Merge branch 'main' into main

Author: RohanBhattaraiNP

CITATION.cff

@@ -11,11 +11,11 @@ authors:
 abstract: Python wrapper for CaltechDATA API.
 repository-code: "https://github.com/caltechlibrary/caltechdata_api"
 type: software
-version: 1.7.1
+version: 1.8.1
 license-url: "https://data.caltech.edu/license"
 keywords:
   - GitHub
   - metadata
   - software
   - InvenioRDM
-date-released: 2024-08-19
+date-released: 2024-10-18

caltechdata_api/cli.py

@@ -140,7 +140,7 @@ def get_funding_entries():
 def validate_funder_identifier(funder_identifier):
     response = requests.get(f"https://api.ror.org/organizations/{funder_identifier}")
     if response.status_code == 200:
-        return True
+        return response.json().get("name")
     else:
         return False
 
@@ -157,7 +157,8 @@ def get_funding_details():
     award_title = get_user_input("Enter the award title for funding: ")
     while True:
         funder_identifier = get_user_input("Enter the funder ROR (https://ror.org): ")
-        if validate_funder_identifier(funder_identifier):
+        name = validate_funder_identifier(funder_identifier)
+        if name:
             break
         else:
             print(
@@ -169,6 +170,7 @@ def get_funding_details():
     return {
         "awardNumber": award_number,
         "awardTitle": award_title,
+        "funderName": name,
         "funderIdentifier": funder_identifier,
         "funderIdentifierType": "ROR",
     }
@@ -194,9 +196,18 @@ def parse_arguments():
         if license_number.isdigit() and 1 <= int(license_number) <= 8:
             # Valid license number selected
             args["license"] = {
-                "1": "cc0-1.0",
-                "2": "cc-by-4.0",
-                "3": "cc-by-nc-4.0",
+                "1": {
+                    "rights": "Creative Commons Zero v1.0 Universal",
+                    "rightsIdentifier": "cc0-1.0",
+                },
+                "2": {
+                    "rights": "Creative Commons Attribution v4.0 Universal",
+                    "rightsIdentifier": "cc-by-4.0",
+                },
+                "3": {
+                    "rights": "Creative Commons Attribution Non-Commercial v4.0 Universal",
+                    "rightsIdentifier": "cc-by-nc-4.0",
+                },
             }[license_number]
             break
         else:
@@ -259,9 +270,11 @@ def get_names(orcid):
     return family_name, given_name
 
 
-def write_s3cmd_config(access_key, secret_key, endpoint):
+def write_s3cmd_config(endpoint):
     configf = os.path.join(home_directory, ".s3cfg")
     if not os.path.exists(configf):
+        access_key = get_user_input("Enter the access key: ")
+        secret_key = get_user_input("Enter the secret key: ")
         with open(configf, "w") as file:
             file.write(
                 f"""[default]
@@ -286,9 +299,7 @@ def upload_supporting_file(record_id=None):
             endpoint = "sdsc.osn.xsede.org"
             path = "ini230004-bucket01/"
             if not record_id:
-                access_key = get_user_input("Enter the access key: ")
-                secret_key = get_user_input("Enter the secret key: ")
-                write_s3cmd_config(access_key, secret_key, endpoint)
+                write_s3cmd_config(endpoint)
                 print("""S3 connection configured.""")
                 break
             endpoint = f"https://{endpoint}/"
@@ -478,9 +489,7 @@ def create_record(production):
                 ],
                 "types": {"resourceType": "", "resourceTypeGeneral": "Dataset"},
                 "rightsList": [
-                    {
-                        "rightsIdentifier": args["license"],
-                    }
+                    args["license"],
                 ],
                 "fundingReferences": args["fundingReferences"],
                 "schemaVersion": "http://datacite.org/schema/kernel-4",

caltechdata_api/customize_schema.py

@@ -394,73 +394,103 @@ def validate_metadata(json_record):
     """
     errors = []
 
