httputil.py 35.5 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144
#
# Copyright 2009 Facebook
#
# Licensed under the Apache License, Version 2.0 (the "License"); you may
# not use this file except in compliance with the License. You may obtain
# a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
# WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
# License for the specific language governing permissions and limitations
# under the License.

"""HTTP utility code shared by clients and servers.

This module also defines the `HTTPServerRequest` class which is exposed
via `tornado.web.RequestHandler.request`.
"""

import calendar
import collections
import copy
import datetime
import email.utils
from http.client import responses
import http.cookies
import re
from ssl import SSLError
import time
import unicodedata
from urllib.parse import urlencode, urlparse, urlunparse, parse_qsl

from tornado.escape import native_str, parse_qs_bytes, utf8
from tornado.log import gen_log
from tornado.util import ObjectDict, unicode_type


# responses is unused in this file, but we re-export it to other files.
# Reference it so pyflakes doesn't complain.
responses

import typing
from typing import (
    Tuple,
    Iterable,
    List,
    Mapping,
    Iterator,
    Dict,
    Union,
    Optional,
    Awaitable,
    Generator,
    AnyStr,
)

if typing.TYPE_CHECKING:
    from typing import Deque  # noqa: F401
    from asyncio import Future  # noqa: F401
    import unittest  # noqa: F401


# RFC 7230 section 3.5: a recipient MAY recognize a single LF as a line
# terminator and ignore any preceding CR.
_CRLF_RE = re.compile(r"\r?\n")


class _NormalizedHeaderCache(dict):
    """Dynamic cached mapping of header names to Http-Header-Case.

    Implemented as a dict subclass so that cache hits are as fast as a
    normal dict lookup, without the overhead of a python function
    call.

    >>> normalized_headers = _NormalizedHeaderCache(10)
    >>> normalized_headers["coNtent-TYPE"]
    'Content-Type'
    """

    def __init__(self, size: int) -> None:
        super(_NormalizedHeaderCache, self).__init__()
        self.size = size
        self.queue = collections.deque()  # type: Deque[str]

    def __missing__(self, key: str) -> str:
        normalized = "-".join([w.capitalize() for w in key.split("-")])
        self[key] = normalized
        self.queue.append(key)
        if len(self.queue) > self.size:
            # Limit the size of the cache.  LRU would be better, but this
            # simpler approach should be fine.  In Python 2.7+ we could
            # use OrderedDict (or in 3.2+, @functools.lru_cache).
            old_key = self.queue.popleft()
            del self[old_key]
        return normalized


_normalized_headers = _NormalizedHeaderCache(1000)


class HTTPHeaders(collections.abc.MutableMapping):
    """A dictionary that maintains ``Http-Header-Case`` for all keys.

    Supports multiple values per key via a pair of new methods,
    `add()` and `get_list()`.  The regular dictionary interface
    returns a single value per key, with multiple values joined by a
    comma.

    >>> h = HTTPHeaders({"content-type": "text/html"})
    >>> list(h.keys())
    ['Content-Type']
    >>> h["Content-Type"]
    'text/html'

    >>> h.add("Set-Cookie", "A=B")
    >>> h.add("Set-Cookie", "C=D")
    >>> h["set-cookie"]
    'A=B,C=D'
    >>> h.get_list("set-cookie")
    ['A=B', 'C=D']

    >>> for (k,v) in sorted(h.get_all()):
    ...    print('%s: %s' % (k,v))
    ...
    Content-Type: text/html
    Set-Cookie: A=B
    Set-Cookie: C=D
    """

    @typing.overload
    def __init__(self, __arg: Mapping[str, List[str]]) -> None:
        pass

    @typing.overload  # noqa: F811
    def __init__(self, __arg: Mapping[str, str]) -> None:
        pass

    @typing.overload  # noqa: F811
    def __init__(self, *args: Tuple[str, str]) -> None:
        pass

    @typing.overload  # noqa: F811
    def __init__(self, **kwargs: str) -> None:
        pass

    def __init__(self, *args: typing.Any, **kwargs: str) -> None:  # noqa: F811
        self._dict = {}  # type: typing.Dict[str, str]
        self._as_list = {}  # type: typing.Dict[str, typing.List[str]]
        self._last_key = None
        if len(args) == 1 and len(kwargs) == 0 and isinstance(args[0], HTTPHeaders):
            # Copy constructor
            for k, v in args[0].get_all():
                self.add(k, v)
        else:
            # Dict-style initialization
            self.update(*args, **kwargs)

