Add shortcut for HEAD requests on slower views

We sometimes see some web bots and crawlers make HEAD requests to verify
existence of certain pages in the application. However, they are less
than kind as 20-50 requests might arrive at the same time, and package
search and details pages are some of the slowest rendering pages we have
due to the Django template engine.

Rather than waste time generating the content only to throw it away,
response as soon as we can with either a 404 or 200 response as
appropriate, omitting the 'Content-Length' header completely, which
seems to be acceptable by the HTTP spec.

Signed-off-by: Dan McGee <dan@archlinux.org>

3 files changed, 15 insertions, 1 deletions

diff --git a/main/utils.py b/main/utils.py
index cdd4ff71..8394e5cd 100644
--- a/main/utils.py
+++ b/main/utils.py
@@ -8,6 +8,7 @@ import hashlib
 
 from django.core.cache import cache
 from django.db import connections, router
+from django.http import HttpResponse
 from django.utils.timezone import now
 from django.template.defaultfilters import slugify
 
@@ -55,6 +56,14 @@ def clear_cache_function(func, args, kwargs):
     cache.delete(key)
 
 
+def empty_response():
+    empty = HttpResponse('')
+    # designating response as 'streaming' forces ConditionalGetMiddleware to
+    # not add a 'Content-Length: 0' header
+    empty.streaming = True
+    return empty
+
+
 def format_http_headers(request):
     headers = sorted((k, v) for k, v in request.META.items()
             if k.startswith('HTTP_'))
diff --git a/packages/views/display.py b/packages/views/display.py
index 50783835..87424483 100644
--- a/packages/views/display.py
+++ b/packages/views/display.py
@@ -7,6 +7,7 @@ from django.shortcuts import get_object_or_404, redirect, render
 from django.utils.timezone import now
 
 from main.models import Package, PackageFile, Arch, Repo
+from main.utils import empty_response
 from mirrors.utils import get_mirror_url_for_download
 from ..models import Update
 from ..utils import get_group_info, PackageJSONEncoder
@@ -126,6 +127,8 @@ def details(request, name='', repo='', arch=''):
             pkg = Package.objects.select_related(
                     'arch', 'repo', 'packager').get(pkgname=name,
                     repo=repo_obj, arch=arch_obj)
+            if request.method == 'HEAD':
+                return empty_response()
             return render(request, 'packages/details.html', {'pkg': pkg})
         except Package.DoesNotExist:
             # attempt a variety of fallback options before 404ing
diff --git a/packages/views/search.py b/packages/views/search.py
index 0362602e..b3778172 100644
--- a/packages/views/search.py
+++ b/packages/views/search.py
@@ -7,7 +7,7 @@ from django.http import HttpResponse
 from django.views.generic import ListView
 
 from main.models import Package, Arch, Repo
-from main.utils import make_choice
+from main.utils import empty_response, make_choice
 from ..models import PackageRelation
 from ..utils import attach_maintainers, PackageJSONEncoder
 
@@ -99,6 +99,8 @@ class SearchListView(ListView):
     allowed_sort = list(sort_fields) + ["-" + s for s in sort_fields]
 
     def get(self, request, *args, **kwargs):
+        if request.method == 'HEAD':
+            return empty_response()
         self.form = PackageSearchForm(data=request.GET,
                 show_staging=self.request.user.is_authenticated())
         return super(SearchListView, self).get(request, *args, **kwargs)