caltechdata-api 1.8.1__tar.gz → 1.9.0__tar.gz

{caltechdata_api-1.8.1 → caltechdata_api-1.9.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: caltechdata_api
-Version: 1.8.1
+Version: 1.9.0
 Summary: Python wrapper for CaltechDATA API.
 Home-page: https://github.com/caltechlibrary/caltechdata_api
 Author: Thomas E Morrell, Bhattarai Rohan , Won Elizabeth
@@ -20,6 +20,8 @@ License-File: LICENSE
 
 # CaltechDATA API Python Library
 
+[![DOI](https://img.shields.io/badge/dynamic/json.svg?label=DOI&query=$.pids.doi.identifier&uri=https://data.caltech.edu/api/records/wfjr5-kw507/versions/latest)](https://data.caltech.edu/records/wfjr5-kw507/latest)
+
 The `caltechdata_api` Python library provides a convenient interface for interacting with the CaltechDATA API. It allows users to write files, create DataCite 4 standard JSON records, edit existing records, and retrieve metadata from the CaltechDATA repository.
 
 ## Features

{caltechdata_api-1.8.1 → caltechdata_api-1.9.0}/README.md

@@ -1,5 +1,7 @@
 # CaltechDATA API Python Library
 
+[![DOI](https://img.shields.io/badge/dynamic/json.svg?label=DOI&query=$.pids.doi.identifier&uri=https://data.caltech.edu/api/records/wfjr5-kw507/versions/latest)](https://data.caltech.edu/records/wfjr5-kw507/latest)
+
 The `caltechdata_api` Python library provides a convenient interface for interacting with the CaltechDATA API. It allows users to write files, create DataCite 4 standard JSON records, edit existing records, and retrieve metadata from the CaltechDATA repository.
 
 ## Features

{caltechdata_api-1.8.1 → caltechdata_api-1.9.0}/caltechdata_api/caltechdata_write.py

@@ -248,7 +248,10 @@ def caltechdata_write(
     # Make draft and publish
     result = requests.post(url + "/api/records", headers=headers, json=data)
     if result.status_code != 201:
-        raise Exception(result.text)
+        if result.status_code == 400 and "Referer checking failed" in result.text:
+            raise Exception("Token is incorrect or missing referer.")
+        else:
+            raise Exception(result.text)
     idv = result.json()["id"]
     publish_link = result.json()["links"]["publish"]
 

{caltechdata_api-1.8.1 → caltechdata_api-1.9.0}/caltechdata_api/cli.py

@@ -2,7 +2,7 @@ import argparse
 import requests
 import s3fs
 from caltechdata_api import caltechdata_write, caltechdata_edit
-from .md_to_json import parse_readme_to_json
+from md_to_json import parse_readme_to_json
 import json
 import os
 from cryptography.fernet import Fernet
@@ -71,6 +71,11 @@ def get_or_set_token(production=True):
         with open(token_file, "rb") as f:
             encrypted_token = f.read()
             token = decrypt_token(encrypted_token, key)
+            print(
+                "Using saved CaltechDATA production token."
+                if production
+                else "Using saved CaltechDATA test token."
+            )
             return token
     except FileNotFoundError:
         while True:
@@ -422,8 +427,6 @@ def main():
 
 def create_record(production):
     token = get_or_set_token(production)
-    # keep_file = input("Do you want to keep your existing files? (yes/no): ").lower() == "yes"
-    print("Using CaltechDATA token:", token)
     while True:
         choice = get_user_input(
             "Do you want to use metadata from an existing file or create new metadata? (existing/create): "
@@ -466,6 +469,7 @@ def create_record(production):
                 "descriptions": [
                     {"description": args["description"], "descriptionType": "Abstract"}
                 ],
+                "publisher": "CaltechDATA",
                 "creators": [
                     {
                         "affiliation": [

{caltechdata_api-1.8.1 → caltechdata_api-1.9.0}/caltechdata_api/customize_schema.py

@@ -1,5 +1,4 @@
-# Convert a DataCite 4 or 4.3 standard schema json record to the customized internal
-# schema used by TIND in CaltechDATA
+# Convert a DataCite 4.3 standard schema json record to the InvenioRDM schema
 import argparse
 import json
 from datetime import date
@@ -81,7 +80,7 @@ def rdm_creators_contributors(person_list, peopleroles):
             else:
                 print(f"Name type {ntype} not known")
         else:
-            # We default to organizational if not known
+            # We default to personal if not known
             cre["type"] = "personal"
         change_label(cre, "givenName", "given_name")
         change_label(cre, "familyName", "family_name")
@@ -253,7 +252,7 @@ def customize_schema_rdm(json_record):
 
     if "identifiers" in json_record:
         identifiers = []
-        system_pids = ["DOI", "oai"]
+        system_pids = ["oai"]
         for identifier in json_record["identifiers"]:
             if identifier["identifierType"] not in system_pids:
                 identifier["scheme"] = identifiertypes[identifier.pop("identifierType")]
@@ -394,20 +393,12 @@ def validate_metadata(json_record):
     """
     errors = []
 
-    # Check for 'types' and 'resourceTypeGeneral'
-    if "types" not in json_record:
-        errors.append("'types' field is missing.")
-    elif not isinstance(json_record["types"], dict):
-        errors.append("'types' field should be a dictionary.")
-    elif "resourceTypeGeneral" not in json_record["types"]:
-        errors.append("'resourceTypeGeneral' field is missing in 'types'.")
-
-    # Check for 'title'
     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:
@@ -417,32 +408,6 @@ def validate_metadata(json_record):
 
     # 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):
-            errors.append("'contributors' should be a list.")
-        else:
-            for contributor in json_record["contributors"]:
-                if not isinstance(contributor, dict) or "name" not in contributor:
-                    errors.append(
-                        "Each contributor must be a dictionary with a 'name' key."
-                    )
-
     # Check for 'resourceType'
     if "resourceType" not in json_record["types"]:
         errors.append("'resourceType' field is missing in 'types'.")
@@ -481,6 +446,7 @@ def validate_metadata(json_record):
             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
@@ -494,17 +460,180 @@ def validate_metadata(json_record):
         if not isinstance(json_record["rightsList"], list):
             errors.append("'rightsList' should be a list.")
         else:
-            for rights in json_record["rightsList"]:
-                if not isinstance(rights, dict) or "rights" not in rights:
+
+            for right in json_record["rightsList"]:
+                if not isinstance(right, dict) or "rights" not in right:
+                    errors.append("Each 'rightsList' entry must have 'rights'.")
+                if "rightsURI" in right and not isinstance(right["rightsURI"], str):
+                    errors.append("'rightsURI' should be a string.")
+
+    # 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 have a 'subject' key.")
+
+    # Check for 'dates'
+    if "dates" not in json_record:
+        errors.append("'dates' field is missing.")
+    elif not isinstance(json_record["dates"], list) or len(json_record["dates"]) == 0:
+        errors.append("'dates' should be a non-empty list.")
+    else:
+        for date in json_record["dates"]:
+            if (
+                not isinstance(date, dict)
+                or "date" not in date
+                or "dateType" not in date
+            ):
+                errors.append("Each 'date' must have 'date' and 'dateType'.")
+
+    # Check for 'identifiers'
+    if "identifiers" not in json_record:
+        errors.append("'identifiers' field is missing.")
+    elif (
+        not isinstance(json_record["identifiers"], list)
+        or len(json_record["identifiers"]) == 0
+    ):
+        errors.append("'identifiers' should be a non-empty list.")
+    else:
+        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 have 'identifier' and 'identifierType'."
+                )
+
+    # 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):
+                errors.append("Each 'creator' must be a dictionry")
+            if "nameType" in creator:
+                if creator["nameType"] == "Organizational":
+                    if "name" not in creator:
+                        errors.append("Each organizational 'creator' must have 'name'.")
+            else:
+                if "familyName" not in creator:
                     errors.append(
-                        "Each entry in 'rightsList' must be a dictionary with a 'rights' key."
+                        "Each 'creator' must have a 'familyName' or have type Organizational"
                     )
+            if "affiliation" in creator:
+                if not isinstance(creator["affiliation"], list):
+                    errors.append("'affiliation' in 'creators' should be a list.")
+                for affiliation in creator["affiliation"]:
+                    if not isinstance(affiliation, dict) or "name" not in affiliation:
+                        errors.append(
+                            "Each 'affiliation' in 'creators' must have a 'name'."
+                        )
+
+    # Check for 'contributors'
+    if "contributors" in json_record:
+        if (
+            not isinstance(json_record["contributors"], list)
+            or len(json_record["contributors"]) == 0
+        ):
+            errors.append("'creators' should be a non-empty list.")
+        else:
+            for contributor in json_record["contributors"]:
+                if not isinstance(contributor, dict):
+                    errors.append("Each 'contributor' must be a dictionry")
+                if "nameType" in contributor:
+                    if contributor["nameType"] == "Organizational":
+                        if "name" not in creator:
+                            errors.append(
+                                "Each organizational 'contributor' must have 'name'."
+                            )
+                else:
+                    if "familyName" not in contributor:
+                        errors.append(
+                            "Each 'contributor' must have a 'familyName' or have type Organizational"
+                        )
+                if "affiliation" in contributor:
+                    if not isinstance(contributor["affiliation"], list):
+                        errors.append(
+                            "'affiliation' in 'contributors' should be a list."
+                        )
+                    for affiliation in contributor["affiliation"]:
+                        if (
+                            not isinstance(affiliation, dict)
+                            or "name" not in affiliation
+                        ):
+                            errors.append(
+                                "Each 'affiliation' in 'contributors' must have a 'name'."
+                            )
 
