spiff-arena/spiffworkflow-backend/bin/data_migrations/run_all.py

117 lines
4.0 KiB
Python
Raw Normal View History

import time
from flask import current_app
from spiffworkflow_backend import create_app
from spiffworkflow_backend.data_migrations.version_1_3 import VersionOneThree
from spiffworkflow_backend.data_migrations.version_2 import Version2
from spiffworkflow_backend.models.db import db
from spiffworkflow_backend.models.human_task import HumanTaskModel
from spiffworkflow_backend.models.process_instance import ProcessInstanceModel
from sqlalchemy import update
# simple decorator to time the func
# https://stackoverflow.com/a/11151365/6090676, thank you
def benchmark_log_func(func):
"""
decorator to calculate the total time of a func
"""
def st_func(*args, **kwargs):
t1 = time.time()
r = func(*args, **kwargs)
t2 = time.time()
# __qualname__, i know you use it every day. but if not, it's the function name prefixed with any qualifying class names
current_app.logger.debug(f"Function={func.__qualname__}, Time={t2 - t1}")
return r
return st_func
@benchmark_log_func
def put_serializer_version_onto_numeric_track() -> None:
old_busted_serializer_version = "1.0-spiffworkflow-backend"
update_query = (
update(ProcessInstanceModel)
.where(ProcessInstanceModel.spiff_serializer_version == old_busted_serializer_version)
.values(spiff_serializer_version="1")
)
db.session.execute(update_query)
db.session.commit()
@benchmark_log_func
def remove_duplicate_human_task_rows() -> None:
result = (
db.session.query(HumanTaskModel.process_instance_id, HumanTaskModel.task_guid, db.func.count().label("ct"))
.group_by(HumanTaskModel.task_guid, HumanTaskModel.process_instance_id)
.having(db.func.count() > 1)
.all()
)
# Process the result as needed
rows_to_delete = []
for row in result:
human_tasks = (
HumanTaskModel.query.filter_by(task_guid=row.task_guid).order_by(HumanTaskModel.created_at_in_seconds.desc()).all()
)
rows_to_delete = rows_to_delete + human_tasks[1:]
for row in rows_to_delete:
db.session.delete(row)
db.session.commit()
@benchmark_log_func
def backfill_task_guid_for_human_tasks() -> None:
update_query = (
update(HumanTaskModel).where(HumanTaskModel.task_guid == None).values(task_guid=HumanTaskModel.task_id) # noqa: E711
)
db.session.execute(update_query)
db.session.commit()
def all_potentially_relevant_process_instances() -> list[ProcessInstanceModel]:
return ProcessInstanceModel.query.filter(
ProcessInstanceModel.spiff_serializer_version < Version2.version(),
ProcessInstanceModel.status.in_(ProcessInstanceModel.non_terminal_statuses()),
).all()
@benchmark_log_func
def run_version_1() -> None:
VersionOneThree().run() # make this a class method
@benchmark_log_func
def run_version_2(process_instances: list[ProcessInstanceModel]) -> None:
Version2.run(process_instances)
def main() -> None:
start_time = time.time()
app = create_app()
end_time = time.time()
with app.app_context():
current_app.logger.debug(f"data_migrations/run_all::create_app took {end_time - start_time} seconds")
start_time = time.time()
put_serializer_version_onto_numeric_track()
remove_duplicate_human_task_rows()
backfill_task_guid_for_human_tasks()
process_instances = all_potentially_relevant_process_instances()
potentially_relevant_instance_count = len(process_instances)
Feature/background proc with celery (#788) * WIP: some initial test code to test out celery w/ burnettk * some cleanup for celery and added base model to put tasks waiting on timers * removed dup bpmn file * some more cleanup and added strategy to queue instructions * some minor code changes w/ burnettk * remove the unused next_task key from api calls since nobody uses it w/ burnettk essweine * added migration for future tasks and added test to make sure we are inserting into it w/ burnettk essweine * ensure future task run at time can be updated w/ burnettk * added table to queue instructions for end user in w/ burnettk * added test to ensure we are storing instructions for end users w/ burnettk * added progress page to display new instructions to user * ignore dup instructions on db insert w/ burnettk * some more updates for celery w/ burnettk * some pyl and test fixes w/ burnettk * fixed tests w/ burnettk * WIP: added in page to show instructions on pi show page w/ burnettk * pi show page is fully using not interstitial now w/ burnettk * fixed broken test w/ burnettk * moved background processing items to own module w/ burnettk * fixed apscheduler start script * updated celery task queue to handle future tasks and upgraded black and set its line-length to match ruff w/ burnettk * added support to run future tasks using countdown w/ burnettk * build image for celery branch w/ burnettk * poet does not exist in the image w/ burnettk * start blocking scheduler should always start the scheduler w/ burnettk * add init and stuff for this branch * make this work not just on my mac * send other args to only * added running status for process instance and use that on fe to go to show page and added additional identifier to locking system to isolate celery workers better w/ burnettk * fixed typing error that typeguard found, not sure why mypy did not w/ burnettk * do not check for no instructions on interstitial page for cypress tests on frontend w/ burnettk * do not queue process instances twice w/ burnettk * removed bad file w/ burnettk * queue tasks using strings to avoid circular imports when attmepting to queue w/ burnettk * only queue imminent new timer events and mock celery * some keyboard shortcut support on frontend and added ability to force run a process instance over the api w/ burnettk * some styles added for the shortcut menu w/ burnettk * pyl w/ burnettk * fixed test w/ burnettk * removed temporary celery script and added support for celery worker in run server locally w/ burnettk * cleaned up migrations w/ burnettk * created new migration to clean up old migrations --------- Co-authored-by: jasquat <jasquat@users.noreply.github.com> Co-authored-by: burnettk <burnettk@users.noreply.github.com>
2023-12-05 16:41:59 +00:00
current_app.logger.debug(f"Found potentially relevant process_instances: {potentially_relevant_instance_count}")
if potentially_relevant_instance_count > 0:
run_version_1()
# this will run while using the new per instance on demand data migration framework
# run_version_2(process_instances)
end_time = time.time()
current_app.logger.debug(
f"done running data migrations in ./bin/data_migrations/run_all.py. took {end_time - start_time} seconds"
)
if __name__ == "__main__":
main()