Port to sortedcontainers (with tests!) (#3332)

synapse/util/caches/stream_change_cache.py

@@ -13,10 +13,10 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from synapse.util.caches import register_cache, CACHE_SIZE_FACTOR
+from synapse.util import caches
 
 
-from blist import sorteddict
+from sortedcontainers import SortedDict
 import logging
 
 
@@ -32,16 +32,18 @@ class StreamChangeCache(object):
     entities that may have changed since that position. If position key is too
     old then the cache will simply return all given entities.
     """
-    def __init__(self, name, current_stream_pos, max_size=10000, prefilled_cache={}):
-        self._max_size = int(max_size * CACHE_SIZE_FACTOR)
+
+    def __init__(self, name, current_stream_pos, max_size=10000, prefilled_cache=None):
+        self._max_size = int(max_size * caches.CACHE_SIZE_FACTOR)
         self._entity_to_key = {}
-        self._cache = sorteddict()
+        self._cache = SortedDict()
         self._earliest_known_stream_pos = current_stream_pos
         self.name = name
-        self.metrics = register_cache("cache", self.name, self._cache)
+        self.metrics = caches.register_cache("cache", self.name, self._cache)
 
-        for entity, stream_pos in prefilled_cache.items():
-            self.entity_has_changed(entity, stream_pos)
+        if prefilled_cache:
+            for entity, stream_pos in prefilled_cache.items():
+                self.entity_has_changed(entity, stream_pos)
 
     def has_entity_changed(self, entity, stream_pos):
         """Returns True if the entity may have been updated since stream_pos
@@ -65,22 +67,25 @@ class StreamChangeCache(object):
         return False
 
     def get_entities_changed(self, entities, stream_pos):
-        """Returns subset of entities that have had new things since the
-        given position. If the position is too old it will just return the given list.
+        """
+        Returns subset of entities that have had new things since the given
+        position.  Entities unknown to the cache will be returned.  If the
+        position is too old it will just return the given list.
         """
         assert type(stream_pos) is int
 
         if stream_pos >= self._earliest_known_stream_pos:
-            keys = self._cache.keys()
-            i = keys.bisect_right(stream_pos)
+            not_known_entities = set(entities) - set(self._entity_to_key)
 
-            result = set(
-                self._cache[k] for k in keys[i:]
-            ).intersection(entities)
+            result = (
+                set(self._cache.values()[self._cache.bisect_right(stream_pos) :])
+                .intersection(entities)
+                .union(not_known_entities)
+            )
 
             self.metrics.inc_hits()
         else:
-            result = entities
+            result = set(entities)
             self.metrics.inc_misses()
 
         return result
@@ -90,12 +95,13 @@ class StreamChangeCache(object):
         """
         assert type(stream_pos) is int
 
+        if not self._cache:
+            # If we have no cache, nothing can have changed.
+            return False
+
         if stream_pos >= self._earliest_known_stream_pos:
             self.metrics.inc_hits()
-            keys = self._cache.keys()
-            i = keys.bisect_right(stream_pos)
-
-            return i < len(keys)
+            return self._cache.bisect_right(stream_pos) < len(self._cache)
         else:
             self.metrics.inc_misses()
             return True
@@ -107,10 +113,7 @@ class StreamChangeCache(object):
         assert type(stream_pos) is int
 
         if stream_pos >= self._earliest_known_stream_pos:
-            keys = self._cache.keys()
-            i = keys.bisect_right(stream_pos)
-
-            return [self._cache[k] for k in keys[i:]]
+            return self._cache.values()[self._cache.bisect_right(stream_pos) :]
         else:
             return None
 
@@ -129,8 +132,10 @@ class StreamChangeCache(object):
             self._entity_to_key[entity] = stream_pos
 
             while len(self._cache) > self._max_size:
-                k, r = self._cache.popitem()
-                self._earliest_known_stream_pos = max(k, self._earliest_known_stream_pos)
+                k, r = self._cache.popitem(0)
+                self._earliest_known_stream_pos = max(
+                    k, self._earliest_known_stream_pos,
+                )
                 self._entity_to_key.pop(r, None)
 
     def get_max_pos_of_last_change(self, entity):