From 26f57173442df5f3c300c7cf92c43916f5687f31 Mon Sep 17 00:00:00 2001
From: Leonard Lausen <leonard@lausen.nl>
Date: Tue, 3 Jul 2018 23:03:32 +0000
Subject: [PATCH] Remove gluon.utils.download copy with verify_ssl support

The problematic server now servers a valid SSL certificate.
---
 gluonnlp/data/word_embedding_evaluation.py | 64 +---------------------
 1 file changed, 2 insertions(+), 62 deletions(-)

diff --git a/gluonnlp/data/word_embedding_evaluation.py b/gluonnlp/data/word_embedding_evaluation.py
index 0719953c08..0056f0387b 100644
--- a/gluonnlp/data/word_embedding_evaluation.py
+++ b/gluonnlp/data/word_embedding_evaluation.py
@@ -25,7 +25,7 @@
 import zipfile
 
 from mxnet.gluon.data.dataset import SimpleDataset
-from mxnet.gluon.utils import check_sha1, _get_repo_file_url
+from mxnet.gluon.utils import check_sha1, _get_repo_file_url, download
 
 from .. import _constants as C
 from .dataset import CorpusDataset
@@ -52,68 +52,10 @@ class requests_failed_to_import(object):
 __all__ = base_datasets + word_similarity_datasets + word_analogy_datasets
 
 
-# TODO Remove once verify support is merged in mxnet.gluon.utils.download
-def download(url, path=None, overwrite=False, sha1_hash=None, verify=True):
-    """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.
-    verify : bool
-        Toggle verification of SSL certificates.
-
-    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, verify=verify)
-        if r.status_code != 200:
-            raise RuntimeError('Failed downloading url %s' % url)
-        with open(fname, 'wb') as f:
-            for chunk in r.iter_content(chunk_size=1024):
-                if chunk:  # filter out keep-alive new chunks
-                    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
-
-
 class _Dataset(SimpleDataset):
     _url = None  # Dataset is retrieved from here if not cached
     _archive_file = (None, None)  # Archive name and checksum
     _checksums = None  # Checksum of archive contents
-    _verify_ssl = True  # Verify SSL certificates when downloading from self._url
     _namespace = None  # Contains S3 namespace for self-hosted datasets
 
     def __init__(self, root):
@@ -135,8 +77,7 @@ def _download_data(self):
                 else:
                     url = self._url
                 downloaded_file_path = download(url, path=self.root,
-                                                sha1_hash=archive_hash,
-                                                verify=self._verify_ssl)
+                                                sha1_hash=archive_hash)
 
                 if downloaded_file_path.lower().endswith('zip'):
                     with zipfile.ZipFile(downloaded_file_path, 'r') as zf:
@@ -644,7 +585,6 @@ class BakerVerb143(WordSimilarityEvaluationDataset):
         'verb_similarity dataset.txt':
         'd7e4820c7504cbae56898353e4d94e6408c330fc'
     }
-    _verify_ssl = False  # ie.technion.ac.il serves an invalid cert as of 2018-04-16
 
     min = 0
     max = 10