Add duplicate audio hash detection

tests/test_hashing.py

@@ -0,0 +1,25 @@
+from serato_doctor.hashing import compare_audio_files, sha256_file
+
+
+def test_equal_files_have_the_same_hash(tmp_path):
+    first = tmp_path / "First.mp3"
+    second = tmp_path / "Second.mp3"
+    first.write_bytes(b"same audio bytes")
+    second.write_bytes(b"same audio bytes")
+
+    result = compare_audio_files((first, second))
+
+    assert result["status"] == "identical"
+    assert sha256_file(first) == sha256_file(second)
+
+
+def test_different_files_are_not_reported_as_identical(tmp_path):
+    first = tmp_path / "First.mp3"
+    second = tmp_path / "Second.mp3"
+    first.write_bytes(b"version one")
+    second.write_bytes(b"version two")
+
+    result = compare_audio_files((first, second))
+
+    assert result["status"] == "different"
+    assert result["files"][0]["sha256"] != result["files"][1]["sha256"]

tests/test_web.py

@@ -143,5 +143,6 @@ def test_batch_preview_combines_approved_groups_without_changes(tmp_path):
     assert len(result["replaced"]) == 2
     assert len(result["decisions"]) == 2
     assert result["decisions"][0]["keeper"].endswith("First.mp3")
+    assert result["decisions"][0]["hash_status"] == "different"
     assert len(result["decisions"][0]["replaced"]) == 1
     assert all(not Path(choice["group_files"][1]).is_symlink() for choice in choices)