f7ba712646
Fixes #2673 Changes in this PR: - Adds a new `file_uploads.py` module and corresponding `/files` API prefix with methods/endpoints for uploading, GETing, and deleting seed files (can be extended to other types of files moving forward) - Seed files are supported via `CrawlConfig.config.seedFileId` on POST and PATCH endpoints. This seedFileId is replaced by a presigned url when passed to the crawler by the operator - Seed files are read when first uploaded to calculate `firstSeed` and `seedCount` and store them in the database, and this is copied into the workflow and crawl documents when they are created. - Logic is added to store `firstSeed` and `seedCount` for other workflows as well, and a migration added to backfill data, to maintain consistency and fix some of the pymongo aggregations that previously assumed all workflows would have at least one `Seed` object in `CrawlConfig.seeds` - Seed file and thumbnail storage stats are added to org stats - Seed file and thumbnail uploads first check that the org's storage quota has not been exceeded and return a 400 if so - A cron background job (run weekly each Sunday at midnight by default, but configurable) is added to look for seed files at least x minutes old (1440 minutes, or 1 day, by default, but configurable) that are not in use in any workflows, and to delete them when they are found. The backend pods will ensure this k8s batch job exists when starting up and create it if it does not already exist. A database entry for each run of the job is created in the operator on job completion so that it'll appear in the `/jobs` API endpoints, but retrying of this type of regularly scheduled background job is not supported as we don't want to accidentally create multiple competing scheduled jobs. - Adds a `min_seed_file_crawler_image` value to the Helm chart that is checked before creating a crawl from a workflow if set. If a workflow cannot be run, return the detail of the exception in `CrawlConfigAddedResponse.errorDetail` so that we can display the reason in the frontend - Add SeedFile model from base UserFile (former ImageFIle), ensure all APIs returning uploaded files return an absolute pre-signed URL (either with external origin or internal service origin) --------- Co-authored-by: Ilya Kreymer <ikreymer@gmail.com>
96 lines
3.1 KiB
Python
96 lines
3.1 KiB
Python
"""
|
|
Migration 0048 - Calculate firstSeed/seedCount and store directly in database
|
|
"""
|
|
|
|
from typing import cast, List, Dict, Any
|
|
|
|
from btrixcloud.migrations import BaseMigration
|
|
from btrixcloud.models import CrawlConfig, Crawl, Seed
|
|
|
|
|
|
MIGRATION_VERSION = "0048"
|
|
|
|
|
|
# pylint: disable=duplicate-code
|
|
class Migration(BaseMigration):
|
|
"""Migration class."""
|
|
|
|
# pylint: disable=unused-argument
|
|
def __init__(self, mdb, **kwargs):
|
|
super().__init__(mdb, migration_version=MIGRATION_VERSION)
|
|
|
|
async def migrate_up(self) -> None:
|
|
"""Perform migration up.
|
|
|
|
Calculate firstSeed and seedCount for workflows and store in db
|
|
"""
|
|
crawls_mdb = self.mdb["crawls"]
|
|
crawl_configs_mdb = self.mdb["crawl_configs"]
|
|
|
|
match_query = {"$or": [{"firstSeed": None}, {"seedCount": None}]}
|
|
|
|
# Workflows
|
|
async for config_raw in crawl_configs_mdb.find(match_query):
|
|
config = CrawlConfig.from_dict(config_raw)
|
|
|
|
try:
|
|
if not config.config.seeds:
|
|
print(
|
|
f"Unable to find seeds for config {config.id}, skipping",
|
|
flush=True,
|
|
)
|
|
continue
|
|
|
|
seeds = cast(List[Seed], config.config.seeds)
|
|
seed_count = len(seeds)
|
|
first_seed = seeds[0].url
|
|
|
|
await crawl_configs_mdb.find_one_and_update(
|
|
{"_id": config.id},
|
|
{
|
|
"$set": {
|
|
"firstSeed": first_seed,
|
|
"seedCount": seed_count,
|
|
}
|
|
},
|
|
)
|
|
# pylint: disable=broad-exception-caught
|
|
except Exception as err:
|
|
print(
|
|
f"Unable to update seed info for workflow {config.id}: {err}",
|
|
flush=True,
|
|
)
|
|
|
|
# Crawls
|
|
crawl_query: Dict[str, Any] = {
|
|
"type": "crawl",
|
|
"$or": [
|
|
{"firstSeed": {"$in": [None, ""]}},
|
|
{"seedCount": {"$in": [None, 0]}},
|
|
],
|
|
}
|
|
async for crawl_raw in crawls_mdb.find(crawl_query):
|
|
crawl_id = crawl_raw["_id"]
|
|
try:
|
|
crawl = Crawl.from_dict(crawl_raw)
|
|
config_raw = await crawl_configs_mdb.find_one({"_id": crawl.cid})
|
|
|
|
seed_count = config_raw.get("seedCount", 0)
|
|
first_seed = config_raw.get("firstSeed", "")
|
|
|
|
await crawls_mdb.find_one_and_update(
|
|
{"_id": crawl_id},
|
|
{
|
|
"$set": {
|
|
"firstSeed": first_seed,
|
|
"seedCount": seed_count,
|
|
}
|
|
},
|
|
)
|
|
# pylint: disable=broad-exception-caught
|
|
except Exception as err:
|
|
print(
|
|
f"Unable to update seed info for crawl {crawl_id}: {err}",
|
|
flush=True,
|
|
)
|