Skip to content
This repository

HTTPS clone URL

Subversion checkout URL

You can clone with HTTPS or Subversion.

Download ZIP
Fetching contributors…

Octocat-spinner-32-eaf2f5

Cannot retrieve contributors at this time

file 473 lines (386 sloc) 18.1 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
#!/usr/bin/env python
#
# 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.

"""A non-blocking, single-threaded HTTP server.

Typical applications have little direct interaction with the `HTTPServer`
class except to start a server at the beginning of the process
(and even that is often done indirectly via `tornado.web.Application.listen`).

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

from __future__ import absolute_import, division, with_statement

import Cookie
import logging
import socket
import time
import urlparse

from tornado.escape import native_str, parse_qs_bytes
from tornado import httputil
from tornado import iostream
from tornado.netutil import TCPServer
from tornado import stack_context
from tornado.util import b, bytes_type

try:
    import ssl # Python 2.6+
except ImportError:
    ssl = None


class HTTPServer(TCPServer):
    r"""A non-blocking, single-threaded HTTP server.

A server is defined by a request callback that takes an HTTPRequest
instance as an argument and writes a valid HTTP response with
`HTTPRequest.write`. `HTTPRequest.finish` finishes the request (but does
not necessarily close the connection in the case of HTTP/1.1 keep-alive
requests). A simple example server that echoes back the URI you
requested::

import httpserver
import ioloop

def handle_request(request):
message = "You requested %s\n" % request.uri
request.write("HTTP/1.1 200 OK\r\nContent-Length: %d\r\n\r\n%s" % (
len(message), message))
request.finish()

http_server = httpserver.HTTPServer(handle_request)
http_server.listen(8888)
ioloop.IOLoop.instance().start()

`HTTPServer` is a very basic connection handler. Beyond parsing the
HTTP request body and headers, the only HTTP semantics implemented
in `HTTPServer` is HTTP/1.1 keep-alive connections. We do not, however,
implement chunked encoding, so the request callback must provide a
``Content-Length`` header or implement chunked encoding for HTTP/1.1
requests for the server to run correctly for HTTP/1.1 clients. If
the request handler is unable to do this, you can provide the
``no_keep_alive`` argument to the `HTTPServer` constructor, which will
ensure the connection is closed on every request no matter what HTTP
version the client is using.

If ``xheaders`` is ``True``, we support the ``X-Real-Ip`` and ``X-Scheme``
headers, which override the remote IP and HTTP scheme for all requests.
These headers are useful when running Tornado behind a reverse proxy or
load balancer.

`HTTPServer` can serve SSL traffic with Python 2.6+ and OpenSSL.
To make this server serve SSL traffic, send the ssl_options dictionary
argument with the arguments required for the `ssl.wrap_socket` method,
including "certfile" and "keyfile"::

HTTPServer(applicaton, ssl_options={
"certfile": os.path.join(data_dir, "mydomain.crt"),
"keyfile": os.path.join(data_dir, "mydomain.key"),
})

`HTTPServer` initialization follows one of three patterns (the
initialization methods are defined on `tornado.netutil.TCPServer`):

1. `~tornado.netutil.TCPServer.listen`: simple single-process::

server = HTTPServer(app)
server.listen(8888)
IOLoop.instance().start()

In many cases, `tornado.web.Application.listen` can be used to avoid
the need to explicitly create the `HTTPServer`.

2. `~tornado.netutil.TCPServer.bind`/`~tornado.netutil.TCPServer.start`:
simple multi-process::

server = HTTPServer(app)
server.bind(8888)
server.start(0) # Forks multiple sub-processes
IOLoop.instance().start()

When using this interface, an `IOLoop` must *not* be passed
to the `HTTPServer` constructor. `start` will always start
the server on the default singleton `IOLoop`.

3. `~tornado.netutil.TCPServer.add_sockets`: advanced multi-process::

sockets = tornado.netutil.bind_sockets(8888)
tornado.process.fork_processes(0)
server = HTTPServer(app)
server.add_sockets(sockets)
IOLoop.instance().start()

The `add_sockets` interface is more complicated, but it can be
used with `tornado.process.fork_processes` to give you more
flexibility in when the fork happens. `add_sockets` can
also be used in single-process servers if you want to create
your listening sockets in some way other than
`tornado.netutil.bind_sockets`.

