Mercurial > repos > guerler > springsuite
diff planemo/lib/python3.7/site-packages/urllib3/poolmanager.py @ 1:56ad4e20f292 draft
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
author | guerler |
---|---|
date | Fri, 31 Jul 2020 00:32:28 -0400 |
parents | |
children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/planemo/lib/python3.7/site-packages/urllib3/poolmanager.py Fri Jul 31 00:32:28 2020 -0400 @@ -0,0 +1,492 @@ +from __future__ import absolute_import +import collections +import functools +import logging +import warnings + +from ._collections import RecentlyUsedContainer +from .connectionpool import HTTPConnectionPool, HTTPSConnectionPool +from .connectionpool import port_by_scheme +from .exceptions import ( + LocationValueError, + MaxRetryError, + ProxySchemeUnknown, + InvalidProxyConfigurationWarning, +) +from .packages import six +from .packages.six.moves.urllib.parse import urljoin +from .request import RequestMethods +from .util.url import parse_url +from .util.retry import Retry + + +__all__ = ["PoolManager", "ProxyManager", "proxy_from_url"] + + +log = logging.getLogger(__name__) + +SSL_KEYWORDS = ( + "key_file", + "cert_file", + "cert_reqs", + "ca_certs", + "ssl_version", + "ca_cert_dir", + "ssl_context", + "key_password", +) + +# All known keyword arguments that could be provided to the pool manager, its +# pools, or the underlying connections. This is used to construct a pool key. +_key_fields = ( + "key_scheme", # str + "key_host", # str + "key_port", # int + "key_timeout", # int or float or Timeout + "key_retries", # int or Retry + "key_strict", # bool + "key_block", # bool + "key_source_address", # str + "key_key_file", # str + "key_key_password", # str + "key_cert_file", # str + "key_cert_reqs", # str + "key_ca_certs", # str + "key_ssl_version", # str + "key_ca_cert_dir", # str + "key_ssl_context", # instance of ssl.SSLContext or urllib3.util.ssl_.SSLContext + "key_maxsize", # int + "key_headers", # dict + "key__proxy", # parsed proxy url + "key__proxy_headers", # dict + "key_socket_options", # list of (level (int), optname (int), value (int or str)) tuples + "key__socks_options", # dict + "key_assert_hostname", # bool or string + "key_assert_fingerprint", # str + "key_server_hostname", # str +) + +#: The namedtuple class used to construct keys for the connection pool. +#: All custom key schemes should include the fields in this key at a minimum. +PoolKey = collections.namedtuple("PoolKey", _key_fields) + + +def _default_key_normalizer(key_class, request_context): + """ + Create a pool key out of a request context dictionary. + + According to RFC 3986, both the scheme and host are case-insensitive. + Therefore, this function normalizes both before constructing the pool + key for an HTTPS request. If you wish to change this behaviour, provide + alternate callables to ``key_fn_by_scheme``. + + :param key_class: + The class to use when constructing the key. This should be a namedtuple + with the ``scheme`` and ``host`` keys at a minimum. + :type key_class: namedtuple + :param request_context: + A dictionary-like object that contain the context for a request. + :type request_context: dict + + :return: A namedtuple that can be used as a connection pool key. + :rtype: PoolKey + """ + # Since we mutate the dictionary, make a copy first + context = request_context.copy() + context["scheme"] = context["scheme"].lower() + context["host"] = context["host"].lower() + + # These are both dictionaries and need to be transformed into frozensets + for key in ("headers", "_proxy_headers", "_socks_options"): + if key in context and context[key] is not None: + context[key] = frozenset(context[key].items()) + + # The socket_options key may be a list and needs to be transformed into a + # tuple. + socket_opts = context.get("socket_options") + if socket_opts is not None: + context["socket_options"] = tuple(socket_opts) + + # Map the kwargs to the names in the namedtuple - this is necessary since + # namedtuples can't have fields starting with '_'. + for key in