    # new public methods

    def add(self, name: str, value: str) -> None:
        """Adds a new value for the given key."""
        norm_name = _normalized_headers[name]
        self._last_key = norm_name
        if norm_name in self:
            self._dict[norm_name] = (
                native_str(self[norm_name]) + "," + native_str(value)
            )
            self._as_list[norm_name].append(value)
        else:
            self[norm_name] = value

    def get_list(self, name: str) -> List[str]:
        """Returns all values for the given header as a list."""
        norm_name = _normalized_headers[name]
        return self._as_list.get(norm_name, [])

    def get_all(self) -> Iterable[Tuple[str, str]]:
        """Returns an iterable of all (name, value) pairs.

        If a header has multiple values, multiple pairs will be
        returned with the same name.
        """
        for name, values in self._as_list.items():
            for value in values:
                yield (name, value)

    def parse_line(self, line: str) -> None:
        """Updates the dictionary with a single header line.

        >>> h = HTTPHeaders()
        >>> h.parse_line("Content-Type: text/html")
        >>> h.get('content-type')
        'text/html'
        """
        if line[0].isspace():
            # continuation of a multi-line header
            if self._last_key is None:
                raise HTTPInputError("first header line cannot start with whitespace")
            new_part = " " + line.lstrip()
            self._as_list[self._last_key][-1] += new_part
            self._dict[self._last_key] += new_part
        else:
            try:
                name, value = line.split(":", 1)
            except ValueError:
                raise HTTPInputError("no colon in header line")
            self.add(name, value.strip())

    @classmethod
    def parse(cls, headers: str) -> "HTTPHeaders":
        """Returns a dictionary from HTTP header text.

        >>> h = HTTPHeaders.parse("Content-Type: text/html\\r\\nContent-Length: 42\\r\\n")
        >>> sorted(h.items())
        [('Content-Length', '42'), ('Content-Type', 'text/html')]

        .. versionchanged:: 5.1

           Raises `HTTPInputError` on malformed headers instead of a
           mix of `KeyError`, and `ValueError`.

        """
        h = cls()
        for line in _CRLF_RE.split(headers):
            if line:
                h.parse_line(line)
        return h

    # MutableMapping abstract method implementations.

    def __setitem__(self, name: str, value: str) -> None:
        norm_name = _normalized_headers[name]
        self._dict[norm_name] = value
        self._as_list[norm_name] = [value]

    def __getitem__(self, name: str) -> str:
        return self._dict[_normalized_headers[name]]

    def __delitem__(self, name: str) -> None:
        norm_name = _normalized_headers[name]
        del self._dict[norm_name]
        del self._as_list[norm_name]

    def __len__(self) -> int:
        return len(self._dict)

    def __iter__(self) -> Iterator[typing.Any]:
        return iter(self._dict)

    def copy(self) -> "HTTPHeaders":
        # defined in dict but not in MutableMapping.
        return HTTPHeaders(self)

    # Use our overridden copy method for the copy.copy module.
    # This makes shallow copies one level deeper, but preserves
    # the appearance that HTTPHeaders is a single container.
    __copy__ = copy

    def __str__(self) -> str:
        lines = []
        for name, value in self.get_all():
            lines.append("%s: %s\n" % (name, value))
        return "".join(lines)

    __unicode__ = __str__


class HTTPServerRequest(object):
    """A single HTTP request.

    All attributes are type `str` unless otherwise noted.

    .. attribute:: method

       HTTP request method, e.g. "GET" or "POST"

    .. attribute:: uri

       The requested uri.

    .. attribute:: path

       The path portion of `uri`

    .. attribute:: query

       The query portion of `uri`

    .. attribute:: version

       HTTP version specified in request, e.g. "HTTP/1.1"

    .. attribute:: headers

       `.HTTPHeaders` dictionary-like object for request headers.  Acts like
       a case-insensitive dictionary with additional methods for repeated
       headers.

    .. attribute:: body

       Request body, if present, as a byte string.

    .. attribute:: remote_ip

       Client's IP address as a string.  If ``HTTPServer.xheaders`` is set,
       will pass along the real IP address provided by a load balancer
       in the ``X-Real-Ip`` or ``X-Forwarded-For`` header.

