def _extract_sinergise_fields(path: Path,
p: DatasetAssembler) -> Iterable[Path]:
"""Extract Sinergise metadata and return list of image offsets"""
product_info_path = path / "productInfo.json"
metadata_xml_path = path / "metadata.xml"
if not product_info_path.exists():
raise ValueError(
"No productInfo.json file found. "
"Are you sure the input is a sinergise dataset folder?")
p.properties.update(process_sinergise_product_info(product_info_path))
p.add_accessory_file("metadata:sinergise_product_info", product_info_path)
p.properties.update(process_tile_metadata(metadata_xml_path.read_text()))
p.add_accessory_file("metadata:s2_tile", metadata_xml_path)
# TODO: sinergise folders could `process_datastrip_metadata()` in an outer directory?
return path.glob("*.jp2")
def _write_stac(
metadata_path: Path,
task: AlchemistTask,
dataset_assembler: DatasetAssembler,
):
out_dataset = serialise.from_path(metadata_path)
stac_path = Path(str(metadata_path).replace("odc-metadata.yaml", "stac-item.json"))
# Madness in deferred destination logic
uri_base = dataset_assembler.names.destination_folder(
Path(task.settings.output.location)
)
uri_base = str(uri_base) + "/"
stac = dc_to_stac(
out_dataset,
metadata_path,
stac_path,
uri_base.replace("s3:/", "s3://"),
task.settings.output.explorer_url,
False,
)
with stac_path.open("w") as f:
json.dump(stac, f, default=json_fallback)
dataset_assembler.add_accessory_file("metadata:stac", stac_path)
# dataset_assembler._checksum.write(dataset_assembler._accessories["checksum:sha1"])
# Need a new checksummer because EODatasets is insane
checksummer = PackageChecksum()
checksum_file = (
dataset_assembler._dataset_location
/ dataset_assembler._accessories["checksum:sha1"].name
)
checksummer.read(checksum_file)
checksummer.add_file(stac_path)
checksummer.write(checksum_file)
return stac