record queries smartly

Author: dojutsu-user

readthedocs/search/api.py

@@ -1,6 +1,7 @@
 import itertools
 import logging
 
+from django.utils import timezone
 from rest_framework import generics, serializers
 from rest_framework.exceptions import ValidationError
 from rest_framework.pagination import PageNumberPagination
@@ -160,15 +161,19 @@ def list(self, request, *args, **kwargs):
 
         project_slug = self.request.query_params.get('project', None)
         version_slug = self.request.query_params.get('version', None)
-        query = self.request.query_params.get('q', '')
         total_results = response.data.get('count', 0)
+        time = timezone.now()
+
+        query = self.request.query_params.get('q', '')
+        query = query.lower()
 
         # record the search query with a celery task
         tasks.record_search_query.delay(
             project_slug,
             version_slug,
             query,
             total_results,
+            time,
         )
 
         return response

readthedocs/search/tasks.py

@@ -142,37 +142,73 @@ def delete_old_search_queries_from_db():
 
 
 @app.task(queue='web')
-def record_search_query(project_slug, version_slug, query, total_results):
-    """Record search query in database."""
-    if not project_slug or not version_slug or not query or not total_results:
+def record_search_query(project_slug, version_slug, query, total_results, time):
+    """Record/update search query in database."""
+    if not project_slug or not version_slug or not query:
         log.debug(
             'Not recording the search query. Passed arguments: '
-            'project_slug: %s, version_slug: %s, query: %s, total_results: %s' % (
-                project_slug, version_slug, query, total_results
+            'project_slug: %s, version_slug: %s, query: %s, total_results: %s, time: %s' % (
+                project_slug, version_slug, query, total_results, time
             )
         )
         return
 
-    project_qs = Project.objects.filter(slug=project_slug)
-
-    if not project_qs.exists():
-        log.debug(
-            'Not recording the search query because project does not exist. '
-            'project_slug: %s' % (
-                project_slug
-            )
-        )
+    before_10_sec = time - timezone.timedelta(seconds=10)
+    partial_query_qs = SearchQuery.objects.filter(
+        project__slug=project_slug,
+        version__slug=version_slug,
+        query__startswith=query,
+        created__gte=before_10_sec,
+    ).order_by('-created')
+
+    # if partial query exists,
+    # just update it instead of creating new SearchQuery object.
+    if partial_query_qs.exists():
+        obj = partial_query_qs.first()
+        obj.created = time
+        obj.query = query
+        obj.save()
         return
-
-    project = project_qs.first()
-    version_qs = Version.objects.filter(project=project, slug=version_slug)
-
-    if not version_qs.exists():
-        return
-
-    version = version_qs.first()
-    SearchQuery.objects.create(
-        project=project,
-        version=version,
-        query=query,
-    )
+    else:
+        # don't record query with zero results.
+        if not total_results:
+            log.debug(
+                'Not recording search query because of zero results. Passed arguments: '
+                'project_slug: %s, version_slug: %s, query: %s, total_results: %s, time: %s' % (
+                    project_slug, version_slug, query, total_results, time
+                )
+            )
+            return
+        else:
+            project_qs = Project.objects.filter(slug=project_slug)
+            if not project_qs.exists():
+                log.debug(
+                    'Not recording the search query because project does not exist. '
+                    'project_slug: %s' % (
+                        project_slug
+                    )
+                )
+                return
+
+            project = project_qs.first()
+            version_qs = Version.objects.filter(project=project, slug=version_slug)
+
+            if not version_qs.exists():
+                log.debug(
+                    'Not recording the search query because version does not exist. '
+                    'project_slug: %s, version_slug: %s' % (
+                        project_slug, version_slug
+                    )
+                )
+                return
+
+            version = version_qs.first()
+
+            # make a new SearchQuery object.
+            obj = SearchQuery.objects.create(
+                project=project,
+                version=version,
+                query=query,
+            )
+            obj.created = time
+            obj.save()