django.http.request のソースコード
from __future__ import unicode_literals
import copy
import re
import sys
from io import BytesIO
from itertools import chain
from django.conf import settings
from django.core import signing
from django.core.exceptions import (
DisallowedHost, ImproperlyConfigured, RequestDataTooBig,
)
from django.core.files import uploadhandler
from django.http.multipartparser import MultiPartParser, MultiPartParserError
from django.utils import six
from django.utils.datastructures import ImmutableList, MultiValueDict
from django.utils.encoding import (
escape_uri_path, force_bytes, force_str, force_text, iri_to_uri,
)
from django.utils.http import is_same_domain, limited_parse_qsl
from django.utils.six.moves.urllib.parse import (
quote, urlencode, urljoin, urlsplit,
)
RAISE_ERROR = object()
host_validation_re = re.compile(r"^([a-z0-9.-]+|\[[a-f0-9]*:[a-f0-9\.:]+\])(:\d+)?$")
class RawPostDataException(Exception):
"""
You cannot access raw_post_data from a request that has
multipart/* POST data if it has been accessed via POST,
FILES, etc..
"""
pass
[ドキュメント]class HttpRequest(object):
"""A basic HTTP request."""
# The encoding used in GET/POST dicts. None means use default setting.
_encoding = None
_upload_handlers = []
def __init__(self):
# WARNING: The `WSGIRequest` subclass doesn't call `super`.
# Any variable assignment made here should also happen in
# `WSGIRequest.__init__()`.
self.GET = QueryDict(mutable=True)
self.POST = QueryDict(mutable=True)
self.COOKIES = {}
self.META = {}
self.FILES = MultiValueDict()
self.path = ''
self.path_info = ''
self.method = None
self.resolver_match = None
self._post_parse_error = False
self.content_type = None
self.content_params = None
def __repr__(self):
if self.method is None or not self.get_full_path():
return force_str('<%s>' % self.__class__.__name__)
return force_str(
'<%s: %s %r>' % (self.__class__.__name__, self.method, force_str(self.get_full_path()))
)
def _get_raw_host(self):
"""
Return the HTTP host using the environment or request headers. Skip
allowed hosts protection, so may return an insecure host.
"""
# We try three options, in order of decreasing preference.
if settings.USE_X_FORWARDED_HOST and (
'HTTP_X_FORWARDED_HOST' in self.META):
host = self.META['HTTP_X_FORWARDED_HOST']
elif 'HTTP_HOST' in self.META:
host = self.META['HTTP_HOST']
else:
# Reconstruct the host using the algorithm from PEP 333.
host = self.META['SERVER_NAME']
server_port = self.get_port()
if server_port != ('443' if self.is_secure() else '80'):
host = '%s:%s' % (host, server_port)
return host
[ドキュメント] def get_host(self):
"""Return the HTTP host using the environment or request headers."""
host = self._get_raw_host()
# Allow variants of localhost if ALLOWED_HOSTS is empty and DEBUG=True.
allowed_hosts = settings.ALLOWED_HOSTS
if settings.DEBUG and not allowed_hosts:
allowed_hosts = ['localhost', '127.0.0.1', '[::1]']
domain, port = split_domain_port(host)
if domain and validate_host(domain, allowed_hosts):
return host
else:
msg = "Invalid HTTP_HOST header: %r." % host
if domain:
msg += " You may need to add %r to ALLOWED_HOSTS." % domain
else:
msg += " The domain name provided is not valid according to RFC 1034/1035."
raise DisallowedHost(msg)
[ドキュメント] def get_port(self):
"""Return the port number for the request as a string."""
if settings.USE_X_FORWARDED_PORT and 'HTTP_X_FORWARDED_PORT' in self.META:
port = self.META['HTTP_X_FORWARDED_PORT']
else:
port = self.META['SERVER_PORT']
return str(port)
[ドキュメント] def get_full_path(self, force_append_slash=False):
# RFC 3986 requires query string arguments to be in the ASCII range.
# Rather than crash if this doesn't happen, we encode defensively.
return '%s%s%s' % (
escape_uri_path(self.path),
'/' if force_append_slash and not self.path.endswith('/') else '',
('?' + iri_to_uri(self.META.get('QUERY_STRING', ''))) if self.META.get('QUERY_STRING', '') else ''
)
[ドキュメント] def get_signed_cookie(self, key, default=RAISE_ERROR, salt='', max_age=None):
"""
Attempts to return a signed cookie. If the signature fails or the
cookie has expired, raises an exception... unless you provide the
default argument in which case that value will be returned instead.