    .. versionchanged:: 3.1
       The list format of ``X-Forwarded-For`` is now supported.

    .. attribute:: protocol

       The protocol used, either "http" or "https".  If ``HTTPServer.xheaders``
       is set, will pass along the protocol used by a load balancer if
       reported via an ``X-Scheme`` header.

    .. attribute:: host

       The requested hostname, usually taken from the ``Host`` header.

    .. attribute:: arguments

       GET/POST arguments are available in the arguments property, which
       maps arguments names to lists of values (to support multiple values
       for individual names). Names are of type `str`, while arguments
       are byte strings.  Note that this is different from
       `.RequestHandler.get_argument`, which returns argument values as
       unicode strings.

    .. attribute:: query_arguments

       Same format as ``arguments``, but contains only arguments extracted
       from the query string.

       .. versionadded:: 3.2

    .. attribute:: body_arguments

       Same format as ``arguments``, but contains only arguments extracted
       from the request body.

       .. versionadded:: 3.2

    .. attribute:: files

       File uploads are available in the files property, which maps file
       names to lists of `.HTTPFile`.

    .. attribute:: connection

       An HTTP request is attached to a single HTTP connection, which can
       be accessed through the "connection" attribute. Since connections
       are typically kept open in HTTP/1.1, multiple requests can be handled
       sequentially on a single connection.

    .. versionchanged:: 4.0
       Moved from ``tornado.httpserver.HTTPRequest``.
    """

    path = None  # type: str
    query = None  # type: str

    # HACK: Used for stream_request_body
    _body_future = None  # type: Future[None]

    def __init__(
        self,
        method: str = None,
        uri: str = None,
        version: str = "HTTP/1.0",
        headers: HTTPHeaders = None,
        body: bytes = None,
        host: str = None,
        files: Dict[str, List["HTTPFile"]] = None,
        connection: "HTTPConnection" = None,
        start_line: "RequestStartLine" = None,
        server_connection: object = None,
    ) -> None:
        if start_line is not None:
            method, uri, version = start_line
        self.method = method
        self.uri = uri
        self.version = version
        self.headers = headers or HTTPHeaders()
        self.body = body or b""

        # set remote IP and protocol
        context = getattr(connection, "context", None)
        self.remote_ip = getattr(context, "remote_ip", None)
        self.protocol = getattr(context, "protocol", "http")

        self.host = host or self.headers.get("Host") or "127.0.0.1"
        self.host_name = split_host_and_port(self.host.lower())[0]
        self.files = files or {}
        self.connection = connection
        self.server_connection = server_connection
        self._start_time = time.time()
        self._finish_time = None

        if uri is not None:
            self.path, sep, self.query = uri.partition("?")
        self.arguments = parse_qs_bytes(self.query, keep_blank_values=True)
        self.query_arguments = copy.deepcopy(self.arguments)
        self.body_arguments = {}  # type: Dict[str, List[bytes]]

    @property
    def cookies(self) -> Dict[str, http.cookies.Morsel]:
        """A dictionary of ``http.cookies.Morsel`` objects."""
        if not hasattr(self, "_cookies"):
            self._cookies = http.cookies.SimpleCookie()
            if "Cookie" in self.headers:
                try:
                    parsed = parse_cookie(self.headers["Cookie"])
                except Exception:
                    pass
                else:
                    for k, v in parsed.items():
                        try:
                            self._cookies[k] = v
                        except Exception:
                            # SimpleCookie imposes some restrictions on keys;
                            # parse_cookie does not. Discard any cookies
                            # with disallowed keys.
                            pass
        return self._cookies

    def full_url(self) -> str:
        """Reconstructs the full URL for this request."""
        return self.protocol + "://" + self.host + self.uri

    def request_time(self) -> float:
        """Returns the amount of time it took for this request to execute."""
        if self._finish_time is None:
            return time.time() - self._start_time
        else:
            return self._finish_time - self._start_time

    def get_ssl_certificate(
        self, binary_form: bool = False
    ) -> Union[None, Dict, bytes]:
        """Returns the client's SSL certificate, if any.

