7eac0fdf95
- optimization: convert all uses of 'async for' to use iterator directly instead of converting to list to avoid unbounded size lists - additional cursor.to_list() to async for conversions for stats computation, simply crawlconfigs stats computation --------- Co-authored-by: Tessa Walsh <tessa@bitarchivist.net>
33 lines
1004 B
Python
33 lines
1004 B
Python
"""
|
|
Migration 0008 - Precomputing crawl file stats
|
|
"""
|
|
from btrixcloud.crawls import recompute_crawl_file_count_and_size
|
|
from btrixcloud.migrations import BaseMigration
|
|
|
|
|
|
MIGRATION_VERSION = "0008"
|
|
|
|
|
|
class Migration(BaseMigration):
|
|
"""Migration class."""
|
|
|
|
def __init__(self, mdb, migration_version=MIGRATION_VERSION):
|
|
super().__init__(mdb, migration_version)
|
|
|
|
async def migrate_up(self):
|
|
"""Perform migration up.
|
|
|
|
Add data on crawl file count and size to database that was previously
|
|
dynamically generated in the API endpoints.
|
|
"""
|
|
# pylint: disable=duplicate-code
|
|
crawls = self.mdb["crawls"]
|
|
|
|
async for crawl in crawls.find({}):
|
|
crawl_id = crawl["_id"]
|
|
try:
|
|
await recompute_crawl_file_count_and_size(crawls, crawl_id)
|
|
# pylint: disable=broad-exception-caught
|
|
except Exception as err:
|
|
print(f"Unable to update crawl {crawl_id}: {err}", flush=True)
|