list(context.keys()): + context["key_" + key] = context.pop(key) + + # Default to ``None`` for keys missing from the context + for field in key_class._fields: + if field not in context: + context[field] = None + + return key_class(**context) + + +#: A dictionary that maps a scheme to a callable that creates a pool key. +#: This can be used to alter the way pool keys are constructed, if desired. +#: Each PoolManager makes a copy of this dictionary so they can be configured +#: globally here, or individually on the instance. +key_fn_by_scheme = { + "http": functools.partial(_default_key_normalizer, PoolKey), + "https": functools.partial(_default_key_normalizer, PoolKey), +} + +pool_classes_by_scheme = {"http": HTTPConnectionPool, "https": HTTPSConnectionPool} + + +class PoolManager(RequestMethods): + """ + Allows for arbitrary requests while transparently keeping track of + necessary connection pools for you. + + :param num_pools: + Number of connection pools to cache before discarding the least + recently used pool. + + :param headers: + Headers to include with all requests, unless other headers are given + explicitly. + + :param \\**connection_pool_kw: + Additional parameters are used to create fresh + :class:`urllib3.connectionpool.ConnectionPool` instances. + + Example:: + + >>> manager = PoolManager(num_pools=2) + >>> r = manager.request('GET', 'http://google.com/') + >>> r = manager.request('GET', 'http://google.com/mail') + >>> r = manager.request('GET', 'http://yahoo.com/') + >>> len(manager.pools) + 2 + + """ + + proxy = None + + def __init__(self, num_pools=10, headers=None, **connection_pool_kw): + RequestMethods.__init__(self, headers) + self.connection_pool_kw = connection_pool_kw + self.pools = RecentlyUsedContainer(num_pools, dispose_func=lambda p: p.close()) + + # Locally set the pool classes and keys so other PoolManagers can + # override them. + self.pool_classes_by_scheme = pool_classes_by_scheme + self.key_fn_by_scheme = key_fn_by_scheme.copy() + + def __enter__(self): + return self + + def __exit__(self, exc_type, exc_val, exc_tb): + self.clear() + # Return False to re-raise any potential exceptions + return False + + def _new_pool(self, scheme, host, port, request_context=None): + """ + Create a new :class:`ConnectionPool` based on host, port, scheme, and + any additional pool keyword arguments. + + If ``request_context`` is provided, it is provided as keyword arguments + to the pool class used. This method is used to actually create the + connection pools handed out by :meth:`connection_from_url` and + companion methods. It is intended to be overridden for customization. + """ + pool_cls = self.pool_classes_by_scheme[scheme] + if request_context is None: + request_context = self.connection_pool_kw.copy() + + # Although the context has everything necessary to create the pool, + # this function has historically only used the scheme, host, and port + # in the positional args. When an API change is acceptable these can + # be removed. + for key in ("scheme", "host", "port"): + request_context.pop(key, None) + + if scheme == "http": + for kw in SSL_KEYWORDS: + request_context.pop(kw, None) + + return pool_cls(host, port, **request_context) + + def clear(self): + """ + Empty our store of pools and direct them all to close. + + This will not affect in-flight connections, but they will not be + re-used after completion. + """ + self.pools.clear() + + def connection_from_host(self, host, port=None, scheme="http", pool_kwargs=None): + """ + Get a :class:`ConnectionPool` based on the host, port, and scheme. + + If ``port`` isn't given, it will be derived from the ``scheme`` using + ``urllib3.connectionpool.port_by_scheme``. If ``pool_kwargs`` is + provided, it is merged with the instance's ``connection_pool_kw`` + variable and used to create the new connection pool, if one is + needed. + """ + + if not host: + raise LocationValueError("No host specified.") + + request_context = self._merge_pool_kwargs(pool_kwargs) + request_context["scheme"] = scheme or "http" + if not port: + port = port_by_scheme.get(request_context["scheme"].lower(), 80) + request_context["port"] = port + request_context["host"] = host + + return self.connection_from_context(request_context) + + def connection_from_context(self, request_context): + """ + Get a :class:`ConnectionPool` based on the request context. + + ``request_context`` must at least contain the ``scheme`` key and its + value must be a key in ``key_fn_by_scheme`` instance variable. + """ + scheme = request_context["scheme"].lower() + pool_key_constructor = self.key_fn_by_scheme[scheme] + pool_key = pool_key_constructor(request_context) + + return self.connection_from_pool_key(pool_key, request_context=request_context) + + def connection_from_pool_key(self, pool_key, request_context=None): + """ + Get a :class:`ConnectionPool` based on the provided pool key. + + ``pool_key`` should be a namedtuple that only contains immutable + objects. At a minimum it must have the ``scheme``, ``host``, and + ``port`` fields. + """ + with self.pools.lock: + # If the scheme, host, or port doesn't match existing open + # connections, open a new ConnectionPool. + pool = self.pools.get(pool_key) + if pool: + return pool + + # Make a fresh ConnectionPool of the desired type + scheme = request_context["scheme"] + host = request_context["host"] + port = request_context["port"] + pool = self._new_pool(scheme, host, port, request_context=request_context) + self.pools[pool_key] = pool + + return pool + + def connection_from_url(self, url, pool_kwargs=None): + """ + Similar to :func:`urllib3.connectionpool.connection_from_url`. + + If ``pool_kwargs`` is not provided and a new pool needs to be + constructed, ``self.connection_pool_kw`` is used to initialize + the :class:`urllib3.connectionpool.ConnectionPool`. If ``pool_kwargs`` + is provided, it is used instead. Note that if a new pool does not + need to be created for the request, the provided ``pool_kwargs`` are + not used. + """ + u = parse_url(url) + return self.connection_from_host( + u.host, port=u.port, scheme=u.scheme, pool_kwargs=pool_kwargs + ) + + def _merge_pool_kwargs(self, override): + """ + Merge a dictionary of override values for self.connection_pool_kw. + + This does not modify self.connection_pool_kw and returns a new dict. + Any keys in the override dictionary with a value of ``None`` are + removed from the merged dictionary. + """ + base_pool_kwargs = self.connection_pool_kw.copy() + if override: + for key, value in override.items(): + if value is None: + try: + del base_pool_kwargs[key] + except KeyError: + pass + else: + base_pool_kwargs[key] = value + return base_pool_kwargs + + def urlopen(self, method, url, redirect=True, **kw): + """ + Same as :meth:`urllib3.connectionpool.HTTPConnectionPool.urlopen` + with custom cross-host redirect logic and only sends the request-uri + portion of the ``url``. + + The given ``url`` parameter must be absolute, such that an appropriate + :class:`urllib3.connectionpool.ConnectionPool` can be chosen for it. + """ + u = parse_url(url) + conn = self.connection_from_host(u.host, port=u.port, scheme=u.scheme) + + kw["assert_same_host"] = False + kw["redirect"] = False + + if "headers" not in kw: + kw["headers"] = self.headers.copy() + + if self.proxy is not None and u.scheme == "http": + response = conn.urlopen(method, url, **kw) + else: + response = conn.urlopen(method, u.request_uri, **kw) + + redirect_location = redirect and response.get_redirect_location() + if not redirect_location: + return response + + # Support relative URLs for redirecting. + redirect_location = urljoin(url, redirect_location) + + # RFC 7231, Section 6.4.4 + if response.status == 303: + method = "GET" + + retries = kw.get("retries") + if not isinstance(retries, Retry): + retries = Retry.from_int(retries, redirect=redirect) + + # Strip headers marked as unsafe to forward to the redirected location. + # Check remove_headers_on_redirect to avoid a potential network call within + # conn.is_same_host() which may use socket.gethostbyname() in the future. + if