        To use client certificates, the HTTPServer's
        `ssl.SSLContext.verify_mode` field must be set, e.g.::

            ssl_ctx = ssl.create_default_context(ssl.Purpose.CLIENT_AUTH)
            ssl_ctx.load_cert_chain("foo.crt", "foo.key")
            ssl_ctx.load_verify_locations("cacerts.pem")
            ssl_ctx.verify_mode = ssl.CERT_REQUIRED
            server = HTTPServer(app, ssl_options=ssl_ctx)

        By default, the return value is a dictionary (or None, if no
        client certificate is present).  If ``binary_form`` is true, a
        DER-encoded form of the certificate is returned instead.  See
        SSLSocket.getpeercert() in the standard library for more
        details.
        http://docs.python.org/library/ssl.html#sslsocket-objects
        """
        try:
            if self.connection is None:
                return None
            # TODO: add a method to HTTPConnection for this so it can work with HTTP/2
            return self.connection.stream.socket.getpeercert(  # type: ignore
                binary_form=binary_form
            )
        except SSLError:
            return None

    def _parse_body(self) -> None:
        parse_body_arguments(
            self.headers.get("Content-Type", ""),
            self.body,
            self.body_arguments,
            self.files,
            self.headers,
        )

        for k, v in self.body_arguments.items():
            self.arguments.setdefault(k, []).extend(v)

    def __repr__(self) -> str:
        attrs = ("protocol", "host", "method", "uri", "version", "remote_ip")
        args = ", ".join(["%s=%r" % (n, getattr(self, n)) for n in attrs])
        return "%s(%s)" % (self.__class__.__name__, args)


class HTTPInputError(Exception):
    """Exception class for malformed HTTP requests or responses
    from remote sources.

    .. versionadded:: 4.0
    """

    pass


class HTTPOutputError(Exception):
    """Exception class for errors in HTTP output.

    .. versionadded:: 4.0
    """

    pass


class HTTPServerConnectionDelegate(object):
    """Implement this interface to handle requests from `.HTTPServer`.

    .. versionadded:: 4.0
    """

    def start_request(
        self, server_conn: object, request_conn: "HTTPConnection"
    ) -> "HTTPMessageDelegate":
        """This method is called by the server when a new request has started.

        :arg server_conn: is an opaque object representing the long-lived
            (e.g. tcp-level) connection.
        :arg request_conn: is a `.HTTPConnection` object for a single
            request/response exchange.

        This method should return a `.HTTPMessageDelegate`.
        """
        raise NotImplementedError()

    def on_close(self, server_conn: object) -> None:
        """This method is called when a connection has been closed.

        :arg server_conn: is a server connection that has previously been
            passed to ``start_request``.
        """
        pass


class HTTPMessageDelegate(object):
    """Implement this interface to handle an HTTP request or response.

    .. versionadded:: 4.0
    """

    # TODO: genericize this class to avoid exposing the Union.
    def headers_received(
        self,
        start_line: Union["RequestStartLine", "ResponseStartLine"],
        headers: HTTPHeaders,
    ) -> Optional[Awaitable[None]]:
        """Called when the HTTP headers have been received and parsed.

        :arg start_line: a `.RequestStartLine` or `.ResponseStartLine`
            depending on whether this is a client or server message.
        :arg headers: a `.HTTPHeaders` instance.

        Some `.HTTPConnection` methods can only be called during
        ``headers_received``.

        May return a `.Future`; if it does the body will not be read
        until it is done.
        """
        pass

    def data_received(self, chunk: bytes) -> Optional[Awaitable[None]]:
        """Called when a chunk of data has been received.

        May return a `.Future` for flow control.
        """
        pass

    def finish(self) -> None:
        """Called after the last chunk of data has been received."""
        pass

    def on_connection_close(self) -> None:
        """Called if the connection is closed without finishing the request.

        If ``headers_received`` is called, either ``finish`` or
        ``on_connection_close`` will be called, but not both.
        """
        pass


class HTTPConnection(object):
    """Applications use this interface to write their responses.

    .. versionadded:: 4.0
    """

    def write_headers(
        self,
        start_line: Union["RequestStartLine", "ResponseStartLine"],
        headers: HTTPHeaders,
        chunk: bytes = None,
    ) -> "Future[None]":
        """Write an HTTP header block.

        :arg start_line: a `.RequestStartLine` or `.ResponseStartLine`.
        :arg headers: a `.HTTPHeaders` instance.
        :arg chunk: the first (optional) chunk of data.  This is an optimization
            so that small responses can be written in the same call as their
            headers.

