whole-file sarif-size

bin/sarif-size

@@ -0,0 +1,36 @@
+#!/usr/bin/env python
+import orjson
+import sys
+
+def sizeof(x):
+    t = type(x)
+    if t is dict:
+        return sum(len(k) + sizeof(v) for k, v in x.items())
+    if t is list:
+        return sum(sizeof(v) for v in x)
+    if t is str:
+        return len(x)
+    return 8  # numbers, bools, null
+
+def walk(x, path="root"):
+    if isinstance(x, dict):
+        yield path, sizeof(x)
+        for k,v in x.items():
+            yield from walk(v, f"{path}.{k}")
+    elif isinstance(x, list):
+        yield path, sizeof(x)
+        for i,v in enumerate(x):
+            yield from walk(v, f"{path}[{i}]")
+
+# with open(sys.stdin, 'rb') as f:
+#     data_bytes = f.read()
+
+data_bytes = sys.stdin.buffer.read()
+
+parsed_data = orjson.loads(data_bytes)
+
+sizes = sorted(walk(parsed_data), key=lambda kv: kv[1], reverse=True)
+for p, s in sizes[:50]:
+    print(f"{s:10d}  {p}")
+
+