"""
    def __init__(self, request_callback, no_keep_alive=False, io_loop=None,
                 xheaders=False, ssl_options=None, **kwargs):
        self.request_callback = request_callback
        self.no_keep_alive = no_keep_alive
        self.xheaders = xheaders
        TCPServer.__init__(self, io_loop=io_loop, ssl_options=ssl_options,
                           **kwargs)

    def handle_stream(self, stream, address):
        HTTPConnection(stream, address, self.request_callback,
                       self.no_keep_alive, self.xheaders)


class _BadRequestException(Exception):
    """Exception class for malformed HTTP requests."""
    pass


class HTTPConnection(object):
    """Handles a connection to an HTTP client, executing HTTP requests.

We parse HTTP headers and bodies, and execute the request callback
until the HTTP conection is closed.
"""
    def __init__(self, stream, address, request_callback, no_keep_alive=False,
                 xheaders=False):
        self.stream = stream
        self.address = address
        self.request_callback = request_callback
        self.no_keep_alive = no_keep_alive
        self.xheaders = xheaders
        self._request = None
        self._request_finished = False
        # Save stack context here, outside of any request. This keeps
        # contexts from one request from leaking into the next.
        self._header_callback = stack_context.wrap(self._on_headers)
        self.stream.read_until(b("\r\n\r\n"), self._header_callback)
        self._write_callback = None

    def write(self, chunk, callback=None):
        """Writes a chunk of output to the stream."""
        assert self._request, "Request closed"
        if not self.stream.closed():
            self._write_callback = stack_context.wrap(callback)
            self.stream.write(chunk, self._on_write_complete)

    def finish(self):
        """Finishes the request."""
        assert self._request, "Request closed"
        self._request_finished = True
        if not self.stream.writing():
            self._finish_request()

    def _on_write_complete(self):
        if self._write_callback is not None:
            callback = self._write_callback
            self._write_callback = None
            callback()
        # _on_write_complete is enqueued on the IOLoop whenever the
        # IOStream's write buffer becomes empty, but it's possible for
        # another callback that runs on the IOLoop before it to
        # simultaneously write more data and finish the request. If
        # there is still data in the IOStream, a future
        # _on_write_complete will be responsible for calling
        # _finish_request.
        if self._request_finished and not self.stream.writing():
            self._finish_request()

    def _finish_request(self):
        if self.no_keep_alive:
            disconnect = True
        else:
            connection_header = self._request.headers.get("Connection")
            if connection_header is not None:
                connection_header = connection_header.lower()
            if self._request.supports_http_1_1():
                disconnect = connection_header == "close"
            elif ("Content-Length" in self._request.headers
                    or self._request.method in ("HEAD", "GET")):
                disconnect = connection_header != "keep-alive"
            else:
                disconnect = True
        self._request = None
        self._request_finished = False
        if disconnect:
            self.stream.close()
            return
        self.stream.read_until(b("\r\n\r\n"), self._header_callback)

    def _on_headers(self, data):
        try:
            data = native_str(data.decode('latin1'))
            eol = data.find("\r\n")
            start_line = data[:eol]
            try:
                method, uri, version = start_line.split(" ")
            except ValueError:
                raise _BadRequestException("Malformed HTTP request line")
            if not version.startswith("HTTP/"):
                raise _BadRequestException("Malformed HTTP version in HTTP Request-Line")
            headers = httputil.HTTPHeaders.parse(data[eol:])

            # HTTPRequest wants an IP, not a full socket address
            if getattr(self.stream.socket, 'family', socket.AF_INET) in (
                socket.AF_INET, socket.AF_INET6):
                # Jython 2.5.2 doesn't have the socket.family attribute,
                # so just assume IP in that case.
                remote_ip = self.address[0]
            else:
                # Unix (or other) socket; fake the remote address
                remote_ip = '0.0.0.0'

            path, sep, query = uri.partition('?')
            self._request = HTTPRequest(
                connection=self, method=method, path=path, query=query,
                arguments=httputil.parse_query(query), version=version,
                headers=headers, remote_ip=remote_ip)

