), b""):
        hash_md5.update(chunk)
    f.close()
    return hash_md5.hexdigest()
36 37 38 39 40 41 42 43 44


def download(url, module_name, md5sum):
    dirname = os.path.join(DATA_HOME, module_name)
    if not os.path.exists(dirname):
        os.makedirs(dirname)

    filename = os.path.join(dirname, url.split('/')[-1])
    if not (os.path.exists(filename) and md5file(filename) == md5sum):
H
Helin Wang 已提交
45
        print "Cache file %s not found, downloading %s" % (filename, url)
46
        r = requests.get(url, stream=True)
H
Helin Wang 已提交
47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62
        total_length = r.headers.get('content-length')

        if total_length is None:
            with open(filename, 'w') as f:
                shutil.copyfileobj(r.raw, f)
        else:
            with open(filename, 'w') as f:
                dl = 0
                total_length = int(total_length)
                for data in r.iter_content(chunk_size=4096):
                    dl += len(data)
                    f.write(data)
                    done = int(50 * dl / total_length)
                    sys.stdout.write("\r[%s%s]" % ('=' * done,
                                                   ' ' * (50 - done)))
                    sys.stdout.flush()
63 64

    return filename
Y
Yi Wang 已提交
65 66 67 68 69 70 71


def dict_add(a_dict, ele):
    if ele in a_dict:
        a_dict[ele] += 1
    else:
        a_dict[ele] = 1