9c7a312a4c
* Track collections in Crawl rather than crawls in Collection * Add delete collection API endpoint and tests * Precompute collection crawlCount, pageCount, and tags and add them to GET collection responses * Add modified field to Collection * Update collection replay.json method * Make add and remove crawls accept list of crawl ids * Auto-add new workflow crawls to collections when they successfully complete via CrawlConfig.autoAddCollections field * Move long-running post-crawl operator tasks into asyncio task * Make CrawlConfig.autoAddCollections updatable via /update API endpoint
38 lines
1.2 KiB
Python
38 lines
1.2 KiB
Python
"""
|
|
Migration 0006 - Precomputing workflow crawl stats
|
|
"""
|
|
from btrixcloud.crawlconfigs import update_config_crawl_stats
|
|
from btrixcloud.migrations import BaseMigration
|
|
|
|
|
|
MIGRATION_VERSION = "0006"
|
|
|
|
|
|
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 workflow crawl statistics that was previously dynamically
|
|
computed when needed to the database.
|
|
"""
|
|
# pylint: disable=duplicate-code
|
|
crawl_configs = self.mdb["crawl_configs"]
|
|
crawls = self.mdb["crawls"]
|
|
|
|
configs = [res async for res in crawl_configs.find({"inactive": {"$ne": True}})]
|
|
if not configs:
|
|
return
|
|
|
|
for config in configs:
|
|
config_id = config["_id"]
|
|
try:
|
|
await update_config_crawl_stats(crawl_configs, crawls, config_id)
|
|
# pylint: disable=broad-exception-caught
|
|
except Exception as err:
|
|
print(f"Unable to update workflow {config_id}: {err}", flush=True)
|