Add profile ids filter to crawlconfigs search-values endpoint (#3000)

Backend work to help support #2978

Author: tw4l

backend/btrixcloud/crawlconfigs.py

@@ -4,7 +4,17 @@
 
 # pylint: disable=too-many-lines
 
-from typing import List, Optional, TYPE_CHECKING, cast, Dict, Tuple, Annotated, Union
+from typing import (
+    List,
+    Optional,
+    TYPE_CHECKING,
+    cast,
+    Dict,
+    Tuple,
+    Annotated,
+    Union,
+    Any,
+)
 
 import asyncio
 import json
@@ -1174,12 +1184,18 @@ async def get_crawl_config_tag_counts(self, org):
         ).to_list()
         return tags
 
-    async def get_crawl_config_search_values(self, org):
+    async def get_crawl_config_search_values(
+        self, org, profile_ids: Optional[List[UUID]] = None
+    ):
         """List unique names, first seeds, and descriptions from all workflows in org"""
-        names = await self.crawl_configs.distinct("name", {"oid": org.id})
-        descriptions = await self.crawl_configs.distinct("description", {"oid": org.id})
-        workflow_ids = await self.crawl_configs.distinct("_id", {"oid": org.id})
-        first_seeds = await self.crawl_configs.distinct("firstSeed", {"oid": org.id})
+        query: Dict[str, Any] = {"oid": org.id}
+        if profile_ids:
+            query["profileid"] = {"$in": profile_ids}
+
+        names = await self.crawl_configs.distinct("name", query)
+        descriptions = await self.crawl_configs.distinct("description", query)
+        workflow_ids = await self.crawl_configs.distinct("_id", query)
+        first_seeds = await self.crawl_configs.distinct("firstSeed", query)
 
         # Remove empty strings
         names = [name for name in names if name]
@@ -1700,8 +1716,11 @@ async def get_crawl_config_tag_counts(org: Organization = Depends(org_viewer_dep
     @router.get("/search-values", response_model=CrawlConfigSearchValues)
     async def get_crawl_config_search_values(
         org: Organization = Depends(org_viewer_dep),
+        profile_ids: Annotated[
+            Optional[List[UUID]], Query(alias="profileIds", title="Profile IDs")
+        ] = None,
     ):
-        return await ops.get_crawl_config_search_values(org)
+        return await ops.get_crawl_config_search_values(org, profile_ids)
 
     @router.get("/crawler-channels", response_model=CrawlerChannels)
     async def get_crawler_channels(

backend/test/test_crawl_config_search_values.py

@@ -124,3 +124,17 @@ def test_get_search_values_3(admin_auth_headers, default_org_id):
     assert sorted(data["firstSeeds"]) == sorted(
         ["https://old.webrecorder.net/", FIRST_SEED_1_URL, FIRST_SEED_2_URL]
     )
+
+
+def test_get_search_values_filter_profiles(
+    admin_auth_headers, default_org_id, profile_id, profile_config_id
+):
+    """Test profile_ids filter"""
+    r = requests.get(
+        f"{API_PREFIX}/orgs/{default_org_id}/crawlconfigs/search-values?profileIds={profile_id}",
+        headers=admin_auth_headers,
+    )
+    data = r.json()
+    assert data["names"] == ["Profile Test Crawl"]
+    assert data["descriptions"] == ["Crawl using browser profile"]
+    assert data["firstSeeds"] == ["https://old.webrecorder.net/"]

backend/test/test_filter_sort_results.py

@@ -362,9 +362,9 @@ def test_sort_crawl_configs(
         headers=crawler_auth_headers,
     )
     data = r.json()
-    assert data["total"] == 16
+    assert data["total"] == 17
     items = data["items"]
-    assert len(items) == 16
+    assert len(items) == 17
 
     last_created = None
     for config in items: