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

Update the check_landsat_orphans script #151

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Update the check_landsat_orphans script #151

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
075f1cb
Update the check_landsat_orphans script
Bskr-P May 23, 2024
baee2ab
Updated format to satisfy the checks
Bskr-P May 23, 2024
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
45 changes: 34 additions & 11 deletions scripts/misc/check_landsat_orphans.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,9 +2,11 @@
Read latest landsat gap reports(i.e. Landsat 5, Landsat 7 and Landsat 8),
check orphan scenes and generate report for cleanup
"""

import json
from datetime import datetime
from odc.aws import s3_client, s3_fetch, s3_ls, s3_dump, s3_ls_dir
import re

DEAFRICA_AWS_REGION = "af-south-1"
DEAFRICA_LANDSAT_BUCKET_NAME = "deafrica-landsat"
Expand All @@ -19,6 +21,12 @@
PUBLISH_TO_S3 = True


def find_date(text):
date_pattern = re.compile(r"(\d{4}-\d{2}-\d{2})")
date = re.search(date_pattern, text).group(0)
return date


def get_orphans():
s3 = s3_client(region_name=DEAFRICA_AWS_REGION)

Expand All @@ -30,15 +38,30 @@ def get_orphans():

# fetch the latest report: Landsat 5, Landsat 7 and Landsat 8
report_files_json.sort()
landsat_8_report = [
report_file for report_file in report_files_json if "landsat_8" in report_file
][-1]
landsat_7_report = [
report_file for report_file in report_files_json if "landsat_7" in report_file
][-1]
landsat_5_report = [
report_file for report_file in report_files_json if "landsat_5" in report_file
][-1]
landsat_8_report = sorted(
[
report_file
for report_file in report_files_json
if "landsat_8" in report_file.lower()
],
key=lambda x: find_date(x),
)[-1]
landsat_7_report = sorted(
[
report_file
for report_file in report_files_json
if "landsat_7" in report_file.lower()
],
key=lambda x: find_date(x),
)[-1]
landsat_5_report = sorted(
[
report_file
for report_file in report_files_json
if "landsat_5" in report_file.lower()
],
key=lambda x: find_date(x),
)[-1]

# collect orphan paths
list_orphan_paths = []
Expand Down Expand Up @@ -75,12 +98,12 @@ def publish_to_s3(data: list, output_filename: str, content_type: str = "text/pl
s3 = s3_client(region_name=DEAFRICA_AWS_REGION)
s3_dump(
data=data,
url=str(DEAFRICA_ORPHAN_REPORT_S3_PATH / output_filename),
url=str(DEAFRICA_ORPHAN_REPORT_S3_PATH + output_filename),
s3=s3,
ContentType=content_type,
)
print(
f"Report can be accessed from {DEAFRICA_ORPHAN_REPORT_S3_PATH / output_filename}"
f"Report can be accessed from {DEAFRICA_ORPHAN_REPORT_S3_PATH + output_filename}"
)


Expand Down
Loading