Merge branch 'develop' of github.com:matrix-org/synapse into erikj/cleanup_user_ips_2

3 files changed, 185 insertions, 61 deletions

diff --git a/synapse/config/registration.py b/synapse/config/registration.py
index d4654e99b3..bef89e2bf4 100644
--- a/synapse/config/registration.py
+++ b/synapse/config/registration.py
@@ -293,6 +293,8 @@ class RegistrationConfig(Config):
         # by the Matrix Identity Service API specification:
         # https://matrix.org/docs/spec/identity_service/latest
         #
+        # If a delegate is specified, the config option public_baseurl must also be filled out.
+        #
         account_threepid_delegates:
             #email: https://example.com     # Delegate email sending to example.org
             #msisdn: http://localhost:8090  # Delegate SMS sending to this local process
diff --git a/synapse/config/saml2_config.py b/synapse/config/saml2_config.py
index 6a8161547a..ab34b41ca8 100644
--- a/synapse/config/saml2_config.py
+++ b/synapse/config/saml2_config.py
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # Copyright 2018 New Vector Ltd
+# Copyright 2019 The Matrix.org Foundation C.I.C.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -12,11 +13,47 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+
+import re
+
 from synapse.python_dependencies import DependencyException, check_requirements
+from synapse.types import (
+    map_username_to_mxid_localpart,
+    mxid_localpart_allowed_characters,
+)
+from synapse.util.module_loader import load_python_module
 
 from ._base import Config, ConfigError
 
 
+def _dict_merge(merge_dict, into_dict):
+    """Do a deep merge of two dicts
+
+    Recursively merges `merge_dict` into `into_dict`:
+      * For keys where both `merge_dict` and `into_dict` have a dict value, the values
+        are recursively merged
+      * For all other keys, the values in `into_dict` (if any) are overwritten with
+        the value from `merge_dict`.
+
+    Args:
+        merge_dict (dict): dict to merge
+        into_dict (dict): target dict
+    """
+    for k, v in merge_dict.items():
+        if k not in into_dict:
+            into_dict[k] = v
+            continue
+
+        current_val = into_dict[k]
+
+        if isinstance(v, dict) and isinstance(current_val, dict):
+            _dict_merge(v, current_val)
+            continue
+
+        # otherwise we just overwrite
+        into_dict[k] = v
+
+
 class SAML2Config(Config):
     def read_config(self, config, **kwargs):
         self.saml2_enabled = False
@@ -26,6 +63,9 @@ class SAML2Config(Config):
         if not saml2_config or not saml2_config.get("enabled", True):
             return
 
+        if not saml2_config.get("sp_config") and not saml2_config.get("config_path"):
+            return
+
         try:
             check_requirements("saml2")
         except DependencyException as e:
@@ -33,21 +73,40 @@ class SAML2Config(Config):
 
         self.saml2_enabled = True
 
-        import saml2.config
+        self.saml2_mxid_source_attribute = saml2_config.get(
+            "mxid_source_attribute", "uid"
+        )
 
-        self.saml2_sp_config = saml2.config.SPConfig()
-        self.saml2_sp_config.load(self._default_saml_config_dict())
-        self.saml2_sp_config.load(saml2_config.get("sp_config", {}))
+        self.saml2_grandfathered_mxid_source_attribute = saml2_config.get(
+            "grandfathered_mxid_source_attribute", "uid"
+        )
+
+        saml2_config_dict = self._default_saml_config_dict()
+        _dict_merge(
+            merge_dict=saml2_config.get("sp_config", {}), into_dict=saml2_config_dict
+        )
 
         config_path = saml2_config.get("config_path", None)
         if config_path is not None:
-            self.saml2_sp_config.load_file(config_path)
+            mod = load_python_module(config_path)
+            _dict_merge(merge_dict=mod.CONFIG, into_dict=saml2_config_dict)
+
+        import saml2.config
+
+        self.saml2_sp_config = saml2.config.SPConfig()
+        self.saml2_sp_config.load(saml2_config_dict)
 
         # session lifetime: in milliseconds
         self.saml2_session_lifetime = self.parse_duration(
             saml2_config.get("saml_session_lifetime", "5m")
         )
 
+        mapping = saml2_config.get("mxid_mapping", "hexencode")
+        try:
+            self.saml2_mxid_mapper = MXID_MAPPER_MAP[mapping]
+        except KeyError:
+            raise ConfigError("%s is not a known mxid_mapping" % (mapping,))
+
     def _default_saml_config_dict(self):
         import saml2
 
