Add Vocabulary class

.pre-commit-config.yaml

@@ -2,12 +2,12 @@
 # See https://pre-commit.com/hooks.html for more hooks
 repos:
 - repo: https://github.com/pre-commit/pre-commit-hooks
-  rev: v3.2.0
+  rev: v5.0.0
   hooks:
   - id: trailing-whitespace
   - id: end-of-file-fixer
   - id: check-yaml
-  - id: check-added-large-files
+  # - id: check-added-large-files
 - repo: https://github.com/psf/black-pre-commit-mirror
   rev: 24.3.0
   hooks:
@@ -22,8 +22,3 @@ repos:
   hooks:
     - id: isort
       additional_dependencies: [toml]
-        # - repo: https://github.com/pycqa/isort
-        #   rev: 5.11.2
-        #   hooks:
-        #     - id: isort
-        #       name: isort (python)

api/rda.py

@@ -1343,7 +1343,7 @@ def rda_all(body, eva):
     try:
         with open(api_config, "r") as f:
             documents = yaml.full_load(f)
-        logging.debug("API configuration successfully loaded: %s" % api_config)
+        logger.debug("API configuration successfully loaded: %s" % api_config)
     except Exception as e:
         message = "Could not find API config file: %s" % api_config
         logger.error(message)
@@ -1357,7 +1357,7 @@ def rda_all(body, eva):
             if documents["paths"][e]["x-indicator"]:
                 indi_code = e.split("/")
                 indi_code = indi_code[len(indi_code) - 1]
-                logger.debug("Running - %s" % indi_code)
+                logger.info("Running - %s" % indi_code)
                 points, msg = getattr(eva, indi_code)()
                 x_principle = documents["paths"][e]["x-principle"]
                 if "Findable" in x_principle:

api/utils.py

@@ -1,5 +1,6 @@
 import json
 import logging
+import os
 import re
 import sys
 import urllib
@@ -571,12 +572,15 @@ def orcid_basic_info(orcid):
         "Authorization": "Bearer a354d82e-37fa-47de-b4a2-740dbe90f355",
     }
     try:
+        if not idutils.is_orcid(orcid):
+            raise Exception("Malformed ORCID value: %s" % orcid)
         url = "https://pub.orcid.org/v3.0/" + orcid
         r = requests.get(url, verify=False, headers=headers)  # GET with headers
         xmlTree = ET.fromstring(r.text)
-        item = xmlTree.findall(
-            ".//{http://www.orcid.org/ns/common}assertion-origin-name"
-        )
+        for prop in ["assertion-origin-name", "source-name"]:
+            item = xmlTree.findall(".//{http://www.orcid.org/ns/common}%s" % prop)
+            if item:
+                break
     except Exception as e:
         logging.error(e)
         return basic_info
@@ -878,13 +882,23 @@ def resolve_handle(handle_id):
     return resolves, msg, values
 
 
-def check_link(address):
+def check_link(address, return_http_code=False):
+    resolves = False
     req = urllib.request.Request(url=address)
-    resp = urllib.request.urlopen(req)
-    if resp.status in [400, 404, 403, 408, 409, 501, 502, 503]:
-        return False
+    try:
+        resp = urllib.request.urlopen(req, timeout=15)
+    except urllib.error.URLError as e:
+        logging.warning("Timeout reached while trying to connect to '%s'" % address)
+    except urllib.error.HTTPError as e:
+        logging.warning("Could not access to resource: %s" % address)
     else:
-        return True
+        http_code = resp.status
+        logging.debug("Returned HTTP status from '%s': %s" % (address, http_code))
+        if return_http_code:
+            return http_code
+        if http_code not in ["400", "404", "403", "408", "409", "501", "502", "503"]:
+            resolves = True
+    return resolves
 
 
 def get_protocol_scheme(url):
@@ -913,76 +927,6 @@ def make_http_request(url, request_type="GET", verify=False):
     return payload
 
 
-def get_fairsharing_metadata(offline=True, username="", password="", path=""):
-    if offline == True:
-        f = open(path)
-        fairlist = json.load(f)
-        f.close()
-
-    else:
-        url = "https://api.fairsharing.org/users/sign_in"
-        payload = {"user": {"login": username, "password": password}}
-        headers = {"Accept": "application/json", "Content-Type": "application/json"}
-
-        response = requests.request(
-            "POST", url, headers=headers, data=json.dumps(payload)
-        )
-
-        # Get the JWT from the response.text to use in the next part.
-        data = response.json()
-        jwt = data["jwt"]
-
-        url = "https://api.fairsharing.org/search/fairsharing_records?page[size]=2500&fairsharing_registry=standard&user_defined_tags=metadata standardization"
-
-        headers = {
-            "Accept": "application/json",
-            "Content-Type": "application/json",
-            "Authorization": "Bearer {0}".format(jwt),
-        }
-
-        response = requests.request("POST", url, headers=headers)
-        fairlist = response.json()
-        user = open(path, "w")
-        json.dump(fairlist, user)
-        user.close()
-    return fairlist
-
-
-def get_fairsharing_formats(offline=True, username="", password="", path=""):
-    if offline == True:
-        f = open(path)
-        fairlist = json.load(f)
-        f.close()
-
-    else:
-        url = "https://api.fairsharing.org/users/sign_in"
-        payload = {"user": {"login": username, "password": password}}
-        headers = {"Accept": "application/json", "Content-Type": "application/json"}
-
-        response = requests.request(
-            "POST", url, headers=headers, data=json.dumps(payload)
-        )
-
-        # Get the JWT from the response.text to use in the next part.
-        data = response.json()
-        jwt = data["jwt"]
-
-        url = "https://api.fairsharing.org/search/fairsharing_records?page[size]=2500&user_defined_tags=Geospatial data"
-
-        headers = {
-            "Accept": "application/json",
-            "Content-Type": "application/json",
-            "Authorization": "Bearer {0}".format(jwt),
-        }
-
-        response = requests.request("POST", url, headers=headers)
-        fairlist = response.json()
-        user = open(path, "w")
-        json.dump(fairlist, user)
-        user.close()
-    return fairlist
-
-
 def check_fairsharing_abbreviation(fairlist, abreviation):
     for standard in fairlist["data"]:
         if abreviation == standard["attributes"]["abbreviation"]: