refine

msr.py

@@ -50,7 +50,7 @@ UPLOAD_DELAY_SECONDS = 5
 UPLOAD_MAX_BACKOFF = 3600
 
 # Scheduler configuration
-SCHEDULE_ENABLED = False
+SCHEDULE_ENABLED = True
 SCHEDULE_DAY_OF_WEEK = 'wed'  # Wednesday
 SCHEDULE_HOUR = 0
 SCHEDULE_MINUTE = 0
@@ -405,16 +405,16 @@ def fetch_all_pr_metadata_streaming(conn, identifiers, start_date, end_date):
                     '/pull/',
                     CAST(payload.pull_request.number AS VARCHAR)
                 ) as url,
-                struct_extract(payload.pull_request.user, 'login') as pr_author,
+                payload.pull_request.user.login as pr_author, -- CHANGED
                 created_at as event_time,
                 payload.action as event_action,
-                struct_extract(payload.pull_request, 'merged_at') as merged_at
+                payload.pull_request.merged_at as merged_at -- CHANGED
             FROM read_json({file_patterns_sql}, union_by_name=true, filename=true, compression='gzip', format='newline_delimited', ignore_errors=true, maximum_object_size=2147483648)
             WHERE
                 type = 'PullRequestEvent'
                 AND payload.action IN ('opened', 'closed')
                 AND payload.pull_request.number IS NOT NULL
-                AND struct_extract(payload.pull_request.user, 'login') IN ({identifier_list})
+                AND payload.pull_request.user.login IN ({identifier_list}) -- CHANGED
         ),
         pr_timeline AS (
             SELECT