@@ -55,6 +114,13 @@ class SAML2Config(Config):
         if public_baseurl is None:
             raise ConfigError("saml2_config requires a public_baseurl to be set")
 
+        required_attributes = {"uid", self.saml2_mxid_source_attribute}
+
+        optional_attributes = {"displayName"}
+        if self.saml2_grandfathered_mxid_source_attribute:
+            optional_attributes.add(self.saml2_grandfathered_mxid_source_attribute)
+        optional_attributes -= required_attributes
+
         metadata_url = public_baseurl + "_matrix/saml2/metadata.xml"
         response_url = public_baseurl + "_matrix/saml2/authn_response"
         return {
@@ -66,8 +132,9 @@ class SAML2Config(Config):
                             (response_url, saml2.BINDING_HTTP_POST)
                         ]
                     },
-                    "required_attributes": ["uid"],
-                    "optional_attributes": ["mail", "surname", "givenname"],
+                    "required_attributes": list(required_attributes),
+                    "optional_attributes": list(optional_attributes),
+                    # "name_id_format": saml2.saml.NAMEID_FORMAT_PERSISTENT,
                 }
             },
         }
@@ -76,12 +143,13 @@ class SAML2Config(Config):
         return """\
         # Enable SAML2 for registration and login. Uses pysaml2.
         #
-        # `sp_config` is the configuration for the pysaml2 Service Provider.
-        # See pysaml2 docs for format of config.
+        # At least one of `sp_config` or `config_path` must be set in this section to
+        # enable SAML login.
         #
-        # Default values will be used for the 'entityid' and 'service' settings,
-        # so it is not normally necessary to specify them unless you need to
-        # override them.
+        # (You will probably also want to set the following options to `false` to
+        # disable the regular login/registration flows:
+        #   * enable_registration
+        #   * password_config.enabled
         #
         # Once SAML support is enabled, a metadata file will be exposed at
         # https://<server>:<port>/_matrix/saml2/metadata.xml, which you may be able to
@@ -89,52 +157,105 @@ class SAML2Config(Config):
         # the IdP to use an ACS location of
         # https://<server>:<port>/_matrix/saml2/authn_response.
         #
-        #saml2_config:
-        #  sp_config:
-        #    # point this to the IdP's metadata. You can use either a local file or
-        #    # (preferably) a URL.
-        #    metadata:
-        #      #local: ["saml2/idp.xml"]
-        #      remote:
-        #        - url: https://our_idp/metadata.xml
-        #
-        #    # By default, the user has to go to our login page first. If you'd like to
-        #    # allow IdP-initiated login, set 'allow_unsolicited: True' in a
-        #    # 'service.sp' section:
-        #    #
-        #    #service:
-        #    #  sp:
-        #    #    allow_unsolicited: True
-        #
-        #    # The examples below are just used to generate our metadata xml, and you
-        #    # may well not need it, depending on your setup. Alternatively you
-        #    # may need a whole lot more detail - see the pysaml2 docs!
-        #
-        #    description: ["My awesome SP", "en"]
-        #    name: ["Test SP", "en"]
-        #
-        #    organization:
-        #      name: Example com
-        #      display_name:
-        #        - ["Example co", "en"]
-        #      url: "http://example.com"
-        #
-        #    contact_person:
-        #      - given_name: Bob
-        #        sur_name: "the Sysadmin"
-        #        email_address": ["admin@example.com"]
-        #        contact_type": technical
-        #
-        #  # Instead of putting the config inline as above, you can specify a
-        #  # separate pysaml2 configuration file:
-        #  #
-        #  config_path: "%(config_dir_path)s/sp_conf.py"
-        #
-        #  # the lifetime of a SAML session. This defines how long a user has to
-        #  # complete the authentication process, if allow_unsolicited is unset.
-        #  # The default is 5 minutes.
-        #  #
-        #  # saml_session_lifetime: 5m
+        saml2_config:
+          # `sp_config` is the configuration for the pysaml2 Service Provider.
+          # See pysaml2 docs for format of config.
+          #
+          # Default values will be used for the 'entityid' and 'service' settings,
+          # so it is not normally necessary to specify them unless you need to
+          # override them.
+          #
+          #sp_config:
+          #  # point this to the IdP's metadata. You can use either a local file or
