args = parser.parse_args()
fn = args.timeline_filename
logging.info("Loading file or prefix %s" % fn)
sel_file_list = common.read_files_with_prefix(fn)
ts_db = edb.get_timeseries_db()
ats_db = edb.get_analysis_timeseries_db()
udb = edb.get_uuid_db()
psdb = edb.get_pipeline_state_db()
db_array = [ts_db, ats_db, udb, psdb]
for i, filename in enumerate(sel_file_list):
if "pipelinestate" in filename:
continue
logging.info("=" * 50)
logging.info("Deleting data from file %s" % filename)
entries = json.load(gzip.open(filename), object_hook = bju.object_hook)
# Obtain uuid and rerun information from entries
curr_uuid_list, needs_rerun = common.analyse_timeline(entries)
if len(curr_uuid_list) > 1:
logging.warning("Found %d users, %s in filename, aborting! " %
(len(curr_uuid_list), curr_uuid_list))
raise RuntimeException("Found %d users, %s in filename, expecting 1, %s" %
(len(curr_uuid_list), curr_uuid_list, common.split_user_id(filename)))
curr_uuid = curr_uuid_list[0]
if not args.info_only:
common.purge_entries_for_user(curr_uuid, args.pipeline_purge, db_array)
if "pipelinestate" in filename:
continue
logging.info("=" * 50)
logging.info("Loading data from file %s" % filename)
entries = json.load(gzip.open(filename), object_hook=bju.object_hook)
# Obtain uuid and rerun information from entries
curr_uuid_list, needs_rerun = common.analyse_timeline(entries)
if len(curr_uuid_list) > 1:
logging.warning("Found %d users, %s in filename, aborting! " %
(len(curr_uuid_list), curr_uuid_list))
raise RuntimeException(
"Found %d users, %s in filename, expecting 1, %s" %
(len(curr_uuid_list), curr_uuid_list,
common.split_user_id(filename)))
curr_uuid = curr_uuid_list[0]
all_user_list.append(curr_uuid)
all_rerun_list.append(needs_rerun)
load_ranges = get_load_ranges(entries)
if not args.info_only:
ts = esta.TimeSeries.get_time_series(curr_uuid)
for j, curr_range in enumerate(load_ranges):
if args.verbose is not None and j % args.verbose == 0:
logging.info("About to load range %s -> %s" %
(curr_range[0], curr_range[1]))
wrapped_entries = [
ecwe.Entry(e) for e in entries[curr_range[0]:curr_range[1]]
]
for entry in wrapped_entries:
ts_db = edb.get_timeseries_db()
ats_db = edb.get_analysis_timeseries_db()
udb = edb.get_uuid_db()
for i, filename in enumerate(sel_file_list):
logging.info("=" * 50)
logging.info("Deleting data from file %s" % filename)
entries = json.load(gzip.open(filename), object_hook = bju.object_hook)
# Obtain uuid and rerun information from entries
curr_uuid_list, needs_rerun = common.analyse_timeline(entries)
if len(curr_uuid_list) > 1:
logging.warning("Found %d users, %s in filename, aborting! " %
(len(curr_uuid_list), curr_uuid_list))
raise RuntimeException("Found %d users, %s in filename, expecting 1, %s" %
(len(curr_uuid_list), curr_uuid_list, common.split_user_id(filename)))
curr_uuid = curr_uuid_list[0]
if not args.info_only:
logging.info("For uuid = %s, deleting entries from the timeseries" % curr_uuid)
timeseries_del_result = ts_db.remove({"user_id": curr_uuid})
logging.info("result = %s" % timeseries_del_result)
logging.info("For uuid = %s, deleting entries from the analysis_timeseries" % curr_uuid)
analysis_timeseries_del_result = ats_db.remove({"user_id": curr_uuid})
logging.info("result = %s" % analysis_timeseries_del_result)
logging.info("For uuid %s, deleting entries from the user_db" % curr_uuid)
user_db_del_result = udb.remove({"uuid": curr_uuid})
logging.info("result = %s" % user_db_del_result)