+
     if "titles" not in json_record:
         errors.append("'titles' field is missing.")
     elif not isinstance(json_record["titles"], list) or len(json_record["titles"]) == 0:
         errors.append("'titles' should be a non-empty list.")
     else:
+
+        # Ensure each title is a dictionary with 'title' field
         for title in json_record["titles"]:
             if not isinstance(title, dict) or "title" not in title:
-                errors.append("Each entry in 'titles' must be a dictionary with a 'title' key.")
-    
+                errors.append(
+                    "Each entry in 'titles' must be a dictionary with a 'title' key."
+                )
+
+    # Publication date is handled by customize function
+
+    # Check for 'creators'
+    if "creators" not in json_record:
+        errors.append("'creators' field is missing.")
+    elif (
+        not isinstance(json_record["creators"], list)
+        or len(json_record["creators"]) == 0
+    ):
+        errors.append("'creators' should be a non-empty list.")
+    else:
+        for creator in json_record["creators"]:
+            if not isinstance(creator, dict) or "name" not in creator:
+                errors.append(
+                    "Each creator in 'creators' must be a dictionary with a 'name' key."
+                )
+
     # Check for 'contributors'
     if "contributors" in json_record:
-        if not isinstance(json_record["contributors"], list) or len(json_record["contributors"]) == 0:
-            errors.append("'contributors' should be a non-empty list.")
+        if not isinstance(json_record["contributors"], list):
+            errors.append("'contributors' should be a list.")
         else:
             for contributor in json_record["contributors"]:
-                if not isinstance(contributor, dict) or "name" not in contributor or "contributorType" not in contributor:
-                    errors.append("Each 'contributor' must have 'name' and 'contributorType'.")
-                if "nameIdentifiers" in contributor:
-                    if not isinstance(contributor["nameIdentifiers"], list):
-                        errors.append("'nameIdentifiers' should be a list.")
-                    for name_id in contributor["nameIdentifiers"]:
-                        if not isinstance(name_id, dict) or "nameIdentifier" not in name_id or "nameIdentifierScheme" not in name_id:
-                            errors.append("Each 'nameIdentifier' should have 'nameIdentifier' and 'nameIdentifierScheme'.")
-                if "affiliation" in contributor:
-                    if not isinstance(contributor["affiliation"], list):
-                        errors.append("'affiliation' should be a list.")
-                    for affiliation in contributor["affiliation"]:
-                        if not isinstance(affiliation, dict) or "name" not in affiliation:
-                            errors.append("Each 'affiliation' should have a 'name' key.")
-
-    # Check for 'descriptions'
-    if "descriptions" not in json_record:
-        errors.append("'descriptions' field is missing.")
-    elif not isinstance(json_record["descriptions"], list) or len(json_record["descriptions"]) == 0:
-        errors.append("'descriptions' should be a non-empty list.")
-    else:
-        for description in json_record["descriptions"]:
-            if not isinstance(description, dict) or "description" not in description or "descriptionType" not in description:
-                errors.append("Each 'description' must have 'description' and 'descriptionType'.")
+                if not isinstance(contributor, dict) or "name" not in contributor:
+                    errors.append(
+                        "Each contributor must be a dictionary with a 'name' key."
+                    )
 
-    # Check for 'fundingReferences'
-    if "fundingReferences" in json_record:
-        if not isinstance(json_record["fundingReferences"], list):
-            errors.append("'fundingReferences' should be a list.")
+    # Check for 'resourceType'
+    if "resourceType" not in json_record["types"]:
+        errors.append("'resourceType' field is missing in 'types'.")
+    elif not isinstance(json_record["types"]["resourceType"], str):
+        errors.append("'resourceType' should be a string.")
+
+    # Check for 'identifiers'
+    if "identifiers" in json_record:
+        if not isinstance(json_record["identifiers"], list):
+            errors.append("'identifiers' should be a list.")
         else:
-            for fund_ref in json_record["fundingReferences"]:
-                if not isinstance(fund_ref, dict) or "funderName" not in fund_ref:
-                    errors.append("Each 'fundingReference' must have 'funderName'.")
-                if "funderIdentifier" in fund_ref and "funderIdentifierType" not in fund_ref:
-                    errors.append("'funderIdentifier' should have an associated 'funderIdentifierType'.")
+            for identifier in json_record["identifiers"]:
+                if (
+                    not isinstance(identifier, dict)
+                    or "identifier" not in identifier
+                    or "identifierType" not in identifier
+                ):
+                    errors.append(
+                        "Each identifier must be a dictionary with 'identifier' and 'identifierType' keys."
+                    )
+
+    # Check for 'subjects'
+    if "subjects" in json_record:
+        if not isinstance(json_record["subjects"], list):
+            errors.append("'subjects' should be a list.")
+        else:
+            for subject in json_record["subjects"]:
+                if not isinstance(subject, dict) or "subject" not in subject:
+                    errors.append(
+                        "Each subject must be a dictionary with a 'subject' key."
+                    )
+
 
