def test_is_eo3(sample_doc, sample_doc_180):
identity = list(Affine.translation(0, 0))
assert is_doc_eo3(sample_doc) is True
assert is_doc_eo3(sample_doc_180) is True
# If there's no schema field at all, it's treated as legacy eo.
assert is_doc_eo3({}) is False
assert is_doc_eo3({'crs': 'EPSG:4326'}) is False
assert is_doc_eo3({'crs': 'EPSG:4326', 'grids': {}}) is False
with pytest.raises(ValueError, match="Unsupported dataset schema.*"):
is_doc_eo3({'$schema': 'https://schemas.opendatacube.org/eo4'})
def get_dataset_file_offsets(dataset: Dataset) -> Dict[str, str]:
"""
Get (usually relative) paths for all known files of a dataset.
Returns {name, url}
"""
# Get paths to measurements (usually relative, but may not be)
uri_list = {
name: m["path"]
for name, m in dataset.measurements.items() if m.get("path")
}
# Add accessories too, if possible
if is_doc_eo3(dataset.metadata_doc):
dataset_doc = serialise.from_doc(dataset.metadata_doc,
skip_validation=True)
uri_list.update(
{name: a.path
for name, a in dataset_doc.accessories.items()})
return uri_list
def prepare_dataset_formatting(
dataset: Dataset,
include_source_url=False,
include_locations=False,
) -> CommentedMap:
"""
Try to format a raw Dataset document for readability.
This will change property order, add comments on the type & source url.
"""
doc = dict(dataset.metadata_doc)
# If it's EO3, use eodatasets's formatting. It's better.
if is_doc_eo3(doc):
if include_locations:
if len(dataset.uris) == 1:
doc["location"] = dataset.uris[0]
else:
doc["locations"] = dataset.uris
doc = eodatasets3.serialise.prepare_formatting(doc)
if include_source_url:
doc.yaml_set_comment_before_after_key(
"$schema",
before=f"url: {flask.request.url}",
)
# Strip EO-legacy fields.
undo_eo3_compatibility(doc)
return doc
else:
return prepare_document_formatting(
doc,
# Label old-style datasets as old-style datasets.
doc_friendly_label="EO1 Dataset",
include_source_url=include_source_url,
)