fix: apply upstream bugfixes and add proxy support from the-library-code/dspace-rest-python

Backport critical bugfixes and improvements from upstream v0.1.14-v0.1.16.

Bug fixes:
- Fix User class field definitions with trailing commas creating tuples
- Fix get_items() checking wrong _embedded key ('collections' vs 'items')
- Fix InProgressSubmission step/type assignment bugs in __init__
- Fix EntityType type field overwriting label in __init__

Improvements:
- Add proxy support (PROXY_DICT, proxies param, all HTTP methods)
- Add params parameter to api_patch() signature
- Add embedded attribute to HALResource for _embedded API data

Author: jm

dspace_rest_client/client.py

@@ -73,6 +73,8 @@ class DSpaceClient:
     if 'USER_AGENT' in os.environ:
         USER_AGENT = os.environ['USER_AGENT']
     verbose = False
+    ITER_PAGE_SIZE = 20
+    PROXY_DICT = dict(http=os.environ["PROXY_URL"],https=os.environ["PROXY_URL"]) if "PROXY_URL" in os.environ else dict()
 
     # Simple enum for patch operation types
     class PatchOperation:
@@ -82,7 +84,7 @@ class PatchOperation:
         MOVE = 'move'
 
     def __init__(self, api_endpoint=API_ENDPOINT, username=USERNAME, password=PASSWORD, solr_endpoint=SOLR_ENDPOINT,
-                 solr_auth=SOLR_AUTH, fake_user_agent=False):
+                 solr_auth=SOLR_AUTH, fake_user_agent=False, proxies=PROXY_DICT):
         """
         Accept optional API endpoint, username, password arguments using the OS environment variables as defaults
         :param api_endpoint:    base path to DSpace REST API, eg. http://localhost:8080/server/api
@@ -95,6 +97,7 @@ def __init__(self, api_endpoint=API_ENDPOINT, username=USERNAME, password=PASSWO
         self.USERNAME = username
         self.PASSWORD = password
         self.SOLR_ENDPOINT = solr_endpoint
+        self.proxies = proxies
         self.solr = None
         self._last_err = None
         try:
@@ -128,7 +131,8 @@ def authenticate(self, retry=False):
         # Set headers for requests made during authentication
         # Get and update CSRF token
         r = self.session.post(self.LOGIN_URL, data={'user': self.USERNAME, 'password': self.PASSWORD},
-                              headers=self.auth_request_headers)
+                              headers=self.auth_request_headers,
+                              proxies=self.proxies)
         self.update_token(r)
 
         if r.status_code == 403:
@@ -203,7 +207,8 @@ def api_get(self, url, params=None, data=None, headers=None):
         self._last_err = None
         if headers is None:
             headers = self.request_headers
-        r = self.session.get(url, params=params, data=data, headers=headers)
+        r = self.session.get(url, params=params, data=data, headers=headers,
+                             proxies=self.proxies)
         self.update_token(r)
         return r
 
@@ -218,7 +223,8 @@ def api_post(self, url, params, json, retry=False):
         @return:        Response from API
         """
         self._last_err = None
-        r = self.session.post(url, json=json, params=params, headers=self.request_headers)
+        r = self.session.post(url, json=json, params=params, headers=self.request_headers,
+                              proxies=self.proxies)
         self.update_token(r)
 
         if r.status_code == 403:
@@ -262,7 +268,8 @@ def api_post_uri(self, url, params, uri_list, retry=False):
         @return:        Response from API
         """
         self._last_err = None
-        r = self.session.post(url, data=uri_list, params=params, headers=self.list_request_headers)
+        r = self.session.post(url, data=uri_list, params=params, headers=self.list_request_headers,
+                              proxies=self.proxies)
         self.update_token(r)
 
         if r.status_code == 403:
@@ -291,7 +298,8 @@ def api_put(self, url, params, json, retry=False):
         @return:        Response from API
         """
         self._last_err = None
-        r = self.session.put(url, params=params, json=json, headers=self.request_headers)
+        r = self.session.put(url, params=params, json=json, headers=self.request_headers,
+                             proxies=self.proxies)
         self.update_token(r)
 
