Learn more  » Push, build, and install  RubyGems npm packages Python packages Maven artifacts PHP packages Go Modules Bower components Debian packages RPM packages NuGet packages

aroundthecode / pip   python

Repository URL to install this package:

Version: 18.1 

/ _vendor / urllib3 / connectionpool.py

from __future__ import absolute_import
import errno
import logging
import sys
import warnings

from socket import error as SocketError, timeout as SocketTimeout
import socket


from .exceptions import (
    ClosedPoolError,
    ProtocolError,
    EmptyPoolError,
    HeaderParsingError,
    HostChangedError,
    LocationValueError,
    MaxRetryError,
    ProxyError,
    ReadTimeoutError,
    SSLError,
    TimeoutError,
    InsecureRequestWarning,
    NewConnectionError,
)
from .packages.ssl_match_hostname import CertificateError
from .packages import six
from .packages.six.moves import queue
from .connection import (
    port_by_scheme,
    DummyConnection,
    HTTPConnection, HTTPSConnection, VerifiedHTTPSConnection,
    HTTPException, BaseSSLError,
)
from .request import RequestMethods
from .response import HTTPResponse

from .util.connection import is_connection_dropped
from .util.request import set_file_position
from .util.response import assert_header_parsing
from .util.retry import Retry
from .util.timeout import Timeout
from .util.url import get_host, Url, NORMALIZABLE_SCHEMES
from .util.queue import LifoQueue


xrange = six.moves.xrange

log = logging.getLogger(__name__)

_Default = object()


# Pool objects
class ConnectionPool(object):
    """
    Base class for all connection pools, such as
    :class:`.HTTPConnectionPool` and :class:`.HTTPSConnectionPool`.
    """

    scheme = None
    QueueCls = LifoQueue

    def __init__(self, host, port=None):
        if not host:
            raise LocationValueError("No host specified.")

        self.host = _ipv6_host(host, self.scheme)
        self._proxy_host = host.lower()
        self.port = port

    def __str__(self):
        return '%s(host=%r, port=%r)' % (type(self).__name__,
                                         self.host, self.port)

    def __enter__(self):
        return self

    def __exit__(self, exc_type, exc_val, exc_tb):
        self.close()
        # Return False to re-raise any potential exceptions
        return False

    def close(self):
        """
        Close all pooled connections and disable the pool.
        """
        pass


# This is taken from http://hg.python.org/cpython/file/7aaba721ebc0/Lib/socket.py#l252
_blocking_errnos = set([errno.EAGAIN, errno.EWOULDBLOCK])


class HTTPConnectionPool(ConnectionPool, RequestMethods):
    """
    Thread-safe connection pool for one host.

    :param host:
        Host used for this HTTP Connection (e.g. "localhost"), passed into
        :class:`httplib.HTTPConnection`.

    :param port:
        Port used for this HTTP Connection (None is equivalent to 80), passed
        into :class:`httplib.HTTPConnection`.

    :param strict:
        Causes BadStatusLine to be raised if the status line can't be parsed
        as a valid HTTP/1.0 or 1.1 status line, passed into
        :class:`httplib.HTTPConnection`.

        .. note::
           Only works in Python 2. This parameter is ignored in Python 3.

    :param timeout:
        Socket timeout in seconds for each individual connection. This can
        be a float or integer, which sets the timeout for the HTTP request,
        or an instance of :class:`urllib3.util.Timeout` which gives you more
        fine-grained control over request timeouts. After the constructor has
        been parsed, this is always a `urllib3.util.Timeout` object.

    :param maxsize:
        Number of connections to save that can be reused. More than 1 is useful
        in multithreaded situations. If ``block`` is set to False, more
        connections will be created but they will not be saved once they've
        been used.

    :param block:
        If set to True, no more than ``maxsize`` connections will be used at
        a time. When no free connections are available, the call will block
        until a connection has been released. This is a useful side effect for
        particular multithreaded situations where one does not want to use more
        than maxsize connections per host to prevent flooding.

    :param headers:
        Headers to include with all requests, unless other headers are given
        explicitly.

    :param retries:
        Retry configuration to use by default with requests in this pool.

    :param _proxy:
        Parsed proxy URL, should not be used directly, instead, see
        :class:`urllib3.connectionpool.ProxyManager`"

    :param _proxy_headers:
        A dictionary with proxy headers, should not be used directly,
        instead, see :class:`urllib3.connectionpool.ProxyManager`"

    :param \\**conn_kw:
        Additional parameters are used to create fresh :class:`urllib3.connection.HTTPConnection`,
        :class:`urllib3.connection.HTTPSConnection` instances.
    """

    scheme = 'http'
    ConnectionCls = HTTPConnection
    ResponseCls = HTTPResponse

    def __init__(self, host, port=None, strict=False,
                 timeout=Timeout.DEFAULT_TIMEOUT, maxsize=1, block=False,
                 headers=None, retries=None,
                 _proxy=None, _proxy_headers=None,
                 **conn_kw):
        ConnectionPool.__init__(self, host, port)
        RequestMethods.__init__(self, headers)

        self.strict = strict

        if not isinstance(timeout, Timeout):
            timeout = Timeout.from_float(timeout)

        if retries is None:
            retries = Retry.DEFAULT

        self.timeout = timeout
        self.retries = retries

        self.pool = self.QueueCls(maxsize)
        self.block = block

        self.proxy = _proxy
        self.proxy_headers = _proxy_headers or {}

        # Fill the queue up so that doing get() on it will block properly
        for _ in xrange(maxsize):
            self.pool.put(None)