        The ``version`` field of ``start_line`` is ignored.

        Returns a future for flow control.

        .. versionchanged:: 6.0

           The ``callback`` argument was removed.
        """
        raise NotImplementedError()

    def write(self, chunk: bytes) -> "Future[None]":
        """Writes a chunk of body data.

        Returns a future for flow control.

        .. versionchanged:: 6.0

           The ``callback`` argument was removed.
        """
        raise NotImplementedError()

    def finish(self) -> None:
        """Indicates that the last body data has been written.
        """
        raise NotImplementedError()


def url_concat(
    url: str,
    args: Union[
        None, Dict[str, str], List[Tuple[str, str]], Tuple[Tuple[str, str], ...]
    ],
) -> str:
    """Concatenate url and arguments regardless of whether
    url has existing query parameters.

    ``args`` may be either a dictionary or a list of key-value pairs
    (the latter allows for multiple values with the same key.

    >>> url_concat("http://example.com/foo", dict(c="d"))
    'http://example.com/foo?c=d'
    >>> url_concat("http://example.com/foo?a=b", dict(c="d"))
    'http://example.com/foo?a=b&c=d'
    >>> url_concat("http://example.com/foo?a=b", [("c", "d"), ("c", "d2")])
    'http://example.com/foo?a=b&c=d&c=d2'
    """
    if args is None:
        return url
    parsed_url = urlparse(url)
    if isinstance(args, dict):
        parsed_query = parse_qsl(parsed_url.query, keep_blank_values=True)
        parsed_query.extend(args.items())
    elif isinstance(args, list) or isinstance(args, tuple):
        parsed_query = parse_qsl(parsed_url.query, keep_blank_values=True)
        parsed_query.extend(args)
    else:
        err = "'args' parameter should be dict, list or tuple. Not {0}".format(
            type(args)
        )
        raise TypeError(err)
    final_query = urlencode(parsed_query)
    url = urlunparse(
        (
            parsed_url[0],
            parsed_url[1],
            parsed_url[2],
            parsed_url[3],
            final_query,
            parsed_url[5],
        )
    )
    return url


class HTTPFile(ObjectDict):
    """Represents a file uploaded via a form.

    For backwards compatibility, its instance attributes are also
    accessible as dictionary keys.

    * ``filename``
    * ``body``
    * ``content_type``
    """

    pass


def _parse_request_range(
    range_header: str,
) -> Optional[Tuple[Optional[int], Optional[int]]]:
    """Parses a Range header.

    Returns either ``None`` or tuple ``(start, end)``.
    Note that while the HTTP headers use inclusive byte positions,
    this method returns indexes suitable for use in slices.

    >>> start, end = _parse_request_range("bytes=1-2")
    >>> start, end
    (1, 3)
    >>> [0, 1, 2, 3, 4][start:end]
    [1, 2]
    >>> _parse_request_range("bytes=6-")
    (6, None)
    >>> _parse_request_range("bytes=-6")
    (-6, None)
    >>> _parse_request_range("bytes=-0")
    (None, 0)
    >>> _parse_request_range("bytes=")
    (None, None)
    >>> _parse_request_range("foo=42")
    >>> _parse_request_range("bytes=1-2,6-10")

    Note: only supports one range (ex, ``bytes=1-2,6-10`` is not allowed).

    See [0] for the details of the range header.

    [0]: http://greenbytes.de/tech/webdav/draft-ietf-httpbis-p5-range-latest.html#byte.ranges
    """
    unit, _, value = range_header.partition("=")
    unit, value = unit.strip(), value.strip()
    if unit != "bytes":
        return None
    start_b, _, end_b = value.partition("-")
    try:
        start = _int_or_none(start_b)
        end = _int_or_none(end_b)
    except ValueError:
        return None
    if end is not None:
        if start is None:
            if end != 0:
                start = -end
                end = None
        else:
            end += 1
    return (start, end)


def _get_content_range(start: Optional[int], end: Optional[int], total: int) -> str:
    """Returns a suitable Content-Range header:

    >>> print(_get_content_range(None, 1, 4))
    bytes 0-0/4
    >>> print(_get_content_range(1, 3, 4))
    bytes 1-2/4
    >>> print(_get_content_range(None, None, 4))
    bytes 0-3/4
    """
    start = start or 0
    end = (end or total) - 1
    return "bytes %s-%s/%s" % (start, end, total)


def _int_or_none(val: str) -> Optional[int]:
    val = val.strip()
    if val == "":
        return None
    return int(val)


def parse_body_arguments(
    content_type: str,
    body: bytes,
    arguments: Dict[str, List[bytes]],
    files: Dict[str, List[HTTPFile]],
    headers: HTTPHeaders = None,
) -> None:
    """Parses a form request body.

