|
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373 |
- """
- This module contains helper functions for controlling caching. It does so by
- managing the "Vary" header of responses. It includes functions to patch the
- header of response objects directly and decorators that change functions to do
- that header-patching themselves.
-
- For information on the Vary header, see:
-
- https://tools.ietf.org/html/rfc7231#section-7.1.4
-
- Essentially, the "Vary" HTTP header defines which headers a cache should take
- into account when building its cache key. Requests with the same path but
- different header content for headers named in "Vary" need to get different
- cache keys to prevent delivery of wrong content.
-
- An example: i18n middleware would need to distinguish caches by the
- "Accept-language" header.
- """
- from __future__ import unicode_literals
-
- import hashlib
- import logging
- import re
- import time
-
- from django.conf import settings
- from django.core.cache import caches
- from django.http import HttpResponse, HttpResponseNotModified
- from django.utils.encoding import force_bytes, force_text, iri_to_uri
- from django.utils.http import (
- http_date, parse_etags, parse_http_date_safe, quote_etag,
- )
- from django.utils.timezone import get_current_timezone_name
- from django.utils.translation import get_language
-
- cc_delim_re = re.compile(r'\s*,\s*')
-
- logger = logging.getLogger('django.request')
-
-
- def patch_cache_control(response, **kwargs):
- """
- This function patches the Cache-Control header by adding all
- keyword arguments to it. The transformation is as follows:
-
- * All keyword parameter names are turned to lowercase, and underscores
- are converted to hyphens.
- * If the value of a parameter is True (exactly True, not just a
- true value), only the parameter name is added to the header.
- * All other parameters are added with their value, after applying
- str() to it.
- """
- def dictitem(s):
- t = s.split('=', 1)
- if len(t) > 1:
- return (t[0].lower(), t[1])
- else:
- return (t[0].lower(), True)
-
- def dictvalue(t):
- if t[1] is True:
- return t[0]
- else:
- return '%s=%s' % (t[0], t[1])
-
- if response.has_header('Cache-Control'):
- cc = cc_delim_re.split(response['Cache-Control'])
- cc = dict(dictitem(el) for el in cc)
- else:
- cc = {}
-
- # If there's already a max-age header but we're being asked to set a new
- # max-age, use the minimum of the two ages. In practice this happens when
- # a decorator and a piece of middleware both operate on a given view.
- if 'max-age' in cc and 'max_age' in kwargs:
- kwargs['max_age'] = min(int(cc['max-age']), kwargs['max_age'])
-
- # Allow overriding private caching and vice versa
- if 'private' in cc and 'public' in kwargs:
- del cc['private']
- elif 'public' in cc and 'private' in kwargs:
- del cc['public']
-
- for (k, v) in kwargs.items():
- cc[k.replace('_', '-')] = v
- cc = ', '.join(dictvalue(el) for el in cc.items())
- response['Cache-Control'] = cc
-
-
- def get_max_age(response):
- """
- Returns the max-age from the response Cache-Control header as an integer
- (or ``None`` if it wasn't found or wasn't an integer.
- """
- if not response.has_header('Cache-Control'):
- return
- cc = dict(_to_tuple(el) for el in
- cc_delim_re.split(response['Cache-Control']))
- if 'max-age' in cc:
- try:
- return int(cc['max-age'])
- except (ValueError, TypeError):
- pass
-
-
- def set_response_etag(response):
- if not response.streaming:
- response['ETag'] = quote_etag(hashlib.md5(response.content).hexdigest())
- return response
-
-
- def _precondition_failed(request):
- logger.warning('Precondition Failed: %s', request.path,
- extra={
- 'status_code': 412,
- 'request': request,
- },
- )
- return HttpResponse(status=412)
-
-
- def _not_modified(request, response=None):
- if response:
- # We need to keep the cookies, see ticket #4994.
- cookies = response.cookies
- response = HttpResponseNotModified()
- response.cookies = cookies
- return response
- else:
- return HttpResponseNotModified()
-
-
- def get_conditional_response(request, etag=None, last_modified=None, response=None):
- # Get HTTP request headers
- if_modified_since = request.META.get('HTTP_IF_MODIFIED_SINCE')
- if if_modified_since:
- if_modified_since = parse_http_date_safe(if_modified_since)
- if_unmodified_since = request.META.get('HTTP_IF_UNMODIFIED_SINCE')
- if if_unmodified_since:
- if_unmodified_since = parse_http_date_safe(if_unmodified_since)
- if_none_match = request.META.get('HTTP_IF_NONE_MATCH')
- if_match = request.META.get('HTTP_IF_MATCH')
- etags = []
- if if_none_match or if_match:
- # There can be more than one ETag in the request, so we
- # consider the list of values.
