97 lines
4.0 KiB
Python
97 lines
4.0 KiB
Python
from typing import Dict, Generator
|
|
|
|
from pip._vendor.requests.models import CONTENT_CHUNK_SIZE, Response
|
|
|
|
from pip._internal.exceptions import NetworkConnectionError
|
|
|
|
# The following comments and HTTP headers were originally added by
|
|
# Donald Stufft in git commit 22c562429a61bb77172039e480873fb239dd8c03.
|
|
#
|
|
# We use Accept-Encoding: identity here because requests defaults to
|
|
# accepting compressed responses. This breaks in a variety of ways
|
|
# depending on how the server is configured.
|
|
# - Some servers will notice that the file isn't a compressible file
|
|
# and will leave the file alone and with an empty Content-Encoding
|
|
# - Some servers will notice that the file is already compressed and
|
|
# will leave the file alone, adding a Content-Encoding: gzip header
|
|
# - Some servers won't notice anything at all and will take a file
|
|
# that's already been compressed and compress it again, and set
|
|
# the Content-Encoding: gzip header
|
|
# By setting this to request only the identity encoding we're hoping
|
|
# to eliminate the third case. Hopefully there does not exist a server
|
|
# which when given a file will notice it is already compressed and that
|
|
# you're not asking for a compressed file and will then decompress it
|
|
# before sending because if that's the case I don't think it'll ever be
|
|
# possible to make this work.
|
|
HEADERS: Dict[str, str] = {"Accept-Encoding": "identity"}
|
|
|
|
|
|
def raise_for_status(resp: Response) -> None:
|
|
http_error_msg = ""
|
|
if isinstance(resp.reason, bytes):
|
|
# We attempt to decode utf-8 first because some servers
|
|
# choose to localize their reason strings. If the string
|
|
# isn't utf-8, we fall back to iso-8859-1 for all other
|
|
# encodings.
|
|
try:
|
|
reason = resp.reason.decode("utf-8")
|
|
except UnicodeDecodeError:
|
|
reason = resp.reason.decode("iso-8859-1")
|
|
else:
|
|
reason = resp.reason
|
|
|
|
if 400 <= resp.status_code < 500:
|
|
http_error_msg = (
|
|
f"{resp.status_code} Client Error: {reason} for url: {resp.url}"
|
|
)
|
|
|
|
elif 500 <= resp.status_code < 600:
|
|
http_error_msg = (
|
|
f"{resp.status_code} Server Error: {reason} for url: {resp.url}"
|
|
)
|
|
|
|
if http_error_msg:
|
|
raise NetworkConnectionError(http_error_msg, response=resp)
|
|
|
|
|
|
def response_chunks(
|
|
response: Response, chunk_size: int = CONTENT_CHUNK_SIZE
|
|
) -> Generator[bytes, None, None]:
|
|
"""Given a requests Response, provide the data chunks."""
|
|
try:
|
|
# Special case for urllib3.
|
|
for chunk in response.raw.stream(
|
|
chunk_size,
|
|
# We use decode_content=False here because we don't
|
|
# want urllib3 to mess with the raw bytes we get
|
|
# from the server. If we decompress inside of
|
|
# urllib3 then we cannot verify the checksum
|
|
# because the checksum will be of the compressed
|
|
# file. This breakage will only occur if the
|
|
# server adds a Content-Encoding header, which
|
|
# depends on how the server was configured:
|
|
# - Some servers will notice that the file isn't a
|
|
# compressible file and will leave the file alone
|
|
# and with an empty Content-Encoding
|
|
# - Some servers will notice that the file is
|
|
# already compressed and will leave the file
|
|
# alone and will add a Content-Encoding: gzip
|
|
# header
|
|
# - Some servers won't notice anything at all and
|
|
# will take a file that's already been compressed
|
|
# and compress it again and set the
|
|
# Content-Encoding: gzip header
|
|
#
|
|
# By setting this not to decode automatically we
|
|
# hope to eliminate problems with the second case.
|
|
decode_content=False,
|
|
):
|
|
yield chunk
|
|
except AttributeError:
|
|
# Standard file-like object.
|
|
while True:
|
|
chunk = response.raw.read(chunk_size)
|
|
if not chunk:
|
|
break
|
|
yield chunk
|