Merge pull request #123 from fpdcc/patch/search-rankings

Improve search scores for direct matches

Author: xmedr

.github/workflows/main.yml

@@ -19,7 +19,7 @@ jobs:
         run: |
             mkdir -p data && touch data/requirements.txt
             cp .env.example .env
-            docker-compose -f docker-compose.yml -f tests/docker-compose.yml run --rm app
+            docker compose -f docker-compose.yml -f tests/docker-compose.yml run --rm app
   deploy:
     if:
       contains('

README.md

@@ -27,13 +27,13 @@ cp docsearch/local_settings.example.py docsearch/local_settings.dev.py
 Next, build containers:
 
 ```
-docker-compose build
+docker compose build
 ```
 
 Run the app:
 
 ```
-docker-compose up
+docker compose up
 ```
 
 The app will be available at http://localhost:8000. The database will be exposed
@@ -42,7 +42,7 @@ on port 32001.
 Create a superuser to view the application:
 
 ```
-docker-compose run --rm app ./manage.py createsuperuser
+docker compose run --rm app ./manage.py createsuperuser
 ```
 
 ### Loading initial data
@@ -67,27 +67,27 @@ cp -R ./document-search-data/ ./document-search/data/
 Then, load initial data using GNU Make:
 
 ```
-docker-compose -f docker-compose.yml -f data/docker-compose.yml run --rm app make all
+docker compose -f docker-compose.yml -f data/docker-compose.yml run --rm app make all
 ```
 
 To create the search index, start by bringing up Solr in one shell:
 
 ```
-docker-compose up solr
+docker compose up solr
 ```
 
 Then, in another shell, run the `rebuild_index` command:
 
 ```
-docker-compose run --rm app ./manage.py rebuild_index
+docker compose run --rm app ./manage.py rebuild_index
 ```
 
 ### Running tests
 
 Run tests with Docker Compose:
 
 ```
-docker-compose -f docker-compose.yml -f tests/docker-compose.yml run --rm app
+docker compose -f docker-compose.yml -f tests/docker-compose.yml run --rm app
 ```
 
 ## Deployment

docsearch/views/base.py

@@ -146,6 +146,26 @@ def form_valid(self, form):
 
     def get_queryset(self):
         sqs = super().get_queryset().models(self.model)
+
+        q = self.request.GET.get('q')
+        if q:
+            """
+            Boost results that contain direct matches of each term in the query,
+            regardless of whether any terms are enclosed in double quotes.
+            Terms in double quotes are exact match terms, so give them a bit of
+            an extra boost, and boost them as is - whitespace and all.
+            """
+            exact_match_re = re.compile(r'"(?P<phrase>.*?)"')
+            tokens = exact_match_re.split(q)
+            exacts = exact_match_re.findall(q)
+
+            for t in tokens:
+                if t and not t.strip().startswith("-"):
+                    if t in exacts:
+                        sqs = sqs.boost(t, 1)
+                    else:
+                        sqs = sqs.boost(t, .5)
+
         for facet_field in self.facet_fields:
             # Sort facet options alphabetically, not by hit count
             sqs = sqs.facet(facet_field, sort='index', limit=1000)

scripts/after_install.sh

@@ -78,7 +78,7 @@ $VENV_DIR/bin/python $PROJECT_DIR/scripts/render_configs.py $DEPLOYMENT_ID $DEPL
 echo "DEPLOYMENT_ID='$DEPLOYMENT_ID'" > $PROJECT_DIR/docsearch/deployment.py
 
 # Make sure Solr is running
-(docker ps | grep document-search-solr) || (cd $PROJECT_DIR && docker-compose up -d solr)
+(docker ps | grep document-search-solr) || (cd $PROJECT_DIR && docker compose up -d solr)
 
 
 # Add the virtualenv directory name to python command in the script