feat: detect exact copies via MD5 hash, separate from perceptual duplicates

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

analyzer.py

@@ -33,6 +33,28 @@ def is_underexposed(path: str, threshold: float = 30.0) -> bool:
     return _mean_brightness(path) < threshold
 
 
+def find_exact_copies(paths: List[str]) -> List[List[str]]:
+    """
+    Findet exakte Kopien anhand von MD5-Hash (byte-identische Dateien).
+    Das erste Element jeder Gruppe gilt als Original, der Rest als Kopien.
+    """
+    import hashlib
+
+    hashes: dict = {}
+    for path in paths:
+        try:
+            h = hashlib.md5()
+            with open(path, "rb") as f:
+                for chunk in iter(lambda: f.read(65536), b""):
+                    h.update(chunk)
+            digest = h.hexdigest()
+            hashes.setdefault(digest, []).append(path)
+        except Exception:
+            continue
+
+    return [group for group in hashes.values() if len(group) > 1]
+
+
 def find_duplicates(paths: List[str], threshold: int = 8) -> List[List[str]]:
     """
     Findet Gruppen aehnlicher Bilder via perceptual hashing.
@@ -155,7 +177,16 @@ def analyze_folder(
         except Exception:
             continue
 
-    dup_groups = find_duplicates(paths, dup_threshold)
+    exact_copy_paths: set = set()
+    exact_groups = find_exact_copies(paths)
+    for group in exact_groups:
+        original = os.path.basename(group[0])
+        for copy_path in group[1:]:
+            results[copy_path].append(f"exakte Kopie von {original}")
+            exact_copy_paths.add(copy_path)
+
+    dup_paths = [p for p in paths if p not in exact_copy_paths]
+    dup_groups = find_duplicates(dup_paths, dup_threshold)
     for group in dup_groups:
         original = os.path.basename(group[0])
         for dup_path in group[1:]: