From 7bd2579022c527ba316a8f7a9fc1ab54a71eec27 Mon Sep 17 00:00:00 2001
From: Abdessamad Derraz <3028866+Abdess@users.noreply.github.com>
Date: Sun, 18 Oct 2026 08:41:32 +0200
Subject: [PATCH] fix: stop calling a held file its own duplicate

---
 scripts/validate_pr.py    | 16 +++++++++++++---
 tests/test_validate_pr.py | 11 +++++++++++
 2 files changed, 24 insertions(+), 3 deletions(-)

diff --git a/scripts/validate_pr.py b/scripts/validate_pr.py
index f2b915d8..b801d533 100644
--- a/scripts/validate_pr.py
+++ b/scripts/validate_pr.py
@@ -210,9 +210,19 @@ def validate_file(
     if db:
         if result.sha1 in db.get("files", {}):
             existing = db["files"][result.sha1]
-            result.add_warning(
-                f"Duplicate: identical file already exists at `{existing['path']}`"
-            )
+            held_at = {
+                os.path.normpath(p)
+                for p in [existing.get("path"), *(existing.get("paths") or [])] if p
+            }
+            if os.path.normpath(filepath) in held_at:
+                # The file the database was built from, not a copy of it: a
+                # PR that regenerated database.json was told each new file
+                # duplicated itself.
+                result.add_check(True, "Already in the database at this path")
+            else:
+                result.add_warning(
+                    f"Duplicate: identical file already exists at `{existing['path']}`"
+                )
         else:
             result.add_check(True, "Not a duplicate in database")
 
diff --git a/tests/test_validate_pr.py b/tests/test_validate_pr.py
index 43127578..65f4d3f2 100644
--- a/tests/test_validate_pr.py
+++ b/tests/test_validate_pr.py
@@ -184,6 +184,17 @@ class HashRecognition(_Fixture):
         self.assertTrue(validate_pr.validate_file(rel, db, EMPTY_HASHES).passed)
 
 
+    def test_the_file_the_database_holds_is_not_its_own_duplicate(self):
+        """The documented example on a tracked file warned "Duplicate:
+        identical file already exists at" the very path being validated."""
+        rel = self._bios_file("bios/Sony/PS/held.bin")
+        probe = validate_pr.validate_file(rel, None, EMPTY_HASHES)
+        db = {"files": {probe.sha1: {"path": rel}}}
+        markdown = validate_pr.validate_file(rel, db, EMPTY_HASHES).to_markdown()
+        self.assertNotIn("Duplicate", markdown)
+        self.assertIn("Already in the database at this path", markdown)
+
+
 class Placement(_Fixture):
     def test_manufacturer_and_console_directories_are_accepted(self):
         rel = self._bios_file("bios/Sega/Saturn/sega_101.bin")