US07-04: Prove Concurrency and Crash Recovery (#86)

photo_pipeline/integrations/exiftool.py

@@ -17,6 +17,20 @@ import os
 import subprocess
 from collections.abc import Iterable
 
+# A hung exiftool must not hang the worker with it: every call is bounded, and a
+# call that runs out of time is treated exactly like a failed one — no metadata
+# answer, nothing marked verified (US07-04). The knob exists because "slow" is a
+# property of the machine, not of the code: huge files on a slow network volume
+# legitimately take longer than the default.
+DEFAULT_TIMEOUT_SECONDS = 120.0
+
+
+def _timeout() -> float:
+    try:
+        return float(os.environ.get("PHOTO_PIPELINE_EXIFTOOL_TIMEOUT", DEFAULT_TIMEOUT_SECONDS))
+    except ValueError:
+        return DEFAULT_TIMEOUT_SECONDS
+
 
 def read_keyword_sets(paths: Iterable[str]) -> dict[str, set[str]]:
     """Map each path to its lowercased set of ``Keywords`` + ``Subject`` values.
@@ -34,8 +48,9 @@ def read_keyword_sets(paths: Iterable[str]) -> dict[str, set[str]]:
             input="\n".join(paths),
             capture_output=True,
             text=True,
+            timeout=_timeout(),
         )
-    except FileNotFoundError:
+    except (FileNotFoundError, subprocess.TimeoutExpired):
         return {}
     out: dict[str, set[str]] = {}
     try:
@@ -67,9 +82,12 @@ def read_all(path: str) -> dict | None:
     """
     try:
         result = subprocess.run(
-            ["exiftool", "-m", "-j", "-G0:1", path], capture_output=True, text=True
+            ["exiftool", "-m", "-j", "-G0:1", path],
+            capture_output=True,
+            text=True,
+            timeout=_timeout(),
         )
-    except FileNotFoundError:
+    except (FileNotFoundError, subprocess.TimeoutExpired):
         return None
     try:
         records = json.loads(result.stdout or "[]")
@@ -91,4 +109,10 @@ def apply_keywords(path: str, *, add: Iterable[str] = (), remove: Iterable[str]
     if len(args) == 3:
         return True
     args.append(path)
-    return subprocess.run(args, capture_output=True, text=True).returncode == 0
+    try:
+        return subprocess.run(
+            args, capture_output=True, text=True, timeout=_timeout()
+        ).returncode == 0
+    except (FileNotFoundError, subprocess.TimeoutExpired):
+        # A write that never returned is not a write that succeeded.
+        return False