"""
try:
cookie_value = self.COOKIES[key]
except KeyError:
if default is not RAISE_ERROR:
return default
else:
raise
try:
value = signing.get_cookie_signer(salt=key + salt).unsign(
cookie_value, max_age=max_age)
except signing.BadSignature:
if default is not RAISE_ERROR:
return default
else:
raise
return value
def get_raw_uri(self):
"""
Return an absolute URI from variables available in this request. Skip
allowed hosts protection, so may return insecure URI.
"""
return '{scheme}://{host}{path}'.format(
scheme=self.scheme,
host=self._get_raw_host(),
path=self.get_full_path(),
)
[ドキュメント] def build_absolute_uri(self, location=None):
"""
Builds an absolute URI from the location and the variables available in
this request. If no ``location`` is specified, the absolute URI is
built on ``request.get_full_path()``. Anyway, if the location is
absolute, it is simply converted to an RFC 3987 compliant URI and
returned and if location is relative or is scheme-relative (i.e.,
``//example.com/``), it is urljoined to a base URL constructed from the
request variables.
"""
if location is None:
# Make it an absolute url (but schemeless and domainless) for the
# edge case that the path starts with '//'.
location = '//%s' % self.get_full_path()
bits = urlsplit(location)
if not (bits.scheme and bits.netloc):
current_uri = '{scheme}://{host}{path}'.format(scheme=self.scheme,
host=self.get_host(),
path=self.path)
# Join the constructed URL with the provided location, which will
# allow the provided ``location`` to apply query strings to the
# base path as well as override the host, if it begins with //
location = urljoin(current_uri, location)
return iri_to_uri(location)
def _get_scheme(self):
"""
Hook for subclasses like WSGIRequest to implement. Returns 'http' by
default.
"""
return 'http'
@property
def scheme(self):
if settings.SECURE_PROXY_SSL_HEADER:
try:
header, value = settings.SECURE_PROXY_SSL_HEADER
except ValueError:
raise ImproperlyConfigured(
'The SECURE_PROXY_SSL_HEADER setting must be a tuple containing two values.'
)
if self.META.get(header) == value:
return 'https'
return self._get_scheme()
@property
def encoding(self):
return self._encoding
@encoding.setter
def encoding(self, val):
"""
Sets the encoding used for GET/POST accesses. If the GET or POST
dictionary has already been created, it is removed and recreated on the
next access (so that it is decoded correctly).
"""
self._encoding = val
if hasattr(self, 'GET'):
del self.GET
if hasattr(self, '_post'):
del self._post
def _initialize_handlers(self):
self._upload_handlers = [uploadhandler.load_handler(handler, self)
for handler in settings.FILE_UPLOAD_HANDLERS]
@property
def upload_handlers(self):
if not self._upload_handlers:
# If there are no upload handlers defined, initialize them from settings.
self._initialize_handlers()
return self._upload_handlers
@upload_handlers.setter
def upload_handlers(self, upload_handlers):
if hasattr(self, '_files'):
raise AttributeError("You cannot set the upload handlers after the upload has been processed.")
self._upload_handlers = upload_handlers
def parse_file_upload(self, META, post_data):
"""Returns a tuple of (POST QueryDict, FILES MultiValueDict)."""
self.upload_handlers = ImmutableList(
self.upload_handlers,
warning="You cannot alter upload handlers after the upload has been processed."
)
parser = MultiPartParser(META, post_data, self.upload_handlers, self.encoding)
return parser.parse()
@property
def body(self):
if not hasattr(self, '_body'):
if self._read_started:
raise RawPostDataException("You cannot access body after reading from request's data stream")
# Limit the maximum request data size that will be handled in-memory.
if (settings.DATA_UPLOAD_MAX_MEMORY_SIZE is not None and
int(self.META.get('CONTENT_LENGTH') or 0) > settings.DATA_UPLOAD_MAX_MEMORY_SIZE):
raise RequestDataTooBig('Request body exceeded settings.DATA_UPLOAD_MAX_MEMORY_SIZE.')
