implemented async-only common middleware

Author: amirreza8002

django_async_extensions/amiddleware/common.py

@@ -0,0 +1,179 @@
+import re
+from urllib.parse import urlsplit
+
+from django.conf import settings
+from django.core.exceptions import PermissionDenied
+from django.core.mail import mail_managers
+from django.http import HttpResponsePermanentRedirect
+from django.urls import is_valid_path
+from django.utils.http import escape_leading_slashes
+
+from django_async_extensions.amiddleware.base import AsyncMiddlewareMixin
+
+
+class AsyncCommonMiddleware(AsyncMiddlewareMixin):
+    """
+    "Common" middleware for taking care of some basic operations:
+
+        - Forbid access to User-Agents in settings.DISALLOWED_USER_AGENTS
+
+        - URL rewriting: Based on the APPEND_SLASH and PREPEND_WWW settings,
+          append missing slashes and/or prepends missing "www."s.
+
+            - If APPEND_SLASH is set and the initial URL doesn't end with a
+              slash, and it is not found in urlpatterns, form a new URL by
+              appending a slash at the end. If this new URL is found in
+              urlpatterns, return an HTTP redirect to this new URL; otherwise
+              process the initial URL as usual.
+
+          This behavior can be customized by subclassing AsyncCommonMiddleware and
+          overriding the response_redirect_class attribute.
+    """
+
+    response_redirect_class = HttpResponsePermanentRedirect
+
+    async def process_request(self, request):
+        """
+        Check for denied User-Agents and rewrite the URL based on
+        settings.APPEND_SLASH and settings.PREPEND_WWW
+        """
+
+        # Check for denied User-Agents
+        user_agent = request.META.get("HTTP_USER_AGENT")
+        if user_agent is not None:
+            for user_agent_regex in settings.DISALLOWED_USER_AGENTS:
+                if user_agent_regex.search(user_agent):
+                    raise PermissionDenied("Forbidden user agent")
+
+        # Check for a redirect based on settings.PREPEND_WWW
+        host = request.get_host()
+
+        if settings.PREPEND_WWW and host and not host.startswith("www."):
+            # Check if we also need to append a slash so we can do it all
+            # with a single redirect. (This check may be somewhat expensive,
+            # so we only do it if we already know we're sending a redirect,
+            # or in process_response if we get a 404.)
+            if self.should_redirect_with_slash(request):
+                path = self.get_full_path_with_slash(request)
+            else:
+                path = request.get_full_path()
+
+            return self.response_redirect_class(f"{request.scheme}://www.{host}{path}")
+
+    def should_redirect_with_slash(self, request):
+        """
+        Return True if settings.APPEND_SLASH is True and appending a slash to
+        the request path turns an invalid path into a valid one.
+        """
+        if settings.APPEND_SLASH and not request.path_info.endswith("/"):
+            urlconf = getattr(request, "urlconf", None)
+            if not is_valid_path(request.path_info, urlconf):
+                match = is_valid_path("%s/" % request.path_info, urlconf)
+                if match:
+                    view = match.func
+                    return getattr(view, "should_append_slash", True)
+        return False
+
+    def get_full_path_with_slash(self, request):
+        """
+        Return the full path of the request with a trailing slash appended.
+
+        Raise a RuntimeError if settings.DEBUG is True and request.method is
+        DELETE, POST, PUT, or PATCH.
+        """
+        new_path = request.get_full_path(force_append_slash=True)
+        # Prevent construction of scheme relative urls.
+        new_path = escape_leading_slashes(new_path)
+        if settings.DEBUG and request.method in ("DELETE", "POST", "PUT", "PATCH"):
+            raise RuntimeError(
+                "You called this URL via %(method)s, but the URL doesn't end "
+                "in a slash and you have APPEND_SLASH set. Django can't "
+                "redirect to the slash URL while maintaining %(method)s data. "
+                "Change your form to point to %(url)s (note the trailing "
+                "slash), or set APPEND_SLASH=False in your Django settings."
+                % {
+                    "method": request.method,
+                    "url": request.get_host() + new_path,
+                }
+            )
+        return new_path
+
+    async def process_response(self, request, response):
+        """
+        When the status code of the response is 404, it may redirect to a path
+        with an appended slash if should_redirect_with_slash() returns True.
+        """
+        # If the given URL is "Not Found", then check if we should redirect to
+        # a path with a slash appended.
+        if response.status_code == 404 and self.should_redirect_with_slash(request):
+            return self.response_redirect_class(self.get_full_path_with_slash(request))
+
+        # Add the Content-Length header to non-streaming responses if not
+        # already set.
+        if not response.streaming and not response.has_header("Content-Length"):
+            response.headers["Content-Length"] = str(len(response.content))
+
+        return response
+
+
+class AsyncBrokenLinkEmailsMiddleware(AsyncMiddlewareMixin):
+    async def process_response(self, request, response):
+        """Send broken link emails for relevant 404 NOT FOUND responses."""
+        if response.status_code == 404 and not settings.DEBUG:
+            domain = request.get_host()
+            path = request.get_full_path()
+            referer = request.META.get("HTTP_REFERER", "")
+
+            if not self.is_ignorable_request(request, path, domain, referer):
+                ua = request.META.get("HTTP_USER_AGENT", "<none>")
+                ip = request.META.get("REMOTE_ADDR", "<none>")
+                mail_managers(
+                    "Broken %slink on %s"
+                    % (
+                        (
+                            "INTERNAL "
+                            if self.is_internal_request(domain, referer)
+                            else ""
+                        ),
+                        domain,
+                    ),
+                    "Referrer: %s\nRequested URL: %s\nUser agent: %s\n"
+                    "IP address: %s\n" % (referer, path, ua, ip),
+                    fail_silently=True,
+                )
+        return response
+
+    def is_internal_request(self, domain, referer):
+        """
+        Return True if the referring URL is the same domain as the current
+        request.
+        """
+        # Different subdomains are treated as different domains.
+        return bool(re.match("^https?://%s/" % re.escape(domain), referer))
+
+    def is_ignorable_request(self, request, uri, domain, referer):
+        """
+        Return True if the given request *shouldn't* notify the site managers
+        according to project settings or in situations outlined by the inline
+        comments.
+        """
+        # The referer is empty.
+        if not referer:
+            return True
+
+        # APPEND_SLASH is enabled and the referer is equal to the current URL
+        # without a trailing slash indicating an internal redirect.
+        if settings.APPEND_SLASH and uri.endswith("/") and referer == uri[:-1]:
+            return True
+
+        # A '?' in referer is identified as a search engine source.
+        if not self.is_internal_request(domain, referer) and "?" in referer:
+            return True
+
+        # The referer is equal to the current URL, ignoring the scheme (assumed
+        # to be a poorly implemented bot).
+        parsed_referer = urlsplit(referer)
+        if parsed_referer.netloc in ["", domain] and parsed_referer.path == uri:
+            return True
+
+        return any(pattern.search(uri) for pattern in settings.IGNORABLE_404_URLS)