feat: new metadata_urls field (#171)

* feat: new metadata_urls field

* isBasedOn to snake case

---------

Co-authored-by: Luca Fabbri <l.fabbri@bopen.eu>

Author: alfredotoselli

alembic/versions/79280fd201ed_add_metadata_urls_field.py

@@ -0,0 +1,29 @@
+"""add metadata_urls field.
+
+Revision ID: 79280fd201ed
+Revises: ddf161fdce37
+Create Date: 2025-12-24 10:38:39.791341
+
+"""
+
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql as dialect_postgresql
+
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision = "79280fd201ed"
+down_revision = "ddf161fdce37"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "resources",
+        sa.Column("metadata_urls", dialect_postgresql.ARRAY(sa.String)),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("resources", "metadata_urls")

cads_catalogue/database.py

@@ -332,6 +332,7 @@ class Resource(BaseModel):
     update_frequency = sa.Column(sa.String)
     variables: Any = sa.Column(dialect_postgresql.JSONB)
     content_size = sa.Column(sa.Float)
+    metadata_urls = sa.Column(dialect_postgresql.ARRAY(sa.String))
 
     # FAIR
     fair_timestamp = sa.Column(sa.DateTime(timezone=True), default=None, nullable=True)

cads_catalogue/manager.py

@@ -350,6 +350,7 @@ def load_resource_metadata_file(folder_path: str | pathlib.Path) -> dict[str, An
     metadata["use_limitation"] = data.get("use_limitation")
     metadata["content_size"] = data.get("content_size")
     metadata["update_frequency"] = data.get("update_frequency")
+    metadata["metadata_urls"] = data.get("isBasedOn", []) or []
     return metadata
 
 

cads_catalogue/validations.py

@@ -297,6 +297,7 @@ def validate_metadata_json(dataset_folder):
         "use_limitation",
         "content_size",
         "update_frequency",
+        "is_based_on",
     ]
     # suggest to insert a value for missing/None fields:
     for optional_field in optional_fields:
@@ -376,6 +377,13 @@ def validate_metadata_json(dataset_folder):
             if not utils.is_url(keyword_url):
                 logger.error(f"keyword_url {keyword_url} is not an url")
 
+    # validate is_based_on as list of urls
+    is_based_on = data.get("is_based_on")
+    if is_based_on:
+        for item in is_based_on:
+            if not utils.is_url(item):
+                logger.error(f"is_based_on entry {item} is not an url")
+
     # validate field that is a list of strings
     for field in ["licences", "qos_tags", "related_resources_keywords"]:
         field_value = data.get(field)

tests/data/cads-forms-json/legacy/reanalysis-era5-land/metadata.json

@@ -49,6 +49,7 @@
   ],
   "popularity": 500,
   "qos_tags": ["tag1", "tag2", "tag3"],
+  "isBasedOn": ["http://cfconventions.org/documents.html"],
   "api_enforce_constraints": true,
   "title": "ERA5-Land hourly data from 1950 to present",
   "abstract": "ERA5-Land is a reanalysis dataset providing a consistent view of the evolution of land variables over several decades at an enhanced resolution compared to ERA5. ERA5-Land has been produced by replaying the land component of the ECMWF ERA5 climate reanalysis. Reanalysis combines model data with observations from across the world into a globally complete and consistent dataset using the laws of physics. Reanalysis produces data that goes several decades back in time, providing an accurate description of the climate of the past."

tests/data/cads-forms-json/reanalysis-era5-land/metadata.json

@@ -50,6 +50,7 @@
   "keywords_urls": [],
   "popularity": 500,
   "qos_tags": ["tag1", "tag2", "tag3"],
+  "isBasedOn": ["http://cfconventions.org/documents.html"],
   "api_enforce_constraints": true,
   "title": "ERA5-Land hourly data from 1950 to present",
   "abstract": "ERA5-Land is a reanalysis dataset providing a consistent view of the evolution of land variables over several decades at an enhanced resolution compared to ERA5. ERA5-Land has been produced by replaying the land component of the ECMWF ERA5 climate reanalysis. Reanalysis combines model data with observations from across the world into a globally complete and consistent dataset using the laws of physics. Reanalysis produces data that goes several decades back in time, providing an accurate description of the climate of the past."

