Update requests package to 2.10.0

This commit is contained in:
JonnyWong16 2016-05-02 23:26:10 -07:00
parent 7be651f5cf
commit 4043398e01
41 changed files with 3585 additions and 1534 deletions

View file

@ -1,13 +1,18 @@
from __future__ import absolute_import
from contextlib import contextmanager
import zlib
import io
from socket import timeout as SocketTimeout
from socket import error as SocketError
from ._collections import HTTPHeaderDict
from .exceptions import ProtocolError, DecodeError, ReadTimeoutError
from .packages.six import string_types as basestring, binary_type
from .exceptions import (
ProtocolError, DecodeError, ReadTimeoutError, ResponseNotChunked
)
from .packages.six import string_types as basestring, binary_type, PY3
from .packages.six.moves import http_client as httplib
from .connection import HTTPException, BaseSSLError
from .util.response import is_fp_closed
from .util.response import is_fp_closed, is_response_to_head
class DeflateDecoder(object):
@ -21,6 +26,9 @@ class DeflateDecoder(object):
return getattr(self._obj, name)
def decompress(self, data):
if not data:
return data
if not self._first_try:
return self._obj.decompress(data)
@ -36,9 +44,23 @@ class DeflateDecoder(object):
self._data = None
class GzipDecoder(object):
def __init__(self):
self._obj = zlib.decompressobj(16 + zlib.MAX_WBITS)
def __getattr__(self, name):
return getattr(self._obj, name)
def decompress(self, data):
if not data:
return data
return self._obj.decompress(data)
def _get_decoder(mode):
if mode == 'gzip':
return zlib.decompressobj(16 + zlib.MAX_WBITS)
return GzipDecoder()
return DeflateDecoder()
@ -76,9 +98,10 @@ class HTTPResponse(io.IOBase):
strict=0, preload_content=True, decode_content=True,
original_response=None, pool=None, connection=None):
self.headers = HTTPHeaderDict()
if headers:
self.headers.update(headers)
if isinstance(headers, HTTPHeaderDict):
self.headers = headers
else:
self.headers = HTTPHeaderDict(headers)
self.status = status
self.version = version
self.reason = reason
@ -100,6 +123,16 @@ class HTTPResponse(io.IOBase):
if hasattr(body, 'read'):
self._fp = body
# Are we using the chunked-style of transfer encoding?
self.chunked = False
self.chunk_left = None
tr_enc = self.headers.get('transfer-encoding', '').lower()
# Don't incur the penalty of creating a list and then discarding it
encodings = (enc.strip() for enc in tr_enc.split(","))
if "chunked" in encodings:
self.chunked = True
# If requested, preload the body.
if preload_content and not self._body:
self._body = self.read(decode_content=decode_content)
@ -140,6 +173,102 @@ class HTTPResponse(io.IOBase):
"""
return self._fp_bytes_read
def _init_decoder(self):
"""
Set-up the _decoder attribute if necessar.
"""
# Note: content-encoding value should be case-insensitive, per RFC 7230
# Section 3.2
content_encoding = self.headers.get('content-encoding', '').lower()
if self._decoder is None and content_encoding in self.CONTENT_DECODERS:
self._decoder = _get_decoder(content_encoding)
def _decode(self, data, decode_content, flush_decoder):
"""
Decode the data passed in and potentially flush the decoder.
"""
try:
if decode_content and self._decoder:
data = self._decoder.decompress(data)
except (IOError, zlib.error) as e:
content_encoding = self.headers.get('content-encoding', '').lower()
raise DecodeError(
"Received response with content-encoding: %s, but "
"failed to decode it." % content_encoding, e)
if flush_decoder and decode_content:
data += self._flush_decoder()
return data
def _flush_decoder(self):
"""
Flushes the decoder. Should only be called if the decoder is actually
being used.
"""
if self._decoder:
buf = self._decoder.decompress(b'')
return buf + self._decoder.flush()
return b''
@contextmanager
def _error_catcher(self):
"""
Catch low-level python exceptions, instead re-raising urllib3
variants, so that low-level exceptions are not leaked in the
high-level api.
On exit, release the connection back to the pool.