retries.remove_headers_on_redirect and not conn.is_same_host( + redirect_location + ): + headers = list(six.iterkeys(kw["headers"])) + for header in headers: + if header.lower() in retries.remove_headers_on_redirect: + kw["headers"].pop(header, None) + + try: + retries = retries.increment(method, url, response=response, _pool=conn) + except MaxRetryError: + if retries.raise_on_redirect: + response.drain_conn() + raise + return response + + kw["retries"] = retries + kw["redirect"] = redirect + + log.info("Redirecting %s -> %s", url, redirect_location) + + response.drain_conn() + return self.urlopen(method, redirect_location, **kw) + + +class ProxyManager(PoolManager): + """ + Behaves just like :class:`PoolManager`, but sends all requests through + the defined proxy, using the CONNECT method for HTTPS URLs. + + :param proxy_url: + The URL of the proxy to be used. + + :param proxy_headers: + A dictionary containing headers that will be sent to the proxy. In case + of HTTP they are being sent with each request, while in the + HTTPS/CONNECT case they are sent only once. Could be used for proxy + authentication. + + Example: + >>> proxy = urllib3.ProxyManager('http://localhost:3128/') + >>> r1 = proxy.request('GET', 'http://google.com/') + >>> r2 = proxy.request('GET', 'http://httpbin.org/') + >>> len(proxy.pools) + 1 + >>> r3 = proxy.request('GET', 'https://httpbin.org/') + >>> r4 = proxy.request('GET', 'https://twitter.com/') + >>> len(proxy.pools) + 3 + + """ + + def __init__( + self, + proxy_url, + num_pools=10, + headers=None, + proxy_headers=None, + **connection_pool_kw + ): + + if isinstance(proxy_url, HTTPConnectionPool): + proxy_url = "%s://%s:%i" % ( + proxy_url.scheme, + proxy_url.host, + proxy_url.port, + ) + proxy = parse_url(proxy_url) + if not proxy.port: + port = port_by_scheme.get(proxy.scheme, 80) + proxy = proxy._replace(port=port) + + if proxy.scheme not in ("http", "https"): + raise ProxySchemeUnknown(proxy.scheme) + + self.proxy = proxy + self.proxy_headers = proxy_headers or {} + + connection_pool_kw["_proxy"] = self.proxy + connection_pool_kw["_proxy_headers"] = self.proxy_headers + + super(ProxyManager, self).__init__(num_pools, headers, **connection_pool_kw) + + def connection_from_host(self, host, port=None, scheme="http", pool_kwargs=None): + if scheme == "https": + return super(ProxyManager, self).connection_from_host( + host, port, scheme, pool_kwargs=pool_kwargs + ) + + return super(ProxyManager, self).connection_from_host( + self.proxy.host, self.proxy.port, self.proxy.scheme, pool_kwargs=pool_kwargs + ) + + def _set_proxy_headers(self, url, headers=None): + """ + Sets headers needed by proxies: specifically, the Accept and Host + headers. Only sets headers not provided by the user. + """ + headers_ = {"Accept": "*/*"} + + netloc = parse_url(url).netloc + if netloc: + headers_["Host"] = netloc + + if headers: + headers_.update(headers) + return headers_ + + def _validate_proxy_scheme_url_selection(self, url_scheme): + if url_scheme == "https" and self.proxy.scheme == "https": + warnings.warn( + "Your proxy configuration specified an HTTPS scheme for the proxy. " + "Are you sure you want to use HTTPS to contact the proxy? " + "This most likely indicates an error in your configuration. " + "Read this issue for more info: " + "https://github.com/urllib3/urllib3/issues/1850", + InvalidProxyConfigurationWarning, + stacklevel=3, + ) + + def urlopen(self, method, url, redirect=True, **kw): + "Same as HTTP(S)ConnectionPool.urlopen, ``url`` must be absolute." + u = parse_url(url) + self._validate_proxy_scheme_url_selection(u.scheme) + + if u.scheme == "http": + # For proxied HTTPS requests, httplib sets the necessary headers + # on the CONNECT to the proxy. For HTTP, we'll definitely + # need to set 'Host' at the very least. + headers = kw.get("headers", self.headers) + kw["headers"] = self._set_proxy_headers(url, headers) + + return super(ProxyManager, self).urlopen(method, url, redirect=redirect, **kw) + + +def proxy_from_url(url, **kw): + return ProxyManager(proxy_url=url, **kw)