- try:
- etags = parse_etags(if_none_match or if_match)
- except ValueError:
- # In case of an invalid ETag, ignore all ETag headers.
- # Apparently Opera sends invalidly quoted headers at times
- # (we should be returning a 400 response, but that's a
- # little extreme) -- this is bug #10681.
- if_none_match = None
- if_match = None
-
- # If-None-Match must be ignored if original result would be anything
- # other than a 2XX or 304 status. 304 status would result in no change.
- # http://www.w3.org/Protocols/rfc2616/rfc2616-sec14.html#sec14.26
- if response and not (200 <= response.status_code < 300):
- if_none_match = None
- if_match = None
-
- # If-Modified-Since must be ignored if the original result was not a 200.
- # http://www.w3.org/Protocols/rfc2616/rfc2616-sec14.html#sec14.25
- if response and response.status_code != 200:
- if_modified_since = None
- if_unmodified_since = None
-
- if not ((if_match and if_modified_since) or
- (if_none_match and if_unmodified_since) or
- (if_modified_since and if_unmodified_since) or
- (if_match and if_none_match)):
- # We only get here if no undefined combinations of headers are
- # specified.
- if ((if_none_match and (etag in etags or
- '*' in etags and etag)) and
- (not if_modified_since or
- (last_modified and if_modified_since and
- last_modified <= if_modified_since))):
- if request.method in ('GET', 'HEAD'):
- return _not_modified(request, response)
- else:
- return _precondition_failed(request)
- elif (if_match and ((not etag and '*' in etags) or
- (etag and etag not in etags) or
- (last_modified and if_unmodified_since and
- last_modified > if_unmodified_since))):
- return _precondition_failed(request)
- elif (not if_none_match and request.method in ('GET', 'HEAD') and
- last_modified and if_modified_since and
- last_modified <= if_modified_since):
- return _not_modified(request, response)
- elif (not if_match and
- last_modified and if_unmodified_since and
- last_modified > if_unmodified_since):
- return _precondition_failed(request)
-
- return response
-
-
- def patch_response_headers(response, cache_timeout=None):
- """
- Adds some useful headers to the given HttpResponse object:
- ETag, Last-Modified, Expires and Cache-Control
-
- Each header is only added if it isn't already set.
-
- cache_timeout is in seconds. The CACHE_MIDDLEWARE_SECONDS setting is used
- by default.
- """
- if cache_timeout is None:
- cache_timeout = settings.CACHE_MIDDLEWARE_SECONDS
- if cache_timeout < 0:
- cache_timeout = 0 # Can't have max-age negative
- if settings.USE_ETAGS and not response.has_header('ETag'):
- if hasattr(response, 'render') and callable(response.render):
- response.add_post_render_callback(set_response_etag)
- else:
- response = set_response_etag(response)
- if not response.has_header('Last-Modified'):
- response['Last-Modified'] = http_date()
- if not response.has_header('Expires'):
- response['Expires'] = http_date(time.time() + cache_timeout)
- patch_cache_control(response, max_age=cache_timeout)
-
-
- def add_never_cache_headers(response):
- """
- Adds headers to a response to indicate that a page should never be cached.
- """
- patch_response_headers(response, cache_timeout=-1)
- patch_cache_control(response, no_cache=True, no_store=True, must_revalidate=True)
-
-
- def patch_vary_headers(response, newheaders):
- """
- Adds (or updates) the "Vary" header in the given HttpResponse object.
- newheaders is a list of header names that should be in "Vary". Existing
- headers in "Vary" aren't removed.
- """
- # Note that we need to keep the original order intact, because cache
- # implementations may rely on the order of the Vary contents in, say,
- # computing an MD5 hash.
- if response.has_header('Vary'):
- vary_headers = cc_delim_re.split(response['Vary'])
- else:
- vary_headers = []
- # Use .lower() here so we treat headers as case-insensitive.
- existing_headers = set(header.lower() for header in vary_headers)
- additional_headers = [newheader for newheader in newheaders
- if newheader.lower() not in existing_headers]
- response['Vary'] = ', '.join(vary_headers + additional_headers)
-
-
- def has_vary_header(response, header_query):
- """
- Checks to see if the response has a given header name in its Vary header.
- """
- if not response.has_header('Vary'):
- return False
- vary_headers = cc_delim_re.split(response['Vary'])
- existing_headers = set(header.lower() for header in vary_headers)
- return header_query.lower() in existing_headers
-
-
- def _i18n_cache_key_suffix(request, cache_key):
- """If necessary, adds the current locale or time zone to the cache key."""
