Merge pull request #176 from openedx/saleem-latif/ENT-7123-algolia

ENT-7123: Added the ability to ignore unrelated jobs from being indexed on algolia.

CHANGELOG.rst

@@ -13,6 +13,10 @@ Change Log
 
 Unreleased
 
+[1.44.0] - 2023-08-09
+---------------------
+* feat: Added the ability to ignore unrelated jobs from being indexed on algolia.
+
 [1.43.4] - 2023-08-02
 ---------------------
 * fix: Added missing comma in algolia constants that was masking the b2c_opt_in attribute.

taxonomy/__init__.py

@@ -15,6 +15,6 @@
 # 2. MINOR version when you add functionality in a backwards compatible manner, and
 # 3. PATCH version when you make backwards compatible bug fixes.
 # More details can be found at https://semver.org/
-__version__ = '1.43.4'
+__version__ = '1.44.0'
 
 default_app_config = 'taxonomy.apps.TaxonomyConfig'  # pylint: disable=invalid-name

taxonomy/algolia/constants.py

@@ -24,3 +24,8 @@
 
 # This is the maximum number of objects that should be embedded inside an algolia record.
 EMBEDDED_OBJECT_LENGTH_CAP = 20
+
+# External ID of all the jobs that should not be indexed on algolia.
+JOBS_TO_IGNORE = [
+    'ET0000000000000000',  # 'Unclassified' job
+]

taxonomy/algolia/utils.py

@@ -3,16 +3,21 @@
 Utility functions related to algolia indexing.
 """
 import logging
-from datetime import datetime
 from collections import deque, namedtuple
+from datetime import datetime
 
 from django.conf import settings
-from django.db.models import Sum
+from django.db.models import Q, Sum
 
 from taxonomy.algolia.client import AlgoliaClient
-from taxonomy.algolia.constants import ALGOLIA_JOBS_INDEX_SETTINGS, JOBS_PAGE_SIZE, EMBEDDED_OBJECT_LENGTH_CAP
+from taxonomy.algolia.constants import (
+    ALGOLIA_JOBS_INDEX_SETTINGS,
+    EMBEDDED_OBJECT_LENGTH_CAP,
+    JOBS_PAGE_SIZE,
+    JOBS_TO_IGNORE,
+)
 from taxonomy.algolia.serializers import JobSerializer
-from taxonomy.models import Job, Industry, JobSkills, IndustryJobSkill
+from taxonomy.models import Industry, IndustryJobSkill, Job, JobSkills
 
 LOGGER = logging.getLogger(__name__)
 
@@ -238,7 +243,7 @@ def fetch_jobs_data():
     Returns:
         (list<dict>): A list of dicts containing job data.
     """
-    qs = Job.objects.exclude(name__isnull=True)
+    qs = Job.objects.exclude(Q(name__isnull=True) | Q(external_id__in=JOBS_TO_IGNORE))
 
     LOGGER.info('[TAXONOMY] Started combining skills and recommendations data for the jobs.')
     jobs_data = fetch_and_combine_job_details(qs)