    Supports ``application/x-www-form-urlencoded`` and
    ``multipart/form-data``.  The ``content_type`` parameter should be
    a string and ``body`` should be a byte string.  The ``arguments``
    and ``files`` parameters are dictionaries that will be updated
    with the parsed contents.
    """
    if content_type.startswith("application/x-www-form-urlencoded"):
        if headers and "Content-Encoding" in headers:
            gen_log.warning(
                "Unsupported Content-Encoding: %s", headers["Content-Encoding"]
            )
            return
        try:
            uri_arguments = parse_qs_bytes(native_str(body), keep_blank_values=True)
        except Exception as e:
            gen_log.warning("Invalid x-www-form-urlencoded body: %s", e)
            uri_arguments = {}
        for name, values in uri_arguments.items():
            if values:
                arguments.setdefault(name, []).extend(values)
    elif content_type.startswith("multipart/form-data"):
        if headers and "Content-Encoding" in headers:
            gen_log.warning(
                "Unsupported Content-Encoding: %s", headers["Content-Encoding"]
            )
            return
        try:
            fields = content_type.split(";")
            for field in fields:
                k, sep, v = field.strip().partition("=")
                if k == "boundary" and v:
                    parse_multipart_form_data(utf8(v), body, arguments, files)
                    break
            else:
                raise ValueError("multipart boundary not found")
        except Exception as e:
            gen_log.warning("Invalid multipart/form-data: %s", e)


def parse_multipart_form_data(
    boundary: bytes,
    data: bytes,
    arguments: Dict[str, List[bytes]],
    files: Dict[str, List[HTTPFile]],
) -> None:
    """Parses a ``multipart/form-data`` body.

    The ``boundary`` and ``data`` parameters are both byte strings.
    The dictionaries given in the arguments and files parameters
    will be updated with the contents of the body.

    .. versionchanged:: 5.1

       Now recognizes non-ASCII filenames in RFC 2231/5987
       (``filename*=``) format.
    """
    # The standard allows for the boundary to be quoted in the header,
    # although it's rare (it happens at least for google app engine
    # xmpp).  I think we're also supposed to handle backslash-escapes
    # here but I'll save that until we see a client that uses them
    # in the wild.
    if boundary.startswith(b'"') and boundary.endswith(b'"'):
        boundary = boundary[1:-1]
    final_boundary_index = data.rfind(b"--" + boundary + b"--")
    if final_boundary_index == -1:
        gen_log.warning("Invalid multipart/form-data: no final boundary")
        return
    parts = data[:final_boundary_index].split(b"--" + boundary + b"\r\n")
    for part in parts:
        if not part:
            continue
        eoh = part.find(b"\r\n\r\n")
        if eoh == -1:
            gen_log.warning("multipart/form-data missing headers")
            continue
        headers = HTTPHeaders.parse(part[:eoh].decode("utf-8"))
        disp_header = headers.get("Content-Disposition", "")
        disposition, disp_params = _parse_header(disp_header)
        if disposition != "form-data" or not part.endswith(b"\r\n"):
            gen_log.warning("Invalid multipart/form-data")
            continue
        value = part[eoh + 4 : -2]
        if not disp_params.get("name"):
            gen_log.warning("multipart/form-data value missing name")
            continue
        name = disp_params["name"]
        if disp_params.get("filename"):
            ctype = headers.get("Content-Type", "application/unknown")
            files.setdefault(name, []).append(
                HTTPFile(
                    filename=disp_params["filename"], body=value, content_type=ctype
                )
            )
        else:
            arguments.setdefault(name, []).append(value)


def format_timestamp(
    ts: Union[int, float, tuple, time.struct_time, datetime.datetime]
) -> str:
    """Formats a timestamp in the format used by HTTP.

    The argument may be a numeric timestamp as returned by `time.time`,
    a time tuple as returned by `time.gmtime`, or a `datetime.datetime`
    object.

