Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Replace HTTP with HTTPS in enwiki URLs #3459

Merged
merged 1 commit into from
Apr 29, 2023
Merged

Replace HTTP with HTTPS in enwiki URLs #3459

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions docs/notebooks/Word2Vec_FastText_Comparison.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,7 +40,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
"--2019-05-12 19:40:14-- http://mattmahoney.net/dc/enwik9.zip\n",
"--2019-05-12 19:40:14-- https://mattmahoney.net/dc/enwik9.zip\n",
"Resolving mattmahoney.net (mattmahoney.net)... 67.195.197.75\n",
"Connecting to mattmahoney.net (mattmahoney.net)|67.195.197.75|:80... connected.\n",
"HTTP request sent, awaiting response... 200 OK\n",
Expand All @@ -51,7 +51,7 @@
"\n",
"2019-05-12 19:50:17 (247 KB/s) - Connection closed at byte 152553031. Retrying.\n",
"\n",
"--2019-05-12 19:50:18-- (try: 2) http://mattmahoney.net/dc/enwik9.zip\n",
"--2019-05-12 19:50:18-- (try: 2) https://mattmahoney.net/dc/enwik9.zip\n",
"Connecting to mattmahoney.net (mattmahoney.net)|67.195.197.75|:80... connected.\n",
"HTTP request sent, awaiting response... 206 Partial Content\n",
"Length: 322592222 (308M), 170039191 (162M) remaining [application/zip]\n",
Expand Down Expand Up @@ -83,11 +83,11 @@
"# download the text8 corpus (a 100 MB sample of cleaned wikipedia text)\n",
"import os.path\n",
"if not os.path.isfile('text8'):\n",
" !wget -c http://mattmahoney.net/dc/text8.zip\n",
" !wget -c https://mattmahoney.net/dc/text8.zip\n",
" !unzip text8.zip\n",
"# download and preprocess the text9 corpus\n",
"if not os.path.isfile('text9'):\n",
" !wget -c http://mattmahoney.net/dc/enwik9.zip\n",
" !wget -c https://mattmahoney.net/dc/enwik9.zip\n",
" !unzip enwik9.zip\n",
" !perl {FT_HOME}wikifil.pl enwik9 > text9"
]
Expand Down
2 changes: 1 addition & 1 deletion docs/notebooks/Wordrank_comparisons.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,7 +62,7 @@
"# download the text8 corpus (a 100 MB sample of preprocessed wikipedia text)\n",
"import os.path\n",
"if not os.path.isfile('text8'):\n",
" !wget -c http://mattmahoney.net/dc/text8.zip\n",
" !wget -c https://mattmahoney.net/dc/text8.zip\n",
" !unzip text8.zip"
]
},
Expand Down
2 changes: 1 addition & 1 deletion docs/notebooks/downloader_api_tutorial.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -328,7 +328,7 @@
" \"parts\": 3\n",
" }, \n",
" \"text8\": {\n",
" \"source\": \"http://mattmahoney.net/dc/text8.zip\", \n",
" \"source\": \"https://mattmahoney.net/dc/text8.zip\", \n",
" \"checksum\": \"68799af40b6bda07dfa47a32612e5364\", \n",
" \"parts\": 1, \n",
" \"description\": \"Cleaned small sample from wikipedia\", \n",
Expand Down
4 changes: 2 additions & 2 deletions docs/notebooks/nmslibtutorial.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -87,7 +87,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
"--2019-06-27 13:48:42-- http://mattmahoney.net/dc/text8.zip\n",
"--2019-06-27 13:48:42-- https://mattmahoney.net/dc/text8.zip\n",
"Resolving mattmahoney.net... 67.195.197.75\n",
"Connecting to mattmahoney.net|67.195.197.75|:80... connected.\n",
"HTTP request sent, awaiting response... 200 OK\n",
Expand All @@ -106,7 +106,7 @@
"source": [
"import os.path\n",
"if not os.path.isfile('text8'):\n",
" !wget -c http://mattmahoney.net/dc/text8.zip\n",
" !wget -c https://mattmahoney.net/dc/text8.zip\n",
" !unzip text8.zip"
]
},
Expand Down
2 changes: 1 addition & 1 deletion docs/src/auto_examples/howtos/run_downloader_api.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -335,7 +335,7 @@ Here's how to list all resources available in gensim-data:
"checksum": "68799af40b6bda07dfa47a32612e5364",
"file_name": "text8.gz",
"read_more": [
"http://mattmahoney.net/dc/textdata.html"
"https://mattmahoney.net/dc/textdata.html"
],
"parts": 1
},
Expand Down
2 changes: 1 addition & 1 deletion gensim/downloader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -260,7 +260,7 @@ def info(name=None, show_only_latest=True, name_only=False):
u'description': u'Cleaned small sample from wikipedia',
u'file_name': u'text8.gz',
u'parts': 1,
u'source': u'http://mattmahoney.net/dc/text8.zip'}
u'source': u'https://mattmahoney.net/dc/text8.zip'}
>>>
>>> api.info() # retrieve information about all available datasets and models

Expand Down
2 changes: 1 addition & 1 deletion gensim/models/word2vec.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2041,7 +2041,7 @@ def __iter__(self):

class Text8Corpus:
def __init__(self, fname, max_sentence_length=MAX_WORDS_IN_BATCH):
"""Iterate over sentences from the "text8" corpus, unzipped from http://mattmahoney.net/dc/text8.zip."""
"""Iterate over sentences from the "text8" corpus, unzipped from https://mattmahoney.net/dc/text8.zip."""
self.fname = fname
self.max_sentence_length = max_sentence_length

Expand Down
2 changes: 1 addition & 1 deletion gensim/scripts/benchmark.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,6 @@
print(globals()['__doc__'] % locals())
sys.exit(1)

corpus = Text8Corpus(sys.argv[1]) # text8/text9 format from http://mattmahoney.net/dc/textdata.html
corpus = Text8Corpus(sys.argv[1]) # text8/text9 format from https://mattmahoney.net/dc/textdata.html
cls = FastText
cls(corpus, workers=12, epochs=1).save(f'/tmp/{cls.__name__}.gensim{__version__}')