"""
clean_exit = False
try:
try:
yield
except SocketTimeout:
# FIXME: Ideally we'd like to include the url in the ReadTimeoutError but
# there is yet no clean way to get at it from this context.
raise ReadTimeoutError(self._pool, None, 'Read timed out.')
except BaseSSLError as e:
# FIXME: Is there a better way to differentiate between SSLErrors?
if 'read operation timed out' not in str(e): # Defensive:
# This shouldn't happen but just in case we're missing an edge
# case, let's avoid swallowing SSL errors.
raise
raise ReadTimeoutError(self._pool, None, 'Read timed out.')
except (HTTPException, SocketError) as e:
# This includes IncompleteRead.
raise ProtocolError('Connection broken: %r' % e, e)
# If no exception is thrown, we should avoid cleaning up
# unnecessarily.
clean_exit = True
finally:
# If we didn't terminate cleanly, we need to throw away our
# connection.
if not clean_exit:
# The response may not be closed but we're not going to use it
# anymore so close it now to ensure that the connection is
# released back to the pool.
if self._original_response:
self._original_response.close()
# Closing the response may not actually be sufficient to close
# everything, so if we have a hold of the connection close that
# too.
if self._connection:
self._connection.close()
# If we hold the original response but it's closed now, we should
# return the connection back to the pool.
if self._original_response and self._original_response.isclosed():
self.release_conn()
def read(self, amt=None, decode_content=None, cache_content=False):
"""
Similar to :meth:`httplib.HTTPResponse.read`, but with two additional
@ -161,12 +290,7 @@ class HTTPResponse(io.IOBase):
after having ``.read()`` the file object. (Overridden if ``amt`` is
set.)
"""
# Note: content-encoding value should be case-insensitive, per RFC 7230
# Section 3.2
content_encoding = self.headers.get('content-encoding', '').lower()
if self._decoder is None:
if content_encoding in self.CONTENT_DECODERS:
self._decoder = _get_decoder(content_encoding)
self._init_decoder()
if decode_content is None:
decode_content = self.decode_content
@ -174,67 +298,36 @@ class HTTPResponse(io.IOBase):
return
flush_decoder = False
data = None
try:
try:
if amt is None:
# cStringIO doesn't like amt=None
data = self._fp.read()
with self._error_catcher():
if amt is None:
# cStringIO doesn't like amt=None
data = self._fp.read()
flush_decoder = True
else:
cache_content = False
data = self._fp.read(amt)
if amt != 0 and not data: # Platform-specific: Buggy versions of Python.
# Close the connection when no data is returned
#
# This is redundant to what httplib/http.client _should_
# already do. However, versions of python released before
# December 15, 2012 (http://bugs.python.org/issue16298) do
# not properly close the connection in all cases. There is
# no harm in redundantly calling close.
self._fp.close()
flush_decoder = True
else:
cache_content = False
data = self._fp.read(amt)
if amt != 0 and not data: # Platform-specific: Buggy versions of Python.
# Close the connection when no data is returned
#
# This is redundant to what httplib/http.client _should_
# already do. However, versions of python released before
# December 15, 2012 (http://bugs.python.org/issue16298) do
# not properly close the connection in all cases. There is
# no harm in redundantly calling close.
self._fp.close()
flush_decoder = True
except SocketTimeout:
# FIXME: Ideally we'd like to include the url in the ReadTimeoutError but
# there is yet no clean way to get at it from this context.
raise ReadTimeoutError(self._pool, None, 'Read timed out.')
except BaseSSLError as e:
# FIXME: Is there a better way to differentiate between SSLErrors?
if not 'read operation timed out' in str(e): # Defensive:
# This shouldn't happen but just in case we're missing an edge
# case, let's avoid swallowing SSL errors.
raise
raise ReadTimeoutError(self._pool, None, 'Read timed out.')
except HTTPException as e:
# This includes IncompleteRead.
raise ProtocolError('Connection broken: %r' % e, e)
if data:
self._fp_bytes_read += len(data)
try:
if decode_content and self._decoder:
data = self._decoder.decompress(data)
except (IOError, zlib.error) as e:
raise DecodeError(
"Received response with content-encoding: %s, but "
"failed to decode it." % content_encoding, e)
if flush_decoder and decode_content and self._decoder:
buf = self._decoder.decompress(binary_type())
data += buf + self._decoder.flush()
data = self._decode(data, decode_content, flush_decoder)
if cache_content:
self._body = data
return data
finally:
if self._original_response and self._original_response.isclosed():
self.release_conn()
return data
def stream(self, amt=2**16, decode_content=None):
"""
@ -252,11 +345,15 @@ class HTTPResponse(io.IOBase):
If True, will attempt to decode the body based on the
'content-encoding' header.