try:
self._body = self.read()
except IOError as e:
six.reraise(UnreadablePostError, UnreadablePostError(*e.args), sys.exc_info()[2])
self._stream = BytesIO(self._body)
return self._body
def _mark_post_parse_error(self):
self._post = QueryDict()
self._files = MultiValueDict()
self._post_parse_error = True
def _load_post_and_files(self):
"""Populate self._post and self._files if the content-type is a form type"""
if self.method != 'POST':
self._post, self._files = QueryDict(encoding=self._encoding), MultiValueDict()
return
if self._read_started and not hasattr(self, '_body'):
self._mark_post_parse_error()
return
if self.content_type == 'multipart/form-data':
if hasattr(self, '_body'):
# Use already read data
data = BytesIO(self._body)
else:
data = self
try:
self._post, self._files = self.parse_file_upload(self.META, data)
except MultiPartParserError:
# An error occurred while parsing POST data. Since when
# formatting the error the request handler might access
# self.POST, set self._post and self._file to prevent
# attempts to parse POST data again.
# Mark that an error occurred. This allows self.__repr__ to
# be explicit about it instead of simply representing an
# empty POST
self._mark_post_parse_error()
raise
elif self.content_type == 'application/x-www-form-urlencoded':
self._post, self._files = QueryDict(self.body, encoding=self._encoding), MultiValueDict()
else:
self._post, self._files = QueryDict(encoding=self._encoding), MultiValueDict()
def close(self):
if hasattr(self, '_files'):
for f in chain.from_iterable(l[1] for l in self._files.lists()):
f.close()
# File-like and iterator interface.
#
# Expects self._stream to be set to an appropriate source of bytes by
# a corresponding request subclass (e.g. WSGIRequest).
# Also when request data has already been read by request.POST or
# request.body, self._stream points to a BytesIO instance
# containing that data.
[ドキュメント] def read(self, *args, **kwargs):
self._read_started = True
try:
return self._stream.read(*args, **kwargs)
except IOError as e:
six.reraise(UnreadablePostError, UnreadablePostError(*e.args), sys.exc_info()[2])
[ドキュメント] def readline(self, *args, **kwargs):
self._read_started = True
try:
return self._stream.readline(*args, **kwargs)
except IOError as e:
six.reraise(UnreadablePostError, UnreadablePostError(*e.args), sys.exc_info()[2])
__iter__ = xreadlines
[ドキュメント]class QueryDict(MultiValueDict):
"""
A specialized MultiValueDict which represents a query string.
A QueryDict can be used to represent GET or POST data. It subclasses
MultiValueDict since keys in such data can be repeated, for instance
in the data from a form with a <select multiple> field.
By default QueryDicts are immutable, though the copy() method
will always return a mutable copy.
Both keys and values set on this class are converted from the given encoding
(DEFAULT_CHARSET by default) to unicode.
"""
# These are both reset in __init__, but is specified here at the class
# level so that unpickling will have valid values
_mutable = True
_encoding = None
[ドキュメント] def __init__(self, query_string=None, mutable=False, encoding=None):
super(QueryDict, self).__init__()
if not encoding:
encoding = settings.DEFAULT_CHARSET
self.encoding = encoding
query_string = query_string or ''
parse_qsl_kwargs = {
'keep_blank_values': True,
'fields_limit': settings.DATA_UPLOAD_MAX_NUMBER_FIELDS,
'encoding': encoding,
}
if six.PY3:
if isinstance(query_string, bytes):
# query_string normally contains URL-encoded data, a subset of ASCII.
try:
query_string = query_string.decode(encoding)
except UnicodeDecodeError:
# ... but some user agents are misbehaving :-(
query_string = query_string.decode('iso-8859-1')
for key, value in limited_parse_qsl(query_string, **parse_qsl_kwargs):
self.appendlist(key, value)
else:
for key, value in limited_parse_qsl(query_string, **parse_qsl_kwargs):
try:
value = value.decode(encoding)
except UnicodeDecodeError:
value = value.decode('iso-8859-1')
self.appendlist(force_text(key, encoding, errors='replace'),
value)
self._mutable = mutable
[ドキュメント] @classmethod
def fromkeys(cls, iterable, value='', mutable=False, encoding=None):
"""
Return a new QueryDict with keys (may be repeated) from an iterable and
values from value.
