File size: 9,610 Bytes
f65b4f1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
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
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
# This file is derived from the code at
# https://github.com/huggingface/transformers/blob/master/transformers/file_utils.py
# and the code at
# https://github.com/allenai/allennlp/blob/master/allennlp/common/file_utils.py.
#
# Original copyright notice:
#
# This file is adapted from the AllenNLP library at https://github.com/allenai/allennlp
# Copyright by the AllenNLP authors.
"""Utilities for working with the local dataset cache."""

from __future__ import (absolute_import, division, print_function, unicode_literals)

import sys
import json
import logging
import os
import shutil
import tempfile
import fnmatch
from functools import wraps
from hashlib import sha256
import sys
from io import open

import boto3
import requests
from botocore.exceptions import ClientError
from tqdm import tqdm

try:
    from torch.hub import _get_torch_home

    torch_cache_home = _get_torch_home()
except ImportError:
    torch_cache_home = os.path.expanduser(
        os.getenv('TORCH_HOME', os.path.join(
            os.getenv('XDG_CACHE_HOME', '~/.cache'), 'torch')))
default_cache_path = os.path.join(torch_cache_home, 'pytorch_pretrained_bert')

try:
    from urllib.parse import urlparse
except ImportError:
    from urlparse import urlparse

try:
    from pathlib import Path

    PYTORCH_PRETRAINED_BERT_CACHE = Path(
        os.getenv('PYTORCH_PRETRAINED_BERT_CACHE', default_cache_path))
except (AttributeError, ImportError):
    PYTORCH_PRETRAINED_BERT_CACHE = os.getenv('PYTORCH_PRETRAINED_BERT_CACHE',
                                              default_cache_path)

CONFIG_NAME = "config.json"
WEIGHTS_NAME = "pytorch_model.bin"

logger = logging.getLogger(__name__)  # pylint: disable=invalid-name


def url_to_filename(url, etag=None):
    """
    Convert `url` into a hashed filename in a repeatable way.
    If `etag` is specified, append its hash to the url's, delimited
    by a period.
    """
    url_bytes = url.encode('utf-8')
    url_hash = sha256(url_bytes)
    filename = url_hash.hexdigest()

    if etag:
        etag_bytes = etag.encode('utf-8')
        etag_hash = sha256(etag_bytes)
        filename += '.' + etag_hash.hexdigest()

    return filename


def filename_to_url(filename, cache_dir=None):
    """
    Return the url and etag (which may be ``None``) stored for `filename`.
    Raise ``EnvironmentError`` if `filename` or its stored metadata do not exist.
    """
    if cache_dir is None:
        cache_dir = PYTORCH_PRETRAINED_BERT_CACHE
    if sys.version_info[0] == 3 and isinstance(cache_dir, Path):
        cache_dir = str(cache_dir)

    cache_path = os.path.join(cache_dir, filename)
    if not os.path.exists(cache_path):
        raise EnvironmentError("file {} not found".format(cache_path))

    meta_path = cache_path + '.json'
    if not os.path.exists(meta_path):
        raise EnvironmentError("file {} not found".format(meta_path))

    with open(meta_path, encoding="utf-8") as meta_file:
        metadata = json.load(meta_file)
    url = metadata['url']
    etag = metadata['etag']

    return url, etag


def cached_path(url_or_filename, cache_dir=None):
    """
    Given something that might be a URL (or might be a local path),
    determine which. If it's a URL, download the file and cache it, and
    return the path to the cached file. If it's already a local path,
    make sure the file exists and then return the path.
    """
    if cache_dir is None:
        cache_dir = PYTORCH_PRETRAINED_BERT_CACHE
    if sys.version_info[0] == 3 and isinstance(url_or_filename, Path):
        url_or_filename = str(url_or_filename)
    if sys.version_info[0] == 3 and isinstance(cache_dir, Path):
        cache_dir = str(cache_dir)

    parsed = urlparse(url_or_filename)

    if parsed.scheme in ('http', 'https', 's3'):
        # URL, so get it from the cache (downloading if necessary)
        return get_from_cache(url_or_filename, cache_dir)
    elif os.path.exists(url_or_filename):
        # File, and it exists.
        return url_or_filename
    elif parsed.scheme == '':
        # File, but it doesn't exist.
        raise EnvironmentError("file {} not found".format(url_or_filename))
    else:
        # Something unknown
        raise ValueError("unable to parse {} as a URL or as a local path".format(url_or_filename))


def split_s3_path(url):
    """Split a full s3 path into the bucket name and path."""
    parsed = urlparse(url)
    if not parsed.netloc or not parsed.path:
        raise ValueError("bad s3 path {}".format(url))
    bucket_name = parsed.netloc
    s3_path = parsed.path
    # Remove '/' at beginning of path.
    if s3_path.startswith("/"):
        s3_path = s3_path[1:]
    return bucket_name, s3_path


def s3_request(func):
    """
    Wrapper function for s3 requests in order to create more helpful error
    messages.
    """

