ingestion: group oversize and binary rejections in the report

corpus/sources/estate.py

@@ -54,7 +54,14 @@ class Harvest:
     def rejection_summary(self) -> dict:
         counts = {}
         for row in self.rejections:
-            key = f"{row.get('platform')}/{row.get('reason')}"
+            reason = str(row.get("reason") or "unknown")
+            # Keep the summary readable: 200 distinct oversize byte counts are
+            # one finding, not two hundred.
+            if reason.startswith("oversize"):
+                reason = "oversize"
+            elif reason.startswith("binary"):
+                reason = "binary"
+            key = f"{row.get('platform')}/{reason}"
             counts[key] = counts.get(key, 0) + 1
         return dict(sorted(counts.items()))