            content_length = headers.get("Content-Length")
            if content_length:
                content_length = int(content_length)
                if content_length > self.stream.max_buffer_size:
                    raise _BadRequestException("Content-Length too long")
                if headers.get("Expect") == "100-continue":
                    self.stream.write(b("HTTP/1.1 100 (Continue)\r\n\r\n"))
                self.stream.read_bytes(content_length, self._on_request_body)
                return

            self.request_callback(self._request)
        except _BadRequestException, e:
            logging.info("Malformed HTTP request from %s: %s",
                         self.address[0], e)
            self.stream.close()
            return

    def _on_request_body(self, data):
        self._request.body = data
        if self._request.method in ("POST", "PATCH", "PUT"):
            httputil.parse_body_arguments(
                self._request.headers.get("Content-Type", ""), data,
                self._request.arguments, self._request.files)
        self.request_callback(self._request)


class HTTPRequest(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

`HTTPHeader` 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`` header

.. 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:: files

File uploads are available in the files property, which maps file
names to lists of :class:`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. This attribute is set to ``None``
in WSGI applications, which do not support asynchronous requests.
"""
    def __init__(self, method, path, query="", arguments=None, version="HTTP/1.0",
                 headers=None, body="", remote_ip=None, protocol=None,
                 host=None, files=None, connection=None):
        self.method = method
        self.uri = path
        if query:
            self.uri += '?' + query
        self.path = path
        self.query = query
        self.arguments = arguments or {}
        self.version = version
        self.headers = headers or httputil.HTTPHeaders()
        self.body = body or ""
        if connection and connection.xheaders:
            # Squid uses X-Forwarded-For, others use X-Real-Ip
            self.remote_ip = self.headers.get(
                "X-Real-Ip", self.headers.get("X-Forwarded-For", remote_ip))
            if not self._valid_ip(self.remote_ip):
                self.remote_ip = remote_ip
            # AWS uses X-Forwarded-Proto
            self.protocol = self.headers.get(
                "X-Scheme", self.headers.get("X-Forwarded-Proto", protocol))
            if self.protocol not in ("http", "https"):
                self.protocol = "http"
        else:
            self.remote_ip = remote_ip
            if protocol:
                self.protocol = protocol
            elif connection and isinstance(connection.stream,
                                           iostream.SSLIOStream):
                self.protocol = "https"
            else:
                self.protocol = "http"
        self.host = host or self.headers.get("Host") or "127.0.0.1"
        self.files = files or {}
        self.connection = connection

        self._start_time = time.time()
        self._finish_time = None
        self._cookies = None

    def supports_http_1_1(self):
        """Returns True if this request supports HTTP/1.1 semantics"""
        return self.version == "HTTP/1.1"

    @property
    def cookies(self):
        """A dictionary of Cookie.Morsel objects."""
        if self._cookies is None:
            self._cookies = Cookie.SimpleCookie()
            if "Cookie" in self.headers:
                try:
                    self._cookies.load(
                        native_str(self.headers["Cookie"]))
                except Exception:
                    self._cookies = {}
        return self._cookies

    def write(self, chunk, callback=None):
        """Writes the given chunk to the response stream."""
        assert isinstance(chunk, bytes_type)
        self.connection.write(chunk, callback=callback)

    def finish(self):
        """Finishes this HTTP request on the open connection."""
        self.connection.finish()
        self._finish_time = time.time()

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

    def request_time(self):
        """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):
        """Returns the client's SSL certificate, if any.

To use client certificates, the HTTPServer must have been constructed
with cert_reqs set in ssl_options, e.g.::

server = HTTPServer(app,
ssl_options=dict(
certfile="foo.crt",
keyfile="foo.key",
cert_reqs=ssl.CERT_REQUIRED,
ca_certs="cacert.crt"))

The return value is a dictionary, see SSLSocket.getpeercert() in
the standard library for more details.
http://docs.python.org/library/ssl.html#sslsocket-objects
"""
        try:
            return self.connection.stream.socket.getpeercert()
        except ssl.SSLError:
            return None

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

    def _valid_ip(self, ip):
        try:
            res = socket.getaddrinfo(ip, 0, socket.AF_UNSPEC,
                                     socket.SOCK_STREAM,
                                     0, socket.AI_NUMERICHOST)
            return bool(res)
        except socket.gaierror, e:
            if e.args[0] == socket.EAI_NONAME:
                return False
            raise
        return True
Something went wrong with that request. Please try again.