Copy tags from crawlconfig to crawl (#467), fixes #466

- add tags to crawl object
- ensure tags are copied from crawlconfig to crawl when crawl is created (both manually and scheduled)
- tests: add test to ensure tags added to crawl, remove redundant wait replaced with fixtures

backend/btrixcloud/crawl_job.py

@@ -47,6 +47,7 @@ class CrawlJob(ABC):
         self.userid = uuid.UUID(os.environ["USER_ID"])
 
         self.is_manual = os.environ.get("RUN_MANUAL") == "1"
+        self.tags = os.environ.get("TAGS", "").split(",")
 
         self.scale = int(os.environ.get("INITIAL_SCALE") or 0)
 
@@ -360,6 +361,7 @@ class CrawlJob(ABC):
             manual=self.is_manual,
             scale=scale,
             started=self.started,
+            tags=self.tags,
             # colls=json.loads(job.metadata.annotations.get("btrix.colls", [])),
         )
 

backend/btrixcloud/crawlmanager.py

@@ -183,6 +183,7 @@ class BaseCrawlManager(ABC):
             "schedule": schedule,
             "env": os.environ,
             "mongo_db_url": resolve_db_url(),
+            "tags": ",".join(crawlconfig.tags),
         }
 
         return self.templates.env.get_template("crawl_job.yaml").render(params)

backend/btrixcloud/crawls.py

@@ -84,6 +84,7 @@ class Crawl(BaseMongoModel):
     files: Optional[List[CrawlFile]] = []
 
     colls: Optional[List[str]] = []
+    tags: Optional[List[str]] = []
 
 
 # ============================================================================
@@ -121,6 +122,7 @@ class ListCrawlOut(BaseMongoModel):
     fileCount: int = 0
 
     colls: Optional[List[str]] = []
+    tags: Optional[List[str]] = []
 
 
 # ============================================================================
@@ -358,6 +360,7 @@ class CrawlOps:
             scale=crawlconfig.scale,
             manual=True,
             started=ts_now(),
+            tags=crawlconfig.tags,
         )
 
         try:

backend/btrixcloud/k8s/templates/crawl_job.yaml

@@ -70,6 +70,9 @@ spec:
             - name: CRAWL_CONFIG_ID
               value: "{{ cid }}"
 
+            - name: TAGS
+              value: "{{ tags }}"
+
             - name: STORE_PATH
               valueFrom:
                 configMapKeyRef:

backend/test/conftest.py

@@ -58,7 +58,11 @@ def admin_crawl_id(admin_auth_headers, admin_aid):
     crawl_data = {
         "runNow": True,
         "name": "Admin Test Crawl",
-        "config": {"seeds": ["https://webrecorder.net/"], "limit": 1},
+        "tags": ["wr-test-1", "wr-test-2"],
+        "config": {
+            "seeds": ["https://webrecorder.net/"],
+            "limit": 1,
+        },
     }
     r = requests.post(
         f"{API_PREFIX}/archives/{admin_aid}/crawlconfigs/",

backend/test/test_org.py

@@ -14,7 +14,7 @@ def test_ensure_only_one_default_org(admin_auth_headers):
     default_org_name = default_orgs[0]["name"]
     orgs_with_same_name = [org for org in orgs if org["name"] == default_org_name]
     assert len(orgs_with_same_name) == 1
-    
+
 
 def test_rename_org(admin_auth_headers, admin_aid):
     UPDATED_NAME = "updated org name"
@@ -35,6 +35,7 @@ def test_rename_org(admin_auth_headers, admin_aid):
     data = r.json()
     assert data["name"] == UPDATED_NAME
 
+
 def test_create_org(admin_auth_headers):
     NEW_ORG_NAME = "New Org"
     r = requests.post(

backend/test/test_run_crawl.py

@@ -46,28 +46,18 @@ def test_create_new_config(admin_auth_headers, admin_aid):
 
 
 def test_wait_for_complete(admin_auth_headers, admin_aid, admin_crawl_id):
-    print("")
-    print("---- Running Crawl ----")
-
-    while True:
-        r = requests.get(
-            f"{API_PREFIX}/archives/{admin_aid}/crawls/{admin_crawl_id}/replay.json",
-            headers=admin_auth_headers,
-        )
-        data = r.json()
-        assert (
-            data["state"] == "starting"
-            or data["state"] == "running"
-            or data["state"] == "complete"
-        ), data["state"]
-        if data["state"] == "complete":
-            break
-
-        time.sleep(5)
+    r = requests.get(
+        f"{API_PREFIX}/archives/{admin_aid}/crawls/{admin_crawl_id}/replay.json",
+        headers=admin_auth_headers,
+    )
+    data = r.json()
+    assert data["state"] == "complete"
 
     assert len(data["resources"]) == 1
     assert data["resources"][0]["path"]
 
+    assert data["tags"] == ["wr-test-1", "wr-test-2"]
+
     global wacz_path
     global wacz_size
     global wacz_hash