/usr/lib/python2.7/dist-packages/tornado/httputil.py is in python-tornado 3.1.1-1ubuntu2.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 | #!/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.
"""HTTP utility code shared by clients and servers."""
from __future__ import absolute_import, division, print_function, with_statement
import calendar
import collections
import datetime
import email.utils
import numbers
import time
from tornado.escape import native_str, parse_qs_bytes, utf8
from tornado.log import gen_log
from tornado.util import ObjectDict
try:
from httplib import responses # py2
except ImportError:
from http.client import responses # py3
# responses is unused in this file, but we re-export it to other files.
# Reference it so pyflakes doesn't complain.
responses
try:
from urllib import urlencode # py2
except ImportError:
from urllib.parse import urlencode # py3
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):
super(_NormalizedHeaderCache, self).__init__()
self.size = size
self.queue = collections.deque()
def __missing__(self, key):
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(dict):
"""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
"""
def __init__(self, *args, **kwargs):
# Don't pass args or kwargs to dict.__init__, as it will bypass
# our __setitem__
dict.__init__(self)
self._as_list = {}
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, value):
"""Adds a new value for the given key."""
norm_name = _normalized_headers[name]
self._last_key = norm_name
if norm_name in self:
# bypass our override of __setitem__ since it modifies _as_list
dict.__setitem__(self, 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):
"""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):
"""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):
"""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
new_part = ' ' + line.lstrip()
self._as_list[self._last_key][-1] += new_part
dict.__setitem__(self, self._last_key,
self[self._last_key] + new_part)
else:
name, value = line.split(":", 1)
self.add(name, value.strip())
@classmethod
def parse(cls, headers):
"""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')]
"""
h = cls()
for line in headers.splitlines():
if line:
h.parse_line(line)
return h
# dict implementation overrides
def __setitem__(self, name, value):
norm_name = _normalized_headers[name]
dict.__setitem__(self, norm_name, value)
self._as_list[norm_name] = [value]
def __getitem__(self, name):
return dict.__getitem__(self, _normalized_headers[name])
def __delitem__(self, name):
norm_name = _normalized_headers[name]
dict.__delitem__(self, norm_name)
del self._as_list[norm_name]
def __contains__(self, name):
norm_name = _normalized_headers[name]
return dict.__contains__(self, norm_name)
def get(self, name, default=None):
return dict.get(self, _normalized_headers[name], default)
def update(self, *args, **kwargs):
# dict.update bypasses our __setitem__
for k, v in dict(*args, **kwargs).items():
self[k] = v
def copy(self):
# default implementation returns dict(self), not the subclass
return HTTPHeaders(self)
def url_concat(url, args):
"""Concatenate url and argument dictionary regardless of whether
url has existing query parameters.
>>> url_concat("http://example.com/foo?a=b", dict(c="d"))
'http://example.com/foo?a=b&c=d'
"""
if not args:
return url
if url[-1] not in ('?', '&'):
url += '&' if ('?' in url) else '?'
return url + urlencode(args)
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):
"""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, end, total):
"""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):
val = val.strip()
if val == "":
return None
return int(val)
def parse_body_arguments(content_type, body, arguments, files):
"""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"):
uri_arguments = parse_qs_bytes(native_str(body), keep_blank_values=True)
for name, values in uri_arguments.items():
if values:
arguments.setdefault(name, []).extend(values)
elif content_type.startswith("multipart/form-data"):
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:
gen_log.warning("Invalid multipart/form-data")
def parse_multipart_form_data(boundary, data, arguments, files):
"""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.
"""
# 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):
"""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, numbers.Real):
pass
elif isinstance(ts, (tuple, time.struct_time)):
ts = calendar.timegm(ts)
elif isinstance(ts, datetime.datetime):
ts = calendar.timegm(ts.utctimetuple())
else:
raise TypeError("unknown timestamp type: %r" % ts)
return email.utils.formatdate(ts, usegmt=True)
# _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.
def _parseparam(s):
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):
"""Parse a Content-type like header.
Return the main content-type and a dictionary of options.
"""
parts = _parseparam(';' + line)
key = next(parts)
pdict = {}
for p in parts:
i = p.find('=')
if i >= 0:
name = p[:i].strip().lower()
value = p[i + 1:].strip()
if len(value) >= 2 and value[0] == value[-1] == '"':
value = value[1:-1]
value = value.replace('\\\\', '\\').replace('\\"', '"')
pdict[name] = value
return key, pdict
def doctests():
import doctest
return doctest.DocTestSuite()
|