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.

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

[python][treasury-report] add force-regenerate parameter to allow for deletion of the existing treasury file before generation #515

Merged
merged 16 commits into from
Dec 9, 2024
Merged
Show file tree
Hide file tree
Changes from 10 commits
Commits
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
39 changes: 38 additions & 1 deletion python/src/functions/generate_treasury_report.py
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,11 @@
from pydantic import BaseModel

from src.lib.logging import get_logger, reset_contextvars
from src.lib.s3_helper import download_s3_object, upload_generated_file_to_s3
from src.lib.s3_helper import (
delete_file_from_s3,
download_s3_object,
upload_generated_file_to_s3,
)
from src.lib.treasury_generation_common import (
OrganizationObj,
OutputFileType,
Expand Down Expand Up @@ -54,6 +58,7 @@ class ProjectLambdaPayload(BaseModel):
ProjectType: str
uploadsToAdd: Dict[AgencyId, UploadObj]
uploadsToRemove: Dict[AgencyId, UploadObj]
forceRegenerate: bool = False


@reset_contextvars
Expand Down Expand Up @@ -132,6 +137,16 @@ def process_event(

organization = payload.organization

# If we need to force-regenerate the treasury report, we delete the treasury
# report from s3 so that it starts with the template file.
if payload.forceRegenerate:
delete_output_file(
s3_client=s3_client,
organization=organization,
project_use_code=project_use_code,
logger=logger,
)

# If the treasury report file exists, download it and store the data
# If it doesn't exist, download the output template

Expand Down Expand Up @@ -267,6 +282,28 @@ def process_event(
return {"statusCode": 200, "body": "Success"}


def delete_output_file(
s3_client: S3Client,
organization: OrganizationObj,
project_use_code: str,
logger: structlog.stdlib.BoundLogger,
):
try:
delete_file_from_s3(
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Note: we also need to delete the report.zip file in the same directory in addition to this file

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This should be the list of files to delete:

        delete_file_from_s3(
            client=s3_client,
            bucket=os.environ["REPORTING_DATA_BUCKET_NAME"],
            key=get_generated_output_file_key(
                file_type=OutputFileType.XLSX,
                project=project_use_code,
                organization=organization,
            ),
        )
        delete_file_from_s3(
            client=s3_client,
            bucket=os.environ["REPORTING_DATA_BUCKET_NAME"],
            key=get_generated_output_file_key(
                file_type=OutputFileType.CSV,
                project=project_use_code,
                organization=organization,
            ),
        )
        delete_file_from_s3(
            client=s3_client,
            bucket=os.environ["REPORTING_DATA_BUCKET_NAME"],
            key=get_generated_output_file_key(
                file_type=OutputFileType.JSON,
                project=project_use_code,
                organization=organization,
            ),
        )
        report_key = f"treasuryreports/{organization.id}/{organization.preferences.current_reporting_period_id}/report.zip"
        delete_file_from_s3(
            client=s3_client,
            bucket=os.environ["REPORTING_DATA_BUCKET_NAME"],
            key=report_key,
        )

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Added, but I'm looking into fixing the issue with the CI; (all the changed files have a python/ prepended that needs to be removed)

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Should be fixed here: #575 🤞🏼

client=s3_client,
bucket=os.environ["REPORTING_DATA_BUCKET_NAME"],
key=get_generated_output_file_key(
file_type=OutputFileType.XLSX,
project=project_use_code,
organization=organization,
),
)
except ClientError as e:
error = e.response.get("Error") or {}
if error.get("Code") == "404":
logger.exception("Expected to find an existing treasury output report")
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

note: no raise because the file could've already been deleted before



def download_output_file(
s3_client: S3Client,
output_file: IO[bytes],
Expand Down
27 changes: 26 additions & 1 deletion python/src/lib/s3_helper.py
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,31 @@ def download_s3_object(
raise


def delete_file_from_s3(client: S3Client, bucket: str, key: str) -> None:
"""Deletes file from S3.

Args:
client: Client facilitating delete from S3
bucket: bucket file should be deleted from
key: S3 key for file
"""
logger = get_logger()

logger = logger.bind(upload={"s3": {"bucket": bucket, "key": key}})
try:
client.delete_object(
Bucket=bucket,
Key=unquote_plus(key),
)
except:
logger.exception(
f"failed to delete file from S3, bucket {bucket} and key {key}"
)
raise

logger.info("successfully deleted file from s3")


def upload_generated_file_to_s3(
client: S3Client,
bucket: str,
Expand All @@ -45,7 +70,7 @@ def upload_generated_file_to_s3(
"""
logger = get_logger()

logger = logger.bind(upload={"s3": {"bucket": bucket, "key": key}})
logger = logger.bind(delete={"s3": {"bucket": bucket, "key": key}})
try:
file.seek(0)
client.put_object(
Expand Down
Loading