tests/data/dumped_resources1.txt

@@ -23,7 +23,7 @@
         "begin_date": "1950-01-01",
         "end_date": "2023-02-11",
         "publication_date": "2019-07-12",
-        "record_update": "2025-08-27 07:45:50.510200+03:00",
+        "record_update": "2025-12-24 10:11:04.217153+01:00",
         "resource_update": "2023-02-17",
         "abstract": "ERA5-Land is a reanalysis dataset providing a consistent view of the evolution of land variables over several decades at an enhanced resolution compared to ERA5. ERA5-Land has been produced by replaying the land component of the ECMWF ERA5 climate reanalysis. Reanalysis combines model data with observations from across the world into a globally complete and consistent dataset using the laws of physics. Reanalysis produces data that goes several decades back in time, providing an accurate description of the climate of the past.",
         "citation": null,
@@ -58,12 +58,15 @@
         "update_frequency": null,
         "variables": [],
         "content_size": null,
+        "metadata_urls": [
+            "http://cfconventions.org/documents.html"
+        ],
+        "fair_timestamp": null,
         "fulltext": null,
         "high_priority_terms": "reanalysis ERA5 land",
         "popularity": 500,
         "search_field": "'1950':11A 'accur':92B 'across':65B 'back':87B 'climat':56B,96B 'combin':59B 'compar':38B 'complet':71B 'compon':51B 'consist':23B,73B 'data':9A,61B,82B 'dataset':20B,74B 'decad':33B,86B 'descript':93B 'ecmwf':54B 'enhanc':36B 'era5':3A,6A,15B,40B,42B,55B,101 'era5-land':5A,14B,41B 'evolut':27B 'global':70B 'goe':84B 'hour':8A 'land':4A,7A,16B,29B,43B,50B,102 'law':77B 'model':60B 'observ':63B 'past':99B 'physic':79B 'present':13A 'produc':46B,81B 'provid':21B,90B 'reanalysi':2A,19B,57B,58B,80B,100 'reanalysis-era5-land':1A 'replay':48B 'resolut':37B 'sever':32B,85B 'time':89B 'use':75B 'variabl':30B 'view':24B 'world':67B",
-        "fts": "'era5':2 'land':3 'reanalysi':1",
-        "fair_timestamp": null
+        "fts": "'era5':2 'land':3 'reanalysi':1"
     },
     {
         "resource_id": 2,
@@ -89,7 +92,7 @@
         "begin_date": "1950-01-01",
         "end_date": "2022-12-01",
         "publication_date": "2019-06-23",
-        "record_update": "2025-08-27 07:45:50.531565+03:00",
+        "record_update": "2025-12-24 10:11:04.257466+01:00",
         "resource_update": "2023-02-17",
         "abstract": "ERA5-Land is a reanalysis dataset providing a consistent view of the evolution of land variables over several decades at an enhanced resolution compared to ERA5. ERA5-Land has been produced by replaying the land component of the ECMWF ERA5 climate reanalysis. Reanalysis combines model data with observations from across the world into a globally complete and consistent dataset using the laws of physics. Reanalysis produces data that goes several decades back in time, providing an accurate description of the climate of the past.",
         "citation": null,
@@ -122,11 +125,12 @@
         "update_frequency": null,
         "variables": [],
         "content_size": null,
+        "metadata_urls": [],
+        "fair_timestamp": null,
         "fulltext": "climate reanalysis past land era5 hydrology physics biosphere copernicus c3s conditions variables monthly means",
         "high_priority_terms": "",
         "popularity": 1,
         "search_field": "'1950':14A 'accur':95B 'across':68B 'averag':11A 'back':90B 'biospher':110C 'c3s':112C 'climat':59B,99B,103C 'combin':62B 'compar':41B 'complet':74B 'compon':54B 'condit':113C 'consist':26B,76B 'copernicus':111C 'data':12A,64B,85B 'dataset':23B,77B 'decad':36B,89B 'descript':96B 'ecmwf':57B 'enhanc':39B 'era5':3A,8A,18B,43B,45B,58B,107C 'era5-land':7A,17B,44B 'evolut':30B 'global':73B 'goe':87B 'hydrolog':108C 'land':4A,9A,19B,32B,46B,53B,106C 'law':80B 'mean':6A,116C 'model':63B 'month':5A,10A,115C 'observ':66B 'past':102B,105C 'physic':82B,109C 'present':16A 'produc':49B,84B 'provid':24B,93B 'reanalysi':2A,22B,60B,61B,83B,104C 'reanalysis-era5-land-monthly-means':1A 'replay':51B 'resolut':40B 'sever':35B,88B 'time':92B 'use':78B 'variabl':33B,114C 'view':27B 'world':70B",
-        "fts": "",
-        "fair_timestamp": null
+        "fts": ""
     }
 ]

