Skip to content

Operationalize SSC operations #2

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

Merged
nikki-t merged 3 commits into from
May 13, 2025
Merged

Operationalize SSC operations #2

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
d04a683
Create SSC input directory
nikki-t May 8, 2025
8945a47
Update for SSC data requirements
nikki-t May 12, 2025
995376a
Handle cases where data is not found in S3
nikki-t May 12, 2025
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: 32 additions & 7 deletions init_workflow.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,6 +77,7 @@ def set_up_efs():

EFS_DIR_INPUT.joinpath("gage").mkdir(parents=True, exist_ok=True)
EFS_DIR_INPUT.joinpath("gage").joinpath("Rtarget").mkdir(parents=True, exist_ok=True)
EFS_DIR_INPUT.joinpath("ssc", "model_static_files").mkdir(parents=True, exist_ok=True)
EFS_DIR_INPUT.joinpath("sos").mkdir(parents=True, exist_ok=True)
EFS_DIR_INPUT.joinpath("sword").mkdir(parents=True, exist_ok=True)
EFS_DIR_INPUT.joinpath("swot").mkdir(parents=True, exist_ok=True)
Expand All @@ -88,6 +89,7 @@ def set_up_efs():
EFS_DIR_FLPE.joinpath("momma").mkdir(parents=True, exist_ok=True)
EFS_DIR_FLPE.joinpath("sad").mkdir(parents=True, exist_ok=True)
EFS_DIR_FLPE.joinpath("sic4dvar").mkdir(parents=True, exist_ok=True)
EFS_DIR_FLPE.joinpath("ssc").mkdir(parents=True, exist_ok=True)

EFS_DIR_DIAGNOSTICS.joinpath("prediagnostics").mkdir(parents=True, exist_ok=True)
EFS_DIR_DIAGNOSTICS.joinpath("postdiagnostics").joinpath("basin").mkdir(parents=True, exist_ok=True)
Expand All @@ -105,14 +107,27 @@ def download_data(prefix, reaches_of_interest):
"""Download data needed to run the Confluence workflow."""

config_bucket = f"{prefix}-config"
json_bucket = f"{prefix}-json"

if reaches_of_interest:
roi = EFS_DIR_INPUT.joinpath(reaches_of_interest)
S3.download_file(
config_bucket,
reaches_of_interest,
EFS_DIR_INPUT.joinpath(reaches_of_interest)
roi
)
logging.info("Downloaded %s/%s to %s", config_bucket, reaches_of_interest, EFS_DIR_INPUT.joinpath(reaches_of_interest))

S3.upload_file(
roi,
json_bucket,
reaches_of_interest,
ExtraArgs={
"ServerSideEncryption": "aws:kms"
}
)
logging.info("Uploaded %s to %s/%s", roi, json_bucket, reaches_of_interest)

cont_setfinder = EFS_DIR_INPUT.joinpath("continent-setfinder.json")
S3.download_file(
config_bucket,
Expand All @@ -121,7 +136,6 @@ def download_data(prefix, reaches_of_interest):
)
logging.info("Downloaded %s/continent-setfinder.json to %s", config_bucket, cont_setfinder)

json_bucket = f"{prefix}-json"
S3.upload_file(
cont_setfinder,
json_bucket,
Expand All @@ -140,22 +154,30 @@ def download_data(prefix, reaches_of_interest):
)
logging.info("Downloaded %s/%s to %s", config_bucket, SWORD_PATCHES.name, SWORD_PATCHES)

download_directory(config_bucket, "gage")
download_directory(config_bucket, "sword")
download_directory(config_bucket, "gage", EFS_DIR_INPUT)
download_directory(config_bucket, "sword", EFS_DIR_INPUT)
download_directory(config_bucket, "ssc", EFS_DIR_INPUT)


def download_directory(config_bucket, prefix):
def download_directory(config_bucket, prefix, efs_dir):
"""Download all files located at prefix."""

paginator = S3.get_paginator('list_objects_v2')
page_iterator = paginator.paginate(
Bucket=config_bucket,
Prefix=prefix
)
items = [key["Key"] for page in page_iterator for key in page["Contents"]]

items = []
for page in page_iterator:
if page.get("Contents", None):
for content in page.get("Contents"):
items.append(content["Key"])

for item in items:
efs_file = EFS_DIR_INPUT.joinpath(item)
efs_file = efs_dir.joinpath(item)
if not efs_file.exists():
efs_file.parent.mkdir(parents=True, exist_ok=True)
S3.download_file(
config_bucket,
item,
Expand All @@ -165,6 +187,9 @@ def download_directory(config_bucket, prefix):
else:
logging.info("Not downloading %s", efs_file)

if len(items) == 0:
logging.info("No items detected for %s/%s", config_bucket, prefix)


if __name__ == "__main__":
init_workflow()