+          #  # (preferably) a URL.
+          #  metadata:
+          #    #local: ["saml2/idp.xml"]
+          #    remote:
+          #      - url: https://our_idp/metadata.xml
+          #
+          #    # By default, the user has to go to our login page first. If you'd like
+          #    # to allow IdP-initiated login, set 'allow_unsolicited: True' in a
+          #    # 'service.sp' section:
+          #    #
+          #    #service:
+          #    #  sp:
+          #    #    allow_unsolicited: true
+          #
+          #    # The examples below are just used to generate our metadata xml, and you
+          #    # may well not need them, depending on your setup. Alternatively you
+          #    # may need a whole lot more detail - see the pysaml2 docs!
+          #
+          #    description: ["My awesome SP", "en"]
+          #    name: ["Test SP", "en"]
+          #
+          #    organization:
+          #      name: Example com
+          #      display_name:
+          #        - ["Example co", "en"]
+          #      url: "http://example.com"
+          #
+          #    contact_person:
+          #      - given_name: Bob
+          #        sur_name: "the Sysadmin"
+          #        email_address": ["admin@example.com"]
+          #        contact_type": technical
+
+          # Instead of putting the config inline as above, you can specify a
+          # separate pysaml2 configuration file:
+          #
+          #config_path: "%(config_dir_path)s/sp_conf.py"
+
+          # the lifetime of a SAML session. This defines how long a user has to
+          # complete the authentication process, if allow_unsolicited is unset.
+          # The default is 5 minutes.
+          #
+          #saml_session_lifetime: 5m
+
+          # The SAML attribute (after mapping via the attribute maps) to use to derive
+          # the Matrix ID from. 'uid' by default.
+          #
+          #mxid_source_attribute: displayName
+
+          # The mapping system to use for mapping the saml attribute onto a matrix ID.
+          # Options include:
+          #  * 'hexencode' (which maps unpermitted characters to '=xx')
+          #  * 'dotreplace' (which replaces unpermitted characters with '.').
+          # The default is 'hexencode'.
+          #
+          #mxid_mapping: dotreplace
+
+          # In previous versions of synapse, the mapping from SAML attribute to MXID was
+          # always calculated dynamically rather than stored in a table. For backwards-
+          # compatibility, we will look for user_ids matching such a pattern before
+          # creating a new account.
+          #
+          # This setting controls the SAML attribute which will be used for this
+          # backwards-compatibility lookup. Typically it should be 'uid', but if the
+          # attribute maps are changed, it may be necessary to change it.
+          #
+          # The default is 'uid'.
+          #
+          #grandfathered_mxid_source_attribute: upn
         """ % {
             "config_dir_path": config_dir_path
         }
+
+
+DOT_REPLACE_PATTERN = re.compile(
+    ("[^%s]" % (re.escape("".join(mxid_localpart_allowed_characters)),))
+)
+
+
+def dot_replace_for_mxid(username: str) -> str:
+    username = username.lower()
+    username = DOT_REPLACE_PATTERN.sub(".", username)
+
+    # regular mxids aren't allowed to start with an underscore either
+    username = re.sub("^_", "", username)
+    return username
+
+
+MXID_MAPPER_MAP = {
+    "hexencode": map_username_to_mxid_localpart,
+    "dotreplace": dot_replace_for_mxid,
+}
diff --git a/synapse/config/server.py b/synapse/config/server.py
index f8b7b4bef9..9d3f1b5bfc 100644
--- a/synapse/config/server.py
+++ b/synapse/config/server.py
@@ -362,10 +362,8 @@ class ServerConfig(Config):
 
         _check_resource_config(self.listeners)
 
-        # An experimental option to try and periodically clean up extremities
-        # by sending dummy events.
         self.cleanup_extremities_with_dummy_events = config.get(
-            "cleanup_extremities_with_dummy_events", False
+            "cleanup_extremities_with_dummy_events", True
         )
 
     def has_tls_listener(self):
@@ -552,6 +550,9 @@ class ServerConfig(Config):
         # blacklist IP address CIDR ranges. If this option is not specified, or
         # specified with an empty list, no ip range blacklist will be enforced.
         #
+        # As of Synapse v1.4.0 this option also affects any outbound requests to identity
+        # servers provided by user input.
+        #
         # (0.0.0.0 and :: are always blacklisted, whether or not they are explicitly
         # listed here, since they correspond to unroutable addresses.)
         #