tests/data/dumped_resources2.txt

@@ -23,7 +23,7 @@
         "begin_date": "1950-01-01",
         "end_date": "2023-02-11",
         "publication_date": "2019-07-12",
-        "record_update": "2025-08-27 07:45:50.510200+03:00",
+        "record_update": "2025-12-24 10:11:04.217153+01:00",
         "resource_update": "2023-02-17",
         "abstract": "ERA5-Land is a reanalysis dataset providing a consistent view of the evolution of land variables over several decades at an enhanced resolution compared to ERA5. ERA5-Land has been produced by replaying the land component of the ECMWF ERA5 climate reanalysis. Reanalysis combines model data with observations from across the world into a globally complete and consistent dataset using the laws of physics. Reanalysis produces data that goes several decades back in time, providing an accurate description of the climate of the past.",
         "citation": null,
@@ -58,12 +58,15 @@
         "update_frequency": null,
         "variables": [],
         "content_size": null,
+        "metadata_urls": [
+            "http://cfconventions.org/documents.html"
+        ],
+        "fair_timestamp": null,
         "fulltext": null,
         "high_priority_terms": "reanalysis ERA5 land",
         "popularity": 500,
         "search_field": "'1950':11A 'accur':92B 'across':65B 'back':87B 'climat':56B,96B 'combin':59B 'compar':38B 'complet':71B 'compon':51B 'consist':23B,73B 'data':9A,61B,82B 'dataset':20B,74B 'decad':33B,86B 'descript':93B 'ecmwf':54B 'enhanc':36B 'era5':3A,6A,15B,40B,42B,55B,101 'era5-land':5A,14B,41B 'evolut':27B 'global':70B 'goe':84B 'hour':8A 'land':4A,7A,16B,29B,43B,50B,102 'law':77B 'model':60B 'observ':63B 'past':99B 'physic':79B 'present':13A 'produc':46B,81B 'provid':21B,90B 'reanalysi':2A,19B,57B,58B,80B,100 'reanalysis-era5-land':1A 'replay':48B 'resolut':37B 'sever':32B,85B 'time':89B 'use':75B 'variabl':30B 'view':24B 'world':67B",
-        "fts": "'era5':2 'land':3 'reanalysi':1",
-        "fair_timestamp": null
+        "fts": "'era5':2 'land':3 'reanalysi':1"
     },
     {
         "resource_id": 2,
@@ -89,7 +92,7 @@
         "begin_date": "1950-01-01",
         "end_date": "2022-12-01",
         "publication_date": "2019-06-23",
-        "record_update": "2025-08-27 07:45:50.531565+03:00",
+        "record_update": "2025-12-24 10:11:04.257466+01:00",
         "resource_update": "2023-02-17",
         "abstract": "ERA5-Land is a reanalysis dataset providing a consistent view of the evolution of land variables over several decades at an enhanced resolution compared to ERA5. ERA5-Land has been produced by replaying the land component of the ECMWF ERA5 climate reanalysis. Reanalysis combines model data with observations from across the world into a globally complete and consistent dataset using the laws of physics. Reanalysis produces data that goes several decades back in time, providing an accurate description of the climate of the past.",
         "citation": null,
@@ -122,11 +125,12 @@
         "update_frequency": null,
         "variables": [],
         "content_size": null,
+        "metadata_urls": [],
+        "fair_timestamp": null,
         "fulltext": "climate reanalysis past land era5 hydrology physics biosphere copernicus c3s conditions variables monthly means",
         "high_priority_terms": "",
         "popularity": 1,
         "search_field": "'1950':14A 'accur':95B 'across':68B 'averag':11A 'back':90B 'biospher':110C 'c3s':112C 'climat':59B,99B,103C 'combin':62B 'compar':41B 'complet':74B 'compon':54B 'condit':113C 'consist':26B,76B 'copernicus':111C 'data':12A,64B,85B 'dataset':23B,77B 'decad':36B,89B 'descript':96B 'ecmwf':57B 'enhanc':39B 'era5':3A,8A,18B,43B,45B,58B,107C 'era5-land':7A,17B,44B 'evolut':30B 'global':73B 'goe':87B 'hydrolog':108C 'land':4A,9A,19B,32B,46B,53B,106C 'law':80B 'mean':6A,116C 'model':63B 'month':5A,10A,115C 'observ':66B 'past':102B,105C 'physic':82B,109C 'present':16A 'produc':49B,84B 'provid':24B,93B 'reanalysi':2A,22B,60B,61B,83B,104C 'reanalysis-era5-land-monthly-means':1A 'replay':51B 'resolut':40B 'sever':35B,88B 'time':92B 'use':78B 'variabl':33B,114C 'view':27B 'world':70B",
-        "fts": "",
-        "fair_timestamp": null
+        "fts": ""
     }
 ]

