file_utils.py 2.7 KB
Newer Older
M
Meiyim 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21
#   Copyright (c) 2018 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.
from __future__ import division
from __future__ import absolute_import
from __future__ import print_function
from __future__ import unicode_literals

import os
import logging
from tqdm import tqdm
M
Meiyim 已提交
22 23
from pathlib import Path
import six
Z
zhanghan17 已提交
24 25
import paddle as P
import time
M
Meiyim 已提交
26 27 28 29
if six.PY2:
    from pathlib2 import Path
else:
    from pathlib import Path
M
Meiyim 已提交
30 31 32

log = logging.getLogger(__name__)

C
chenxuyi 已提交
33 34 35 36

def _fetch_from_remote(url,
                       force_download=False,
                       cached_dir='~/.paddle-ernie-cache'):
M
Meiyim 已提交
37
    import hashlib, tempfile, requests, tarfile
Z
zhanghan17 已提交
38 39
    env = P.distributed.ParallelEnv()

M
Meiyim 已提交
40
    sig = hashlib.md5(url.encode('utf8')).hexdigest()
M
Meiyim 已提交
41 42 43 44 45 46
    cached_dir = Path(cached_dir).expanduser()
    try:
        cached_dir.mkdir()
    except OSError:
        pass
    cached_dir_model = cached_dir / sig
Z
zhanghan17 已提交
47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69
    done_file = cached_dir_model / 'fetch_done'
    if force_download or not done_file.exists():
        if env.dev_id == 0:
            cached_dir_model.mkdir()
            tmpfile = cached_dir_model / 'tmp'
            with tmpfile.open('wb') as f:
                r = requests.get(url, stream=True)
                total_len = int(r.headers.get('content-length'))
                for chunk in tqdm(
                        r.iter_content(chunk_size=1024),
                        total=total_len // 1024,
                        desc='downloading %s' % url,
                        unit='KB'):
                    if chunk:
                        f.write(chunk)
                        f.flush()
                log.debug('extacting... to %s' % tmpfile)
                with tarfile.open(tmpfile.as_posix()) as tf:
                    tf.extractall(path=cached_dir_model.as_posix())
            os.remove(tmpfile.as_posix())
            f = done_file.open('wb')
            f.close()
        else:
70 71 72
            while not done_file.exists():
                time.sleep(1)

M
Meiyim 已提交
73
    log.debug('%s cached in %s' % (url, cached_dir))
M
Meiyim 已提交
74
    return cached_dir_model
M
Meiyim 已提交
75

M
Meiyim 已提交
76 77 78 79 80 81

def add_docstring(doc):
    def func(f):
        f.__doc__ += ('\n======other docs from supper class ======\n%s' % doc)
        return f

C
chenxuyi 已提交
82
    return func