"""
while not is_fp_closed(self._fp):
data = self.read(amt=amt, decode_content=decode_content)
if self.chunked:
for line in self.read_chunked(amt, decode_content=decode_content):
yield line
else:
while not is_fp_closed(self._fp):
data = self.read(amt=amt, decode_content=decode_content)
if data:
yield data
if data:
yield data
@classmethod
def from_httplib(ResponseCls, r, **response_kw):
@ -267,14 +364,17 @@ class HTTPResponse(io.IOBase):
Remaining parameters are passed to the HTTPResponse constructor, along
with ``original_response=r``.
"""
headers = r.msg
headers = HTTPHeaderDict()
for k, v in r.getheaders():
headers.add(k, v)
if not isinstance(headers, HTTPHeaderDict):
if PY3: # Python 3
headers = HTTPHeaderDict(headers.items())
else: # Python 2
headers = HTTPHeaderDict.from_httplib(headers)
# HTTPResponse objects in Python 3 don't have a .strict attribute
strict = getattr(r, 'strict', 0)
return ResponseCls(body=r,
resp = ResponseCls(body=r,
headers=headers,
status=r.status,
version=r.version,
@ -282,6 +382,7 @@ class HTTPResponse(io.IOBase):
strict=strict,
original_response=r,
**response_kw)
return resp
# Backwards-compatibility methods for httplib.HTTPResponse
def getheaders(self):
@ -295,6 +396,9 @@ class HTTPResponse(io.IOBase):
if not self.closed:
self._fp.close()
if self._connection:
self._connection.close()
@property
def closed(self):
if self._fp is None:
@ -331,3 +435,92 @@ class HTTPResponse(io.IOBase):
else:
b[:len(temp)] = temp
return len(temp)
def _update_chunk_length(self):
# First, we'll figure out length of a chunk and then
# we'll try to read it from socket.
if self.chunk_left is not None:
return
line = self._fp.fp.readline()
line = line.split(b';', 1)[0]
try:
self.chunk_left = int(line, 16)
except ValueError:
# Invalid chunked protocol response, abort.
self.close()
raise httplib.IncompleteRead(line)
def _handle_chunk(self, amt):
returned_chunk = None
if amt is None:
chunk = self._fp._safe_read(self.chunk_left)
returned_chunk = chunk
self._fp._safe_read(2) # Toss the CRLF at the end of the chunk.
self.chunk_left = None
elif amt < self.chunk_left:
value = self._fp._safe_read(amt)
self.chunk_left = self.chunk_left - amt
returned_chunk = value
elif amt == self.chunk_left:
value = self._fp._safe_read(amt)
self._fp._safe_read(2) # Toss the CRLF at the end of the chunk.
self.chunk_left = None
returned_chunk = value
else: # amt > self.chunk_left
returned_chunk = self._fp._safe_read(self.chunk_left)
self._fp._safe_read(2) # Toss the CRLF at the end of the chunk.
self.chunk_left = None
return returned_chunk
def read_chunked(self, amt=None, decode_content=None):
"""
Similar to :meth:`HTTPResponse.read`, but with an additional
parameter: ``decode_content``.
:param decode_content:
If True, will attempt to decode the body based on the
'content-encoding' header.
"""
self._init_decoder()
# FIXME: Rewrite this method and make it a class with a better structured logic.
if not self.chunked:
raise ResponseNotChunked(
"Response is not chunked. "
"Header 'transfer-encoding: chunked' is missing.")
# Don't bother reading the body of a HEAD request.
if self._original_response and is_response_to_head(self._original_response):
self._original_response.close()
return
with self._error_catcher():
while True:
self._update_chunk_length()
if self.chunk_left == 0:
break
chunk = self._handle_chunk(amt)
decoded = self._decode(chunk, decode_content=decode_content,
flush_decoder=False)
if decoded:
yield decoded
if decode_content:
# On CPython and PyPy, we should never need to flush the
# decoder. However, on Jython we *might* need to, so
# lets defensively do it anyway.
decoded = self._flush_decoder()
if decoded: # Platform-specific: Jython.
yield decoded
# Chunk content ends with \r\n: discard it.
while True:
line = self._fp.fp.readline()
if not line:
# Some sites may not end with '\r\n'.
break
if line == b'\r\n':
break
# We read everything; close the "file".
if self._original_response:
self._original_response.close()