Improvements to map current edit workflow

Author: tmorrell

caltechdata_api/caltechdata_edit.py

@@ -36,13 +36,12 @@ def caltechdata_edit(
     if isinstance(ids, str):
         ids = [ids]
 
-    data = customize_schema.customize_schema(
-        copy.deepcopy(metadata), schema=schema)
+    data = customize_schema.customize_schema(copy.deepcopy(metadata), schema=schema)
     if production == True:
-        url = "https://data.caltech.edu/"
+        url = "https://data.caltech.edu"
         verify = True
     else:
-        url = "https://data.caltechlibrary.dev/"
+        url = "https://data.caltechlibrary.dev"
         verify = True
 
     headers = {
@@ -90,8 +89,19 @@ def caltechdata_edit(
 
         else:
             # just update metadata
+            # result = requests.post(
+            #    url + "/api/records/" + idv + "/draft",
+            #    headers=headers,
+            #    verify=verify,
+            # )
+            # if result.status_code != 200:
+            #    print(result.text)
+            #    exit()
+            # print(result.json())
+            # exit()
+            # print(url + "/api/records/" + idv + "/draft")
             result = requests.get(
-                url + "/api/records/" + idv + "/draft",
+                url + "/api/records/" + idv,
                 headers=headers,
                 verify=verify,
             )
@@ -100,6 +110,7 @@ def caltechdata_edit(
                 exit()
             # We want files to stay the same as the existing record
             data["files"] = result.json()["files"]
+            print(url + "/api/records/" + idv + "/draft")
             result = requests.put(
                 url + "/api/records/" + idv + "/draft",
                 headers=headers,
@@ -112,6 +123,7 @@ def caltechdata_edit(
 
         if publish:
             publish_link = f"{url}/api/records/{idv}/draft/actions/publish"
+            print(publish_link)
             result = requests.post(publish_link, headers=headers, verify=verify)
             if result.status_code != 202:
                 print(result.text)

caltechdata_api/customize_schema.py

@@ -221,16 +221,31 @@ def customize_schema_rdm(json_record):
     if "identifiers" in json_record:
         identifiers = []
         for identifier in json_record["identifiers"]:
-            if identifier["identifierType"] != "DOI":
+            if identifier["identifierType"] == "DOI":
+                doi = identifier["identifier"]
+                prefix = doi.split("/")[0]
+                if prefix == "10.22002":
+                    pids = {
+                        "doi": {
+                            "identifier": doi,
+                            "provider": "datacite",
+                            "client": "datacite",
+                        }
+                    }
+                else:
+                    pids = {
+                        "doi": {
+                            "identifier": doi,
+                            "provider": "external",
+                        }
+                    }
+            elif identifier["identifierType"] == "oai":
+                # All OAI identifiers are system generated, and are not accepted
+                # via this API
+                print("Discarding oai identifier")
+            else:
                 identifier["scheme"] = identifiertypes[identifier.pop("identifierType")]
                 identifiers.append(identifier)
-            else:
-                pids = {
-                    "doi": {
-                        "identifier": identifier["identifier"],
-                        "provider": "external",
-                    }
-                }
         json_record["identifiers"] = identifiers
 
     if "relatedIdentifiers" in json_record:

caltechdata_api/vocabularies/identifier_types.yaml

@@ -95,6 +95,6 @@
     en: W3ID
 - id: cdid
   props:
-    datacite: CaltechDATA_Identifier
+    datacite: cdid
   title:
     en: CALTECHDATA_ID

setup.py

@@ -58,7 +58,7 @@ def package_files(package, directory):
 REQUIRES_PYTHON = ">=3.6.0"
 
 # What packages are required for this module to be executed?
-REQUIRED = ["requests", "datacite>1.1.0", "tqdm", "pyyaml"]
+REQUIRED = ["requests", "datacite>1.1.0", "tqdm>=4.62.3", "pyyaml"]
 
 # What packages are optional?
 EXTRAS = {

outdated/write.py renamed to write.py

@@ -9,19 +9,19 @@
 parser.add_argument(
     "json_file", nargs=1, help="file name for json DataCite metadata file"
 )
-parser.add_argument("-ids", nargs="*", help="CaltechDATA IDs")
 parser.add_argument("-fnames", nargs="*", help="New Files")
-parser.add_argument("-schema", default="40", help="Metadata Schema")
+parser.add_argument("-schema", default="43", help="Metadata Schema")
 
 args = parser.parse_args()
 
 # Get access token as environment variable
-token = os.environ["TINDTOK"]
+token = os.environ["RDMTOK"]
 
 metaf = open(args.json_file[0], "r")
 metadata = json.load(metaf)
 
 production = True
+publish = False
 
-response = caltechdata_write(metadata, token, args.fnames, production, args.schema)
+response = caltechdata_write(metadata, token, args.fnames, production, args.schema, publish)
 print(response)