Fix technique (#18)

* fix case issue #14

* fix issue causing failure due to url length limit #17

src/parser.py

@@ -89,6 +89,7 @@ def process_tags_and_labels(cls, data: dict):
             if value := data.get(key):
                 references.append(dict(source_name='sigma-rule', external_id=key, description=value))
         for tag in data.get('tags', []):
+            tag = tag.lower()
             if match := re.match(r'detection\.(.*)', tag):
                 references.append(dict(source_name='sigma-rule', external_id='detection', description=match.group(1)))
             elif match := re.match(r'(cve\..*)', tag):

src/retriever.py

@@ -23,12 +23,15 @@ def get_attack_objects(self, matrix, attack_id):
         return self._retrieve_objects(endpoint)
 
     def get_objects_by_external_ids(self, ids, type, key='objects', query_filter='id'):
-        objects = self._retrieve_objects(urljoin(self.api_root, f"v1/{type}/objects/?{query_filter}={','.join(ids)}"), key)
         objects_map : dict[str, list[dict]] = {}
-        for obj in objects:
-            object_id = obj['external_references'][0]['external_id']
-            arr = objects_map.setdefault(object_id, [])
-            arr.append(obj)
+        ids = list(set(ids))
+
+        for chunked_ids in chunked(ids, 100):
+            objects = self._retrieve_objects(urljoin(self.api_root, f"v1/{type}/objects/?{query_filter}={','.join(chunked_ids)}"), key)
+            for obj in objects:
+                object_id = obj['external_references'][0]['external_id']
+                arr = objects_map.setdefault(object_id, [])
+                arr.append(obj)
         return objects_map
 
     def get_attack_tactics(self, matrix):
@@ -61,4 +64,10 @@ def _retrieve_objects(self, endpoint, key='objects'):
             if d['page_results_count'] < d['page_size']:
                 break
         return data
-
+
+
+def chunked(iterable, n):
+    if not iterable:
+        return []
+    for i in range(0, len(iterable), n):
+        yield iterable[i : i + n]