Add support for user based default access

Author: krakan

docs/manual/access-control.rst

@@ -151,6 +151,26 @@ For example, this header may be set based on IP range, or based on password auth
 
 Further examples of how to set this header will be provided in the deployments section.
 
+One may also specify default access for different users by adding sub keys to the ``default_access`` setting::
+
+  collections:
+       test:
+           ...
+           default_access:
+               default: block
+               admin: allow
+
+Note that the ``default`` entry will be applied both if the user name is empty and if it actually is ``default``.
+If the ``default`` entry is missing, it will be assumed to be ``allow``::
+
+  collections:
+       test:
+           ...
+           default_access:
+               guest: block
+
+This works whether the ``default_access`` is specified at the top level or for a specific collection.
+
 **Note: Do not use the user-based rules without configuring proper authentication on an Apache or Nginx frontend to set or remove this header, otherwise the 'X-Pywb-ACL-User' can easily be faked.**
 
 See the :ref:`config-acl-header` section in Usage for examples on how to configure this header.

pywb/warcserver/access_checker.py

@@ -107,6 +107,10 @@ def __init__(self, access_source, default_access='allow', embargo=None):
         self.default_rule['access'] = default_access
         self.default_rule['default'] = 'true'
 
+        if isinstance(self.default_rule['access'], dict):
+            if 'default' not in self.default_rule['access']:
+                self.default_rule['access']['default'] = 'allow'
+
         self.embargo = self.parse_embargo(embargo)
 
     def parse_embargo(self, embargo):
@@ -273,7 +277,17 @@ def find_access_rule(self, url, ts=None, urlkey=None, collection=None, acl_user=
             if acl_key < tld:
                 break
 
-        return last_obj if last_obj else self.default_rule
+
+        if last_obj:
+            return last_obj
+
+        if isinstance(self.default_rule['access'], dict):
+            default_rule = dict(self.default_rule)
+            user = acl_user if acl_user in default_rule['access'] else 'default'
+            default_rule['access'] = default_rule['access'][user]
+            return default_rule
+
+        return self.default_rule
 
     def __call__(self, res, acl_user):
         """Wraps the cdx iter in the supplied tuple returning a
@@ -334,6 +348,9 @@ def wrap_iter(self, cdx_iter, acl_user):
             if not access:
                 access = self.default_rule['access']
 
+            if isinstance(access, dict):
+                access = self.default_rule['access']['default']
+
             if access == 'allow_ignore_embargo':
                 access = 'allow'
 

tests/config_test_access.yaml

@@ -6,7 +6,8 @@ collections:
         archive_paths: ./sample_archive/warcs/
         acl_paths: ./sample_archive/access/pywb.aclj
 
-        default_access: block
+        default_access:
+            default: block
 
     pywb-acl-list:
         index_paths: ./sample_archive/cdx/
@@ -62,6 +63,12 @@ collections:
         acl_paths:
             - ./sample_archive/access/pywb.aclj
 
+    pywb-acl-user-default:
+        index_paths: ./sample_archive/cdx/
+        archive_paths: ./sample_archive/warcs/
+        acl_paths: ./sample_archive/access/user-default.aclj
 
+        default_access:
+            staff2: block
 
 

tests/test_acl.py

@@ -96,5 +96,12 @@ def test_allowed_different_coll_acl_dir(self):
 
         assert '"http://httpbin.org/anything/resource.json"' in resp.text
 
+    def test_user_default(self):
+        headers = {"X-Pywb-ACL-User": "staff"}
+        self.testapp.get('/pywb-acl-user-default/mp_/http://www.iana.org/', headers=headers, status=200)
+        self.testapp.get('/pywb-acl-user-default/mp_/http://www.example.com/', headers=headers, status=451)
+        headers = {"X-Pywb-ACL-User": "staff2"}
+        self.testapp.get('/pywb-acl-user-default/mp_/http://www.iana.org/', headers=headers, status=451)
+        self.testapp.get('/pywb-acl-user-default/mp_/http://www.example.com/', headers=headers, status=200)