         if r.status_code == 403:
@@ -321,7 +329,8 @@ def api_delete(self, url, params, retry=False):
         @return:        Response from API
         """
         self._last_err = None
-        r = self.session.delete(url, params=params, headers=self.request_headers)
+        r = self.session.delete(url, params=params, headers=self.request_headers,
+                                proxies=self.proxies)
         self.update_token(r)
 
         if r.status_code == 403:
@@ -341,7 +350,7 @@ def api_delete(self, url, params, retry=False):
 
         return r
 
-    def api_patch(self, url, operation, path, value, retry=False):
+    def api_patch(self, url, operation, path, value, params=None, retry=False):
         """
         @param url: DSpace REST API URL
         @param operation: 'add', 'remove', 'replace', or 'move' (see PatchOperation enumeration)
@@ -377,7 +386,8 @@ def api_patch(self, url, operation, path, value, retry=False):
 
         # set headers
         # perform patch request
-        r = self.session.patch(url, json=[data], headers=self.request_headers)
+        r = self.session.patch(url, json=[data], params=params, headers=self.request_headers,
+                               proxies=self.proxies)
         self.update_token(r)
 
         if r.status_code == 403:
@@ -922,7 +932,7 @@ def get_items(self, page=0, size=20):
         r = self.api_get(url, params=params)
         r_json = parse_json(response=r)
         if '_embedded' in r_json:
-            if 'collections' in r_json['_embedded']:
+            if 'items' in r_json['_embedded']:
                 for item_resource in r_json['_embedded']['items']:
                     items.append(Item(item_resource))
         elif 'uuid' in r_json:

dspace_rest_client/models.py

@@ -21,6 +21,7 @@ class HALResource:
     Base class to represent HAL+JSON API resources
     """
     links = {}
+    embedded = {}
     type = None
 
     def __init__(self, api_resource=None):
@@ -29,6 +30,7 @@ def __init__(self, api_resource=None):
         @param api_resource: optional API resource (JSON) from a GET response or successful POST can populate instance
         """
         self._from_d = None
+        self.embedded = {}
         if api_resource is not None:
             self._from_d = api_resource
             if 'type' in api_resource:
@@ -37,6 +39,8 @@ def __init__(self, api_resource=None):
                 self.links = api_resource['_links'].copy()
             else:
                 self.links = {'self': {'href': None}}
+            if '_embedded' in api_resource:
+                self.embedded = api_resource['_embedded'].copy()
 
 class AddressableHALResource(HALResource):
     id = None
@@ -421,12 +425,12 @@ class User(SimpleDSpaceObject):
     Extends DSpaceObject to implement specific attributes and methods for users (aka. EPersons)
     """
     type = 'user'
-    name = None,
-    netid = None,
-    lastActive = None,
-    canLogIn = False,
-    email = None,
-    requireCertificate = False,
+    name = None
+    netid = None
+    lastActive = None
+    canLogIn = False
+    email = None
+    requireCertificate = False
     selfRegistered = False
 
     def __init__(self, api_resource=None):
@@ -473,11 +477,11 @@ def __init__(self, api_resource):
         if 'lastModified' in api_resource:
             self.lastModified = api_resource['lastModified']
         if 'step' in api_resource:
-            self.step = api_resource['lastModified']
+            self.step = api_resource['step']
         if 'sections' in api_resource:
             self.sections = api_resource['sections'].copy()
         if 'type' in api_resource:
-            self.lastModified = api_resource['lastModified']
+            self.type = api_resource['type']
 
     def as_dict(self):
         parent_dict = super(InProgressSubmission, self).as_dict()
@@ -508,7 +512,7 @@ def __init__(self, api_resource):
         if 'label' in api_resource:
             self.label = api_resource['label']
         if 'type' in api_resource:
-            self.label = api_resource['type']
+            self.type = api_resource['type']
 
 class RelationshipType(AddressableHALResource):
     """