forked from tornadoweb/tornado
/
httpserver.py
330 lines (289 loc) · 13 KB
/
httpserver.py
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
#!/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."""
import cgi
import errno
import fcntl
import functools
import ioloop
import iostream
import logging
import socket
import time
import urlparse
class HTTPServer(object):
"""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
request.write(). request.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.
"""
def __init__(self, request_callback, no_keep_alive=False, io_loop=None,
xheaders=False):
self.request_callback = request_callback
self.no_keep_alive = no_keep_alive
self.io_loop = io_loop or ioloop.IOLoop.instance()
self.xheaders = xheaders
self._socket = None
def listen(self, port):
assert not self._socket
self._socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM, 0)
flags = fcntl.fcntl(self._socket.fileno(), fcntl.F_GETFD)
flags |= fcntl.FD_CLOEXEC
fcntl.fcntl(self._socket.fileno(), fcntl.F_SETFD, flags)
self._socket.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
self._socket.setblocking(0)
self._socket.bind(("", port))
self._socket.listen(128)
self.io_loop.add_handler(self._socket.fileno(), self._handle_events,
self.io_loop.READ)
def _handle_events(self, fd, events):
while True:
try:
connection, address = self._socket.accept()
except socket.error, e:
if e[0] in (errno.EWOULDBLOCK, errno.EAGAIN):
return
raise
try:
stream = iostream.IOStream(connection, io_loop=self.io_loop)
HTTPConnection(stream, address, self.request_callback,
self.no_keep_alive, self.xheaders)
except:
logging.error("Error in connection callback", exc_info=True)
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
self.stream.read_until("\r\n\r\n", self._on_headers)
def write(self, chunk):
assert self._request, "Request closed"
self.stream.write(chunk, self._on_write_complete)
def finish(self):
assert self._request, "Request closed"
self._request_finished = True
if not self.stream.writing():
self._finish_request()
def _on_write_complete(self):
if self._request_finished:
self._finish_request()
def _finish_request(self):
if self.no_keep_alive:
disconnect = True
else:
connection_header = self._request.headers.get("Connection")
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("\r\n\r\n", self._on_headers)
def _on_headers(self, data):
eol = data.find("\r\n")
start_line = data[:eol]
method, uri, version = start_line.split(" ")
if not version.startswith("HTTP/"):
raise Exception("Malformed HTTP version in HTTP Request-Line")
headers = HTTPHeaders.parse(data[eol:])
self._request = HTTPRequest(
connection=self, method=method, uri=uri, version=version,
headers=headers, remote_ip=self.address[0])
content_length = headers.get("Content-Length")
if content_length:
content_length = int(content_length)
if content_length > self.stream.max_buffer_size:
raise Exception("Content-Length too long")
if headers.get("Expect") == "100-continue":
self.stream.write("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)
def _on_request_body(self, data):
self._request.body = data
content_type = self._request.headers.get("Content-Type", "")
if self._request.method == "POST":
if content_type.startswith("application/x-www-form-urlencoded"):
arguments = cgi.parse_qs(self._request.body)
for name, values in arguments.iteritems():
values = [v for v in values if v]
if values:
self._request.arguments.setdefault(name, []).extend(
values)
elif content_type.startswith("multipart/form-data"):
boundary = content_type[30:]
if boundary: self._parse_mime_body(boundary, data)
self.request_callback(self._request)
def _parse_mime_body(self, boundary, data):
if data.endswith("\r\n"):
footer_length = len(boundary) + 6
else:
footer_length = len(boundary) + 4
parts = data[:-footer_length].split("--" + boundary + "\r\n")
for part in parts:
if not part: continue
eoh = part.find("\r\n\r\n")
if eoh == -1:
logging.warning("multipart/form-data missing headers")
continue
headers = HTTPHeaders.parse(part[:eoh])
name_header = headers.get("Content-Disposition", "")
if not name_header.startswith("form-data;") or \
not part.endswith("\r\n"):
logging.warning("Invalid multipart/form-data")
continue
value = part[eoh + 4:-2]
name_values = {}
for name_part in name_header[10:].split(";"):
name, name_value = name_part.strip().split("=", 1)
name_values[name] = name_value.strip('"').decode("utf-8")
if not name_values.get("name"):
logging.warning("multipart/form-data value missing name")
continue
name = name_values["name"]
if name_values.get("filename"):
ctype = headers.get("Content-Type", "application/unknown")
self._request.files.setdefault(name, []).append(dict(
filename=name_values["filename"], body=value,
content_type=ctype))
else:
self._request.arguments.setdefault(name, []).append(value)
class HTTPRequest(object):
"""A single HTTP request.
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 and values are both unicode always.
File uploads are available in the files property, which maps file
names to list of files. Each file is a dictionary of the form
{"filename":..., "content_type":..., "body":...}. The content_type
comes from the provided HTTP header and should not be trusted
outright given that it can be easily forged.
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.
"""
def __init__(self, method, uri, version="HTTP/1.0", headers=None,
body=None, remote_ip=None, protocol=None, host=None,
files=None, connection=None):
self.method = method
self.uri = uri
self.version = version
self.headers = headers or HTTPHeaders()
self.body = body or ""
if connection and connection.xheaders:
self.remote_ip = headers.get("X-Real-Ip", remote_ip)
self.protocol = headers.get("X-Scheme", protocol) or "http"
else:
self.remote_ip = remote_ip
self.protocol = protocol or "http"
self.host = host or headers.get("Host") or "127.0.0.1"
self.files = files or {}
self.connection = connection
self._start_time = time.time()
self._finish_time = None
scheme, netloc, path, query, fragment = urlparse.urlsplit(uri)
self.path = path
self.query = query
arguments = cgi.parse_qs(query)
self.arguments = {}
for name, values in arguments.iteritems():
values = [v for v in values if v]
if values: self.arguments[name] = values
def supports_http_1_1(self):
"""Returns True if this request supports HTTP/1.1 semantics"""
return self.version == "HTTP/1.1"
def write(self, chunk):
"""Writes the given chunk to the response stream."""
assert isinstance(chunk, str)
self.connection.write(chunk)
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 __repr__(self):
attrs = ("protocol", "host", "method", "uri", "version", "remote_ip",
"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))
class HTTPHeaders(dict):
"""A dictionary that maintains Http-Header-Case for all keys."""
def __setitem__(self, name, value):
dict.__setitem__(self, self._normalize_name(name), value)
def __getitem__(self, name):
return dict.__getitem__(self, self._normalize_name(name))
def _normalize_name(self, name):
return "-".join([w.capitalize() for w in name.split("-")])
@classmethod
def parse(cls, headers_string):
headers = cls()
for line in headers_string.splitlines():
if line:
name, value = line.split(": ", 1)
headers[name] = value
return headers