"""
q = cls('', mutable=True, encoding=encoding)
for key in iterable:
q.appendlist(key, value)
if not mutable:
q._mutable = False
return q
@property
def encoding(self):
if self._encoding is None:
self._encoding = settings.DEFAULT_CHARSET
return self._encoding
@encoding.setter
def encoding(self, value):
self._encoding = value
def _assert_mutable(self):
if not self._mutable:
raise AttributeError("This QueryDict instance is immutable")
[ドキュメント] def __setitem__(self, key, value):
self._assert_mutable()
key = bytes_to_text(key, self.encoding)
value = bytes_to_text(value, self.encoding)
super(QueryDict, self).__setitem__(key, value)
def __delitem__(self, key):
self._assert_mutable()
super(QueryDict, self).__delitem__(key)
def __copy__(self):
result = self.__class__('', mutable=True, encoding=self.encoding)
for key, value in six.iterlists(self):
result.setlist(key, value)
return result
def __deepcopy__(self, memo):
result = self.__class__('', mutable=True, encoding=self.encoding)
memo[id(self)] = result
for key, value in six.iterlists(self):
result.setlist(copy.deepcopy(key, memo), copy.deepcopy(value, memo))
return result
[ドキュメント] def setlist(self, key, list_):
self._assert_mutable()
key = bytes_to_text(key, self.encoding)
list_ = [bytes_to_text(elt, self.encoding) for elt in list_]
super(QueryDict, self).setlist(key, list_)
[ドキュメント] def setlistdefault(self, key, default_list=None):
self._assert_mutable()
return super(QueryDict, self).setlistdefault(key, default_list)
[ドキュメント] def appendlist(self, key, value):
self._assert_mutable()
key = bytes_to_text(key, self.encoding)
value = bytes_to_text(value, self.encoding)
super(QueryDict, self).appendlist(key, value)
[ドキュメント] def pop(self, key, *args):
self._assert_mutable()
return super(QueryDict, self).pop(key, *args)
def clear(self):
self._assert_mutable()
super(QueryDict, self).clear()
[ドキュメント] def setdefault(self, key, default=None):
self._assert_mutable()
key = bytes_to_text(key, self.encoding)
default = bytes_to_text(default, self.encoding)
return super(QueryDict, self).setdefault(key, default)
[ドキュメント] def urlencode(self, safe=None):
"""
Returns an encoded string of all query string arguments.
:arg safe: Used to specify characters which do not require quoting, for
example::
>>> q = QueryDict(mutable=True)
>>> q['next'] = '/a&b/'
>>> q.urlencode()
'next=%2Fa%26b%2F'
>>> q.urlencode(safe='/')
'next=/a%26b/'
"""
output = []
if safe:
safe = force_bytes(safe, self.encoding)
def encode(k, v):
return '%s=%s' % ((quote(k, safe), quote(v, safe)))
else:
def encode(k, v):
return urlencode({k: v})
for k, list_ in self.lists():
k = force_bytes(k, self.encoding)
output.extend(encode(k, force_bytes(v, self.encoding))
for v in list_)
return '&'.join(output)
# It's neither necessary nor appropriate to use
# django.utils.encoding.force_text for parsing URLs and form inputs. Thus,
# this slightly more restricted function, used by QueryDict.
def bytes_to_text(s, encoding):
"""
Converts basestring objects to unicode, using the given encoding. Illegally
encoded input characters are replaced with Unicode "unknown" codepoint
(\ufffd).
Returns any non-basestring objects without change.
"""
if isinstance(s, bytes):
return six.text_type(s, encoding, 'replace')
else:
return s
def split_domain_port(host):
"""
Return a (domain, port) tuple from a given host.
Returned domain is lower-cased. If the host is invalid, the domain will be
empty.
"""
host = host.lower()
if not host_validation_re.match(host):
return '', ''
if host[-1] == ']':
# It's an IPv6 address without a port.
return host, ''
bits = host.rsplit(':', 1)
domain, port = bits if len(bits) == 2 else (bits[0], '')
# Remove a trailing dot (if present) from the domain.
domain = domain[:-1] if domain.endswith('.') else domain
return domain, port
def validate_host(host, allowed_hosts):
"""
Validate the given host for this site.
Check that the host looks valid and matches a host or host pattern in the
given list of ``allowed_hosts``. Any pattern beginning with a period
matches a domain and all its subdomains (e.g. ``.example.com`` matches
``example.com`` and any subdomain), ``*`` matches anything, and anything
else must match exactly.
Note: This function assumes that the given host is lower-cased and has
already had the port, if any, stripped off.
Return ``True`` for a valid host, ``False`` otherwise.
"""
for pattern in allowed_hosts:
if pattern == '*' or is_same_domain(host, pattern):
return True
return False
