chore: multiple products for a dataset in the mapping (#247)

allow a dataset to be in several products (they are now comma separated in the mapping)
mercator-ocean · Dec 10, 2024 · 2fc0b30 · 2fc0b30
1 parent 38021d2
commit 2fc0b30
Showing 1 changed file with 27 additions and 19 deletions.
diff --git a/copernicusmarine/catalogue_parser/catalogue_parser.py b/copernicusmarine/catalogue_parser/catalogue_parser.py
@@ -58,26 +58,34 @@ def get_dataset_metadata(
         dataset_product_mapping_url = (
             f"{root_url}/dataset_product_id_mapping.json"
         )
-        product_id = connection.get_json_file(dataset_product_mapping_url).get(
-            dataset_id
-        )
-        if not product_id:
+        product_ids = connection.get_json_file(
+            dataset_product_mapping_url
+        ).get(dataset_id)
+        if not product_ids:
             raise DatasetNotFound(dataset_id)
-        url = f"{stac_url}/{product_id}/product.stac.json"
-        product_json = connection.get_json_file(url)
-        product_collection = pystac.Collection.from_dict(product_json)
-        product_datasets_metadata_links = product_collection.get_item_links()
-        datasets_metadata_links = [
-            dataset_metadata_link
-            for dataset_metadata_link in product_datasets_metadata_links
-            if dataset_id in dataset_metadata_link.href
-        ]
-        if not datasets_metadata_links:
-            return None
-        dataset_jsons: list[dict] = [
-            connection.get_json_file(f"{stac_url}/{product_id}/{link.href}")
-            for link in datasets_metadata_links
-        ]
+        dataset_jsons: list[dict] = []
+        for product_id in product_ids.split(","):
+            url = f"{stac_url}/{product_id}/product.stac.json"
+            product_json = connection.get_json_file(url)
+            product_collection = pystac.Collection.from_dict(product_json)
+            product_datasets_metadata_links = (
+                product_collection.get_item_links()
+            )
+            datasets_metadata_links = [
+                dataset_metadata_link
+                for dataset_metadata_link in product_datasets_metadata_links
+                if dataset_id in dataset_metadata_link.href
+            ]
+            if not datasets_metadata_links:
+                continue
+            dataset_jsons.extend(
+                [
+                    connection.get_json_file(
+                        f"{stac_url}/{product_id}/{link.href}"
+                    )
+                    for link in datasets_metadata_links
+                ]
+            )
 
         dataset_items = [
             dataset_item