bring issue-2098 up to date with master

ISSUE_TEMPLATES/kg2rollout.md

@@ -192,6 +192,7 @@ Before rolling out, we need to pre-upload the new databases (referenced in `conf
     - [ ] verify once more that ARAX is still working properly, even with the self-hosted new-KG2c-version PloverDB service turned off
 - [ ] upload the new `kg2c_lite_2.X.Y.json.gz` file to the [translator-lfs-artifacts](https://github.com/ncats/translator-lfs-artifacts/tree/main/files) repo
 - [ ] upload the new `kg2_nodes_not_in_sri_nn.tsv` file to the [translator-lfs-artifacts](https://github.com/ncats/translator-lfs-artifacts/tree/main/files) repo
+- [ ] upload KG2c TSV tarball to the [Translator Knowledge Graph Exchange (KGE)](https://archive.translator.ncats.io/home).
 
 #### 7. Roll-out to ITRB TEST 
 - [ ] In GitHub, for the RTXteam/RTX project, merge `master` to `itrb-test`. Record this issue number in the merge message.

code/ARAX/ARAXQuery/ARAX_query_tracker.py

@@ -10,7 +10,7 @@ def eprint(*args, **kwargs): print(*args, file=sys.stderr, **kwargs)
 import json
 import psutil
 
-from datetime import datetime
+from datetime import datetime, timezone
 import sqlalchemy
 from sqlalchemy import create_engine
 from sqlalchemy.ext.declarative import declarative_base
@@ -687,6 +687,7 @@ def main():
     argparser.add_argument('--show_ongoing', action='count', help='Show all ongoing queries')
     argparser.add_argument('--reset_job', action='count', help='Reset the specified job_id(s)')
     argparser.add_argument('--job_ids', type=str, help='Job IDs to show (comma separated list)')
+    argparser.add_argument('--prune_jobs', action='count', help='Simply prune very stale jobs from the active query table')
     params = argparser.parse_args()
 
     #### Set verbose
@@ -695,18 +696,30 @@ def main():
 
     query_tracker = ARAXQueryTracker()
 
+    #### If pruning, then also show
+    if params.prune_jobs:
+        params.show_ongoing = True
+        params.reset_job = True
+    prune_job_ids = []
+
     #### Check ongoing queries
     if params.show_ongoing:
         entries = query_tracker.get_entries(ongoing_queries=True)
         for entry in entries:
             #print(entry.__dict__)
-            print(f"{entry.query_id}\t{entry.pid}\t{entry.start_datetime}\t{entry.instance_name}\t{entry.hostname}\t{entry.status}\t{entry.elapsed}\t{entry.origin}\t{entry.message_id}\t{entry.message_code}\t{entry.code_description}")
-        return
+            now = datetime.now(timezone.utc)
+            now = now.replace(tzinfo=None)
+            elapsed = now - datetime.fromisoformat(entry.start_datetime)
+            elapsed = elapsed.seconds + elapsed.days * 24 * 60 * 60
+            print(f"{entry.query_id}\t{entry.start_datetime}\t{elapsed}\t{entry.instance_name}\t{entry.hostname}\t{entry.status}\t{entry.origin}\t{entry.pid}\t{entry.message_id}\t{entry.message_code}\t{entry.code_description}")
+            if params.prune_jobs and elapsed > 70000: 
+                prune_job_ids.append(entry.query_id)
 
     #### Extract job_ids
     job_ids = []
     if params.job_ids:
         job_ids = params.job_ids.split(',')
+    job_ids.extend(prune_job_ids)
 
     #### If the request is to reset jobs, do it
     if params.reset_job and len(job_ids) > 0:

code/ARAX/ARAXQuery/Expand/kg2_querier.py

@@ -5,8 +5,8 @@
 import time
 from collections import defaultdict
 from typing import Dict, Tuple, Union, Set
-
 import requests
+import traceback
 
 sys.path.append(os.path.dirname(os.path.abspath(__file__)))
 import expand_utilities as eu
@@ -183,13 +183,21 @@ def _answer_query_using_plover(qg: QueryGraph, log: ARAXResponse) -> Tuple[Dict[
                     qnode["allow_subclasses"] = True
         # Then send the actual query
         log.debug(f"Sending query to {rtxc.plover_url}")
-        response = requests.post(f"{rtxc.plover_url}/query", json=dict_qg, timeout=60,
-                                 headers={'accept': 'application/json'})
+        try:
+            response = requests.post(f"{rtxc.plover_url}/query",
+                                     json=dict_qg,
+                                     timeout=60,
+                                     headers={'accept': 'application/json'})
+        except Exception as e:
+            log.error(f"Error querying PloverDB: {e} "
+                      f"TRACE {traceback.format_exc()}")
+            raise e
         if response.status_code == 200:
-            log.debug(f"Got response back from Plover")
+            log.debug(f"Plover returned status code {response.status_code}")
             return response.json(), response.status_code
         else:
-            log.warning(f"Plover returned a status code of {response.status_code}. Response was: {response.text}")
+            log.warning(f"Plover returned status code {response.status_code}."
+                        f" Response was: {response.text}")
             return dict(), response.status_code
 
     def _load_plover_answer_into_object_model(self, plover_answer: Dict[str, Dict[str, Union[set, dict]]],