tests/data/dumped_resources3.txt

@@ -10,7 +10,7 @@
         "adaptor_properties_hash": "3cfceb3cb45d4fb56d6dc29575c36af4",
         "api_enforce_constraints": true,
         "disabled_reason": null,
-        "sources_hash": "3cbb4e51e9993fac651033ea7334f7a5",
+        "sources_hash": "29a88c88049cd4dbf385dd1a2584140f",
         "related_resources_keywords": [],
         "sanity_check": null,
         "sanity_check_conf": null,
@@ -23,7 +23,7 @@
         "begin_date": "1950-01-01",
         "end_date": "2023-02-11",
         "publication_date": "2019-07-12",
-        "record_update": "2025-08-27 07:45:51.253762+03:00",
+        "record_update": "2025-12-24 10:11:05.982515+01:00",
         "resource_update": "2023-02-17",
         "abstract": "ERA5-Land is a reanalysis dataset providing a consistent view of the evolution of land variables over several decades at an enhanced resolution compared to ERA5. ERA5-Land has been produced by replaying the land component of the ECMWF ERA5 climate reanalysis. Reanalysis combines model data with observations from across the world into a globally complete and consistent dataset using the laws of physics. Reanalysis produces data that goes several decades back in time, providing an accurate description of the climate of the past.",
         "citation": null,
@@ -58,11 +58,14 @@
         "update_frequency": null,
         "variables": [],
         "content_size": null,
+        "metadata_urls": [
+            "http://cfconventions.org/documents.html"
+        ],
+        "fair_timestamp": null,
         "fulltext": null,
         "high_priority_terms": "reanalysis ERA5 land",
         "popularity": 500,
         "search_field": "'1950':11A 'accur':92B 'across':65B 'back':87B 'climat':56B,96B 'combin':59B 'compar':38B 'complet':71B 'compon':51B 'consist':23B,73B 'data':9A,61B,82B 'dataset':20B,74B 'decad':33B,86B 'descript':93B 'ecmwf':54B 'enhanc':36B 'era5':3A,6A,15B,40B,42B,55B,101 'era5-land':5A,14B,41B 'evolut':27B 'global':70B 'goe':84B 'hour':8A 'land':4A,7A,16B,29B,43B,50B,102 'law':77B 'model':60B 'observ':63B 'past':99B 'physic':79B 'present':13A 'produc':46B,81B 'provid':21B,90B 'reanalysi':2A,19B,57B,58B,80B,100 'reanalysis-era5-land':1A 'replay':48B 'resolut':37B 'sever':32B,85B 'time':89B 'use':75B 'variabl':30B 'view':24B 'world':67B",
-        "fts": "'era5':2 'land':3 'reanalysi':1",
-        "fair_timestamp": null
+        "fts": "'era5':2 'land':3 'reanalysi':1"
     }
 ]