US07-03: Harden Media and Metadata Edge Cases

photo_pipeline/integrations/exiftool.py

@@ -56,6 +56,30 @@ def read_keyword_sets(paths: Iterable[str]) -> dict[str, set[str]]:
     return out
 
 
+def read_all(path: str) -> dict | None:
+    """Every tag exiftool can read from ``path``, or ``None`` when it cannot answer.
+
+    This is the snapshot an EXIF checkpoint compares against: proving that a write
+    preserved the fields it does not own requires knowing all of them, not just the
+    ones being written (US07-03). ``None`` (exiftool missing, unreadable file,
+    unparsable output) is not an empty snapshot — a caller must not read it as
+    "nothing was there".
+    """
+    try:
+        result = subprocess.run(
+            ["exiftool", "-m", "-j", "-G0:1", path], capture_output=True, text=True
+        )
+    except FileNotFoundError:
+        return None
+    try:
+        records = json.loads(result.stdout or "[]")
+    except ValueError:
+        return None
+    if not records:
+        return None
+    return {k: v for k, v in records[0].items() if k != "SourceFile"}
+
+
 def apply_keywords(path: str, *, add: Iterable[str] = (), remove: Iterable[str] = ()) -> bool:
     """Idempotently add/remove keywords in Keywords + Subject; preserve all else."""
     args = ["exiftool", "-m", "-overwrite_original"]