utils.py 2.85 KB
Newer Older
soumith's avatar
soumith committed
1
import os
soumith's avatar
soumith committed
2
import os.path
soumith's avatar
soumith committed
3
4
import hashlib
import errno
5
6
7
8
9
10
11
12
13
from tqdm import tqdm


def gen_bar_updator(pbar):
    def bar_update(count, block_size, total_size):
        pbar.total = total_size / block_size
        pbar.update(count)

    return bar_update
soumith's avatar
soumith committed
14

soumith's avatar
soumith committed
15

16
17
18
def check_integrity(fpath, md5):
    if not os.path.isfile(fpath):
        return False
soumith's avatar
soumith committed
19
    md5o = hashlib.md5()
soumith's avatar
soumith committed
20
    with open(fpath, 'rb') as f:
soumith's avatar
soumith committed
21
        # read in 1MB chunks
22
        for chunk in iter(lambda: f.read(1024 * 1024), b''):
soumith's avatar
soumith committed
23
24
            md5o.update(chunk)
    md5c = md5o.hexdigest()
25
26
27
28
29
    if md5c != md5:
        return False
    return True


soumith's avatar
soumith committed
30
def download_url(url, root, filename, md5):
31
32
    from six.moves import urllib

33
    root = os.path.expanduser(root)
34
35
36
37
38
39
40
41
42
43
44
45
46
47
    fpath = os.path.join(root, filename)

    try:
        os.makedirs(root)
    except OSError as e:
        if e.errno == errno.EEXIST:
            pass
        else:
            raise

    # downloads file
    if os.path.isfile(fpath) and check_integrity(fpath, md5):
        print('Using downloaded and verified file: ' + fpath)
    else:
Tzu-Wei Huang's avatar
Tzu-Wei Huang committed
48
49
        try:
            print('Downloading ' + url + ' to ' + fpath)
50
            urllib.request.urlretrieve(url, fpath, reporthook=gen_bar_updator(tqdm()))
Tzu-Wei Huang's avatar
Tzu-Wei Huang committed
51
52
53
54
55
56
        except:
            if url[:5] == 'https':
                url = url.replace('https:', 'http:')
                print('Failed download. Trying https -> http instead.'
                      ' Downloading ' + url + ' to ' + fpath)
                urllib.request.urlretrieve(url, fpath)
Sanyam Kapoor's avatar
Sanyam Kapoor committed
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102


def list_dir(root, prefix=False):
    """List all directories at a given root

    Args:
        root (str): Path to directory whose folders need to be listed
        prefix (bool, optional): If true, prepends the path to each result, otherwise
            only returns the name of the directories found
    """
    root = os.path.expanduser(root)
    directories = list(
        filter(
            lambda p: os.path.isdir(os.path.join(root, p)),
            os.listdir(root)
        )
    )

    if prefix is True:
        directories = [os.path.join(root, d) for d in directories]

    return directories


def list_files(root, suffix, prefix=False):
    """List all files ending with a suffix at a given root

    Args:
        root (str): Path to directory whose folders need to be listed
        suffix (str or tuple): Suffix of the files to match, e.g. '.png' or ('.jpg', '.png').
            It uses the Python "str.endswith" method and is passed directly
        prefix (bool, optional): If true, prepends the path to each result, otherwise
            only returns the name of the files found
    """
    root = os.path.expanduser(root)
    files = list(
        filter(
            lambda p: os.path.isfile(os.path.join(root, p)) and p.endswith(suffix),
            os.listdir(root)
        )
    )

    if prefix is True:
        files = [os.path.join(root, d) for d in files]

    return files