Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

BI-4975: added old_tenant_id parameter to rename_tenant_files task #57

Merged
merged 2 commits into from
Oct 31, 2023
Merged

BI-4975: added old_tenant_id parameter to rename_tenant_files task #57

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5856b8e
BI-4975: added old_tenant_id parameter to rename_tenant_files task
asnytin Oct 30, 2023
78f9385
attrs fix
asnytin Oct 31, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions lib/dl_file_uploader_api_lib/dl_file_uploader_api_lib/schemas/misc.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,4 +8,5 @@ class CleanupRequestSchema(BaseRequestSchema):


class RenameFilesRequestSchema(BaseRequestSchema):
old_tenant_id = ma.fields.String(allow_none=True, load_default=None)
tenant_id = ma.fields.String(required=True)
5 changes: 3 additions & 2 deletions lib/dl_file_uploader_api_lib/dl_file_uploader_api_lib/views/misc.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,12 +68,13 @@ class RenameTenantFilesView(FileUploaderBaseView):
async def post(self) -> web.StreamResponse:
req_data = await self._load_post_request_schema_data(misc_schemas.RenameFilesRequestSchema)
tenant_id = req_data["tenant_id"]
old_tenant_id = req_data["old_tenant_id"]

rmm = self.dl_request.get_redis_model_manager()
await RenameTenantStatusModel(manager=rmm, id=tenant_id, status=RenameTenantStatus.scheduled).save()

task_processor = self.dl_request.get_task_processor()
await task_processor.schedule(RenameTenantFilesTask(tenant_id=tenant_id))
LOGGER.info(f"Scheduled RenameTenantFilesTask for tenant_id {tenant_id}")
await task_processor.schedule(RenameTenantFilesTask(tenant_id=tenant_id, old_tenant_id=old_tenant_id))
LOGGER.info(f"Scheduled RenameTenantFilesTask for tenant_id {tenant_id} (old_tenant_id = {old_tenant_id})")

return web.Response()
3 changes: 2 additions & 1 deletion lib/dl_file_uploader_task_interface/dl_file_uploader_task_interface/tasks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -106,8 +106,9 @@ class CleanupTenantFilePreviewsTask(BaseTaskMeta):
tenant_id: str = attr.ib()


@attr.s
@attr.s(kw_only=True)
class RenameTenantFilesTask(BaseTaskMeta):
name = TaskName("rename_tenant_files_task")

old_tenant_id: Optional[str] = attr.ib(default=None)
tenant_id: str = attr.ib()
KonstantAnxiety marked this conversation as resolved.
Show resolved Hide resolved
43 changes: 31 additions & 12 deletions lib/dl_file_uploader_worker_lib/dl_file_uploader_worker_lib/tasks/cleanup.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,10 @@
timedelta,
)
import logging
from typing import Any
from typing import (
Any,
Optional,
)

import attr
from botocore.exceptions import ClientError
Expand Down Expand Up @@ -211,7 +214,8 @@ class RenameTenantFilesTask(BaseExecutorTask[task_interface.RenameTenantFilesTas

async def run(self) -> TaskResult:
tenant_id = self.meta.tenant_id
LOGGER.info(f"RenameTenantFilesTask. Moving to {tenant_id}")
old_tenant_id = self.meta.old_tenant_id
LOGGER.info(f"RenameTenantFilesTask. Moving to {tenant_id} (old_tenant_id = {old_tenant_id})")

rmm = RedisModelManager(
redis=self._ctx.redis_service.get_redis(),
Expand Down Expand Up @@ -256,23 +260,38 @@ async def run(self) -> TaskResult:
assert isinstance(conn, BaseFileS3Connection)
conn_changed = False
for source in conn.data.sources:
old_s3_filename = source.s3_filename
if old_s3_filename is None:
if source.s3_filename is None and source.s3_filename_suffix is None:
LOGGER.info(
f"Cannot rename file for source_id {source.id} - s3_filename not set"
)
continue
if old_s3_filename.startswith(tenant_id):
LOGGER.info(f"File is already tagged with the new tenant: {old_s3_filename}")
continue

old_fname_parts = old_s3_filename.split("_")
if len(old_fname_parts) >= 2 and all(part for part in old_fname_parts):
# assume that first part is old tenant id
old_tenants.add(old_fname_parts[0])
old_s3_filename: str
if source.s3_filename:
old_s3_filename = source.s3_filename
else:
assert old_tenant_id
old_s3_filename = "_".join(
(old_tenant_id, conn.uuid, source.s3_filename_suffix)
)

s3_filename_suffix = make_source_s3_filename_suffix()
if not old_tenant_id:
old_fname_parts = old_s3_filename.split("_")
if len(old_fname_parts) >= 2 and all(part for part in old_fname_parts):
# assume that first part is old tenant id
old_tenant_id = old_fname_parts[0]
old_tenants.add(old_tenant_id)

s3_filename_suffix = (
source.s3_filename_suffix
if source.s3_filename_suffix is not None
else make_source_s3_filename_suffix()
)
new_s3_filename = conn.get_full_s3_filename(s3_filename_suffix)
if old_s3_filename == new_s3_filename:
LOGGER.info(f"The file already has the correct name: {new_s3_filename}")
continue

await s3_client.copy_object(
CopySource=dict(
Bucket=s3_service.persistent_bucket_name,
Expand Down
Loading