    >>> format_timestamp(1359312200)
    'Sun, 27 Jan 2013 18:43:20 GMT'
    """
    if isinstance(ts, (int, float)):
        time_num = ts
    elif isinstance(ts, (tuple, time.struct_time)):
        time_num = calendar.timegm(ts)
    elif isinstance(ts, datetime.datetime):
        time_num = calendar.timegm(ts.utctimetuple())
    else:
        raise TypeError("unknown timestamp type: %r" % ts)
    return email.utils.formatdate(time_num, usegmt=True)


RequestStartLine = collections.namedtuple(
    "RequestStartLine", ["method", "path", "version"]
)


def parse_request_start_line(line: str) -> RequestStartLine:
    """Returns a (method, path, version) tuple for an HTTP 1.x request line.

    The response is a `collections.namedtuple`.

    >>> parse_request_start_line("GET /foo HTTP/1.1")
    RequestStartLine(method='GET', path='/foo', version='HTTP/1.1')
    """
    try:
        method, path, version = line.split(" ")
    except ValueError:
        # https://tools.ietf.org/html/rfc7230#section-3.1.1
        # invalid request-line SHOULD respond with a 400 (Bad Request)
        raise HTTPInputError("Malformed HTTP request line")
    if not re.match(r"^HTTP/1\.[0-9]$", version):
        raise HTTPInputError(
            "Malformed HTTP version in HTTP Request-Line: %r" % version
        )
    return RequestStartLine(method, path, version)


ResponseStartLine = collections.namedtuple(
    "ResponseStartLine", ["version", "code", "reason"]
)


def parse_response_start_line(line: str) -> ResponseStartLine:
    """Returns a (version, code, reason) tuple for an HTTP 1.x response line.

    The response is a `collections.namedtuple`.

    >>> parse_response_start_line("HTTP/1.1 200 OK")
    ResponseStartLine(version='HTTP/1.1', code=200, reason='OK')
    """
    line = native_str(line)
    match = re.match("(HTTP/1.[0-9]) ([0-9]+) ([^\r]*)", line)
    if not match:
        raise HTTPInputError("Error parsing response start line")
    return ResponseStartLine(match.group(1), int(match.group(2)), match.group(3))


# _parseparam and _parse_header are copied and modified from python2.7's cgi.py
# The original 2.7 version of this code did not correctly support some
# combinations of semicolons and double quotes.
# It has also been modified to support valueless parameters as seen in
# websocket extension negotiations, and to support non-ascii values in
# RFC 2231/5987 format.


def _parseparam(s: str) -> Generator[str, None, None]:
    while s[:1] == ";":
        s = s[1:]
        end = s.find(";")
        while end > 0 and (s.count('"', 0, end) - s.count('\\"', 0, end)) % 2:
            end = s.find(";", end + 1)
        if end < 0:
            end = len(s)
        f = s[:end]
        yield f.strip()
        s = s[end:]


def _parse_header(line: str) -> Tuple[str, Dict[str, str]]:
    r"""Parse a Content-type like header.

    Return the main content-type and a dictionary of options.

    >>> d = "form-data; foo=\"b\\\\a\\\"r\"; file*=utf-8''T%C3%A4st"
    >>> ct, d = _parse_header(d)
    >>> ct
    'form-data'
    >>> d['file'] == r'T\u00e4st'.encode('ascii').decode('unicode_escape')
    True
    >>> d['foo']
    'b\\a"r'
    """
    parts = _parseparam(";" + line)
    key = next(parts)
    # decode_params treats first argument special, but we already stripped key
    params = [("Dummy", "value")]
    for p in parts:
        i = p.find("=")
        if i >= 0:
            name = p[:i].strip().lower()
            value = p[i + 1 :].strip()
            params.append((name, native_str(value)))
    decoded_params = email.utils.decode_params(params)
    decoded_params.pop(0)  # get rid of the dummy again
    pdict = {}
    for name, decoded_value in decoded_params:
        value = email.utils.collapse_rfc2231_value(decoded_value)
        if len(value) >= 2 and value[0] == '"' and value[-1] == '"':
            value = value[1:-1]
        pdict[name] = value
    return key, pdict


def _encode_header(key: str, pdict: Dict[str, str]) -> str:
    """Inverse of _parse_header.

