21379: Follow rules for federated list queries.

[arvados.git] / tools / user-activity / arvados_user_activity / main.py

diff --git a/tools/user-activity/arvados_user_activity/main.py b/tools/user-activity/arvados_user_activity/main.py
index 26a4f28067663898ac660e647d91ba5fa71dbfb3..66d03b20410e009104e75cb2f1086e2c48adbf59 100755 (executable)
--- a/tools/user-activity/arvados_user_activity/main.py
+++ b/tools/user-activity/arvados_user_activity/main.py
@@ -95,20 +95,22 @@ def getuserinfocsv(arv, uuid):
 collectionNameCache = {}
 def getCollectionName(arv, uuid, pdh):
     lookupField = uuid
-    filters = [["uuid","=",uuid]]
+    filters = [["uuid", "=", uuid]]
+    order = None
     cached = uuid in collectionNameCache
     # look up by uuid if it is available, fall back to look up by pdh
-    if len(uuid) != 27:
+    if uuid is None or len(uuid) != 27:
         # Look up by pdh. Note that this can be misleading; the download could
         # have happened from a collection with the same pdh but different name.
         # We arbitrarily pick the oldest collection with the pdh to lookup the
         # name, if the uuid for the request is not known.
         lookupField = pdh
-        filters = [["portable_data_hash","=",pdh]]
+        filters = [["portable_data_hash", "=", pdh]]
+        order = "created_at"
         cached = pdh in collectionNameCache
 
     if not cached:
-        u = arv.collections().list(filters=filters,order="created_at",limit=1).execute().get("items")
+        u = arv.collections().list(filters=filters, order=order, limit=1, count="none").execute().get("items")
         if len(u) < 1:
             return "(deleted)"
         collectionNameCache[lookupField] = u[0]["name"]
@@ -169,17 +171,12 @@ def main(arguments=None):
             users[owner].append([loguuid, event_at,"Updated project %s" % (getname(e["properties"]["new_attributes"]))])
 
         elif e["event_type"] in ("create", "update") and e["object_uuid"][6:11] == "gj3su":
-            since_last = None
-            if len(users[owner]) > 0 and users[owner][-1][-1].endswith("activity"):
-                sp = users[owner][-1][-1].split(" ")
-                start = users[owner][-1][1]
-                since_last = ciso8601.parse_datetime(event_at) - ciso8601.parse_datetime(sp[1]+" "+sp[2])
-                span = ciso8601.parse_datetime(event_at) - ciso8601.parse_datetime(start)
-
-            if since_last is not None and since_last < datetime.timedelta(minutes=61):
-                users[owner][-1] = [loguuid, start,"to %s (%02d:%02d) Account activity" % (event_at, span.days*24 + int(span.seconds/3600), int((span.seconds % 3600)/60))]
-            else:
-                users[owner].append([loguuid, event_at,"to %s (0:00) Account activity" % (event_at)])
+            # Don't log token activity, it is too noisy (bug #19179)
+            pass
+
+        # We want to report when a user goes through the login
+        # process, but controller doesn't do that yet, so revisit
+        # this when #19388 is done.
 
         elif e["event_type"] == "create" and e["object_uuid"][6:11] == "o0j2j":
             if e["properties"]["new_attributes"]["link_class"] == "tag":
@@ -213,20 +210,19 @@ def main(arguments=None):
                 users[owner].append([loguuid, event_at, "Deleted collection %s" % (getname(e["properties"]["old_attributes"]))])
 
         elif e["event_type"] == "file_download":
-                users.setdefault(e["object_uuid"], [])
-                users[e["object_uuid"]].append([loguuid, event_at, "Downloaded file \"%s\" from \"%s\" (%s) (%s)" % (
-                                                                                       e["properties"].get("collection_file_path") or e["properties"].get("reqPath"),
-                                                                                       getCollectionName(arv, e["properties"].get("collection_uuid"), e["properties"].get("portable_data_hash")),
-                                                                                       e["properties"].get("collection_uuid"),
-                                                                                       e["properties"].get("portable_data_hash"))])
-
+            users.setdefault(e["object_uuid"], [])
+            users[e["object_uuid"]].append([loguuid, event_at, "Downloaded file \"%s\" from \"%s\" (%s) (%s)" % (
+                e["properties"].get("collection_file_path") or e["properties"].get("reqPath"),
+                getCollectionName(arv, e["properties"].get("collection_uuid"), e["properties"].get("portable_data_hash")),
+                e["properties"].get("collection_uuid"),
+                e["properties"].get("portable_data_hash"))])
 
         elif e["event_type"] == "file_upload":
-                users.setdefault(e["object_uuid"], [])
-                users[e["object_uuid"]].append([loguuid, event_at, "Uploaded file \"%s\" to \"%s\" (%s)" % (
-                                                                                    e["properties"].get("collection_file_path") or e["properties"].get("reqPath"),
-                                                                                    getCollectionName(arv, e["properties"].get("collection_uuid"), e["properties"].get("portable_data_hash")),
-                                                                                    e["properties"].get("collection_uuid"))])
+            users.setdefault(e["object_uuid"], [])
+            users[e["object_uuid"]].append([loguuid, event_at, "Uploaded file \"%s\" to \"%s\" (%s)" % (
+                e["properties"].get("collection_file_path") or e["properties"].get("reqPath"),
+                getCollectionName(arv, e["properties"].get("collection_uuid"), e["properties"].get("portable_data_hash")),
+                e["properties"].get("collection_uuid"))])
 
         else:
             users[owner].append([loguuid, event_at, "%s %s %s" % (e["event_type"], e["object_kind"], e["object_uuid"])])
@@ -235,8 +231,14 @@ def main(arguments=None):
         csvwriter = csv.writer(sys.stdout, dialect='unix')
 
     for k,v in users.items():
+        # Skip system user
         if k is None or k.endswith("-tpzed-000000000000000"):
             continue
+
+        # Skip users with no activity to report
+        if not v:
+            continue
+
         if not args.csv:
           print(getuserinfo(arv, k))
           for ev in v: