Fix doi bug

Author: tmorrell

caltechdata_api/caltechdata_edit.py

@@ -225,6 +225,8 @@ def caltechdata_edit(
             data = customize_schema.customize_schema(metadata, schema=schema)
         else:
             # Authors, force oai PID
+            if "pids" not in metadata:
+                metadata["pids"] = {}
             metadata["pids"]["oai"] = {
                 "identifier": f"oai:authors.library.caltech.edu:{idv}",
                 "provider": "oai",

caltechdata_api/caltechdata_write.py

@@ -189,6 +189,7 @@ def caltechdata_write(
     elif "identifiers" in metadata:
         identifiers = metadata["identifiers"]
     for identifier in identifiers:
+        doi = False
         if "identifierType" in identifier:
             if identifier["identifierType"] == "DOI":
                 doi = identifier["identifier"]
@@ -198,17 +199,11 @@ def caltechdata_write(
                     "identifier": identifier["identifier"],
                     "provider": "oai",
                 }
-            else:
-                doi = False
         elif "scheme" in identifier:
             # We have RDM internal metadata
             if identifier["scheme"] == "doi":
                 doi = identifier["identifier"]
                 prefix = doi.split("/")[0]
-            else:
-                doi = False
-        else:
-            doi = False
         if doi != False:
             if prefix == repo_prefix:
                 pids["doi"] = {

caltechdata_api/get_metadata.py

@@ -7,7 +7,9 @@
 from datacite import schema43
 
 
-def get_metadata(idv, production=True, validate=True, emails=False, schema="43"):
+def get_metadata(
+    idv, production=True, validate=True, emails=False, schema="43", token=False
+):
     # Returns just DataCite metadata or DataCite metadata with emails
 
     if production == True:
@@ -21,7 +23,11 @@ def get_metadata(idv, production=True, validate=True, emails=False, schema="43")
         "accept": "application/vnd.datacite.datacite+json",
     }
 
+    if token:
+        headers["Authorization"] = "Bearer %s" % token
+
     response = requests.get(url + idv, headers=headers, verify=verify)
+    print(response.headers)
     if response.status_code != 200:
         raise Exception(response.text)
     else:

edit_osn.py

@@ -1,5 +1,5 @@
 import argparse, os, json
-import s3fs
+import s3fs, requests
 from datacite import schema43
 from caltechdata_api import caltechdata_edit, get_metadata
 
@@ -25,7 +25,20 @@
 path = "ini210004tommorrell/" + folder + "/"
 
 idv = args.id[0]
-metadata = get_metadata(idv, schema="43")
+try:
+    metadata = get_metadata(idv, schema="43")
+except:
+    url = "https://data.caltech.edu/api/records/"
+
+    headers = {
+        "accept": "application/vnd.datacite.datacite+json",
+        "Authorization": "Bearer %s" % token,
+        }
+
+    response = requests.get(url + idv +'/draft', headers=headers)
+    if response.status_code != 200:
+        raise Exception(response.text)
+    metadata = response.json()
 
 # Find the files
 files = s3.glob(path + "/*")
@@ -56,6 +69,6 @@
 production = True
 
 response = caltechdata_edit(
-    idv, metadata, token, [], production, "43", publish=True, file_links=file_links
+    idv, metadata, token, [], production, "43", publish=False, file_links=file_links
 )
 print(response)