summary refs log tree commit diff
path: root/tests/push
diff options
context:
space:
mode:
authorRichard van der Hoff <1389908+richvdh@users.noreply.github.com>2021-05-11 10:47:23 +0100
committerGitHub <noreply@github.com>2021-05-11 11:47:23 +0200
commit03318a766cac9f8b053db2214d9c332a977d226c (patch)
tree3444111943cbfda45609535c83e53f9adede3a90 /tests/push
parentUnpin attrs dep after new version has been released (#9946) (diff)
downloadsynapse-03318a766cac9f8b053db2214d9c332a977d226c.tar.xz
Merge pull request from GHSA-x345-32rc-8h85
* tests for push rule pattern matching

* tests for acl pattern matching

* factor out common `re.escape`

* Factor out common re.compile

* Factor out common anchoring code

* add word_boundary support to `glob_to_regex`

* Use `glob_to_regex` in push rule evaluator

NB that this drops support for character classes. I don't think anyone ever
used them.

* Improve efficiency of globs with multiple wildcards

The idea here is that we compress multiple `*` globs into a single `.*`. We
also need to consider `?`, since `*?*` is as hard to implement efficiently as
`**`.

* add assertion on regex pattern

* Fix mypy

* Simplify glob_to_regex

* Inline the glob_to_regex helper function

Signed-off-by: Dan Callahan <danc@element.io>

* Moar comments

Signed-off-by: Dan Callahan <danc@element.io>

Co-authored-by: Dan Callahan <danc@element.io>
Diffstat (limited to 'tests/push')
-rw-r--r--tests/push/test_push_rule_evaluator.py166
1 files changed, 166 insertions, 0 deletions
diff --git a/tests/push/test_push_rule_evaluator.py b/tests/push/test_push_rule_evaluator.py
index 45906ce720..a52e89e407 100644
--- a/tests/push/test_push_rule_evaluator.py
+++ b/tests/push/test_push_rule_evaluator.py
@@ -12,6 +12,8 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+from typing import Any, Dict
+
 from synapse.api.room_versions import RoomVersions
 from synapse.events import FrozenEvent
 from synapse.push import push_rule_evaluator
@@ -66,6 +68,170 @@ class PushRuleEvaluatorTestCase(unittest.TestCase):
         # A display name with spaces should work fine.
         self.assertTrue(evaluator.matches(condition, "@user:test", "foo bar"))
 
+    def _assert_matches(
+        self, condition: Dict[str, Any], content: Dict[str, Any], msg=None
+    ) -> None:
+        evaluator = self._get_evaluator(content)
+        self.assertTrue(evaluator.matches(condition, "@user:test", "display_name"), msg)
+
+    def _assert_not_matches(
+        self, condition: Dict[str, Any], content: Dict[str, Any], msg=None
+    ) -> None:
+        evaluator = self._get_evaluator(content)
+        self.assertFalse(
+            evaluator.matches(condition, "@user:test", "display_name"), msg
+        )
+
+    def test_event_match_body(self):
+        """Check that event_match conditions on content.body work as expected"""
+
+        # if the key is `content.body`, the pattern matches substrings.
+
+        # non-wildcards should match
+        condition = {
+            "kind": "event_match",
+            "key": "content.body",
+            "pattern": "foobaz",
+        }
+        self._assert_matches(
+            condition,
+            {"body": "aaa FoobaZ zzz"},
+            "patterns should match and be case-insensitive",
+        )
+        self._assert_not_matches(
+            condition,
+            {"body": "aa xFoobaZ yy"},
+            "pattern should only match at word boundaries",
+        )
+        self._assert_not_matches(
+            condition,
+            {"body": "aa foobazx yy"},
+            "pattern should only match at word boundaries",
+        )
+
+        # wildcards should match
+        condition = {
+            "kind": "event_match",
+            "key": "content.body",
+            "pattern": "f?o*baz",
+        }
+
+        self._assert_matches(
+            condition,
+            {"body": "aaa FoobarbaZ zzz"},
+            "* should match string and pattern should be case-insensitive",
+        )
+        self._assert_matches(
+            condition, {"body": "aa foobaz yy"}, "* should match 0 characters"
+        )
+        self._assert_not_matches(
+            condition, {"body": "aa fobbaz yy"}, "? should not match 0 characters"
+        )
+        self._assert_not_matches(
+            condition, {"body": "aa fiiobaz yy"}, "? should not match 2 characters"
+        )
+        self._assert_not_matches(
+            condition,
+            {"body": "aa xfooxbaz yy"},
+            "pattern should only match at word boundaries",
+        )
+        self._assert_not_matches(
+            condition,
+            {"body": "aa fooxbazx yy"},
+            "pattern should only match at word boundaries",
+        )
+
+        # test backslashes
+        condition = {
+            "kind": "event_match",
+            "key": "content.body",
+            "pattern": r"f\oobaz",
+        }
+        self._assert_matches(
+            condition,
+            {"body": r"F\oobaz"},
+            "backslash should match itself",
+        )
+        condition = {
+            "kind": "event_match",
+            "key": "content.body",
+            "pattern": r"f\?obaz",
+        }
+        self._assert_matches(
+            condition,
+            {"body": r"F\oobaz"},
+            r"? after \ should match any character",
+        )
+
+    def test_event_match_non_body(self):
+        """Check that event_match conditions on other keys work as expected"""
+
+        # if the key is anything other than 'content.body', the pattern must match the
+        # whole value.
+
+        # non-wildcards should match
+        condition = {
+            "kind": "event_match",
+            "key": "content.value",
+            "pattern": "foobaz",
+        }
+        self._assert_matches(
+            condition,
+            {"value": "FoobaZ"},
+            "patterns should match and be case-insensitive",
+        )
+        self._assert_not_matches(
+            condition,
+            {"value": "xFoobaZ"},
+            "pattern should only match at the start/end of the value",
+        )
+        self._assert_not_matches(
+            condition,
+            {"value": "FoobaZz"},
+            "pattern should only match at the start/end of the value",
+        )
+
+        # wildcards should match
+        condition = {
+            "kind": "event_match",
+            "key": "content.value",
+            "pattern": "f?o*baz",
+        }
+        self._assert_matches(
+            condition,
+            {"value": "FoobarbaZ"},
+            "* should match string and pattern should be case-insensitive",
+        )
+        self._assert_matches(
+            condition, {"value": "foobaz"}, "* should match 0 characters"
+        )
+        self._assert_not_matches(
+            condition, {"value": "fobbaz"}, "? should not match 0 characters"
+        )
+        self._assert_not_matches(
+            condition, {"value": "fiiobaz"}, "? should not match 2 characters"
+        )
+        self._assert_not_matches(
+            condition,
+            {"value": "xfooxbaz"},
+            "pattern should only match at the start/end of the value",
+        )
+        self._assert_not_matches(
+            condition,
+            {"value": "fooxbazx"},
+            "pattern should only match at the start/end of the value",
+        )
+        self._assert_not_matches(
+            condition,
+            {"value": "x\nfooxbaz"},
+            "pattern should not match after a newline",
+        )
+        self._assert_not_matches(
+            condition,
+            {"value": "fooxbaz\nx"},
+            "pattern should not match before a newline",
+        )
+
     def test_no_body(self):
         """Not having a body shouldn't break the evaluator."""
         evaluator = self._get_evaluator({})