Close FastParquet file even on error (pandas-dev#46556)

Author: flying-sheep

doc/source/whatsnew/v1.5.0.rst

@@ -561,7 +561,8 @@ I/O
 - Bug in :func:`read_parquet` when ``engine="pyarrow"`` which caused partial write to disk when column of unsupported datatype was passed (:issue:`44914`)
 - Bug in :func:`DataFrame.to_excel` and :class:`ExcelWriter` would raise when writing an empty DataFrame to a ``.ods`` file (:issue:`45793`)
 - Bug in Parquet roundtrip for Interval dtype with ``datetime64[ns]`` subtype (:issue:`45881`)
-- Bug in :func:`read_excel` when reading a ``.ods`` file with newlines between xml elements(:issue:`45598`)
+- Bug in :func:`read_excel` when reading a ``.ods`` file with newlines between xml elements (:issue:`45598`)
+- Bug in :func:`read_parquet` when ``engine="fastparquet"`` where the file was not closed on error (:issue:`46555`)
 
 Period
 ^^^^^^

pandas/io/parquet.py

@@ -349,13 +349,12 @@ def read(
             )
             path = handles.handle
 
-        parquet_file = self.api.ParquetFile(path, **parquet_kwargs)
-
-        result = parquet_file.to_pandas(columns=columns, **kwargs)
-
-        if handles is not None:
-            handles.close()
-        return result
+        try:
+            parquet_file = self.api.ParquetFile(path, **parquet_kwargs)
+            return parquet_file.to_pandas(columns=columns, **kwargs)
+        finally:
+            if handles is not None:
+                handles.close()
 
 
 @doc(storage_options=_shared_docs["storage_options"])

pandas/tests/io/test_parquet.py

@@ -1155,3 +1155,11 @@ def test_use_nullable_dtypes_not_supported(self, fp):
             df.to_parquet(path)
             with pytest.raises(ValueError, match="not supported for the fastparquet"):
                 read_parquet(path, engine="fastparquet", use_nullable_dtypes=True)
+
+    def test_close_file_handle_on_read_error(self):
+        with tm.ensure_clean("test.parquet") as path:
+            pathlib.Path(path).write_bytes(b"breakit")
+            with pytest.raises(Exception, match=""):  # Not important which exception
+                read_parquet(path, engine="fastparquet")
+            # The next line raises an error on Windows if the file is still open
+            pathlib.Path(path).unlink(missing_ok=False)