    @wraps(func)
    def wrapper(url, *args, **kwargs):
        try:
            return func(url, *args, **kwargs)
        except ClientError as exc:
            if int(exc.response["Error"]["Code"]) == 404:
                raise EnvironmentError("file {} not found".format(url))
            else:
                raise

    return wrapper


@s3_request
def s3_etag(url):
    """Check ETag on S3 object."""
    s3_resource = boto3.resource("s3")
    bucket_name, s3_path = split_s3_path(url)
    s3_object = s3_resource.Object(bucket_name, s3_path)
    return s3_object.e_tag


@s3_request
def s3_get(url, temp_file):
    """Pull a file directly from S3."""
    s3_resource = boto3.resource("s3")
    bucket_name, s3_path = split_s3_path(url)
    s3_resource.Bucket(bucket_name).download_fileobj(s3_path, temp_file)


def http_get(url, temp_file):
    req = requests.get(url, stream=True)
    content_length = req.headers.get('Content-Length')
    total = int(content_length) if content_length is not None else None
    progress = tqdm(unit="B", total=total)
    for chunk in req.iter_content(chunk_size=1024):
        if chunk:  # filter out keep-alive new chunks
            progress.update(len(chunk))
            temp_file.write(chunk)
    progress.close()


def get_from_cache(url, cache_dir=None):
    """
    Given a URL, look for the corresponding dataset in the local cache.
    If it's not there, download it. Then return the path to the cached file.
    """
    if cache_dir is None:
        cache_dir = PYTORCH_PRETRAINED_BERT_CACHE
    if sys.version_info[0] == 3 and isinstance(cache_dir, Path):
        cache_dir = str(cache_dir)

    if not os.path.exists(cache_dir):
        os.makedirs(cache_dir)

    # Get eTag to add to filename, if it exists.
    if url.startswith("s3://"):
        etag = s3_etag(url)
    else:
        try:
            response = requests.head(url, allow_redirects=True)
            if response.status_code != 200:
                etag = None
            else:
                etag = response.headers.get("ETag")
        except EnvironmentError:
            etag = None

    if sys.version_info[0] == 2 and etag is not None:
        etag = etag.decode('utf-8')
    filename = url_to_filename(url, etag)

    # get cache path to put the file
    cache_path = os.path.join(cache_dir, filename)

    # If we don't have a connection (etag is None) and can't identify the file
    # try to get the last downloaded one
    if not os.path.exists(cache_path) and etag is None:
        matching_files = fnmatch.filter(os.listdir(cache_dir), filename + '.*')
        matching_files = list(filter(lambda s: not s.endswith('.json'), matching_files))
        if matching_files:
            cache_path = os.path.join(cache_dir, matching_files[-1])

    if not os.path.exists(cache_path):
        # Download to temporary file, then copy to cache dir once finished.
        # Otherwise you get corrupt cache entries if the download gets interrupted.
        with tempfile.NamedTemporaryFile() as temp_file:
            logger.info("%s not found in cache, downloading to %s", url, temp_file.name)

            # GET file object
            if url.startswith("s3://"):
                s3_get(url, temp_file)
            else:
                http_get(url, temp_file)

            # we are copying the file before closing it, so flush to avoid truncation
            temp_file.flush()
            # shutil.copyfileobj() starts at the current position, so go to the start
            temp_file.seek(0)

            logger.info("copying %s to cache at %s", temp_file.name, cache_path)
            with open(cache_path, 'wb') as cache_file:
                shutil.copyfileobj(temp_file, cache_file)

            logger.info("creating metadata file for %s", cache_path)
            meta = {'url': url, 'etag': etag}
            meta_path = cache_path + '.json'
            with open(meta_path, 'w') as meta_file:
                output_string = json.dumps(meta)
                if sys.version_info[0] == 2 and isinstance(output_string, str):
                    output_string = unicode(output_string, 'utf-8')  # The beauty of python 2
                meta_file.write(output_string)

            logger.info("removing temp file %s", temp_file.name)

    return cache_path


def read_set_from_file(filename):
    '''
    Extract a de-duped collection (set) of text from a file.
    Expected file format is one item per line.
    '''
    collection = set()
    with open(filename, 'r', encoding='utf-8') as file_:
        for line in file_:
            collection.add(line.rstrip())
    return collection


def get_file_extension(path, dot=True, lower=True):
    ext = os.path.splitext(path)[1]
    ext = ext if dot else ext[1:]
    return ext.lower() if lower else ext