    >>> _encode_header('permessage-deflate',
    ...     {'client_max_window_bits': 15, 'client_no_context_takeover': None})
    'permessage-deflate; client_max_window_bits=15; client_no_context_takeover'
    """
    if not pdict:
        return key
    out = [key]
    # Sort the parameters just to make it easy to test.
    for k, v in sorted(pdict.items()):
        if v is None:
            out.append(k)
        else:
            # TODO: quote if necessary.
            out.append("%s=%s" % (k, v))
    return "; ".join(out)


def encode_username_password(
    username: Union[str, bytes], password: Union[str, bytes]
) -> bytes:
    """Encodes a username/password pair in the format used by HTTP auth.

    The return value is a byte string in the form ``username:password``.

    .. versionadded:: 5.1
    """
    if isinstance(username, unicode_type):
        username = unicodedata.normalize("NFC", username)
    if isinstance(password, unicode_type):
        password = unicodedata.normalize("NFC", password)
    return utf8(username) + b":" + utf8(password)


def doctests():
    # type: () -> unittest.TestSuite
    import doctest

    return doctest.DocTestSuite()


def split_host_and_port(netloc: str) -> Tuple[str, Optional[int]]:
    """Returns ``(host, port)`` tuple from ``netloc``.

    Returned ``port`` will be ``None`` if not present.

    .. versionadded:: 4.1
    """
    match = re.match(r"^(.+):(\d+)$", netloc)
    if match:
        host = match.group(1)
        port = int(match.group(2))  # type: Optional[int]
    else:
        host = netloc
        port = None
    return (host, port)


def qs_to_qsl(qs: Dict[str, List[AnyStr]]) -> Iterable[Tuple[str, AnyStr]]:
    """Generator converting a result of ``parse_qs`` back to name-value pairs.

    .. versionadded:: 5.0
    """
    for k, vs in qs.items():
        for v in vs:
            yield (k, v)


_OctalPatt = re.compile(r"\\[0-3][0-7][0-7]")
_QuotePatt = re.compile(r"[\\].")
_nulljoin = "".join


def _unquote_cookie(s: str) -> str:
    """Handle double quotes and escaping in cookie values.

    This method is copied verbatim from the Python 3.5 standard
    library (http.cookies._unquote) so we don't have to depend on
    non-public interfaces.
    """
    # If there aren't any doublequotes,
    # then there can't be any special characters.  See RFC 2109.
    if s is None or len(s) < 2:
        return s
    if s[0] != '"' or s[-1] != '"':
        return s

    # We have to assume that we must decode this string.
    # Down to work.

    # Remove the "s
    s = s[1:-1]

    # Check for special sequences.  Examples:
    #    \012 --> \n
    #    \"   --> "
    #
    i = 0
    n = len(s)
    res = []
    while 0 <= i < n:
        o_match = _OctalPatt.search(s, i)
        q_match = _QuotePatt.search(s, i)
        if not o_match and not q_match:  # Neither matched
            res.append(s[i:])
            break
        # else:
        j = k = -1
        if o_match:
            j = o_match.start(0)
        if q_match:
            k = q_match.start(0)
        if q_match and (not o_match or k < j):  # QuotePatt matched
            res.append(s[i:k])
            res.append(s[k + 1])
            i = k + 2
        else:  # OctalPatt matched
            res.append(s[i:j])
            res.append(chr(int(s[j + 1 : j + 4], 8)))
            i = j + 4
    return _nulljoin(res)


def parse_cookie(cookie: str) -> Dict[str, str]:
    """Parse a ``Cookie`` HTTP header into a dict of name/value pairs.

    This function attempts to mimic browser cookie parsing behavior;
    it specifically does not follow any of the cookie-related RFCs
    (because browsers don't either).

    The algorithm used is identical to that used by Django version 1.9.10.

    .. versionadded:: 4.4.2
    """
    cookiedict = {}
    for chunk in cookie.split(str(";")):
        if str("=") in chunk:
            key, val = chunk.split(str("="), 1)
        else:
            # Assume an empty name per
            # https://bugzilla.mozilla.org/show_bug.cgi?id=169091
            key, val = str(""), chunk
        key, val = key.strip(), val.strip()
        if key or val:
            # unquote using Python's algorithm.
            cookiedict[key] = _unquote_cookie(val)
    return cookiedict