Merge branch 'master' into feat/1755

CHANGELOG.md

@@ -9,6 +9,7 @@
 - document Antivirus warnings and VirusTotal false positive detections #2028 @RionEV @mr-tz
 - render maec/* fields #843 @s-ff
 - replace Halo spinner with Rich #2086 @s-ff
+- optimize rule matching #2080 @williballenthin
 
 ### Breaking Changes
 

capa/engine.py

@@ -270,6 +270,14 @@ def evaluate(self, features: FeatureSet, short_circuit=True):
 MatchResults = Mapping[str, List[Tuple[Address, Result]]]
 
 
+def get_rule_namespaces(rule: "capa.rules.Rule") -> Iterator[str]:
+    namespace = rule.meta.get("namespace")
+    if namespace:
+        while namespace:
+            yield namespace
+            namespace, _, _ = namespace.rpartition("/")
+
+
 def index_rule_matches(features: FeatureSet, rule: "capa.rules.Rule", locations: Iterable[Address]):
     """
     record into the given featureset that the given rule matched at the given locations.
@@ -280,11 +288,8 @@ def index_rule_matches(features: FeatureSet, rule: "capa.rules.Rule", locations:
     updates `features` in-place. doesn't modify the remaining arguments.
     """
     features[capa.features.common.MatchedRule(rule.name)].update(locations)
-    namespace = rule.meta.get("namespace")
-    if namespace:
-        while namespace:
-            features[capa.features.common.MatchedRule(namespace)].update(locations)
-            namespace, _, _ = namespace.rpartition("/")
+    for namespace in get_rule_namespaces(rule):
+        features[capa.features.common.MatchedRule(namespace)].update(locations)
 
 
 def match(rules: List["capa.rules.Rule"], features: FeatureSet, addr: Address) -> Tuple[FeatureSet, MatchResults]:

capa/features/common.py

@@ -385,10 +385,12 @@ def __init__(self, value: bytes, description=None):
         self.value = value
 
     def evaluate(self, features: "capa.engine.FeatureSet", short_circuit=True):
+        assert isinstance(self.value, bytes)
+
         capa.perf.counters["evaluate.feature"] += 1
         capa.perf.counters["evaluate.feature.bytes"] += 1
+        capa.perf.counters["evaluate.feature.bytes." + str(len(self.value))] += 1
 
-        assert isinstance(self.value, bytes)
         for feature, locations in features.items():
             if not isinstance(feature, (Bytes,)):
                 continue
@@ -490,6 +492,6 @@ def __init__(self, value: str, description=None):
 def is_global_feature(feature):
     """
     is this a feature that is extracted at every scope?
-    today, these are OS and arch features.
+    today, these are OS, arch, and format features.
     """
-    return isinstance(feature, (OS, Arch))
+    return isinstance(feature, (OS, Arch, Format))