browsertrix/backend/btrixcloud/migrations/migration_0024_crawlerchannel.py
Tessa Walsh 032859f361
Support multiple crawler versions (#1420)
Fixes #1385 

## Changes
Supports multiple crawler 'channels' which can be configured to
different browsertrix-crawler versions
- Replaces `crawler_image` in helm chart with `crawler_channels` array
similar to how storages are handled
- The `default` crawler channel must always be provided and specifies
the default crawler image
- Adds backend `/orgs/{oid}/crawlconfigs/crawler-channels` API endpoint
to fetch information about available crawler versions (name, image, and
label) and test
- Adds crawler channel select to workflow creation/edit screens and
profile creation dialog, and updates related API endpoints and
configmaps accordingly. The select dropdown is shown only if more than
one channel is configured.
- Adds `crawlerChannel` to workflow and crawl details.
- Add `image` to crawler image, used to display actual image used as
part of the crawl.
- Modifies `crawler_crawl_id` backend test fixture to use `test` crawler
version to ensure crawler versions other than latest work
- Adds migration to add `crawlerChannel` set to `default` to existing
workflow and profile objects and workflow configmaps

---------
Co-authored-by: Ilya Kreymer <ikreymer@gmail.com>
Co-authored-by: Henry Wilkinson <henry@wilkinson.graphics>
2024-01-16 15:32:12 -08:00

72 lines
2.5 KiB
Python

"""
Migration 0024 -- crawlerChannel
"""
from btrixcloud.crawlmanager import CrawlManager
from btrixcloud.migrations import BaseMigration
from btrixcloud.models import CrawlConfig, UpdateCrawlConfig
MIGRATION_VERSION = "0024"
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 crawlerChannel to existing workflows and profiles, and update configmaps
"""
# pylint: disable=duplicate-code
mdb_crawl_configs = self.mdb["crawl_configs"]
mdb_profiles = self.mdb["profiles"]
async for config in mdb_crawl_configs.find(
{"crawlerChannel": {"$in": ["", None]}}
):
config_id = config["_id"]
try:
await mdb_crawl_configs.find_one_and_update(
{"_id": config_id},
{"$set": {"crawlerChannel": "default"}},
)
# pylint: disable=broad-except
except Exception as err:
print(
f"Error adding crawlerChannel 'default' to workflow {config_id}: {err}",
flush=True,
)
async for profile in mdb_profiles.find({"crawlerChannel": {"$in": ["", None]}}):
profile_id = profile["_id"]
try:
await mdb_profiles.find_one_and_update(
{"_id": profile_id},
{"$set": {"crawlerChannel": "default"}},
)
# pylint: disable=broad-except
except Exception as err:
print(
f"Error adding crawlerChannel 'default' to profile {profile_id}: {err}",
flush=True,
)
# Update configmaps
crawl_manager = CrawlManager()
match_query = {"crawlerChannel": {"$in": ["", None]}}
async for config_dict in mdb_crawl_configs.find(match_query):
config = CrawlConfig.from_dict(config_dict)
try:
await crawl_manager.update_crawl_config(
config, UpdateCrawlConfig(crawlerChannel="default")
)
# pylint: disable=broad-except
except Exception as exc:
print(
"Skip configmap migration due to error, likely missing config",
exc,
)