Merge pull request #813 from mapillary/sqlite-cache-error-handling-v2

[mapillary_tools] Handle SQLite database errors gracefully in cache reads

Author: caglarpir

mapillary_tools/history.py

@@ -118,12 +118,21 @@ def get(self, key: str) -> str | None:
 
         s = time.perf_counter()
 
-        with store.KeyValueStore(self._file, flag="r") as db:
+        try:
+            db_ctx = store.KeyValueStore(self._file, flag="r")
+        except sqlite3.DatabaseError as ex:
+            LOG.warning(f"Failed to open cache database: {ex}")
+            return None
+
+        with db_ctx as db:
             try:
                 raw_payload: bytes | None = db.get(key)  # data retrieved from db[key]
             except Exception as ex:
                 if self._table_not_found(ex):
                     return None
+                if isinstance(ex, sqlite3.DatabaseError):
+                    LOG.warning(f"Cache read error for {key}: {ex}")
+                    return None
                 raise ex
 
         if raw_payload is None:

tests/unit/test_persistent_cache.py

@@ -372,6 +372,20 @@ def test_keys_read_mode_corrupted_database(tmpdir):
     assert all(isinstance(key, str) for key in keys)
 
 
+def test_get_returns_none_on_corrupt_database_file(tmpdir):
+    """Test that get() returns None instead of raising when the database is corrupt."""
+    cache_file = os.path.join(tmpdir, "cache_corrupt")
+    cache = PersistentCache(cache_file)
+
+    cache.set("key1", "value1")
+    assert cache.get("key1") == "value1"
+
+    with open(cache_file, "wb") as f:
+        f.write(b"this is not a valid sqlite database file")
+
+    assert cache.get("key1") is None
+
+
 def test_multithread_shared_cache_comprehensive(tmpdir):
     """Test shared cache instance across multiple threads using get->set pattern.