        # These are mostly for testing and debugging purposes.
        self.num_connections = 0
        self.num_requests = 0
        self.conn_kw = conn_kw

        if self.proxy:
            # Enable Nagle's algorithm for proxies, to avoid packet fragmentation.
            # We cannot know if the user has added default socket options, so we cannot replace the
            # list.
            self.conn_kw.setdefault('socket_options', [])

    def _new_conn(self):
        """
        Return a fresh :class:`HTTPConnection`.
        """
        self.num_connections += 1
        log.debug("Starting new HTTP connection (%d): %s:%s",
                  self.num_connections, self.host, self.port or "80")

        conn = self.ConnectionCls(host=self.host, port=self.port,
                                  timeout=self.timeout.connect_timeout,
                                  strict=self.strict, **self.conn_kw)
        return conn

    def _get_conn(self, timeout=None):
        """
        Get a connection. Will return a pooled connection if one is available.

        If no connections are available and :prop:`.block` is ``False``, then a
        fresh connection is returned.

        :param timeout:
            Seconds to wait before giving up and raising
            :class:`urllib3.exceptions.EmptyPoolError` if the pool is empty and
            :prop:`.block` is ``True``.
        """
        conn = None
        try:
            conn = self.pool.get(block=self.block, timeout=timeout)

        except AttributeError:  # self.pool is None
            raise ClosedPoolError(self, "Pool is closed.")

        except queue.Empty:
            if self.block:
                raise EmptyPoolError(self,
                                     "Pool reached maximum size and no more "
                                     "connections are allowed.")
            pass  # Oh well, we'll create a new connection then

        # If this is a persistent connection, check if it got disconnected
        if conn and is_connection_dropped(conn):
            log.debug("Resetting dropped connection: %s", self.host)
            conn.close()
            if getattr(conn, 'auto_open', 1) == 0:
                # This is a proxied connection that has been mutated by
                # httplib._tunnel() and cannot be reused (since it would
                # attempt to bypass the proxy)
                conn = None

        return conn or self._new_conn()

    def _put_conn(self, conn):
        """
        Put a connection back into the pool.

        :param conn:
            Connection object for the current host and port as returned by
            :meth:`._new_conn` or :meth:`._get_conn`.

        If the pool is already full, the connection is closed and discarded
        because we exceeded maxsize. If connections are discarded frequently,
        then maxsize should be increased.

        If the pool is closed, then the connection will be closed and discarded.
        """
        try:
            self.pool.put(conn, block=False)
            return  # Everything is dandy, done.
        except AttributeError:
            # self.pool is None.
            pass
        except queue.Full:
            # This should never happen if self.block == True
            log.warning(
                "Connection pool is full, discarding connection: %s",
                self.host)

        # Connection never got put back into the pool, close it.
        if conn:
            conn.close()

    def _validate_conn(self, conn):
        """
        Called right before a request is made, after the socket is created.
        """
        pass

    def _prepare_proxy(self, conn):
        # Nothing to do for HTTP connections.
        pass

    def _get_timeout(self, timeout):
        """ Helper that always returns a :class:`urllib3.util.Timeout` """
        if timeout is _Default:
            return self.timeout.clone()

        if isinstance(timeout, Timeout):
            return timeout.clone()
        else:
            # User passed us an int/float. This is for backwards compatibility,
            # can be removed later
            return Timeout.from_float(timeout)

    def _raise_timeout(self, err, url, timeout_value):
        """Is the error actually a timeout? Will raise a ReadTimeout or pass"""

        if isinstance(err, SocketTimeout):
            raise ReadTimeoutError(self, url, "Read timed out. (read timeout=%s)" % timeout_value)

        # See the above comment about EAGAIN in Python 3. In Python 2 we have
        # to specifically catch it and throw the timeout error
        if hasattr(err, 'errno') and err.errno in _blocking_errnos:
            raise ReadTimeoutError(self, url, "Read timed out. (read timeout=%s)" % timeout_value)

        # Catch possible read timeouts thrown as SSL errors. If not the
        # case, rethrow the original. We need to do this because of:
        # http://bugs.python.org/issue10272
        if 'timed out' in str(err) or 'did not complete (read)' in str(err):  # Python 2.6
            raise ReadTimeoutError(self, url, "Read timed out. (read timeout=%s)" % timeout_value)

    def _make_request(self, conn, method, url, timeout=_Default, chunked=False,
                      **httplib_request_kw):
        """
        Perform a request on a given urllib connection object taken from our
        pool.

        :param conn:
            a connection from one of our connection pools

        :param timeout:
            Socket timeout in seconds for the request. This can be a
            float or integer, which will set the same timeout value for
            the socket connect and the socket read, or an instance of
            :class:`urllib3.util.Timeout`, which gives you more fine-grained
            control over your timeouts.
        """
        self.num_requests += 1

        timeout_obj = self._get_timeout(timeout)
        timeout_obj.start_connect()
        conn.timeout = timeout_obj.connect_timeout

        # Trigger any extra validation we need to do.
        try:
            self._validate_conn(conn)
        except (SocketTimeout, BaseSSLError) as e:
            # Py2 raises this as a BaseSSLError, Py3 raises it as socket timeout.
Loading ...