- if settings.USE_I18N or settings.USE_L10N:
- # first check if LocaleMiddleware or another middleware added
- # LANGUAGE_CODE to request, then fall back to the active language
- # which in turn can also fall back to settings.LANGUAGE_CODE
- cache_key += '.%s' % getattr(request, 'LANGUAGE_CODE', get_language())
- if settings.USE_TZ:
- # The datetime module doesn't restrict the output of tzname().
- # Windows is known to use non-standard, locale-dependent names.
- # User-defined tzinfo classes may return absolutely anything.
- # Hence this paranoid conversion to create a valid cache key.
- tz_name = force_text(get_current_timezone_name(), errors='ignore')
- cache_key += '.%s' % tz_name.encode('ascii', 'ignore').decode('ascii').replace(' ', '_')
- return cache_key
-
-
- def _generate_cache_key(request, method, headerlist, key_prefix):
- """Returns a cache key from the headers given in the header list."""
- ctx = hashlib.md5()
- for header in headerlist:
- value = request.META.get(header)
- if value is not None:
- ctx.update(force_bytes(value))
- url = hashlib.md5(force_bytes(iri_to_uri(request.build_absolute_uri())))
- cache_key = 'views.decorators.cache.cache_page.%s.%s.%s.%s' % (
- key_prefix, method, url.hexdigest(), ctx.hexdigest())
- return _i18n_cache_key_suffix(request, cache_key)
-
-
- def _generate_cache_header_key(key_prefix, request):
- """Returns a cache key for the header cache."""
- url = hashlib.md5(force_bytes(iri_to_uri(request.build_absolute_uri())))
- cache_key = 'views.decorators.cache.cache_header.%s.%s' % (
- key_prefix, url.hexdigest())
- return _i18n_cache_key_suffix(request, cache_key)
-
-
- def get_cache_key(request, key_prefix=None, method='GET', cache=None):
- """
- Returns a cache key based on the request URL and query. It can be used
- in the request phase because it pulls the list of headers to take into
- account from the global URL registry and uses those to build a cache key
- to check against.
-
- If there is no headerlist stored, the page needs to be rebuilt, so this
- function returns None.
- """
- if key_prefix is None:
- key_prefix = settings.CACHE_MIDDLEWARE_KEY_PREFIX
- cache_key = _generate_cache_header_key(key_prefix, request)
- if cache is None:
- cache = caches[settings.CACHE_MIDDLEWARE_ALIAS]
- headerlist = cache.get(cache_key)
- if headerlist is not None:
- return _generate_cache_key(request, method, headerlist, key_prefix)
- else:
- return None
-
-
- def learn_cache_key(request, response, cache_timeout=None, key_prefix=None, cache=None):
- """
- Learns what headers to take into account for some request URL from the
- response object. It stores those headers in a global URL registry so that
- later access to that URL will know what headers to take into account
- without building the response object itself. The headers are named in the
- Vary header of the response, but we want to prevent response generation.
-
- The list of headers to use for cache key generation is stored in the same
- cache as the pages themselves. If the cache ages some data out of the
- cache, this just means that we have to build the response once to get at
- the Vary header and so at the list of headers to use for the cache key.
- """
- if key_prefix is None:
- key_prefix = settings.CACHE_MIDDLEWARE_KEY_PREFIX
- if cache_timeout is None:
- cache_timeout = settings.CACHE_MIDDLEWARE_SECONDS
- cache_key = _generate_cache_header_key(key_prefix, request)
- if cache is None:
- cache = caches[settings.CACHE_MIDDLEWARE_ALIAS]
- if response.has_header('Vary'):
- is_accept_language_redundant = settings.USE_I18N or settings.USE_L10N
- # If i18n or l10n are used, the generated cache key will be suffixed
- # with the current locale. Adding the raw value of Accept-Language is
- # redundant in that case and would result in storing the same content
- # under multiple keys in the cache. See #18191 for details.
- headerlist = []
- for header in cc_delim_re.split(response['Vary']):
- header = header.upper().replace('-', '_')
- if header == 'ACCEPT_LANGUAGE' and is_accept_language_redundant:
- continue
- headerlist.append('HTTP_' + header)
- headerlist.sort()
- cache.set(cache_key, headerlist, cache_timeout)
- return _generate_cache_key(request, request.method, headerlist, key_prefix)
- else:
- # if there is no Vary header, we still need a cache key
- # for the request.build_absolute_uri()
- cache.set(cache_key, [], cache_timeout)
- return _generate_cache_key(request, request.method, [], key_prefix)
-
-
- def _to_tuple(s):
- t = s.split('=', 1)
- if len(t) == 2:
- return t[0].lower(), t[1]
- return t[0].lower(), True
|