     # 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'.")
+                if "geoLocationPoint" in geo_loc:
+                    point = geo_loc["geoLocationPoint"]
+                    if (
+                        not isinstance(point, dict)
+                        or "pointLatitude" not in point
+                        or "pointLongitude" not in point
+                    ):
+                        errors.append(
+                            "'geoLocationPoint' must have 'pointLatitude' and 'pointLongitude'."
+                        )
+
+    # Check for 'formats'
+    if "formats" in json_record and (
+        not isinstance(json_record["formats"], list) or len(json_record["formats"]) == 0
+    ):
+        errors.append("'formats' should be a non-empty list.")
+
+    # Check for 'language'
+    if "language" in json_record:
+        if not isinstance(json_record["language"], str):
+            errors.append("'language' should be a string.")
+
+    # Check for 'version'
+    if "version" in json_record and not isinstance(json_record["version"], str):
+        errors.append("'version' should be a string.")
+
+    # Check for 'publisher'
+    if "publisher" not in json_record:
+        errors.append("'publisher' field is missing.")
+    elif not isinstance(json_record["publisher"], str):
+        errors.append("'publisher' should be a string.")
+
+    # Check for 'publicationYear'
+    if "publicationYear" not in json_record:
+        errors.append("'publicationYear' field is missing.")
+    elif not isinstance(json_record["publicationYear"], str):
+        errors.append("'publicationYear' should be a string.")
+
+    # Check for 'types'
+    if "types" not in json_record:
+        errors.append("'types' field is missing.")
+    elif not isinstance(json_record["types"], dict):
+        errors.append("'types' should be a dictionary.")
+    else:
+        if "resourceTypeGeneral" not in json_record["types"]:
+            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.")

{caltechdata_api-1.8.1 → caltechdata_api-1.9.0}/caltechdata_api/get_metadata.py

@@ -8,26 +8,43 @@ from datacite import schema43
 
 
 def get_metadata(
-    idv, production=True, validate=True, emails=False, schema="43", token=False
+    idv,
+    production=True,
+    validate=True,
+    emails=False,
+    schema="43",
+    token=False,
+    authors=False,
 ):
     # Returns just DataCite metadata or DataCite metadata with emails
 
     if production == True:
-        url = "https://data.caltech.edu/api/records/"
+        if authors:
+            url = "https://authors.library.caltech.edu/api/records/"
+        else:
+            url = "https://data.caltech.edu/api/records/"
         verify = True
     else:
-        url = "https://data.caltechlibrary.dev/api/records/"
+        if authors:
+            url = "https://authors.caltechlibrary.dev/api/records/"
+        else:
+            url = "https://data.caltechlibrary.dev/api/records/"
         verify = True
 
-    headers = {
-        "accept": "application/vnd.datacite.datacite+json",
-    }
+    if authors:
+        headers = {
+            "accept": "application/json",
+        }
+        validate = False
+    else:
+        headers = {
+            "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:
@@ -59,6 +76,7 @@ if __name__ == "__main__":
         help="The CaltechDATA ID for each record of interest",
     )
     parser.add_argument("-test", dest="production", action="store_false")
+    parser.add_argument("-authors", dest="authors", action="store_true")
     parser.add_argument("-xml", dest="save_xml", action="store_true")
     parser.add_argument(
         "-skip_validate",
@@ -72,6 +90,7 @@ if __name__ == "__main__":
 
     production = args.production
     schema = args.schema
+    authors = args.authors
     skip_validate = args.skip_validate
     if skip_validate:
         validate = False
@@ -79,7 +98,9 @@ if __name__ == "__main__":
         validate = True
 
     for idv in args.ids:
-        metadata = get_metadata(idv, production, validate, schema)
+        metadata = get_metadata(
+            idv, production, validate, schema=schema, authors=authors
+        )
         outfile = open(str(idv) + ".json", "w")
         outfile.write(json.dumps(metadata, indent=4))
         outfile.close()

{caltechdata_api-1.8.1 → caltechdata_api-1.9.0}/caltechdata_api.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: caltechdata-api
-Version: 1.8.1
+Version: 1.9.0
 Summary: Python wrapper for CaltechDATA API.
 Home-page: https://github.com/caltechlibrary/caltechdata_api
 Author: Thomas E Morrell, Bhattarai Rohan , Won Elizabeth
@@ -20,6 +20,8 @@ License-File: LICENSE
 
 # CaltechDATA API Python Library
 
+[![DOI](https://img.shields.io/badge/dynamic/json.svg?label=DOI&query=$.pids.doi.identifier&uri=https://data.caltech.edu/api/records/wfjr5-kw507/versions/latest)](https://data.caltech.edu/records/wfjr5-kw507/latest)
+
 The `caltechdata_api` Python library provides a convenient interface for interacting with the CaltechDATA API. It allows users to write files, create DataCite 4 standard JSON records, edit existing records, and retrieve metadata from the CaltechDATA repository.
 
 ## Features