     # Check for 'relatedIdentifiers'
     if "relatedIdentifiers" in json_record:
         if not isinstance(json_record["relatedIdentifiers"], list):
             errors.append("'relatedIdentifiers' should be a list.")
         else:
             for related_id in json_record["relatedIdentifiers"]:
-                if not isinstance(related_id, dict) or "relatedIdentifier" not in related_id or "relationType" not in related_id:
-                    errors.append("Each 'relatedIdentifier' must have 'relatedIdentifier' and 'relationType'.")
-                if "relatedIdentifierType" not in related_id:
-                    errors.append("Each 'relatedIdentifier' must have 'relatedIdentifierType'.")
+
+                if (
+                    not isinstance(related_id, dict)
+                    or "relatedIdentifier" not in related_id
+                ):
+                    errors.append(
+                        "Each relatedIdentifier must be a dictionary with a 'relatedIdentifier' key."
+                    )
+
 
     # Check for 'rightsList'
     if "rightsList" in json_record:
         if not isinstance(json_record["rightsList"], list):
             errors.append("'rightsList' should be a list.")
         else:
+
             for right in json_record["rightsList"]:
                 if not isinstance(right, dict) or "rights" not in right:
                     errors.append("Each 'rightsList' entry must have 'rights'.")
@@ -512,11 +542,18 @@ def validate_metadata(json_record):
                     if not isinstance(affiliation, dict) or "name" not in affiliation:
                         errors.append("Each 'affiliation' in 'creators' must have a 'name'.")
 
+            for rights in json_record["rightsList"]:
+                if not isinstance(rights, dict) or "rights" not in rights:
+                    errors.append(
+                        "Each entry in 'rightsList' must be a dictionary with a 'rights' key."
+                    )
+
     # Check for 'geoLocations'
     if "geoLocations" in json_record:
         if not isinstance(json_record["geoLocations"], list):
             errors.append("'geoLocations' should be a list.")
         else:
+
             for geo_loc in json_record["geoLocations"]:
                 if not isinstance(geo_loc, dict) or "geoLocationPlace" not in geo_loc:
                     errors.append("Each 'geoLocation' must have 'geoLocationPlace'.")
@@ -560,6 +597,29 @@ def validate_metadata(json_record):
             errors.append("'types' must have 'resourceTypeGeneral'.")
         if "resourceType" in json_record["types"] and not isinstance(json_record["types"]["resourceType"], str):
             errors.append("'resourceType' should be a string if provided.")
+=======
+            for location in json_record["geoLocations"]:
+                if not isinstance(location, dict):
+                    errors.append("Each entry in 'geoLocations' must be a dictionary.")
+                elif (
+                    "geoLocationPoint" not in location
+                    and "geoLocationBox" not in location
+                    and "geoLocationPlace" not in location
+                ):
+                    errors.append(
+                        "Each geoLocation entry must contain at least one of 'geoLocationPoint', 'geoLocationBox', or 'geoLocationPlace'."
+                    )
+
+    # Check for 'fundingReferences'
+    if "fundingReferences" in json_record:
+        if not isinstance(json_record["fundingReferences"], list):
+            errors.append("'fundingReferences' should be a list.")
+        else:
+            for funding in json_record["fundingReferences"]:
+                if not isinstance(funding, dict):
+                    errors.append("Each funding reference must be a dictionary.")
+                if "funderName" not in funding:
+                    errors.append("Each funding reference must contain 'funderName'.")
 
     # Return errors if any are found
     if errors:

codemeta.json

@@ -6,7 +6,7 @@
   "codeRepository": "https://github.com/caltechlibrary/caltechdata_api",
   "issueTracker": "https://github.com/caltechlibrary/caltechdata_api/issues",
   "license": "https://data.caltech.edu/license",
-  "version": "1.7.1",
+  "version": "1.8.1",
   "author": [
     {
       "@type": "Person",
@@ -39,7 +39,7 @@
             }
     }],
   "developmentStatus": "active",
-  "downloadUrl": "https://github.com/caltechlibrary/caltechdata_api/archive/1.7.1.zip",
+  "downloadUrl": "https://github.com/caltechlibrary/caltechdata_api/archive/1.8.1.zip",
   "keywords": [
     "GitHub",
     "metadata",